Anomaly detection method, device, detection equipment and computer readable storage medium

Abstract

The application is suitable for the technical field of communication equipment production, and provides an abnormality detection method, device, detection equipment and computer readable storage medium, comprising: obtaining verification data of a plurality of communication equipment, wherein the verification data comprises a calibration gain value; determining a reference gain value according to a mode of the calibration gain value; determining a reference power value corresponding to the reference gain value of the communication equipment on each station; determining an actual power value corresponding to the reference gain value of the communication equipment on each station; and judging whether the station is abnormal according to the actual power value and the reference power value. Through the above method, the detection efficiency of the communication equipment can be improved.

Description

Technical Field

[0001] This application belongs to the field of communication equipment manufacturing technology, and in particular relates to anomaly detection methods, devices, detection equipment, and computer-readable storage media. Background Technology

[0002] In communication equipment, whether the actual transmitted power meets the standard is crucial to whether the communication equipment can successfully perform its functions. Therefore, ensuring that the actual transmitted power meets the standard is an important part of the communication equipment testing process.

[0003] In existing testing processes, the actual power output of communication equipment is typically monitored based on the calibration gain value provided by the factory, and the monitoring results are used to determine whether the communication equipment is malfunctioning. However, this method has too low detection efficiency and cannot meet user needs. Summary of the Invention

[0004] This application provides an anomaly detection method, apparatus, detection equipment, and computer-readable storage medium, which can solve the problem of low detection efficiency in existing communication devices.

[0005] In a first aspect, embodiments of this application provide an anomaly detection method, including:

[0006] Acquire verification data from multiple communication devices, the verification data including calibration gain values;

[0007] The reference gain value is determined based on the mode of the calibration gain value;

[0008] Determine the reference power value corresponding to the reference gain value for the communication equipment at each workstation;

[0009] Determine the actual power value of the communication equipment at each workstation corresponding to the reference gain value;

[0010] The presence of any abnormality at the workstation is determined based on the actual power value and the reference power value.

[0011] Secondly, embodiments of this application provide an anomaly detection device, including:

[0012] The verification data acquisition module is used to acquire verification data from multiple communication devices, including calibration gain values.

[0013] A reference gain value determination module is used to determine a reference gain value based on the mode of the calibration gain value;

[0014] A reference power value determination module is used to determine the reference power value corresponding to the reference gain value of the communication equipment at each workstation.

[0015] The actual power value determination module is used to determine the actual power value of the communication equipment at each workstation corresponding to the reference gain value;

[0016] An anomaly detection module is used to determine whether there is an anomaly at the workstation based on the actual power value and the reference power value.

[0017] Thirdly, embodiments of this application provide a detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0019] Fifthly, embodiments of this application provide a computer program product that, when run on a testing device, causes the testing device to execute the method described in the first aspect above.

[0020] The beneficial effects of the embodiments of this application compared with the prior art are:

[0021] In this embodiment, since the mode of the calibration gain value refers to the value with a clear central tendency in the statistical distribution of the calibration gain value, determining the reference gain value based on the mode of the calibration gain value can reduce the number of adjustments to the gain value to be monitored, thereby increasing the speed of obtaining the reference power value and the actual power value used for workstation anomaly judgment, and thus improving the detection efficiency of the communication equipment. Furthermore, since this embodiment determines the reference gain value based on the calibration gain value, then determines the reference power value and the actual power value based on the reference gain value, and judges whether the workstation is abnormal based on the reference power value and the actual power value, it is not necessary to determine the starting power of the communication equipment and calculate the actual line loss of the communication equipment when judging whether the workstation is abnormal. Since the starting power of the communication equipment is difficult to determine accurately, judging whether the workstation is abnormal based on the reference power value and the actual power value can improve the convenience of anomaly judgment, thereby improving the detection efficiency of the communication equipment. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0023] Figure 1 This is a schematic diagram illustrating the process from initial power generation to actual power generation according to an embodiment of this application;

[0024] Figure 2This is a flowchart illustrating an anomaly detection method provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram illustrating a linear relationship between gain and power values ​​according to an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of the structure of an anomaly detection device provided in one embodiment of this application;

[0027] Figure 5 This is a schematic diagram of the structure of the testing equipment provided in the embodiments of this application. Detailed Implementation

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0029] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0030] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0031] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0033] Example 1:

[0034] When a factory manufactures communication equipment, it provides corresponding verification data for these devices so that the actual power value of the communication equipment can be monitored based on the calibration gain value in the verification data.

[0035] During testing, the prototype emits a specified power based on the calibration gain value set in the chip. This power is attenuated by the line loss of the wires within the topology to obtain the actual power output. The general process is as follows: Figure 1 As shown.

[0036] Since the calibration gain value is the same for communication equipment of the same model (such as wireless radio frequency equipment), the actual power (i.e., the actual power value) of different communication equipment of the same model usually varies after the initial power is attenuated by the line loss of the conductor in the topology. Therefore, it may be difficult to effectively detect communication equipment by directly relying on the calibration gain value. Thus, it is necessary to adjust the corresponding calibration gain value for different communication equipment before monitoring the actual power, resulting in low detection efficiency and difficulty in meeting user needs.

[0037] To improve the detection efficiency of communication equipment, this application provides an anomaly detection method.

[0038] In this detection method, after acquiring the verification data of multiple communication devices, a reference gain value is determined based on the mode of the calibration gain values ​​in these verification data. The corresponding reference power value and actual power value are then determined based on the reference gain value. Finally, the presence of any abnormality at the corresponding workstation is determined based on the reference power value and the actual power value.

[0039] Since the mode of the calibration gain value refers to the value that has a clear central tendency in the statistical distribution of the calibration gain value, determining the reference gain value and the corresponding reference power value and actual power value based on the mode of the calibration gain value can reduce the number of adjustments to the gain value to be monitored, thereby improving the detection efficiency of communication equipment.

[0040] The anomaly detection method provided in the embodiments of this application is described below with reference to the accompanying drawings.

[0041] Figure 2 A flowchart illustrating an anomaly detection method provided in an embodiment of this application is shown, applied to a testing system, and is described in detail below:

[0042] Step S21: Obtain verification data from multiple communication devices, including calibration gain values.

[0043] Specifically, when the testing system performs anomaly detection on various communication devices on the production line, it can acquire the verification data corresponding to the communication devices on the production line within a first time period as the verification data for the aforementioned multiple communication devices. This first time period can be set according to actual conditions, such as 30 minutes, or acquiring the verification data corresponding to the communication devices on the production line within the previous 30 minutes every 5 minutes.

[0044] In this application embodiment, the data to be verified includes a calibration gain value. In some embodiments, a communication device corresponds to at least one calibration gain value. Further, the data to be verified in this application embodiment also includes the power value corresponding to the calibration gain value.

[0045] Table 1 below records a type of verification data generated by calibrating communication equipment using a one-point calibration method.

[0046] Table 1:

[0047]

[0048] In this embodiment of the application, the test system reads a specified field from the raw data in Table 1 generated by the factory. For example, it reads the data in Table 1 with the field "[PWRCAL]" to obtain the verification data of the communication device. For example, when the verification data is "M1|N1.M2|N2", it indicates that the calibration gain value is "M1" and the power value corresponding to "M1" is "N1". When the calibration gain value is "M2", the power value corresponding to "M2" is "N2".

[0049] Table 2 below records a type of verification data generated by calibrating communication equipment using the five-point calibration method.

[0050] Table 2:

[0051]

[0052] In this embodiment of the application, the test system reads a specified field from the raw data in Table 2 generated by the factory. For example, it reads the data in Table 2 with the field "[PWRCAL]" to obtain the verification data of the communication device. For example, when the verification data is "M3|N3.M4|N4", it indicates that the calibration gain value is "M3" and the power value corresponding to "M3" is "N3". The calibration gain value is "M4" and the power value corresponding to "M4" is "N4".

[0053] In this embodiment, to facilitate statistics and ensure the accuracy of the obtained anomaly judgment results, the verification data of the communication equipment is obtained according to the part number (i.e., the model of the communication equipment), production line, workstation, antenna, and channel as granularities. That is, in this embodiment, the verification data of the communication equipment at the same granularity is analyzed to obtain the anomaly judgment result of the communication equipment at that granularity. For example, assuming that the communication equipment has models I and II, production lines have production line 1 and production line 2, workstations have workstation 1 and workstation 2, antennas have antenna 1 and antenna 2, and channels have channel 1 and channel 2, then the verification data of different models (i.e., model I and model II) of communication equipment at different production lines (production line 1 and production line 2), different workstations (workstation 1 and workstation 2), different antennas (antenna 1 and antenna 2), and different channels (channel 1 and channel 2) are obtained respectively. Subsequently, the verification data obtained at the same granularity (i.e., the same model, production line, workstation, antenna, and channel) at the current time are used to determine whether there is an anomaly at the workstation at the current time. Since the verification data of the same granularity but acquired at different times is compared to determine whether the workstation is abnormal, the interference between verification data of different granularities can be avoided, thereby improving the accuracy of the abnormality judgment results.

[0054] In some embodiments, the data to be verified is data filtered out from the target production line and / or from prototypes (i.e., communication devices) that failed the complete machine test. The target production line includes rework lines and repair lines. Since most of the prototypes on rework and repair lines are defective, and prototypes that failed the complete machine test are also defective, and the abnormal values ​​of defective prototypes can interfere with the anomaly judgment results, filtering out the data to be verified from rework and repair lines can improve the accuracy of the subsequent anomaly judgment results.

[0055] Step S22: Determine the reference gain value based on the mode of the above calibration gain value.

[0056] Specifically, the mode of the calibration gain value in each data set to be verified is found, and this mode is determined as the reference gain value of the communication device corresponding to these data sets.

[0057] In some embodiments, to improve the speed of determining the reference gain value, the method for determining the mode of the calibration gain value can be selected according to the calibration method. For example, when the calibration method is one-point calibration, since one-point calibration does not adjust the gain value test multiple times, there is less selectable data. Therefore, the first gain value of each data to be verified can be directly selected, and then the mode of each gain value obtained within the first time period can be calculated. That is, when the calibration method is one-point calibration, the mode of each first gain value is used as the reference gain value, which can ensure both the accuracy and speed of determining the reference gain value. When the calibration method is five-point calibration, the gain value is adjusted multiple times for testing (i.e., each step increases the gain value to obtain the corresponding power value; the testing logic is to continuously increase the gain value until the condition of "five power levels, each differing by approximately 3" is met). Therefore, the data characteristics are: the gain value increases arithmetically, the power value also increases, there are multiple sets of data, the gain value growth path may be different for different machines, and the number of tests may be different for different machines). To address this, for each reported data point to be verified, we select the third-to-last gain value and then determine the mode of these gain values ​​as the reference gain value. Since the third-to-last gain value has relatively high coverage (many data points to be verified have gain values ​​around this point), and the linear consistency between the gain value and the power value is good and the fit is relatively accurate near the third-to-last gain value, the reference gain value can be quickly and accurately determined based on the third-to-last gain value of each data point to be verified when the calibration method is five-point calibration.

[0058] Step S23: Determine the reference power value corresponding to the reference gain value of the communication equipment at each workstation.

[0059] The reference power value refers to the power value that is not actually monitored by the test system.

[0060] Specifically, for each piece of data to be verified, a reference power value corresponding to the reference gain value of the communication device is determined. For example, assuming that the data to be verified itself includes a reference gain value and a power value corresponding to the base station gain value, the power value corresponding to the reference gain value can be directly obtained from the data to be verified as the reference power value of the reference gain value.

[0061] Step S24: Determine the actual power value of the communication equipment at each workstation corresponding to the aforementioned reference gain value.

[0062] In this embodiment, the power value of the communication device at each workstation is monitored at the reference gain value to obtain the actual power value of the communication device at each workstation.

[0063] Step S25: Determine whether there is any abnormality in the above-mentioned workstation based on the above-mentioned actual power value and the above-mentioned reference power value.

[0064] Specifically, when the actual power value of the communication equipment differs significantly from the reference power value, it indicates an anomaly at that workstation. This anomaly may include a malfunction in the communication equipment itself, or it may include a malfunction in the detection equipment at that workstation, such as a damaged probe.

[0065] In this embodiment, since the mode of the calibration gain value refers to the value with a clear central tendency in the statistical distribution of the calibration gain value, determining the reference gain value based on the mode of the calibration gain value can reduce the number of adjustments to the gain value to be monitored, thereby increasing the speed of obtaining the reference power value and the actual power value used for workstation anomaly judgment, and thus improving the detection efficiency of the communication equipment. Furthermore, since this embodiment determines the reference gain value based on the calibration gain value, then determines the reference power value and the actual power value based on the reference gain value, and judges whether the workstation is abnormal based on the reference power value and the actual power value, it is not necessary to determine the starting power of the communication equipment and calculate the actual line loss of the communication equipment when judging whether the workstation is abnormal. Since the starting power of the communication equipment is difficult to determine accurately, judging whether the workstation is abnormal based on the reference power value and the actual power value can improve the convenience of anomaly judgment, thereby improving the detection efficiency of the communication equipment.

[0066] In some embodiments, considering that both the communication equipment itself and the detection equipment at the workstation require manual intervention, after an anomaly is detected at the workstation, anomaly information is displayed on the target terminal. This anomaly information includes an identifier of the workstation with the anomaly. Here, the target terminal can be a mobile phone belonging to a specified user.

[0067] In this embodiment of the application, since abnormal information is displayed on the target terminal and the abnormal information includes the identifier of the abnormal workstation, it is beneficial for the user to quickly determine the abnormal workstation based on the displayed abnormal information, thereby improving the speed of processing abnormal workstations.

[0068] In some embodiments, step S23 above includes:

[0069] If the data to be verified does not include a calibration gain value equal to the aforementioned reference gain value, then the reference power value corresponding to the aforementioned reference gain value is calculated according to the data fitting algorithm.

[0070] Of course, if the data to be verified includes a reference power value corresponding to the aforementioned reference gain value, then the required reference power value can be directly extracted from the data to be verified.

[0071] Specifically, since the reference gain value is determined by taking the mode of the calibration gain values ​​of multiple data points to be verified, there may be cases where the calibration gain value of some data points to be verified is not equal to the reference gain value. Correspondingly, these data points to be verified will not include the reference power value corresponding to the reference gain value. In this case, it is necessary to calculate the reference power value corresponding to the reference gain value through a data fitting algorithm. Figure 3 As shown, since the gain and power values ​​are usually linearly related, the reference power value corresponding to the reference gain value can be accurately determined by determining the ratio of the calibration gain value to the power value in a certain data set to be verified. For example, assuming that the data set to be verified includes a calibration gain value of 9 and a power value of 12, and the reference gain value is 12, then first calculate the ratio of the calibration gain value to the power value "9 / 12", and then calculate the reference power value corresponding to the reference gain value "12*12 / 9=16".

[0072] In some embodiments, step S25 includes:

[0073] A1. Calculate the average value of the above reference power values ​​to obtain the average reference power.

[0074] Specifically, the average value of the reference power is calculated using part number, production line, work station, antenna, channel, etc. as granularities.

[0075] A2. Calculate the average value of the actual power of the communication equipment at the above workstations to obtain the average actual power.

[0076] Specifically, the average value of the actual power is calculated according to the part number, production line, work station, antenna, channel, etc. For example, for every three communication devices tested, the actual power values ​​of the first ten communication devices are extracted and the average value of the actual power values ​​of the first ten communication devices is calculated.

[0077] A3. If the difference between the above-mentioned average actual power and the above-mentioned average reference power is greater than the preset average difference threshold, then the workstation corresponding to the above-mentioned average actual power is determined to be abnormal.

[0078] Specifically, the average actual power value of the same granularity is compared with the average reference power value. If the difference between the average actual power value and the average reference power value is greater than the preset threshold for the difference between the average values, it indicates that there is an abnormality in the detection equipment at the workstation corresponding to the actual power value, or that there is an abnormality in the communication equipment corresponding to each actual power value.

[0079] In this embodiment, since the actual power average is calculated from multiple actual power values, that is, the actual power average corresponds to multiple communication devices, each time the difference between the actual power average and the reference power average is used to determine whether there is an abnormality in the workstation corresponding to the actual power average, it is equivalent to performing a judgment operation to determine whether there is an abnormality in multiple communication devices and the workstations corresponding to the multiple communication devices, thereby greatly improving the detection efficiency of the communication devices.

[0080] In some embodiments, step S25 includes:

[0081] B1. Calculate the standard deviation of the above reference power value to obtain the reference power standard deviation value.

[0082] The standard deviation is the square root of the arithmetic mean of the squares of the deviations from the mean. That is, by first calculating the average value of the reference power value, the standard deviation of the reference power value can be calculated based on the average value of the reference power value and each reference power value.

[0083] B2. Calculate the standard deviation of the actual power value of the communication equipment at the above workstations to obtain the actual power standard deviation.

[0084] The calculation of the standard deviation of the actual power value is similar to the calculation of the standard deviation of the reference power value. The difference is that one is calculated using the actual power value and the other is calculated using the reference power value. This will not be elaborated on here.

[0085] B3. If the difference between the above-mentioned actual power standard deviation and the above-mentioned reference power standard deviation is greater than the preset standard deviation threshold, then the workstation corresponding to the above-mentioned actual power value is determined to be abnormal.

[0086] Specifically, the standard deviation of the actual power at the same granularity is compared with the standard deviation of the reference power. If the difference between the standard deviation of the actual power and the standard deviation of the reference power is greater than the preset standard deviation threshold, it indicates that the detection equipment at the workstation corresponding to the actual power is abnormal, or that the communication equipment corresponding to each actual power is abnormal.

[0087] In this embodiment, since the actual power standard deviation is calculated from multiple actual power values, that is, the actual power standard deviation corresponds to multiple communication devices, each time the difference between the actual power standard deviation and the reference power standard deviation is used to determine whether there is an abnormality in the workstation corresponding to the actual power standard deviation, it is equivalent to performing a judgment operation to determine whether there is an abnormality in multiple communication devices and the workstations corresponding to the multiple communication devices, thereby greatly improving the detection efficiency of the communication devices.

[0088] In some embodiments, after step S24 described above, the method further includes:

[0089] C1. Calculate the average difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation to obtain the average line loss corresponding to the above-mentioned workstation.

[0090] C2. If the difference between the average line loss corresponding to the first workstation and the average line loss corresponding to multiple second workstations is greater than a preset first difference threshold, then the first workstation is determined to be abnormal, wherein the second workstation is a different workstation from the first workstation, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

[0091] In this embodiment, if the average line loss of a certain workstation differs significantly from the average line loss of multiple workstations (or all workstations) producing the same model of communication equipment, it indicates that the topology of that workstation exhibits an overall deviation anomaly due to uncompensated line loss. This overall deviation anomaly may be caused by a deviation in the line loss calibration of that workstation or by damage to the devices at that workstation. Since different workstations test different communication devices of the same model (i.e., communication devices with the same model, antenna, channel, etc.), if neither the workstation itself nor the communication device itself is abnormal, the average line loss corresponding to different workstations should be similar. Therefore, once it is determined that the average line loss of a certain workstation differs significantly from the average line loss of other workstations, it indicates that the workstation or the communication device itself is likely to have an anomaly. That is, the above method can increase the probability of detecting an abnormal workstation.

[0092] In some embodiments, after step S24 described above, the method further includes:

[0093] D1. Calculate the difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation to obtain the line loss corresponding to the above-mentioned workstation.

[0094] D2. If, within the second time period, the difference between the maximum and minimum line loss corresponding to the first workstation is greater than a preset second difference threshold, and the difference between the maximum and minimum line loss corresponding to the first workstation is greater than the average of the differences between the maximum and minimum line loss corresponding to multiple second workstations, then the first workstation is determined to be abnormal. In this case, the second workstation is a different workstation from the first workstation, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

[0095] In this embodiment, the maximum and minimum line losses for each workstation are statistically analyzed. The difference between the maximum and minimum line losses for the same workstation is calculated. If the difference between the maximum and minimum line losses for a certain workstation within a certain period (such as a second time period set according to actual conditions) exceeds a preset second difference threshold, it indicates that the workstation experiences significant vertical fluctuations within the second time period. Furthermore, if the difference between the maximum and minimum line losses for this workstation is significantly larger than the average difference between the maximum and minimum line losses for multiple workstations (or all workstations) producing the same model, i.e., the vertical fluctuation amplitude of this workstation differs significantly from the average fluctuation amplitude of multiple workstations producing the same model of communication equipment within the second time period, it indicates that the topology of this workstation exhibits an uncompensated line loss instability anomaly. The main causes of uncompensated line loss instability anomalies include poor device contact and device damage. For example, if a probe is damaged, the pressing position will be different each time, resulting in different uncalibrated line losses each time. Therefore, the above method can increase the probability of detecting abnormal workstations.

[0096] In some embodiments, after step S24 described above, the method further includes:

[0097] E1. Calculate the difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation to obtain the line loss corresponding to the above-mentioned workstation.

[0098] E2. If, within the third time period, the difference in line loss between the various stations corresponding to the first station gradually increases or decreases, then the first station is determined to be abnormal.

[0099] In this embodiment of the application, if the uncompensated line loss shows a significant upward or downward trend in the topology of a certain workstation without recalibrating the line loss, it indicates that the topology has experienced a gradual shift in line loss. The main reason for the gradual shift in line loss is the gradual deterioration of the performance of consumable components. In other words, the above method can increase the probability of detecting abnormal workstations.

[0100] In some embodiments, after step S24 described above, the method further includes:

[0101] For each workstation, if the absolute value of the difference between the actual power value corresponding to the first workstation and the average value of the actual power value corresponding to the first workstation within the fourth time period is greater than the preset third difference threshold, then the first workstation is determined to be abnormal.

[0102] Specifically, if a sudden change in the actual power value of a prototype at a certain workstation is detected—that is, a sudden increase or decrease in the actual power value of the communication equipment—then it is determined that the workstation itself or the communication equipment at that workstation is malfunctioning. Since a sudden change in the actual power value of the communication equipment indicates a malfunction in the communication equipment or the testing equipment at the workstation, the above method can increase the probability of detecting malfunctioning workstations.

[0103] It should be noted that the first, second, third, and fourth durations mentioned above can be equal or unequal; no limitation is made here.

[0104] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0105] Example 2:

[0106] Corresponding to the anomaly detection method in the above embodiments, Figure 4 A structural block diagram of the anomaly detection device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0107] Reference Figure 4 The anomaly detection device 4 includes: a data acquisition module 41, a reference gain value determination module 42, a reference power value determination module 43, an actual power value determination module 44, and an anomaly judgment module 45. Wherein:

[0108] The verification data acquisition module 41 is used to acquire the verification data of the communication device obtained within a first time period, including the calibration gain value.

[0109] The reference gain value determination module 42 is used to determine the reference gain value based on the mode of the above calibration gain value;

[0110] The reference power value determination module 43 is used to determine the reference power value corresponding to the above-mentioned reference gain value for the communication equipment at each workstation.

[0111] The actual power value determination module 44 is used to determine the actual power value of the communication equipment at each workstation corresponding to the above-mentioned reference gain value;

[0112] The anomaly detection module 45 is used to determine whether there is an anomaly at the above workstation based on the above actual power value and the above reference power value.

[0113] In this embodiment, since the mode of the calibration gain value refers to the value with a clear central tendency in the statistical distribution of the calibration gain value, determining the reference gain value based on the mode of the calibration gain value can reduce the number of adjustments to the gain value to be monitored, thereby increasing the speed of obtaining the reference power value and the actual power value used for workstation anomaly judgment, and thus improving the detection efficiency of the communication equipment. Furthermore, since this embodiment determines the reference gain value based on the calibration gain value, then determines the reference power value and the actual power value based on the reference gain value, and judges whether the workstation is abnormal based on the reference power value and the actual power value, it is not necessary to determine the starting power of the communication equipment and calculate the actual line loss of the communication equipment when judging whether the workstation is abnormal. Since the starting power of the communication equipment is difficult to determine accurately, judging whether the workstation is abnormal based on the reference power value and the actual power value can improve the convenience of anomaly judgment, thereby improving the detection efficiency of the communication equipment.

[0114] In some embodiments, considering that both the communication equipment itself and the detection equipment at the workstation are faulty, manual intervention is required, therefore, the fault detection device 4 further includes:

[0115] The abnormal information display module is used to display abnormal information on the target terminal after it is determined that there is an abnormality at the workstation. The abnormal information includes the identifier of the workstation with the abnormality.

[0116] In some embodiments, the reference power value determination module 43 is specifically used for:

[0117] If the data to be verified does not include the reference power value corresponding to the reference gain value, then the reference power value corresponding to the reference gain value is calculated according to the data fitting algorithm.

[0118] In some embodiments, the above-mentioned anomaly detection module 45 includes:

[0119] The reference power average calculation unit is used to calculate the average value of the above reference power values ​​to obtain the reference power average.

[0120] The actual power average calculation unit is used to calculate the average value of the actual power of the communication equipment at the above workstations to obtain the actual power average.

[0121] The first workstation anomaly determination unit is used to determine that the workstation corresponding to the above-mentioned average actual power is abnormal if the difference between the above-mentioned average actual power and the above-mentioned average reference power is greater than a preset average difference threshold.

[0122] In some embodiments, the above-mentioned anomaly detection module 45 includes:

[0123] The reference power standard deviation calculation unit is used to calculate the standard deviation of the above reference power value to obtain the reference power standard deviation value.

[0124] The actual power standard deviation calculation unit is used to calculate the standard deviation of the actual power value of the communication equipment at the above workstation, and obtain the actual power standard deviation.

[0125] The second workstation anomaly determination unit is used to determine that the workstation corresponding to the actual power value is abnormal if the difference between the actual power standard deviation and the reference power standard deviation is greater than a preset standard deviation threshold.

[0126] In some embodiments, the anomaly detection device 4 further includes:

[0127] The average line loss calculation module corresponding to each workstation is used to calculate the average difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation, so as to obtain the average line loss corresponding to the above-mentioned workstation.

[0128] The overall offset anomaly determination module is used to determine that the first workstation is abnormal if the difference between the average line loss corresponding to the first workstation and the average line loss corresponding to multiple second workstations is greater than a preset first difference threshold. The second workstations are different from the first workstations, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

[0129] In some embodiments, the anomaly detection device 4 further includes:

[0130] The line loss calculation module corresponding to each workstation is used to calculate the difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation, and obtain the line loss corresponding to the above-mentioned workstation.

[0131] The unstable anomaly determination module is used to determine that the first workstation is abnormal if, within a second time period, the difference between the maximum and minimum line loss corresponding to the first workstation is greater than a preset second difference threshold, and the difference between the maximum and minimum line loss corresponding to the first workstation is greater than the average of the differences between the maximum and minimum line loss corresponding to multiple second workstations. The second workstation is a different workstation from the first workstation, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

[0132] In some embodiments, the anomaly detection device 4 further includes:

[0133] The line loss calculation module corresponding to each workstation is used to calculate the difference between the above-mentioned reference gain value and the above-mentioned actual power value for each workstation, and obtain the line loss corresponding to the above-mentioned workstation.

[0134] The up and down trend anomaly determination module is used to determine that the first workstation is abnormal if the difference in line loss of each workstation gradually increases or decreases within the third time period.

[0135] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0136] Example 3:

[0137] Figure 5 This is a schematic diagram of the structure of a testing device provided in one embodiment of this application. Figure 5 As shown, the detection device 5 of this embodiment includes: at least one processor 50 ( Figure 5 The diagram shows only one processor, memory 51, and computer program 52 stored in the memory 51 and executable on at least one processor 50. When the processor 50 executes the computer program 52, it implements the steps in any of the above method embodiments.

[0138] The testing device 5 can be a desktop computer, laptop, handheld computer, or cloud server, etc. This testing device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will understand that... Figure 5 This is merely an example of the detection device 5 and does not constitute a limitation on the detection device 5. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0139] The processor 50 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0140] In some embodiments, the memory 51 may be an internal storage unit of the detection device 5, such as a hard disk or memory of the detection device 5. In other embodiments, the memory 51 may be an external storage device of the detection device 5, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the detection device 5. Furthermore, the memory 51 may include both internal and external storage units of the detection device 5. The memory 51 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0141] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0142] This application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0143] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0144] This application provides a computer program product that, when run on a testing device, enables the testing device to implement the steps described in the above-described method embodiments.

[0145] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing / detection device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0146] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0147] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0148] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An anomaly detection method, characterized in that, include: Acquire verification data from multiple communication devices, the verification data including calibration gain values; Select the corresponding calibration gain value according to the calibration method of the communication device, and determine the reference gain value according to the mode of the selected calibration gain value; Determine the reference power value corresponding to the reference gain value for the communication equipment at each workstation; Determine the actual power value of the communication equipment at each workstation corresponding to the reference gain value; The presence of any abnormality at the workstation is determined based on the actual power value and the reference power value.

2. The anomaly detection method as described in claim 1, characterized in that, Determining the reference power value corresponding to the reference gain value for the communication equipment at each workstation includes: If the data to be verified does not include a calibration gain value equal to the reference gain value, then the reference power value corresponding to the reference gain value is calculated according to the data fitting algorithm.

3. The anomaly detection method as described in claim 1, characterized in that, The step of determining whether the workstation is abnormal based on the actual power value and the reference power value includes: Calculate the average value of the reference power values ​​to obtain the average reference power. Calculate the average value of the actual power of the communication devices at the workstation to obtain the average actual power. If the difference between the actual average power and the reference average power is greater than a preset average difference threshold, then the workstation corresponding to the actual average power is determined to be abnormal.

4. The anomaly detection method as described in claim 1, characterized in that, The step of determining whether the workstation is abnormal based on the actual power value and the reference power value includes: Calculate the standard deviation of the reference power value to obtain the reference power standard deviation value; Calculate the standard deviation of the actual power value of the communication equipment at the workstation to obtain the actual power standard deviation; If the difference between the actual power standard deviation and the reference power standard deviation is greater than a preset standard deviation threshold, then the workstation corresponding to the actual power value is determined to be abnormal.

5. The anomaly detection method according to any one of claims 1 to 4, characterized in that, After determining the actual power value corresponding to the reference gain value for the communication equipment at each workstation, the method further includes: The average difference between the reference gain value and the actual power value is calculated for each workstation to obtain the average line loss corresponding to that workstation; If the difference between the average line loss corresponding to the first workstation and the average line loss corresponding to multiple second workstations is greater than a preset first difference threshold, then the first workstation is determined to be abnormal, wherein the second workstation is a different workstation from the first workstation, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

6. The anomaly detection method according to any one of claims 1 to 4, characterized in that, After determining the actual power value corresponding to the reference gain value for the communication equipment at each workstation, the method further includes: The difference between the reference gain value and the actual power value is calculated for each workstation to obtain the line loss corresponding to that workstation; If, within the second time period, the difference between the maximum and minimum line loss corresponding to the first workstation is greater than a preset second difference threshold, and the difference between the maximum and minimum line loss corresponding to the first workstation is greater than the average of the differences between the maximum and minimum line loss corresponding to multiple second workstations, then the first workstation is determined to be abnormal. Here, the second workstation is a different workstation from the first workstation, and the model of the communication device on the second workstation is the same as the model of the communication device on the first workstation.

7. The anomaly detection method according to any one of claims 1 to 4, characterized in that, After determining the actual power value corresponding to the reference gain value for the communication equipment at each workstation, the method further includes: The difference between the reference gain value and the actual power value is calculated for each workstation to obtain the line loss corresponding to that workstation; If, within the third time period, the difference in line loss between the various stations corresponding to the first station gradually increases or decreases, then the first station is determined to be abnormal.

8. An anomaly detection device, characterized in that, include: The verification data acquisition module is used to acquire verification data from multiple communication devices, including calibration gain values. The reference gain value determination module is used to select the corresponding calibration gain value for the calibration method of the communication device, and determine the reference gain value based on the mode of the selected calibration gain value. A reference power value determination module is used to determine the reference power value corresponding to the reference gain value of the communication equipment at each workstation. The actual power value determination module is used to determine the actual power value of the communication equipment at each workstation corresponding to the reference gain value; An anomaly detection module is used to determine whether there is an anomaly at the workstation based on the actual power value and the reference power value.

9. A detection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images