Interference positioning method and device for wireless communication, and electronic device

By combining variational autoencoders and multi-classifier models with the fusion processing of signal coverage and geographic location information, the problem of low accuracy and efficiency in interference localization in wireless communication is solved, and accurate identification and efficient localization of multiple interference types are achieved.

CN115347963BActive Publication Date: 2024-11-12CHINA TELECOM CORP LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210989296.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-17
Publication Date
2024-11-12
Estimated Expiration
2042-08-17

AI Technical Summary

Technical Problem

Existing technologies have low accuracy and efficiency in locating wireless communication interference, making it difficult to effectively identify and locate interference sources.

Method used

A combination model of variational autoencoder and multiple classifiers is adopted to obtain interference feature data of the target cell, identify the interference category, and perform fusion processing by combining signal coverage and geographical location information to determine the location of the interference source.

Benefits of technology

It improves the accuracy and efficiency of interference localization, enables accurate identification of multiple interference types, reduces the occupation of manual resources, and is suitable for complex wireless communication scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115347963B_ABST
    Figure CN115347963B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method and device for locating interference in wireless communication, and an electronic device, and relates to the field of wireless communication technology. The method includes obtaining interference feature data of a target cell; identifying the interference category result of the target cell according to the interference feature data; when the interference category includes an external interference source, determining the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage of the target cell and the first cell; and fusing the geographical location information of the multiple second cells according to the measurement data of the multiple second cells in the interference area to determine the location of the interference source of the target cell. The present disclosure can solve the problems of low accuracy and low efficiency of interference positioning in wireless communication.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of wireless communications, and in particular to a method and device for locating interference in wireless communications, and an electronic device. Background Art

[0002] For wireless communications, interference during communication is a key factor affecting wireless network quality and user perception. Interference detection plays an important role in reducing call drop rates, load balancing, and improving Internet access speeds.

[0003] In the related art, interference detection and positioning are mostly completed through manual carpet search, which has the problems of low interference positioning accuracy, low interference detection and positioning efficiency, and time-consuming and labor-intensive.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present disclosure is to provide a method and device for locating interference in wireless communications, and an electronic device, thereby solving the problem of low accuracy and low efficiency in locating interference in wireless communications to a certain extent.

[0006] According to a first aspect of the present disclosure, a method for interference positioning of wireless communication is provided, the method comprising: obtaining interference characteristic data of a target cell; identifying an interference category result of the target cell according to the interference characteristic data; the interference category result comprising one or more interference categories; when the interference category result comprises the interference category of an external interference source, determining an interference area where the external interference source is located according to an overlapping area of ​​signal coverage between the target cell and a first cell; the first cell is a neighboring cell having the same interference category as the target cell; obtaining measurement data of a plurality of second cells within the interference area, the measurement data comprising geographic location information of the second cells; and according to the measurement data, fusing the geographic location information of the plurality of second cells to determine the location of the interference source of the target cell.

[0007] Optionally, the interference category result of the target cell is identified based on the interference feature data, including: encoding the interference feature data using a trained variational autoencoder to obtain a corresponding reconstruction probability; classifying the reconstruction probabilities using multiple trained classifiers to obtain classification results of labels corresponding to each classifier; each classifier corresponds to an interference category label; and determining the interference category of the target cell based on the classification results of each classifier.

[0008] Optionally, the variational autoencoder includes an encoder and a decoder, and the training process of the variational autoencoder includes: obtaining historical interference sample data; inputting the historical interference sample data into the encoder for encoding to obtain latent encoded data of the historical interference sample data; using the decoder to restore the latent encoded data to obtain restored data; and updating the model parameters of the variational autoencoder with the goal of minimizing the first loss function between the restored data and the input data of the encoder.

[0009] Optionally, the training process of the multiple classifiers includes: using a trained encoder to encode the historical interference sample data to obtain corresponding latent encoded data; using the multiple classifiers to classify the latent encoded data to obtain prediction results; calculating a second loss function based on the prediction results and corresponding category labels; and updating the model parameters of the multiple classifiers based on the second loss function.

[0010] Optionally, obtaining the interference characteristic data of the target cell includes: obtaining communication resource data of the target cell from engineering parameters; obtaining resource usage of the target cell from a network management system; extracting time-frequency domain resource fluctuation data of the target cell based on the communication resource data and the resource usage; and using the communication resource data, the resource usage and the time-frequency domain resource fluctuation data as the interference characteristic data of the target cell.

[0011] Optionally, the geographic location information of multiple second cells is fused based on the measurement data, including: obtaining index data in the measurement data of multiple second cells, and determining the attenuation degree of the index data; determining the location weights of multiple second cells based on the attenuation degree; determining the location of the interference source of the target cell based on the geographic location information of multiple second cells and the location weights.

[0012] Optionally, the method further includes: acquiring communication resource data and resource usage of all cells in the area to be identified; and screening the communication resource data and / or resource usage of all cells using preset rules to determine the target cell.

[0013] Optionally, the method further includes: when the interference category result does not include the interference category of the external interference source, determining the interference source position of the target cell according to the overlapping area of ​​the signal coverage range of the target cell and the first cell.

[0014] According to a second aspect of the present disclosure, there is provided an interference positioning device for wireless communication, the device comprising: an identification module, a first determination module, an acquisition module and a fusion positioning module; the identification module is used to acquire interference feature data of a target cell; the interference category result of the target cell is identified according to the interference feature data; the interference category result includes one or more interference categories; the first determination module is used to determine the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage of the target cell and the first cell when the interference category result includes the interference category of the external interference source; the first cell is a neighboring cell with the same interference category as the target cell; the acquisition module is used to acquire measurement data of multiple second cells in the interference area, the measurement data including geographical location information of the second cells; the fusion positioning module is used to fuse the geographical location information of the multiple second cells according to the measurement data to determine the location of the interference source of the target cell.

[0015] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of any of the above embodiments is implemented.

[0016] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of any of the above embodiments by executing the executable instructions.

[0017] The exemplary embodiments of the present disclosure may have some or all of the following beneficial effects:

[0018] In the interference positioning method for wireless communication provided in the exemplary embodiment of the present disclosure, on the one hand, when the interference category result includes the interference category of the external interference source, the interference area where the external interference source is located is determined according to the overlapping area of ​​the signal coverage of the target cell and the first cell; further, by obtaining the measurement data in the interference area, the geographical location information of multiple second cells in the interference area is fused and processed to determine the interference source position of the target cell. The accuracy and efficiency of interference positioning can be improved by two-step positioning. On the other hand, the automatic attribution of delay anomalies is realized, the efficiency of delay anomaly attribution is improved, and the occupation of manual resources is reduced. On the other hand, the interference category result of the target cell can be identified according to the interference feature data, and the automatic identification of the interference category can be realized, which saves manpower and material resources, improves the efficiency of interference identification, and thus improves the efficiency of interference positioning. In addition, the interference category result identified by the present disclosure can include one or more interference categories, that is, the situation where multiple interferences are mixed in actual communication can be accurately identified, the identification accuracy can be improved, and it can be applied to complex scenarios where multiple interference categories are mixed.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0021] Figure 1 A schematic diagram of the system architecture of a method and device for locating interference in wireless communications according to an embodiment of the present disclosure is schematically shown.

[0022] Figure 2 One of the flowcharts of the interference location method for wireless communication according to an embodiment of the present disclosure is schematically shown.

[0023] Figure 3 The flowchart of the interference type identification process according to an embodiment of the present disclosure is schematically shown.

[0024] Figure 4 A schematic diagram of a training process flow of an interference identification model according to an embodiment of the present disclosure is shown schematically.

[0025] Figure 5 The second flowchart of the interference location method for wireless communication according to an embodiment of the present disclosure is schematically shown.

[0026] Figure 6 The structure block diagram of an interference location device for wireless communication according to an embodiment of the present disclosure is schematically shown.

[0027] Figure 7 A block diagram of an exemplary electronic device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0029] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0030] Figure 1 FIG. 1 is a schematic diagram showing an exemplary system architecture 100 of a method and apparatus for locating interference in wireless communication to which the present disclosure can be applied. Figure 1 As shown, the system architecture 100 may include a terminal device 110, a server 120 and an access device 130. The terminal device 110 includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, an intelligent home appliance, a vehicle-mounted terminal, a test terminal, etc., such as a spectrum analyzer or a dedicated test terminal, a computer, or any other user terminal electronic device capable of wireless communication, which is not limited in this example.

[0031] The terminal device 110 can generate MR (Measurement Report) data to reflect information such as network quality, user behavior habits and surrounding environment.

[0032] The terminal 100 can transmit the MR data to the server 120 in real time. The server 120 can obtain the engineering parameters of the area to be identified from the base station 130, and can also obtain the resource usage of the target cell from the network management system, and extract the time-frequency domain resource fluctuation data of the target cell to obtain the interference characteristic data of the target cell; identify the interference category result of the target cell according to the interference characteristic data; the interference category result includes one or more interference categories; when the interference category result includes the interference category of the external interference source, determine the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage of the target cell and the first cell; the first cell is a neighboring cell with the same interference category as the target cell; obtain measurement data of multiple second cells in the interference area, the measurement data includes the geographical location information of the second cell; according to the measurement data, the geographical location information of the multiple second cells is fused and processed to determine the location of the interference source of the target cell.

[0033] In this example, server 120 can be an independent physical server or a server cluster or distributed system composed of multiple physical servers, wherein multiple servers can form a blockchain, and the server is a node on the blockchain. Server 120 can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network) and big data and artificial intelligence platforms.

[0034] The access device 130 may be a base station, such as a 4G base station or a 5G base station; as an access device for a user terminal to access an operator's network, the base station can provide communication services for the terminal device 110. If the server 120 locates the interference source, it can send the interference source location to the terminal or transmit it to the base station for corresponding anti-interference processing.

[0035] The interference positioning method for wireless communication provided by the embodiment of the present disclosure may be executed on the server 120 , and accordingly, the interference positioning method device for wireless communication is generally disposed in the server 120 .

[0036] The technical solution of the embodiment of the present disclosure is described in detail below:

[0037] refer to Figure 2 As shown, an interference positioning method for wireless communication according to an exemplary embodiment of the present disclosure may include the following steps S210-S240.

[0038] Step S210, obtaining interference characteristic data of the target cell; and identifying the interference category result of the target cell according to the interference characteristic data.

[0039] In this example implementation, the target cell refers to a cell where interference may exist, and the target cell may include one or more cells. The cell refers to the range that the signal of a base station can cover, and the cell corresponds to the base station one by one. The interference characteristic data may include information such as the frequency band, frequency point, bandwidth, subcarrier spacing, longitude, latitude, etc. of the cell, and may also include data such as uplink PRB received power and PRB utilization. The signal volatility characteristics may also be extracted from the dimensions of the time domain and the frequency domain as interference characteristic data, which is not limited in this example.

[0040] In this example implementation, interference feature data may be input into a neural network model to identify interference categories. The neural network model may be any neural network model that can perform machine learning, such as a convolutional neural network (CNN), an artificial neural network, etc., and a classifier or classification layer may be added to the neural network model to implement interference classification. In this example, the classifier is a multi-class classifier for multiple labels, and a set of interference feature data is input to output one or more interference categories.

[0041] Step S220: When the interference category result includes the interference category of the external interference source, determine the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage range of the target cell and the first cell.

[0042] In this example implementation, it can be determined whether the interference comes from inside or outside the communication system according to the interference category. Exemplarily, the internal interference source may include GPS desynchronization, frame header offset configuration error, atmospheric waveguide, etc. The external interference source may include multichannel digital microwave (Multichannel Microwave Distribution System, MMDS) interference, video surveillance interference, pseudo base station interference, jammer interference, satellite earth station interference, etc., and may also include other interference sources that may interfere with the target cell, which is not limited in this example.

[0043] In this example implementation, the interference category result may include multiple interference categories, for example, both internal interference sources and external interference sources. When the interference category includes external interference sources, other neighboring cells (first cell) with the same interference category can be screened, and the interference area where the external interference source is located can be determined based on the overlapping area of ​​the signal coverage range between the target cell and the first cell.

[0044] For example, when it is determined that the interference category includes an external interference source, the first-order neighboring area and the second-order neighboring area of ​​the target cell are extracted. The first-order neighboring area is a neighboring area with overlapping coverage area with the target cell, and the second-order neighboring area is a neighboring area with overlapping coverage with the first-order neighboring area. After determining the target cell and the set of neighboring areas that may be affected by external interference, it is necessary to determine whether there is interference correlation between the interfering cells interfered by the interference source, which can be determined by the consistency of interference change and regional correlation. The consistency of interference change is to determine whether there is consistency in the change of RSSI (Received Signal Strength Indication) indicators between cells. Regional correlation is to determine whether the distance between the interfered cells is within a certain range (such as 1000 meters). For the interfering cell (i.e., the first cell) with interference correlation, the interference source area is determined as follows: take the neighboring cells affected by the same interference source as the center of the circle, and draw a circle with a preset length (such as r=500) as the radius to obtain multiple circles, and the overlapping and intersecting range of multiple circles is the interference area where the interference source is located.

[0045] Step S230: Acquire measurement data of multiple second cells in the interference area.

[0046] In this example implementation, the measurement data may be a measurement report reported by a user terminal, and the measurement report may include the corresponding geographic location information of the second cell, for example, the geographic location information of the second cell may be obtained by carrying Assisted Global Positioning System AGPS information. The geographic location information may be longitude and latitude information, or other location information obtained by coordinate conversion of longitude and latitude information, which is not limited in this example.

[0047] In this exemplary implementation, the second cell is located in the interference area and is a cell of the same interference category as the target cell and having the same external interference source.

[0048] Step S240: performing fusion processing on the geographical location information of the plurality of second cells according to the measurement data to determine the location of the interference source of the target cell.

[0049] In this example implementation, the signal energy change of the second cell can be extracted from the measurement data, and the interference size of the interference source on each second cell can be determined by the degree of signal energy change. The fusion process can be to use the geographic location information of the second cell with the largest signal energy change as the initial position, and then use the geographic location information of other second cells to correct the initial position and finally determine the location of the interference source. The fusion process can also be to screen several second cells with large signal energy changes, and use the center of the geometric shape formed by the screened cells as the location of the interference source. Fusion processing can also be performed in other ways, which are not limited in this example.

[0050] In the interference positioning method for wireless communication provided by the embodiment of the present disclosure, on the one hand, when the interference category result includes the interference category of the external interference source, the interference area where the external interference source is located is determined according to the overlapping area of ​​the signal coverage range of the target cell and the first cell; further, by obtaining the measurement data in the interference area, the geographical location information of multiple second cells in the interference area is fused and processed to determine the location of the interference source of the target cell. The accuracy and efficiency of interference positioning can be improved by a two-step positioning method. On the other hand, the automatic attribution of delay anomalies is realized, the efficiency of delay anomaly attribution is improved, and the occupation of manual resources is reduced. On the other hand, the interference category result of the target cell can be identified according to the interference feature data, and the automatic identification of the interference category can be realized, which saves manpower and material resources, improves the efficiency of interference identification, and thus improves the efficiency of interference positioning. In addition, the interference category result identified by the present disclosure may include one or more interference categories, that is, the situation where multiple interferences are mixed in actual communication can be accurately identified, the identification accuracy can be improved, and it can be applied to complex scenarios where multiple interference categories are mixed.

[0051] In some embodiments, reference Figure 3 The interference identification model may include a variational autoencoder 310 and a plurality of classifiers 320, and the interference category results of the target cell are identified according to the interference feature data, including:

[0052] The trained variational autoencoder is used to encode the interference feature data to obtain the corresponding reconstruction probability.

[0053] In this example implementation, the variational autoencoder (VAE), as a form of deep generative model, is a generative network structure based on variational Bayesian inference. The variational autoencoder consists of an encoder and a decoder. The role of the encoder is to project the sample data in the observation space into the hidden layer space to obtain the representation of the data in the hidden space, and the role of the decoder is to decode the representation of the hidden space into the original representation.

[0054] In this example implementation, the encoder of the trained variational autoencoder can be used to learn the hidden layer features of the interference feature data, that is, the interference feature data is encoded in the hidden layer to obtain the reconstruction probability corresponding to the interference feature data. The encoder can include CNN, batch normalization and activation layer.

[0055] The reconstruction probabilities are classified respectively using multiple trained classifiers to obtain the classification results of the labels corresponding to each classifier; each classifier corresponds to an interference category label.

[0056] In this example implementation, the multiple classifiers may be multilayer perceptrons (MLPs), or multiple fully connected layers, each classifier performing binary classification processing on a label, and the reconstruction probability is subjected to multiple binary classification processing by the trained multiple classifiers to determine whether the target cell has the interference category corresponding to the label of each classifier.

[0057] According to the classification result of each classifier, the interference category of the target cell is determined.

[0058] In this example implementation, the interference category determined by each classifier can be used as an interference category of the target cell. The target cell can have multiple interference categories. In this way, all interference categories of the target cell can be identified, which is more in line with the situation where multiple interferences coexist in actual situations and enhances the practicality of the method disclosed herein.

[0059] In some embodiments, reference Figure 4 ,The interference recognition model may include a variational autoencoder and a plurality of classifiers, the variational autoencoder includes an encoder and a decoder, and the training process of the interference recognition model may include the following two parts of steps.

[0060] The first part is the training of the variational autoencoder:

[0061] The first step is to obtain historical interference sample data.

[0062] In this example implementation, the historical interference sample data may be the historical interference data of the base station cell with an interference category label. It may include communication resource data such as the cell frequency band, frequency point, bandwidth, subcarrier spacing, longitude, latitude, and resource usage data such as uplink PRB receiving power and PRB utilization during a certain period of history. It is also possible to extract time-frequency domain resource fluctuation data from the communication resource data and resource usage data, and use the above data as interference sample data. In this example, a certain period of history can be determined according to the specific circumstances, for example, it can be several days, a month, or several months before the current moment, or it can be data from the same period in previous years.

[0063] In this example implementation, a series of preprocessing may be performed on the communication resource data, resource usage data, and time-frequency domain resource fluctuation data, and the preprocessed data may be used as interference sample data. Exemplarily, the preprocessing may include one or more of removing data with too many null values, filling null values ​​in the data with mean values, and normalizing the null values, and may also include other preprocessing means, which are not limited in this example.

[0064] In the second step, the historical interference sample data is input into the encoder for encoding to obtain the latent encoding data of the historical interference sample data.

[0065] In this example implementation, the encoder in the variational autoencoder may be used to encode the historical interference sample data, map the high-dimensional space data into low-dimensional space data, and obtain latent coding data.

[0066] The third step is to use the decoder to restore the latent coded data to obtain the restored data.

[0067] In this example implementation, the decoder may be used to restore the output data of the encoder, restore the latent coded data to the input space, and obtain restored data having the same dimension as the encoder input data.

[0068] The fourth step is to update the model parameters of the variational autoencoder with the goal of minimizing the first loss function between the restored data and the encoder's input data.

[0069] In this example implementation, the first loss function may be a cross entropy loss function, or may be determined using KL divergence and mean square error, which is not limited in this example. An existing parameter update algorithm, such as a stochastic gradient descent algorithm, may be used to update the model parameters of the variational autoencoder.

[0070] The second part is the training of multiple classifiers, during which the model parameters of the variational autoencoder can be kept unchanged.

[0071] The fifth step is to use the trained encoder to encode the historical interference sample data to obtain the corresponding latent coding data.

[0072] The sixth step is to use multiple classifiers to classify the latent coded data and obtain the prediction results.

[0073] In this example implementation, multiple classifiers output probability vectors of interference category labels, which are used as prediction results.

[0074] Step 7: Calculate the second loss function based on the prediction results and the corresponding category labels.

[0075] In this example implementation, the second loss function may be a cross entropy loss function or a mean square error MSE between the prediction result and the corresponding category label may be used as the second loss function, which is not limited in this example.

[0076] In the eighth step, the model parameters of multiple classifiers are updated according to the second loss function.

[0077] In this example implementation, the model parameters of multiple classifiers may be updated according to an existing parameter updating algorithm, such as a stochastic gradient descent algorithm.

[0078] In the above embodiments, the first loss function and the second loss function may be the same or different. The parameter update algorithm of the variational autoencoder and the multi-layer classifier may be the same or different, and this example does not limit this. The training cutoff condition for each training part may be model convergence or reaching the maximum training round. Model hyperparameters such as the scale of training data per round, the maximum training round Batch parameter update optimization algorithm, and the corresponding settings for early termination can be set according to experience and needs. Model parameters need to be stored after model training is completed. In order to maintain the robustness of the model, the model parameters can be updated periodically using new interference sample data.

[0079] In some embodiments, obtaining interference characteristic data of a target cell includes:

[0080] The communication resource data of the target cell is obtained from the engineering parameters; and the resource usage of the target cell is obtained from the network management system.

[0081] In this example implementation, the communication resource data may include information such as cell frequency band, frequency point, bandwidth, subcarrier spacing, longitude, latitude, etc. Resource usage may include data such as resource receiving power of uplink physical resource blocks, uplink or downlink PRB utilization, etc. Physical resource block (PRB), PRB corresponds to 12 consecutive carriers in the frequency domain (180K in the case of 15K carrier spacing), and a time system in the time domain (half subframe, 0.5ms). Exemplarily, the frequency band of uplink communication is divided into 273 physical resource blocks according to the protocol.

[0082] According to the communication resource data and resource usage, the time-frequency domain resource fluctuation data of the target cell is extracted.

[0083] In this example implementation, the time-frequency domain resource fluctuation data may include frequency domain fluctuation data, time domain fluctuation data, frequency domain change rate, maximum steady-state length, frequency domain range, correlation between uplink and downlink PRB utilization rates of the cell (such as similarity), and may also include other data reflecting time-frequency domain fluctuations, which are not limited in this example.

[0084] For example, the frequency domain fluctuation data can be represented by the frequency domain variance D 频域 measure:

[0085]

[0086] Among them, E 频域 represents the frequency domain mean of PRB, n is the number of physical resource blocks, and its value depends on the communication system standard (such as 4G or 5G) and the subcarrier spacing. For example, n = 273 in 5G communication, and n = 100 or 50 in 4G communication. i is the sequence number of the physical resource block, x irepresents the i-th physical resource block.

[0087] The time domain fluctuation data can be represented by the time domain variance D 时域 measure:

[0088]

[0089] Among them, E 时域 Represents the PRB time domain mean.

[0090] Frequency domain rate of change:

[0091]

[0092] The maximum steady-state length is τ:

[0093] For the rate of change δ i , when the backtracking step length is τ, if |δ i -δ i-τ |<η and |δ i -δ i-τ-1 |≥η, it is considered that the maximum steady-state length corresponding to the position of the i physical resource block is τ; η is a preset constant.

[0094] The frequency range R is:

[0095] R = max(PRB) - min(PRB)

[0096] Among them, max means taking the maximum value, and min means taking the minimum value.

[0097] The similarity between the frequency domain and the uplink and downlink PRB utilization can be measured using the Pearson coefficient:

[0098]

[0099] in, represents the frequency domain mean of PRB, y i Indicates the utilization rate of the i-th physical resource block PRB in the uplink and downlink. Indicates the average value of PRB utilization.

[0100] The above communication resource data, resource usage and time-frequency domain resource fluctuation data can be used as interference characteristic data of the target cell. For example, the above data are combined into a characteristic vector and input into the model.

[0101] In some other embodiments, the method further comprises the following steps:

[0102] Obtain the communication resource data and resource usage of all cells in the area to be identified.

[0103] The communication resource data and / or resource usage of all cells are screened using preset rules to determine the target cell.

[0104] In this example implementation, preset rules can be used to filter interfered cells as target cells. The preset rule can be that the average uplink PRB received power in a certain period of time is greater than a preset threshold, and the frequency of occurrence reaches an upper limit value, and the cell can be determined as an interfered cell. The preset rule can also be set using the uplink or downlink PRB utilization rate, or the preset rule can be set in combination with the PRB received power and utilization rate, which is not limited in this example. Communication resource data is used to determine cell frequency band, location and other information. Exemplarily, the interfered cell can be filtered out according to the preset rule that the average uplink PRB received power in one day is greater than -97dbm / 100MHz, and it has appeared for 4 consecutive days or more in the last 7 days.

[0105] In some embodiments, fusing geographic location information of multiple second cells according to measurement data may include the following steps.

[0106] Obtain indicator data from the measurement data of the plurality of second cells, and determine an attenuation degree of the indicator data.

[0107] In this example implementation, the indicator data may include a measurement (MR) indicator and a KPI (Key Performance Indicator), for example, the indicator data may be a signal-to-noise and interference ratio (SINR) and / or a reference signal received power (RSRP). The attenuation (degradation) of the above KPI and MR indicators due to interference is analyzed.

[0108] According to the attenuation degree, position weights of the plurality of second cells are determined.

[0109] In this example implementation, the sum of the location weights of multiple second cells can be set to 1, and the attenuation degree can be represented by the difference between the KPI index before and after attenuation. The greater the attenuation degree, the greater the interference impact on the cell, and a larger location weight can be set for the cell.

[0110] The location of the interference source of the target cell is determined according to the geographical location information and location weights of the plurality of second cells.

[0111] In this example implementation, the geographical location information may be the longitude and latitude of a cell, and the location of the interference source may be determined by a weighted sum of the longitudes and latitudes of a plurality of second cells.

[0112] In some embodiments, the method further includes: when the interference category result does not include the interference category of the external interference source, determining the interference source position of the target cell according to the overlapping area of ​​the signal coverage range of the target cell and the first cell.

[0113] In this example implementation, no external interference source is included, that is, only internal interference sources are included. When the interference category determined by the model only includes internal interference sources, other neighboring cells (first cells) with the same interference category can be screened, and the location of the internal interference source can be determined based on the overlapping area of ​​the signal coverage of the target cell and the first cell. For example, the center of the overlapping area can be used as the location of the interference source, or the location can be determined based on multiple overlapping areas, such as using the first-order neighbor area and second-order neighbor area method of the above embodiment, which is not limited in this example.

[0114] In some embodiments, reference Figure 5 , the interference positioning method in wireless communication may include the following steps S501-S511.

[0115] Step S501, obtaining historical interference feature data.

[0116] Step S502: construct an interference recognition model using a variational autoencoder and a multi-layer perceptron.

[0117] Step S503: Use historical interference feature data to train an interference recognition model.

[0118] Step S504, obtaining communication resource data and resource usage of the area to be identified, and screening to determine the target cell.

[0119] Step S505: determine interference characteristic data of the target cell.

[0120] Step S506: Input the interference feature data of the target cell into the trained interference identification model to obtain an interference category result. The interference category result includes one or more interference categories.

[0121] Step S507, judging whether the current interference category includes the interference category of the external interference source according to the interference category result, if so, proceeding to step S508, otherwise, proceeding to step S511.

[0122] Step S508: Determine the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage ranges of the target cell and the first cell.

[0123] Step S509: Acquire measurement data of multiple second cells in the interference area, where the measurement data includes geographic location information of the second cells.

[0124] Step S510: performing fusion processing on the geographical location information of multiple second cells according to the measurement data to determine the location of the interference source of the target cell.

[0125] Step S511: determine the location of the internal interference source according to the overlapping area of ​​the signal coverage of the target cell and the first cell.

[0126] The order of each step in the above embodiment is only exemplary, and the order of the steps can be adjusted accordingly as needed. The detailed description of each step in the above embodiment can refer to the corresponding description in the above embodiment, and will not be repeated here.

[0127] The interference classification algorithm in the related art mainly relies on a multi-classification model, which can only predict one interference category at a time. However, from the experience of on-site interference troubleshooting, the same base station cell is often affected by multiple interferences, especially the 5G communication system. The interference of the 5G communication system is different from that of the 4G communication system. In the 5G communication system, different operators have different frequency bands, resulting in different types of interference. In the related art, due to the complex interference influencing factors, complex types, and unknown interference sources, the accuracy of interference source positioning is low. In view of this situation, the present invention proposes a multi-label classification model based on variational autoencoder (VAE), which can more comprehensively capture the interference category of the cell, thereby achieving accurate interference source positioning.

[0128] This disclosure proposes an interference classification method based on multi-label classification and an interference source precise positioning method based on AGPS. First, the law of interference patterns is learned through a neural network model to predict the various types of interference that may exist, and then the precise location of the interference source is obtained by analyzing the AGPS data and the degree of degradation of the KPI indicator. The use of multi-label classification can more comprehensively describe the interference situation of the base station cell, and the use of AGPS and KPI data can more accurately locate the interference source.

[0129] The interference source positioning disclosed in the present invention is divided into two parts: coarse positioning and fine positioning. The coarse positioning part uses the triangulation positioning frame to select the approximate area where the interference source may exist. The fine positioning is based on the coarse positioning, further using the MR data containing AGPS, and accurately positioning the interference source by analyzing the degradation degree of KPI and MR indicators, thereby improving the positioning accuracy of the interference source.

[0130] The disclosed method can be used for 4G / 5G base stations with more complex interference situations, and can solve the problem of inaccurate 4G / 5G interference classification and positioning.

[0131] The present disclosure can be applied to wireless interference troubleshooting scenarios to achieve automatic location of interference sources and reduce manual involvement. It can also be applied to wireless network intelligent operation and maintenance scenarios to achieve intelligent operation and maintenance of wireless interference through automatic discovery, troubleshooting, and automatic policy issuance of interference sources.

[0132] See also Figure 6 In this example implementation, a wireless communication interference positioning device 600 is also provided; the device 600 may include: an identification module 610, a first determination module 620, an acquisition module 630 and a fusion positioning module 640; the identification module 610 is used to obtain interference feature data of the target cell; the interference category result of the target cell is identified according to the interference feature data; the interference category result includes one or more interference categories; the first determination module 620 is used to determine the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage of the target cell and the first cell when the interference category result includes the interference category of the external interference source; the first cell is a neighboring cell with the same interference category as the target cell; the acquisition module 630 is used to obtain measurement data of multiple second cells in the interference area, and the measurement data includes geographical location information of the second cells; the fusion positioning module 640 is used to fuse the geographical location information of multiple second cells according to the measurement data to determine the location of the interference source of the target cell.

[0133] In one embodiment of the present disclosure, the identification module 610 also includes a coding submodule, a classification submodule, and a first determination submodule. The coding submodule is used to encode the interference feature data using a trained variational autoencoder to obtain a corresponding reconstruction probability; the classification submodule is used to classify the reconstruction probability using multiple trained classifiers to obtain classification results of labels corresponding to each classifier; each classifier corresponds to an interference category label; the determination submodule is used to determine the interference category of the target cell based on the classification results of each classifier.

[0134] In one embodiment of the present disclosure, the device 600 also includes a first training module, which is used to: obtain historical interference sample data; input the historical interference sample data into the encoder for encoding to obtain latent encoded data of the historical interference sample data; use the decoder to restore the latent encoded data to obtain restored data; and update the model parameters of the variational autoencoder with the goal of minimizing the first loss function between the restored data and the input data of the encoder.

[0135] In one embodiment of the present disclosure, the device 600 also includes a second training module, which is used to: use a trained encoder to encode historical interference sample data to obtain corresponding latent encoded data; use multiple classifiers to classify the latent encoded data to obtain prediction results; calculate a second loss function based on the prediction results and corresponding category labels; and update the model parameters of multiple classifiers based on the second loss function.

[0136] In one embodiment of the present disclosure, the identification module 610 also includes an acquisition submodule, an extraction submodule and a second determination submodule, the acquisition submodule is used to acquire the communication resource data of the target cell from the engineering parameters; acquire the resource usage of the target cell from the network management system; the extraction submodule is used to extract the time-frequency domain resource fluctuation data of the target cell based on the communication resource data and resource usage; the second determination submodule is used to use the communication resource data, resource usage and time-frequency domain resource fluctuation data as the interference characteristic data of the target cell.

[0137] In one embodiment of the present disclosure, the fusion processing module 640 is also used to: obtain indicator data from the measurement data of multiple second cells, and determine the attenuation degree of the indicator data; determine the location weights of the multiple second cells based on the attenuation degree; determine the interference source location of the target cell based on the geographic location information and location weights of the multiple second cells.

[0138] In one embodiment of the present disclosure, the device 600 also includes a screening module, and the acquisition module 630 is also used to obtain the communication resource data and resource usage of all cells in the area to be identified; the screening module is used to use preset rules to screen the communication resource data and / or resource usage of all cells to determine the target cell.

[0139] In one embodiment of the present disclosure, the device 600 also includes a second determination module, which is used to determine the interference source position of the target cell according to the overlapping area of ​​the signal coverage range of the target cell and the first cell when the interference category result does not include the interference category of the external interference source.

[0140] The specific details of each module / unit involved in the interference locating device for wireless communication in the above embodiment have been described in detail in the corresponding interference locating method for wireless communication, so they will not be repeated here.

[0141] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the method in the following embodiment. For example, the device may implement Figure 2-Figure 5 The various steps shown, etc.

[0142] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0143] In addition, in an exemplary embodiment of the present disclosure, a device capable of implementing the above method is also provided. It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which may be collectively referred to herein as a "circuit", "module", or "system".

[0144] See also Figure 7 , Figure 7 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device 700 includes a processor 710, a memory 720, an input / output interface 730, and a communication bus 740. The processor 710 is connected to the memory 720 and the input / output interface 730. For example, the processor 710 can be connected to the memory 720 and the input / output interface 730 via the communication bus 740. The processor 710 is configured to support the electronic device to execute Figure 2-Figure 5The processor 710 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above-mentioned hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (CPLD), a field programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof. The memory 720 is used to store program codes, etc. The memory 720 may include a volatile memory (VM), such as a random access memory (RAM); the memory 720 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 720 may also include a combination of the above types of memory.

[0145] The input / output interface 730 is used to input or output data.

[0146] The processor 710 may call the above program code to perform the following operations:

[0147] Obtain interference characteristic data of a target cell; identify interference category results of the target cell based on the interference characteristic data; the interference category results include one or more interference categories; when the interference category results include the interference category of an external interference source, determine the interference area where the external interference source is located based on the overlapping area of ​​the signal coverage of the target cell and the first cell; the first cell is a neighboring cell with the same interference category as the target cell; obtain measurement data of multiple second cells within the interference area, the measurement data including geographic location information of the second cells; based on the measurement data, fuse the geographic location information of the multiple second cells to determine the location of the interference source of the target cell.

[0148] Optionally, the processor 710 may further identify the interference category result of the target cell according to the interference feature data, and perform the following operations:

[0149] The interference feature data is encoded using a trained variational autoencoder to obtain the corresponding reconstruction probability; the reconstruction probability is classified using multiple trained classifiers to obtain the classification results of the labels corresponding to each classifier; each classifier corresponds to an interference category label; and the interference category of the target cell is determined based on the classification results of each classifier.

[0150] Optionally, the processor 710 may further perform the following operations:

[0151] Obtain historical interference sample data; input the historical interference sample data into the encoder for encoding to obtain latent encoded data of the historical interference sample data; use the decoder to restore the latent encoded data to obtain restored data; update the model parameters of the variational autoencoder with the goal of minimizing the first loss function between the restored data and the input data of the encoder.

[0152] Optionally, the processor 710 may further perform the following operations:

[0153] The historical interference sample data is encoded using the trained encoder to obtain the corresponding latent encoded data; the latent encoded data is classified using multiple classifiers to obtain prediction results; the second loss function is calculated based on the prediction results and the corresponding category labels; and the model parameters of multiple classifiers are updated based on the second loss function.

[0154] Optionally, the processor 710 may also obtain interference characteristic data of the target cell and perform the following operations:

[0155] The communication resource data of the target cell is obtained from the engineering parameters; the resource usage of the target cell is obtained from the network management system; the time-frequency domain resource fluctuation data of the target cell is extracted based on the communication resource data and the resource usage; the communication resource data, the resource usage and the time-frequency domain resource fluctuation data are used as the interference characteristic data of the target cell.

[0156] Optionally, the processor 710 may further perform fusion processing on the geographical location information of multiple second cells according to the measurement data, and perform the following operations:

[0157] Obtain index data from measurement data of multiple second cells, and determine the attenuation degree of the index data; determine the location weights of the multiple second cells according to the attenuation degree; and determine the interference source location of the target cell according to the geographic location information and location weights of the multiple second cells.

[0158] Optionally, the processor 710 may further perform the following operations:

[0159] Acquire the communication resource data and resource usage of all cells in the area to be identified; use preset rules to filter the communication resource data and / or resource usage of all cells to determine the target cell.

[0160] Optionally, the processor 710 may further perform the following operations:

[0161] When the interference category result does not include the interference category of the external interference source, the interference source position of the target cell is determined according to the overlapping area of ​​the signal coverage range of the target cell and the first cell.

[0162] It should be noted that the implementation of each operation can also refer to Figure 2-Figure 5 The processor 710 may also cooperate with the input / output interface 730 to perform other operations in the method embodiment described above.

[0163] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a device to execute the method according to the embodiment of the present disclosure.

[0164] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0165] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in the specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc., which shall all be considered as part of the present disclosure.

[0166] It should be understood that the disclosure disclosed and defined in this specification extends to all alternative combinations of two or more individual features mentioned or evident in the text and / or the accompanying drawings. All these different combinations constitute multiple alternative aspects of the disclosure. The embodiments of this specification illustrate the best mode known for implementing the disclosure and will enable those skilled in the art to utilize the disclosure.

Claims

1. A method for locating interference in wireless communication, characterized in that: The method comprises: Obtain interference characteristic data of the target cell; identify interference category results of the target cell according to the interference characteristic data; the interference category results include one or more interference categories; When the interference category result includes the interference category of the external interference source, determining the interference area where the external interference source is located according to the overlapping area of ​​the signal coverage of the target cell and the first cell; the first cell is a neighboring cell with the same interference category as the target cell; Acquire measurement data of a plurality of second cells in the interference area, wherein the measurement data includes geographic location information of the second cells; Acquire indicator data from the measurement data of the plurality of second cells, and determine an attenuation degree of the indicator data; determining location weights of a plurality of the second cells according to the attenuation degree; The location of the interference source of the target cell is determined according to the geographical location information of the plurality of second cells and the location weights.

2. The method according to claim 1, characterized in that The result of identifying the interference category of the target cell according to the interference characteristic data includes: Encoding the interference feature data using a trained variational autoencoder to obtain a corresponding reconstruction probability; Using multiple trained classifiers to classify the reconstruction probabilities respectively, and obtaining classification results of labels corresponding to each classifier; each classifier corresponds to an interference category label; According to the classification result of each classifier, the interference category of the target cell is determined.

3. The method according to claim 2, characterized in that The variational autoencoder includes an encoder and a decoder, and the training process of the variational autoencoder includes: Obtain historical interference sample data; Inputting the historical interference sample data into the encoder for encoding to obtain latently encoded data of the historical interference sample data; Restoring the latently encoded data using the decoder to obtain restored data; The model parameters of the variational autoencoder are updated with the goal of minimizing a first loss function between the restored data and the input data of the encoder.

4. The method according to claim 3, characterized in that The training process of the multiple classifiers includes: Encoding the historical interference sample data using a trained encoder to obtain corresponding latent encoding data; Using the multiple classifiers to classify the latently encoded data to obtain a prediction result; Calculating a second loss function according to the prediction result and the corresponding category label; According to the second loss function, model parameters of the multiple classifiers are updated.

5. The method according to claim 1, characterized in that The obtaining of interference characteristic data of the target cell includes: Obtain the communication resource data of the target cell from the engineering parameters; obtain the resource usage of the target cell from the network management system; Extracting time-frequency domain resource fluctuation data of the target cell according to the communication resource data and the resource usage; The communication resource data, the resource usage status and the time-frequency domain resource fluctuation data are used as interference characteristic data of the target cell.

6. The method according to claim 1 or 5, characterized in that: The method further comprises: Obtain communication resource data and resource usage of all cells in the area to be identified; The communication resource data and / or the resource usage of all cells are screened using preset rules to determine a target cell.

7. The method according to claim 1, characterized in that The method further comprises: When the interference category result does not include the interference category of the external interference source, the interference source position of the target cell is determined according to the overlapping area of ​​the signal coverage range of the target cell and the first cell.

8. A wireless communication interference positioning device, characterized in that: The device comprises: An identification module, configured to obtain interference characteristic data of a target cell; identify an interference category result of the target cell according to the interference characteristic data; the interference category result includes one or more interference categories; A first determination module is used to determine, when the interference category result includes the interference category of the external interference source, an interference area where the external interference source is located according to the overlapping area of ​​the signal coverage range of the target cell and the first cell; the first cell is a neighboring cell with the same interference category as the target cell; An acquisition module, configured to acquire measurement data of a plurality of second cells in the interference area, wherein the measurement data includes geographic location information of the second cells; A fusion positioning module is used to obtain indicator data from the measurement data of multiple second cells and determine the attenuation degree of the indicator data; determine the location weights of multiple second cells based on the attenuation degree; and determine the location of the interference source of the target cell based on the geographic location information of multiple second cells and the location weights.

9. An electronic device, characterized in that: include: processor; as well as A memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of claims 1-7 by executing the executable instructions.