Network quality evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides a network quality evaluation method and device, electronic equipment and a storage medium, and belongs to the technical field of communication, and the method comprises the steps: carrying out the feature vector combination of network quality indexes based on service experience indexes; taking the service experience index as input data, executing a preset decision tree algorithm to obtain a decision tree, and taking the decision tree as a prediction model; taking the residual error corresponding to the service experience index as input data, executing a preset decision tree algorithm to obtain a new decision tree, and updating the prediction model based on the new decision tree; returning to the step of taking the residual error corresponding to the business experience index as input data, executing the preset decision tree algorithm to obtain a new decision tree, and updating the prediction model based on the new decision tree until a preset stop condition is reached; and predicting the network quality based on the final prediction model. According to the invention, network quality evaluation is carried out according to the multi-source data, and the accuracy of network quality evaluation is improved by using an integration method of multiple decision trees.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a network quality assessment method, device, electronic equipment and storage medium. Background Art

[0002] Private networks are customized for specific scenarios such as enterprises, parks, and factories, and are designed to provide highly reliable, low-latency, and high-bandwidth communication services. Private Network Quality Assessment is an important technology for evaluating and optimizing private network performance. Quality assessment is a key link in ensuring private network performance and user experience. By regularly evaluating network quality, problems can be discovered and resolved in a timely manner, network configuration can be optimized, and network reliability and stability can be improved.

[0003] At present, the quality assessment of private networks is mainly carried out by collecting and analyzing real-time signaling and user plane data to build a three-layer general KPI perception evaluation model including network support layer, general performance layer and business scenario layer, and then using the weighted value calculation method to quantitatively evaluate different business categories and the overall network communication quality. However, this method only considers deep packet inspection (DPI) data, and the data source has limitations; and simply evaluating by weighting cannot accurately and effectively evaluate the user's perceived experience of private network services.

[0004] Therefore, a network quality assessment method is urgently needed to solve the problems of limited data sources and inaccurate service perception assessment in existing private network quality assessment schemes. Summary of the invention

[0005] The present invention provides a network quality assessment method, device, electronic device and storage medium, which are used to solve the defects of the prior art private network quality assessment scheme, such as limited data source and inaccurate network quality assessment.

[0006] The present invention provides a network quality assessment method, comprising the following steps: Based on the service experience index, characteristic vector combinations are performed on the network quality index related to the service experience in order to obtain a target matrix, wherein the service experience index is index data reflecting user experience, and the network quality index is index data reflecting network quality determined based on deep data packet inspection data; Using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; Taking the residual corresponding to the target matrix as input data, executing the preset decision tree algorithm, and obtaining a second decision tree, updating the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result of the prediction model and the actual result; After determining a new residual based on the first decision tree, iteratively updating the first decision tree through the second decision tree until a preset stopping condition is reached; The service quality is predicted based on the iteratively updated first decision tree.

[0007] According to a network quality assessment method provided by the present invention, the execution steps of the preset decision tree algorithm specifically include: The first network quality indicator is used as the current network quality indicator; For the input data, segmenting is performed based on the current network quality indicator to obtain a first area and a second area so as to minimize a loss function value, wherein the loss function value is determined based on the sum of a mean square error of the first area and a mean square error of the second area; The next network quality indicator of the current network quality indicator is used as the new current network quality indicator, and the process returns to the step of dividing based on the current network quality indicator to obtain the first area and the second area, until the last network quality indicator is processed and a decision tree is obtained.

[0008] According to a network quality evaluation method provided by the present invention, the network quality indicator related to the service experience is determined based on the following steps: For the service experience index and network quality index, the correlation coefficient is calculated between them, and we get dimensional correlation matrix, the service experience indicator includes service experience sampling data of n periods, the network quality indicator includes network quality sampling data corresponding to the n periods, and n is a positive integer; Based on the correlation coefficients with a mapping relationship, a correction calculation is performed on the correlation coefficients without a mapping relationship, and the service experience sampling data of the i-th period and the network quality sampling data corresponding to the i-th period have a mapping relationship, i is a positive integer, 0<i≤n; If the corrected correlation coefficient is greater than a preset correlation threshold, it is determined that the network quality indicator is a network quality indicator related to the service experience.

[0009] According to a network quality assessment method provided by the present invention, the correction calculation of the correlation coefficients that do not have a mapping relationship based on the correlation coefficients that have a mapping relationship includes: Based on the business experience sampling data and network quality sampling data that have a mapping relationship, the correlation prediction model is trained; Use the trained correlation prediction model to predict the service experience sampling data and network quality sampling data that do not have a mapping relationship. Based on the prediction results, the corrected correlation coefficient is calculated.

[0010] According to a network quality evaluation method provided by the present invention, the service experience index includes video clarity, number of pauses within a cycle time and picture quality.

[0011] According to a network quality evaluation method provided by the present invention, the service experience index includes a control success mark, an operation failure mark and a control perception delay.

[0012] The present invention also provides a network quality assessment device, comprising the following modules: A matrix generation module is used to: based on a service experience index, sequentially combine characteristic vectors of network quality indicators related to the service experience to obtain a target matrix, wherein the service experience index is indicator data reflecting user experience, and the network quality index is indicator data reflecting network quality determined based on deep data packet inspection data; A decision tree generation module is used to: use the target matrix as input data, execute a preset decision tree algorithm, and obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; A model updating module is used to: take the residual corresponding to the target matrix as input data, execute the preset decision tree algorithm, obtain a second decision tree, and then update the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result and the actual result of the prediction model; An iteration module, configured to: after determining a new residual based on the first decision tree, iteratively update the first decision tree through the second decision tree until a preset stop condition is reached; The network prediction module is used to predict the service quality based on the iteratively updated first decision tree.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned network quality assessment methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the network quality assessment method described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the network quality assessment method described above is implemented.

[0016] The network quality assessment method, device, electronic device and storage medium provided by the present invention, based on the service experience index, sequentially combine the characteristic vectors of the network quality index related to the service experience to obtain a target matrix, wherein the service experience index is the index data reflecting the user experience, and the network quality index is the index data reflecting the network quality determined based on the deep data packet detection data; the target matrix is ​​used as input data, and a preset decision tree algorithm is executed to obtain a first decision tree, and the preset decision tree algorithm is an algorithm for generating a decision tree; the residual corresponding to the target matrix is ​​used as input data, and the preset decision tree algorithm is executed to obtain a second decision tree, and then the first decision tree is updated based on the second decision tree, and the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the predicted result and the actual result of the prediction model; after determining the new residual based on the first decision tree, the first decision tree is iteratively updated through the second decision tree until a preset stop condition is reached; based on the iteratively updated first decision tree, the service quality is predicted. This solution evaluates network quality based on business experience indicators that reflect user experience and network quality data that is strongly correlated with business experience data. The diversified data sources can more accurately evaluate private network business perception. The integrated method of multiple decision trees is used to compensate for the deviation of a single model and to construct a stable and accurate business experience and network quality calculation relationship model, which improves the model's accuracy and generalization ability, thereby further improving the accuracy of network quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the network quality assessment method provided by the present invention; Figure 2 This is the second flow chart of the network quality assessment method provided by the present invention; Figure 3 It is a structural schematic diagram of the prediction model provided by the present invention; Figure 4 It is a hierarchical schematic diagram of the correlation between network quality indicators and service experience provided by the present invention; Figure 5is a schematic diagram of the mapping quantization relationship provided by the present invention; Figure 6 is a schematic diagram of non-mapping quantization relationship correction provided by the present invention; Figure 7 is a schematic diagram of the corrected quantization relationship provided by the present invention; Figure 8 It is a structural schematic diagram of the network quality assessment device provided by the present invention.

[0019] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be noted that in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be a connection between two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0023] Combine the following Figure 1-Figure 9 The network quality assessment method, device, electronic device and storage medium provided by the embodiments of the present invention are described.

[0024] Figure 1 is one of the flow charts of the network quality assessment method provided by the present invention, such as Figure 1 As shown, the network quality assessment method may include the following steps: S110, based on the service experience indicator, sequentially combining characteristic vectors of network quality indicators related to the service experience to obtain a target matrix; S120, using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree; S130, using the residual corresponding to the target matrix as input data, executing the preset decision tree algorithm, obtaining a second decision tree, and updating the first decision tree based on the second decision tree; S140, after determining a new residual based on the first decision tree, iteratively updating the first decision tree through the second decision tree until a preset stop condition is reached; S150: predicting service quality based on the iteratively updated first decision tree.

[0025] It should be noted that the execution subject of the network quality assessment method provided in the embodiment of the present invention can be a server, a computer device, such as a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc.

[0026] In an embodiment of the present invention, the service experience indicator is an indicator data reflecting the user experience. For example, observable service experience data can be obtained for MEP (Multi-access Edge Computing Platform), that is, a series of performance indicators and user experience feedback generated when users use services provided based on the MEP platform, such as high-definition video freezes, remote control response conditions, etc.

[0027] In the embodiment of the present invention, the network quality indicator is an indicator data reflecting the network quality determined based on deep packet inspection (DPI) data; the network quality indicator related to the service experience is a network quality indicator that is strongly related to the service experience.

[0028] In S110, for the service experience indicators and the network quality indicators related to the service experience, high-dimensional feature vectors are combined according to a certain type of service experience indicators. For example, assuming that the network quality indicators related to the service experience include the network layer data packet size B, packet interval Z, uplink and downlink RTT delay RD, uplink and downlink retransmission rate R and uplink and downlink rate U of the transmission pipeline, according to the video freeze situation, high-dimensional feature vectors are combined to obtain the target matrix L R , as the input data for the entire model training: .

[0029] In S120, the preset decision tree algorithm is an algorithm for generating a decision tree, and the service experience index in the target matrix.

[0030] In S130, the residual is a difference between the service experience indicator and a predicted value, and the predicted value is a prediction result of the first decision tree.

[0031] In S140, a new residual is calculated based on the updated first decision tree, and the new residual is used as input data to execute the preset decision tree algorithm. After obtaining a new second decision tree, the first decision tree is updated again based on the new second decision tree, and so on, until the preset iteration stop condition is reached (such as reaching the number of iterations and the residual is less than the preset threshold), and the obtained first decision tree is the final prediction model.

[0032] Figure 3 It is a schematic diagram of the structure of the prediction model provided by the present invention, such as Figure 3 As shown in the figure, when a service experience sample is input, the prediction model starts from the root node, selects the corresponding path according to the feature judgment conditions corresponding to each node, and calculates the difference between multiple decision trees to realize the construction of the calculation relationship model between the service experience index and the network quality index.

[0033] In S150, based on the first decision tree obtained by the final iterative update, the mapping of network quality indicators to service experience indicators is realized, and based on the network quality data that can be monitored and obtained in the private network, the service quality of the private network is evaluated, and the service perception of the user when using the private network is quantified.

[0034] The network quality assessment method provided by the embodiment of the present invention is based on the service experience index, and the network quality index related to the service experience is sequentially combined with the characteristic vectors to obtain a target matrix, wherein the service experience index is the index data reflecting the user experience, and the network quality index is the index data reflecting the network quality determined based on the deep data packet detection data; the target matrix is ​​used as input data, and a preset decision tree algorithm is executed to obtain a first decision tree, and the preset decision tree algorithm is an algorithm for generating a decision tree; the residual corresponding to the target matrix is ​​used as input data, and the preset decision tree algorithm is executed to obtain a second decision tree, and then the first decision tree is updated based on the second decision tree, and the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the predicted result and the actual result of the prediction model; after determining the new residual based on the first decision tree, the first decision tree is iteratively updated through the second decision tree until the preset stop condition is reached; based on the iteratively updated first decision tree, the service quality is predicted. This solution evaluates network quality based on business experience indicators that reflect user experience and network quality data that is strongly correlated with business experience data. The diversified data sources can more accurately evaluate private network business perception. The integrated method of multiple decision trees is used to compensate for the deviation of a single model and to construct a stable and accurate business experience and network quality calculation relationship model, which improves the model's accuracy and generalization ability, thereby further improving the accuracy of network quality assessment.

[0035] In an optional embodiment, the execution steps of the preset decision tree algorithm specifically include: The first network quality indicator is used as the current network quality indicator; For the input data, segmenting is performed based on the current network quality indicator to obtain a first area and a second area so as to minimize a loss function value, wherein the loss function value is determined based on the sum of a mean square error of the first area and a mean square error of the second area; The next network quality indicator of the current network quality indicator is used as the new current network quality indicator, and the process returns to the step of dividing based on the current network quality indicator to obtain the first area and the second area, until the last network quality indicator is processed and a decision tree is obtained.

[0036] Specifically, for a certain service experience indicator feature j (specific value of the sampled service experience), the optimal split point s is optimized for the relevant network quality data, that is, after the network quality indicator is split by s, the mean square error of the service experience indicator values ​​of the two regions R1 and R2 is minimized: ; in, is the i-th network quality index value and the i-th service experience index value, is the mean value of the network quality index in region R1, is the mean value of network quality index in region R2; Afterwards, the optimal point addressing is further continued based on gradient descent hierarchical segmentation, and regions R1 and R2 are segmented based on the next network quality indicator respectively, and so on, until the last layer, to achieve the identification of the minimum interval relationship between a certain service experience indicator value and the network quality indicator value on the gradient decision tree.

[0037] For ease of understanding, the decision tree algorithm provided by the embodiment of the present invention is described below with reference to specific examples: Assume that the sample values ​​of the jamming frequency of the service experience indicator are vectorized according to the related indicators (packet size, packet interval, RTT delay, retransmission rate and transport layer rate); The packet size is used as the current network quality indicator. The jamming frequency is divided into two groups according to the packet size cut-off point. The ones greater than a certain value [y, +∞] are group R1, and the ones less than the value [-∞, y] are group R2. The discreteness of the jamming frequency in each group is minimized, that is, the mean square error is minimized. The next network quality indicator, namely the packet interval, is used as the new current network quality indicator. R1 is further divided according to the packet interval. The group R11 is smaller than a certain value [y, y1], and the group R12 is larger than the value [y1, +∞], so that the discreteness of the jamming frequency of R11 and R12 is minimized. R2 is also divided according to the packet interval to obtain regions R21 and R22, so that the discreteness of the jamming frequency of R21 and R22 is minimized. In this way, the segmentation is performed according to the RTT delay, retransmission rate and transport layer rate until the last layer of processing is completed, that is, until the segmentation according to the transport layer rate is completed, a decision tree is obtained to calculate the mapping relationship between the network quality index and the video freeze frequency.

[0038] The network quality assessment method provided by the embodiment of the present invention realizes the identification of the minimum interval relationship between a certain service experience indicator value and a network quality indicator value on a gradient decision tree through regional segmentation of service experience feature vectors and related service quality indicators, and continues to perform optimal point addressing based on gradient descent hierarchical segmentation, thereby providing a basis for subsequent network quality assessment.

[0039] In an optional embodiment, the service experience index includes video clarity, number of pauses within a cycle time, and picture quality.

[0040] In the embodiment of the present invention, for video surveillance services, which are continuous services, a fixed and configurable time period T is set for matrix quantization of viewing experience L, and viewing experience sampling data is formed according to video definition M, number of pauses K within the period, and picture quality H (such as screen distortion): .

[0041] In an optional embodiment, the service experience indicator includes a control success flag, an operation failure flag, and a control perception delay.

[0042] In the embodiment of the present invention, for interactive control services, which belong to event-triggered services, the matrix quantization of the interactive experience C takes the event abnormality trigger as a cycle, and forms interactive experience sampling data according to the control success S flag, the operation failure F flag and the control perception delay D: .

[0043] In an optional embodiment, the network quality indicator related to the service experience is determined based on the following steps: For the service experience index and network quality index, the correlation coefficient is calculated between them, and we get dimensional correlation matrix, the service experience indicator includes service experience sampling data of n periods, the network quality indicator includes network quality sampling data corresponding to the n periods, and n is a positive integer; Based on the correlation coefficients with a mapping relationship, a correction calculation is performed on the correlation coefficients without a mapping relationship, and the service experience sampling data of the i-th period and the network quality sampling data corresponding to the i-th period have a mapping relationship, i is a positive integer, 0<i≤n; If the corrected correlation coefficient is greater than a preset correlation threshold, it is determined that the network quality indicator is a network quality indicator related to the service experience.

[0044] In the embodiment of the present invention, for the DPI data collected by the 5G private network user plane (N3), the XDR (eXtended Data Record) call list and the original code stream are associated according to time, terminal information, etc., and the network layer packet number N, packet size B, and packet interval Z corresponding to the service experience data can be obtained, and the uplink and downlink TCP link establishment delay CD, uplink and downlink RTT delay RD, uplink and downlink retransmission rate R, uplink and downlink disorder rate O and uplink and downlink rate U of the transmission pipeline corresponding to the service experience data are obtained to form the network quality sampling data corresponding to the service: .

[0045] The service experience sampling data and network quality sampling data of different dimensions are correlated with each other using a preset correlation coefficient calculation method (such as the Pearson coefficient) to form a correlation matrix as shown in Table 1.

[0046] Table 1 Correlation matrix

[0047] Here, after the correlation matrix is ​​calculated, the correlation quantification results with a mapping relationship (i.e., the correlation coefficient Correl (L ti , C i , P i )), and the relevant quantification results that do not have a mapping relationship (that is, the correlation coefficients of the non-diagonal positions in the matrix) are corrected and calculated, and finally the network quality indicators that are strongly correlated with the service experience are determined based on the corrected correlation coefficients.

[0048] Optionally, the correlation between the network quality indicator and the service experience is divided into multiple levels according to the correlation coefficient, and the network quality indicator of the preset level is determined to be the network quality indicator related to the service experience.

[0049] Figure 4 : is a hierarchical schematic diagram of the correlation between network quality indicators and service experience provided by the present invention, such as Figure 4 As shown, the association relationship is divided into 9 levels from Class-4 to Class4, among which Class0 is not cared about, Class1, Class2, Class-1, Class-2 are slightly related, and Class3, Class4, Class-3, Class-4 are strongly related.

[0050] Figure 5 is a schematic diagram of the mapping quantization relationship provided by the present invention; Figure 6 is a schematic diagram of non-mapping quantization relationship correction provided by the present invention; Figure 7 is a schematic diagram of the corrected quantization relationship provided by the present invention; like Figure 5-Figure 7 As shown, the correlation coefficient between the uplink RTT delay and the corrected video sending rate is 0.42, which is greater than the preset correlation threshold (0.4), and it is determined that the uplink RTT delay is a network quality indicator related to the service experience.

[0051] The network quality assessment method provided in the embodiment of the present invention is based on the network quality data provided by DPI and the service perception data of MEP (card disconnection, screen distortion, control plane protocol success rate, control protocol response delay, etc.). Through the correctable Pearson algorithm, the network quality data that is strongly correlated with the service experience data is quickly and accurately found, thereby avoiding subsequent network quality assessment based on irrelevant or weakly correlated data. On the one hand, the calculation amount of subsequent network quality assessment is reduced, and on the other hand, the accuracy of network quality assessment is improved.

[0052] In an optional embodiment, the correction calculation of the correlation coefficients that do not have a mapping relationship based on the correlation coefficients that have a mapping relationship includes: Based on the business experience sampling data and network quality sampling data that have a mapping relationship, the correlation prediction model is trained; Use the trained correlation prediction model to predict the service experience sampling data and network quality sampling data that do not have a mapping relationship. Based on the prediction results, the corrected correlation coefficient is calculated.

[0053] Specifically, the data with a mapping relationship is used as a benchmark to correct the data without a mapping relationship. The correction method can be linear regression, proportional adjustment, etc. Taking linear regression as an example, the service experience sampling data and network quality sampling data with a mapping relationship are used to train a linear regression model, and the trained linear regression model is used to predict the data without a mapping relationship, and the correlation coefficient is corrected according to the prediction result.

[0054] The network quality assessment method provided by the embodiment of the present invention effectively uses data with a mapping relationship to perform correction calculations on data without a mapping relationship, thereby improving the accuracy and reliability of the data and providing a reliable data basis for the subsequent determination of network quality indicators that are correlated with the service experience.

[0055] Figure 2 This is the second flow chart of the network quality assessment method provided by the present invention. Figure 2 , the preferred network quality assessment method process of the present invention is described.

[0056] The service experience data of MEP is processed by matrix quantization to form service experience data labels. The network DPI data and network element performance data during service transmission are quantitatively analyzed to form network quality label data. The two types of data are analyzed for correlation through a correlation algorithm to obtain network quality data that is strongly correlated with the service experience data. Based on the two types of correlated data, the mapping relationship between the service experience data and the network quality data is trained through a decision tree algorithm to obtain a prediction model for the service experience data and the network quality data. The network quality data collected and analyzed in real time is combined with the prediction model to derive the service experience data of the entire network, and combined with the network quality data to support the quantitative analysis of the network quality of the service experience.

[0057] The network quality assessment device provided by an embodiment of the present invention is described below. The network quality assessment device described below and the network quality assessment method described above can be referenced to each other.

[0058] Figure 8 is a schematic diagram of the structure of the network quality assessment device provided by the present invention, such as Figure 8 As shown, the network quality assessment device may include but is not limited to; The matrix generation module 810 is used to: based on the service experience index, sequentially combine the characteristic vectors of the network quality index related to the service experience to obtain a target matrix, wherein the service experience index is the index data reflecting the user experience, and the network quality index is the index data reflecting the network quality determined based on the deep data packet inspection data; A decision tree generation module 820 is used to: use the target matrix as input data, execute a preset decision tree algorithm, and obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; A model updating module 830 is used to: use the residual corresponding to the target matrix as input data, execute the preset decision tree algorithm, obtain a second decision tree, and then update the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result and the actual result of the prediction model; An iteration module 840 is used to: after determining a new residual based on the first decision tree, iteratively update the first decision tree through the second decision tree until a preset stop condition is reached; The network prediction module 850 is used to predict service quality based on the iteratively updated first decision tree.

[0059] It should be noted that the network quality assessment device provided in the embodiment of the present invention can execute the network quality assessment method described in any of the above embodiments during specific operation, which will not be described in detail in this embodiment.

[0060] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute the network quality evaluation method, which includes: based on the service experience index, sequentially combining the characteristic vectors of the network quality index related to the service experience to obtain the target matrix, wherein the service experience index is the index data reflecting the user experience, and the network quality index is the index data reflecting the network quality determined based on the deep data packet inspection data; Using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; Taking the residual corresponding to the target matrix as input data, executing the preset decision tree algorithm, and obtaining a second decision tree, updating the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result of the prediction model and the actual result; After determining a new residual based on the first decision tree, iteratively updating the first decision tree through the second decision tree until a preset stopping condition is reached; The service quality is predicted based on the iteratively updated first decision tree.

[0061] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0062] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the network quality evaluation method provided by the above methods, the method comprising: based on a service experience indicator, sequentially combining feature vectors of network quality indicators related to the service experience to obtain a target matrix, the service experience indicator is indicator data reflecting user experience, and the network quality indicator is indicator data reflecting network quality determined based on deep data packet inspection data; Using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; Taking the residual corresponding to the target matrix as input data, executing the preset decision tree algorithm, and obtaining a second decision tree, updating the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result of the prediction model and the actual result; After determining a new residual based on the first decision tree, iteratively updating the first decision tree through the second decision tree until a preset stopping condition is reached; The service quality is predicted based on the iteratively updated first decision tree.

[0063] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the network quality evaluation method provided by the above methods, the method comprising: based on a service experience indicator, sequentially combining feature vectors of network quality indicators related to the service experience to obtain a target matrix, wherein the service experience indicator is indicator data reflecting user experience, and the network quality indicator is indicator data reflecting network quality determined based on deep data packet inspection data; Using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; Taking the residual corresponding to the target matrix as input data, executing the preset decision tree algorithm, and obtaining a second decision tree, updating the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result of the prediction model and the actual result; After determining a new residual based on the first decision tree, iteratively updating the first decision tree through the second decision tree until a preset stopping condition is reached; The service quality is predicted based on the iteratively updated first decision tree.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A network quality assessment method, characterized in that: include: Based on the service experience index, characteristic vector combinations are performed on the network quality index related to the service experience in order to obtain a target matrix, wherein the service experience index is index data reflecting user experience, and the network quality index is index data reflecting network quality determined based on deep data packet inspection data; Using the target matrix as input data, executing a preset decision tree algorithm to obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; The residual corresponding to the target matrix is ​​used as input data, the preset decision tree algorithm is executed, and after obtaining the second decision tree, the first decision tree is updated based on the second decision tree, the residual is the difference between the service experience index and the predicted value, and the predicted value is the prediction result of the first decision tree; after determining the new residual based on the first decision tree, the first decision tree is iteratively updated through the second decision tree until the preset stop condition is reached; based on the iteratively updated first decision tree, the service quality is predicted.

2. The network quality assessment method according to claim 1, characterized in that: The execution steps of the preset decision tree algorithm specifically include: The first network quality indicator is used as the current network quality indicator; For the input data, segmenting is performed based on the current network quality indicator to obtain a first area and a second area so as to minimize a loss function value, wherein the loss function value is determined based on the sum of a mean square error of the first area and a mean square error of the second area; The next network quality indicator of the current network quality indicator is used as the new current network quality indicator, and the process returns to the step of dividing based on the current network quality indicator to obtain the first area and the second area, until the last network quality indicator is processed and a decision tree is obtained.

3. The network quality assessment method according to claim 1, characterized in that: The network quality indicator related to the service experience is determined based on the following steps: For the service experience index and network quality index, the correlation coefficient is calculated between them, and we get dimensional correlation matrix, the service experience indicator includes service experience sampling data of n periods, the network quality indicator includes network quality sampling data corresponding to the n periods, and n is a positive integer; Based on the correlation coefficients with a mapping relationship, a correction calculation is performed on the correlation coefficients without a mapping relationship, and the service experience sampling data of the i-th period and the network quality sampling data corresponding to the i-th period have a mapping relationship, i is a positive integer, 0<i≤n; If the corrected correlation coefficient is greater than a preset correlation threshold, it is determined that the network quality indicator is a network quality indicator related to the service experience.

4. The network quality assessment method according to claim 3, characterized in that: The corrective calculation of the correlation coefficients that do not have a mapping relationship based on the correlation coefficients that have a mapping relationship includes: Based on the business experience sampling data and network quality sampling data that have a mapping relationship, the correlation prediction model is trained; Use the trained correlation prediction model to predict the service experience sampling data and network quality sampling data that do not have a mapping relationship. Based on the prediction results, the corrected correlation coefficient is calculated.

5. The network quality assessment method according to any one of claims 1 to 4, characterized in that: The service experience indicators include video clarity, the number of pauses within a cycle time, and picture quality.

6. The network quality assessment method according to any one of claims 1 to 4, characterized in that: The service experience indicators include a control success indicator, an operation failure indicator, and a control perception delay.

7. A network quality assessment device, characterized in that: include: A matrix generation module is used to: based on a service experience index, sequentially combine characteristic vectors of network quality indicators related to the service experience to obtain a target matrix, wherein the service experience index is indicator data reflecting user experience, and the network quality index is indicator data reflecting network quality determined based on deep data packet inspection data; A decision tree generation module is used to: use the target matrix as input data, execute a preset decision tree algorithm, and obtain a first decision tree, wherein the preset decision tree algorithm is an algorithm for generating a decision tree; A model updating module is used to: take the residual corresponding to the target matrix as input data, execute the preset decision tree algorithm, obtain a second decision tree, and then update the first decision tree based on the second decision tree, wherein the residual is the difference between the service experience index and the loss value, and the loss value is calculated based on the prediction result and the actual result of the prediction model; An iteration module, configured to: after determining a new residual based on the first decision tree, iteratively update the first decision tree through the second decision tree until a preset stop condition is reached; The network prediction module is used to predict the service quality based on the iteratively updated first decision tree.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the network quality assessment method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the network quality assessment method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the network quality assessment method according to any one of claims 1 to 6 is implemented.

Images