Information communication system fault locating method and system combining multi-factor judgment

Abstract

The embodiment of the application provides a kind of information communication system fault location method and system combined with multi-factor judgment, belong to the technical field of information system maintenance.The method comprises: obtaining the fault frequency of information communication system in historical time period;Build the multi-factor module matrix of the information communication system;According to the fault frequency, determine the stability index of the information communication system in each historical time period;The multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i th historical time period is used as output, to determine the multi-factor attention mechanism;Obtain the multi-factor module matrix of information communication system in current time period;According to the multi-factor module matrix and the multi-factor attention mechanism, calculate the stability index of the information communication system in the next time period.

Description

Technical Field

[0001] The present invention relates to the technical field of information system maintenance, and in particular to a method and system for locating faults in an information communication system combining multi-factor judgment. Background Art

[0002] In the field of information and communication systems, stability assessment and prediction have always been key technical challenges. As networks continue to expand in scale and complexity, the requirements for system stability are becoming increasingly stringent. However, existing technical solutions often rely on extremely complex network models for assessment and prediction, which not only leads to high costs but also places extremely high demands on the computing power and load of equipment.

[0003] Specifically, these complex network models often require extensive data input and meticulous parameter adjustments to ensure accurate evaluation. This not only increases the difficulty of data collection and processing, but also prolongs the evaluation cycle and reduces overall efficiency. Furthermore, highly complex models also result in higher computational loads, which can be an insurmountable obstacle for scenarios with limited resources or limited device performance.

[0004] More importantly, existing technical methods often lack flexibility and adaptability. Once the network structure or operating environment changes, these complex model-based evaluation methods may need to be redesigned and adjusted, which undoubtedly increases the difficulty and cost of operations and maintenance. Therefore, in practical applications, the universality and practicality of these methods are often questioned. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for locating faults in an information communication system that combines multi-factor judgment. The method and system can efficiently perform stability location assessment on the information communication system.

[0006] To achieve the above objectives, an embodiment of the present invention provides an information communication system fault location method combining multi-factor judgment, including:

[0007] Obtain the failure frequency of the information communication system in a historical period;

[0008] Constructing a multi-factor module matrix of the information communication system;

[0009] determining a stability index of the information communication system in each of the historical time periods according to the failure frequency;

[0010] The multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as output to determine the multi-factor attention mechanism;

[0011] Obtain the multi-factor module matrix of the information and communication system in the current time period;

[0012] The stability index of the information communication system in the next time period is calculated based on the multi-factor module matrix and the multi-factor attention mechanism.

[0013] Optionally, obtaining the failure frequency of the information communication system in a historical time period includes:

[0014] Obtaining historical failure frequencies of the information communication system;

[0015] Initialize the value of the time period;

[0016] Determining the fault frequency and the multi-factor module matrix according to the time period;

[0017] Determining the correlation between the fault frequency and the multi-factor module matrix;

[0018] Determining whether the correlation is greater than or equal to a preset value;

[0019] If it is determined that the correlation is greater than or equal to the preset value, recording the current time period as the optimal solution;

[0020] If it is determined that the correlation is less than the preset value, the value of the time period is updated, and the process returns to the step of determining the fault frequency and the multi-factor module matrix according to the time period.

[0021] Optionally, determining the correlation between the fault frequency and the multi-factor module matrix includes:

[0022] The correlation is calculated according to formula (1),

[0023]

[0024] Where S is the correlation, n is the number of divided time periods, B i+1 is the multi-factor module matrix of the i+1th time period, B i is the multi-factor module matrix of the i-th time period, f i is the fault frequency level in the i-th time period, f i-1 is the fault frequency level in the i-1th time period.

[0025] Optionally, updating the value of the time period includes:

[0026] Determine the magnitude relationship between the correlation of the previous iteration and the correlation of this iteration;

[0027] If the correlation degree of the previous iteration is greater than or equal to the correlation degree of the current iteration, continue to execute the updating method of updating the time period selected in the previous iteration;

[0028] When the correlation degree of the previous iteration is less than the correlation degree of the current iteration, the updating method for updating the time period is changed.

[0029] Optionally, the updating method includes:

[0030] Update the time period according to formula (2),

[0031] T i+1 =T i +Δt, (2)

[0032] Among them, T i+1 is the updated time period value, T i is the value of the time period before the update, and Δt is the unit update time; or

[0033] Update the time period according to formula (3),

[0034] T i+1 =T i -Δt, (3).

[0035] Optionally, updating the value of the time period includes:

[0036] Determining a switching frequency of the update method;

[0037] Determining whether the switching frequency is greater than or equal to a preset frequency threshold;

[0038] When it is determined that the switching frequency is greater than or equal to the frequency threshold, the value of the unit update time is adjusted when the update method is updated this time.

[0039] Optionally, adjusting the value of the unit update time includes:

[0040] When it is determined that the switching frequency is less than the frequency threshold, the unit update time is adjusted back to the initial value.

[0041] Optionally, the multi-factor module matrix in the i-1th historical time period is used as input and the stability index in the i-th historical time period is used as output to determine the multi-factor attention mechanism, including:

[0042] Initializing the multi-factor attention mechanism;

[0043] The multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as the standard output to calculate the deviation degree of the current multi-factor attention mechanism;

[0044] Determining whether the degree of deviation is greater than or equal to a preset degree threshold;

[0045] If it is determined that the degree of deviation is greater than or equal to the degree threshold, updating the multi-factor attention mechanism according to the degree of deviation, and returning to the step of calculating the degree of deviation of the current multi-factor attention mechanism by taking the multi-factor module matrix in the i-1th historical time period as input and the stability index in the i-th historical time period as a standard output;

[0046] When it is determined that the degree of deviation is less than the degree threshold, the multi-factor attention mechanism is output.

[0047] Optionally, updating the multi-factor attention mechanism according to the degree of deviation includes:

[0048] Determine whether there are any unselected row vectors in the current multi-factor attention mechanism;

[0049] When it is determined that there is still an unselected row vector in the current multi-factor attention mechanism, randomly select an unselected row vector from the multi-factor attention mechanism as the row vector to be updated;

[0050] Determining whether the degree of deviation when updating the row vector to be updated in the previous round is greater than the degree of deviation calculated before the update;

[0051] When it is determined that the deviation degree when updating the row vector to be updated in the previous round is less than or equal to the deviation degree calculated before the update, the row vector to be updated is updated using the corresponding trend matrix;

[0052] When it is determined that the deviation degree calculated this time is greater than the deviation degree, the correction matrix of the corresponding trend matrix is ​​used to update the row vector to be updated, and the correction matrix is ​​used as the new trend matrix of the vector to be updated.

[0053] On the other hand, the present invention further provides an information communication system fault location system combining multi-factor judgment, the system comprising a processor, and the processor is configured to execute any of the above methods.

[0054] Through the above-mentioned technical solution, the present invention provides a method and system for locating information and communication system faults that integrates multi-factor judgment. This method and system utilizes an attention mechanism to perform weighted calculations on a historical multi-factor module matrix, thereby determining the stability index of the information and communication system within a predetermined time period. Compared to existing technologies, the method and system provided by the present invention, which relies solely on weighted matrix calculations, avoids the use of complex model calculations, reduces design costs, and achieves higher computational efficiency.

[0055] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0057] Figure 1 is a flow chart of a method for locating a fault in an information communication system combining multi-factor judgment according to an embodiment of the present invention;

[0058] Figure 2 is a flow chart of a method of determining a value of a time period according to one embodiment of the present invention;

[0059] Figure 3 is a flowchart of a method for updating a time period according to one embodiment of the present invention;

[0060] Figure 4 is a flowchart of a method for determining a multi-factor attention mechanism according to one embodiment of the present invention;

[0061] Figure 5 4 is a flowchart of a method for updating a multi-factor attention mechanism according to a degree of deviation according to one embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0063] like Figure 1 The figure shows a flow chart of a method for locating a fault in an information communication system according to an embodiment of the present invention, which combines multiple factors for judgment. Figure 1 In the method, the method may include the following steps:

[0064] In step S10, the failure frequency of the information communication system in a historical time period is obtained;

[0065] In step S11, a multi-factor module matrix of the information communication system is constructed;

[0066] In step S12, a stability index of the information communication system in each historical time period is determined based on the fault frequency;

[0067] In step S13, the multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as output to determine the multi-factor attention mechanism;

[0068] In step S14, a multi-factor module matrix of the information communication system in the current time period is obtained;

[0069] In step S15, the stability index of the information communication system in the next time period is calculated based on the multi-factor module matrix and the multi-factor attention mechanism.

[0070] In this Figure 1 In the method shown, step S10 can be used to obtain the failure frequency of the information communication system in the historical time period. The failure frequency can be the cumulative number of failures of the information communication system in the historical time period, or the average number of failures of the information communication system per day in the historical time period, or the mode number of failures of the information communication system per day in the historical time period. The value of the time period can be determined in a variety of ways known to those skilled in the art, such as a manually set method. However, considering that the method provided by the present invention needs to ensure that the multi-factor module moment as input and the stability index as output are correlated, if the value of the time period is not properly selected, it will make the subsequent multi-factor attention mechanism difficult to iteratively calculate. Therefore, in a preferred example of the present invention, the method for determining the value of the time period may further include: Figure 2 The steps shown in Figure 2 In the method of determining the value of the time period, the method may include the following steps:

[0071] In step S20, the historical failure frequency of the information communication system is obtained;

[0072] In step S21, the value of the time period is initialized;

[0073] In step S22, the fault frequency and the multi-factor module matrix are determined according to the time period;

[0074] In step S23, the correlation between the fault frequency and the multi-factor module matrix is ​​determined;

[0075] In step S24, it is determined whether the correlation is greater than or equal to a preset value;

[0076] In step S25, if the correlation is greater than or equal to the preset value, the current time period is recorded as the optimal solution;

[0077] In step S26, when it is determined that the correlation is less than the preset value, the value of the time period is updated, and the process returns to the step of determining the fault frequency and the multi-factor module matrix according to the time period, that is, returns to step S22.

[0078] In this Figure 2 In the method shown, step S20 can be used to obtain the historical fault frequency of the information communication system. Step S21 can be used to initialize the value of the time period to form an initial solution. After the initial solution is determined, the fault frequency and the multi-factor module matrix can be determined according to the time period through step S22, and then the correlation between the fault frequency and the multi-factor module matrix can be determined in combination with step S23, and the threshold judgment of the correlation in step S24 can be used to determine whether the feature correlation between the fault frequency and the multi-factor module matrix meets the requirements. If the correlation is greater than or equal to the preset value, that is, the feature correlation meets the requirements, then the value of the current time period can be directly determined as the optimal solution. Otherwise, it is necessary to update the value of the time period and return to execute step S22 for re-judgment. Among them, the specific calculation method of the correlation can be a variety of forms known to people in this field. In a preferred example of the present invention, the correlation can be calculated using the following formula (1):

[0079] Calculate the correlation according to formula (1):

[0080]

[0081] Among them, S is the correlation, n is the number of time periods divided, B i+1 is the multi-factor module matrix of the i+1th time period, B i is the multi-factor module matrix of the i-th time period, f i is the fault frequency level in the i-th time period, f i-1 is the fault frequency level in the i-1th time period.

[0082] In addition, the method for updating the value of the time period can be various forms known to those skilled in the art. However, considering the operation efficiency of the algorithm, in one example of the present invention, the method can be as follows: Figure 3 Specifically, the method for updating the time period may include the following steps:

[0083] In step S30, the magnitude relationship between the correlation of the previous iteration and the correlation of the current iteration is determined, thereby determining the direction of the current update time period.

[0084] In step S31, if the correlation of the previous iteration is greater than or equal to the correlation of the current iteration, it means that the direction of the previous update time period is close to the optimization direction, so the update method of the previously selected update time period can be continued;

[0085] In step S32 , when the correlation of the previous iteration is less than the correlation of the current iteration, the updating method of the current updating time period is changed.

[0086] In this Figure 3 In the method shown, the method of updating the time period may include updating the time period according to formula (2) or according to formula (3),

[0087] T i+1 =T i +Δt, (2)

[0088] T i+1 =T i -Δt, (3)

[0089] Among them, T i+1 is the updated time period value, T i is the value of the time period before the update, and Δt is the unit update time.

[0090] In addition, considering that when switching the update method, in order to avoid falling into the problem of a local optimal solution, the switching frequency of the update method can be determined while switching the update method, and then it can be determined whether the switching frequency is greater than or equal to a preset frequency threshold. If it is greater than or equal to the frequency threshold, it means that the update method is repeatedly switching during each iteration and has fallen into a local optimal solution. In this case, the value of the unit update time can be adjusted when the update method is updated this time. Furthermore, in order to avoid the value of the unit update time being over-adjusted, when it is determined that the switching frequency is less than the frequency threshold, the unit update time can be adjusted back to the initial value.

[0091] Step S11 can be used to construct a multi-factor module matrix for the information communication system. The multi-factor module matrix can include multiple parameters of the information communication system. For example, the multi-factor module matrix can include module type, equipment, cumulative operating time, average response speed during the test period, average response speed during the operating period, non-response rate, etc.

[0092] Step S12 may be used to determine a stability index of the information communication system within each historical time period based on the failure frequency. The stability index may be determined based on the number of system failures, system response time, and number of system offline times within the historical time period. The specific method for determining the stability index may be various methods known to those skilled in the art, such as weighted calculation.

[0093] Step S13 can be used to take the multi-factor module matrix in the i-1th historical time period as input and the stability index in the i-th historical time period as output to determine the multi-factor attention mechanism. The specific method for determining the multi-factor attention mechanism can be various forms known to those skilled in the art. In one example of the present invention, the method for determining the multi-factor attention mechanism can include the following: Figure 4 The steps shown in Figure 4 In the method of determining the multi-factor attention mechanism, the method may include the following steps:

[0094] In step S40, the multi-factor attention mechanism is initialized;

[0095] In step S41, the multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as the standard output to calculate the deviation degree of the current multi-factor attention mechanism;

[0096] In step S42, it is determined whether the degree of deviation is greater than or equal to a preset degree threshold;

[0097] In step S43, if it is determined that the deviation degree is greater than or equal to the degree threshold, the multi-factor attention mechanism is updated according to the deviation degree, and the process returns to step S41;

[0098] In step S44, when it is judged that the degree of deviation is less than the degree threshold, the multi-factor attention mechanism is output.

[0099] In this Figure 4 In the method shown, the specific method for updating the multi-factor attention mechanism according to the degree of deviation in step S43 can be various forms known to those skilled in the art. In one example of the present invention, step S43 can further include the following: Figure 5 The method shown in Figure 5 In , the method of updating the multi-factor attention mechanism may include the following steps:

[0100] In step S50, it is determined whether there are any unselected row vectors in the current multi-factor attention mechanism;

[0101] In step S51, when it is determined that there are still unselected row vectors in the current multi-factor attention mechanism, an unselected row vector is randomly selected from the multi-factor attention mechanism as the row vector to be updated;

[0102] In step S52, it is determined whether the deviation degree when updating the row vector to be updated in the previous round is greater than the deviation degree calculated before the update;

[0103] In step S53, when it is determined that the deviation degree when updating the row vector to be updated in the previous round is less than or equal to the deviation degree calculated before the update, the row vector to be updated is updated using the corresponding trend matrix;

[0104] In step S54, when it is determined that the deviation degree calculated this time is greater than the deviation degree, the correction matrix of the corresponding trend matrix is ​​used to update the row vector to be updated, and the correction matrix is ​​used as the new trend matrix of the vector to be updated.

[0105] like Figure 5 The main idea of ​​the method for updating the multi-factor attention mechanism shown is to first randomly update the row vectors one by one, and record the trend matrix for the updated quality. The trend matrix can be used to represent the optimization direction of the multi-factor attention mechanism. Specifically, in this example Figure 5 In the method shown, step S50 determines whether the current update round has ended by judging whether there are still unselected row vectors in the current multi-factor attention mechanism. If it has ended, it is necessary to restart a new round of updates, that is, clear the set of all currently selected row vectors. If it has not ended, that is, there are still unselected row vectors in the current multi-factor attention mechanism, then the row vectors can be updated through steps S52 to S54. Among them, step S52 is used to determine whether the trend matrix recorded previously is the optimization direction. If so, the trend matrix is ​​directly used for updating. Otherwise, the correction matrix of the trend matrix can be used for updating. The specific forms of the trend matrix and the correction matrix can be various forms known to people in this field. In this example, the trend matrix can be expressed by the following formula (4),

[0106] G={a1,a2,a3,..}, (4)

[0107] Where G represents the trend matrix, a1, a2, and a3 represent the correction values ​​of each vector in the row vector. The correction matrix can be expressed using the following formula (5):

[0108] G ′ ={a1+δ 1 ,a2+δ 2 ,a3+δ 3 ,..}, (5)

[0109] Among them, G ′ represents the correction matrix, δ 1 , δ 2 , δ 3 Represents a random integer from 0 to 3.

[0110] In another aspect, the present invention further provides an information communication system fault location system that combines multi-factor judgment, the system including a processor configured to execute any of the above methods. Specifically, the method may include the following steps:

[0111] In step S10, the failure frequency of the information communication system in a historical time period is obtained;

[0112] In step S11, a multi-factor module matrix of the information communication system is constructed;

[0113] In step S12, a stability index of the information communication system in each historical time period is determined based on the fault frequency;

[0114] In step S13, the multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as output to determine the multi-factor attention mechanism;

[0115] In step S14, a multi-factor module matrix of the information communication system in the current time period is obtained;

[0116] In step S15, the stability index of the information communication system in the next time period is calculated based on the multi-factor module matrix and the multi-factor attention mechanism.

[0117] In this Figure 1 In the method shown, step S10 can be used to obtain the failure frequency of the information communication system in the historical time period. The failure frequency can be the cumulative number of failures of the information communication system in the historical time period, or the average number of failures of the information communication system per day in the historical time period, or the mode number of failures of the information communication system per day in the historical time period. The value of the time period can be determined in a variety of ways known to those skilled in the art, such as a manually set method. However, considering that the method provided by the present invention needs to ensure that the multi-factor module moment as input and the stability index as output are correlated, if the value of the time period is not properly selected, it will make the subsequent multi-factor attention mechanism difficult to iteratively calculate. Therefore, in a preferred example of the present invention, the method for determining the value of the time period may further include: Figure 2 The steps shown in Figure 2 In the method of determining the value of the time period, the method may include the following steps:

[0118] In step S20, the historical failure frequency of the information communication system is obtained;

[0119] In step S21, the value of the time period is initialized;

[0120] In step S22, the fault frequency and the multi-factor module matrix are determined according to the time period;

[0121] In step S23, the correlation between the fault frequency and the multi-factor module matrix is ​​determined;

[0122] In step S24, it is determined whether the correlation is greater than or equal to a preset value;

[0123] In step S25, if the correlation is greater than or equal to the preset value, the current time period is recorded as the optimal solution;

[0124] In step S26, when it is determined that the correlation is less than the preset value, the value of the time period is updated, and the process returns to the step of determining the fault frequency and the multi-factor module matrix according to the time period, that is, returns to step S22.

[0125] In this Figure 2 In the method shown, step S20 can be used to obtain the historical fault frequency of the information communication system. Step S21 can be used to initialize the value of the time period to form an initial solution. After the initial solution is determined, the fault frequency and the multi-factor module matrix can be determined according to the time period through step S22, and then the correlation between the fault frequency and the multi-factor module matrix can be determined in combination with step S23, and the threshold judgment of the correlation in step S24 can be used to determine whether the feature correlation between the fault frequency and the multi-factor module matrix meets the requirements. If the correlation is greater than or equal to the preset value, that is, the feature correlation meets the requirements, then the value of the current time period can be directly determined as the optimal solution. Otherwise, it is necessary to update the value of the time period and return to execute step S22 for re-judgment. Among them, the specific calculation method of the correlation can be a variety of forms known to people in this field. In a preferred example of the present invention, the correlation can be calculated using the following formula (1):

[0126] Calculate the correlation according to formula (1):

[0127]

[0128] Among them, S is the correlation, n is the number of time periods divided, B i+1 is the multi-factor module matrix of the i+1th time period, B i is the multi-factor module matrix of the i-th time period, f i is the fault frequency level in the i-th time period, f i-1 is the fault frequency level in the i-1th time period.

[0129] In addition, the method for updating the value of the time period can be various forms known to those skilled in the art. However, considering the operation efficiency of the algorithm, in one example of the present invention, the method can be as follows: Figure 3 Specifically, the method for updating the time period may include the following steps:

[0130] In step S30, the magnitude relationship between the correlation of the previous iteration and the correlation of the current iteration is determined, thereby determining the direction of the current update time period.

[0131] In step S31, if the correlation of the previous iteration is greater than or equal to the correlation of the current iteration, it means that the direction of the previous update time period is close to the optimization direction, so the update method of the previously selected update time period can be continued;

[0132] In step S32 , when the correlation of the previous iteration is less than the correlation of the current iteration, the updating method of the current updating time period is changed.

[0133] In this Figure 3 In the method shown, the method of updating the time period may include updating the time period according to formula (2) or according to formula (3),

[0134] T i+1 =T i +Δt, (2)

[0135] T i+1 =T i -Δt, (3)

[0136] Among them, T i+1 is the updated time period value, T i is the value of the time period before the update, and Δt is the unit update time.

[0137] In addition, considering that when switching the update method, in order to avoid falling into the problem of a local optimal solution, the switching frequency of the update method can be determined while switching the update method, and then it can be determined whether the switching frequency is greater than or equal to a preset frequency threshold. If it is greater than or equal to the frequency threshold, it means that the update method is repeatedly switching during each iteration and has fallen into a local optimal solution. In this case, the value of the unit update time can be adjusted when the update method is updated this time. Furthermore, in order to avoid the value of the unit update time being over-adjusted, when it is determined that the switching frequency is less than the frequency threshold, the unit update time can be adjusted back to the initial value.

[0138] Step S11 can be used to construct a multi-factor module matrix for the information communication system. The multi-factor module matrix can include multiple parameters of the information communication system. For example, the multi-factor module matrix can include module type, equipment, cumulative operating time, average response speed during the test period, average response speed during the operating period, non-response rate, etc.

[0139] Step S12 may be used to determine a stability index of the information communication system within each historical time period based on the failure frequency. The stability index may be determined based on the number of system failures, system response time, and number of system offline times within the historical time period. The specific method for determining the stability index may be various methods known to those skilled in the art, such as weighted calculation.

[0140] Step S13 can be used to take the multi-factor module matrix in the i-1th historical time period as input and the stability index in the i-th historical time period as output to determine the multi-factor attention mechanism. The specific method for determining the multi-factor attention mechanism can be various forms known to those skilled in the art. In one example of the present invention, the method for determining the multi-factor attention mechanism can include the following: Figure 4 The steps shown in Figure 4 In the method of determining the multi-factor attention mechanism, the method may include the following steps:

[0141] In step S40, the multi-factor attention mechanism is initialized;

[0142] In step S41, the multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as the standard output to calculate the deviation degree of the current multi-factor attention mechanism;

[0143] In step S42, it is determined whether the degree of deviation is greater than or equal to a preset degree threshold;

[0144] In step S43, if it is determined that the deviation degree is greater than or equal to the degree threshold, the multi-factor attention mechanism is updated according to the deviation degree, and the process returns to step S41;

[0145] In step S44, when it is judged that the degree of deviation is less than the degree threshold, the multi-factor attention mechanism is output.

[0146] In this Figure 4 In the method shown, the specific method for updating the multi-factor attention mechanism according to the degree of deviation in step S43 can be various forms known to those skilled in the art. In one example of the present invention, step S43 can further include the following: Figure 5 The method shown in Figure 5 In , the method of updating the multi-factor attention mechanism may include the following steps:

[0147] In step S50, it is determined whether there are any unselected row vectors in the current multi-factor attention mechanism;

[0148] In step S51, when it is determined that there are still unselected row vectors in the current multi-factor attention mechanism, an unselected row vector is randomly selected from the multi-factor attention mechanism as the row vector to be updated;

[0149] In step S52, it is determined whether the deviation degree when updating the row vector to be updated in the previous round is greater than the deviation degree calculated before the update;

[0150] In step S53, when it is determined that the deviation degree when updating the row vector to be updated in the previous round is less than or equal to the deviation degree calculated before the update, the row vector to be updated is updated using the corresponding trend matrix;

[0151] In step S54, when it is determined that the deviation degree calculated this time is greater than the deviation degree, the correction matrix of the corresponding trend matrix is ​​used to update the row vector to be updated, and the correction matrix is ​​used as the new trend matrix of the vector to be updated.

[0152] like Figure 5 The main idea of ​​the method for updating the multi-factor attention mechanism shown is to first randomly update the row vectors one by one, and record the trend matrix for the updated quality. The trend matrix can be used to represent the optimization direction of the multi-factor attention mechanism. Specifically, in this example Figure 5 In the method shown, step S50 determines whether the current update round has ended by judging whether there are still unselected row vectors in the current multi-factor attention mechanism. If it has ended, it is necessary to restart a new round of updates, that is, clear the set of all currently selected row vectors. If it has not ended, that is, there are still unselected row vectors in the current multi-factor attention mechanism, then the row vectors can be updated through steps S52 to S54. Among them, step S52 is used to determine whether the trend matrix recorded previously is the optimization direction. If so, the trend matrix is ​​directly used for updating. Otherwise, the correction matrix of the trend matrix can be used for updating. The specific forms of the trend matrix and the correction matrix can be various forms known to people in this field. In this example, the trend matrix can be expressed by the following formula (4),

[0153] G={a1,a2,a3,..}, (4)

[0154] Where G represents the trend matrix, a1, a2, and a3 represent the correction values ​​of each vector in the row vector. The correction matrix can be expressed using the following formula (5):

[0155] G ′ ={a1+δ 1 ,a2+δ 2 ,a3+δ 3 ,..}, (5)

[0156] Among them, G ′ represents the correction matrix, δ 1 , δ 2 , δ 3 Represents a random integer from 0 to 3.

[0157] Through the above-mentioned technical solution, the present invention provides a method and system for locating information and communication system faults that integrates multi-factor judgment. This method and system utilizes an attention mechanism to perform weighted calculations on a historical multi-factor module matrix, thereby determining the stability index of the information and communication system within a predetermined time period. Compared to existing technologies, the method and system provided by the present invention, which relies solely on weighted matrix calculations, avoids the use of complex model calculations, reduces design costs, and achieves higher computational efficiency.

[0158] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0159] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0160] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0162] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0163] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0164] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0165] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0166] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for locating faults in an information communication system by combining multi-factor judgment, characterized in that: The method comprises: Obtain the failure frequency of the information communication system in a historical period; Constructing a multi-factor module matrix of the information communication system; determining a stability index of the information communication system in each of the historical time periods according to the failure frequency; The multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as output to determine the multi-factor attention mechanism; Obtain the multi-factor module matrix of the information and communication system in the current time period; Calculating a stability index of the information communication system in a next time period based on the multi-factor module matrix and the multi-factor attention mechanism; Obtain the failure frequency of the information and communication system within a historical period, including: Obtaining historical failure frequencies of the information communication system; Initialize the value of the time period; Determining the fault frequency and the multi-factor module matrix according to the time period; Determining the correlation between the fault frequency and the multi-factor module matrix; Determining whether the correlation is greater than or equal to a preset value; If it is determined that the correlation is greater than or equal to the preset value, recording the current time period as the optimal solution; If it is determined that the correlation is less than the preset value, the value of the time period is updated, and the process returns to the step of determining the fault frequency and the multi-factor module matrix according to the time period.

2. The method according to claim 1, wherein: Determining the correlation between the fault frequency and the multi-factor module matrix includes: The correlation is calculated according to formula (1), ，（1） in, is the correlation, is the number of time periods divided, For the The multi-factor module matrix for each time period, For the The multi-factor module matrix for each time period, For the The fault frequency level in each time period, For the The fault frequency level in a time period.

3. The method according to claim 1, characterized in that Update the value of the time period, including: Determine the magnitude relationship between the correlation of the previous iteration and the correlation of this iteration; If the correlation degree of the previous iteration is greater than or equal to the correlation degree of the current iteration, continue to execute the updating method of updating the time period selected in the previous iteration; When the correlation degree of the previous iteration is less than the correlation degree of the current iteration, the updating method for updating the time period is changed.

4. The method according to claim 3, characterized in that The updating method includes: Update the time period according to formula (2), ，（2） in, is the value of the updated time period, is the value of the time period before the update, Update time for the unit; or Update the time period according to formula (3), ，（3）。 5. The method according to claim 4, characterized in that Update the value of the time period, including: Determining a switching frequency of the update method; Determining whether the switching frequency is greater than or equal to a preset frequency threshold; When it is determined that the switching frequency is greater than or equal to the frequency threshold, the value of the unit update time is adjusted when the update method is updated this time.

6. The method according to claim 5, characterized in that Adjust the value of the unit update time, including: When it is determined that the switching frequency is less than the frequency threshold, the unit update time is adjusted back to the initial value.

7. The method according to claim 1, characterized in that The multi-factor module matrix in the i-1th historical period is used as input and the stability index in the i-th historical period is used as output to determine the multi-factor attention mechanism, including: Initializing the multi-factor attention mechanism; The multi-factor module matrix in the i-1th historical time period is used as input, and the stability index in the i-th historical time period is used as the standard output to calculate the deviation degree of the current multi-factor attention mechanism; Determining whether the degree of deviation is greater than or equal to a preset degree threshold; If it is determined that the degree of deviation is greater than or equal to the degree threshold, updating the multi-factor attention mechanism according to the degree of deviation, and returning to the step of calculating the degree of deviation of the current multi-factor attention mechanism by taking the multi-factor module matrix in the i-1th historical time period as input and the stability index in the i-th historical time period as the standard output; When it is determined that the degree of deviation is less than the degree threshold, the multi-factor attention mechanism is output.

8. The method according to claim 7, characterized in that Updating the multi-factor attention mechanism according to the degree of deviation includes: Determine whether there are any unselected row vectors in the current multi-factor attention mechanism; When it is determined that there is still an unselected row vector in the current multi-factor attention mechanism, randomly select an unselected row vector from the multi-factor attention mechanism as the row vector to be updated; Determining whether the degree of deviation when updating the row vector to be updated in the previous round is greater than the degree of deviation calculated before the update; When it is determined that the deviation degree when updating the row vector to be updated in the previous round is less than or equal to the deviation degree calculated before the update, updating the row vector to be updated using the corresponding trend matrix; When it is determined that the deviation degree of this calculation is greater than the deviation degree, the row vector to be updated is updated using a correction matrix of the corresponding trend matrix, and the correction matrix is ​​used as a new trend matrix of the row vector to be updated.

9. An information communication system fault location system combining multi-factor judgment, characterized in that: The system comprises a processor configured to execute the method according to any one of claims 1 to 8.

Images