Multi-level quality indicator management system and method for context-aware system

Abstract

The multi-level quality index management system and method for context-aware system disclosed in the present invention include: a QoD evaluation and management module, a QoC evaluation and management module, a QoS evaluation and management module and a QoI evaluation and management module which are sequentially connected to form a closed loop, wherein the QoC evaluation and management module, the QoS evaluation and management module and the QoI evaluation and management module are respectively connected to the QoE evaluation and management module; wherein the QoI evaluation and management module is configured to obtain QoI parameters and adjust the quality index according to the predicted objective QoE; the QoE evaluation and management module is configured to predict the objective QoE according to the QoC parameters obtained by the QoC evaluation and management module, the QoS parameters obtained by the QoS evaluation and management module and the QoI parameters obtained by the QoI evaluation and management module; and the QoD evaluation and management module, the QoC evaluation and management module and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality index. Adaptive adjustment of system quality index is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of context awareness, and in particular to a multi-level quality indicator management system and method for a context awareness system. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The context-aware system is the core application of ubiquitous computing in the intelligent perception space. This computing system perceives the relevant context and its changes of the studied entity in real time, and provides users with appropriate services to meet their needs through a series of intelligent processing and autonomous decision-making such as information modeling, fusion, and reasoning, realizing the transformation from perceptual intelligence to cognitive intelligence, and emphasizing transparent human-computer interaction. Context-aware technology has been widely used in scenarios such as digital homes, smart medical care, and smart cities, making operations in various fields more intelligent and humane.

[0004] Context-aware system frameworks for different application scenarios have their own characteristics. It is an inevitable trend to design a systematic evaluation index with strong universality. Some researchers have proposed basic concepts such as quality of device (QoD), quality of context (QoC), quality of service (QoS) and quality of experience (QoE) for different levels of context-aware systems, and discussed the relationship between quality indicators at each level. At the same time, a new system comprehensive quality evaluation system QoX (Quality of indeXes) is proposed by integrating quality indicators at each level. Research in this area has achieved good results.

[0005] However, the existing quality indicators at each level are not comprehensive enough, and do not consider the impact of the quality of the application layer software on the user experience and even the entire context-aware system, and there is a lack of unified standards for different systems. The quality indicators within and between each level are diverse, but there is a lack of a unified management mechanism. The optimization method of the system is unclear, and the role of each quality indicator other than evaluation cannot be played, resulting in the inability to adaptively optimize the system, thereby failing to realize the core value of ubiquitous computing. Therefore, how to refine and uniformly manage the quality indicators at each level and design a comprehensive context-aware system quality evaluation and management system for optimizing the system is a research problem that urgently needs to be solved. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a multi-level quality indicator management system and method for context-aware systems, which realizes adaptive adjustment of system quality indicators.

[0007] To achieve the above object, the present invention adopts the following technical solution:

[0008] First, a multi-level quality indicator management system for context-aware systems is proposed, including a QoD evaluation and management module, a QoC evaluation and management module, a QoS evaluation and management module, and a QoI evaluation and management module, which are sequentially connected to form a closed loop, and the QoC evaluation and management module, the QoS evaluation and management module, and the QoI evaluation and management module are respectively connected to the QoE evaluation and management module;

[0009] Among them, the QoI evaluation and management module is configured to obtain QoI parameters and adjust the quality indicators according to the predicted objective QoE; the QoE evaluation and management module is configured to predict the objective QoE according to the QoC parameters obtained by the QoC evaluation and management module, the QoS parameters obtained by the QoS evaluation and management module, and the QoI parameters obtained by the QoI evaluation and management module; the QoD evaluation and management module, the QoC evaluation and management module, and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality indicators.

[0010] Secondly, a working method of a multi-level quality indicator management system for context-aware systems is proposed, including:

[0011] Filter perception devices according to quality indicators, and collect context information through the filtered perception devices;

[0012] Obtain QoC parameters and system decision information based on context information;

[0013] Determine system services and QoS parameters of the determined system services according to the system decision information;

[0014] Get the QoI parameters of the determined system service;

[0015] Predict objective QoE based on QoC parameters, QoS parameters, and QoI parameters;

[0016] Adjust the quality indicators based on the predicted objective QoE;

[0017] The QoD evaluation and management module, the QoC evaluation and management module and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality indicators.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1. The present invention can actively perceive various types of context information, monitor changes in environmental status in real time, and actively provide users with appropriate services through a series of processing of context information.

[0020] 2. The present invention can utilize the relationship between various evaluation and management modules to continuously adjust and optimize system performance, and can achieve adaptive adjustment of application programs or perception device configurations.

[0021] 3. The present invention utilizes the QoX system composed of QoD, QoC, QoS, QoI and QoE to process context information at each layer, thereby reducing computing resources while improving context quality and decision accuracy, making the system highly efficient.

[0022] 4. The present invention filters out low-quality contexts and privacy-invading contexts, and pushes appropriate services through intelligent recommendation combined with graded screening, thereby ensuring the reliability of the system.

[0023] 5. The present invention supports two adjustment modes: adaptive adjustment and forced adjustment, making the system flexible.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0026] Figure 1 This is a structural framework diagram of the system disclosed in Example 1 of the present invention;

[0027] Figure 2 A diagram showing the composition and connection relationship of the system disclosed in Example 1 of the present invention;

[0028] Figure 3 This is a flow chart of the method disclosed in Example 2 of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0032] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0033] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. Relevant scientific research or technical personnel in this field can determine the specific meanings of the above terms in the present invention according to specific circumstances, and they should not be understood as limiting the present invention.

[0034] Example 1

[0035] In this embodiment, a multi-level quality indicator management system for a context-aware system is disclosed, including a QoD evaluation and management module, a QoC evaluation and management module, a QoS evaluation and management module, a QoI evaluation and management module, and a QoE evaluation and management module. The QoD evaluation and management module, the QoC evaluation and management module, the QoS evaluation and management module, and the QoI evaluation and management module are sequentially connected to form a closed loop, and the QoC evaluation and management module, the QoS evaluation and management module, and the QoI evaluation and management module are respectively connected to the QoE evaluation and management module.

[0036] Among them, the QoI evaluation and management module is configured to obtain QoI parameters and adjust the quality indicators according to the objective QoE predicted by the QoE evaluation and management module or the subjective QoE provided by the user; the QoE evaluation and management module is configured to predict the objective QoE according to the QoC parameters obtained by the QoC evaluation and management module, the QoS parameters obtained by the QoS evaluation and management module and the QoI parameters obtained by the QoI evaluation and management module, or capture the user's subjective QoE; the QoD evaluation and management module, the QoC evaluation and management module and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality indicators.

[0037] Further, the QoD evaluation and management module is configured to screen the sensing devices according to the quality indicators, collect context information through the screened sensing devices, and send the collected context information to the QoC evaluation and management module;

[0038] The QoC evaluation and management module is configured to obtain QoC parameters and decision information of the system according to the context information, and send the QoC parameters to the QoE evaluation and management module, and send the decision information to the QoS evaluation and management module;

[0039] The QoS evaluation and management module is configured to determine the system service according to the system decision information, calculate the QoS parameters of the determined system service, and send the QoS parameters of the determined system service to the QoE evaluation and management module, and send the determined system service to the QoI evaluation and management module.

[0040] Further, the QoD evaluation and management module comprises a perception device information configuration unit, a perception device QoD acquisition unit and a context information acquisition unit which are connected in sequence;

[0041] A sensing device information configuration unit, configured to preset and adjust configuration information of the sensing device;

[0042] A perception device QoD acquisition unit, configured to acquire QoD parameters of the intelligent perception device that has completed information configuration;

[0043] The context information collection unit is configured to select an intelligent sensing device whose QoD parameters meet the quality index, and collect context information through the selected intelligent sensing device.

[0044] Further, the QoC evaluation and management module includes a knowledge base real-time storage unit, a QoC parameter calculation unit, a QoC-based privacy information filtering unit, a QoC parameter classification fusion unit, a QoC-based context uncertainty processing unit, and a high-level context fusion reasoning unit, which are connected in sequence;

[0045] A knowledge base real-time storage unit configured to store context information;

[0046] A QoC parameter calculation unit, configured to calculate the QoC parameter of the context information;

[0047] A QoC-based privacy information filtering unit configured to filter context information;

[0048] A QoC parameter classification and fusion unit is configured to classify the filtered context information and calculate each type of fused QoC parameter;

[0049] A QoC-based context uncertainty processing unit configured to process uncertainty of context information according to the classified fusion QoC parameters to obtain high-level context information;

[0050] The high-level context fusion reasoning unit is configured to perform fusion reasoning on the high-level context information, obtain decision information, and apply for a service matching the decision information.

[0051] Furthermore, the QoS evaluation and management module includes a knowledge graph service recommendation unit, a combined service QoS acquisition unit, and a service level classification and optimization unit which are connected in sequence;

[0052] A knowledge graph service recommendation unit configured to make a request for a required service based on the decision information;

[0053] A combined service QoS acquisition unit, configured to acquire QoS parameters that meet the required services;

[0054] The service level classification and optimization unit is configured to classify the services that meet the requirements according to the QoS parameters and select the best service as the final system service.

[0055] Further, the QoI evaluation and management module includes a QoI parameter acquisition unit, a QoI parameter fusion unit and a quality management unit connected in sequence;

[0056] A QoI parameter acquisition unit is configured to acquire a QoI parameter of a determined system service;

[0057] A QoI parameter fusion unit is configured to perform weighted fusion of the acquired QoI parameters to obtain a comprehensive QoI parameter;

[0058] The quality management unit includes a quality indicator adaptive adjustment subunit and a user feedback forced adjustment subunit, wherein the quality indicator adaptive adjustment subunit is configured to adaptively adjust the quality indicator according to the predicted objective QoE result; the user feedback forced adjustment subunit is configured to generate a subjective adjustment strategy according to subjective QoE information to adjust the quality indicator; the user feedback forced adjustment subunit has a higher priority than the quality indicator adaptive adjustment subunit.

[0059] Further, the QoE evaluation and management module includes an objective QoE evaluation unit and a subjective QoE acquisition unit;

[0060] The objective QoE evaluation unit is configured to evaluate and predict the objective QoE by integrating the comprehensive QoC parameter, the QoS parameter and the comprehensive QoI parameter, and the predicted objective QoE result is sent to the adaptive adjustment subunit to participate in the adaptive adjustment of the quality indicator;

[0061] The subjective QoE acquisition unit is configured to capture the subjective QoE actively provided by the user, send the subjective QoE information to the user feedback forced adjustment subunit to generate a subjective adjustment strategy, and adjust the quality indicator.

[0062] Combination Figure 1 , Figure 2 A multi-level quality indicator management system for context-aware systems is described in detail.

[0063] The present invention incorporates the Quality of Information (QoI) into the system comprehensive quality evaluation system QoX, and forms an adaptive adjustment mechanism of the center plus closed loop mode with QoD, QoC, QoS, and QoE indicators. At the same time, it refines the quality indicators of each level and broadens their role in system optimization. The QoD indicator is used to optimize the quality of the context source and the original context; the QoC indicator is used to protect user privacy and eliminate the uncertainty of the context; the QoS indicator is used to recommend and make decisions on services; and the QoI indicator is used to perform adaptive and mandatory quality management from the application level. Among them, the QoE indicator is the "heart" of this system. This indicator is based on other indicators and provides feedback from the user, providing a basis for the adaptive adjustment of the system.

[0064] like Figure 1 As shown, it includes: QoD evaluation and management module, QoC evaluation and management module, QoS evaluation and management module, QoI evaluation and management module, and QoE evaluation and management module.

[0065] The QoD evaluation and management module, the QoC evaluation and management module, the QoS evaluation and management module, and the QoI evaluation and management module are connected in a closed loop in sequence, and the QoC evaluation and management module, the QoS evaluation and management module, and the QoI evaluation and management module are synchronously connected to the QoE evaluation and management module, wherein the QoE evaluation and management module is interactively connected to the QoI evaluation and management module.

[0066] The QoD evaluation and management module is used to manage the information configuration of the perception devices, obtain the relevant QoD parameters of the perception devices, and thereby screen out suitable perception devices for collecting contextual information. The QoD parameters are parameters used to describe the performance of the information collection device, mainly including the accuracy, placement, sampling frequency, etc. of the sensor.

[0067] The QoC evaluation and management module is used to calculate QoC parameters based on context information and perform preprocessing operations such as privacy context filtering and context uncertainty elimination based on the QoC parameters. After obtaining the high-level context, fusion reasoning is performed to obtain the system's decision information. QoC parameters are parameters used to describe the quality of context information, mainly including reliability, update degree, correctness probability, etc. Context uncertainty includes context inconsistency, context incompleteness and context imprecision.

[0068] The QoS evaluation and management module is used to recommend required services or service combinations based on system decision information, and calculate the QoS parameters of the services or service combinations. After rating and selecting the best ones, the recommended required services are determined and pushed to the users. QoS parameters are parameters used to describe the system service quality, including bandwidth, packet loss rate, latency, etc.

[0069] The QoI evaluation and management module is used to calculate and fuse QoI parameters such as the perceived ease of use (PEOU), perceived usefulness (PU) and richness of information (RI) of the system application, obtain the fused QoI parameters, and connect to the QoD evaluation and management module to perform a new round of cyclic work, so that the system can achieve the adaptability of closed-loop adjustment. QoI parameters are parameters used to describe the quality of system applications. The QoI evaluation and management module adjusts the quality indicators and performs quality management in combination with the system feedback information provided by the QoE evaluation and management module. The QoD evaluation and management module, the QoC evaluation and management module, and the QoS evaluation and management module adaptively adjust the configuration information, indicator parameter thresholds and other parameters.

[0070] like Figure 2 As shown, the QoD evaluation and management module includes a perception device information configuration unit, a perception device QoD acquisition unit and a context information acquisition unit which are connected in sequence.

[0071] The perception device information configuration unit presets and adjusts relevant configuration information of the intelligent perception device according to the specific application requirements of the context perception system; the intelligent perception device includes physical sensors, virtual sensors, Internet information acquisition devices, etc.; the configuration information includes relevant functional parameters and quality parameters of the intelligent perception device.

[0072] The perception device QoD acquisition unit is used to obtain the QoD parameters of the intelligent perception device in the application state in the current scene; the QoD parameters include sensor accuracy, service life, sampling frequency and the maximum distance to ensure the validity of the sensor measurement value.

[0073] The context information collection unit is used to select an intelligent sensing device whose QoD parameters meet the quality index required by the system, and collect context information through the selected intelligent sensing device.

[0074] The biggest advantage of using the QoD evaluation and management module is that it can obtain the QoD parameters of each intelligent sensing device in the current scenario, intuitively quantify the degree of matching between each intelligent sensing device and the current processing requirements, and at the same time, through the system threshold, select the intelligent sensing device that meets the system requirements to avoid collecting useless context information, saving storage space and computing resources; for example, if the preset sensor accuracy is 0.6, then the sensing device with an accuracy lower than 0.6 will not participate in the information collection in this scenario. Secondly, the information can be adjusted according to the feedback generated by the QoI evaluation and management module, and the information configuration of the sensing device can be adjusted to make the system proactive and adaptive.

[0075] The QoC evaluation and management module includes a knowledge base real-time storage unit, a QoC parameter calculation unit, a QoC-based privacy information filtering unit, a QoC parameter classification fusion unit, a QoC-based context uncertainty processing unit and an advanced context fusion reasoning unit, which are connected in sequence.

[0076] The knowledge base real-time storage unit includes a domain database subunit and a context database subunit; the domain database subunit is used to store the original data collected by the intelligent sensing device and the various parameters involved in the context processing process in the current application scenario; the context database subunit is used to store the modeled context information; the QoC parameter calculation unit is used to calculate the quality QoC parameters of the acquired context information to facilitate subsequent operations; QoC parameters include reliability, update degree, correctness probability, relevance and other parameters; the QoC-based privacy information filtering unit is used to filter out some context information that may infringe on user privacy due to excessively high QoC parameters; for example, in private scenarios, in order to protect user privacy, the accuracy requirements for location context cannot be too high. If the preset accuracy is 0.95, then location context information below 0.95 will be deleted; QoC parameters The classification fusion unit is used to classify the filtered context information into sensed context and non-sensed context, classify and calculate the comprehensive quality of the sensed context and non-sensed context, and obtain the fusion QoC parameters of each category; the sensed context refers to the context information sensed and collected by the physical sensor, and the rest of the context information is non-sensed context, mainly including user-defined context, derived context, etc.; the QoC-based context uncertainty processing unit uses the comprehensive context quality information of classification fusion to process the uncertainty of context information to obtain high-level context information; the uncertainty of context information includes incomplete context information, inconsistency of context information and imprecise context information; the high-level context fusion reasoning unit uses methods such as evidence theory, Bayesian network, neural network, etc. to perform fusion reasoning operations on the context information to obtain system decision information and apply for matching services.

[0077] The beneficial effect of the QoC evaluation and management module is that it uses QoC parameters to protect the privacy of users and truly provides the services they need from the user's perspective without causing user disgust. At the same time, according to different types of contexts, different QoC parameters are flexibly used to eliminate context uncertainty, improve the quality of context to obtain advanced context, and fundamentally improve the correctness, effectiveness and efficiency of system reasoning fusion and subsequent decision-making.

[0078] The QoS evaluation and management module includes a knowledge graph service recommendation unit, a combined service QoS acquisition unit and a service level classification and optimization unit which are connected in sequence.

[0079] The knowledge graph service recommendation unit uses the knowledge graph-based recommendation system algorithm to make a request for the currently required service or service combination according to the system decision information obtained by the fusion reasoning high-level context; the combined service QoS acquisition unit is used to obtain the QoS parameters of the service or service combination that meets the current requirements; QoS parameters include bandwidth, packet loss rate, latency and other parameters; the service level classification and optimization unit is used to classify the services or service combinations that meet the current requirements according to the QoS parameters and select the optimal service or service combination as the final system service for response.

[0080] The advantage of the QoS evaluation and management module is that it uses a combination of knowledge graph and recommendation system to recommend system services, which is conducive to the divergence of recommendation results and in-depth exploration of user interests. The service level is then determined by QoS parameters to finally select the service that best suits the current scenario requirements, making the system reliable.

[0081] The QoI evaluation and management module includes a QoI parameter acquisition unit, a QoI parameter fusion unit and a quality management unit which are connected in sequence.

[0082] The QoI parameter acquisition unit is used to obtain the QoI parameters of the interactive application device corresponding to the service or service combination recommended by the system; the QoI parameters include PEOU, PU, ​​RI parameters, etc.; the QoI parameter fusion unit weightedly fuses the obtained QoI parameters according to a certain weight distribution method to obtain a comprehensive QoI; the quality management unit includes a quality indicator adaptive adjustment subunit and a user feedback forced adjustment subunit, wherein the user feedback forced adjustment subunit has a high priority; the quality indicator adaptive adjustment subunit adaptively adjusts the system according to the interactive performance of the quality indicators at all levels of the system; the user feedback forced adjustment subunit forces the system's quality indicators to adjust according to the subjective QoE information through the application's interactive interface; the adjustment operation is mainly to adjust the relevant information data of the perception device information configuration unit and the knowledge base real-time storage unit.

[0083] The beneficial effect of the QoI evaluation and management module is that it incorporates QoI indicators into the QoX system, focuses on the useful information obtained in the application, and enriches the objective evaluation of QoE. The embedded quality management unit supports two adjustment methods: adaptive adjustment and forced adjustment, making the system flexible.

[0084] The QoE evaluation and management module includes an objective QoE evaluation unit and a subjective QoE acquisition unit.

[0085] The objective QoE evaluation unit integrates comprehensive QoC parameters, QoS parameters and comprehensive QoI parameters to evaluate and predict the objective QoE. The predicted objective QoE result is sent to the adaptive adjustment subunit to participate in the adaptive adjustment of quality indicators. The subjective QoE acquisition unit captures the subjective QoE actively provided by the user, sends the subjective QoE information to the user feedback forced adjustment subunit to generate a subjective adjustment strategy, and performs user feedback forced adjustment on the quality target through the application's interactive interface.

[0086] The beneficial effect of the QoE evaluation and management module is that it uses other level indicators to evaluate objective QoE, making up for the lack of feedback information when users do not actively provide subjective QoE, which meets the requirements of ubiquitous computing transparency. The system is continuously optimized through subjective and objective QoE feedback information until the preset QoE threshold is reached, thereby improving user satisfaction.

[0087] This embodiment can actively perceive various types of context information, monitor changes in environmental status in real time, and actively provide appropriate services to users through a series of processing of context information.

[0088] This embodiment can utilize the relationship between various evaluation and management modules to continuously adjust and optimize system performance, and can achieve adaptive adjustment of application programs or perception device configurations.

[0089] This embodiment uses the QoX system composed of QoD, QoC, QoS, QoI and QoE to process context information at each layer, which reduces computing resources while improving context quality and decision accuracy, making the system highly efficient.

[0090] This embodiment filters out low-quality contexts and privacy-invading contexts, and pushes appropriate services through intelligent recommendation combined with grade screening, so that the reliability of the system is guaranteed.

[0091] The system of this embodiment supports two adjustment modes: adaptive adjustment and forced adjustment, making the system flexible.

[0092] The multi-level quality indicator management system for context-aware systems disclosed in this embodiment includes a QoD evaluation and management module, a QoC evaluation and management module, a QoS evaluation and management module, a QoI evaluation and management module, and a QoE evaluation and management module. The QoD evaluation and management module obtains the QoD parameters of each intelligent sensing device in the current scenario, and optimizes the intelligent sensing devices that meet the system requirements through the system threshold to avoid collecting useless context information. The QoC evaluation and management module uses the QoC parameters to filter out the context information that infringes on the user's privacy, and performs context uncertainty elimination and high-level context fusion reasoning. The QoS evaluation and management module recommends system services by combining knowledge graphs with recommendation systems, and then pushes services based on QoS parameters. The QoE evaluation and management module, as the core module of the system, generates subjective and objective feedback information and sends it to the QoI evaluation and management module. The embedded quality management unit in the QoI evaluation and management module supports two adjustment modes: adaptive adjustment and forced adjustment. The evaluation, utilization, and management of quality indicators at all levels of the system in this embodiment make the system highly proactive, adaptive, efficient, reliable, and flexible.

[0093] Example 2

[0094] In this embodiment, a working method of a multi-level quality indicator management system for a context-aware system is disclosed, including:

[0095] Filter perception devices according to quality indicators, and collect context information through the filtered perception devices;

[0096] Obtain QoC parameters and system decision information based on context information;

[0097] Determine system services and QoS parameters of the determined system services according to the system decision information;

[0098] Get the QoI parameters of the determined system service;

[0099] Predict objective QoE based on QoC parameters, QoS parameters, and QoI parameters;

[0100] Adjust the quality indicators based on the predicted objective QoE;

[0101] The QoD evaluation and management module, the QoC evaluation and management module and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality indicators.

[0102] Specific working methods such as Figure 3 As shown in the figure, taking the smart tourism system as an example, the system collects tourists' location information through four methods: WIFI, Bluetooth, infrared and Zigbee, and pushes appropriate scenic spot recommendation services to tourists after system calculation and processing.

[0103] Step S01: Perceiving device information configuration

[0104] The perception device information configuration unit presets and adjusts relevant configuration information of the intelligent perception device according to the specific application requirements of the context perception system; in this embodiment, two QoD parameters are mainly obtained: accuracy and sampling interval.

[0105] Step S02: Acquisition of device QoD

[0106] The perception device QoD acquisition unit acquires the QoD parameters of the intelligent perception device in the application state in the current scene.

[0107] Step S03: Context information collection

[0108] The context information collection unit selects an intelligent sensing device whose QoD parameters meet the system quality index requirements to collect context information; in this embodiment, the collected original context information is all location information.

[0109] Step S04: Real-time storage of knowledge base

[0110] The knowledge base real-time storage unit stores the collected original context information and system preset values ​​in the domain database, performs preprocessing modeling on the original context information and stores it in the context database.

[0111] Step S05: QoC parameter calculation

[0112] The QoC parameter calculation unit calculates the quality of the acquired context information, including parameters such as reliability, update degree, correctness probability, and relevance.

[0113] Step S06: Privacy and security information filtering

[0114] The QoC-based privacy information filtering unit filters out some context information that may infringe on user privacy due to excessively high QoC parameters; in this embodiment, the preset QoC parameter accuracy of the location information in the private space is 0.95, and the location context information with an accuracy higher than 0.95 is deleted.

[0115] Step S07: QoC parameter classification and fusion

[0116] The QoC parameter classification fusion unit classifies and calculates the comprehensive quality of the sensed context and the non-sensed context in the filtered context information; the comprehensive quality of the sensed context is evaluated by the fusion of reliability, update degree, correctness probability, and relevance, and the comprehensive quality of the non-sensed context is evaluated by the fusion of correctness probability and reliability.

[0117] Step S08: Context uncertainty processing

[0118] The QoC-based context uncertainty processing unit utilizes the comprehensive context quality information of classification fusion and processes the context information uncertainty based on DS evidence theory to obtain high-level context information.

[0119] Step S09: Context fusion reasoning decision

[0120] The advanced context fusion reasoning unit uses evidence theory, Bayesian network, neural network and other methods to perform fusion reasoning operations on context information to obtain services that match the system judgment information application.

[0121] Step S10: Knowledge graph service recommendation

[0122] The knowledge graph service recommendation unit uses the knowledge graph-based recommendation system algorithm to make requests for the currently required services or service combinations based on the system decision information obtained by integrating the high-level context of reasoning.

[0123] Step S11: Acquisition of combined service QoS

[0124] The combined service QoS acquisition unit acquires QoS parameters that meet the currently required service or service combination.

[0125] Step S12: QoS level classification

[0126] The service level classification and optimization unit is used to classify and sort the services or service combinations that meet the current requirements according to the QoS parameters.

[0127] Step S13: Select the service combination with the highest QoS

[0128] Select the service or service combination with the highest QoS to respond.

[0129] Step S14: QoI parameter acquisition

[0130] The QoI parameter acquisition unit acquires the QoI parameters of the interactive application device corresponding to the selected service or service combination, including PEOU, PU, ​​RI parameters, etc.

[0131] Step S15: QoI parameter fusion

[0132] The QoI parameter fusion unit performs weighted fusion on the acquired QoI parameters according to a certain weight distribution method to obtain the comprehensive QoI.

[0133] Step S16: Objective QoE evaluation

[0134] The objective QoE evaluation unit objectively evaluates and predicts the objective QoE by fusing the comprehensive QoC parameter calculated in step S07, the comprehensive QoS parameter of the determined service obtained in step S13, and the comprehensive QoI parameter calculated in step S15 using a certain weight distribution method.

[0135] Step S17: Obtaining Subjective QoE

[0136] The subjective QoE acquisition unit captures the subjective QoE actively provided by the user.

[0137] Step S18: Adaptive adjustment of quality indicators

[0138] The quality indicator adaptive adjustment subunit performs adaptive adjustment operations on the system according to the interactive performance of quality indicators at all levels of the system, that is, adaptively adjusts the relevant information data of the perception device information configuration unit and the knowledge base real-time storage unit.

[0139] Step S19: User feedback forced adjustment

[0140] The user feedback forced adjustment subunit performs forced adjustment operations on the system through the application's interactive interface according to the subjective QoE information, that is, forced adjustment is performed on the relevant information data of the perception device information configuration unit and the knowledge base real-time storage unit.

[0141] Step S20: Adjusting priority determination

[0142] User feedback is not always available. The final adjustment information is determined based on the principle that mandatory adjustments based on user feedback take precedence over adaptive adjustments of quality indicators.

[0143] Step S21: Determine whether the QoE threshold is reached

[0144] The QoE indicator obtained in steps S16-S17 is compared with the QoE threshold preset by the system. If the QoE indicator is less than the QoE threshold, the relevant functional parameters and quality parameters of the intelligent sensing device in step S01 are adjusted according to the adjustment strategy determined in step S20. Otherwise, it indicates that the system requirements have been met, and the previous sensing device configuration information is maintained, and the context information collection continues directly.

[0145] In this embodiment, the QoE indicator threshold is 4.5 points. If the acquired subjective / objective QoE is less than 4.5 points, it is necessary to adjust the relevant information data of the perception device information configuration unit and the knowledge base real-time storage unit. Otherwise, it ends, indicating that the system performance is qualified at this time and no adjustment is required.

[0146] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0147] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0148] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-level quality indicator management system for context-aware systems, characterized in that: Including, a QoD evaluation and management module, a QoC evaluation and management module, a QoS evaluation and management module and a QoI evaluation and management module which are sequentially connected to form a closed loop, and the QoC evaluation and management module, the QoS evaluation and management module and the QoI evaluation and management module are respectively connected to the QoE evaluation and management module; Among them, the QoI evaluation and management module is configured to obtain QoI parameters and adjust the quality indicators according to the predicted objective QoE; the QoE evaluation and management module is configured to predict the objective QoE according to the QoC parameters obtained by the QoC evaluation and management module, the QoS parameters obtained by the QoS evaluation and management module, and the QoI parameters obtained by the QoI evaluation and management module; the QoD evaluation and management module, the QoC evaluation and management module, and the QoS evaluation and management module all perform parameter adaptive adjustment according to the quality indicators.

2. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoE evaluation and management module is further configured to capture subjective QoE information, and the QoI evaluation and management module is further configured to adjust the quality indicator according to the subjective QoE information.

3. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoD evaluation and management module is configured to screen the sensing devices according to the quality indicators, collect context information through the screened sensing devices, and send the collected context information to the QoC evaluation and management module; The QoC evaluation and management module is configured to obtain QoC parameters and decision information of the system according to the context information, and send the QoC parameters to the QoE evaluation and management module, and send the decision information to the QoS evaluation and management module; The QoS evaluation and management module is configured to determine the system service according to the system decision information, calculate the QoS parameters of the determined system service, and send the QoS parameters of the determined system service to the QoE evaluation and management module, and send the determined system service to the QoI evaluation and management module.

4. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoD evaluation and management module comprises a perception device information configuration unit, a perception device QoD acquisition unit and a context information acquisition unit connected in sequence; A sensing device information configuration unit, configured to preset and adjust configuration information of the sensing device; A perception device QoD acquisition unit, configured to acquire QoD parameters of the intelligent perception device that has completed information configuration; The context information collection unit is configured to select an intelligent sensing device whose QoD parameters meet the quality index, and collect context information through the selected intelligent sensing device.

5. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoC evaluation and management module includes a knowledge base real-time storage unit, a QoC parameter calculation unit, a QoC-based privacy information filtering unit, a QoC parameter classification fusion unit, a QoC-based context uncertainty processing unit, and an advanced context fusion reasoning unit, which are connected in sequence; A knowledge base real-time storage unit configured to store context information; A QoC parameter calculation unit, configured to calculate the QoC parameter of the context information; A QoC-based privacy information filtering unit configured to filter context information; A QoC parameter classification and fusion unit is configured to classify the filtered context information and calculate each type of fused QoC parameter; A QoC-based context uncertainty processing unit configured to process uncertainty of context information according to the classified fusion QoC parameters to obtain high-level context information; The high-level context fusion reasoning unit is configured to perform fusion reasoning on the high-level context information, obtain decision information, and apply for a service matching the decision information.

6. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoS evaluation and management module includes a knowledge graph service recommendation unit, a combined service QoS acquisition unit, and a service level classification and optimization unit connected in sequence; A knowledge graph service recommendation unit configured to make a request for a required service based on the decision information; A combined service QoS acquisition unit, configured to acquire QoS parameters that meet the required services; The service level classification and optimization unit is configured to classify the services that meet the requirements according to the QoS parameters and select the best service as the final system service.

7. The multi-level quality indicator management system for context-aware systems according to claim 1, characterized in that: The QoI evaluation and management module includes a QoI parameter acquisition unit, a QoI parameter fusion unit and a quality management unit connected in sequence; A QoI parameter acquisition unit is configured to acquire a QoI parameter of a determined system service; A QoI parameter fusion unit is configured to perform weighted fusion of the acquired QoI parameters to obtain a comprehensive QoI parameter; The quality management unit includes a quality indicator adaptive adjustment subunit and a user feedback forced adjustment subunit, wherein the quality indicator adaptive adjustment subunit is configured to adjust the quality indicator according to the predicted objective QoE result; the user feedback forced adjustment subunit is configured to generate a subjective adjustment strategy according to subjective QoE information to adjust the quality indicator.

8. The multi-level quality indicator management system for context-aware systems according to claim 7, characterized in that: The user feedback mandatory adjustment subunit has a higher priority than the quality indicator adaptive adjustment subunit.

9. The multi-level quality indicator management system for context-aware systems according to claim 7, characterized in that: The QoE evaluation and management module includes an objective QoE evaluation unit and a subjective QoE acquisition unit; An objective QoE evaluation unit is configured to evaluate and predict the objective QoE by integrating the comprehensive QoC parameter, the QoS parameter and the comprehensive QoI parameter, and the predicted objective QoE result is sent to the adaptive adjustment subunit; The subjective QoE acquisition unit is configured to capture the subjective QoE actively provided by the user and send the subjective QoE information to the user feedback forced adjustment subunit.

10. The working method of the multi-level quality indicator management system for context-aware system according to any one of claims 1 to 9, characterized in that: include: Filter perception devices according to quality indicators, and collect context information through the filtered perception devices; Obtain QoC parameters and system decision information based on context information; Determine system services and QoS parameters of the determined system services according to the system decision information; Get the QoI parameters of the determined system service; Predict objective QoE based on QoC parameters, QoS parameters, and QoI parameters; Adjust the quality indicators based on the predicted objective QoE; The QoD evaluation and management module, the QoC evaluation and management module and the QoS evaluation and management module all perform adaptive parameter adjustments based on quality indicators.

Images