Video conference failure prediction method and device, computer device and storage medium

Abstract

The application relates to a video conference fault prediction method and device, computer equipment and a storage medium. The application relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring video conference data of a current video conference; the video conference data comprises running environment data and video content data; each environment analysis value is obtained by analyzing the running environment data through a video analysis strategy, and an environment analysis value meeting a running fault condition is taken as current conference fault data; the fault grades corresponding to the current conference fault data are determined, and the fault information of the video conference in a target period is predicted according to the current conference fault data, the fault grades corresponding to the current conference fault data and the video content data. The method can improve the fault prediction efficiency of the video conference.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer equipment, and storage medium for predicting video conferencing failures. Background Technology

[0002] Video conferencing is a highly real-time application, and traditionally, real-time business data for video conferencing is primarily obtained from the backend MCU server. Staff review the video conferencing data, which may include, but is not limited to, real-time data such as video encoding / decoding protocols, audio / video formats, bitrate, and network connectivity (packet loss, jitter, latency), to assess the current video quality and meeting effectiveness, and adjust relevant parameters to ensure smooth conferencing. Therefore, predicting video conferencing fault information is a key research focus for improving video quality and meeting effectiveness.

[0003] Traditional video conferencing fault prediction relies on staff analyzing video conferencing data from clients to obtain current fault information and then manually predicting future failures. However, this method lacks comprehensive system-wide data analysis, has limited data types, and fails to cover the entire video conferencing process. Furthermore, maintenance personnel often lack the timeliness to respond to system faults and performance degradation analyses, making real-time fault prediction inefficient. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product capable of predicting video conferencing failures, in response to the aforementioned technical problems.

[0005] Firstly, this application provides a method for predicting video conferencing failures. The method includes:

[0006] Acquire the video conference data of the current video conference; the video conference data includes operating environment data and video content data;

[0007] By analyzing the video analysis strategy and the operating environment data, we obtain various environmental analysis values, and use the environmental analysis values ​​that meet the operating failure conditions as the current meeting failure data.

[0008] Determine the fault level corresponding to each of the current meeting fault data, and predict the fault information of the video conference in the target time period based on each of the current meeting fault data, the fault level corresponding to each of the current meeting fault data, and the video content data.

[0009] Optionally, obtaining the video conference data of the current video conference includes:

[0010] Obtain data information from the current video conference;

[0011] Cluster the data information of the same category according to the category identifier of the data information to obtain the data information of each category;

[0012] By using preset category attributes, categories with the same attributes are aggregated to obtain operating environment data and video content data. Based on the operating environment data and the video content data, the current video conference data is determined. The category attributes include operating environment attributes and video content attributes.

[0013] Optionally, the step of analyzing the video analysis strategy and the operating environment data to obtain various environmental analysis values, and using the environmental analysis values ​​that meet the operating failure conditions as the current meeting failure data, includes:

[0014] Obtain the operating data threshold corresponding to each of the operating environment data, and determine the category to which each operating environment data belongs;

[0015] For the same category of operating environment data, the environmental analysis value of each operating environment data in the category is analyzed using the operating environment data analysis strategy for that category;

[0016] If the environmental analysis value meets the operational fault conditions corresponding to the operational environment data, the environmental analysis value of the operational environment data is determined to be the current meeting fault data.

[0017] Optionally, the step of analyzing the environmental analysis value of each operational environment data in the category using the operational environment data analysis strategy of the category includes:

[0018] For each category of operating environment data, extract the environmental data information corresponding to the environmental analysis value from the operating environment data;

[0019] According to the data parsing strategy, the environmental data information of the environmental analysis values ​​is parsed and processed to obtain the environmental analysis values ​​corresponding to each of the operating environment data.

[0020] Optionally, determining the fault level corresponding to each of the current meeting fault data includes:

[0021] The current meeting fault data are categorized according to the categories of the operating environment data.

[0022] For each type of current meeting fault data, the fault level corresponding to each type of current meeting fault data is determined by the preset fault warning level classification strategy corresponding to the category.

[0023] Optionally, predicting the fault information of video conference data for a target time period based on each of the current conference fault data, the fault level corresponding to each of the current conference fault data, and the video content data includes:

[0024] Based on the video content data, an adaptive trend analysis algorithm is used to predict the data traffic change trend of each video content data.

[0025] Based on the current meeting failure data and the corresponding failure level, a periodic comparison strategy is used to predict the failure change trend of each of the operating environment data.

[0026] Based on the time series, a fault trend analysis is performed on the data traffic change trend of video content data at the same time point in the time series and the fault change trend of the operating environment data at the same time point in the time series to obtain the fault trend information of the video conference; the time series includes the sequence of each time point between the current time point of the video conference and the end time point of the target time period.

[0027] In the fault trend information, the fault trend information of the target time period is selected, and the fault information of the fault trend information of the target time period is analyzed to obtain the fault information of the video conferencing data of the target time period.

[0028] Secondly, this application also provides a video conferencing failure prediction device. The device includes:

[0029] The acquisition module is used to acquire the video conference data of the current video conference; the video conference data includes operating environment data and video content data;

[0030] The analysis module is used to analyze the video analysis strategy and the operating environment data to obtain various environmental analysis values, and to use the environmental analysis values ​​that meet the operating failure conditions as the current meeting failure data;

[0031] The prediction module is used to determine the fault level corresponding to each of the current meeting fault data, and predict the fault information of the video conference for the target time period based on each of the current meeting fault data, the fault level corresponding to each of the current meeting fault data, and the video content data.

[0032] Optionally, the acquisition module is specifically used for:

[0033] Obtain data information from the current video conference;

[0034] Cluster the data information of the same category according to the category identifier of the data information to obtain the data information of each category;

[0035] By using preset category attributes, categories with the same attributes are aggregated to obtain operating environment data and video content data. Based on the operating environment data and the video content data, the current video conference data is determined. The category attributes include operating environment attributes and video content attributes.

[0036] Optionally, the analysis module is specifically used for:

[0037] Obtain the operating data threshold corresponding to each of the operating environment data, and determine the category to which each operating environment data belongs;

[0038] For the same category of operating environment data, the environmental analysis value of each operating environment data in the category is analyzed using the operating environment data analysis strategy for that category;

[0039] If the environmental analysis value meets the operational fault conditions corresponding to the operational environment data, the environmental analysis value of the operational environment data is determined to be the current meeting fault data.

[0040] Optionally, the analysis module is specifically used for:

[0041] For each category of operating environment data, extract the environmental data information corresponding to the environmental analysis value from the operating environment data;

[0042] According to the data parsing strategy, the environmental data information of the environmental analysis values ​​is parsed and processed to obtain the environmental analysis values ​​corresponding to each of the operating environment data.

[0043] Optionally, the prediction module is specifically used for:

[0044] The current meeting fault data are categorized according to the categories of the operating environment data.

[0045] For each type of current meeting fault data, the fault level corresponding to each type of current meeting fault data is determined by the preset fault warning level classification strategy corresponding to the category.

[0046] Optionally, the prediction module is specifically used for:

[0047] Based on the video content data, an adaptive trend analysis algorithm is used to predict the data traffic change trend of each video content data.

[0048] Based on the current meeting failure data and the corresponding failure level, a periodic comparison strategy is used to predict the failure change trend of each of the operating environment data.

[0049] Based on the time series, a fault trend analysis is performed on the data traffic change trend of video content data at the same time point in the time series and the fault change trend of the operating environment data at the same time point in the time series to obtain the fault trend information of the video conference; the time series includes the sequence of each time point between the current time point of the video conference and the end time point of the target time period.

[0050] In the fault trend information, the fault trend information of the target time period is selected, and the fault information of the fault trend information of the target time period is analyzed to obtain the fault information of the video conferencing data of the target time period.

[0051] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0052] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0053] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0054] The aforementioned video conferencing fault prediction method, apparatus, computer equipment, and storage medium acquire video conferencing data of the current video conference. This video conferencing data includes operating environment data and video content data. Through video analysis strategies and the operating environment data, various environmental analysis values ​​are obtained, and those values ​​meeting the operational fault conditions are used as the current conference fault data. The fault level corresponding to each current conference fault data is determined, and based on the current conference fault data, its corresponding fault level, and the video content data, the fault information of the video conference for a target time period is predicted. By analyzing the current conference fault data in each operating environment data and determining the fault level of each current conference fault data, and then comprehensively predicting the fault information of the video conference for a target time period based on the video content data and the current conference fault data, the efficiency of video conferencing fault prediction is improved. Attached Figure Description

[0055] Figure 1This is a flowchart illustrating a video conferencing failure prediction method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating the steps for determining current meeting failure data in one embodiment;

[0057] Figure 3 This is a flowchart illustrating the steps for predicting fault information in video conferencing data for a target time period in one embodiment.

[0058] Figure 4 This is a flowchart illustrating an example of video conferencing failure prediction in another embodiment;

[0059] Figure 5 This is a structural block diagram of a video conferencing fault prediction device in one embodiment;

[0060] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] The video conferencing fault prediction method provided in this application can be applied to terminals, servers, or systems including both terminals and servers, and is implemented through interaction between the terminal and the server. The terminal can include, but is not limited to, various personal computers, laptops, tablets, etc. The terminal analyzes current meeting fault data in various operating environment data and determines the fault level of each current meeting fault data point. Then, based on video content data and current meeting fault data, it comprehensively predicts the fault information of the video conference for a target time period, thereby improving the efficiency of video conferencing fault prediction.

[0063] In one embodiment, such as Figure 1 As shown, a video conferencing fault prediction method is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0064] Step S101: Obtain the video conference data of the current video conference.

[0065] The video conferencing data includes operating environment data and video content data.

[0066] In this embodiment, the terminal obtains the operating environment data of the video conference through the interfaces of each device in the video conference, and obtains the video content data of the video conference through the live video feed. The operating environment data refers to the operating data of each carrier in the current video conference, including the operating status of the video devices, the quality of the video network connection, and the operating status of the conference application. The video content data refers to the video content of the current video conference, which may include, but is not limited to, the number of viewers, participants, the number of video conference ports, the video conference process, and the complexity of the conference functions required for the video conference.

[0067] Specifically, due to the numerous carrier devices required for video conferencing, and the varying data from these devices with different functions, the terminal needs to acquire operational data (i.e., operational environment data) from all the devices involved in the video conferencing. To ensure compatibility, the terminal uses traditional information collection methods, which may include, but are not limited to, API programming interfaces, syslog data reporting, SNMP information capture, and FTP active uploads, covering logs and data from each time point of the video conference. The collected data is tagged and stored sequentially according to the video conference process. The collected data can be labeled with names such as device number, conference ID, user ID, and IP address.

[0068] Step S102: Analyze the video analysis strategy and operating environment data to obtain various environmental analysis values, and use the environmental analysis values ​​that meet the operating failure conditions as the current meeting failure data.

[0069] In this embodiment, the terminal analyzes the environmental analysis value of each operating environment data point using a video analytics strategy. For each environmental analysis value, the terminal determines whether it meets the operating fault conditions. If the environmental analysis value meets the operating fault conditions, the terminal uses that environmental analysis value as the current meeting fault data. Here, the environmental analysis value is the operating value of the operating environment data. For example, if the operating environment data is the device's CPU utilization rate, the environmental analysis value could be a CPU utilization rate of 30% obtained by the terminal after parsing the current CPU utilization rate data. The operating fault conditions can be, but are not limited to, a fault threshold preset by the terminal for each environmental analysis value. That is, if the environmental analysis value is greater than the preset fault threshold, the terminal uses that environmental analysis value as the current meeting fault data. The specific process of analyzing the environmental analysis values ​​will be explained in detail later.

[0070] Step S103: Determine the fault level corresponding to each current meeting fault data, and predict the fault information of the video conference in the target time period based on each current meeting fault data, the fault level corresponding to each current meeting fault data, and the video content data.

[0071] In this embodiment, for each current meeting failure data point, the terminal determines the corresponding failure level using a failure level classification strategy. Based on video content data, current meeting failure data, and the failure levels corresponding to each current meeting failure data point, the terminal predicts the failure trend information of the video conference and analyzes the failure trend information within a target time period to obtain the video conference failure information for that target time period. The failure level classification strategy differs depending on the category of the operating environment data corresponding to each current meeting failure data point. The failure level classification strategy corresponds to the category of the operating environment data.

[0072] For example, the categories of operational environment data include device packet loss rate, device latency, and image jitter. The classification strategy for device packet loss rate is: 10%-30% is Level 1, 30%-60% is Level 2, and above 60% is Level 3. The classification strategy for device latency is: 0ms-10ms is Level 1, 10ms-20ms is Level 2, and above 20ms is Level 3. The classification strategy for image jitter is: 0°-3° is Level 1, 3°-6° is Level 2, and above 6° is Level 3. Therefore, if the terminal obtains current meeting fault data with a device packet loss rate of 40%, a device latency of 16ms, and an image jitter of 4°, the corresponding fault levels are: 40% device packet loss rate is Level 2, 16ms device latency is Level 2, and 4° image jitter is Level 2.

[0073] Based on the above scheme, the system analyzes the current meeting failure data in various operating environments and determines the corresponding failure level for each failure. Then, by combining the video content data and the current meeting failure data, it comprehensively predicts the failure information of video conferences during the target time period, thereby improving the efficiency of video conference failure prediction.

[0074] Optionally, the process of acquiring video conference data for the current video conference includes: acquiring data information for the current video conference; clustering data information of the same category according to the category identifier of the data information to obtain data information of each category; aggregating categories with the same attributes through preset category attributes to obtain operating environment data and video content data, and determining the current video conference data based on the operating environment data and video content data; the category attributes include operating environment attributes and video content attributes.

[0075] In this embodiment, the terminal receives data information from the video carrier device of the current video conference. This data information includes all video conference-related data, such as the conference content and the conference carrier device. The data information includes category identifiers for multiple unclassified video conference data. The terminal clusters data information of the same category according to each category identifier, obtaining data information of each category. The categories of data information can be, but are not limited to, broad categories such as device operating status, network connection quality, application operating status, and conference content. Each major category contains multiple subcategories. Among them, the device operating status subcategories include items such as device CPU / memory / disk utilization, file handles, thread resources, database connection pool, MCU resource capacity, and TCP connection count; the network connection quality subcategories include items such as MCU device packet loss rate, latency, jitter, video transmission bitrate, and video frame format; the application operating status subcategories include items such as terminal registration, authentication, call entry, meeting center keep-alive, meeting control, and interface call logs; and the meeting content subcategories include items such as the number of current video viewers, the number of participants in the video conference, the number of video conference interfaces, the video conference process content, and the meeting functions required for the video conference.

[0076] The terminal presets category attributes and aggregates categories with the same attribute to obtain data information for each attribute. These categories include operating environment attributes and video content attributes. The operating environment attribute corresponds to the category of operating environment data, and the video content data corresponds to the category of video content data. The operating environment data includes categories such as device operating status, network connection quality, and application operating status; the video content data includes the category of meeting content. The terminal uses the attributed operating environment data and the attributed video content data as the current video conference data for the current video conference.

[0077] Based on the above scheme, by dividing the data information, it is possible to analyze the fault information of the current video conferencing data more accurately, thereby improving the accuracy of the analysis of the fault information of the current video conferencing data.

[0078] Optional, such as Figure 2 As shown, through video analytics strategies and operational environment data, various environmental analysis values ​​are obtained. Environmental analysis values ​​that meet the operational failure conditions are used as the current meeting failure data, including:

[0079] Step S201: Obtain the operating data threshold corresponding to each operating environment data, and determine the category to which each operating environment data belongs.

[0080] In this embodiment, the terminal obtains the corresponding operating data threshold for each operating environment data based on each operating environment data, and determines the category to which each operating environment data belongs. The terminal stores the operating data threshold corresponding to each operating environment data in the terminal's storage area.

[0081] Step S202: For the same category of operating environment data, analyze the environment analysis value of each video operating data in the category using the category's operating environment data analysis strategy.

[0082] In this embodiment, the terminal presets a video conferencing data analysis strategy corresponding to each category of operating environment data. For operating environment data of the same category, the terminal analyzes the environmental analysis value corresponding to each type of operating environment data according to the corresponding operating environment data analysis strategy. The specific analysis process will be described in detail later.

[0083] Step S203: If the environmental analysis value meets the operating fault conditions corresponding to the operating environment data of the environmental analysis value, the environmental analysis value of the operating environment data is determined to be the current meeting fault data.

[0084] In this embodiment, the terminal presets a correspondence between each operating environment data and an operating fault condition. For each environmental analysis value, the terminal queries the correspondence between the operating environment data and the operating fault condition for that environmental analysis value to determine the corresponding operating fault condition. If the environmental analysis value meets the operating fault condition corresponding to its operating environment data, the terminal determines that the environmental analysis value of that operating environment data is the current meeting fault data.

[0085] Specifically, the terminal analyzes the environmental analysis values ​​related to the device's operating status: After obtaining environmental analysis values ​​for data such as device CPU / memory / disk utilization, file handles, thread resources, database connection pool, MCU resource capacity, and TCP connection count, the terminal compares each environmental analysis value with its corresponding data threshold. If any environmental analysis value exceeds the data threshold, the terminal treats this value as a current meeting failure.

[0086] The environmental analysis values ​​for network connection quality are analyzed: network connectivity data collected by the terminal from the MCU device includes data such as packet loss rate, latency, jitter, video transmission bitrate, and video frame format from the video terminal to the MCU device (i.e., operating environment data), and the environmental analysis values ​​of each operating environment data are analyzed. If an environmental analysis value reaches the fault judgment threshold within a detection period, the terminal determines that the environmental analysis value reaching the fault judgment threshold is the fault data for the current meeting.

[0087] Environmental analysis values ​​for application runtime status are analyzed: Real-time log analysis is performed throughout the entire video conferencing process, combining video conferencing system and client logs, including terminal registration, authentication, call inbound, meeting center jump keep-alive, meeting control, and API call logs. For example, if the number of registration failures exceeds a preset value within a detection period, the environmental analysis value reaching that preset value is determined as the current meeting failure data.

[0088] Based on the above scheme, by identifying the current meeting failure data in the environmental analysis values, a data foundation is provided for predicting failure information for the target time period.

[0089] Optionally, through a category-based video conferencing data analysis strategy, the environmental analysis value of each operating environment data in the category is analyzed, including: for each operating environment data in the category, extracting the environmental data information corresponding to the environmental analysis value from the operating environment data; and performing data parsing processing on the environmental data information of the environmental analysis value according to the data parsing strategy to obtain the environmental analysis value corresponding to each operating environment data.

[0090] In this embodiment, for each category of operating environment data, the terminal extracts the environmental data information corresponding to the environmental analysis value. The terminal then performs data parsing processing on the environmental data information according to a data parsing strategy to obtain the environmental analysis value corresponding to each operating environment data. The data parsing strategy can be, but is not limited to, any strategy program capable of implementing the above steps and parsing multiple different types of environmental data information. The operating environment data includes multiple types of environmental data information, which may include environmental analysis value information, operating environment category identifier information, operating environment name information, and operating environment carrier device information.

[0091] Based on the above scheme, by analyzing the environmental analysis values ​​of the operating environment data, a data foundation is provided for determining whether each environmental analysis value is the current video fault data.

[0092] Optionally, the fault level corresponding to each current meeting fault data is determined, including: classifying each current meeting fault data according to the category of operating environment data; and determining the fault level corresponding to each category of current meeting fault data by using a preset fault warning level classification strategy corresponding to the category.

[0093] In this embodiment, the terminal presets a fault warning level classification strategy and a correspondence between the categories of operating environment data and the fault warning level classification strategy. Based on the categories of operating environment data, each current meeting fault data is classified into the corresponding category, resulting in multiple current meeting fault data sets. For each category of current meeting fault data, the terminal queries the correspondence between the categories of operating environment data and the fault warning level classification strategy to obtain the corresponding fault warning level classification strategy. The terminal determines the fault level corresponding to each current meeting fault data set within that category according to the fault warning level classification strategy.

[0094] Based on the above scheme, by determining the fault level corresponding to each current meeting fault data, it is easier to predict the fault change trend of the corresponding operating environment data, thereby improving the accuracy of predicting fault change trends.

[0095] Optional, such as Figure 3 As shown, based on the fault data of each current meeting, the fault level corresponding to each current meeting fault data, and the video content data, the fault information of the video conference data for the target time period is predicted, including:

[0096] Step S301: Based on the video content data, predict the data traffic change trend of each video content data using an adaptive trend analysis algorithm.

[0097] In this embodiment, the terminal uses an adaptive trend analysis algorithm to predict the data traffic change trend of each video content data point from the current time point onwards, based on the data of each video content. The adaptive trend analysis algorithm can be, but is not limited to, any dynamic adaptive trend analysis tool capable of implementing the above steps.

[0098] Among them, the data traffic change trend refers to the change trend of video content data traffic from the current point in time. For example, the trend of peak client usage and user growth, the trend of bandwidth demand growth for different access network access methods, and the trend of degradation of access line indicators as the number of users increases.

[0099] Step S302: Based on the current meeting failure data and the corresponding failure level, predict the failure change trend of each operating environment data through a periodic comparison strategy.

[0100] In this embodiment, the terminal predicts the fault change trend of each operating environment data point based on each current meeting fault data point and the corresponding fault level, using a periodic comparison strategy. Specifically, when the environmental analysis value corresponding to the operating environment data is not part of the current meeting fault data, the terminal predicts the fault change trend of that operating environment data based on the environmental analysis value of that operating environment data, using a periodic comparison strategy. The periodic comparison strategy involves dividing the acquired meeting fault data for the current time period into multiple periodic sub-time periods, and predicting the fault change trend of the operating environment data corresponding to that meeting fault data starting from the current time point by comparing the changing trends of meeting fault data in adjacent sub-time periods within the time series of the current time period.

[0101] The fault change trend is the increase or decrease trend of faults for each operating environment data starting from the current point in time. For example, the increase in the number of user-end software versions installed, the error frequency trend of different versions, and the trend of MCU resource pool usage on the system side, as well as the predicted resource expansion amount and frequency trend, etc.

[0102] Step S303: According to the time series, perform fault trend analysis on the data traffic change trend of video content data at the same time point in the time series and the fault change trend of operating environment data at the same time point in the time series to obtain the fault trend information of the video conference.

[0103] The time series includes a sequence of time points from the current video conference time point to the end of the target time period.

[0104] In this embodiment, the terminal divides the data traffic change trend of video content data and the fault change trend of operating environment data into multiple time points and multiple time points of fault change trends, according to the sequence of time points from the current time point of the video conference to the end time point of the target period. The terminal compares and integrates the data traffic change trends of video content data and the fault change trends of operating environment data at the same time point, and comprehensively analyzes the fault trend information of the video conference at that time point to obtain the fault trend information of the video conference at that time point. Similarly, through the above method, the terminal analyzes and obtains the fault trend information of the video conference at each time point, and arranges the fault trend information in a time sequence to obtain the fault trend information of the entire video conference. The fault trend information refers to the fault trend direction information of each data information in the video conference.

[0105] Step S304: Select the fault trend information for the target time period from the fault trend information, and analyze the fault information of the fault trend information for the target time period to obtain the fault information of the video conferencing data for the target time period.

[0106] In this embodiment, the terminal selects the fault trend information for a target time period from the fault trend information of the video conference, according to the time sequence. Based on the fault trend information of each data point within the target time period, the terminal predicts the fault point of the video conference within the target time period, the time period in which the fault point occurs, and the corresponding fault cause. The terminal uses the fault point of the target time period, the time period in which the fault point occurs, and the corresponding fault cause as the fault information of the video conference data for the target time period.

[0107] Based on the above scheme, the system analyzes the current meeting failure data in various operating environments and determines the corresponding failure level for each failure. Then, by combining the video content data and the current meeting failure data, it comprehensively predicts the failure information of video conferences during the target time period, thereby improving the efficiency of video conference failure prediction.

[0108] This application also provides an example of video conferencing failure prediction, as shown in Figure 4. The specific processing procedure includes the following steps:

[0109] Step S401: Obtain the data information of the current video conference.

[0110] Step S402: Cluster the data information of the same category according to the category identifier of the data information to obtain the data information of each category.

[0111] Step S403: By using preset category attributes, categories with the same attributes are aggregated to obtain operating environment data and video content data. Based on the operating environment data and video content data, the current video conference data is determined. Category attributes include operating environment attributes and video content attributes.

[0112] Step S404: Obtain the operating data threshold corresponding to each operating environment data, and determine the category to which each operating environment data belongs.

[0113] Step S405: For the same category of operating environment data, for each category of operating environment data, extract the environmental data information corresponding to the environmental analysis value from the operating environment data.

[0114] Step S406: According to the data parsing strategy, perform data parsing processing on the environmental data information of the environmental analysis values ​​to obtain the environmental analysis values ​​corresponding to each operating environment data.

[0115] Step S407: If the environmental analysis value meets the operating fault conditions corresponding to the operating environment data of the environmental analysis value, determine the environmental analysis value of the operating environment data as the current meeting fault data.

[0116] Step S408: Classify the current meeting fault data according to the category of operating environment data.

[0117] Step S409: For each type of current meeting fault data, determine the fault level corresponding to each type of current meeting fault data by using the preset fault warning level classification strategy corresponding to the category.

[0118] Step S410: Based on the video content data, predict the data traffic change trend of each video content data using an adaptive trend analysis algorithm.

[0119] Step S411: Based on the current meeting failure data and the corresponding failure level, predict the failure change trend of each operating environment data through a periodic comparison strategy.

[0120] Step S412: According to the time series, perform fault trend analysis on the data traffic change trend of video content data at the same time point in the time series and the fault change trend of operating environment data at the same time point in the time series to obtain fault trend information of video conferencing.

[0121] Step S413: Select the fault trend information for the target time period from the fault trend information, and analyze the fault information of the fault trend information for the target time period to obtain the fault information of the video conferencing data for the target time period.

[0122] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0123] Based on the same inventive concept, this application also provides a video conferencing fault prediction device for implementing the video conferencing fault prediction method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more video conferencing fault prediction device embodiments provided below can be found in the limitations of the video conferencing fault prediction method described above, and will not be repeated here.

[0124] In one embodiment, such as Figure 5As shown, a video conferencing fault prediction device is provided, including: an acquisition module 510, an analysis module 520, and a prediction module 530, wherein:

[0125] The acquisition module 510 is used to acquire the video conference data of the current video conference; the video conference data includes operating environment data and video content data;

[0126] Analysis module 520 is used to analyze and obtain various environmental analysis values ​​through video analysis strategies and the operating environment data, and to use the environmental analysis values ​​that meet the operating fault conditions as the current meeting fault data;

[0127] The prediction module 530 is used to determine the fault level corresponding to each of the current meeting fault data, and predict the fault information of the video conference in the target time period based on each of the current meeting fault data, the fault level corresponding to each of the current meeting fault data, and the video content data.

[0128] Optionally, the acquisition module 510 is specifically used for:

[0129] Obtain data information from the current video conference;

[0130] Cluster the data information of the same category according to the category identifier of the data information to obtain the data information of each category;

[0131] By using preset category attributes, categories with the same attributes are aggregated to obtain operating environment data and video content data. Based on the operating environment data and the video content data, the current video conference data is determined. The category attributes include operating environment attributes and video content attributes.

[0132] Optionally, the analysis module 520 is specifically used for:

[0133] Obtain the operating data threshold corresponding to each of the operating environment data, and determine the category to which each operating environment data belongs;

[0134] For the same category of operating environment data, the environmental analysis value of each operating environment data in the category is analyzed using the operating environment data analysis strategy for that category;

[0135] If the environmental analysis value meets the operational fault conditions corresponding to the operational environment data, the environmental analysis value of the operational environment data is determined to be the current meeting fault data.

[0136] Optionally, the analysis module 520 is specifically used for:

[0137] For each category of operating environment data, extract the environmental data information corresponding to the environmental analysis value from the operating environment data;

[0138] According to the data parsing strategy, the environmental data information of the environmental analysis values ​​is parsed and processed to obtain the environmental analysis values ​​corresponding to each of the operating environment data.

[0139] Optionally, the prediction module 530 is specifically used for:

[0140] The current meeting fault data are categorized according to the categories of the operating environment data.

[0141] For each type of current meeting fault data, the fault level corresponding to each type of current meeting fault data is determined by the preset fault warning level classification strategy corresponding to the category.

[0142] Optionally, the prediction module 530 is specifically used for:

[0143] Based on the video content data, an adaptive trend analysis algorithm is used to predict the data traffic change trend of each video content data.

[0144] Based on the current meeting failure data and the corresponding failure level, a periodic comparison strategy is used to predict the failure change trend of each of the operating environment data.

[0145] Based on the time series, a fault trend analysis is performed on the data traffic change trend of video content data at the same time point in the time series and the fault change trend of the operating environment data at the same time point in the time series to obtain the fault trend information of the video conference; the time series includes the sequence of each time point between the current time point of the video conference and the end time point of the target time period.

[0146] In the fault trend information, the fault trend information of the target time period is selected, and the fault information of the fault trend information of the target time period is analyzed to obtain the fault information of the video conferencing data of the target time period.

[0147] The modules in the aforementioned video conferencing fault prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0148] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a video conferencing fault prediction method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0149] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0150] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0152] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0154] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting video conferencing failures, characterized in that, The method includes: Acquire the video conference data of the current video conference; the video conference data includes operating environment data and video content data; By analyzing the video analysis strategy and the aforementioned operating environment data, various environmental analysis values ​​are obtained, and the environmental analysis values ​​that meet the operating failure conditions are used as the current meeting failure data. Determine the fault level corresponding to each of the current meeting fault data; Based on the video content data, an adaptive trend analysis algorithm is used to predict the data traffic change trend of each video content data. Based on the current meeting failure data and the corresponding failure level, a periodic comparison strategy is used to predict the failure change trend of each of the operating environment data. Based on the time series, a fault trend analysis is performed on the data traffic change trend of video content data at the same time point in the time series, and the fault change trend of the operating environment data at the same time point in the time series, to obtain the fault trend information of the video conference; the time series includes the sequence of each time point between the current time point of the video conference and the end time point of the target time period. In the fault trend information, the fault trend information of the target time period is selected, and the fault information of the fault trend information of the target time period is analyzed to obtain the fault information of the video conferencing data of the target time period.

2. The method according to claim 1, characterized in that, The step of obtaining the video conference data of the current video conference includes: Obtain data information from the current video conference; Cluster the data information of the same category according to the category identifier of the data information to obtain the data information of each category; By using preset category attributes, categories with the same attributes are aggregated to obtain operating environment data and video content data. Based on the operating environment data and the video content data, the current video conference data is determined. The category attributes include operating environment attributes and video content attributes.

3. The method according to claim 1, characterized in that, The process involves analyzing video analytics strategies and operational environment data to obtain various environmental analysis values. Environmental analysis values ​​that meet operational failure conditions are then used as the current meeting failure data, including: Obtain the operating data threshold corresponding to each of the operating environment data, and determine the category to which each operating environment data belongs; For the same category of operating environment data, the environmental analysis value of each operating environment data in the category is analyzed using the operating environment data analysis strategy for that category; If the environmental analysis value meets the operational fault conditions corresponding to the operational environment data, the environmental analysis value of the operational environment data is determined to be the current meeting fault data.

4. The method according to claim 3, characterized in that, The environmental analysis value of each operational environment data in the category, analyzed using the operational environment data analysis strategy of the category, includes: For each category of operating environment data, extract the environmental data information corresponding to the environmental analysis value from the operating environment data; According to the data parsing strategy, the environmental data information of the environmental analysis values ​​is parsed and processed to obtain the environmental analysis values ​​corresponding to each of the operating environment data.

5. The method according to claim 1, characterized in that, Determining the fault level corresponding to each of the current meeting fault data includes: The current meeting fault data are categorized according to the types of the operating environment data. For each type of current meeting fault data, the fault level corresponding to each type of current meeting fault data is determined by the preset fault warning level classification strategy corresponding to the category.

6. A video conferencing fault prediction device, characterized in that, The device includes: The acquisition module is used to acquire the video conference data of the current video conference; the video conference data includes operating environment data and video content data; The analysis module is used to analyze the video analysis strategy and the operating environment data to obtain various environmental analysis values, and to use the environmental analysis values ​​that meet the operating failure conditions as the current meeting failure data; The prediction module is used to determine the fault level corresponding to each of the current meeting fault data; predict the data traffic change trend of each video content data using an adaptive trend analysis algorithm based on each video content data; predict the fault change trend of each operating environment data using a periodic comparison strategy based on each of the current meeting fault data and the fault level corresponding to the current meeting fault data; perform fault trend analysis on the data traffic change trend of the video content data and the fault change trend of the operating environment data at the same time point in the time series according to the time series, to obtain the fault trend information of the video conference; the time series includes the sequence of each time point from the current video conference time point to the end time point of the target time period; select the fault trend information of the target time period from the fault trend information, and analyze the fault information of the fault trend information of the target time period to obtain the fault information of the video conference data of the target time period.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images