Quality of experience evaluation method and system based on incremental learning and dynamic updating

Abstract

An experience of quality (QoE) evaluation method and system based on incremental learning and dynamic updating. The method comprises raw data acquisition, data preprocessing, data mining, and construction of a width forest-based QoE prediction model. When the constructed QoE prediction model cannot reach the required performance in the actual application, an existing width forest is dynamically updated by means of incremental learning, and under the condition that user data is continuously increased, the weight is updated only for a new input in an incremental learning mode.

Description

User experience quality evaluation method and system based on incremental learning and dynamic updating Technical Field

[0001] The present invention relates to the field of user experience quality assessment, and in particular to a method and system for user experience quality assessment based on incremental learning and dynamic updating. Background Art

[0002] As the user base grows, users' expectations for service experience are becoming increasingly demanding. To improve user retention and market competitiveness, businesses and operators urgently need a suitable quality evaluation system to reflect and characterize users' evaluation and experience of the quality of current services. Quality of Experience (QoE) is defined as "the overall acceptability of an application or service to end users." For example, in IPTV scenarios, QoE is influenced not only by objective network factors such as bit rate, latency, and packet loss rate, but also by subjective user factors and those influenced by the user's environment. In recent years, user-centric QoE has become the preferred strategy for evaluating operator services. By proactively monitoring user QoE, operators can better understand user needs, improve service quality, and enhance market competitiveness.

[0003] The traditional method for measuring QoE is through user satisfaction surveys, but these require high user satisfaction and lack real-time performance, which doesn't meet the needs of operators. Therefore, it's necessary to research QoE evaluation methods to achieve real-time, accurate analysis and prediction of user QoE, thereby improving services and ultimately enhancing the user experience.

[0004] Therefore, there is a need for methods and systems that can improve upon the deficiencies in the prior art.

[0005] Summary of the Invention

[0006] This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0007] In response to the technical problems in the existing technology, the technical solution in this disclosure is based on the theoretical background of machine learning algorithms and provides a method for evaluating the quality of user experience in a big data environment, thereby realizing real-time and accurate analysis and prediction of user QoE, thereby improving services and ultimately enhancing user experience.

[0008] Specifically, in one embodiment of the present invention, a method for evaluating user quality of experience (QoE) is provided, the method comprising:

[0009] Get user data;

[0010] Extract key parameters from the acquired user data;

[0011] By taking these key parameters as input data, a user QoE prediction model based on width forest is constructed, which includes feature layer forest and enhancement layer forest;

[0012] Adaptively and iteratively expanding the enhancement layer forest to strengthen the user QoE prediction model when the user QoE prediction model fails to achieve required performance;

[0013] Continuously acquiring new user data and updating the enhanced user QoE prediction model based on the new user data; and

[0014] The user data to be predicted is input into the updated and enhanced user QoE prediction model to obtain the final user QoE prediction result.

[0015] In one embodiment of the present invention, acquiring user data further includes cleaning and standardizing the acquired user data.

[0016] In one embodiment of the present invention, extracting key parameters from the acquired user data further includes extracting key parameters that affect user QoE using data mining technology, wherein the key parameters are extracted by comparing the relationship between data and targets using a Pearson correlation coefficient method.

[0017] In one embodiment of the present invention, constructing the width forest-based user QoE prediction model further includes: constructing the feature layer forest and the enhancement layer forest and estimating the connection weights of the feature layer forest and the enhancement layer forest.

[0018] In the above embodiment of the present invention, constructing the feature layer forest and the enhancement layer forest and estimating the connection weights of the feature layer forest and the enhancement layer forest further includes:

[0019] Initialize each forest;

[0020] Training the feature layer forest based on the input data to generate corresponding prediction probabilities and compressing the input data into important feature data;

[0021] Using the important feature data and the predicted probability as inputs of the enhancement layer forest to train the enhancement layer forest; and

[0022] The probability matrix of the class distribution estimated by the feature layer forest and the enhancement layer forest is combined as the input of the final layer and the connection weight is determined by taking the pseudo inverse of the input.

[0023] In one embodiment of the present invention, adaptively and iteratively expanding the enhancement layer forest further comprises:

[0024] Based on the new output of the expanded enhancement layer forest and the mapping relationship between the new output and the new input of the expanded enhancement layer forest, pseudo-inverse is obtained for the new input to update the connection weights of the enhancement layer forest;

[0025] Verify whether the expanded enhancement layer forest brings significant performance improvement by comparing the average out-of-bag error of all forest groups; and

[0026] The enhancement layer forest is continued to be expanded when the out-of-bag error is significantly reduced and the enhancement layer forest is stopped to be expanded when the out-of-bag error is almost unchanged.

[0027] In the above embodiments of the present invention, the feature layer forest is expanded in the same manner when the expanded enhancement layer forest cannot achieve the required performance.

[0028] In one embodiment of the present invention, updating the enhanced user QoE prediction model based on the new user data further includes:

[0029] The new user data is used as input to the feature layer forest and the enhancement layer forest to obtain output;

[0030] representing a new input based on the output; and

[0031] The new input is added to the input matrix of the width forest and the pseudo-inverse of the input matrix is ​​calculated to update the connection weights of the width forest.

[0032] In another embodiment of the present invention, a system for evaluating user experience quality (QoE) is provided, the system comprising:

[0033] A user data acquisition module configured to acquire user data;

[0034] A key parameter extraction module configured to extract key parameters from the acquired user data;

[0035] A user QoE prediction model building module is configured to build a user QoE prediction model based on a width forest by taking the key parameters as input data, where the width forest includes a feature layer forest and an enhancement layer forest;

[0036] The user QoE prediction model enhancement and update module is configured to:

[0037] Adaptively and iteratively expanding the enhancement layer forest to strengthen the user QoE prediction model when the user QoE prediction model fails to achieve required performance; and

[0038] Continuously acquiring new user data and updating the enhanced user QoE prediction model based on the new user data; and

[0039] The user QoE prediction module is configured to input the to-be-predicted user data into the updated and enhanced user QoE prediction model to obtain a final user QoE prediction result.

[0040] In one embodiment of the present invention, the user QoE prediction model construction module is further configured to construct the width forest-based user QoE prediction model by constructing the feature layer forest and the enhancement layer forest and estimating the connection weights of the feature layer forest and the enhancement layer forest, and the user QoE prediction model construction module is further configured to construct the feature layer forest and the enhancement layer forest and estimate the connection weights of the feature layer forest and the enhancement layer forest by the following operations:

[0041] Initialize each forest;

[0042] Training the feature layer forest based on the input data to generate corresponding prediction probabilities and compressing the input data into important feature data;

[0043] Using the important feature data and the predicted probability as inputs of the enhancement layer forest to train the enhancement layer forest; and

[0044] The probability matrix of the class distribution estimated by the feature layer forest and the enhancement layer forest is combined as the input of the final layer and the connection weight is determined by taking the pseudo inverse of the input.

[0045] In one embodiment of the present invention, the user QoE prediction model enhancement and update module is further configured to adaptively and iteratively expand the enhancement layer forest by performing the following operations:

[0046] Based on the new output of the expanded enhancement layer forest and the mapping relationship between the new output and the new input of the expanded enhancement layer forest, pseudo-inverse is obtained for the new input to update the connection weights of the enhancement layer forest;

[0047] Verify whether the expanded enhancement layer forest brings significant performance improvement by comparing the average out-of-bag error of all forest groups; and

[0048] The enhancement layer forest is continued to be expanded when the out-of-bag error is significantly reduced and the enhancement layer forest is stopped to be expanded when the out-of-bag error is almost unchanged.

[0049] In one embodiment of the present invention, the user QoE prediction model enhancement and update module is further configured to update the enhanced user QoE prediction model based on the new user data by:

[0050] The new user data is used as input to the feature layer forest and the enhancement layer forest to obtain output;

[0051] representing a new input based on the output; and

[0052] The new input is added to the input matrix of the width forest and the pseudo-inverse of the input matrix is ​​calculated to update the connection weights of the width forest.

[0053] In yet another embodiment of the present invention, a computer-readable medium storing computer-executable instructions is provided, the instructions comprising:

[0054] Instructions for obtaining user data;

[0055] Instructions for extracting key parameters from the acquired user data;

[0056] Instructions for constructing a user QoE prediction model based on a width forest by using the key parameters as input data, the width forest including a feature layer forest and an enhancement layer forest;

[0057] Instructions for adaptively and iteratively expanding the enhancement layer forest to strengthen the user QoE prediction model when the user QoE prediction model fails to achieve required performance;

[0058] Instructions for continuously acquiring new user data and updating the enhanced user QoE prediction model based on the new user data; and

[0059] Instructions for inputting the to-be-predicted user data into the updated and enhanced user QoE prediction model to obtain a final user QoE prediction result.

[0060] After studying the description of specific exemplary embodiments of the present invention below in conjunction with the accompanying drawings, other aspects, features and embodiments of the present invention will be apparent to those of ordinary skill in the art. Although features of the present invention may be discussed below with respect to certain embodiments and drawings, all embodiments of the present invention may include one or more of the advantageous features discussed herein. In other words, although one or more embodiments may be discussed as having certain advantageous features, one or more of such features may also be used according to the various embodiments of the present invention discussed herein. In a similar manner, although exemplary embodiments may be discussed below as device, system or method embodiments, it should be appreciated that such exemplary embodiments may be implemented in various devices, systems, and methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order that the manner in which the above-recited features of the present disclosure may be understood in detail, a more particular description of the content briefly summarized above may be obtained by reference to various aspects, some of which are illustrated in the accompanying drawings. It should be noted, however, that the drawings illustrate only certain typical aspects of the disclosure and are therefore not to be considered limiting of its scope, as the description may admit to other equally effective aspects.

[0062] FIG1 shows a schematic block diagram of a system for user QoE evaluation according to an embodiment of the present disclosure.

[0063] FIG2 shows a schematic diagram of dynamically adding enhancement layer forests based on adaptive incremental learning according to an embodiment of the present disclosure.

[0064] FIG3 shows a schematic diagram of dynamically adding feature layer forests based on adaptive incremental learning according to an embodiment of the present disclosure.

[0065] FIG4 shows a schematic diagram of adding input user data according to an embodiment of the present disclosure.

[0066] FIG5 shows a flowchart of a method for user QoE evaluation according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0067] The various embodiments will be described in more detail below with reference to the accompanying drawings that form a part of the present invention and illustrate specific exemplary embodiments. However, the embodiments may be implemented in many different forms and should not be construed as limiting the embodiments set forth herein; rather, these embodiments are provided so that this disclosure is thorough and complete and the scope of these embodiments is fully conveyed to those skilled in the art. The embodiments may be implemented as a method, system, or device. Accordingly, the embodiments may be implemented in hardware, in full software, or in a combination of software and hardware. Therefore, the following detailed description is not intended to be limiting.

[0068] The steps in each flowchart may be performed by hardware (e.g., a processor, an engine, a memory, a circuit), software (e.g., an operating system, an application, a driver, a machine / processor executable instruction), or a combination thereof. As will be understood by those skilled in the art, the methods involved in each embodiment may include more or fewer steps than shown.

[0069] To address the shortcomings of the existing technology, the present invention proposes a user experience quality assessment method based on big data incremental learning. This method includes raw data collection, data preprocessing, data mining, and the construction of a user QoE prediction model based on a width forest. Data mining is used to extract key parameters affecting user QoE, reducing model complexity. The width forest algorithm is applied to user experience quality of experience (QoE) assessment to improve the accuracy of user QoE prediction. Furthermore, considering the large and complex volume of user data in the context of big data, when the width forest algorithm cannot achieve the required performance in practical applications, the existing width forest is modified using the concept of incremental learning. Two methods are used: 1. Dynamically adding enhancement layer forests based on adaptive incremental learning; 2. Dynamically adding feature layer forests based on adaptive incremental learning to adaptively tune the model, further improving the accuracy of user QoE prediction in complex big data environments. Furthermore, considering the continuous increase in user data, incremental learning is used to update weights only for new inputs, rather than retraining the entire model, saving computational cost and time.

[0070] The various aspects of the present disclosure will be described in more detail and comprehensively below through block diagrams and method flow charts.

[0071] FIG1 shows a schematic block diagram of a system 100 for user QoE evaluation according to an embodiment of the present disclosure.

[0072] As shown in FIG. 1 , the system 100 may include a user data acquisition module 102 , a key parameter extraction module 104 , a user QoE prediction model construction module 106 , a user QoE prediction model enhancement and update module 108 , and a user QoE prediction module 110 .

[0073] In one embodiment of the present invention, user data acquisition module 102 can be configured to obtain user data.As an example and not limitation, in the scene of IPTV, can utilize means such as set-top box probe to gather IPTV user viewing behavior and set-top box network status data.In this scene, can gather user viewing record with every 5 minutes interval by set-top box probe means, comprise the behavioral data such as user switching, pausing and the network status information data such as delay, jitter.In one embodiment of the present invention, obtaining user data can further comprise that the user data that is obtained is cleaned and standardized.In this embodiment, can the data collected be cleaned, comprise the meaningless data such as deduplication, deletion empty attribute, and utilize such as Z-Score zero mean normalization method that the data after cleaning is standardized, as shown in the following formula:

[0074] As those skilled in the art will appreciate, in other embodiments, any other suitable normalization method may be used to normalize the cleaned data, without being limited to the above method.

[0075] In one embodiment of the present invention, the key parameter extraction module 104 may be configured to extract key parameters from the acquired user data. In this embodiment, extracting key parameters from the acquired user data may further include utilizing data mining techniques to extract key parameters that affect user QoE. Specifically, as an example and not a limitation, the Pearson correlation coefficient method may be utilized to extract key factors that affect user QoE from the acquired user data by comparing the relationship between the data and the target. The stronger the correlation, the closer the correlation coefficient r is to 1, thereby mining the user data features. The formula is as follows:

[0076] In one embodiment of the present invention, the user QoE prediction model construction module 106 can be configured to construct a user QoE prediction model based on a width forest using these key parameters as input data. In one embodiment of the present invention, the width forest includes a feature layer forest and an enhancement layer forest. In this embodiment, the user QoE prediction model construction module 106 can be further configured to construct the user QoE prediction model based on the width forest by constructing the feature layer forest and the enhancement layer forest and estimating the connection weights between the feature layer forest and the enhancement layer forest. That is, the extracted key parameters are used as input data, and a training data set and a test data set are divided for constructing the user QoE prediction model. First, a width forest is constructed based on the training data, and the process includes constructing the feature layer forest, constructing the enhancement layer forest, and estimating the connection weights.

[0077] Specifically, in one embodiment of the present invention, the user QoE prediction model construction module 106 may be further configured to construct the feature layer forest and the enhancement layer forest and estimate the connection weights of the feature layer forest and the enhancement layer forest by performing the following operations:

[0078] First, each forest is initialized. As an example, not a limitation, each forest can be initialized to 50 trees with no limit on tree depth. The feature-level forest can be composed of n groups of forests. Each group of forests can contain two different types of random forests, depending on how the training samples are drawn: a random forest (randomly drawn samples) and an extreme random forest (using all training samples).

[0079] Subsequently, the feature layer forest can be trained based on the input data to generate corresponding prediction probabilities and compress the input data into important feature data. Specifically, the IPTV user data input training set can be recorded as X∈R N×M , Y∈R N×K, where N represents the sample size, M represents the number of input features, and K represents the number of categories. The feature layer forest can generate n sets of prediction probabilities, expressed as Z n ={Z i} i＝1，...，n , where Z i ∈R N×2K , Z n ∈R N×2nK At the same time, the feature layer random forest can be used to select rM features with the highest importance scores (r is the feature selection ratio, which can be set to 0.8, for example), that is, the input data X∈R N×M Compressed to X′∈R N×γM .

[0080] Then, the important feature data and the predicted probability can be used as the input of the enhancement layer forest to train the enhancement layer forest. Specifically, the enhancement layer forest can be composed of m groups of random forests, which are the same as the feature layer forest, and each group contains a random forest and an extreme random forest. N×γM And the predicted output Z of the feature layer forest n , as the input of the enhancement layer forest, expressed as [Z n |X′]∈R N×(2nK+γM) , after enhanced layer forest training, the output H is obtained m ={H i} i=1，...，m , where H i ∈R N×2K , H m ∈R N×2mK .

[0081] Finally, the probability matrix of the class distribution estimated by the feature layer forest and the enhancement layer forest can be combined as the input of the final layer and the connection weight is determined by taking the pseudo-inverse of the input. Specifically, the probability matrix of the class distribution estimated by the feature layer forest and the enhancement layer forest is combined as the input of the final layer, which is expressed as [Z n |H m ]∈R N×(2nK+2mK) , the algorithm output is expressed as: in, Represents the connection weight of the width structure; by input data [Z n |H m ]Find pseudo-inverse to calculate connection weights Right now: [Z n |H m ] + =([Z n |H m ]·[Z n |Hm ] T +λI) -1 ·[Z n |H m ] T , where λ is the regularization parameter (which can be set to 10 by default, for example -3 ).

[0082] In the context of big data, due to the large amount and complexity of user data, the above-mentioned width forest may not be able to achieve the required performance, so it is necessary to consider adaptive tuning of the algorithm. At the same time, considering that user data will continue to be input over time, traditional algorithm models usually put new data and old trained data together, and retrain the entire algorithm model, which takes a lot of time and space. The idea of ​​incremental learning is to update the trained model based on the changes caused by new data or newly added structures of the model, rather than retraining. It is suitable for complex application scenarios of big data and saves computing resources while ensuring the accuracy of the model. This patent uses the idea of ​​incremental learning to transform the existing width forest based on a dynamic and gradually updated algorithm to improve the accuracy of user QoE prediction under big data.

[0083] Therefore, in one embodiment of the present invention, the user QoE prediction model enhancement and update module 108 may be configured to adaptively and iteratively expand the enhancement layer forest to enhance the user QoE prediction model when the user QoE prediction model fails to achieve the required performance. In this embodiment of the present invention, the user QoE prediction model enhancement and update module 108 may be further configured to adaptively and iteratively expand the enhancement layer forest by performing the following operations:

[0084] First, based on the new output of the expanded enhancement layer forest and the mapping relationship between the new output and the new input of the expanded enhancement layer forest, the pseudo-inverse of the new input can be calculated to update the connection weights of the enhancement layer forest. Specifically, FIG2 shows a schematic diagram of dynamically increasing the enhancement layer forest based on adaptive incremental learning according to an embodiment of the present disclosure. As shown in FIG2, the input of the constructed width forest is recorded as After the enhancement layer forest is expanded, the expanded forest obtains a new output, which is recorded as Among them, f(·) represents the mapping relationship between the input and output of the enhancement layer forest, f(Z n |X′) represents the output of the newly added enhancement layer forest. According to the pseudo-inverse principle of the partition matrix in the dynamic step-by-step update algorithm, the pseudo-inverse of the new input of the width forest is obtained:

[0085] In order to facilitate the above expression, D and B in the formula are T for:

[0086] Will Denote the connection weight of the width forest before updating as The updated weight is expressed as

[0087] Then, the average out-of-bag error of all forest groups can be compared to verify whether the expanded enhancement layer forest has brought significant performance improvement. If the out-of-bag error is significantly reduced, the enhancement layer forest can be continued to be expanded. If the out-of-bag error is almost unchanged (those skilled in the art can set a change threshold to define what is almost unchanged), the expansion of the enhancement layer forest can be stopped.

[0088] In another embodiment of the present invention, the user QoE prediction model enhancement and updating module 108 may be further configured to expand the feature layer forest in the same or similar manner if the expanded enhancement layer forest fails to achieve the required performance.

[0089] Specifically, FIG3 shows a schematic diagram of dynamically adding feature layer forests based on adaptive incremental learning according to an embodiment of the present disclosure. As shown in FIG3, adding feature layer forests can allow more forests to participate in feature selection decisions, utilizing the representation capabilities of more forests, and facilitating the extraction of more effective features. The predicted output of the added feature layer forest is denoted as Z n+1 , then the output of the corresponding enhanced forest layer is f(Z n+1 |X′). Therefore, the input of the updated width forest is Seeking false and counterfeit

[0090] Among them, D and B in the formula T for:

[0091] The updated connection weight is recorded as Then:

[0092] Therefore, in one embodiment of the present invention, the user QoE prediction model enhancement and update module 108 may be further configured to continuously acquire new user data and update the enhanced user QoE prediction model based on the new user data. In this embodiment, the user QoE prediction model enhancement and update module 108 may be further configured to update the enhanced user QoE prediction model based on the new user data by performing the following operations:

[0093] First, the new user data can be used as the input of the feature layer forest and the enhancement layer forest to obtain the output. Specifically, FIG4 shows a schematic diagram of adding input user data according to an embodiment of the present disclosure. As shown in FIG4, assuming that the new input training data is {X a , Y a}, the data dimension is N a , the outputs of the existing model, namely the n groups of feature layer forests and m groups of enhancement layer forests constructed above, are expressed as and Then, a new input can be represented based on the output. Specifically, the new input can be represented as A a =[Z a n |H a m ]. Finally, the new input can be added to the input matrix of the width forest and the pseudo-inverse of the input matrix can be calculated to update the connection weights of the width forest. Specifically, after adding the new input, the input matrix of the width forest becomes:

[0094] And according to the principle of finding pseudo-inverse by matrix partition, we can find the pseudo-inverse:

[0095] Where D and B in the formula T Respectively expressed as:

[0096] Accordingly, its updated weight is expressed as:

[0097] In one embodiment of the present invention, the user QoE prediction module 110 may be configured to input the to-be-predicted user data into the updated and enhanced user QoE prediction model to obtain a final user QoE prediction result.

[0098] FIG5 shows a flowchart of a method 500 for user QoE evaluation according to an embodiment of the present disclosure.

[0099] As shown in Figure 5, method 500 begins at step 502, where user data is obtained. In one embodiment of the present invention, obtaining user data may further include cleaning and standardizing the obtained user data.

[0100] Subsequently, method 500 proceeds to step 504, extracting key parameters from the acquired user data. In one embodiment of the present invention, extracting key parameters from the acquired user data may further include utilizing data mining techniques to extract key parameters that affect user QoE. The key parameters may be extracted by comparing the relationship between the data and the target using a Pearson correlation coefficient method.

[0101] Next, method 500 proceeds to step 506, where a width-forest-based user QoE prediction model is constructed using these key parameters as input data, the width-forest comprising a feature-layer forest and an enhancement-layer forest. In one embodiment of the present invention, constructing the width-forest-based user QoE prediction model further includes: constructing the feature-layer forest and the enhancement-layer forest and estimating the connection weights between the feature-layer forest and the enhancement-layer forest. In the above embodiment of the present invention, constructing the feature-layer forest and the enhancement-layer forest and estimating the connection weights between the feature-layer forest and the enhancement-layer forest further includes: initializing each forest; training the feature-layer forest based on the input data to generate corresponding prediction probabilities and compressing the input data into important feature data; training the enhancement-layer forest using the important feature data and the prediction probabilities as inputs to the enhancement-layer forest; and combining the probability matrices of the class distribution estimates of the feature-layer forest and the enhancement-layer forest as inputs to the final layer and determining the connection weights by taking the pseudo-inverse of the inputs.

[0102] Then, method 500 proceeds to step 508, where the enhancement layer forest is adaptively and iteratively expanded to strengthen the user QoE prediction model if the user QoE prediction model fails to achieve the required performance. In one embodiment of the present invention, adaptively and iteratively expanding the enhancement layer forest may further include: taking a pseudo-inverse of the new input of the expanded enhancement layer forest based on a new output of the expanded enhancement layer forest and a mapping relationship between the new output and the new input of the expanded enhancement layer forest to update the connection weights of the enhancement layer forest; verifying whether the expanded enhancement layer forest has achieved a significant performance improvement by comparing the average out-of-bag error of all forest groups; and continuing to expand the enhancement layer forest if the out-of-bag error is significantly reduced and stopping to expand the enhancement layer forest if the out-of-bag error is almost unchanged. In the above embodiment of the present invention, the feature layer forest is expanded in the same or similar manner if the expanded enhancement layer forest fails to achieve the required performance.

[0103] Next, method 500 proceeds to step 510, where new user data is continuously acquired and the enhanced user QoE prediction model is updated based on the new user data. In one embodiment of the present invention, updating the enhanced user QoE prediction model based on the new user data may further include: using the new user data as input to the feature layer forest and the enhancement layer forest to obtain an output; representing a new input based on the output; and adding the new input to the input matrix of the width forest and taking the pseudo-inverse of the input matrix to update the connection weights of the width forest.

[0104] Finally, the method 500 proceeds to step 512 , where the user data to be predicted is input into the updated and enhanced user QoE prediction model to obtain a final user QoE prediction result.

[0105] Method 500 ends after step 512 .

[0106] In summary, the present invention proposes a method for evaluating the quality of IPTV user experience based on incremental learning of big data, and applies the width forest algorithm and the idea of ​​incremental learning to the evaluation of the quality of IPTV user experience. Taking into account that the amount of IPTV user data in the context of big data is large and complex, when the width forest algorithm cannot achieve the required performance in practical applications, the idea of ​​incremental learning is used to transform the existing width forest, that is, through two means: 1. Dynamically increase the enhancement layer forest based on adaptive incremental learning, 2. Dynamically increase the feature layer forest based on adaptive incremental learning, so as to adaptively tune the model and further improve the accuracy of user QoE prediction under the complex background of big data. At the same time, the situation of continuous increase of user IPTV data is taken into account. Through incremental learning, the weights are updated only for new inputs, instead of retraining the entire model, which saves computing costs and time consumption.

[0107] Embodiments of the present invention have been described above with reference to the block diagrams and / or operational descriptions of methods, systems, and computer program products according to embodiments of the present invention. The functions / actions indicated in the blocks may appear in an order different from that shown in any flow chart. For example, depending on the functions / actions involved, two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order.

[0108] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for evaluating user experience quality (QoE), the method comprising: Get user data; Extract key parameters from the acquired user data; A user QoE prediction model based on a width forest is constructed by taking these key parameters as input data, wherein the width forest includes a feature layer forest and an enhancement layer forest; Adaptively and iteratively expanding the enhancement layer forest to strengthen the user QoE prediction model when the user QoE prediction model fails to achieve the required performance; Continuously acquiring new user data and updating the enhanced user QoE prediction model based on the new user data; as well as The user data to be predicted is input into the updated and enhanced user QoE prediction model to obtain the final user QoE prediction result.

2. The method as claimed in claim 1, wherein extracting key parameters from the acquired user data further comprises using data mining technology to extract key parameters that affect user QoE, and wherein the key parameters are extracted by comparing the relationship between data and targets using a Pearson correlation coefficient method.

3. The method of claim 1, wherein constructing a user QoE prediction model based on a width forest further comprises: The feature layer forest and the enhancement layer forest are constructed, and connection weights of the feature layer forest and the enhancement layer forest are estimated.

4. The method of claim 3, wherein constructing the feature layer forest and the enhancement layer forest and estimating the connection weights of the feature layer forest and the enhancement layer forest further comprises: Initialize each forest; Training the feature layer forest based on the input data to generate corresponding prediction probabilities and compressing the input data into important feature data; Training the enhancement layer forest by using the important feature data and the predicted probability as inputs of the enhancement layer forest; as well as The probability matrices of class distribution estimates from the feature layer forest and the enhancement layer forest are combined as the input of the final layer and the connection weights are determined by taking the pseudo-inverse of the input.

5. The method of claim 1, wherein adaptively and iteratively expanding the enhancement layer forest further comprises: Based on the new output of the expanded enhancement layer forest and the mapping relationship between the new output and the new input of the expanded enhancement layer forest, pseudo-inverse the new input to update the connection weights of the enhancement layer forest; Verify whether the extended enhancement layer forest brings significant performance improvement by comparing the average out-of-bag errors of all forest groups; as well as The enhancement layer forest is continued to be expanded when the out-of-bag error is significantly reduced and the enhancement layer forest is stopped to be expanded when the out-of-bag error is almost unchanged.

6. The method of claim 5, wherein the feature layer forest is expanded in the same manner if the expanded enhancement layer forest fails to achieve the desired performance.

7. The method of claim 1, wherein updating the enhanced user QoE prediction model based on the new user data further comprises: Taking the new user data as input of the feature layer forest and the enhancement layer forest to obtain output; representing a new input based on the output; as well as The new input is added to the input matrix of the width forest and the pseudo-inverse of the input matrix is ​​calculated to update the connection weights of the width forest.

8. A system for evaluating user experience quality (QoE), the system comprising: A user data acquisition module configured to acquire user data; A key parameter extraction module, configured to extract key parameters from the acquired user data; A user QoE prediction model building module is configured to build a user QoE prediction model based on a width forest by taking the key parameters as input data, wherein the width forest includes a feature layer forest and an enhancement layer forest; The user QoE prediction model enhancement and update module is configured to: Adaptively iteratively expand when the user QoE prediction model fails to achieve the required performance The enhancement layer forest is used to strengthen the user QoE prediction model; and Continuously acquiring new user data and updating the enhanced user QoE prediction model based on the new user data; as well as The user QoE prediction module is configured to input the to-be-predicted user data into the updated and enhanced user QoE prediction model to obtain a final user QoE prediction result.

9. The system of claim 8, wherein the user QoE prediction model building module is further configured to build a width forest-based user QoE prediction model by building the feature layer forest and the enhancement layer forest and estimating the connection weights of the feature layer forest and the enhancement layer forest, and wherein the user QoE prediction model building module is further configured to build the feature layer forest and the enhancement layer forest and estimate the connection weights of the feature layer forest and the enhancement layer forest by: Initialize each forest; Training the feature layer forest based on the input data to generate corresponding prediction probabilities and compressing the input data into important feature data; Training the enhancement layer forest by using the important feature data and the predicted probability as inputs of the enhancement layer forest; as well as The probability matrices of class distribution estimates from the feature layer forest and the enhancement layer forest are combined as the input of the final layer and the connection weights are determined by taking the pseudo-inverse of the input.

10. The system of claim 8, wherein the user QoE prediction model enhancement and updating module is further configured to adaptively and iteratively expand the enhancement layer forest by: Based on the new output of the expanded enhancement layer forest and the mapping relationship between the new output and the new input of the expanded enhancement layer forest, pseudo-inverse the new input to update the connection weights of the enhancement layer forest; Verify whether the extended enhancement layer forest brings significant performance improvement by comparing the average out-of-bag errors of all forest groups; as well as Continue to expand the enhancement layer forest when the out-of-bag error is significantly reduced and stop expanding the enhancement layer forest when the out-of-bag error is almost unchanged, and The user QoE prediction model enhancement and update module is further configured to update the enhanced user QoE prediction model based on the new user data by: The new user data is used as the input of the feature layer forest and the enhancement layer forest to obtain the input out; representing a new input based on the output; as well as The new input is added to the input matrix of the width forest and the pseudo-inverse of the input matrix is ​​calculated to update the connection weights of the width forest.

Images