Method, device, electronic device and storage medium for generating risk prediction model

Abstract

An embodiment of the present invention provides a method, device, electronic device and storage medium for generating a risk prediction model, the method comprising: obtaining a device instruction for a network device input by a target user; if the device instruction is an abnormal instruction, obtaining a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to the abnormal type corresponding to the abnormal instruction, the first risk coefficient being the risk coefficient set when the network device leaves the factory, and the second risk coefficient being the risk coefficient set by the target user when using the network device; grouping data according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction, and generating an abnormal data group corresponding to the network device; calculating a relationship function between the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction according to the abnormal data group, and obtaining a risk prediction model for performing risk prediction on the device instructions of the network device.

Description

Technical Field

[0001] The present invention relates to the field of communication equipment processing technology, and in particular to a method for generating a risk prediction model for equipment instructions, a device for generating a risk prediction model for equipment instructions, an electronic device, and a computer-readable storage medium. Background Art

[0002] The operation of network equipment by operators affects the use of various industries. A slight mistake may cause a series of network failures. At present, the risk factor of equipment instructions is determined by manual labeling by operation and maintenance personnel, that is, the risk factor of instructions is defined based on their past operation records. However, the instructions used by operation and maintenance personnel on a daily basis are common instructions, and there are a large number of instructions that are not used, so the risk factor of these instructions cannot be determined. If you only consider network security and identify most instructions as high-risk, operation and maintenance personnel will need to review with the technical supervisor when performing operations, which may lead to a significant decrease in the overall work efficiency. Summary of the invention

[0003] An embodiment of the present invention provides a method, apparatus, electronic device and computer-readable storage medium for generating a risk prediction model for device instructions, so as to solve or partially solve the problem that risk prediction of device instructions for network devices has incomplete risk coefficient labeling and is prone to prediction errors.

[0004] An embodiment of the present invention discloses a method for generating a risk prediction model for device instructions, comprising:

[0005] Obtaining device instructions for network devices input by a target user;

[0006] If the device instruction is an abnormal instruction, a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device;

[0007] Grouping data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction, and generating an abnormal data group corresponding to the network device;

[0008] A relationship function is calculated between the first risk coefficient and the second risk coefficient corresponding to each of the abnormal instructions according to the abnormal data group to obtain a risk prediction model for predicting the risk of the device instructions of the network device.

[0009] Optionally, if the device instruction is an abnormal instruction, obtaining a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to an abnormal type corresponding to the abnormal instruction includes:

[0010] S1, determining whether the device instruction is an abnormal instruction, if the device instruction is an abnormal instruction, executing S2, if the device instruction is not an abnormal instruction, returning to the device instruction for the network device input by the target user;

[0011] S2, determining whether the input duration of the device instruction is greater than a preset value, treating the device instruction whose input duration is greater than the preset value as a timeout instruction, and obtaining a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction; if the input duration of the device instruction is less than or equal to the preset value, executing S3;

[0012] S3, determining whether the device instruction is incomplete, treating the incomplete device instruction as a defective instruction, and obtaining a first defect risk coefficient and a second defect risk coefficient corresponding to the defective instruction; if the device instruction is complete, executing S4;

[0013] S4, determine whether the device instruction is input incorrectly, treat the incorrectly input device instruction as an error instruction, and obtain a first error risk coefficient and a second error risk coefficient corresponding to the error instruction; if the device instruction is a correct instruction, return the device instruction for the network device input by the target user.

[0014] Optionally, grouping data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device includes:

[0015] According to the instruction type, the timeout instruction is combined with the first timeout risk coefficient and the second timeout risk coefficient, the defect instruction is combined with the first defect risk coefficient and the second defect risk coefficient, and the error instruction is combined with the first error risk coefficient and the second error risk coefficient to generate an abnormal data group corresponding to the network device.

[0016] Optionally, the abnormal data group includes a plurality of sub-data groups, and the relationship function calculation is performed on the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction according to the abnormal data group to obtain a risk prediction model for predicting the risk of the device instruction of the network device, including:

[0017] Acquire the number of arrays contained in each of the sub-data groups, wherein the arrays are composed of the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction;

[0018] If the number is greater than a preset number threshold, calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups;

[0019] The weight value corresponding to each of the sub-data groups is obtained, and each of the relationship functions is multiplied by the corresponding weight value to generate a risk prediction model for predicting the risk of the device instructions of the network device.

[0020] Optionally, the sub-data group includes a first sub-data group corresponding to the timeout instruction, a second sub-data group corresponding to the defect instruction, and a third sub-data group corresponding to the error instruction, and the calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups includes:

[0021] Calculating a first relationship function between a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction in the first sub-data group by using a least square method;

[0022] Calculating a second relationship function between a first defect risk coefficient and a second defect risk coefficient corresponding to the defect instruction in the second sub-data group by using the least squares method;

[0023] The least square method is used to calculate a third relationship function between the first error risk coefficient and the second error risk coefficient corresponding to the erroneous instruction in the third sub-data group.

[0024] Optionally, the weight values ​​include a first weight value corresponding to the first sub-data group, a second weight value corresponding to the second sub-data group, and a third weight value corresponding to the third sub-data group, and multiplying each of the relationship functions by the corresponding weight value to generate a risk prediction model for performing risk prediction on the device instruction of the network device includes:

[0025] The first relationship function is multiplied by the first weight value, the second relationship function is multiplied by the second weight value, and the third relationship function is multiplied by the third weight value to perform functional combination to generate a risk prediction model for predicting the risk of device instructions of the network device.

[0026] Optionally, it also includes:

[0027] Acquire a current device instruction for the network device input by the target user, and a first current risk coefficient and a second current risk coefficient corresponding to the current device instruction;

[0028] Inputting the first current risk coefficient into the risk prediction model for coefficient prediction, and obtaining a target risk coefficient corresponding to the first current risk coefficient, wherein the target risk coefficient is a predicted risk coefficient corresponding to the current device instruction input by the target user;

[0029] Calculating a deviation value between the second current risk coefficient and the target risk coefficient, and if the deviation value is greater than 0, obtaining a first adjustment value for the risk prediction model, and adjusting the risk prediction model to a first risk prediction model based on the first adjustment value;

[0030] If the deviation value is less than 0, the risk prediction model is adjusted to a second risk prediction model based on the first adjustment value.

[0031] The embodiment of the present invention also discloses a risk prediction model generation device for device instructions, comprising:

[0032] A device instruction acquisition module is used to acquire device instructions for network devices input by a target user;

[0033] a risk coefficient acquisition module, configured to, if the device instruction is an abnormal instruction, acquire a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to the abnormal type corresponding to the abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device;

[0034] A data grouping module, used for grouping data according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction, and generating an abnormal data group corresponding to the network device;

[0035] The model generation module is used to calculate the relationship function between the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction according to the abnormal data group, so as to obtain a risk prediction model for predicting the risk of the device instructions of the network device.

[0036] Optionally, the risk coefficient acquisition module is specifically used to:

[0037] S1, determining whether the device instruction is an abnormal instruction, if the device instruction is an abnormal instruction, executing S2, if the device instruction is not an abnormal instruction, returning to the device instruction for the network device input by the target user;

[0038] S2, determining whether the input duration of the device instruction is greater than a preset value, treating the device instruction whose input duration is greater than the preset value as a timeout instruction, and obtaining a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction; if the input duration of the device instruction is less than or equal to the preset value, executing S3;

[0039] S3, determining whether the device instruction is incomplete, treating the incomplete device instruction as a defective instruction, and obtaining a first defect risk coefficient and a second defect risk coefficient corresponding to the defective instruction; if the device instruction is complete, executing S4;

[0040] S4, determine whether the device instruction is input incorrectly, treat the incorrectly input device instruction as an error instruction, and obtain a first error risk coefficient and a second error risk coefficient corresponding to the error instruction; if the device instruction is a correct instruction, return the device instruction for the network device input by the target user.

[0041] Optionally, the data grouping module is specifically used for:

[0042] According to the instruction type, the timeout instruction is combined with the first timeout risk coefficient and the second timeout risk coefficient, the defect instruction is combined with the first defect risk coefficient and the second defect risk coefficient, and the error instruction is combined with the first error risk coefficient and the second error risk coefficient to generate an abnormal data group corresponding to the network device.

[0043] Optionally, the abnormal data group includes several sub-data groups, and the model generation module is specifically used to:

[0044] Acquire the number of arrays contained in each of the sub-data groups, wherein the arrays are composed of the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction;

[0045] If the number is greater than a preset number threshold, calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups;

[0046] The weight value corresponding to each of the sub-data groups is obtained, and each of the relationship functions is multiplied by the corresponding weight value to generate a risk prediction model for predicting the risk of the device instructions of the network device.

[0047] Optionally, the sub-data group includes a first sub-data group corresponding to the timeout instruction, a second sub-data group corresponding to the defect instruction, and a third sub-data group corresponding to the error instruction, and the model generation module is specifically used to:

[0048] Calculating a first relationship function between a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction in the first sub-data group by using a least square method;

[0049] Calculating a second relationship function between a first defect risk coefficient and a second defect risk coefficient corresponding to the defect instruction in the second sub-data group by using the least squares method;

[0050] The least square method is used to calculate a third relationship function between the first error risk coefficient and the second error risk coefficient corresponding to the erroneous instruction in the third sub-data group.

[0051] Optionally, the weight values ​​include a first weight value corresponding to the first sub-data group, a second weight value corresponding to the second sub-data group, and a third weight value corresponding to the third sub-data group, and the model generation module is specifically used to:

[0052] The first relationship function is multiplied by the first weight value, the second relationship function is multiplied by the second weight value, and the third relationship function is multiplied by the third weight value to perform functional combination to generate a risk prediction model for predicting the risk of device instructions of the network device.

[0053] Optionally, it also includes:

[0054] An information acquisition module, used to acquire a current device instruction for the network device input by the target user, and a first current risk coefficient and a second current risk coefficient corresponding to the current device instruction;

[0055] a risk coefficient obtaining module, configured to input the first current risk coefficient into the risk prediction model for coefficient prediction, and obtain a target risk coefficient corresponding to the first current risk coefficient, wherein the target risk coefficient is a predicted risk coefficient corresponding to the current device instruction input by the target user;

[0056] a deviation value calculation module, used to calculate a deviation value between the second current risk coefficient and the target risk coefficient;

[0057] A model adjustment module is used to obtain a first adjustment value for the risk prediction model if the deviation value is greater than 0, and adjust the risk prediction model to a first risk prediction model based on the first adjustment value; if the deviation value is less than 0, adjust the risk prediction model to a second risk prediction model based on the first adjustment value.

[0058] The embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0059] The memory is used to store computer programs;

[0060] The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0061] The embodiment of the present invention further discloses a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the method described in the embodiment of the present invention.

[0062] The embodiments of the present invention include the following advantages:

[0063] In an embodiment of the present invention, for the risk coefficient processing of the device instruction of the network device, the device instruction for the network device input by the target user can be obtained. If the device instruction is an abnormal instruction, the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction. The first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device. Then, data grouping can be performed according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device. Then, the relationship function calculation of the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction can be performed according to the abnormal data group to obtain a risk prediction model for risk prediction of the device instruction of the network device, thereby collecting the data generated by the operation and maintenance personnel when operating the network device, and combining the risk coefficient set by the manufacturer for the device instruction for model training, to obtain a risk prediction model that can be used to predict the risk coefficient of the device instruction. On the one hand, it effectively combines the actual operation of the operation and maintenance personnel, and on the other hand, through the full amount of data configured by the manufacturer, it can effectively ensure the comprehensiveness of the risk coefficient marking, so that the risk prediction model finally generated can accurately and comprehensively mark the risk coefficients of different device instructions, and ensure the efficiency of device operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a flowchart of a method for generating a risk prediction model for device instructions provided in an embodiment of the present invention;

[0065] Figure 2 is a schematic diagram of a flow chart of model generation provided in an embodiment of the present invention;

[0066] Figure 3 It is a structural block diagram of a risk prediction model generating device for device instructions provided in an embodiment of the present invention;

[0067] Figure 4It is a block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0069] As an example, the operation of network equipment of operators is related to the use of various industries. If you are not careful, it may cause a series of network failures. At present, the risk factor of equipment instructions is determined by manual labeling by operation and maintenance personnel, that is, the risk factor of instructions is defined based on their past operation records. However, the instructions used by operation and maintenance personnel on a daily basis are common instructions, and there are a large number of instructions that are not used, so the risk factor of these instructions cannot be determined. If you only consider network security and identify most instructions as high-risk, the operation and maintenance personnel will need to review with the technical supervisor when performing operations, which may greatly reduce the overall work efficiency.

[0070] In this regard, one of the core inventions of the present invention is to provide a method for dividing instruction risk coefficients based on deep learning, which captures the behavioral habits of operation and maintenance personnel inputting risk instructions to formulate risk curves for different personnel, thereby achieving the effect of balancing efficiency and safety. Specifically, for the risk coefficient processing of device instructions of network devices, the device instructions for network devices input by the target user can be obtained. If the device instruction is an abnormal instruction, the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction. The first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device. Then, data grouping can be performed according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction. An abnormal data group corresponding to the network device is generated, and then the relationship function of the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction can be calculated according to the abnormal data group to obtain a risk prediction model for risk prediction of the device instructions of the network device, thereby collecting the data generated by the operation and maintenance personnel operating the network device, and training the model in combination with the risk coefficient set by the manufacturer for the device instruction, to obtain a risk prediction model that can be used to predict the risk coefficient of the device instruction. On the one hand, it effectively combines the actual operation situation of the operation and maintenance personnel, and on the other hand, through the full amount of data configured by the manufacturer, it can effectively ensure the comprehensiveness of the risk coefficient marking, so that the risk prediction model finally generated can accurately and comprehensively mark the risk coefficients of different device instructions, thereby ensuring the efficiency of equipment operation.

[0071] Reference Figure 1, shows a flowchart of a method for generating a risk prediction model for device instructions provided in an embodiment of the present invention, which may specifically include the following steps:

[0072] Step 101, obtaining a device instruction for a network device input by a target user;

[0073] Optionally, the target user may be an operation and maintenance personnel who operates the network device. During the operation of the network device, the operation and maintenance personnel may input corresponding device instructions to control the network device to perform corresponding operations. The device instructions may be historical input instructions of the operation and maintenance personnel for operating the network device within a certain period of time. By collecting the operation behavior data of the operation and maintenance personnel on the network device within a certain period of time and using the operation behavior data as sample data for model training, a risk prediction model corresponding to the operation and maintenance personnel can be effectively obtained.

[0074] Step 102: if the device instruction is an abnormal instruction, a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device;

[0075] In a specific implementation, the device instructions may include normal instructions and abnormal instructions. The abnormal instructions often involve risky operations on network devices. For this, it is necessary to determine the risk coefficient corresponding to such abnormal instructions so as to make corresponding warnings based on the risk coefficient to ensure the stability and security of the operation of the network device. For each device instruction, when the network device leaves the factory, the manufacturer can set a corresponding first risk coefficient for each device instruction. During the use of the network device, due to the centralized use of the device instructions, the operation and maintenance personnel can set a corresponding second risk coefficient for some device instructions according to their own needs. The present invention does not limit this.

[0076] Specifically, the detection process of device instructions can be carried out through the following process:

[0077] S1, determine whether the device instruction is an abnormal instruction, if the device instruction is an abnormal instruction, execute S2, if the device instruction is not an abnormal instruction, return to obtain the device instruction for the network device input by the target user;

[0078] S2, determining whether the input duration of the device instruction is greater than a preset value, treating the device instruction whose input duration is greater than the preset value as a timeout instruction, and obtaining a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction; if the input duration of the device instruction is less than or equal to the preset value, executing S3;

[0079] S3, determining whether the device instruction is incomplete, treating the incomplete device instruction as a defective instruction, and obtaining a first defect risk coefficient and a second defect risk coefficient corresponding to the defective instruction; if the device instruction is complete, executing S4;

[0080] S4, determine whether the device instruction is input incorrectly, treat the incorrectly input device instruction as an incorrect instruction, and obtain the first error risk coefficient and the second error risk coefficient corresponding to the incorrect instruction; if the device instruction is a correct instruction, return to obtain the device instruction for the network device input by the target user.

[0081] Among them, the preset value can be a time threshold set for the device command. For example, if the time required for the operation and maintenance personnel to normally input a device command is 2 seconds, the time threshold can be set to 2 seconds. When the input time of the device command is greater than 2 seconds, the device command is determined to be a timed-out command. The device command needs to be entered completely to control the network device to perform the corresponding operation. When the input is complete, it is also necessary to ensure that the input device command matches the corresponding operation. Otherwise, the device command can be determined as a defective command (the command input is incomplete) or an erroneous command (the device command is inconsistent with the operation of the network device) according to the corresponding situation.

[0082] In addition, the first timeout risk coefficient, the first defect risk coefficient, and the first error risk coefficient, etc., can be the initial risk coefficients set by the manufacturer for the corresponding equipment instructions, while the second timeout risk coefficient, the second defect risk coefficient, and the second error risk coefficient, etc. can be personalized risk coefficients set by the operation and maintenance personnel for the corresponding equipment instructions.

[0083] Step 103, grouping data according to the abnormal type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device;

[0084] In a specific implementation, a timeout instruction can be combined with a first timeout risk coefficient and a second timeout risk coefficient, a defect instruction can be combined with a first defect risk coefficient and a second defect risk coefficient, and an error instruction can be combined with a first error risk coefficient and a second error risk coefficient according to the instruction type to generate an abnormal data group corresponding to the network device.

[0085] In one example, a risk factor database for operation and maintenance personnel can be established to store the behavior habits (behavior information) of operation and maintenance personnel in using instructions during daily operation and maintenance (including daytime and nighttime). The behavior habits include: a : The operation and maintenance personnel input command time exceeds the preset value W; P b : The operation and maintenance personnel input a command and generate an alarm for incomplete command; P c:Operation and maintenance personnel input command error alarm. For the device command input by the operation and maintenance personnel, when the operation and maintenance personnel have P a / b / c When operating, record the risk factor of the instruction at this time, including: the risk factor defined by the manufacturer is T 0 And the risk factor of the operation and maintenance personnel marking is T N , and classify and record them in a stack format, that is, { NN , T 0N ,},X=P a / b / c Next, first determine whether the input time length exceeds the preset value W. If it exceeds, record T 0ai , T Nai If it does not exceed, it is determined whether the operation and maintenance personnel input the command to generate an incomplete command alarm. If it exceeds, it is recorded T 0bi , T Nbi If it does not exceed, it is determined whether the operation and maintenance personnel input the command to generate a command error alarm. If it exceeds, record T 0ci , T Nci If it does not exceed, the process of obtaining the device instructions entered by the operation and maintenance personnel. In addition, the risk factor T defined by the manufacturer and marked by the operation and maintenance personnel can be 0 and T N Import the database with X, and each time an operation record occurs, record the corresponding T 0 and T N , the counter reads N plus 1; determine whether the counter reading is greater than S, S is the upper limit of the record stack, if the counter count is greater than S, then the next step of model training can be entered.

[0086] Step 104, calculating a relationship function between the first risk coefficient and the second risk coefficient corresponding to each of the abnormal instructions according to the abnormal data group, and obtaining a risk prediction model for predicting the risk of the device instructions of the network device.

[0087] In an embodiment of the present invention, the generated abnormal data group may include several sub-data groups, and the number of arrays contained in each sub-data group can be obtained, where the array is composed of a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction; if the number is greater than a preset number threshold, the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group is calculated according to the least squares method to obtain the relationship function corresponding to each sub-data group; the weight value corresponding to each sub-data group is obtained, and each relationship function is multiplied by the corresponding weight value to generate a risk prediction model for risk prediction of device instructions of network devices.

[0088] Among them, the sub-data groups include a first sub-data group corresponding to the timeout instruction, a second sub-data group corresponding to the defect instruction, and a third sub-data group corresponding to the error instruction. The weight values ​​include a first weight value corresponding to the first sub-data group, a second weight value corresponding to the second sub-data group, and a third weight value corresponding to the third sub-data group. Then, the least squares method can be used to calculate the first relationship function between the first timeout risk coefficient and the second timeout risk coefficient corresponding to the timeout instruction in the first sub-data group, the least squares method can be used to calculate the second relationship function between the first defect risk coefficient and the second defect risk coefficient corresponding to the defect instruction in the second sub-data group, and the least squares method can be used to calculate the third relationship function between the first error risk coefficient and the second error risk coefficient corresponding to the error instruction in the third sub-data group. Then, the first relationship function is multiplied by the first weight value, the second relationship function is multiplied by the second weight value, and the third relationship function is multiplied by the third weight value to perform function combination to generate a risk prediction model for risk prediction of device instructions of network devices.

[0089] The risk prediction model can be applied to network equipment. When the network equipment detects that the operation and maintenance personnel have input the corresponding equipment instructions, the equipment instructions and the corresponding risk coefficient can be input into the risk prediction model, and the target risk coefficient corresponding to the equipment instructions can be output. In this way, the target risk coefficient can be used to determine whether the equipment instructions input by the operation and maintenance personnel will cause operational risks to the network equipment, thereby ensuring the stability and security of the operation of the network equipment.

[0090] It should be noted that different device instructions may correspond to different risks, so different weight values ​​can be set for different device instructions so that the trained risk prediction model can accurately predict the risks of different device instructions and output the risk coefficient corresponding to the device instructions.

[0091] In one example, the generation process of the risk prediction model (or risk coefficient function) can be as follows: the data in the database is classified according to X, and three groups of sub-databases {X} and the number of groups Q in each group of sub-databases can be obtained. i ; Then determine whether the number of sub-databases in each group has reached the function requirement Q i > B, B is the minimum number of groups of sub-databases that are preset to form a function. If it does not meet the requirement greater than B, then Q i Set to 0, and then for each group of sub-databases that meet the requirements, use the least squares method to obtain T 0N , T NN relationship function, and multiply by the weight of each group Get the final risk coefficient function Where H is the deviation.

[0092] In addition, as the operation and maintenance personnel use the network equipment, the risk prediction model can be updated according to the operation and maintenance personnel's usage behavior. Specifically, the current device instructions for the network device input by the target user, as well as the first current risk coefficient and the second current risk coefficient corresponding to the current device instructions are obtained. Then the first current risk coefficient can be input into the risk prediction model for coefficient prediction to obtain the target risk coefficient corresponding to the first current risk coefficient. The target risk coefficient is the predicted risk coefficient corresponding to the current device instruction input by the target user. Then, the deviation value between the second current risk coefficient and the target risk coefficient is calculated. If the deviation value is greater than 0, the first adjustment value for the risk prediction model is obtained, and the risk prediction model is adjusted to the first risk prediction model based on the first adjustment value; if the deviation value is less than 0, the risk prediction model is adjusted to the second risk prediction model based on the first adjustment value. Therefore, by updating the risk prediction model, the prediction effect of the risk prediction model is more consistent with the actual operation of the operation and maintenance personnel, effectively ensuring the comprehensiveness of the risk coefficient marking, so that the risk prediction model finally generated can accurately and comprehensively mark the risk coefficients of different device instructions to ensure the efficiency of equipment operation.

[0093] In one example, for the process of generating the risk coefficient, the risk coefficient of the initial instruction given by the manufacturer can be used to generate the risk coefficient of each operation and maintenance personnel according to the risk curve function and their respective behavior habits. After the risk coefficient is generated, the step of updating the risk coefficient database of the operation and maintenance personnel can be added. By capturing the operation and maintenance personnel P according to normal circumstances, a , P b , P c The operation is performed to record the risk coefficient at this time (defined by the operation and maintenance personnel and provided by the manufacturer), and then the risk coefficient and X are imported into the database to determine the difference ΔT between the current risk coefficient and the corresponding risk coefficient under the existing function. If ΔT>0, then the deviation H=H+h, if ΔT<0, then the deviation H=Hh. Among them, h can be an adjustment value set for the risk prediction model, which can be a fixed adjustment value, and the present invention does not limit this.

[0094] It should be noted that the embodiments of the present invention include but are not limited to the above examples. It is understandable that those skilled in the art can also make settings according to actual needs under the guidance of the ideas of the embodiments of the present invention, and the present invention is not limited to this.

[0095] In an embodiment of the present invention, the risk coefficient processing of the device instruction of the network device can be carried out by obtaining the device instruction for the network device input by the target user. If the device instruction is an abnormal instruction, the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction. The first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device. Then, data can be grouped according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device. Then, the first risk coefficient corresponding to each abnormal instruction can be grouped according to the abnormal data group. The relationship function of the risk coefficient and the second risk coefficient is calculated to obtain a risk prediction model for risk prediction of device instructions of network devices, thereby collecting the data generated by the operation and maintenance personnel when operating the network equipment, and combining the risk coefficient set by the manufacturer for the device instructions for model training, to obtain a risk prediction model that can be used to predict the risk coefficient of the device instructions. On the one hand, it effectively combines the actual operation of the operation and maintenance personnel, and on the other hand, through the full amount of data configured by the manufacturer, it can effectively ensure the comprehensiveness of the risk coefficient marking, so that the risk prediction model finally generated can accurately and comprehensively mark the risk coefficients of different device instructions, ensuring that the equipment operation 100002

[0096] Efficiency of 2010.2.

[0097] In order to enable those skilled in the art to better understand the technical solution in the embodiments of the present invention, an example is given below for illustrative explanation:

[0098] Reference Figure 2 , shows a schematic diagram of a flow chart of model generation provided in an embodiment of the present invention, including:

[0099] S010: Obtain the risk factor of the network equipment given by the manufacturer, and at the same time obtain the risk factor defined by the operation and maintenance personnel based on their own operation records. The manufacturer obtains the full data, and the operation and maintenance personnel obtain partial data, because the operation and maintenance personnel usually have relatively concentrated operation instructions.

[0100] S020: Establish a risk factor database for operation and maintenance personnel to store the behavior habits of operation and maintenance personnel in using instructions during daily operation and maintenance (including daytime and nighttime). The behavior habits include: a : The operation and maintenance personnel input command time exceeds the preset value W; P b : The operation and maintenance personnel input a command and generate an alarm for incomplete command; P c : The operation and maintenance personnel input a command and generated a command error alarm.

[0101] S030: When the user appears P a / b / c When operating, record the risk factor of the instruction at this time. The risk factor defined by the manufacturer is T 0 , the risk factor of the operation and maintenance personnel marking is T N , and classify and record them in a stack format, that is, { NN , T 0N ,},X=P a / b / c .

[0102] S030a: First determine whether the input time length exceeds the preset value W. If so, record T 0ai , T Nai , if not, proceed to S020b;

[0103] S030b: Determine whether the operation and maintenance personnel input command generates an incomplete command alarm. If so, record T 0bi , T Nbi , if not, proceed to S020c;

[0104] S030c: Determine whether the operation and maintenance personnel input command generates a command error alarm. If it exceeds, record T 0ci , T Nci , if not, return to S030;

[0105] S040: Risk factor T for vendor definitions and operation and maintenance personnel 0 and T N Import the database with X, and each time an operation record occurs, record the corresponding T 0 and T N , the counter reads N plus 1; determine whether the counter reading is greater than S, S is the upper limit of the record stack, if so, enter the process of generating the risk coefficient curve, if not, return to S030.

[0106] S050: Generate risk coefficient function process. It includes the following steps:

[0107] S050a: Classify the data in the database according to X, and obtain 3 groups of sub-databases {X} and the number of groups Q in each group of sub-databases i

[0108] S050b: Determine whether the number of sub-databases in each group has reached the function requirement Q i > B, B is the minimum number of groups of sub-databases that are preset to form a function. If it does not meet the requirement greater than B, then Q i Set to 0 and enter S050c.

[0109] S050c: For each group of sub-databases that meet the requirements, use the least squares method to obtain T 0N , T NN relationship function, and multiply by the weight of each group Get the final risk coefficient function Where H is the deviation.

[0110] S060: Enter the stage of automatically generating risk coefficients. According to the initial instruction risk coefficients given by the manufacturer, the risk curve functions of different operation and maintenance personnel and their respective behavioral habits, generate their respective risk coefficients.

[0111] S070: After the step of generating risk coefficients, add the step of updating the risk coefficient database of operation and maintenance personnel. The updating steps are as follows:

[0112] S070a: Capture the operation and maintenance personnel P according to normal circumstances a , P b , P c Operations, record the risk factor at that time (defined by the operation and maintenance personnel and provided by the manufacturer);

[0113] S070b: Import the risk coefficient and X into the database, and determine the difference ΔT between the current risk coefficient and the corresponding risk coefficient under the existing function. If ΔT>0, then the deviation H=H+h; if ΔT<0, then the deviation H=Hh;

[0114] S070c: Enter the process of generating risk coefficient function.

[0115] The value of S is a positive integer, which can be customized by the operation and maintenance personnel and can be any value between 25 and 100. In addition, H is the deviation, and its initial value can be 1.

[0116] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0117] Reference Figure 3 , shows a structural block diagram of a risk prediction model generation device for device instructions provided in an embodiment of the present invention, which may specifically include the following modules:

[0118] The device instruction acquisition module 301 is used to acquire the device instruction for the network device input by the target user;

[0119] The risk coefficient acquisition module 302 is used to acquire a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to the abnormal type corresponding to the abnormal instruction if the device instruction is an abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device;

[0120] A data grouping module 303, configured to group data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction, and generate an abnormal data group corresponding to the network device;

[0121] The model generation module 304 is used to calculate the relationship function between the first risk coefficient and the second risk coefficient corresponding to each of the abnormal instructions according to the abnormal data group, so as to obtain a risk prediction model for predicting the risk of the device instructions of the network device.

[0122] In an optional embodiment, the risk coefficient acquisition module 302 is specifically used to:

[0123] S1, determining whether the device instruction is an abnormal instruction, if the device instruction is an abnormal instruction, executing S2, if the device instruction is not an abnormal instruction, returning to the device instruction for the network device input by the target user;

[0124] S2, determining whether the input duration of the device instruction is greater than a preset value, treating the device instruction whose input duration is greater than the preset value as a timeout instruction, and obtaining a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction; if the input duration of the device instruction is less than or equal to the preset value, executing S3;

[0125] S3, determining whether the device instruction is incomplete, treating the incomplete device instruction as a defective instruction, and obtaining a first defect risk coefficient and a second defect risk coefficient corresponding to the defective instruction; if the device instruction is complete, executing S4;

[0126] S4, determine whether the device instruction is input incorrectly, treat the incorrectly input device instruction as an error instruction, and obtain a first error risk coefficient and a second error risk coefficient corresponding to the error instruction; if the device instruction is a correct instruction, return the device instruction for the network device input by the target user.

[0127] In an optional embodiment, the data grouping module 303 is specifically used to:

[0128] According to the instruction type, the timeout instruction is combined with the first timeout risk coefficient and the second timeout risk coefficient, the defect instruction is combined with the first defect risk coefficient and the second defect risk coefficient, and the error instruction is combined with the first error risk coefficient and the second error risk coefficient to generate an abnormal data group corresponding to the network device.

[0129] In an optional embodiment, the abnormal data group includes several sub-data groups, and the model generation module 304 is specifically used to:

[0130] Acquire the number of arrays contained in each of the sub-data groups, wherein the arrays are composed of the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction;

[0131] If the number is greater than a preset number threshold, calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups;

[0132] The weight value corresponding to each of the sub-data groups is obtained, and each of the relationship functions is multiplied by the corresponding weight value to generate a risk prediction model for predicting the risk of the device instructions of the network device.

[0133] In an optional embodiment, the sub-data group includes a first sub-data group corresponding to the timeout instruction, a second sub-data group corresponding to the defect instruction, and a third sub-data group corresponding to the error instruction, and the model generation module 304 is specifically used to:

[0134] Calculating a first relationship function between a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction in the first sub-data group by using a least square method;

[0135] Calculating a second relationship function between a first defect risk coefficient and a second defect risk coefficient corresponding to the defect instruction in the second sub-data group by using the least squares method;

[0136] The least square method is used to calculate a third relationship function between the first error risk coefficient and the second error risk coefficient corresponding to the erroneous instruction in the third sub-data group.

[0137] In an optional embodiment, the weight values ​​include a first weight value corresponding to the first sub-data group, a second weight value corresponding to the second sub-data group, and a third weight value corresponding to the third sub-data group, and the model generation module 304 is specifically used to:

[0138] The first relationship function is multiplied by the first weight value, the second relationship function is multiplied by the second weight value, and the third relationship function is multiplied by the third weight value to perform functional combination to generate a risk prediction model for predicting the risk of device instructions of the network device.

[0139] In an optional embodiment, it also includes:

[0140] An information acquisition module, used to acquire a current device instruction for the network device input by the target user, and a first current risk coefficient and a second current risk coefficient corresponding to the current device instruction;

[0141] a risk coefficient obtaining module, configured to input the first current risk coefficient into the risk prediction model for coefficient prediction, and obtain a target risk coefficient corresponding to the first current risk coefficient, wherein the target risk coefficient is a predicted risk coefficient corresponding to the current device instruction input by the target user;

[0142] a deviation value calculation module, used to calculate a deviation value between the second current risk coefficient and the target risk coefficient;

[0143] A model adjustment module is used to obtain a first adjustment value for the risk prediction model if the deviation value is greater than 0, and adjust the risk prediction model to a first risk prediction model based on the first adjustment value; if the deviation value is less than 0, adjust the risk prediction model to a second risk prediction model based on the first adjustment value.

[0144] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0145] In addition, an embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned risk prediction model generation method embodiment for device instructions are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0146] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned risk prediction model generation method embodiment for device instructions is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0147] Figure 4 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0148] The electronic device 400 includes but is not limited to: a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, a processor 410, and a power supply 411. Those skilled in the art will appreciate that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. In the embodiments of the present invention, the electronic device includes but is not limited to a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted terminal, a wearable device, and a pedometer.

[0149] It should be understood that in the embodiment of the present invention, the radio frequency unit 401 can be used for receiving and sending signals during information transmission or communication. Specifically, after receiving downlink data from the base station, it is sent to the processor 410 for processing; in addition, uplink data is sent to the base station. Generally, the radio frequency unit 401 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 401 can also communicate with the network and other devices through a wireless communication system.

[0150] The electronic device provides users with wireless broadband Internet access through the network module 402, such as helping users to send and receive emails, browse web pages, and access streaming media.

[0151] The audio output unit 403 can convert the audio data received by the RF unit 401 or the network module 402 or stored in the memory 409 into an audio signal and output it as sound. Moreover, the audio output unit 403 can also provide audio output related to a specific function performed by the electronic device 400 (for example, a call signal reception sound, a message reception sound, etc.). The audio output unit 403 includes a speaker, a buzzer, a receiver, etc.

[0152] The input unit 404 is used to receive audio or video signals. The input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 406. The image frame processed by the graphics processor 4041 can be stored in the memory 409 (or other storage medium) or sent via the radio frequency unit 401 or the network module 402. The microphone 4042 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 401 in the case of a telephone call mode.

[0153] The electronic device 400 also includes at least one sensor 405, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 4061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 4061 and / or the backlight when the electronic device 400 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used to identify the posture of the electronic device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; the sensor 405 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be repeated here.

[0154] The display unit 406 is used to display information input by the user or information provided to the user. The display unit 406 may include a display panel 4061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0155] The user input unit 407 can be used to receive input digital or character information, and to generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 4071 or near the touch panel 4071 using any suitable object or accessory such as a finger, stylus, etc.). The touch panel 4071 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the contact point coordinates, and then sends it to the processor 410, receives the command sent by the processor 410 and executes it. In addition, the touch panel 4071 can be implemented using various types such as resistive, capacitive, infrared and surface acoustic waves. In addition to the touch panel 4071, the user input unit 407 may also include other input devices 4072. Specifically, other input devices 4072 may include but are not limited to a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail here.

[0156] Further, the touch panel 4071 may be covered on the display panel 4061. When the touch panel 4071 detects a touch operation on or near it, it is transmitted to the processor 410 to determine the type of the touch event, and then the processor 410 provides a corresponding visual output on the display panel 4061 according to the type of the touch event. It can be understood that in one embodiment, the touch panel 4071 and the display panel 4061 are used as two independent components to implement the input and output functions of the electronic device, but in some embodiments, the touch panel 4071 and the display panel 4061 can be integrated to implement the input and output functions of the electronic device, which is not limited here.

[0157] The interface unit 408 is an interface for connecting an external device to the electronic device 400. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 408 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the electronic device 400 or may be used to transmit data between the electronic device 400 and an external device.

[0158] The memory 409 can be used to store software programs and various data. The memory 409 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 409 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0159] The processor 410 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 409, and calling data stored in the memory 409, so as to monitor the electronic device as a whole. The processor 410 may include one or more processing units; preferably, the processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.

[0160] The electronic device 400 may also include a power supply 411 (such as a battery) for supplying power to each component. Preferably, the power supply 411 may be logically connected to the processor 410 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system.

[0161] In addition, the electronic device 400 includes some functional modules not shown, which will not be described in detail here.

[0162] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0163] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0164] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

[0165] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0166] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0170] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0171] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating a risk prediction model for device instructions, characterized in that: include: Obtaining device instructions for network devices input by a target user; If the device instruction is an abnormal instruction, a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction are obtained according to the abnormal type corresponding to the abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device; Grouping data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction, and generating an abnormal data group corresponding to the network device; The step of grouping data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device includes: Combining a timeout instruction with a first timeout risk coefficient and a second timeout risk coefficient, combining a defect instruction with a first defect risk coefficient and a second defect risk coefficient, and combining an error instruction with a first error risk coefficient and a second error risk coefficient according to the instruction type, to generate an abnormal data group corresponding to the network device; A relationship function is calculated between the first risk coefficient and the second risk coefficient corresponding to each of the abnormal instructions according to the abnormal data group to obtain a risk prediction model for predicting the risk of the device instructions of the network device.

2. The method according to claim 1, characterized in that: If the device instruction is an abnormal instruction, obtaining a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to the abnormal type corresponding to the abnormal instruction includes: S1, determining whether the device instruction is an abnormal instruction, if the device instruction is an abnormal instruction, executing S2, if the device instruction is not an abnormal instruction, returning to the device instruction for the network device input by the target user; S2, determining whether the input duration of the device instruction is greater than a preset value, treating the device instruction whose input duration is greater than the preset value as a timeout instruction, and obtaining a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction; if the input duration of the device instruction is less than or equal to the preset value, executing S3; S3, determining whether the device instruction is incomplete, treating the incomplete device instruction as a defective instruction, and obtaining a first defect risk coefficient and a second defect risk coefficient corresponding to the defective instruction; if the device instruction is complete, executing S4; S4, determine whether the device instruction is input incorrectly, treat the incorrectly input device instruction as an error instruction, and obtain a first error risk coefficient and a second error risk coefficient corresponding to the error instruction; if the device instruction is a correct instruction, return the device instruction for the network device input by the target user.

3. The method according to claim 1, characterized in that The abnormal data group includes a plurality of sub-data groups, and the relationship function calculation is performed on the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction according to the abnormal data group to obtain a risk prediction model for predicting the risk of the device instruction of the network device, including: Acquire the number of arrays contained in each of the sub-data groups, wherein the arrays are composed of the first risk coefficient and the second risk coefficient corresponding to the abnormal instruction; If the number is greater than a preset number threshold, calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data group according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups; The weight value corresponding to each of the sub-data groups is obtained, and each of the relationship functions is multiplied by the corresponding weight value to generate a risk prediction model for predicting the risk of the device instructions of the network device.

4. The method according to claim 3, characterized in that The sub-data groups include a first sub-data group corresponding to the timeout instruction, a second sub-data group corresponding to the defect instruction, and a third sub-data group corresponding to the error instruction, and the calculating the relationship function between the first risk coefficient and the second risk coefficient of the array in the sub-data groups according to the least squares method to obtain the relationship function corresponding to each of the sub-data groups includes: Calculating a first relationship function between a first timeout risk coefficient and a second timeout risk coefficient corresponding to the timeout instruction in the first sub-data group by using a least square method; Calculating a second relationship function between a first defect risk coefficient and a second defect risk coefficient corresponding to the defect instruction in the second sub-data group by using the least squares method; The least square method is used to calculate a third relationship function between the first error risk coefficient and the second error risk coefficient corresponding to the erroneous instruction in the third sub-data group.

5. The method according to claim 4, characterized in that The weight values ​​include a first weight value corresponding to the first sub-data group, a second weight value corresponding to the second sub-data group, and a third weight value corresponding to the third sub-data group, and multiplying each of the relationship functions by the corresponding weight value to generate a risk prediction model for predicting the risk of the device instruction of the network device, including: The first relationship function is multiplied by the first weight value, the second relationship function is multiplied by the second weight value, and the third relationship function is multiplied by the third weight value to perform functional combination to generate a risk prediction model for predicting the risk of device instructions of the network device.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Acquire a current device instruction for the network device input by the target user, and a first current risk coefficient and a second current risk coefficient corresponding to the current device instruction; Inputting the first current risk coefficient into the risk prediction model for coefficient prediction, and obtaining a target risk coefficient corresponding to the first current risk coefficient, wherein the target risk coefficient is a predicted risk coefficient corresponding to the current device instruction input by the target user; Calculating a deviation value between the second current risk coefficient and the target risk coefficient, and if the deviation value is greater than 0, obtaining a first adjustment value for the risk prediction model, and adjusting the risk prediction model to a first risk prediction model based on the first adjustment value; If the deviation value is less than 0, the risk prediction model is adjusted to a second risk prediction model based on the first adjustment value.

7. A risk prediction model generation device for equipment instructions, characterized in that: include: A device instruction acquisition module is used to acquire device instructions for network devices input by a target user; a risk coefficient acquisition module, configured to, if the device instruction is an abnormal instruction, acquire a first risk coefficient and a second risk coefficient corresponding to the abnormal instruction according to the abnormal type corresponding to the abnormal instruction, wherein the first risk coefficient is the risk coefficient set when the network device leaves the factory, and the second risk coefficient is the risk coefficient set by the target user when using the network device; A data grouping module, used for grouping data according to the abnormal type, the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction, and generating an abnormal data group corresponding to the network device; The step of grouping data according to the abnormality type, the first risk coefficient, and the second risk coefficient corresponding to each abnormal instruction to generate an abnormal data group corresponding to the network device includes: Combining a timeout instruction with a first timeout risk coefficient and a second timeout risk coefficient, combining a defect instruction with a first defect risk coefficient and a second defect risk coefficient, and combining an error instruction with a first error risk coefficient and a second error risk coefficient according to the instruction type, to generate an abnormal data group corresponding to the network device; The model generation module is used to calculate the relationship function between the first risk coefficient and the second risk coefficient corresponding to each abnormal instruction according to the abnormal data group, so as to obtain a risk prediction model for predicting the risk of the device instructions of the network device.

8. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 6 when executing the program stored in the memory.

9. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 6.

Images