CN108319545B - Information processing method and electronic equipment - Google Patents
Information processing method and electronic equipment Download PDFInfo
- Publication number
- CN108319545B CN108319545B CN201810101811.9A CN201810101811A CN108319545B CN 108319545 B CN108319545 B CN 108319545B CN 201810101811 A CN201810101811 A CN 201810101811A CN 108319545 B CN108319545 B CN 108319545B
- Authority
- CN
- China
- Prior art keywords
- firmware
- information
- combination
- determining
- firmware combination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G06F11/3419—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment by assessing time
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Abstract
An embodiment of the application provides an information processing method and an electronic device, wherein the method comprises the following steps: acquiring firmware combination information of equipment; determining a probability value that the firmware combination possibly causes the equipment fault according to the firmware combination information; and outputting the probability value. The information processing method in the embodiment of the application can predict the probability value that different firmware combinations will cause equipment failure, so that a user can easily obtain the probability predicted value that any brand-new firmware combination will cause equipment failure, and further, a basis is provided for the user to select the firmware for combination.
Description
Technical Field
The application relates to an information processing method and an electronic device.
Background
At present, for example, before the server manufacturer is shipped, it is able to perform a good test on the firmware (BIOS/BMC, etc.) combination collocated with the server manufacturer, so as to solve the problem of system crash of the device caused by the firmware combination. However, after the server is bought by the client, the client may recombine the firmware or update the firmware in the device, and since the client cannot perfectly test the device, the client does not know whether the current firmware combination version will cause frequent device failure, so that the client has a certain risk in using the device with updated firmware combination.
Content of application
The problem to be solved by the application is to provide an information processing method capable of predicting the probability that different firmware combinations will cause equipment failure and an electronic device applying the method.
In order to solve the above problem, the present application provides an information processing method including:
acquiring firmware combination information of equipment;
determining a probability value that the firmware combination possibly causes the equipment fault according to the firmware combination information;
and outputting the probability value.
Preferably, the method further comprises the following steps:
constructing an artificial intelligence training model for determining a probability value that the firmware combination is likely to cause the equipment fault;
the probability value for determining that the firmware combination may cause the device failure according to the firmware combination information is specifically:
determining, by the artificial intelligence training model, a probability value that the firmware combination is likely to cause the device failure.
Preferably, the constructing an artificial intelligence training model for determining the probability value that the firmware combination may cause the device failure is specifically:
constructing a training model architecture;
acquiring firmware combination information of a plurality of devices;
acquiring fault information of a plurality of devices caused by the firmware combination;
and training the training model architecture based on the firmware combination information and the fault information to determine each weight.
Preferably, the training model architecture based on the firmware combination information and the fault information specifically includes:
determining an update time of the firmware combination;
determining a first failure frequency at which the firmware combination causes the device failure within a first time period after updating;
and determining each weight according to the first fault frequency.
Preferably, the training model architecture based on the firmware combination information and the fault information specifically includes:
determining firmware combination information having the same combination version in a plurality of the firmware combinations;
determining a second failure frequency of the firmware combination with the same combination version causing the corresponding equipment failure in a second updated time period;
determining each weight according to the first fault frequency and the second fault frequency;
wherein the second failure frequency is different from the first failure frequency, and the duration of the second time period is greater than the duration of the first time period.
Preferably, the training model architecture based on the firmware combination information and the fault information specifically includes:
determining a firmware combination having at least the same firmware from among the plurality of firmware combinations;
determining a third failure frequency at which a firmware combination at least having the same firmware causes a corresponding device failure within a third updated time period;
determining each weight according to the first fault frequency, the second fault frequency and the third fault frequency;
wherein the third failure frequency is different from the first and second failure frequencies.
An embodiment of the present invention also provides an electronic device, including
An acquisition unit configured to acquire firmware combination information of a device;
the processing unit is used for determining the probability value that the firmware combination possibly causes the equipment failure according to the firmware combination information;
and the display unit is used for displaying the probability value.
Preferably, the method further comprises the following steps: constructing an artificial intelligence training model for determining a probability value that the firmware combination is likely to cause the equipment fault;
the processing unit is further configured to determine, by the artificial intelligence training model, a probability value that the firmware combination is likely to cause the device failure.
Preferably, the constructing an artificial intelligence training model for determining the probability value that the firmware combination may cause the device failure is specifically:
constructing a training model architecture;
the processing unit is further configured to train the training model architecture based on the firmware combination information and the fault information to determine each weight.
Preferably, the processing unit is further configured to:
determining an update time of the firmware combination;
determining a first frequency of failure of the device caused by the firmware combination within a first time period after updating;
and determining each weight according to the first fault frequency.
The method has the advantages that the artificial intelligence training model is used for summarizing the fault probability of equipment faults, such as dead halt and the like, caused by the combination of the firmware, so that a user can obtain a probability predicted value of the equipment faults caused by any brand-new firmware combination through the model, and a basis is provided for the user to select the firmware for combination.
Drawings
Fig. 1 is a flowchart of an embodiment of an information processing method according to the present application.
Fig. 2 is a flowchart of an artificial intelligence training model training method in the information processing method of the present application.
FIG. 3 is a flowchart of an artificial intelligence training model training method according to another embodiment of the information processing method of the present application.
Fig. 4 is a block diagram of an electronic device according to the present application.
Detailed Description
The present application is described in detail below with reference to the attached drawings.
It will be understood that various modifications may be made to the embodiments disclosed herein. The following description is, therefore, not to be taken in a limiting sense, but is made merely as an exemplification of embodiments. Other modifications will occur to those skilled in the art within the scope and spirit of the disclosure.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the disclosure and, together with a general description of the disclosure given above, and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It should also be understood that, although the present application has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of application, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present disclosure will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely examples of the disclosure that may be embodied in various forms. Well-known and/or repeated functions and structures have not been described in detail so as not to obscure the present disclosure with unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present disclosure in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the disclosure.
Optionally, in this embodiment of the application, the electronic device may be a different electronic device such as a PC, a tablet computer, a notebook computer, and the like, which is not limited in this embodiment of the application.
At present, for example, before the server manufacturer is shipped, the firmware assembly (BIOS/BMC, etc.) collocated with the server manufacturer is tested well, so as to solve the problem of system crash of the device caused by the firmware assembly. However, after the server is bought by the client, the client may recombine the firmware or update the firmware in the device, and since the client cannot perfectly test the device, the client does not know whether the current firmware combination version will cause frequent device failure, so that the client has a certain risk in using the device with updated firmware combination.
As shown in fig. 1, to solve the above technical problem, the present application provides an information processing method, which includes:
s101, acquiring firmware combination information of equipment;
the firmware combination refers to a combination of multiple firmware, such as BIOS, BMC, etc., which have multiple firmware and are formed by combining multiple firmware. The acquired firmware combination information may be the firmware information in the BMC of the current electronic device.
S201, determining a probability value of equipment failure possibly caused by firmware combination according to firmware combination information;
for example, the server may obtain firmware combination information and fault information of each electronic device that causes a fault of the electronic device due to some firmware combination, such as mismatch, abnormal operation, and crash, in advance, and may specifically transmit the firmware combination information and fault information to the central control software of the server, so that the central control software may evaluate and calculate, based on the data information sent by a large number of previous electronic devices, a probability that an updated firmware combination (that is, a firmware combination formed by combining combinations of firmware that has not occurred before) sent by a subsequently produced electronic device may cause a device fault.
S301, outputting a probability value;
and outputting the probability value, for example, displaying the probability value on a screen to enable a user to visually acquire the probability value, or outputting the probability value in a reminding or alarming manner, for example, setting a threshold, and when the probability value exceeds a preset range, giving an alarm, for example, flashing a red warning light on the screen or the like, or giving a voice prompt or the like to inform the user that equipment failure is easily caused by the current firmware combination.
By the method in the embodiment of the application, a user can easily acquire whether the firmware combination can be normally used or not or whether the risk of equipment failure is reduced or improved only by sending relevant information of the firmware combination, such as firmware name information, version information and the like to a server or through a cloud database and the like, and then a reliable and effective basis is provided for the user to select the firmware combination for combination.
Further, in order to improve the accuracy of the probability prediction information on whether various updated firmware combinations will affect the failure of the electronic device, and make the predicted probability value have a reference significance, in the embodiment of the present application, when the step of determining the probability value that the firmware combination may cause the device failure according to the firmware combination information is implemented, the following method is adopted:
constructing an artificial intelligence training model for determining the probability value of the firmware combination possibly causing equipment failure;
and determining the probability value that the firmware combination can cause equipment failure through an artificial intelligence training model.
As shown in fig. 2, the above-mentioned artificial intelligence training model for determining the probability value that the firmware combination may cause the device failure is specifically:
constructing a training model architecture;
acquiring firmware combination information of a plurality of devices, such as acquiring a firmware version list of a BMC (baseboard management controller) of the plurality of devices, wherein the firmware combination information contains basic information of each firmware in the BMC, and meanwhile, the updating time of each firmware can be acquired;
acquiring fault information of a plurality of devices caused by firmware combination, for example, information of major errors or system halt of the devices caused by BMC;
training the training model architecture based on the firmware combination information and the fault information to determine each weight in the training model architecture, and further obtaining a probability value capable of predicting with high precision that equipment faults will be caused by the firmware combination updated later. For example, the version information, name information and update time of the firmware combination are used as input information, and the fault information of the equipment correspondingly caused by each firmware combination is used as output information, so that the weight in each equation in the training model is calculated based on the output information.
Further, as shown in fig. 3, because the time, frequency, and the like of the firmware combination that cause the device to malfunction in the using process are not fixed, in order to eliminate some device malfunctions caused by accidental factors and the like, eliminate the collinearity of data, and avoid affecting the accuracy of weight calculation, in the embodiment of the present application, when the model architecture is trained by using the firmware combination information and the corresponding malfunction information, the following training is performed in combination:
the first mode is as follows:
determining an update time of the firmware combination;
determining a first failure frequency at which the firmware combination causes equipment failure within a first time period after updating;
and determining each weight according to the first fault frequency.
For example, the update time of a certain firmware combination in BMCs in a plurality of electronic devices is 2 month 1 day, 2 month 3 days, 3 month 1 day, and 4 month 1 day in this order, the number of failures of each device in one week (i.e., a first time period, which may be two weeks, three weeks, or the like) after each update day is obtained with each update day as a reference, the frequency of the failure of each device in the first time period, that is, the first failure frequency is calculated based on the number of failures and the time of the first time period, and the higher the first failure frequency is, the higher the weight corresponding to the firmware combination in the corresponding adjustment model is, so that the obtained failure probability value corresponding to the firmware combination is higher.
Of course, the weight corresponding to each firmware combination in the model may also be adjusted and calculated based on the time at which the corresponding device first fails within one week after the update time, so that the obtained failure probability value corresponding to the firmware combination is higher.
The second mode is as follows:
determining firmware combination information having the same combination version in a plurality of firmware combinations;
determining update times of a plurality of firmware combinations;
determining a second failure frequency of the corresponding equipment caused by the firmware combination with the same combination version in a second updated time period;
determining each weight according to the first fault frequency and the second fault frequency;
the second failure frequency is different from the first failure frequency, and the duration of the second time period is greater than that of the first time period.
For example, some devices may use the same version of firmware combination, but the time of failure of the device where the firmware combination with the same version is located is different, for example, a first device and a second device use BMCs with the same version, but the time of failure of the first device is the time of failure occurring only in the second week or the second month after updating, and the second device is the time of failure occurring in the first week after updating, so that the use conditions of the two devices need to be considered comprehensively when calculating the weight value corresponding to the firmware combination in the model, and the calculation cannot be performed only according to the use condition of one device. In specific implementation, a second time period may be determined according to a time when each device having the same firmware combination of the same version first appears after being updated, and the second time period may be set to be longer than the first time period, so as to more fully cover the time when all the devices fail. Then, calculating a second failure frequency of each firmware combination in a second time period, and correspondingly adjusting the weight of the corresponding firmware combination based on the first failure frequency and the second failure frequency with the lowest numerical value, so as to reduce the probability value of the equipment failure caused by the firmware combination. That is, if the normal use time of a certain device is long, the other devices will fail if the device is used for one week, and the device is normally used for two weeks, and then the corresponding failure probability value is appropriately reduced. The specific magnitude of the decrease in probability value may depend on the time of normal use of the device. Of course, the weight corresponding to the firmware combination can also be determined according to the first failure frequency of each device and the chronological trend of the second failure frequency in the second time period.
The third mode is as follows:
determining that at least one firmware combination of the plurality of firmware combinations has the same firmware, that is, some firmware combinations of the plurality of devices may adopt the same version of firmware, which is equivalent to that the firmware combinations of the plurality of devices have similarity;
determining that a firmware combination having at least the same firmware causes a third failure frequency of the corresponding device within a third time period after updating;
determining each weight according to the first fault frequency, the second fault frequency and the third fault frequency;
wherein the third failure frequency is different from the first failure frequency and the second failure frequency.
For example, BMCs (corresponding to firmware combinations) in the multiple devices each include the first firmware, and in a third updated time period, for example, within three weeks (of course, one or two weeks may also be used, that is, the time of the third time period is not fixed, and may be the same as or different from the first time period and the second time period), if the third failure frequency of one or some devices is lower, or the trend of the third failure frequency of the multiple devices with time is an increasing trend, the weight of the corresponding type of firmware combination may be adjusted according to the third failure frequency on the premise that the first failure frequency and the second failure frequency are not changed, so that the probability value that the type of firmware combination causes device failure is reduced. The magnitude of the reduction may also depend on the normal usage time of a device having a firmware combination of the type described above. If the device with the type of firmware combination can be normally used for one month after updating, the corresponding probability value is reduced by 10%, and the like. When the first failure frequency and the second failure frequency are changed, the corresponding weight values need to be determined specifically by combining the three failure frequencies.
As shown in fig. 4, an embodiment of the present application also provides an electronic device, including
An acquisition unit configured to acquire firmware combination information of a device; the firmware combination refers to a combination of multiple firmware, such as BIOS, BMC, etc., which have multiple firmware and are formed by combining multiple firmware. The acquired firmware combination information may be the firmware information in the BMC of the current electronic device.
The processing unit is used for determining the probability value of equipment failure possibly caused by the firmware combination according to the firmware combination information; for example, the processing unit may obtain firmware combination information and fault information of each device that cause a fault of the electronic device due to some firmware combination, such as mismatch, abnormal operation, and crash, in advance, and may specifically transmit the firmware combination information and fault information to the central control software of the processing unit, so that the central control software may evaluate and calculate, based on the data information sent by a large number of previous electronic devices, a probability that an updated firmware combination (that is, a firmware combination formed by combining combinations of firmware that has not occurred before) sent by a subsequently produced electronic device may cause a device fault.
And the display unit is used for displaying the probability value. Or output in a reminding or alarming manner, for example, setting a threshold, and when the probability value exceeds a preset range, giving an alarm, such as flashing a red warning light on a screen, or giving a voice prompt, so as to inform a user that a current firmware combination is very likely to cause equipment failure.
Through the electronic equipment in the embodiment of the application, a user can easily acquire whether the firmware combination can be normally used or not or whether the risk of equipment failure is reduced or improved only by sending relevant information of the firmware combination, such as firmware name information, version information and the like, to the processing unit, so that a reliable and effective basis is provided for the user to select the firmware combination for combination.
Further, in order to improve the accuracy of the probability prediction information on whether various updated firmware combinations will affect the failure of the electronic device, and make the predicted probability value have a reference significance, in the embodiment of the present application, when the step of determining the probability value that the firmware combination may cause the device failure according to the firmware combination information is implemented, the following method is adopted:
constructing an artificial intelligence training model for determining the probability value of the firmware combination possibly causing equipment failure;
the processing unit is also used for determining the probability value that the firmware combination possibly causes equipment failure through the artificial intelligence training model.
The artificial intelligence training model for determining the probability value of the firmware combination possibly causing the equipment fault is specifically constructed as follows:
constructing a training model architecture;
the processing unit is further used for training the training model architecture based on the firmware combination information and the fault information to determine each weight, and further obtaining a probability value capable of predicting with high precision that equipment faults will be caused by the firmware combination updated later. For example, the version information, name information and update time of the firmware combination are used as input information, and the fault information of the equipment correspondingly caused by each firmware combination is used as output information, so that the weight in each equation in the training model is calculated based on the output information.
Further, because the time, frequency, and the like of the firmware combinations that cause the device to malfunction in the using process are not fixed, in order to eliminate some device malfunctions caused by accidental factors and the like, eliminate the collinearity of data, and avoid affecting the accuracy of weight calculation, the processing unit in the embodiment of the present application trains the model architecture by using the firmware combination information and the corresponding malfunction information, and simultaneously trains in combination with the following manners:
the first mode is as follows:
determining an update time of the firmware combination;
determining a first frequency of failure of the device caused by the firmware combination within a first time period after updating;
and determining each weight according to the first fault frequency.
For example, the update time of a certain firmware combination in BMCs in a plurality of electronic devices is 2 month 1 day, 2 month 3 days, 3 month 1 day, and 4 month 1 day in this order, the number of failures of each device in one week (i.e., a first time period, which may be two weeks, three weeks, or the like) after each update day is obtained with each update day as a reference, the frequency of the failure of each device in the first time period, that is, the first failure frequency is calculated based on the number of failures and the time of the first time period, and the higher the first failure frequency is, the higher the weight corresponding to the firmware combination in the corresponding adjustment model is, so that the obtained failure probability value corresponding to the firmware combination is higher.
Of course, the weight corresponding to each firmware combination in the model may also be adjusted and calculated based on the time at which the corresponding device first fails within one week after the update time, so that the obtained failure probability value corresponding to the firmware combination is higher.
The second mode is as follows:
determining firmware combination information having the same combination version in a plurality of firmware combinations;
determining a second failure frequency of the firmware combination with the same combination version causing corresponding equipment failure in a second updated time period;
determining each weight according to the first fault frequency and the second fault frequency;
the second failure frequency is different from the first failure frequency, and the duration of the second time period is greater than that of the first time period.
For example, some devices may use the same version of firmware combination, but the time of failure of the device where the firmware combination with the same version is located is different, for example, a first device and a second device use BMCs with the same version, but the time of failure of the first device is the time of failure occurring only in the second week or the second month after updating, and the second device is the time of failure occurring in the first week after updating, so that the use conditions of the two devices need to be considered comprehensively when calculating the weight value corresponding to the firmware combination in the model, and the calculation cannot be performed only according to the use condition of one device. In specific implementation, a second time period may be determined according to a time when each device having the same firmware combination of the same version first appears after being updated, and the second time period may be set to be longer than the first time period, so as to more fully cover the time when all the devices fail. Then, calculating a second failure frequency of each firmware combination in a second time period, and correspondingly adjusting the weight of the corresponding firmware combination based on the first failure frequency and the second failure frequency with the lowest numerical value, so as to reduce the probability value of the equipment failure caused by the firmware combination. That is, if the normal use time of a certain device is long, the other devices will fail if the device is used for one week, and the device is normally used for two weeks, and then the corresponding failure probability value is appropriately reduced. The specific magnitude of the decrease in probability value may depend on the time of normal use of the device. Of course, the weight corresponding to the firmware combination can also be determined according to the first failure frequency of each device and the chronological trend of the second failure frequency in the second time period.
The third mode is as follows:
determining that at least one firmware combination of the plurality of firmware combinations has the same firmware, that is, some firmware combinations of the plurality of devices may adopt the same version of firmware, which is equivalent to that the firmware combinations of the plurality of devices have similarity;
determining a third failure frequency at which a firmware combination at least having the same firmware causes a corresponding device failure within a third updated time period;
determining each weight according to the first fault frequency, the second fault frequency and the third fault frequency;
wherein the third failure frequency is different from the first and second failure frequencies.
For example, BMCs (corresponding to firmware combinations) in the multiple devices each include the first firmware, and in a third updated time period, for example, within three weeks (of course, one or two weeks may also be used, that is, the time of the third time period is not fixed, and may be the same as or different from the first time period and the second time period), if the third failure frequency of one or some devices is lower, or the trend of the third failure frequency of the multiple devices with time is an increasing trend, the weight of the corresponding type of firmware combination may be adjusted according to the third failure frequency on the premise that the first failure frequency and the second failure frequency are not changed, so that the probability value that the type of firmware combination causes device failure is reduced. The magnitude of the reduction may also depend on the normal usage time of a device having a firmware combination of the type described above. If the device with the type of firmware combination can be normally used for one month after updating, the corresponding probability value is reduced by 10%, and the like. When the first failure frequency and the second failure frequency are changed, the corresponding weight values need to be determined specifically by combining the three failure frequencies.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (6)
1. An information processing method characterized by comprising:
constructing an artificial intelligence training model for determining probability values of equipment faults possibly caused by firmware combinations, wherein the firmware combinations refer to a plurality of firmware used in a matching and combining manner;
acquiring firmware combination information of equipment, wherein the firmware combination information is information of each firmware in a firmware combination;
the artificial intelligence training model determines a probability value that the firmware combination possibly causes the equipment fault according to the firmware combination information and outputs the probability value;
the method for establishing the artificial intelligence training model for determining the probability value of the firmware combination possibly causing the equipment fault specifically comprises the following steps:
constructing a training model architecture;
acquiring firmware combination information of a plurality of devices;
acquiring fault information of a plurality of devices caused by the firmware combination;
and training the training model architecture based on the firmware combination information and the fault information to determine each weight.
2. The method of claim 1, wherein the training model architecture based on the firmware combination information and the fault information is specifically:
determining an update time of the firmware combination;
determining a first failure frequency at which the firmware combination causes the device failure within a first time period after updating;
and determining each weight according to the first fault frequency.
3. The method of claim 2, wherein the training model architecture based on the firmware combination information and the fault information is specifically:
determining firmware combination information having the same combination version in a plurality of the firmware combinations;
determining a second failure frequency of the firmware combination with the same combination version causing the corresponding equipment failure in a second updated time period;
determining each weight according to the first fault frequency and the second fault frequency;
wherein the second failure frequency is different from the first failure frequency, and the duration of the second time period is greater than the duration of the first time period.
4. The method of claim 3, wherein the training model architecture based on the firmware combination information and the fault information is specifically:
determining a firmware combination having at least the same firmware from among the plurality of firmware combinations;
determining a third failure frequency at which a firmware combination at least having the same firmware causes a corresponding device failure within a third updated time period;
determining each weight according to the first fault frequency, the second fault frequency and the third fault frequency;
wherein the third failure frequency is different from the first and second failure frequencies.
5. An electronic device, comprising
The device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring firmware combination information of the device, the firmware combination refers to a plurality of firmware used in a matched combination mode, and the firmware combination information is information of each firmware in the firmware combination;
the processing unit is used for determining the probability value that the firmware combination possibly causes the equipment failure according to the firmware combination information;
a display unit for displaying the probability value;
further comprising: constructing an artificial intelligence training model for determining a probability value that the firmware combination is likely to cause the equipment fault;
the processing unit is further used for determining a probability value that the firmware combination possibly causes the equipment fault through the artificial intelligence training model;
the method for establishing the artificial intelligence training model for determining the probability value of the firmware combination possibly causing the equipment fault specifically comprises the following steps:
constructing a training model architecture;
the processing unit is further configured to train the training model architecture based on the firmware combination information and the fault information to determine each weight.
6. The electronic device of claim 5, wherein the processing unit is further configured to:
determining an update time of the firmware combination;
determining a first frequency of failure of the device caused by the firmware combination within a first time period after updating;
and determining each weight according to the first fault frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101811.9A CN108319545B (en) | 2018-02-01 | 2018-02-01 | Information processing method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810101811.9A CN108319545B (en) | 2018-02-01 | 2018-02-01 | Information processing method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108319545A CN108319545A (en) | 2018-07-24 |
| CN108319545B true CN108319545B (en) | 2021-07-16 |
Family
ID=62888192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810101811.9A Active CN108319545B (en) | 2018-02-01 | 2018-02-01 | Information processing method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319545B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101061464A (en) * | 2004-11-17 | 2007-10-24 | 日本电气株式会社 | Information processing device, program thereof, modular type system operation management system, and component selection method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6070337B2 (en) * | 2013-03-25 | 2017-02-01 | 富士通株式会社 | Physical failure analysis program, physical failure analysis method, and physical failure analysis apparatus |
| CN103246771B (en) * | 2013-05-10 | 2017-02-22 | 北京航空航天大学 | Fault-tolerant circuit fault effect analytical method based on simulation |
| CN103617110B (en) * | 2013-11-11 | 2016-09-07 | 国家电网公司 | Server device condition maintenance system |
| CN103957247A (en) * | 2014-04-22 | 2014-07-30 | 安一恒通（北京）科技有限公司 | Equipment quality assessment score processing method and device |
| US10089178B2 (en) * | 2016-02-29 | 2018-10-02 | International Business Machines Corporation | Developing an accurate dispersed storage network memory performance model through training |
-
2018
- 2018-02-01 CN CN201810101811.9A patent/CN108319545B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101061464A (en) * | 2004-11-17 | 2007-10-24 | 日本电气株式会社 | Information processing device, program thereof, modular type system operation management system, and component selection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108319545A (en) | 2018-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8314694B2 (en) | System and method for suppressing redundant alarms | |
| US9049105B1 (en) | Systems and methods for tracking and managing event records associated with network incidents | |
| US11042476B2 (en) | Variability system and analytics for continuous reliability in cloud-based workflows | |
| US11281519B2 (en) | Health indicator platform for software regression reduction | |
| US20170083400A1 (en) | Automated Incident Resolution System and Method | |
| US8504874B2 (en) | Repair-policy refinement in distributed systems | |
| US7712083B2 (en) | Method and apparatus for monitoring and updating system software | |
| US20190041839A1 (en) | Apparatus for troubleshooting fault component in equipment and method thereof | |
| US11669390B2 (en) | Automated detection and classification of dynamic service outages | |
| US11030828B2 (en) | System and method to auto create aircraft maintenance records by aircraft data | |
| EP3239840B1 (en) | Fault information provision server and fault information provision method | |
| US11423494B2 (en) | Plant assistance assessment system and plant assistance assessment method | |
| KR102281640B1 (en) | AI Gas Leak Detection System with Self-Diagnosis Function and operating Method thereof | |
| CN111104283B (en) | Fault detection method, device, equipment and medium of distributed storage system | |
| JP6880560B2 (en) | Failure prediction device, failure prediction method and failure prediction program | |
| CN115409283A (en) | Equipment failure prediction method, equipment failure prediction device, equipment and storage medium | |
| CN108319545B (en) | Information processing method and electronic equipment | |
| US10007583B2 (en) | Generating a data structure to maintain error and connection information on components and use the data structure to determine an error correction operation | |
| CN111626498A (en) | Equipment operation state prediction method, device, equipment and storage medium | |
| JP2010152539A (en) | Failure detection system verification device, failure detection system verification method and failure detection system verification control program | |
| US11102103B2 (en) | Network stabilizing tool | |
| CN114914008B (en) | Control method and device for emergency response action of nuclear power plant, electronic equipment and medium | |
| CN112712151B (en) | Epidemic situation health code quality control method and device, medium and equipment | |
| CN113126881A (en) | System configuration method, device, equipment, readable storage medium and distributed storage system | |
| CN114503210A (en) | Monitoring performance of predictive computer-implemented models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |