Terminal use state identification method and apparatus, computing device, and storage medium

Abstract

The application discloses a terminal use state recognition method and device, a computing device and a storage medium. The method comprises the following steps: obtaining a network traffic index value of a target terminal at at least one sampling time; obtaining a network traffic index threshold value output by a network traffic index threshold model; comparing the network traffic index value at any sampling time with the network traffic index threshold value to identify a normal use time from the sampling time; and determining a sleep period and / or a normal use period of the target terminal based on the normal use time. According to the scheme, the identification of the target terminal use state can be realized without installing a plug-in in each target terminal to listen to the lock screen or unlock event, thereby improving the user experience and protecting the data security in the target terminal. Moreover, the network traffic index value is obtained according to a machine learning model, so compared with an artificially configured index threshold value, the identification accuracy of the terminal use state can be further improved.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and specifically to a method, apparatus, computing device, and storage medium for identifying the usage status of a terminal. Background Technology

[0002] With the continuous development of technology and society, the emergence of smart terminals has greatly facilitated people's work and life. In order to improve user experience, some operators or platforms will switch network modes and recommend information based on the usage status of smart terminals, etc. Therefore, the identification of the usage status of smart terminals is of great significance.

[0003] However, during implementation, the inventors discovered the following drawbacks in the existing technology: Existing technologies typically embed corresponding plugins into various smart terminals, which then obtain the smart terminal's lock screen events and / or unlock events, etc. However, this approach requires each smart terminal to have a plugin installed, thereby reducing user experience and compromising the data security of the user's smart terminal. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed to provide a method, apparatus, computing device and storage medium for identifying the usage status of a terminal that overcomes or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a method for identifying the usage status of a terminal is provided, comprising:

[0006] Obtain the network traffic metrics of the target terminal at at least one sampling time;

[0007] Obtain the network traffic metric thresholds output by the network traffic metric threshold model;

[0008] The network traffic index value at any sampling time is compared with the network traffic index threshold to identify normal usage time from the sampling time.

[0009] Based on the normal usage time, the sleep period and / or normal usage period of the target terminal are determined.

[0010] In an optional implementation, determining the sleep period and / or normal usage period of the target terminal based on the normal usage time further includes:

[0011] The normal usage time is clustered to generate at least one cluster;

[0012] The normal usage period of the target terminal is determined based on the time period corresponding to the cluster.

[0013] In an optional implementation, determining the normal usage period of the target terminal based on the time period corresponding to the cluster further includes:

[0014] Count the number of items with normal usage time contained in each cluster;

[0015] Filter out target clusters that contain more than a preset number of normal usage times;

[0016] Based on the time period corresponding to the target cluster, the normal usage period of the target terminal is determined.

[0017] In an optional implementation, before obtaining the network traffic metric threshold output by the network traffic metric threshold model, the method further includes:

[0018] Construct a network traffic metric threshold model;

[0019] The network traffic index threshold model was trained offline using the historical network traffic index values ​​of the sample terminals to obtain the offline trained network traffic index threshold model.

[0020] The network traffic index value of the target terminal at at least one sampling time is input into the offline trained network traffic index threshold model;

[0021] Specifically, obtaining the network traffic indicator threshold output by the network traffic indicator threshold model involves: obtaining the network traffic indicator threshold output by the network traffic indicator threshold model after inputting the network traffic indicator value of the target terminal at at least one sampling time into the offline trained network traffic indicator threshold model.

[0022] In one optional implementation, after obtaining the offline-trained network traffic indicator threshold model, the method further includes: obtaining the initial network traffic indicator threshold output by the offline-trained network traffic indicator threshold model.

[0023] The step of inputting the network traffic index value of the target terminal at at least one sampling time into the offline-trained network traffic index threshold model further includes: inputting the network traffic index value of the target terminal at at least one sampling time and the initial network traffic index threshold into the offline-trained network traffic index threshold model.

[0024] In an optional implementation, the offline training of the constructed network traffic indicator threshold model using historical network traffic indicator values ​​from sample terminals further includes:

[0025] Obtain the historical network traffic index values ​​of the sample terminals corresponding to each region;

[0026] The network traffic index threshold model was trained offline using the historical network traffic index values ​​of sample terminals corresponding to each region.

[0027] The step of obtaining the initial network traffic index threshold output by the offline-trained network traffic index threshold model further includes: determining the target region corresponding to the target terminal, and obtaining the initial network traffic index threshold of the target region output by the offline-trained network traffic index threshold model.

[0028] In an optional implementation, obtaining the network traffic indicator value of the target terminal at at least one sampling time further includes:

[0029] Obtain the network traffic index value collected by a preset application in the gateway to which the target terminal belongs.

[0030] According to another aspect of the present invention, a device for identifying the usage status of a terminal is provided, comprising:

[0031] The first acquisition module is used to acquire the network traffic index value of the target terminal at at least one sampling time.

[0032] The second acquisition module is used to acquire the network traffic indicator threshold output by the network traffic indicator threshold model.

[0033] The identification module is used to compare the network traffic indicator value at any sampling time with the network traffic indicator threshold in order to identify the normal usage time from the sampling time.

[0034] The determination module is used to determine the sleep period and / or normal usage period of the target terminal based on the normal usage time.

[0035] In an optional implementation, the determining module is further configured to: perform clustering processing on the normal usage time to generate at least one cluster;

[0036] The normal usage period of the target terminal is determined based on the time period corresponding to the cluster.

[0037] In an optional implementation, the determining module is further configured to: count the number of normal usage times contained in each cluster;

[0038] Filter out target clusters that contain more than a preset number of normal usage times;

[0039] Based on the time period corresponding to the target cluster, the normal usage period of the target terminal is determined.

[0040] In one optional embodiment, the apparatus further includes: a training module for constructing a network traffic indicator threshold model; and offline training the constructed network traffic indicator threshold model using historical network traffic indicator values ​​of sample terminals to obtain an offline trained network traffic indicator threshold model.

[0041] The second acquisition module is further configured to: input the network traffic index value of the target terminal at at least one sampling time into the offline trained network traffic index threshold model;

[0042] The network traffic index threshold output by the network traffic index threshold model is obtained after inputting the network traffic index value of the target terminal at at least one sampling time into the offline trained network traffic index threshold model.

[0043] In an optional implementation, the second acquisition module is further configured to: acquire the initial network traffic index threshold output by the offline trained network traffic index threshold model;

[0044] The network traffic index value of the target terminal at at least one sampling time and the initial network traffic index threshold are input into the offline trained network traffic index threshold model.

[0045] In an optional implementation, the training module is further configured to: obtain the historical network traffic index values ​​of the sample terminals corresponding to each region; and use the historical network traffic index values ​​of the sample terminals corresponding to each region to perform offline training on the constructed network traffic index threshold model.

[0046] The second acquisition module is further used to: determine the target area corresponding to the target terminal, and acquire the initial network traffic index threshold of the target area output by the offline trained network traffic index threshold model.

[0047] In an optional implementation, the first acquisition module is further configured to: acquire the network traffic indicator value collected by a preset application in the gateway to which the target terminal belongs.

[0048] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0049] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the terminal usage state identification method described above.

[0050] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the terminal usage state identification method described above.

[0051] In this invention, the network traffic index value of the target terminal can be obtained by a gateway or operator platform, and the usage status of the target terminal can be identified based on the network traffic index value. Therefore, it is not necessary to install a plugin in each target terminal to listen for screen lock or unlock events to identify the usage status of the target terminal, thereby improving the user experience and ensuring the data security of the target terminal. Moreover, the network traffic index value in this invention is obtained by learning from a machine learning model, so compared with manually configured index thresholds, this invention can further improve the accuracy of terminal usage status identification.

[0052] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0053] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0054] Figure 1 A flowchart illustrating a method for identifying the usage status of a terminal according to an embodiment of the present invention is shown.

[0055] Figure 2 A flowchart illustrating a method for obtaining network traffic indicator thresholds according to an embodiment of the present invention is shown.

[0056] Figure 3 This diagram illustrates an abnormal data filtering method provided by an embodiment of the present invention.

[0057] Figure 4 A flowchart illustrating another method for obtaining network traffic indicator thresholds provided by an embodiment of the present invention is shown;

[0058] Figure 5 This diagram illustrates a cluster provided by an embodiment of the present invention.

[0059] Figure 6 A schematic diagram of the structure of a terminal usage status identification device provided in an embodiment of the present invention is shown;

[0060] Figure 7 This diagram illustrates the architecture of a terminal usage status identification system provided by an embodiment of the present invention.

[0061] Figure 8 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0062] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0063] The inventors' research into existing methods for identifying terminal usage status revealed that, because these methods require monitoring screen lock and / or unlock events, a monitoring plugin needs to be installed on each terminal to be identified. This plugin not only occupies terminal storage and operating space but also negatively impacts user experience and increases the risk of malicious intrusion, thereby reducing data security.

[0064] Therefore, this invention provides a solution for identifying terminal usage status without installing plugins on each terminal, thereby saving terminal storage space, improving user experience, and ensuring terminal data security. The following will illustrate this invention in detail with specific examples.

[0065] Figure 1 The diagram illustrates a flowchart of a method for identifying the usage status of a terminal according to an embodiment of the present invention. The method provided in this embodiment can be executed on the server side.

[0066] like Figure 1 As shown, the method includes the following steps:

[0067] Step S110: Obtain the network traffic index value of the target terminal at at least one sampling time.

[0068] The target terminal is a smart terminal whose usage status is to be identified. This embodiment of the invention does not limit the specific type of the target terminal; for example, the smart terminal can be a mobile phone, computer, smart wearable device, etc. The usage status specifically includes a sleep state and a normal usage state.

[0069] The sampling time specifically refers to the sampling period within a preset time window. This preset time window can be the last 7 days, the last 1 day, etc. In actual implementation, network traffic metrics are usually collected at a corresponding sampling frequency (e.g., once every 5 minutes), and the time at which these network traffic metrics are collected is the sampling time. It should be understood that this sampling time can be a specific point in time or a short period of time. For example, the sampling time could be 10:00, in which case the network traffic metrics collected at that time would be the instantaneous network traffic metrics collected at 10:00; the sampling time could also be 10:00-10:01, in which case the network traffic metrics collected between 10:00 and 10:01 would be the average value of the network traffic metrics collected between 10:00 and 10:01.

[0070] Network traffic metrics are specifically metrics that characterize the network traffic usage of a target terminal. These metrics can be collected by the operator or gateway. In one optional implementation, network traffic metrics include, but are not limited to, at least one of the following: uplink traffic rate and downlink traffic rate. The uplink traffic rate is the rate at which the terminal sends network data, and the downlink traffic rate is the rate at which the terminal receives network data.

[0071] As an optional implementation of this invention, this embodiment can identify the terminal's usage status in a specific area (the area corresponding to the used Wi-Fi) based on the terminal's Wi-Fi traffic usage. Taking home Wi-Fi as an example, this embodiment identifies the terminal's usage status in the area where the terminal is located by the terminal's use of home Wi-Fi traffic. Therefore, the network traffic indicator value mentioned in this embodiment specifically refers to the Wi-Fi traffic indicator value of the target terminal.

[0072] Furthermore, to enhance user experience and improve the accuracy of network traffic metric collection, this embodiment of the invention can configure a preset application (such as an Agent) in the Wi-Fi gateway. This preset application collects network traffic metric values ​​from terminals connected to the gateway. Therefore, this embodiment of the invention specifically obtains network traffic metric values ​​collected by a preset application in the gateway to which the target terminal belongs.

[0073] In one alternative implementation, the corresponding network traffic metric value can be extracted using the terminal's MAC address.

[0074] Step S120: Obtain the network traffic indicator threshold output by the network traffic indicator threshold model.

[0075] Since some processes within the terminal are still running in the background even when the terminal is in sleep mode, there will still be some data consumption. Therefore, this embodiment of the invention does not directly define the time with data consumption as normal usage time and the time without data consumption as sleep time. Instead, it determines a network traffic indicator threshold, which serves as the delimitation value between normal usage time and sleep sampling time.

[0076] Unlike manually setting network traffic indicator thresholds, the network traffic indicator thresholds in this embodiment of the invention are output by a network traffic indicator threshold model, thereby avoiding the technical drawback of low recognition accuracy caused by manually setting network traffic indicator thresholds. The network traffic indicator thresholds can be obtained in, but are not limited to, the following ways:

[0077] Method 1: Using Figure 2 The method shown is used to obtain network traffic metric thresholds. Figure 2 This diagram illustrates a flowchart of a method for obtaining network traffic indicator thresholds according to an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S210-S230:

[0078] Step S210: Construct a network traffic metric threshold model.

[0079] This network traffic metric threshold model is built based on a machine learning algorithm, and the specific construction method and structure are not limited in this embodiment of the invention. For example, a network traffic metric threshold model containing network layers such as convolutional layers and ReLU layers can be constructed based on a deep neural network algorithm.

[0080] Step S220: Use the historical network traffic index values ​​of the sample terminals to perform offline training on the constructed network traffic index threshold model to obtain the offline trained network traffic index threshold model.

[0081] Historical network traffic metrics of a large number of sample terminals are obtained to generate sample data. Specifically, the historical network traffic metrics of the sample terminals are the network traffic metrics of each sample terminal at each sampling time within the historical period.

[0082] The sample data is assigned labels, and the network traffic indicator threshold model is trained offline using the sample data and the corresponding labels. When the preset convergence condition is met, the offline training ends, thus obtaining the offline trained network traffic indicator threshold model.

[0083] In one optional implementation, to improve the training performance of the network traffic metric threshold model, the sample data includes historical network traffic metric values ​​of sample terminals corresponding to a preset time period. This preset time period can be a period from 3:00 AM to 5:00 AM, which is typically a time when terminals are in a dormant state.

[0084] In an optional implementation, to further improve the processing accuracy of the network traffic indicator threshold model, after obtaining the historical network traffic indicator values ​​of sample terminals corresponding to a preset time period, this embodiment of the invention further removes abnormal data within that preset time period. Specifically, the abnormal data refers to data with large fluctuations. For example... Figure 3 As shown, L1 is a data waveform before filtering. After filtering out abnormal data and the peak value is too high, it becomes L4. L2 is another data waveform before filtering. Since there is no abnormal data in it, the L5 waveform after filtering is the same as the L2 waveform. L3 is yet another data waveform before filtering. Since the L3 fluctuates greatly, this entire data segment is removed.

[0085] In one optional implementation, this embodiment of the invention specifically acquires historical data of candidate terminals, and filters out terminals with activity levels higher than a preset activity threshold based on this historical data. These terminals are then used as sample terminals, and data from these highly active terminals is used for model training, thereby further improving the processing accuracy of the network traffic indicator threshold model. Specifically, terminals with activity levels higher than the preset activity threshold can be identified based on factors such as the cumulative online time and / or cumulative data consumption within a preset time period.

[0086] Step S230: Obtain the network traffic indicator threshold output by the offline trained network traffic indicator threshold model.

[0087] In this acquisition method, the network traffic indicator threshold of the offline trained network traffic indicator threshold model is directly used as the network traffic indicator threshold of the target terminal, thereby improving the efficiency of terminal usage status identification.

[0088] In an optional implementation, due to differences in time zones and user behavior habits across different regions, this embodiment of the invention further uses an offline-trained network traffic indicator threshold model to obtain network traffic indicator thresholds for different regions, thereby improving the accuracy of terminal usage status identification. In the specific implementation process, historical network traffic indicator values ​​of sample terminals corresponding to each region are obtained, and a regional training method is adopted. The historical network traffic indicator values ​​of sample terminals corresponding to each region are used to train the constructed network traffic indicator threshold model offline. Finally, the target region corresponding to the target terminal is determined, and the network traffic indicator threshold of the target region output by the offline-trained network traffic indicator threshold model is obtained. This network traffic indicator threshold is then used as the network traffic indicator threshold corresponding to the target terminal.

[0089] Method 2: Using Figure 4 The method shown is used to obtain network traffic metric thresholds. Figure 4 This illustration shows a flowchart of another method for obtaining network traffic indicator thresholds provided by an embodiment of the present invention, as shown below. Figure 4 As shown, the method includes the following steps S410-S440:

[0090] Step S410: Construct a network traffic metric threshold model.

[0091] Step S420: Use the historical network traffic index values ​​of the sample terminals to perform offline training on the constructed network traffic index threshold model to obtain the offline trained network traffic index threshold model.

[0092] The specific implementation process of steps S410 and S420 can be referred to the description in steps S210 and S220, and will not be repeated here.

[0093] Step S430: Input the network traffic index value of the target terminal at at least one sampling time into the network traffic index threshold model trained offline.

[0094] Unlike the first acquisition method, this acquisition method, after obtaining the offline-trained network traffic indicator threshold model, does not directly use the network traffic indicator threshold output by the network traffic indicator threshold model as the network traffic indicator threshold corresponding to the target terminal. Instead, it further inputs the network traffic indicator value of the target terminal at at least one sampling time into the offline-trained network traffic indicator threshold model, and the network traffic indicator threshold model obtains a more accurate network traffic indicator value through further learning of the target terminal data.

[0095] Step S440: Obtain the network traffic index threshold output by the network traffic index threshold model after inputting the network traffic index value of the target terminal at at least one sampling time into the offline trained network traffic index threshold model.

[0096] In this acquisition method, the network traffic index value of the target terminal at at least one sampling time is input into the offline trained network traffic index threshold model, and the network traffic index threshold output by the network traffic index threshold model is the network traffic index threshold corresponding to the target terminal.

[0097] In one optional implementation, after obtaining the offline-trained network traffic indicator threshold model, the initial network traffic indicator threshold output by the offline-trained network traffic indicator threshold model is further obtained, and the network traffic indicator value of the target terminal at at least one sampling time and the initial network traffic indicator threshold are input into the offline-trained network traffic indicator threshold model. Thus, the offline-trained network traffic indicator threshold model can use the initial network traffic indicator threshold as the initial value for iteration to learn, and finally obtain the network traffic indicator threshold corresponding to the target terminal.

[0098] Optionally, to improve the accuracy of terminal usage status identification, this acquisition method obtains the historical network traffic index values ​​of sample terminals corresponding to each region, and uses these historical network traffic index values ​​to train the constructed network traffic index threshold model offline. Then, it determines the target region corresponding to the target terminal, obtains the initial network traffic index threshold of the target region output by the offline-trained network traffic index threshold model, and inputs the initial network traffic index threshold of the target region and the network traffic index value of the target terminal at at least one sampling time into the offline-trained network traffic index threshold model. Thus, the offline-trained network traffic index threshold model can use the initial network traffic index threshold as the initial value for iteration to learn, ultimately obtaining the network traffic index threshold corresponding to the target terminal.

[0099] Step S130: Compare the network traffic index value at any sampling time with the network traffic index threshold to identify normal usage time from the sampling time.

[0100] Specifically, for each sampling time of the target terminal, the network traffic index value of the sampling time is compared with the network traffic index threshold obtained in step S120. If the network traffic index value of the sampling time is greater than the network traffic index threshold, the sampling time is determined as normal usage time; otherwise, the sampling time is determined as sleep time.

[0101] Step S140: Determine the sleep period and / or normal usage period of the target terminal based on normal usage time.

[0102] In one alternative implementation, the set of normal usage time can be used as the normal usage period of the target terminal, and other time periods outside the normal usage period can be used as the sleep period of the target terminal.

[0103] In another optional implementation, since the terminal experiences brief periods of low data consumption during use, to improve the accuracy of identifying normal usage periods, this embodiment of the invention further clusters the normal usage times after obtaining them to generate at least one cluster. Then, based on the time period corresponding to the cluster, the normal usage period of the target terminal is determined. This embodiment of the invention does not limit the specific clustering algorithm; for example, algorithms such as DBSCAN can be used for clustering. After obtaining the clusters, the normal usage times contained in the clusters are arranged sequentially from earliest to latest, and the time period between the start point of the earliest normal usage time and the end point of the latest normal usage time is taken as the time period corresponding to that cluster.

[0104] Optionally, to further improve the accuracy of identifying normal usage periods, after obtaining each cluster, this embodiment of the invention counts the number of normal usage times contained in each cluster, and filters out target clusters whose number of normal usage times is greater than a preset number. Then, based on the time period corresponding to the target cluster, the normal usage period of the target terminal is determined. Figure 5 As shown, since the number of normal usage times contained in cluster C1 is equal to the preset number 1, cluster C1 will no longer be used as the target cluster. Since the number of normal usage times contained in cluster C2 is greater than the preset number 1, cluster C2 will be used as the target cluster.

[0105] Furthermore, after obtaining the target terminal's sleep and / or normal usage periods, the network mode can be switched during the corresponding periods. For example, the network mode can be switched to high-speed mode during normal usage periods and to low-speed mode during sleep periods. Relevant activity information can also be recommended to the target terminal.

[0106] Therefore, the embodiments of the present invention can obtain the network traffic index value of the target terminal through a gateway or operator platform, and identify the usage status of the target terminal based on the network traffic index value. Thus, it is not necessary to install a plugin in each target terminal to listen for screen lock or unlock events to identify the usage status of the target terminal, thereby improving the user experience and ensuring the data security of the target terminal. Moreover, the network traffic index value in the embodiments of the present invention is obtained by learning from a machine learning model. Therefore, compared with manually configured index thresholds, the embodiments of the present invention can further improve the accuracy of terminal usage status identification.

[0107] Figure 6 A schematic diagram of a terminal usage status identification device provided in an embodiment of the present invention is shown. Figure 6 As shown, the device 600 includes:

[0108] The first acquisition module 610 is used to acquire the network traffic index value of the target terminal at at least one sampling time.

[0109] The second acquisition module 620 is used to acquire the network traffic indicator threshold output by the network traffic indicator threshold model.

[0110] The identification module 630 is used to compare the network traffic index value at any sampling time with the network traffic index threshold in order to identify the normal usage time from the sampling time.

[0111] The determination module 640 is used to determine the sleep period and / or normal usage period of the target terminal based on the normal usage time.

[0112] In an optional implementation, the determining module is further configured to: perform clustering processing on the normal usage time to generate at least one cluster;

[0113] The normal usage period of the target terminal is determined based on the time period corresponding to the cluster.

[0114] In an optional implementation, the determining module is further configured to: count the number of normal usage times contained in each cluster;

[0115] Filter out target clusters that contain more than a preset number of normal usage times;

[0116] Based on the time period corresponding to the target cluster, the normal usage period of the target terminal is determined.

[0117] In one optional embodiment, the apparatus further includes: a training module for constructing a network traffic indicator threshold model; and offline training the constructed network traffic indicator threshold model using historical network traffic indicator values ​​of sample terminals to obtain an offline trained network traffic indicator threshold model.

[0118] The second acquisition module is further configured to: input the network traffic index value of the target terminal at at least one sampling time into the offline trained network traffic index threshold model;

[0119] The network traffic index threshold output by the network traffic index threshold model is obtained after inputting the network traffic index value of the target terminal at at least one sampling time into the offline trained network traffic index threshold model.

[0120] In an optional implementation, the second acquisition module is further configured to: acquire the initial network traffic index threshold output by the offline trained network traffic index threshold model;

[0121] The network traffic index value of the target terminal at at least one sampling time and the initial network traffic index threshold are input into the offline trained network traffic index threshold model.

[0122] In an optional implementation, the training module is further configured to: obtain the historical network traffic index values ​​of the sample terminals corresponding to each region; and use the historical network traffic index values ​​of the sample terminals corresponding to each region to perform offline training on the constructed network traffic index threshold model.

[0123] The second acquisition module is further used to: determine the target area corresponding to the target terminal, and acquire the initial network traffic index threshold of the target area output by the offline trained network traffic index threshold model.

[0124] In an optional implementation, the first acquisition module is further configured to: acquire the network traffic indicator value collected by a preset application in the gateway to which the target terminal belongs.

[0125] Therefore, the embodiments of the present invention can obtain the network traffic index value of the target terminal through a gateway or operator platform, and identify the usage status of the target terminal based on the network traffic index value. Thus, it is not necessary to install a plugin in each target terminal to listen for screen lock or unlock events to identify the usage status of the target terminal, thereby improving the user experience and ensuring the data security of the target terminal. Moreover, the network traffic index value in the embodiments of the present invention is obtained by learning from a machine learning model. Therefore, compared with manually configured index thresholds, the embodiments of the present invention can further improve the accuracy of terminal usage status identification.

[0126] Figure 7 This diagram illustrates the architecture of a terminal usage status identification system provided by an embodiment of the present invention. Figure 7 As shown, the terminal usage status identification system 700 includes a terminal usage status identification device 600, at least one gateway 710, and at least one terminal 720.

[0127] Terminal 720 can directly access gateway 710 via a corresponding protocol (such as DHCP), or it can access gateway 710 via an AP device (Wi-Fi repeater). Gateway 710 is specifically a Wi-Fi gateway, which can be set up in homes, offices, etc. Each gateway 710 is equipped with an Agent 711, which can collect relevant data from terminal 720, including network traffic metrics of the terminal at at least one sampling time. The Agent reports the collected data to terminal usage status identification device 600, which processes the data to identify the terminal's sleep period and / or normal usage period. In addition, terminal usage status identification device 600 or other control devices can also issue corresponding control commands to the gateway based on the identified sleep period and / or normal usage period to control network mode switching, etc.

[0128] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the terminal usage status identification method in any of the above method embodiments.

[0129] Figure 8 A schematic diagram of a computing device according to an embodiment of the present invention is shown. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0130] like Figure 8 As shown, the computing device may include: a processor 802, a communications interface 804, a memory 806, and a communications bus 808.

[0131] The processor 802, communication interface 804, and memory 806 communicate with each other via communication bus 808. Communication interface 804 is used to communicate with other network elements such as clients or other servers. Processor 802 executes program 810, specifically performing the relevant steps in the above-described embodiment of the method for identifying the terminal's usage status.

[0132] Specifically, program 810 may include program code that includes computer operation instructions.

[0133] Processor 802 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0134] Memory 806 is used to store program 810. Memory 806 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device. Program 810 can specifically be used to cause processor 802 to execute the methods in the above method embodiments.

[0135] The specific implementation methods of the apparatus, system, storage medium, and computing device in the embodiments of the present invention can be referred to the description in the method embodiments, and will not be repeated here.

[0136] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0137] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0138] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0139] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0140] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0141] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0142] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for identifying the usage status of a terminal, characterized in that, include: Obtain the network traffic metrics of the target terminal at at least one sampling time; Obtain the network traffic metric thresholds output by the network traffic metric threshold model; The network traffic metric value at any sampling time is compared with the network traffic metric threshold to identify normal usage time from the sampling time. Based on the normal usage time, determine the sleep period and / or normal usage period of the target terminal; The step of determining the sleep period and / or normal usage period of the target terminal based on the normal usage time further includes: The normal usage time is clustered to generate at least one cluster; Count the number of items with normal usage time contained in each cluster; Filter out target clusters that contain more than a preset number of normal usage times; Based on the time period corresponding to the target cluster, determine the normal usage period of the target terminal; The method further includes: after obtaining the target terminal's sleep period and / or normal usage period, switching the network mode during the corresponding period.

2. The method according to claim 1, characterized in that, Before obtaining the network traffic metric threshold output by the network traffic metric threshold model, the method further includes: Construct a network traffic metric threshold model; The network traffic index threshold model was trained offline using the historical network traffic index values ​​of the sample terminals to obtain the offline trained network traffic index threshold model. The network traffic index value of the target terminal at at least one sampling time is input into the offline trained network traffic index threshold model; Specifically, obtaining the network traffic indicator threshold output by the network traffic indicator threshold model involves: obtaining the network traffic indicator threshold output by the network traffic indicator threshold model after inputting the network traffic indicator value of the target terminal at at least one sampling time into the offline trained network traffic indicator threshold model.

3. The method according to claim 2, characterized in that, After obtaining the offline-trained network traffic metric threshold model, the method further includes: obtaining the initial network traffic metric threshold output by the offline-trained network traffic metric threshold model; The step of inputting the network traffic index value of the target terminal at at least one sampling time into the offline-trained network traffic index threshold model further includes: inputting the network traffic index value of the target terminal at at least one sampling time and the initial network traffic index threshold into the offline-trained network traffic index threshold model.

4. The method according to claim 3, characterized in that, The offline training of the constructed network traffic indicator threshold model using historical network traffic indicator values ​​from sample terminals further includes: Obtain the historical network traffic index values ​​of the sample terminals corresponding to each region; The network traffic index threshold model was trained offline using the historical network traffic index values ​​of sample terminals corresponding to each region. The step of obtaining the initial network traffic index threshold output by the offline-trained network traffic index threshold model further includes: determining the target region corresponding to the target terminal, and obtaining the initial network traffic index threshold of the target region output by the offline-trained network traffic index threshold model.

5. The method according to any one of claims 1-4, characterized in that, The step of obtaining the network traffic index value of the target terminal at at least one sampling time further includes: Obtain the network traffic index value collected by a preset application in the gateway to which the target terminal belongs.

6. A device for identifying the usage status of a terminal, characterized in that, include: The first acquisition module is used to acquire the network traffic index value of the target terminal at at least one sampling time. The second acquisition module is used to acquire the network traffic indicator threshold output by the network traffic indicator threshold model. The identification module is used to compare the network traffic indicator value at any sampling time with the network traffic indicator threshold in order to identify the normal usage time from the sampling time. The determination module is used to determine the sleep period and / or normal usage period of the target terminal based on the normal usage time; The determining module is further configured to: cluster the normal usage time to generate at least one cluster; count the number of normal usage times contained in each cluster; filter out target clusters containing more than a preset number of normal usage times; and determine the normal usage period of the target terminal based on the time period corresponding to the target cluster. The device is also used to: after obtaining the target terminal's sleep period and / or normal use period, switch the network mode during the corresponding period.

7. A computing device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform an operation corresponding to the terminal usage state identification method as described in any one of claims 1-5.

8. A computer storage medium, characterized in that, The storage medium stores at least one executable instruction that causes the processor to perform the operation corresponding to the terminal usage state identification method as described in any one of claims 1-5.

Images