Method and device for evaluating quality of wireless network and computer equipment

Abstract

The application discloses a quality evaluation method and device of a wireless network and a computer device. The method comprises the following steps: acquiring wireless network sensing data of a target base station, wherein the sensing data comprises at least one of the following: wireless network load condition, wireless network jam condition, wireless network delay condition, and wireless network download rate condition; performing cloud clustering processing on the sensing data to obtain a cloud clustering result, and generating a plurality of wireless network sensing data information streams based on the cloud clustering result; performing cloud separation on each wireless network sensing data information stream to obtain cloud-separated sensing data; and evaluating the quality of the wireless network of a to-be-evaluated area based on the cloud-separated sensing data. The application solves the technical problem of low accuracy of wireless network quality evaluation in the related art.

Description

Technical Field

[0001] This application relates to the field of wireless network technology, and more specifically, to a method, apparatus, and computer device for evaluating the quality of a wireless network. Background Technology

[0002] In recent years, with the rapid development of IoT services, wireless networks, as their core platform, have faced unprecedented challenges. The widespread application of IoT services requires wireless networks to provide stable and efficient services. However, due to significant differences between IoT services and traditional services in data transmission, traffic patterns, and user behavior, the optimization and management of wireless networks have become exceptionally complex. Particularly in terms of user experience, the large-scale deployment of IoT devices and the high-frequency transmission of data make it difficult for traditional network monitoring and optimization methods to accurately and in real-time assess the impact of network quality on user experience.

[0003] While existing network perception evaluation methods can quantify customer perception, their weighting coefficients rely on manual settings, lacking adaptability to dynamic network changes. Improper settings can significantly impact evaluation accuracy, leading to ineffective optimization measures. Alternatively, they may over-rely on thresholds set based on business experience, lacking in-depth analysis and intelligent processing capabilities for multi-dimensional perception data. This results in low accuracy in perception evaluations within complex network environments, making it difficult to comprehensively capture all factors influencing user perception. Summary of the Invention

[0004] This application provides a method, apparatus, and computer device for evaluating the quality of wireless networks, in order to at least solve the technical problem of low accuracy in wireless network quality evaluation in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for quality assessment of a wireless network is provided, comprising: acquiring wireless network sensing data of a target base station, the sensing data including at least one of: wireless network load status, wireless network lag status, wireless network latency status, and wireless network download speed status; performing cloud aggregation processing on the sensing data to obtain cloud aggregation results, and generating multiple types of wireless network sensing data information streams based on the cloud aggregation results; performing cloud separation on each type of wireless network sensing data information stream to obtain cloud-separated sensing data; and assessing the quality of the wireless network in the area to be assessed based on the cloud-separated sensing data.

[0006] Optionally, cloud clustering processing is performed on the sensed data to obtain cloud clustering results, including: normalizing the sensed data to obtain normalized sensed data; extracting features from the normalized sensed data to obtain sensed data containing multi-dimensional features, wherein the multi-dimensional features include at least one of the following: the load corresponding to the sensed data, the collection period corresponding to the sensed data, and the numerical features of the sensed data, wherein the numerical features of the sensed data include the maximum value, minimum value, mean, and standard deviation of different types of sensed data; and performing cloud clustering processing on the sensed data containing multi-dimensional features to obtain the cloud clustering results.

[0007] Optionally, cloud clustering processing is performed on the perceptual data containing multi-dimensional features to obtain the cloud clustering result, including: obtaining an objective function to constrain the cloud clustering result, the objective function being determined at least based on a standard vector distance and a vector supplementation coefficient, the standard vector distance being used to represent the standard vector distance between the perceptual data and the cluster center of the cloud clustering result, and the vector supplementation coefficient being determined based on the ratio of perceptual data that must be included in each cluster; and using the objective function to perform cloud clustering processing on the perceptual data containing multi-dimensional features to obtain the cloud clustering result.

[0008] Optionally, the vector supplementation coefficients are determined by the following methods:

[0009]

[0010] In the formula, DH h Card(Z) represents a subset of data in each type of perceived data that has a correlation. i ) represents the i-th cluster with DH h The number of data points in the data set that have constraints, Card(DH) h ) represents DH h The number of data in Z i Indicates the i-th cluster with DH h The data in Card(Z) is a data set with constraints, and in Card(Z) i ).

[0011] Optionally, generating multiple types of wireless network sensing data information streams based on the cloud clustering results includes: obtaining the center points of multiple clusters in the cloud clustering results; generating multiple wireless network sensing data information streams according to preset rules based on the center points of each cluster, wherein each wireless network sensing data information stream contains a corresponding target feature, the feature value of each target feature is determined according to the feature value contained in the center point of each cluster, the preset rule represents the range of the type to which the target feature contained in the wireless network sensing data information stream belongs, and the wireless network sensing data information stream corresponding to each cluster is a type of wireless network sensing data information stream.

[0012] Optionally, the method further includes: reconstructing the sensing data corresponding to the plurality of wireless network sensing data information streams based on the plurality of wireless network sensing data information streams to obtain reconstructed data; comparing the reconstructed data with the wireless network sensing data, and determining the evaluation result of the plurality of wireless network sensing data information streams based on the comparison result, wherein the evaluation result is used to represent the expressive power of the plurality of wireless network sensing data information streams.

[0013] Optionally, cloud separation is performed on each type of wireless network sensing data information stream to obtain cloud-separated sensing data, including: acquiring multiple target features contained in each type of wireless network sensing data information stream;

[0014] Optionally, cloud separation is performed on each type of wireless network sensing data flow to obtain cloud-separated sensing data, including: acquiring multiple information flow intensity sequences in each type of wireless network sensing data flow, wherein the information flow intensity sequences are used to characterize the indicators corresponding to the wireless network sensing data flow in each type of wireless network sensing data flow, and the indicators are used to evaluate the quality of the wireless network sensing data flow; selecting an information flow intensity sequence within a target area from the multiple information flow intensity sequences to determine it as the information flow intensity sequence to be separated; determining the category of the information flow intensity sequence to be separated based on the distance between the information flow intensity sequence to be separated and each type of wireless network sensing data flow, thereby obtaining the cloud-separated sensing data.

[0015] According to another aspect of the embodiments of this application, a wireless network quality assessment device is also provided, comprising: an acquisition module, configured to acquire wireless network sensing data of a target base station, the sensing data including at least one of: wireless network load status, wireless network lag status, wireless network latency status, and wireless network download speed status; a clustering module, configured to perform cloud clustering processing on the sensing data to obtain cloud clustering results, and generate multiple types of wireless network sensing data information streams based on the cloud clustering results; a separation module, configured to perform cloud separation on each type of wireless network sensing data information stream to obtain cloud-separated sensing data; and an assessment module, configured to assess the quality of the wireless network in the area to be assessed based on the cloud-separated sensing data.

[0016] According to another aspect of the embodiments of this application, a computer device is also provided, including: a memory and a processor, wherein the memory is used to store program instructions; and the processor, connected to the memory, is used to execute the above-described wireless network quality assessment method.

[0017] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device containing the non-volatile storage medium executes the above-described wireless network quality assessment method by running the computer program.

[0018] According to another aspect of the embodiments of this application, a computer program product is also provided, including computer instructions that, when executed by a processor, implement the above-described wireless network quality assessment method.

[0019] In this embodiment, wireless network sensing data of the target base station is acquired. This sensing data includes at least one of the following: wireless network load, wireless network lag, wireless network latency, and wireless network download speed. The sensing data is then subjected to cloud clustering processing to obtain a cloud clustering result, and multiple types of wireless network sensing data information streams are generated based on the cloud clustering result. Each type of wireless network sensing data information stream is then subjected to cloud separation to obtain cloud-separated sensing data. Based on the cloud-separated sensing data, the quality of the wireless network in the area to be evaluated is assessed. This achieves the purpose of secondary subdivision of the clustered data and evaluation of the wireless network based on the secondary subdivision data, thereby improving the accuracy of wireless network quality assessment and solving the technical problem of low accuracy in wireless network quality assessment in related technologies. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0021] Figure 1 This is a hardware structure block diagram of a computer terminal for implementing a wireless network quality assessment method according to an embodiment of this application;

[0022] Figure 2 This is a flowchart of a wireless network quality assessment method according to an embodiment of this application;

[0023] Figure 3 This is a structural diagram of a wireless network quality assessment device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] The information collected in this application embodiment is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, and necessary confidentiality measures have been taken. It does not violate public order and good morals, and provides corresponding operation entry points for users to choose to authorize or reject the automated decision results. If the user chooses to reject, the process will proceed to the expert decision-making process.

[0027] Related technologies primarily rely on manually setting weighting coefficients for various perception indicators, which is overly simplistic, lacks interpretability, and can significantly impact user network perception assessments if the weighting coefficients are not set accurately. Alternatively, assessments may be based on setting basic threshold values ​​for indicators based on business experience, leading to low accuracy in wireless network quality assessment. To address these issues, this application provides a wireless network quality assessment method that can operate on... Figure 1 The computer terminal shown is explained below.

[0028] The wireless network quality assessment method embodiments provided in this application can be executed in mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal for implementing a quality assessment method for wireless networks is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions connected via wired and / or wireless networks. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the wireless network quality assessment method in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned wireless network quality assessment method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission module 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission module 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0032] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0033] It should be noted here that, in some optional embodiments, the above... Figure 1 The computer terminal shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1 This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned computer terminal.

[0034] In the above operating environment, this application provides an embodiment of a wireless network quality assessment method. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] Figure 2 This is a flowchart of a wireless network quality assessment method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0036] Step S202: Obtain wireless network sensing data of the target base station. The sensing data includes at least one of the following: wireless network load, wireless network lag, wireless network latency, and wireless network download speed.

[0037] In step S202, the wireless network sensing data contains multiple data streams, and the target area H covered by the target base station is H = {h1, h2, ..., h...} n}, where h n This represents the nth region, and the data stream set O = {o1, o2, ..., o...} for each region. n}, where o n This represents the data stream contained in the nth region, where each data stream contains multiple types of sensor data, for example: h i ∈(Class1,Class2,...Class E ), indicating that the perceived data categories contained in the i-th region include: Class1, Class2, ... Class E For example: Class1 indicates network lag, Class2 indicates network latency, Class... E This represents the network download speed, and E represents the number of categories of sensing data. Each data stream contains multiple sensing data points, and each sensing data point contains features across multiple dimensions.

[0038] Step S204: Perform cloud clustering processing on the sensing data to obtain cloud clustering results, and generate multiple types of wireless network sensing data information streams based on the cloud clustering results;

[0039] Step S206: Perform cloud separation on the wireless network sensing data information stream of each type to obtain cloud-separated sensing data;

[0040] Step S208: Evaluate the quality of the wireless network in the area to be evaluated based on the cloud separation sensing data.

[0041] Through steps S202 to S208 above, in this embodiment of the application, wireless network sensing data of the target base station is acquired. This sensing data includes at least one of the following: wireless network load, wireless network lag, wireless network latency, and wireless network download speed. The sensing data is then subjected to cloud clustering processing to obtain cloud clustering results, and multiple types of wireless network sensing data information streams are generated based on these results. Each type of wireless network sensing data information stream is then subjected to cloud separation to obtain cloud-separated sensing data. Based on the cloud-separated sensing data, the quality of the wireless network in the area to be evaluated is assessed. This achieves the purpose of secondary subdivision of the clustered data and evaluation of the wireless network based on the secondary subdivision data, thereby improving the accuracy of wireless network quality assessment and solving the technical problem of low accuracy in wireless network quality assessment in related technologies. The following is a detailed explanation.

[0042] In some embodiments of this application, the specific steps for performing cloud clustering processing on the sensed data to obtain cloud clustering results include: normalizing the sensed data to obtain normalized sensed data; extracting features from the normalized sensed data to obtain sensed data containing multi-dimensional features, wherein the multi-dimensional features include at least one of the following: the load corresponding to the sensed data, the collection period corresponding to the sensed data, and the numerical features of the sensed data, wherein the numerical features of the sensed data include the maximum value, minimum value, mean, and standard deviation of different types of sensed data; and performing cloud clustering processing on the sensed data containing multi-dimensional features to obtain the cloud clustering results.

[0043] The process involves performing cloud clustering processing on the perceptual data containing multi-dimensional features to obtain the cloud clustering result, including: obtaining an objective function to constrain the cloud clustering result, wherein the objective function is determined at least based on a standard vector distance and a vector supplementation coefficient, wherein the standard vector distance is used to represent the standard vector distance between the perceptual data and the cluster center of the cloud clustering result, and the vector supplementation coefficient is determined based on the ratio of perceptual data that must be included in each cluster; and using the objective function to perform cloud clustering processing on the perceptual data containing multi-dimensional features to obtain the cloud clustering result.

[0044] It should be noted that the objective function is as follows:

[0045]

[0046] In the formula, c represents the number of nodes (clusters), N represents the number of data streams, and b ie Represents data stream Y e For cloud cluster center (cluster center) A i The membership degree, where 0 ≤ b ie≤1 and A i Let χ represent the i-th cloud cluster center, r represent the fuzzy coefficient (constant), and χ represent the fuzzy coefficient (constant). ie This represents the vector supplementation coefficient. ||·|| represents the standard vector distance.

[0047] The vector supplementation coefficients are determined in the following ways:

[0048]

[0049] In the formula, DH h Card(Z) represents a subset of data in each type of perceived data that has a correlation. i ) represents the i-th cluster with DH h The number of data points in the data set that have constraints, Card(DH) h ) represents DH h The number of data in Z i Indicates the i-th cluster with DH h The data in Card(Z) is a data set with constraints, and in Card(Z) i ).

[0050] It should be noted that the subset of data with correlation in each type of sensing data represents the data related to each type of sensing data, and the constraint relationship represents the constraint relationship of each cluster, such as time, which is the data under the same time.

[0051] In some embodiments of this application, generating multiple types of wireless network sensing data information streams based on the cloud clustering results includes: obtaining the center points (cloud clustering center points) of multiple clusters in the cloud clustering results; generating multiple wireless network sensing data information streams according to preset rules based on the center points of each cluster, wherein each wireless network sensing data information stream contains a corresponding target feature, the feature value of each target feature is determined according to the feature value contained in the center point of each cluster, the preset rule represents the range of the type to which the target feature contained in the wireless network sensing data information stream belongs, and the wireless network sensing data information stream corresponding to each cluster is a type of wireless network sensing data information stream.

[0052] For example: around cloud aggregation center A i For example: A1, A2, ..., A c Constructing multiple wireless network sensing data streams NTG = {P1, P2, ..., P...} c}, where P i ={P i1 ,P i2 ,...,P id}, i = 1, 2, ..., c, d represents the feature dimension of the perceptual data, P iP represents the sensing data flow of the i-th wireless network. i ={P i1 ,P i2 ,...,P id} indicates that the i-th wireless network sensing data flow contains target features from 1 to d.

[0053] It's understandable that the data flow of a wireless network is structurally similar to an information tree. In practical applications, each target feature (each dimension of target feature)...

[0054] P ij =[A ij -δ / 2*range j A ij +δ / 2*range j ]

[0055] Among them, A ij Indicates cloud aggregation center A i The value of the j-th branch (j-th feature), i = 1, 2, ..., c, j = 1, 2, ..., q, where q and c are positive integers, and δ represents G. i The value of G i Represents perceived data, range j This represents the numerical change of the j-th dimension feature of the original data, which is the perceptual data before feature extraction.

[0056] Understandably, A i Indicates the numerical center.

[0057] In one alternative approach, the sensing data corresponding to the plurality of wireless network sensing data information streams is reconstructed based on the plurality of wireless network sensing data information streams, and the sensing data corresponding to the plurality of wireless network sensing data information streams is determined as the reconstructed data; the reconstructed data is compared with the wireless network sensing data, and the evaluation result of the plurality of wireless network sensing data information streams is determined based on the comparison result, wherein the evaluation result is used to represent the expressive power of the plurality of wireless network sensing data information streams.

[0058] The specific reconstruction process is as follows: Data information streams sensed from multiple wireless networks NTG = {P1, P2, ..., P...} c Reconstructing data flow Y in} e To obtain reconstructed data If Y e and If the similarity is greater than the preset similarity threshold, the evaluation result is determined to be a successful reconstruction, and the expressive capability of the wireless network sensing data information flow is verified.

[0059] In wireless network sensing data information flow P i If the expressive ability is verified,

[0060] Data stream Y e For P i The membership degree is The membership degree of other wireless network-sensing data information streams is g = 1, 2, ..., c and g ≠ i

[0061] In wireless network sensing data information flow P i If the expressive power is verified, defuzzification is performed using membership aggregation and the constructed wireless network-aware data stream to calculate...

[0062]

[0063] In the formula, and It is P i The lower and upper bounds of the j-th dimension The calculation formula is:

[0064]

[0065] In the formula, δ j This represents the value of the j-th dimension feature of the perceived data.

[0066] In some embodiments of this application, cloud separation is performed on each type of wireless network sensing data flow to obtain cloud-separated sensing data, including: acquiring multiple information flow intensity sequences in each type of wireless network sensing data flow, wherein the information flow intensity sequences are used to characterize the indicators corresponding to the wireless network sensing data flow in each type of wireless network sensing data flow, and the indicators are used to evaluate the quality of the wireless network sensing data flow; selecting an information flow intensity sequence within a target area from the multiple information flow intensity sequences to determine it as the information flow intensity sequence to be separated; determining the category of the information flow intensity sequence to be separated based on the distance between the information flow intensity sequence to be separated and each type of wireless network sensing data flow, thereby obtaining the cloud-separated sensing data.

[0067] Specifically, if a wireless network sensed data stream does not contain any information flow intensity sequence within a target area, it is considered an unknown category and is not used during the cloud separation phase; for a wireless network sensed data stream that contains at least one information flow intensity sequence within a target area, its category is assigned based on the number of information flow intensity sequences of different categories within it.

[0068] The more uneven the numerical distribution of data in an information flow, the greater the information flow intensity. For example, if the number of users under all base stations is evenly distributed from 10 to 100, the information flow is uniform and the intensity is low. If the traffic range under all base stations is 10M-1000M, with 60% of users above 900M and 30% of users below 100M, the distribution is uneven and the intensity of the information flow is high.

[0069] In one alternative approach, a rule base can be set for the target area level and the information flow intensity level to extract cloud separation rules for information flow intensity from each wireless network sensed data information flow. For information flow intensity cloud separation, the distance between the information flow intensity and each wireless network sensed data information flow is calculated.

[0070] Here, the level represents the value of traffic / number of users, and the rule base is used to define different regions, such as: school, e-commerce.

[0071] The specific cloud separation process is as follows:

[0072] To separate the information stream intensity sequence F, perform cloud separation according to the following steps:

[0073] If the features of the information flow intensity sequence to be separated belong to the multiple target features contained in the wireless network sensing data flow, then the information flow intensity sequence is determined to belong to the category of wireless network sensing data flow. In practical application scenarios, if the features of the information flow intensity sequence to be separated do not belong to the multiple target features contained in the wireless network sensing data flow, then the intensity sequence F to be separated and the wireless network sensing data flow P are compared. i The distance between them is used to assign them to P, which contains the nearest sequence of information flow intensity F. i In the category.

[0074] The system uses cloud-separated sensing data to train a pre-defined model, such as the Xgboost model. It determines the impact of each type of data on wireless network sensing in different scenarios from the cloud-separated sensing data, and determines the weight of each type of data based on the magnitude of the impact. It receives the features of the area to be evaluated, uses the trained model to analyze the features of the area to be evaluated, determines the weight of each type of cloud-separated data in the area to be evaluated, and then evaluates the quality of the wireless network in the area to be evaluated.

[0075] Figure 3 This is a structural diagram of a wireless network quality assessment apparatus according to an embodiment of this application. The apparatus includes:

[0076] The acquisition module 30 is used to acquire wireless network sensing data of the target base station, the sensing data including at least one of the following: wireless network load status, wireless network lag status, wireless network latency status, and wireless network download speed status.

[0077] Clustering module 32 is used to perform cloud clustering processing on the sensing data to obtain cloud clustering results, and generate multiple wireless network sensing data information streams based on the cloud clustering results;

[0078] Separation module 34 is used to perform cloud separation on each type of wireless network sensing data information stream to obtain cloud-separated sensing data;

[0079] Evaluation module 36 is used to evaluate the quality of the wireless network in the area to be evaluated based on the cloud-separated sensing data.

[0080] In this embodiment of the application, the wireless network quality assessment device described above acquires wireless network sensing data of the target base station. This sensing data includes at least one of the following: wireless network load, wireless network lag, wireless network latency, and wireless network download speed. The sensing data undergoes cloud clustering processing to obtain a cloud clustering result, and multiple types of wireless network sensing data information streams are generated based on the cloud clustering result. Each type of wireless network sensing data information stream is then separated into cloud-separated sensing data. The quality of the wireless network in the area to be assessed is evaluated based on the cloud-separated sensing data. This achieves the goal of secondary subdivision of the clustered data and evaluation of the wireless network based on the subdivided data, thereby improving the accuracy of wireless network quality assessment and solving the technical problem of low accuracy in related technologies.

[0081] The clustering module 32 includes a clustering submodule, used to perform cloud clustering processing on the sensed data to obtain cloud clustering results, including: normalizing the sensed data to obtain normalized sensed data; extracting features from the normalized sensed data to obtain sensed data containing multi-dimensional features, wherein the multi-dimensional features include at least one of the following: the load corresponding to the sensed data, the collection period corresponding to the sensed data, and the numerical features of the sensed data, wherein the numerical features of the sensed data include the maximum value, minimum value, mean, and standard deviation of different types of sensed data; and performing cloud clustering processing on the sensed data containing multi-dimensional features to obtain the cloud clustering results.

[0082] The clustering submodule includes a processing unit for performing cloud clustering processing on the perceptual data containing multi-dimensional features to obtain the cloud clustering results. This includes: obtaining an objective function to constrain the cloud clustering results; the objective function being determined at least based on a standard vector distance and a vector supplementation coefficient; the standard vector distance representing the standard vector distance between the perceptual data and the cluster centers of the cloud clustering results; and the vector supplementation coefficient being determined based on the ratio of perceptual data that must be included in each cluster; and performing cloud clustering processing on the perceptual data containing multi-dimensional features using the objective function to obtain the cloud clustering results.

[0083] The processing unit includes: a determination subunit, used to determine the vector supplementation coefficients in the following ways, including:

[0084]

[0085] In the formula, DH h Card(Z) represents a subset of data in each type of perceived data that has a correlation. i ) represents the i-th cluster with DH h The number of data points in the data set that have constraints, Card(DH) h ) represents DH h The number of data in Z i Indicates the i-th cluster with DH h The data in Card(Z) is a data set with constraints, and in Card(Z) i ).

[0086] The clustering module 32 includes a generation submodule, used to generate multiple types of wireless network sensing data information streams based on the cloud clustering results. This includes: obtaining the center points of multiple clusters in the cloud clustering results; generating multiple wireless network sensing data information streams according to preset rules based on the center points of each cluster, wherein each wireless network sensing data information stream contains a corresponding target feature, the feature value of each target feature is determined based on the feature value contained in the center point of each cluster, the preset rules represent the range of the type to which the target feature contained in the wireless network sensing data information stream belongs, and the wireless network sensing data information stream corresponding to each cluster is a type of wireless network sensing data information stream.

[0087] The generation submodule includes: an evaluation unit, used to reconstruct the sensing data corresponding to the multiple wireless network sensing data information streams based on the multiple wireless network sensing data information streams, to obtain reconstructed data; to compare the reconstructed data with the wireless network sensing data, and to determine the evaluation result of the multiple wireless network sensing data information streams based on the comparison result, wherein the evaluation result is used to represent the expressive power of the multiple wireless network sensing data information streams.

[0088] The separation module 34 includes a separation submodule, used to perform cloud separation on each type of wireless network sensing data information stream to obtain cloud-separated sensing data. This includes: acquiring multiple information stream intensity sequences from each type of wireless network sensing data information stream, where each information stream intensity sequence characterizes an indicator corresponding to the wireless network sensing data information stream in each type, and the indicator is used to evaluate the quality of the wireless network sensing data information stream; selecting an information stream intensity sequence within a target area from the multiple information stream intensity sequences to determine it as the information stream intensity sequence to be separated; and determining the category of the information stream intensity sequence to be separated based on the distance between the information stream intensity sequence to be separated and each type of wireless network sensing data information stream to obtain the cloud-separated sensing data.

[0089] It should be noted that, Figure 3 The wireless network quality assessment device shown is used to perform Figure 2 The wireless network quality assessment method shown above is also applicable to the wireless network quality assessment device, and will not be repeated here.

[0090] This application also provides a computer device, including: a memory and a processor, wherein the memory is used to store program instructions; and the processor, connected to the memory, is used to execute the above-described wireless network quality assessment method.

[0091] This application also provides a non-volatile storage medium including a stored computer program, wherein the device containing the non-volatile storage medium executes the aforementioned wireless network quality assessment method by running the computer program.

[0092] This application also provides a computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the wireless network quality assessment method of this application.

[0093] This application also provides a computer program product, including computer instructions that, when executed by a processor, implement the steps of the wireless network quality assessment method of this application.

[0094] This application also provides a computer program that, when executed by a processor, implements the steps of the wireless network quality assessment method of this application.

[0095] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0096] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0098] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0100] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0101] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for quality assessment of a wireless network, characterized in that, include: Obtain wireless network sensing data of the target base station, wherein the sensing data includes at least one of the following: wireless network load, wireless network lag, wireless network latency, and wireless network download speed. The sensed data is subjected to cloud clustering processing to obtain cloud clustering results, and multiple types of wireless network sensed data information streams are generated based on the cloud clustering results. Perform cloud separation on the wireless network sensing data information stream of each type to obtain cloud-separated sensing data; The evaluation of the quality of the wireless network in the area to be evaluated based on the cloud-separated sensing data includes: training a preset model using the cloud-separated sensing data; determining the degree of influence of each type of data on wireless network perception in different scenarios from the cloud-separated sensing data; determining the weight of each type of data according to the degree of influence; receiving the features of the area to be evaluated; analyzing the features of the area to be evaluated using the trained preset model; determining the weight of each type of cloud-separated data in the area to be evaluated; and evaluating the quality of the wireless network in the area to be evaluated.

2. The method according to claim 1, characterized in that, The perceived data is subjected to cloud clustering processing to obtain cloud clustering results, including: The sensed data is normalized to obtain normalized sensed data. Feature extraction is performed on the normalized sensing data to obtain sensing data containing multi-dimensional features. The multi-dimensional features include at least one of the following: the load corresponding to the sensing data, the collection period corresponding to the sensing data, and the numerical features of the sensing data. The numerical features of the sensing data include the maximum value, minimum value, mean, and standard deviation of different types of sensing data. The cloud clustering process is performed on the perceptual data containing multi-dimensional features to obtain the cloud clustering result.

3. The method according to claim 2, characterized in that, The cloud clustering results are obtained by performing cloud clustering processing on the perceptual data containing multi-dimensional features, including: Obtain an objective function to constrain the cloud clustering results. The objective function is determined at least based on the standard vector distance and the vector supplementation coefficients. The standard vector distance is used to represent the standard vector distance between the sensed data and the cluster centers of the cloud clustering results. The vector supplementation coefficients are determined based on the ratio of sensed data that must be included in each cluster. The objective function is used to perform cloud clustering processing on the perceptual data containing multi-dimensional features to obtain the cloud clustering result.

4. The method according to claim 3, characterized in that, The vector supplementation coefficients are determined in the following ways: ； In the formula, This represents a subset of data that are correlated within each type of perceived data. Indicates that in the i-th cluster, ... The number of data points in the dataset that have constraints. express The amount of data in Indicates that in the i-th cluster, ... The data in the set has constraints. .

5. The method according to claim 1, characterized in that, Based on the cloud aggregation results, multiple types of wireless network sensing data information streams are generated, including: Obtain the center points of multiple clusters in the cloud agglomeration results; Multiple wireless network sensing data streams are generated according to preset rules based on the center point of each cluster. Each wireless network sensing data stream contains a corresponding target feature. The feature value of each target feature is determined based on the feature value contained in the center point of each cluster. The preset rules indicate the range of the type of the target feature contained in the wireless network sensing data stream. The wireless network sensing data stream corresponding to each cluster is a type of wireless network sensing data stream.

6. The method according to claim 5, characterized in that, The method further includes: Based on the multiple wireless network sensing data information streams, the sensing data corresponding to the multiple wireless network sensing data information streams is reconstructed to obtain the reconstructed data; The reconstructed data is compared with the wireless network sensing data, and the evaluation result of the multiple wireless network sensing data information streams is determined based on the comparison result. The evaluation result is used to represent the expressive power of the multiple wireless network sensing data information streams.

7. The method according to claim 1, characterized in that, Cloud separation is performed on the sensing data streams of each type of wireless network to obtain cloud-separated sensing data, including: Multiple information flow intensity sequences are obtained in each type of wireless network sensing data information flow. The information flow intensity sequences are used to characterize the indicators corresponding to the wireless network sensing data information flow in each type of wireless network sensing data information flow. The indicators are used to evaluate the quality of the wireless network sensing data information flow. From the multiple information flow intensity sequences mentioned therein, select the information flow intensity sequence within the target region and determine it as the information flow intensity sequence to be separated; Based on the distance between the intensity sequence of the information stream to be separated and the wireless network sensing data information stream of each type, the category of the intensity sequence of the information stream to be separated is determined, and the cloud-separated sensing data is obtained.

8. A quality assessment device for a wireless network, characterized in that, include: The acquisition module is used to acquire wireless network sensing data of the target base station, wherein the sensing data includes at least one of the following: wireless network load status, wireless network lag status, wireless network latency status, and wireless network download speed status. The clustering module is used to perform cloud clustering processing on the sensed data to obtain cloud clustering results, and generate multiple wireless network sensed data information streams based on the cloud clustering results. The separation module is used to perform cloud separation on each type of wireless network sensing data information stream to obtain cloud-separated sensing data. The evaluation module is used to evaluate the quality of the wireless network in the area to be evaluated based on the cloud-separated sensing data. This includes: training a preset model using the cloud-separated sensing data; determining the influence of each type of data on wireless network perception in different scenarios from the cloud-separated sensing data; determining the weight of each type of data based on the magnitude of the influence; receiving features of the area to be evaluated; analyzing the features of the area to be evaluated using the trained preset model; determining the weight of each type of cloud-separated data in the area to be evaluated; and evaluating the quality of the wireless network in the area to be evaluated.

9. A computer device, characterized in that, include: A memory and a processor, wherein the memory is used to store program instructions; The processor, connected to the memory, is used to execute the wireless network quality assessment method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the wireless network quality assessment method according to any one of claims 1 to 7.

Images