5G repeater performance detection system and detection method

Abstract

The invention discloses a 5G repeater performance detection system and detection method, relates to the technical field of communication, and solves the technical problem that the working efficiency of a repeater is reduced due to the fact that potential or sudden problems of the repeater cannot be found in time due to the fact that the adaptability of current 5G repeater performance detection is insufficient. The data acquisition module is used for acquiring a plurality of detection data; the test planning module is used for acquiring a plurality of historical data of the repeater through the database; generating an influence degree coefficient of each detection item according to the historical data; obtaining item characteristic data corresponding to each detection item, and generating a relevance score between the detection items according to the item characteristic data; generating a project detection scheme according to the relevance score and the influence degree coefficient; the performance test module is used for detecting each detection item according to the item detection scheme and generating a detection result of the corresponding detection item according to the detection data; the efficiency of performance detection is effectively improved, and the working efficiency of the repeater is ensured at the same time.

Description

Technical Field

[0001] The present application belongs to the field of communication technology and relates to communication technology, specifically a 5G repeater performance detection system and detection method. Background Art

[0002] With the rapid development of 5G communication technology, 5G repeaters, as key equipment for signal amplification and transmission, are crucial to the entire 5G network in terms of performance stability and reliability. 5G repeaters are affected by many factors during operation, such as equipment aging, parts maintenance, ambient temperature, humidity, electromagnetic interference, etc. These factors may cause changes in repeater performance.

[0003] The prior art (invention patent with announcement number CN114374443B) discloses a repeater signal monitoring device, system and method, which belongs to the field of repeater technology. When the base station transmitter communicates with the terminal receiver through the repeater, this solution is designed to monitor the signal transmission in each link, and can quickly and accurately navigate whether the signal transmission in the communication process is abnormal. In order to avoid wasting resources in the process, when performing signal transmission abnormality monitoring, a method of starting from the starting point of the transmitter to the end point of the receiver is adopted to avoid the signal transmission abnormality monitoring of subsequent links continuing to start when a certain link in the middle is abnormal, resulting in ineffective waste of resources.

[0004] The above-mentioned repeater signal detection method detects the RF transmission signal and RF reception signal of the repeater; the detection items are single, and the overall evaluation effect of the repeater is poor; and the existing method of overall evaluation of the repeater is often to conduct a comprehensive performance evaluation regularly; most of the evaluation results are normal, resulting in most of the evaluation work being wasted; at the same time, due to the high transmission frequency, the penetration ability of 5G signals is relatively weak, resulting in the need for more repeaters to enhance signal coverage; in actual applications, due to the significant differences in the operating environment and operating status of 5G repeaters at different times, these differences have different effects on the performance of the repeaters; the traditional strategy of regular comprehensive performance testing is inefficient; it is difficult to promptly discover potential or sudden problems of the repeater, which may lead to a decrease in the working efficiency of the repeater and even affect the stability and reliability of the entire 5G network. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a 5G repeater performance detection system and detection method, which are used to solve the technical problem that the current 5G repeater performance detection has insufficient adaptability, making it impossible to timely detect potential or sudden problems of the repeater, resulting in a decrease in the working efficiency of the repeater.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a 5G repeater performance detection system, including: a data acquisition module, a test planning module, a performance test module and a database;

[0007] The data acquisition module: acquires a number of test data according to the project test plan through the data acquisition device connected thereto;

[0008] The test planning module: obtains several historical data of the repeater through the database; generates the influence degree coefficient of each test item according to the historical data; obtains the project characteristic data corresponding to each test item, and generates the correlation score between each test item according to the project characteristic data; generates the project test plan according to the correlation score and the influence degree coefficient;

[0009] The performance testing module: tests each test item according to the project test plan, obtains test data, and generates test results of the corresponding test items according to the test data.

[0010] The present application obtains several historical data of the repeater, generates the influence coefficient of each detection item according to the historical data; marks the detection items with the influence score greater than the set influence threshold as the detection items; obtains the project characteristic data corresponding to each detection item, and generates the correlation score between each detection item according to the project characteristic data; generates the project detection plan according to the correlation score and the influence coefficient of each detection item; detects each detection item according to the project detection plan; obtains the detection data, and generates the detection result of the corresponding detection item according to the detection data; realizes the adaptive detection of the performance of the repeater according to the actual use environment and working status of the repeater, so that the potential or sudden problems of the repeater can be discovered in time, which effectively improves the efficiency of performance detection, and at the same time improves the working efficiency of the repeater.

[0011] Preferably, generating the influence coefficient of each detection item according to historical data includes:

[0012] Obtain historical data of several related components corresponding to the inspection project;

[0013] Extract several environmental project data and work project data corresponding to each recording period in the historical usage data; generate each component influence coefficient according to the several environmental project data and work project data of each recording period corresponding to the project component; generate the influence degree coefficient of the detection item according to the influence coefficient of each component corresponding to the detection item; obtain the influence degree coefficient of each detection item in turn.

[0014] Preferably, generating the influence coefficient of each component according to a plurality of environmental project data and work project data of each recording period corresponding to the project component includes:

[0015] Mark the environment project data and work project data as HX respectively mni and GX mnj ; n is the number of the recording period, m is the number of the relevant component; i is the number of the environmental project data; j is the number of the work project data;

[0016] According to the environmental project data and work project data, the formula is:

[0017]

[0018] Calculate the component influence coefficient BY corresponding to the relevant component numbered m m Among them, ZH mi DH is the environmental optimum data corresponding to the environmental item data numbered i in the relevant component numbered m; i is the environmental unit data corresponding to the environmental project data numbered i; αi is the proportional coefficient corresponding to the environmental project data numbered i; ZG mj is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m; mj DG is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m; j is the work item unit data corresponding to the work item data numbered j; βj is the proportional coefficient corresponding to the work item data numbered j.

[0019] Preferably, generating the influence degree coefficient of the detection item according to the influence coefficient of each component corresponding to the detection item includes:

[0020] Get the influence coefficient of each component corresponding to the test item BY m ;

[0021] By formula Calculate the influence coefficient XY of the corresponding test item; where ε m is the weight coefficient corresponding to the relevant component numbered m; m=1, 2, ..., M, where M is the total number of relevant components corresponding to the detection item.

[0022] Preferably, generating the correlation scores between the various test items according to the item characteristic data includes:

[0023] Obtain project feature data corresponding to a number of inspection items, extract the inspection environment requirements, inspection steps and inspection equipment requirements in the feature data of each item; input the inspection environment requirements, inspection steps and inspection equipment requirements corresponding to any two inspection items into a correlation analysis model to obtain the correlation scores corresponding to the two inspection items, and obtain the correlation scores between the various inspection items in turn; the correlation analysis model is obtained through artificial intelligence model training.

[0024] Preferably, the correlation analysis model is obtained by training an artificial intelligence model, including:

[0025] Acquire project characteristic data of several test items and correlation scores between the test items through a database; integrate the several correlation scores and the test environment requirements, test steps and test equipment requirements in the corresponding two project characteristic data into several groups of training data and test data;

[0026] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data, ultimately obtaining a project analysis test model whose input is the test environment requirements, test steps and test equipment requirements in two test items, and whose output is the corresponding correlation score; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0027] Preferably, generating a project detection scheme according to the correlation score and the influence coefficient includes:

[0028] Obtain the impact score of each detection item, and mark the detection items whose impact score is greater than the set impact threshold as items to be detected;

[0029] Obtain the correlation scores between the project to be detected with the largest impact score and the remaining projects to be detected; mark the projects to be detected with correlation scores greater than a set correlation threshold as related projects to be detected; integrate the related projects to be detected and the project to be detected with the largest impact score into a first detection project group;

[0030] Obtain the project to be detected with the largest impact score among the remaining projects to be detected, mark the projects to be detected whose correlation scores are greater than the set correlation threshold among the remaining projects to be detected as the corresponding related projects to be detected, and integrate the related projects to be detected with the project to be detected with the largest impact score among the remaining projects to be detected into a second detection project group;

[0031] Acquire several test item groups in sequence; acquire the test items in each test item group and the test plans corresponding to each related test item; and integrate the test plans corresponding to each test item in each test item group into a project test plan in sequence.

[0032] In this application, test items with a high degree of relevance are grouped into the same test item group, and the test items are tested in the order of the project groups, thereby saving time during the test process and effectively improving the test efficiency when inexperienced or inexperienced employees are conducting the test.

[0033] Preferably, the step of generating a test result of a corresponding test item according to the test data includes:

[0034] Extract the test value in the test data and determine whether the test value is within the qualified range corresponding to the test item; if yes, set the test result of the test item to normal; if not, set the test result of the test item to abnormal.

[0035] Another aspect of the present application provides a 5G repeater performance detection method, comprising the following steps:

[0036] Step 1: Obtain some historical data of the repeater;

[0037] Step 2: Generate the influence coefficient of each test item based on historical data;

[0038] Step 3: Mark the detection items whose impact score is greater than the set impact threshold as items to be detected;

[0039] Step 4: Obtain project characteristic data corresponding to each project to be detected, and generate correlation scores between each project to be detected based on the project characteristic data;

[0040] Step 5: Generate a project testing plan based on the correlation score and impact coefficient of each project to be tested;

[0041] Step 6: Test each test item according to the project test plan;

[0042] Step 7: Obtain test data and generate test results for corresponding test items based on the test data.

[0043] Preferably, generating the correlation scores between the items to be detected according to the item characteristic data includes:

[0044] Extract the testing environment requirements, testing steps and testing equipment requirements from the characteristic data of each project; input the testing environment requirements, testing steps and testing equipment requirements corresponding to any two projects to be tested into the correlation analysis model to obtain the correlation scores corresponding to the two projects to be tested, and obtain the correlation scores between the projects to be tested in turn; the correlation analysis model is obtained through artificial intelligence model training.

[0045] Preferably, generating a project detection scheme according to the correlation score and influence coefficient of each project to be detected includes:

[0046] Obtain the correlation scores between the project to be detected with the largest impact score and the remaining projects to be detected; mark the projects to be detected with correlation scores greater than a set correlation threshold as related projects to be detected; integrate the related projects to be detected and the project to be detected with the largest impact score into a first detection project group;

[0047] Obtain the project to be detected with the largest impact score among the remaining projects to be detected, mark the projects to be detected whose correlation scores are greater than the set correlation threshold among the remaining projects to be detected as the corresponding related projects to be detected, and integrate the related projects to be detected with the project to be detected with the largest impact score among the remaining projects to be detected into a second detection project group;

[0048] Acquire several test item groups in sequence; acquire the test items in each test item group and the test plans corresponding to each related test item; and integrate the test plans corresponding to each test item in each test item group into a project test plan in sequence.

[0049] Compared with the prior art, the beneficial effects of this application are:

[0050] 1. The present application obtains several historical data of a repeater station, and generates an influence coefficient of each detection item according to the historical data; the detection items whose influence score is greater than a set influence threshold are marked as items to be detected; the project characteristic data corresponding to each item to be detected are obtained, and the correlation score between each item to be detected is generated according to the project characteristic data; a project detection plan is generated according to the correlation score and the influence coefficient of each item to be detected; each detection item is detected according to the project detection plan; the detection data is obtained, and the detection result of the corresponding detection item is generated according to the detection data; and adaptive detection of the performance of the repeater station is realized according to the actual use environment and working status of the repeater station, so that potential or sudden problems of the repeater station can be discovered in time, which effectively improves the efficiency of performance detection and the working efficiency of the repeater station.

[0051] 2. In this application, the test items with a high degree of relevance are divided into the same test item group, and the project tests are carried out in the order of the project groups, so as to save time in the test process and effectively improve the test efficiency when inexperienced or insufficiently experienced employees conduct tests. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 This is a module connection diagram of the 5G repeater performance detection system in this application;

[0054] Figure 2 Schematic diagram of the steps of the 5G repeater performance detection method in this application. DETAILED DESCRIPTION

[0055] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0056] See also Figure 1 , the first aspect embodiment of the present application provides a 5G repeater performance detection system and detection method, including: a data acquisition module, a test planning module, a performance test module and a database;

[0057] Data acquisition module: obtains some test data according to the project test plan through the data acquisition equipment connected to it; the test data is the data obtained when testing a certain performance of the 5G repeater in the project test plan; different test items have different test data;

[0058] Test planning module: obtain some historical data of the repeater through the database; historical data are the environment and work-related data recorded since the last performance test of the repeater; generate the influence degree coefficient of each test item based on the historical data, the influence degree coefficient is the change of some related performance of the repeater caused by equipment aging and parts maintenance during the operation of the repeater, the larger the influence degree coefficient, the greater the impact of the operation of the repeater on the performance test item, and the performance test item needs to be tested; obtain the project characteristic data corresponding to each test item, the project characteristic data is the relevant data of the test item test, including the test environment requirements, test steps and test equipment requirements, etc.; generate the correlation score between each test item based on the project characteristic data, the correlation score is the score generated according to the correlation between each test item, the higher the correlation, the higher the corresponding correlation score; generate the project test plan based on the correlation score and the influence degree coefficient;

[0059] Performance testing module: Generates detection signals according to the detection plan, notifies relevant personnel to test each detection item according to the project detection plan, obtains detection data, and generates detection results for the corresponding detection items based on the detection data.

[0060] This embodiment obtains several historical data of the repeater and generates the influence coefficient of each detection item according to the historical data; the detection items with the influence score greater than the set influence threshold are marked as items to be detected; the project characteristic data corresponding to each item to be detected are obtained, and the correlation score between each item to be detected is generated according to the project characteristic data; the project detection plan is generated according to the correlation score and the influence coefficient of each item to be detected; each detection item is detected according to the project detection plan; the detection data is obtained, and the detection result of the corresponding detection item is generated according to the detection data; the performance of the repeater is adaptively detected according to the actual use environment and working status of the repeater, so that potential or sudden problems of the repeater can be discovered in time, which effectively improves the efficiency of performance detection and improves the working efficiency of the repeater.

[0061] Generating an influence degree coefficient of each inspection item according to the historical data, including: obtaining historical data of a number of relevant components corresponding to the inspection item, the historical data including historical use data and maintenance data;

[0062] Extract several environmental project data and work project data corresponding to each recording period in the historical usage data, where the environmental project data is the data recorded for a corresponding environmental project, and the environmental projects include relevant environmental data such as temperature, humidity and electromagnetic interference; the work project data is the relevant data recorded when the corresponding component is working, including monitoring data of the relevant components, such as current, voltage and power; generate each component influence coefficient according to several environmental project data and work project data of each recording period corresponding to the project component; the component influence coefficient is the influence of each environmental project in a recording period and the working state of the equipment on the equipment performance, and the higher the component influence coefficient, the more it means that the working environment of the component in the recording period is not suitable or the working state of the component is not suitable; the impact on the component is greater; generate the influence degree coefficient of the corresponding detection item according to the influence coefficient of each component corresponding to the detection item; obtain the influence degree coefficient of each detection item in turn.

[0063] Generate the influence coefficient of each component according to several environmental project data and work project data of each recording period corresponding to the project component, including:

[0064] Mark the environment project data and work project data as HX respectively mni and GX mnj; n is the number of the recording period, m is the number of the relevant component; i is the number of the environmental item data; j is the number of the working item data; it can be understood that each environmental item of the same component corresponds to one environmental item data in each recording period; each working item corresponds to one working item data in each recording period; environmental items include environmental factors such as ambient temperature and ambient humidity that affect the operation of the corresponding equipment of the repeater; working items include working voltage and current and other items related to the operation of the internal components of the repeater;

[0065] According to the environmental project data and work project data, the formula is:

[0066]

[0067] Calculate the component influence coefficient BY corresponding to the relevant component numbered m m Among them, ZH mi DH is the environmental optimum data corresponding to the environmental item data numbered i in the relevant component numbered m, and the environmental optimum data is the environmental value where the relevant component is least affected by the environmental item; i is the environmental unit data corresponding to the environmental project data numbered i; the specific value is set according to expert experience, which is used to adjust the comparability between different environmental projects and remove units; αi is the proportional coefficient corresponding to the environmental project data numbered i, and the specific value is set according to experience. The proportional coefficient can be set considering the degree of influence of different environmental projects on the components. The greater the degree of influence, the larger the value of the proportional coefficient should be set; ZG mj is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m, and the optimal data of the work item is the working value with the least influence of the relevant component on the work item; ZG mj DG is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m; j is the work item unit data corresponding to the work item data numbered j; βj is the proportional coefficient corresponding to the work item data numbered j. The specific value is set based on experience. The proportional coefficient can be set based on the degree of influence of different work items on the components. The greater the influence, the larger the value of the proportional coefficient should be.

[0068] This embodiment calculates the component influence coefficient of the working environment of the component and the working state of the component in each recording period on the aging or performance of the component itself through the above formula; when the relevant component works under inappropriate environmental conditions, or when the relevant component works under inappropriate conditions, the greater the aging impact it is subjected to, the larger the corresponding component influence coefficient is set; otherwise, the smaller it is set.

[0069] It can be understood that when an environmental item has no impact on a related component, the environmental item data corresponding to the related component is 0, and the optimal environmental data is also 0; when a work item has no impact on a related component, the work item data corresponding to the related component is 0, and the optimal work item data is also 0.

[0070] Generate the influence degree coefficient of the inspection item according to the influence coefficient of each component corresponding to the inspection item, including: obtaining the influence coefficient of each component corresponding to the inspection item BY m ;

[0071] By formula Calculate the influence coefficient XY of the corresponding test item; where ε m is the weight coefficient corresponding to the relevant component numbered m, m=1, 2, ..., M, M is the total number of relevant components corresponding to the detection item; the value of the weight coefficient can be set according to expert experience, specifically referring to the importance of the relevant components to the detection item. The higher the importance, the larger the corresponding weight coefficient is set; it can also be obtained in the following way: obtain component parameters of several components inside the 5G repeater, and construct digital twin models corresponding to the corresponding components according to the component parameters to obtain component models; obtain the working relationship between the various components, and construct a 5G repeater digital twin model corresponding to the detection item according to the working relationship and the various component models; the 5G repeater digital twin model is a digital twin model that can simulate the work of the 5G repeater; simulate the 5G repeater digital twin model to obtain the test values ​​of the corresponding performance of each detection item;

[0072] Lower the gain of a set ratio of a component model in the 5G repeater digital twin model, simulate the 5G repeater digital twin model to obtain the component impact test value of the corresponding performance of each test item; obtain the component impact test value corresponding to each component in turn;

[0073] Obtain the test value corresponding to the detection item and the component impact test value corresponding to each relevant component in the detection item; mark the ratio of the component impact test value corresponding to each relevant component to the test value as the project impact degree of the relevant component; obtain the project impact degree corresponding to each relevant item of the detection item in turn; normalize the project impact degree of each relevant component of the same detection item, and mark the project impact degree of each relevant component after normalization as the weight coefficient of the corresponding relevant component in the detection item; obtain the weight coefficient of each project component corresponding to each detection item in turn; if the detection item is output power, the corresponding relevant components include power amplifier, low noise amplifier and filter, etc. In this embodiment, the gain of the relevant components is reduced by 15% in the digital twin model of the 5G repeater, that is, the gain of the low noise amplifier and the filter is ensured not to change, and the power amplifier is adjusted to 85% of the original gain; the output power at this time is obtained, and the ratio of the output power at this time to the original output power is marked as the project impact degree of the power amplifier; and then other relevant components are reduced in turn to obtain the project impact degree of each relevant component.

[0074] In this embodiment, the component influence coefficients of each component of the test item are weighted and summed up through the above formula to obtain the comprehensive influence coefficient of each component, which is used to express the degree to which the performance corresponding to the test item is affected. The larger the influence coefficient, the greater the possibility that the corresponding performance is affected and the greater the degree of the impact; the more necessary it is to test the item corresponding to the performance.

[0075] Generate correlation scores between various test items according to project characteristic data, including: obtaining project characteristic data corresponding to several test items, extracting test environment requirements, test steps and test equipment requirements in the feature data of each project; the test environment requirements are the requirements for various environmental factors when testing the performance corresponding to the test item; the test steps are the operating steps when testing the corresponding test items; the test equipment requirements are the test equipment required when testing the test items; the test environment requirements, test steps and test equipment requirements corresponding to any two test items are input into the correlation analysis model to obtain the correlation scores corresponding to the two test items, and the correlation scores between the various test items are obtained in turn; the correlation analysis model is obtained through artificial intelligence model training.

[0076] The correlation analysis model is obtained through artificial intelligence model training, including:

[0077] The project characteristic data of several test items and the correlation scores between the test items are obtained through the database. The correlation score is the expert's score of the correlation between the two test items based on the test environment requirements, the duplication and correlation of the test steps and the test equipment between the two test items; the more similar the test environment requirements, the more repeated the test steps and the test equipment, the higher the corresponding correlation score; a high correlation score indicates that the two test items can be tested successively; specifically, the test items of the 5G repeater station include the nominal maximum linear output power test, the automatic level control test, the maximum gain and error test, and the frequency error test, etc. The test steps in the project characteristic data corresponding to the nominal maximum linear output power test include:

[0078] S1: Turn off the uplink or downlink of the TDD band for testing, and the FDD band is tested in normal mode; specifically, when measuring the downlink output power, the uplink of the TDD band is turned off; when measuring the uplink output power, the downlink of the TDD band is turned off;

[0079] S2: Set the signal generator to the center carrier frequency point in the working frequency band within the working frequency range of the device under test, and generate the modulation signal NR-TM3.1a {3500MHz: 100MHz NR signal; 2100MHz: 50MHz NR signal; 800MHz: 15MHz NR signal} and E-TM3.1 {1800MHz: 20MHz LTE signal};

[0080] S3: Set the repeater gain to the maximum gain;

[0081] S4: Adjust the signal source level until the output power of the device under test reaches the ALC control point, back off 1dB, and then increase the power in 0.2dB steps to the maximum linear output power; the power displayed on the spectrum analyzer should meet the tolerance range of the maximum output rated power;

[0082] S5: Record the output level and input power level of the repeater;

[0083] Testing equipment requirements include: signal source, isolator, attenuator, spectrum analyzer;

[0084] Testing environment requirements: environment with little electromagnetic interference.

[0085] The detection steps in the project characteristic data corresponding to the automatic level control test include:

[0086] S1: Turn off the uplink or downlink of the TDD band for testing, and the FDD band is tested in normal mode; specifically, when measuring the downlink output power, the uplink of the TDD band is turned off; when measuring the uplink output power, the downlink of the TDD band is turned off;

[0087] S2: Set the signal source to the center frequency point within the operating frequency range to generate the modulation signals NR-TM3.1a {3500MHz: 100MHz NR signal; 2100MHz: 50MHz NR signal; 800MHz: 15MHz NR signal} and E-TM3.1 {1800MHz: 20MHz LTE signal};

[0088] S3: Set the repeater gain to the maximum gain;

[0089] S4: Adjust the level of the signal source until the output power of the repeater reaches the maximum output power;

[0090] S5: record the output power of the repeater;

[0091] S6: Increase the output signal level of the signal source in 1dB steps until it increases by 10dB, and use a spectrum analyzer to test the output power of the repeater, starting from ALC control until the maximum input power increases by 10dB, and record the carrier output power value;

[0092] S7: Continue to increase the signal generator level to 20dB (if the signal source power is not enough, add a power amplifier). Use a 5G NR signal analyzer to measure and record the output power of the repeater. It should be kept within ±2dB of the maximum transmission power or turned off.

[0093] Testing equipment requirements include: signal source, isolator, attenuator, spectrum analyzer;

[0094] Testing environment requirements: environment with little electromagnetic interference.

[0095] The detection steps in the project characteristic data corresponding to the frequency error test include:

[0096] S1: Set the gain of the device under test to the maximum gain;

[0097] S2: Set the signal generator to the center carrier frequency within the operating frequency band of the device under test, and generate the modulation signals NR-TM3.1a {3500MHz: 100MHz NR signal; 2100MHz: 50MHz NR signal; 800MHz: 15MHz NR signal} and E-TM3.1 {1800MHz: 20MHz LTE signal};

[0098] S3: Adjust the level of the signal source until the output power of the device under test reaches the maximum linear output power;

[0099] S4: Test the frequency deviation between the input signal and the output signal.

[0100] Testing equipment requirements include: signal source, isolator, straight-line isolation head, attenuator, frequency meter;

[0101] Testing environment requirements: environment with little electromagnetic interference.

[0102] It can be seen that the test environment requirements, test steps and test equipment repeatability of the nominal maximum linear output power test and the automatic level control test are very high, so the correlation score between the nominal maximum linear output power test and the automatic level control test is higher; while the correlation score between the nominal maximum linear output power test and the frequency error test is lower.

[0103] Integrate a number of correlation scores and the corresponding testing environment requirements, testing steps and testing equipment requirements in two project feature data into a number of sets of training data and test data;

[0104] The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data, ultimately obtaining a project analysis test model whose input is the test environment requirements, test steps and test equipment requirements in two test items, and whose output is the corresponding correlation score; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0105] Generate a project detection plan according to the correlation score and the impact coefficient, including: obtaining the impact score of each detection project, marking the detection project with an impact score greater than a set impact threshold as a detection project;

[0106] Obtain the correlation scores between the project to be detected with the largest impact score and the remaining projects to be detected; mark the projects to be detected with correlation scores greater than a set correlation threshold as related projects to be detected; integrate the related projects to be detected and the project to be detected with the largest impact score into a first detection project group;

[0107] Obtain the project to be detected with the largest impact score among the remaining projects to be detected, mark the projects to be detected whose correlation scores are greater than the set correlation threshold among the remaining projects to be detected as the corresponding related projects to be detected, and integrate the related projects to be detected with the project to be detected with the largest impact score among the remaining projects to be detected into a second detection project group;

[0108] Acquire several test item groups in sequence; acquire the test items in each test item group and the test plans corresponding to each related test item; and integrate the test plans corresponding to each test item in each test item group into a project test plan in sequence.

[0109] In this embodiment, the detection items with a high degree of relevance are grouped into the same detection item group, and the item detection is performed in the order of the item group, so that time is saved in the detection process and the detection efficiency is effectively improved when inexperienced or insufficiently experienced employees perform the detection.

[0110] Generate the test results of the corresponding test items according to the test data, including: extracting the test value in the test data, and judging whether the test value is within the qualified range corresponding to the test item; if yes, setting the test result of the test item as normal; if not, setting the test result of the test item as abnormal.

[0111] See also Figure 2 Another aspect of the present application provides a 5G repeater performance detection method, comprising the following steps:

[0112] Step 1: Obtain some historical data of the repeater;

[0113] Step 2: Generate the influence coefficient of each test item based on historical data;

[0114] Step 3: Mark the detection items whose impact score is greater than the set impact threshold as items to be detected;

[0115] Step 4: Obtain project characteristic data corresponding to each project to be detected, and generate correlation scores between each project to be detected based on the project characteristic data;

[0116] Step 5: Generate a project testing plan based on the correlation score and impact coefficient of each project to be tested;

[0117] Step 6: Test each test item according to the project test plan;

[0118] Step 7: Obtain test data and generate test results for corresponding test items based on the test data.

[0119] Generate correlation scores between each item to be tested based on the item characteristic data, including:

[0120] Extract the testing environment requirements, testing steps and testing equipment requirements from the characteristic data of each project; input the testing environment requirements, testing steps and testing equipment requirements corresponding to any two projects to be tested into the correlation analysis model to obtain the correlation scores corresponding to the two projects to be tested, and obtain the correlation scores between the projects to be tested in turn; the correlation analysis model is obtained through artificial intelligence model training.

[0121] Generate a project testing plan based on the correlation score and impact coefficient of each project to be tested, including:

[0122] Obtain the correlation scores between the project to be detected with the largest impact score and the remaining projects to be detected; mark the projects to be detected with correlation scores greater than a set correlation threshold as related projects to be detected; integrate the related projects to be detected and the project to be detected with the largest impact score into a first detection project group;

[0123] Obtain the project to be detected with the largest impact score among the remaining projects to be detected, mark the projects to be detected whose correlation scores are greater than the set correlation threshold among the remaining projects to be detected as the corresponding related projects to be detected, and integrate the related projects to be detected with the project to be detected with the largest impact score among the remaining projects to be detected into a second detection project group;

[0124] Acquire several test item groups in sequence; acquire the test items in each test item group and the test plans corresponding to each related test item; and integrate the test plans corresponding to each test item in each test item group into a project test plan in sequence.

[0125] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0126] How this application works:

[0127] The present application obtains several historical data of the repeater, generates the influence coefficient of each detection item according to the historical data; marks the detection items with the influence score greater than the set influence threshold as the detection items; obtains the project characteristic data corresponding to each detection item, and generates the correlation score between each detection item according to the project characteristic data; generates the project detection plan according to the correlation score and the influence coefficient of each detection item; detects each detection item according to the project detection plan; obtains the detection data, and generates the detection result of the corresponding detection item according to the detection data; realizes the adaptive detection of the performance of the repeater according to the actual use environment and working status of the repeater, so that the potential or sudden problems of the repeater can be discovered in time, which effectively improves the efficiency of the performance detection, and ensures the working efficiency of the repeater.

[0128] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. 5G repeater performance detection system, characterized by: include: Data acquisition module, test planning module, performance testing module and database; The data acquisition module: acquires a number of test data according to the project test plan through the data acquisition device connected thereto; The test planning module: obtains several historical data of the repeater through the database; generates the influence degree coefficient of each test item according to the historical data; obtains the project characteristic data corresponding to each test item, and generates the correlation score between each test item according to the project characteristic data; generates the project test plan according to the correlation score and the influence degree coefficient; The performance testing module: tests each test item according to the project test plan, obtains test data, and generates test results of the corresponding test items according to the test data.

2. The 5G repeater performance detection system according to claim 1, characterized in that: The generation of the influence coefficient of each test item according to the historical data includes: Acquire historical data of several relevant components corresponding to the inspection items, wherein the historical data includes historical usage data and maintenance data; Extract several environmental project data and work project data corresponding to each recording period in the historical usage data; generate each component influence coefficient according to several environmental project data and work project data of each recording period corresponding to the project component; generate the influence degree coefficient of the corresponding inspection project according to the influence coefficient of each component corresponding to the inspection project; obtain the influence degree coefficient of each inspection project in turn.

3. The 5G repeater performance detection system according to claim 2, characterized in that: The generating of each component influence coefficient according to a plurality of environmental project data and work project data of each recording period corresponding to the project component includes: Mark the environment project data and work project data as HX respectively mni and GX mnj ; n is the number of the recording period, m is the number of the relevant component; i is the number of the environmental project data; j is the number of the work project data; According to the environmental project data and work project data, the formula is: Calculate the component influence coefficient BY corresponding to the relevant component numbered m m Among them, ZH mi DH is the environmental optimum data corresponding to the environmental item data numbered i in the relevant component numbered m; i is the environmental unit data corresponding to the environmental project data numbered i; αi is the proportional coefficient corresponding to the environmental project data numbered i; ZG mj is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m; mj DG is the optimal data of the work item corresponding to the environmental item data numbered j in the relevant component numbered m; j is the work item unit data corresponding to the work item data numbered j; βj is the proportional coefficient corresponding to the work item data numbered j.

4. The 5G repeater performance detection system according to claim 2, characterized in that: The generating the influence degree coefficient of the detection item according to the influence coefficient of each component corresponding to the detection item comprises: Get the influence coefficient of each component corresponding to the test item BY m ; By formula Calculate the influence coefficient XY of the corresponding test item; where ε m is the weight coefficient corresponding to the relevant component numbered m; m=1, 2, ..., M, where M is the total number of relevant components corresponding to the detection item.

5. The 5G repeater performance detection system according to claim 1, characterized in that: The step of generating the correlation scores between the various detection items according to the item characteristic data includes: Obtain project feature data corresponding to a number of inspection items, extract the inspection environment requirements, inspection steps and inspection equipment requirements in the feature data of each item; input the inspection environment requirements, inspection steps and inspection equipment requirements corresponding to any two inspection items into a correlation analysis model to obtain the correlation scores corresponding to the two inspection items, and obtain the correlation scores between the various inspection items in turn; the correlation analysis model is obtained through artificial intelligence model training.

6. The 5G repeater performance detection system according to claim 5, characterized in that: The correlation analysis model is obtained through artificial intelligence model training, including: Acquire project characteristic data of several test items and correlation scores between the test items through a database; integrate the several correlation scores and the test environment requirements, test steps and test equipment requirements in the corresponding two project characteristic data into several groups of training data and test data; The artificial intelligence model is trained using training data, and the trained artificial intelligence model is tested using test data, ultimately obtaining a project analysis test model whose input is the test environment requirements, test steps and test equipment requirements in two test items, and whose output is the corresponding correlation score; wherein the artificial intelligence model includes a BP neural network model and an RBF neural network model.

7. The 5G repeater performance detection system according to claim 1, characterized in that: The project detection scheme is generated according to the correlation score and the influence coefficient, including: Obtain the impact score of each detection item, and mark the detection items whose impact score is greater than the set impact threshold as items to be detected; Obtain the correlation scores between the project to be detected with the largest impact score and the remaining projects to be detected; mark the projects to be detected with correlation scores greater than a set correlation threshold as related projects to be detected; integrate the related projects to be detected and the project to be detected with the largest impact score into a first detection project group; Obtain the project to be detected with the largest impact score among the remaining projects to be detected, mark the projects to be detected whose correlation scores are greater than the set correlation threshold among the remaining projects to be detected as the corresponding related projects to be detected, and integrate the related projects to be detected with the project to be detected with the largest impact score among the remaining projects to be detected into a second detection project group; Acquire several test item groups in sequence; acquire the test items in each test item group and the test plans corresponding to each related test item; and integrate the test plans corresponding to each test item in each test item group into a project test plan in sequence.

8. The 5G repeater performance detection system according to claim 1, characterized in that: Generating the test results of the corresponding test items according to the test data includes: Extract the test value in the test data and determine whether the test value is within the qualified range corresponding to the test item; if yes, set the test result of the test item to normal; if not, set the test result of the test item to abnormal.

9. A 5G repeater performance detection method, applied to a 5G repeater performance detection system in any one of claims 1 to 8; characterized in that: The following steps are involved: Step 1: Obtain some historical data of the repeater; Step 2: Generate the influence coefficient of each test item based on historical data; Step 3: Mark the detection items whose impact score is greater than the set impact threshold as items to be detected; Step 4: Obtain project characteristic data corresponding to each project to be detected, and generate correlation scores between each project to be detected based on the project characteristic data; Step 5: Generate a project testing plan based on the correlation score and impact coefficient of each project to be tested; Step 6: Test each test item according to the project test plan; Step 7: Obtain test data and generate test results for corresponding test items based on the test data.

10. The 5G repeater performance detection method according to claim 9, characterized in that: The step of generating the correlation scores between the items to be detected according to the item characteristic data includes: Extract the testing environment requirements, testing steps and testing equipment requirements from the characteristic data of each project; input the testing environment requirements, testing steps and testing equipment requirements corresponding to any two projects to be tested into the correlation analysis model to obtain the correlation scores corresponding to the two projects to be tested, and obtain the correlation scores between the projects to be tested in turn; the correlation analysis model is obtained through artificial intelligence model training.

Images