CN113918398A

CN113918398A - Information suppression method and device, computer equipment and readable storage medium

Info

Publication number: CN113918398A
Application number: CN202111415063.XA
Authority: CN
Inventors: 袁婷婷; 朱苏纬; 付昕; 鞠文煜; 姚斌; 王园园
Original assignee: Commercial Aircraft Corp of China Ltd
Current assignee: Commercial Aircraft Corp of China Ltd
Priority date: 2021-11-25
Filing date: 2021-11-25
Publication date: 2022-01-11

Abstract

The embodiment of the application discloses an information suppression method, an information suppression device, computer equipment and a readable storage medium. In the embodiment of the application, fault information is obtained; performing logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and performing algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information; acquiring a first target weight of a first parameter corresponding to the logic judgment, and acquiring a second target weight of a second parameter corresponding to the algorithm judgment; determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight, and the second target weight; and if the target false alarm judgment result indicates that the fault information is a false alarm, inhibiting the fault information. According to the embodiment of the application, the storage resources can be saved, and the labor cost and the time cost of airplane maintenance are reduced.

Description

Information suppression method and device, computer equipment and readable storage medium

Technical Field

The present invention relates to the field of aircraft, and in particular, to an information suppression method, apparatus, computer device, and readable storage medium.

Background

With the development of aviation technology, the complexity of airplanes is higher, and the requirements for Built-In testing (BIT) of airplanes are higher and higher.

The power-up test is one of the built-in tests. In the process of power-on test, a false alarm phenomenon is generated, wherein the false alarm phenomenon refers to a phenomenon that the tested device does not actually have a fault, but generates fault information (namely the tested device is indicated to have a fault). When a false alarm phenomenon occurs, storage resources are wasted, and the labor cost and the time cost of aircraft maintenance are increased.

Disclosure of Invention

Embodiments of the present application provide an information suppression method, apparatus, computer device, and readable storage medium, which can save storage resources and reduce labor cost and time cost for aircraft maintenance.

In order to solve the above technical problem, an embodiment of the present application discloses the following technical solutions:

in one aspect, an information suppression method is provided, including:

acquiring fault information;

performing logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and performing algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information;

acquiring a first target weight of a first parameter corresponding to the logic judgment, and acquiring a second target weight of a second parameter corresponding to the algorithm judgment;

determining a target false alarm determination result of the fault information based on the first initial false alarm determination result, the second initial false alarm determination result, the first target weight, and the second target weight;

and if the target false alarm judgment result indicates that the fault information is a false alarm, suppressing the fault information.

Optionally, the performing the logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information includes:

acquiring the power-on time of a fault reporting system corresponding to the fault information;

and if the power-on time is less than or equal to a preset threshold value, determining the first initial false alarm judgment result as that the fault information is a false alarm.

Optionally, after obtaining the power-on time of the fault reporting system corresponding to the fault information, the method further includes:

if the power-on time is larger than the preset threshold value, extracting a character string of the fault information to obtain a fault character string;

and determining a first initial false alarm judgment result of the fault information based on the fault character string.

Optionally, the determining a first initial false alarm determination result of the fault information based on the fault string includes:

determining the state of a state matrix bit in the fault character string;

and if the state of the state matrix bit is an abnormal state, determining the first initial false alarm determination result as whether the fault information is a false alarm.

Optionally, after determining the state of the state matrix bit in the fault string, the method further includes:

if the state of the state matrix bit is a normal state, extracting the characteristics of the fault character string to obtain a fault type corresponding to the fault information;

and if the fault type corresponding to the fault information is an internal fault, determining the first initial false alarm judgment result as that the fault information is not a false alarm.

Optionally, the determining the fault type corresponding to the fault information according to the fault characteristic value includes:

if the fault type corresponding to the fault information is an external fault, searching a correlation system corresponding to the fault information;

determining an electrical state of the associated system;

if the electrical state of the associated system is a power-on state, determining that the fault information is not a false alarm according to the first initial false alarm determination result;

if the electrical state of the associated system is a power-off state, the first initial false alarm determination result is determined that the fault information is a false alarm.

Optionally, the performing an algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information includes:

and inputting the fault information into a trained neural network model for judgment to obtain a second initial false alarm judgment result of the fault information.

Optionally, the inputting the fault information into a trained neural network model for judgment to obtain a second initial false alarm determination result of the fault information includes:

acquiring external environment parameters corresponding to the fault information;

and inputting the fault information and the external environment parameters into a trained neural network model for judgment to obtain a second initial false alarm judgment result of the fault information.

carrying out logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information;

if the first initial false alarm determination result of the fault information is that the fault information is a false alarm, adopting a first initial value to represent the first initial false alarm determination result;

if the first initial false alarm judgment result of the fault information is that the fault information is not a false alarm, adopting a second initial value to represent the first initial false alarm judgment result;

correspondingly, the performing the algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information includes:

performing algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information;

if a second initial false alarm determination result of the fault information is that the fault information is a false alarm, representing the second initial false alarm determination result by using the first initial value;

and if the second initial false alarm determination result of the fault information indicates that the fault information is not a false alarm, indicating the second initial false alarm determination result by using the second initial value.

Optionally, the determining a target false alarm determination result of the fault information based on the first initial false alarm determination result, a second initial false alarm determination result, the first target weight, and the second target weight includes:

multiplying the first initial false alarm determination result by the first target weight to obtain a first target value;

multiplying the second initial false alarm determination result by the second target weight to obtain a second target value;

adding the first target value and the second target value to obtain an addition result;

and determining a target false alarm determination result of the fault information based on the addition result.

Optionally, the determining a target false alarm determination result of the fault information based on the addition result includes:

if the addition result is greater than a preset value, determining the target false alarm determination result of the fault information as that the fault information is not a false alarm;

and if the addition result is less than or equal to a preset value, determining the target false alarm judgment result of the fault information as that the fault information is a false alarm.

Optionally, the obtaining a first target weight of the first parameter corresponding to the logic judgment and obtaining a second target weight of the second parameter corresponding to the algorithm judgment includes:

initializing a first parameter corresponding to the logic judgment and a second parameter corresponding to the algorithm judgment to obtain a first initial weight of the first parameter and a second initial weight of the second parameter;

acquiring a first history judgment result obtained by logically judging the history fault information and acquiring a second history judgment result obtained by algorithmically judging the history fault information;

determining a final discrimination result of the historical fault information according to the first historical discrimination result, the second historical discrimination result, the first initial weight and the second initial weight;

if the final judgment result does not meet the preset condition, updating the first initial weight and the second initial weight, and returning to execute a first historical judgment result obtained by performing logic judgment on historical fault information and a second historical judgment result obtained by performing algorithm judgment on the historical fault information;

and if the final judgment result meets the preset condition, taking the first initial weight as a first target weight and taking the second initial weight as a second target weight.

Optionally, after the obtaining of the fault information, the method further includes:

storing the fault information as training fault information into a database;

and optimizing the trained neural network model based on the training fault information in the database to obtain the optimized neural network model.

Optionally, after the training fault information in the database is used to optimize the trained neural network model to obtain an optimized neural network model, the method further includes:

modifying the first target weight and the second target weight to obtain a modified first target weight and a modified second target weight;

accordingly, the determining a target false alarm determination result of the fault information based on the first initial false alarm determination result, the second initial false alarm determination result, the first target weight, and the second target weight includes:

determining a target false alarm decision result for the fault information based on the first initial false alarm decision result, the second initial false alarm decision result, the modified first target weight, and the modified second target weight.

In another aspect, an information suppression apparatus is provided, including:

the information acquisition module is used for acquiring fault information;

the judging module is used for carrying out logic judgment on the fault information to obtain a first initial false alarm judging result of the fault information and carrying out algorithm judgment on the fault information to obtain a second initial false alarm judging result of the fault information;

the weight obtaining module is used for obtaining a first target weight of the first parameter corresponding to the logic judgment and obtaining a second target weight of the second parameter corresponding to the algorithm judgment;

a determining module, configured to determine a target false alarm determination result of the fault information based on the first initial false alarm determination result, the second initial false alarm determination result, the first target weight, and the second target weight;

and the suppression module is used for suppressing the fault information if the target false alarm judgment result indicates that the fault information is a false alarm.

In another aspect, a computer device is provided, which includes a processor and a memory, where the memory stores a computer program, and the processor is configured to execute the computer program in the memory to implement the information suppression method provided by the embodiment of the present invention.

In another aspect, a computer-readable storage medium is provided, where a computer program is stored, where the computer program is suitable for being loaded by a processor to execute the steps in any one of the information suppression methods provided by the embodiments of the present invention.

One of the above technical solutions has the following advantages or beneficial effects: acquiring fault information in sequence; performing logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and performing algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information; secondly, acquiring a first target weight of a first parameter corresponding to logic judgment, and acquiring a second target weight of a second parameter corresponding to algorithm judgment; determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight and the second target weight; and if the target false alarm judgment result indicates that the fault information is a false alarm, the fault information is restrained.

In the embodiment of the application, the fault information is subjected to logic judgment and algorithm judgment at the same time to obtain a first initial false alarm judgment result and a second initial false alarm judgment result, then a target false alarm judgment result of the fault information is determined based on the first initial false alarm judgment result, the second initial false alarm judgment result, the first target weight and the second target weight, and if the target false alarm judgment result indicates that the fault information is a false alarm, the fault information is restrained, so that the fault information which is the false alarm is not prompted and not stored, thereby saving storage resources and reducing the labor cost and the time cost of aircraft maintenance.

Another technical scheme in the above technical scheme has the following advantages or beneficial effects: and determining a first initial false alarm judgment result according to the power-on time of the fault reporting system of the fault information.

Another technical scheme in the above technical scheme has the following advantages or beneficial effects: and determining a first initial false alarm judgment result according to the fault character string in the fault information.

Another technical scheme in the above technical scheme has the following advantages or beneficial effects: and determining the first initial false alarm judgment result according to the fault type of the fault information, so that whether the fault information is caused by an associated system can be eliminated, and the accuracy of the first initial false alarm judgment result is further improved.

Another technical scheme in the above technical scheme has the following advantages or beneficial effects: and storing the acquired fault information as training fault information into a database, and optimizing the trained neural network model based on the database, so that the accuracy of the second initial false alarm judgment result is improved.

Another technical scheme in the above technical scheme has the following advantages or beneficial effects: and after the trained neural network model is optimized, modifying the first target weight and the second target weight so as to improve the accuracy of the target false alarm judgment result.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings of the embodiments will be briefly described below, and it is apparent that the drawings in the following description relate only to some embodiments of the present invention and are not limiting thereof, wherein:

fig. 1 is a schematic flowchart of an information suppression method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart illustrating logic determination provided by an embodiment of the present invention;

fig. 3 is an interaction diagram of an information suppression method according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an information suppression apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

In the drawings, the shape and size may be exaggerated for clarity, and the same reference numerals will be used throughout the drawings to designate the same or similar components.

Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The use of "first," "second," and similar terms in the description and claims of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. Also, the use of the terms "a," "an," or "the" and similar referents do not denote a limitation of quantity, but rather denote the presence of at least one. "plurality" means two or more. The word "comprise" or "comprises", and the like, means that the element or item listed before "comprises" or "comprising" covers the element or item listed after "comprising" or "comprises" and its equivalents, and does not exclude other elements or items. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.

The embodiment of the invention provides an information suppression method, an information suppression device, computer equipment and a readable storage medium. The information suppression device may be integrated in a computer device, and the computer device may be a device such as a terminal, an aircraft, or a maintenance system on an aircraft.

The terminal includes, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like. Aircraft include, but are not limited to, airplanes, drones, and space probes, among others.

Example one

The information suppression method provided in the embodiments of the present application is described in detail below.

Referring to fig. 1, fig. 1 shows an information suppression method according to an embodiment of the present invention. The method provided by the embodiment can save storage resources and reduce the time cost and the labor cost of airplane maintenance, and the method provided by the embodiment comprises the following steps:

and S101, acquiring fault information.

The power-on test of an on-board system of an aircraft (the on-board system refers to each system on the aircraft) refers to a test performed to confirm whether there is a failure in a system or equipment on the aircraft after a Line Replaceable Unit (LRU) of the system is powered on.

The power-on test may test hardware of the LRU (the hardware of the LRU includes a Central Processing Unit (CPU) of the LRU, a Random Access Memory (RAM) of the LRU, a Read Only Memory (ROM) of the LRU, a timer of the LRU, an interrupt controller of the LRU, etc.), a peripheral device, and any subsystem of the LRU that does not report a health status of itself.

When an onboard system is tested, it is referred to as the system under test. If the fault information exists in the tested system, the tested system is called a fault reporting system. When the airplane is tested on power, if the tested system indicates that a fault exists, corresponding fault information is generated, and the computer equipment acquires the fault information.

S102, carrying out logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and carrying out algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information.

After the computer device obtains the fault information, the logic judgment and the algorithm judgment can be respectively carried out on the fault information, so that a first initial false alarm judgment result and a second initial false alarm judgment result of the fault information are obtained.

The logic judgment refers to a process of judging the fault information based on the power-on time of the fault reporting system corresponding to the fault information and the fault character string in the fault information. The algorithm judgment refers to a process of judging the fault information by adopting a preset algorithm. For example, the predetermined algorithm may be a neural network model or a fault tree.

The first initial false alarm discrimination result may include whether the fault information is a false alarm and whether the fault information is a false alarm. Alternatively, the computer device may directly output "yes" or "no", "yes" indicating that the fault information is a false alarm, and "no" indicating that the fault information is not a false alarm. Or

Alternatively, the first initial value may be used to indicate that the fault information is a false alarm, and the second initial value indicates that the fault information is not a false alarm, and the computer device directly outputs the first initial value and the second initial value, that is, when the first initial false alarm determination result indicates that the fault information is a false alarm, the computer device outputs the first initial value, and when the second initial false alarm determination result indicates that the fault information is not a false alarm, the computer device outputs the second output value.

For example, the first initial value is 0, the second initial value is 1, and when the computer device outputs 0, it indicates that the fault information is a false alarm, and when the computer device outputs 1, it indicates that the fault information is not a false alarm.

Similarly, the representation manner of the second initial false alarm determination result may refer to the representation manner of the first initial false alarm determination result, and this embodiment is not described herein again.

It should be noted that if the aircraft is currently in the flight state, the computer may directly store and prompt the fault information after acquiring the fault information, and if the aircraft is in the ground state, the logic judgment and the algorithm judgment are performed on the fault information.

In some embodiments, the performing a logic determination on the fault information to obtain a first initial false alarm determination result of the fault information includes:

and if the power-on time is less than or equal to the preset threshold, determining the first initial false alarm judgment result as that the fault information is a false alarm.

And if the power-on time is less than or equal to the preset threshold value, the fault information is a false alarm. When the power supply begins to power the fault reporting system, the indication on the bus of the fault reporting system is set to 1. Therefore, the process of determining the power-on time of the fault reporting system of the fault information may be as follows:

and acquiring a target time when the indication on the bus flow of the fault reporting system is set to be 1, and taking the time interval from the target time to the time when the fault information is acquired as the power-on time of the fault reporting system.

If the power-on time is greater than the preset threshold, the first initial false alarm determination result may be determined as whether the fault information is a false alarm.

In other embodiments, if the power-on time is greater than a preset threshold, extracting a character string from the fault information to obtain a fault character string; a first initial false alarm determination of the fault information is determined based on the fault string.

Before the power-on test, the format of the fault information may be set, so that the fault information includes a fault string, and the fault string may be defined.

For example, the fault string may be a 32-bit number, the 14 th to 29 th bit numbers in the fault string representing the fault type, and the 30 th to 31 th bit numbers in the fault string representing the status matrix bits.

As another example, the fault string may be a 64-bit character, the 24 th to 39 th bit characters in the fault string (in this case, the characters may include numbers and letters) represent the fault type, and the 40 th to 41 th bit characters in the fault string represent the status matrix bits.

The form and number of the characters in the fault character string are specifically set, and a user can select the characters according to actual conditions, and the method and the device are not limited herein.

In this embodiment, when the power-on time is greater than the preset threshold, the first initial false alarm determination result is not determined as the fault information is not a false alarm immediately, but is determined according to the fault character string in the fault information, so as to improve the accuracy of the first initial false alarm determination result.

Alternatively, referring to fig. 2, the process of determining the first initial false alarm determination result of the fault information based on the fault string may be:

determining the state of a state matrix bit in a fault character string;

and if the state of the state matrix bit is an abnormal state, determining the first initial false alarm judgment result as that the fault information is not a false alarm.

If the state of the state matrix bit is a normal state, performing feature extraction on the fault character string to obtain a fault type corresponding to the fault information;

For example, when the status matrix bit is 00 or 11, the status of the status matrix bit is abnormal, and when the status matrix bit is 01 or 10, the status of the status matrix bit is normal.

In this embodiment, various failure types may be stored in the failure string so that the failure type can be extracted from the failure string when the state of the state matrix bit in the failure string is a normal state. If the fault type is an internal fault, the fault information is not a false alarm.

If the fault type corresponding to the fault information is an external fault, which indicates that the fault information is possibly caused by faults existing in the associated system of the fault reporting system, searching the associated system corresponding to the fault information, and then determining the electrical state of the associated system; if the electrical state of the associated system is a power-on state, determining that the fault information is not a false alarm according to the first initial false alarm judgment result; if the electrical state of the associated system is a power-off state, the first initial false alarm determination result determines that the fault information is a false alarm.

After the output information of the system B is input to the system A, the system A performs a power-on test, that is, when the system A performs the power-on test, the output information of the system B is used as the input information of the system A, and the system B is called as a related system of the system A.

The output information of the system B may be directly input information of the system a, or the output information of the system B may be indirectly input information of the system a, for example, the output information of the system B is input information of the system C, and the output information of the system C is input information of the system a, in which case, the system B is also referred to as a related system of the system a.

The computer device can store the fault information in association with the association system based on the predefined fault logic. For example, the fault logic is: when the C system is subjected to the power-on test, the output information of the A system and the output information of the B system are required to be used as the input information of the C system, and if the output information of the A system and/or the output information of the B system are not input into the C system when the C system is subjected to the power-on test, the C system generates fault information. The failure information may be stored in association with the a system and the B system.

Therefore, when the fault type corresponding to the fault information is an external fault, the correlation system corresponding to the fault information is searched: system a and system B. And then determining the electrical state of the associated system, if the electrical state of the associated system is the power-on state, indicating that the output information of the system A and the output information of the system B are input into the system C, and the system A and the system B have no problem, reporting that the system has a fault, and determining the first initial false alarm judgment result as whether the fault information is a false alarm.

And if the electrical state of the associated system is a power-off state, the fault information is caused by the fact that the input information of the associated system does not exist, and the fault information is reported to be not a fault, determining the first initial false alarm judgment result as that the fault information is a false alarm.

Wherein, the process of determining the electrical state of the associated system may be: and checking the indication of the associated system, if the indication of the associated system is 1, indicating that the electrical state of the associated system is a power-on state, and if the indication of the associated system is not 1, indicating that the electrical state of the associated system is a power-off state.

In other embodiments, performing an algorithmic determination on the fault information to obtain a second initial false alarm determination result of the fault information includes:

and inputting the fault information into the trained neural network model for judgment to obtain a second initial false alarm judgment result of the fault information.

In this embodiment, the trained neural network model is used to perform an algorithm determination on the fault information, so as to obtain a second initial false alarm determination result of the fault information.

For example, in this embodiment, the trained neural network model may be a convolutional neural network or a Support Vector Machine (SVM), and this embodiment is not limited specifically herein.

In other embodiments, in the process of inputting the fault information into the trained neural network model for determination, the external environment parameters corresponding to the fault information may also be input into the trained neural network model, so that the trained neural network model may determine the fault information based on the external environment parameters.

Before inputting the fault information and the external environment parameters into the trained neural network model, the fault information and the external environment parameters may be preprocessed, where the preprocessing includes, but is not limited to, extracting fault character strings from the fault information, vectorizing the external environment parameters, normalizing, missing value processing, and feature value extracting.

The external environment parameters include configuration version numbers of aircraft configurations (when the configuration version numbers of the aircraft configurations are different, version numbers of adopted software and hardware are different, and functions of the software and hardware with different version numbers are different, and fault logic is different, so the external parameters may include the configuration version numbers of the aircraft configurations), indication of power-on time of the fault reporting system and bus flow of the fault reporting system, service life duration of the fault reporting system, indication of bus flow of an associated system of the fault reporting system, association relations among the airborne systems, and the like.

It should be noted that, after the fault information is input to the trained neural network model for judgment, a probability value is actually obtained, when the second initial false alarm determination result is represented by the first initial value and the second initial value, if the probability value is smaller than the preset probability, the first initial value is used to represent the second initial false alarm determination result, and if the probability value is greater than or equal to the preset probability, the second initial value is used to represent the second initial false alarm determination result.

For example, the preset probability value is 0.5, the first initial value is 0, the second initial value is 1, 0 indicates that the second initial false alarm determination result is that the fault information is a false alarm, and 1 indicates that the second initial false alarm determination result is that the fault information is not a false alarm. And when the probability value is 0.4 and 0.4 is less than 0.5, adopting 0 to represent the second initial false alarm judgment result, and when the probability value is 0.6 and 0.6 is more than 0.5, adopting 1 to represent the second initial false alarm judgment result.

Before inputting the fault information into the trained neural network model for judgment, the neural network model to be trained may be trained first, and the training process may be:

and acquiring training fault information, and classifying the training fault information by using a preset data dictionary rule to obtain a real label of the training fault information. And inputting the fault information and the real label of the fault information into a neural network model to be trained to obtain a prediction label corresponding to the training fault information, and determining a target loss value based on the prediction label and the real label.

And if the target loss value is smaller than the preset value, stopping training to obtain a trained neural network model, if the target loss value is larger than or equal to the preset value, updating the network parameters of the neural network model to be trained based on the target loss value, returning to execute the step of inputting the fault information and the real label of the fault information into the neural network model to be trained to obtain a prediction label corresponding to the training fault information.

The preset data dictionary rule is a tool that defines all fault information, for example, when the format of the fault information is bus name + "missing", the type of the fault information is interface fault information, that is, the description mode that the interface fault information is defined in the preset data dictionary rule is bus name + "missing".

S103, acquiring a first target weight of the corresponding first parameter judged by the logic, and acquiring a second target weight of the corresponding second parameter judged by the algorithm.

The computer device may set and store a first target weight of a first parameter of the logical judgment and a second target weight of a second parameter of the algorithmic judgment before the logical judgment and the algorithmic judgment are performed on the failure information, and directly obtain the first target weight and the second target weight from the storage space after the logical judgment and the algorithmic judgment are performed on the failure information.

The computer device may also set the first target weight and the second target weight after performing the logical judgment and the algorithmic judgment on the failure information.

For the setting time of the first target weight and the second target weight, the user may select according to the actual situation, and the application is not specifically limited herein. The sum of the first initial weight and the second initial weight may be 1.

In some embodiments, the process of setting the first target weight of the first parameter and the second target weight of the second parameter may be:

and initializing the first parameter and the second parameter to obtain a first initial weight of the first parameter and a second initial weight of the second parameter.

if the final judgment result does not meet the preset condition, updating the first initial weight and the second initial weight, and returning to execute a first historical judgment result obtained by performing logic judgment on the historical fault information and a second historical judgment result obtained by performing algorithm judgment on the historical fault information;

The first initial weight and the second initial weight may be updated manually according to experience, or the first initial weight and the second initial weight may be updated according to a preset search algorithm. The pre-set Search algorithm may be Best-first Search Strategy (Best-first Search Strategy) or Backtracking (Backtracking). The present embodiment is not particularly limited herein.

It should be noted that the value range of the first system and the value range of the second coefficient may be determined based on the discrimination accuracy of the trained neural network model and the discrimination accuracy of the logical judgment, and then the first target weight and the second target weight may be found from the value range of the first coefficient and the value range of the second coefficient according to a preset search algorithm.

The discrimination accuracy may be determined based on the historical discrimination results, for example, if 5 of 10 historical discrimination results are accurate, the discrimination accuracy is 0.5.

However, when performing the algorithm judgment by the trained neural network model, since the number of training fault information in the database at the beginning is small, the accuracy of the second historical judgment result obtained by performing the algorithm judgment on the fault information by the trained neural network model at the beginning may not be very high, that is, the judgment precision of the trained neural network model may be smaller than that of the logic judgment.

The resulting first target weight may be set to be greater than the second target weight. That is, when the preset condition is set, the setting may be performed according to the first target weight being greater than the second target weight.

And, at this time, the first history discrimination result and the second history discrimination result may be replaced by discrimination accuracy, that is, at this time, the final discrimination result of the history fault information is determined based on the discrimination accuracy of the logical discrimination, the algorithm discrimination accuracy, the first initial weight, and the second initial weight.

The process of determining the final discrimination result of the historical fault information according to the discrimination precision judged by the logic, the discrimination precision judged by the algorithm, the first initial weight and the second initial weight may be as follows:

and multiplying the judgment precision judged by the logic by the first initial weight to obtain a first historical value, and multiplying the judgment precision judged by the algorithm by the second initial weight to obtain a second historical value. And adding the first historical value and the second historical value to obtain a historical addition result, and determining a final judgment result according to the historical addition result.

And S104, determining a target false alarm judgment result of the fault information based on the first initial false alarm judgment result, the second initial false alarm judgment result, the first target weight and the second target weight.

In this embodiment, the first initial false alarm determination result and the second initial false alarm determination result of the fault information are weighted and fused, so as to obtain the target false alarm determination result of the fault information.

The method for performing weighted fusion on the first initial false alarm determination result and the second initial false alarm determination result of the fault information may be as follows:

multiplying the first initial false alarm judgment result by the first target weight to obtain a first target value;

multiplying the second initial false alarm judgment result by the second target weight to obtain a second target value;

and determining a target false alarm discrimination result of the fault information based on the addition result.

Alternatively, the process of determining the target false alarm discrimination result of the fault information based on the addition result may be:

if the addition result is larger than a preset value, determining the target false alarm judgment result of the fault information as that the fault information is not a false alarm;

and if the addition result is less than or equal to the preset value, determining the target false alarm judgment result of the fault information as that the fault information is a false alarm.

For example, the first target weight is 0.4, the second target weight is 0.6, and the preset value is 0.5. When the first initial false alarm determination result is 1 and the second initial false alarm determination result is 0, the first target value is 0.4, the second target value is 0, and the addition result is 0.4. Since 0.4 is smaller than 0.5, the target false alarm determination result is that the failure information is a false alarm.

When the first initial false alarm determination result is 0 and the second initial false alarm determination result is 1, the first target value is 0, the second target value is 0.6, and the addition result is 0.6. Since 0.6 is greater than 0.5, the target false alarm determination result is that the fault information is not a false alarm.

In the embodiment, the accuracy of the target false alarm judgment result of the fault information is improved by simultaneously carrying out logic judgment and algorithm judgment on the fault information and then weighting and fusing the result of the logic judgment and the result of the algorithm judgment.

For example, as shown in fig. 3, after the fault information is acquired, the logic judgment and the algorithm judgment are performed on the fault information and the external environment parameter, respectively, so as to obtain a first initial false alarm determination result and a second initial false alarm determination result. And then carrying out weighted fusion on the first initial false alarm judgment result and the second initial false alarm judgment result to obtain a target false alarm judgment result.

In some embodiments, after the computer device obtains the fault information, the fault information may be stored in the database as training fault information, so that more and more training fault information are available in the database, and the trained neural network model may be subsequently optimized according to the database to obtain an optimized neural network model, thereby improving the discrimination accuracy of the neural network model.

It should be noted that, when the number of training fault information added in the database is checked to reach the preset number, the trained neural network model may be optimized according to the database. Alternatively, the trained neural network model may be optimized according to the database after the preset time interval is reached.

In this embodiment, the trained neural network model is optimized, so as to improve the accuracy of the second initial false alarm determination result.

When the discrimination precision of the neural network model is improved, the value of the second parameter can be improved, so that the accuracy of the target false alarm discrimination result is improved. Therefore, after the trained neural network model is optimized, the first target weight and the second target weight may be modified to obtain a modified first target weight and a modified second target weight, where the modified second target weight is greater than the second target weight, and the modified first target weight is less than the first target weight.

The first target weight and the second target weight can be modified manually or according to a preset search algorithm. In the process of searching and modifying the second target weight and modifying the first target weight according to the preset search algorithm, the judgment precision of the optimized neural network model is improved, so that the value range of the second coefficient can be modified, and then the preset search algorithm is utilized to search and modify the first target weight and modify the second target weight from the value range of the first coefficient and the value range after modification of the second coefficient, so that the modified second target weight is larger than the modified first target weight.

And/or, in the process of searching and modifying the second target weight and modifying the first target weight according to the preset search algorithm, modifying the preset condition so as to enable the modified second target weight to be larger than the modified first target weight.

And finally, determining a target false alarm judgment result of the fault information based on the first initial false alarm judgment result, the second initial false alarm judgment result, the modified first target weight and the modified second target weight. After the trained neural network model is optimized and the first target weight and the second target weight are modified, if fault information is obtained again, the optimized neural network model is used for carrying out algorithm judgment on the fault information, and a target false alarm judgment result is determined based on the first target weight modification and the second target weight modification.

In this embodiment, the first target weight and the second target weight are modified, so as to improve the accuracy of the target false alarm determination result.

And S105, if the target false alarm judgment result indicates that the fault information is a false alarm, inhibiting the fault information.

And after the computer equipment obtains the target false alarm judgment result, if the target false alarm judgment result indicates that the fault information is a false alarm, the computer equipment suppresses the fault information. Suppressing the failure information means not presenting and storing the failure information.

And if the target false alarm judgment result indicates that the fault information is not a false alarm, prompting and storing the fault information, or prompting after storing, or prompting before storing.

As can be seen from the above, in the embodiment of the present application, the fault information is obtained successively; performing logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and performing algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information; secondly, acquiring a first target weight of a first parameter corresponding to logic judgment, and acquiring a second target weight of a second parameter corresponding to algorithm judgment; determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight and the second target weight; and if the target false alarm judgment result indicates that the fault information is a false alarm, the fault information is restrained.

Example two

In order to better implement the above method, an embodiment of the present invention further provides an information suppression apparatus, for example, as shown in fig. 4, the information suppression apparatus may include:

an information obtaining module 401, configured to obtain fault information.

The determining module 402 is configured to perform logic determination on the fault information to obtain a first initial false alarm determination result of the fault information, and perform algorithm determination on the fault information to obtain a second initial false alarm determination result of the fault information.

The weight obtaining module 403 is configured to obtain a first target weight of the first parameter corresponding to the logic judgment, and obtain a second target weight of the second parameter corresponding to the algorithm judgment.

A determining module 404, configured to determine a target false alarm determination result of the fault information based on the first initial false alarm determination result, the second initial false alarm determination result, the first target weight, and the second target weight.

The suppressing module 405 is configured to suppress the fault information if the target false alarm determination result indicates that the fault information is a false alarm.

Optionally, the determining module 402 is specifically configured to perform:

if the power-on time is larger than a preset threshold value, extracting a character string from the fault information to obtain a fault character string;

a first initial false alarm determination of the fault information is determined based on the fault string.

Optionally, the determining module 402 is specifically configured to perform:

and if the fault character string does not comprise the state matrix bit, determining the first initial false alarm judgment result as that the fault information is not a false alarm.

Optionally, the determining module 402 is specifically configured to perform:

if the fault character string comprises a state matrix bit, extracting the characteristics of the fault character string to obtain a fault type corresponding to the fault information;

Optionally, the determining module 402 is specifically configured to perform:

determining an electrical state of the associated system;

if the electrical state of the associated system is a power-on state, determining that the fault information is not a false alarm according to the first initial false alarm judgment result;

if the electrical state of the associated system is a power-off state, the first initial false alarm determination result determines that the fault information is a false alarm.

Optionally, the determining module 402 is specifically configured to perform:

and inputting the fault information and the external environment parameters into the trained neural network model for judgment to obtain a second initial false alarm judgment result of the fault information.

Optionally, the determining module 402 is specifically configured to perform:

if the first initial false alarm judgment result of the fault information is that the fault information is a false alarm, adopting the first initial value to represent the first initial false alarm judgment result;

if the second initial false alarm judgment result of the fault information is that the fault information is a false alarm, adopting the first initial value to represent the second initial false alarm judgment result;

and if the second initial false alarm judgment result of the fault information indicates that the fault information is not a false alarm, adopting the second initial value to represent the second initial false alarm judgment result.

Optionally, the determining module 404 is specifically configured to perform:

Optionally, the weight obtaining module 403 is specifically configured to perform:

the initialization logic judges the corresponding first parameter and the algorithm judges the corresponding second parameter to obtain a first initial weight of the first parameter and a second initial weight of the second parameter;

Optionally, the information suppression apparatus further includes:

the storage module is used for storing the fault information as training fault information into a database;

and the optimization module is used for optimizing the trained neural network model based on the training fault information in the database to obtain the optimized neural network model.

Optionally, the information suppression apparatus further includes:

the modification module is used for modifying the first target weight and the second target weight to obtain a modified first target weight and a modified second target weight;

accordingly, the determining module 404 is specifically configured to perform:

and determining a target false alarm decision result of the fault information based on the first initial false alarm decision result, the second initial false alarm decision result, the modified first target weight and the modified second target weight.

The functions of the information suppression device provided in this embodiment correspond to the functions implemented in the first embodiment, so other functions in this embodiment can be referred to in the first embodiment, and are not described in detail here.

EXAMPLE III

An embodiment of the present invention further provides a computer device, as shown in fig. 5, which shows a schematic structural diagram of a computer device according to an embodiment of the present invention, specifically:

the computer device may include components such as a processor 501 of one or more processing cores, memory 502 of one or more computer-readable storage media, a power supply 503, and an input unit 504. Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 5 does not constitute a limitation of computer devices, and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. Wherein:

the processor 501 is a control center of the computer device, connects various parts of the entire computer device by using various interfaces and lines, and performs various functions of the computer device and processes data by running or executing computer programs and/or modules stored in the memory 502 and calling data stored in the memory 502, thereby monitoring the computer device as a whole. Optionally, processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 501.

The memory 502 may be used to store computer programs and modules, and the processor 501 executes various functional applications and data processing by operating the computer programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

The computer device further comprises a power supply 503 for supplying power to the various components, and preferably, the power supply 503 may be logically connected to the processor 501 through a power management system, so that functions of managing charging, discharging, power consumption, and the like are realized through the power management system. The power supply 503 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

The computer device may also include an input unit 504, and the input unit 504 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the computer device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 501 in the computer device loads the executable file corresponding to the process of one or more computer programs into the memory 502 according to the following instructions, and the processor 501 runs the computer program stored in the memory 502, so as to implement various functions, such as:

acquiring fault information;

carrying out logic judgment on the fault information to obtain a first initial false alarm judgment result of the fault information, and carrying out algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information;

acquiring a first target weight of a first parameter corresponding to logic judgment, and acquiring a second target weight of a second parameter corresponding to algorithm judgment;

determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight and the second target weight;

and if the target false alarm judgment result indicates that the fault information is a false alarm, the fault information is restrained.

The specific implementation of the above operations and the corresponding beneficial effects can be referred to the foregoing embodiments, and are not described herein again.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by a computer program, which may be stored in a computer-readable storage medium and loaded and executed by a processor, or by related hardware controlled by the computer program.

To this end, the embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, where the computer program can be loaded by a processor to execute the steps in any one of the information suppression methods provided by the embodiment of the present invention.

Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the computer program stored in the computer-readable storage medium can execute the steps in any information suppression method provided in the embodiments of the present invention, the beneficial effects that can be achieved by any information suppression method provided in the embodiments of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described again here.

According to an aspect of the application, there is provided, among other things, a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information suppression method.

The information suppression method, apparatus, computer device and readable storage medium provided by the embodiments of the present invention are described in detail above, and a specific example is applied in the present disclosure to explain the principle and the implementation of the present invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An information suppression method, comprising:

acquiring fault information;

determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight, and the second target weight;

and if the target false alarm judgment result indicates that the fault information is a false alarm, inhibiting the fault information.

2. The information suppression method of claim 1, wherein said logically determining the fault information to obtain a first initial false alarm determination result of the fault information comprises:

3. The information suppression method according to claim 2, further comprising, after the obtaining of the power-on time of the fault reporting system corresponding to the fault information:

if the power-on time is larger than the preset threshold value, extracting a character string from the fault information to obtain a fault character string;

determining a first initial false alarm discrimination result of the fault information based on the fault string.

4. The information suppression method of claim 3, wherein said determining a first initial false alarm determination of the fault information based on the fault string comprises:

determining the state of a state matrix bit in the fault character string;

5. The information suppression method of claim 4, wherein after said determining the state of the state matrix bits in the faulty string, further comprising:

6. The information suppression method according to claim 5, wherein the determining the fault type corresponding to the fault information according to the fault feature value includes:

determining an electrical state of the associated system;

and if the electrical state of the associated system is a power-off state, determining that the fault information is a false alarm according to the first initial false alarm judgment result.

7. The information suppression method according to claim 1, wherein the performing an algorithmic determination on the fault information to obtain a second initial false alarm determination result of the fault information comprises:

8. The information suppression method according to claim 7, wherein the inputting the fault information into a trained neural network model for judgment to obtain a second initial false alarm determination result of the fault information includes:

9. The information suppression method of claim 1, wherein said logically determining the fault information to obtain a first initial false alarm determination result of the fault information comprises:

if the first initial false alarm judgment result of the fault information is that the fault information is false alarm, adopting a first initial value to represent the first initial false alarm judgment result;

carrying out algorithm judgment on the fault information to obtain a second initial false alarm judgment result of the fault information;

if the second initial false alarm judgment result of the fault information is that the fault information is false alarm, adopting the first initial value to represent the second initial false alarm judgment result;

and if the second initial false alarm judgment result of the fault information is that the fault information is not a false alarm, adopting the second initial value to represent the second initial false alarm judgment result.

10. The information suppression method of claim 9, wherein the determining a target false alarm discrimination result for the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight, and the second target weight comprises:

and determining a target false alarm judgment result of the fault information based on the addition result.

11. The information suppression method according to claim 10, wherein the determining a target false alarm determination result of the fault information based on the addition result includes:

if the addition result is larger than a preset value, determining that the target false alarm judgment result of the fault information is that the fault information is not a false alarm;

and if the addition result is smaller than or equal to a preset value, determining the target false alarm judgment result of the fault information as that the fault information is a false alarm.

12. The information suppression method according to any one of claims 1 to 11, wherein the obtaining a first target weight of the logic determination corresponding to a first parameter and obtaining a second target weight of the algorithm determination corresponding to a second parameter comprises:

determining a final discrimination result of historical fault information according to the first historical discrimination result, the second historical discrimination result, the first initial weight and the second initial weight;

13. The information suppressing method according to claim 1, further comprising, after said acquiring failure information:

storing the fault information as training fault information into a database;

14. The information suppression method according to claim 13, wherein after the optimizing the trained neural network model based on the training fault information in the database to obtain an optimized neural network model, further comprises:

accordingly, the determining a target false alarm discrimination result of the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the first target weight, and the second target weight includes:

determining a target false alarm discrimination result for the fault information based on the first initial false alarm discrimination result, the second initial false alarm discrimination result, the modified first target weight, and the modified second target weight.

15. An information suppression apparatus, comprising:

the information acquisition module is used for acquiring fault information;

16. A computer device comprising a processor and a memory, the memory storing a computer program, the processor being configured to execute the computer program in the memory to perform the information suppression method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that it stores a computer program adapted to be loaded by a processor for performing the information suppression method according to any one of claims 1 to 14.