Method and apparatus for scheduling user equipment to be online or go offline, storage medium, and electronic device

Abstract

The present disclosure relates to the technical field of communications, and relates to a method and apparatus for scheduling user equipment to be online or go offline, a storage medium, and an electronic device. The method comprises: acquiring first device feature information and historical path information of user equipment, and according to the first device feature information, determining a device movement trend of the user equipment; according to the device movement trend and the historical path information, determining predicted path information of the user equipment, and according to the predicted path information and the historical path information, determining whether a current movement behavior of the user equipment is a normal movement behavior; if the current movement behavior is a normal movement behavior, controlling the user equipment to continuously be in an online state, and according to the predicted path information, updating a current online limited region of the user equipment, to obtain a target online limited region; if the current movement behavior is an abnormal movement behavior, performing, on the user equipment, processing to go offline. In the present disclosure, the accuracy of a scheduling result, of the user equipment, for being online or going offline is increased.

Description

User equipment online and offline scheduling method and device, storage medium, and electronic equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number 202310869044.7 filed on July 14, 2023, entitled “User equipment online and offline scheduling method and device, storage medium, electronic device”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of communication technology, and in particular to a method for scheduling online and offline operations of a user equipment, an apparatus for scheduling online and offline operations of a user equipment, a computer-readable storage medium, and an electronic device. Background Art

[0004] In the existing user equipment online and offline scheduling method, when the user equipment exceeds the limited activity area, it is directly offlined without considering the activity pattern of the user equipment itself, resulting in low accuracy of the online and offline scheduling results and a degraded user experience.

[0005] Summary of the Invention

[0006] According to one aspect of the present disclosure, a method for scheduling online and offline operations of a user device is provided, comprising: obtaining first device feature information and historical trajectory information of the user device, and determining a device movement trend of the user device based on the first device feature information; determining predicted trajectory information of the user device based on the device movement trend and the historical trajectory information, and judging whether the current movement behavior of the user device is normal movement behavior based on the predicted trajectory information and the historical trajectory information; if the current movement behavior of the user device is normal movement behavior, controlling the user device to remain online, and updating the current online limited area of ​​the user device based on the predicted trajectory information to obtain a target online limited area; and if the current movement behavior of the user device is abnormal movement behavior, offline processing is performed on the user device.

[0007] According to one aspect of the present disclosure, a device for scheduling online and offline operations of a user device is provided, comprising: a device movement trend determination module, configured to obtain first device feature information and historical trajectory information of the user device, and determine the device movement trend of the user device based on the first device feature information; a current movement behavior determination module, configured to determine predicted trajectory information of the user device based on the device movement trend and historical trajectory information, and determine whether the current movement behavior of the user device is normal movement behavior based on the predicted trajectory information and the historical trajectory information; a current online limited area update module, configured to control the user device to remain online if the current movement behavior of the user device is normal movement behavior, and to update the current online limited area of ​​the user device based on the predicted trajectory information to obtain a target online limited area; and a device offline processing module, configured to offline the user device if the current movement behavior of the user device is abnormal movement behavior.

[0008] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the above-mentioned methods for scheduling online and offline operations of a user equipment is implemented.

[0009] According to one aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods for scheduling online and offline operations of a user equipment by executing the executable instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG1 schematically shows a flow chart of a method for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure.

[0011] FIG2 schematically shows a block diagram of a system for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure.

[0012] FIG3 schematically shows a structural example diagram of a trajectory prediction model according to an exemplary embodiment of the present disclosure.

[0013] FIG4 schematically illustrates a flow chart of a method for determining predicted trajectory information of a user device based on a device movement trend and historical trajectory information according to an exemplary embodiment of the present disclosure.

[0014] FIG5 schematically shows an example diagram of a long short-term memory network according to an example embodiment of the present disclosure.

[0015] FIG6 schematically shows an example diagram of a convolutional neural network model according to an example embodiment of the present disclosure.

[0016] FIG7 schematically shows an example diagram of a bidirectional long short-term memory network incorporating an attention mechanism according to an example embodiment of the present disclosure.

[0017] FIG8 schematically shows a flowchart of another method for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure.

[0018] FIG9 schematically shows a block diagram of a device for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure.

[0019] FIG10 schematically illustrates an electronic device for implementing the above-mentioned method for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0021] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0022] The 5G core network element NWDAF (Network Data Analytics Function) detects and processes abnormal UE (User Equipment) locations. Specifically, relevant requirements require that most UEs be restricted to activities within a certain area. If they exceed the restricted activity area, they will be offlined. The specific processing process of the existing offline operation is to directly offline UEs that exceed the restricted area, without considering the UE's own activity patterns. For example, if a user works in area A and lives in area B, and moves regularly between areas A and B; in this scenario, assuming that area A is an online restricted area, then every time the user leaves area A, the user equipment will be offline, which will bring a bad user experience. In other words, in this offline processing solution, the offline operation of UE is relatively simple, and no graded penalty measures are adopted, such as the offline time increasing with the number of times the UE leaves the restricted area.

[0023] This exemplary embodiment first provides a method for scheduling user device online and offline. This method can be run on a server, server cluster, or cloud server on the network side. Of course, those skilled in the art can also run the method disclosed herein on other platforms as needed, and this exemplary embodiment does not specifically limit this. Specifically, referring to FIG1 , this method for scheduling user device online and offline can include the following steps:

[0024] Step S110. Acquire first device feature information and historical trajectory information of the user device, and determine a device movement trend of the user device based on the first device feature information;

[0025] Step S120. Determine the predicted trajectory information of the user device based on the device movement trend and historical trajectory information, and determine whether the current movement behavior of the user device is normal based on the predicted trajectory information and historical trajectory information;

[0026] Step S130. If the current movement behavior of the user device is normal, control the user device to remain online, and update the current online limited area of ​​the user device according to the predicted trajectory information to obtain a target online limited area;

[0027] Step S140: If the current movement behavior of the user equipment is abnormal, the user equipment is offlined.

[0028] In the above-mentioned method for scheduling user device online and offline, firstly, by obtaining first device feature information and historical trajectory information of the user device and determining the device movement trend of the user device based on the first device feature information; then, based on the device movement trend and historical trajectory information, determining whether the current movement behavior of the user device is normal; and if the current movement behavior of the user device is determined to be normal, controlling the user device to remain online, and updating the current online limited area of ​​the user device based on the predicted trajectory information to obtain a target online limited area; and then, if the current movement behavior of the user device is determined to be abnormal, offline processing is performed on the user device. Since the online or offline status of the user device can be determined based on whether the current movement behavior is reasonable, the problem of low accuracy of online and offline scheduling results in the prior art due to failure to consider the activity patterns of the user device itself is solved, thereby improving the user experience; and, since the current online limited area of ​​the user device can be updated based on the destination location information to obtain the target online limited area, the accuracy of the online limited area of ​​the user device is improved, thereby further improving the accuracy of the online and offline scheduling results.

[0029] Hereinafter, the method for scheduling online and offline operations of a user equipment according to an exemplary embodiment of the present disclosure will be explained and illustrated in detail with reference to the accompanying drawings.

[0030] First, the user equipment involved in the exemplary embodiments of the present disclosure is explained and illustrated.

[0031] The user equipment (UE) involved in the exemplary embodiments of the present disclosure may also be referred to as a terminal device, which may be a device with wireless transceiver capabilities. The user equipment may communicate with the core network via the radio access network (RAN) and exchange voice and / or data with the RAN. The user equipment may be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it may also be deployed on the water (such as a ship); it may also be deployed in the air (such as an airplane, a balloon, and a satellite). The user equipment may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0032] The user equipment may include, for example, a wireless user equipment, a mobile user equipment, a device-to-device (D2D) user equipment, a vehicle-to-everything (V2X) user equipment, a machine-to-machine / machine-type communication (M2M / MTC) user equipment, an Internet of Things (IoT) user equipment, a subscriber unit (SU), a subscriber station (SS), a mobile station (MS), a remote station (RS), an access point (AP), a remote terminal (RT), a customer premises equipment (CPE), a fixed wireless access (FWA), an access terminal (AT), a user terminal (UT), a user agent (UA), or a user device, etc. For example, the user equipment may include a mobile phone (also known as a "cellular" phone), a computer with a mobile user equipment, a portable, pocket-sized, handheld, or computer-built-in mobile device, etc. Examples include personal communication service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, wireless local loop (WLL) stations, and personal digital assistants (PDAs). Also included are limited devices, such as those with low power consumption, limited storage capacity, or limited computing power. Examples include information sensing devices such as barcode scanners, radio frequency identification (RFID), sensors, global positioning systems (GPS), and laser scanners.

[0033] As an example and not a limitation, in the embodiments of the present application, the user device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices or smart wearable devices, etc., which are a general term for the application of wearable technology to intelligently design and develop wearable devices for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and independent of smartphones to achieve complete or partial functions, such as smart watches or smart glasses, etc., as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets, smart helmets, smart jewelry, etc. for vital sign monitoring.

[0034] Secondly, the purpose of the invention of the example embodiment of the present disclosure is explained and illustrated. Specifically, in the existing method for scheduling the online and offline of user equipment, the UE that exceeds the limited area is directly offlined without considering the activity pattern of the UE itself, which brings a bad experience to the user. Therefore, it is necessary to consider using the user behavior characteristics to achieve flexible location limitation to solve the problem of poor user experience; and the existing scheme is relatively simple for the UE offline operation; therefore, how to use graded punishment measures to achieve, on the basis of improving the warning to the terminal user, to a certain extent, avoiding the unreasonable behavior of removing the limited area. Based on this, the method for scheduling the online and offline of user equipment provided by the example embodiment of the present disclosure needs to achieve at least the following purposes: on the one hand, graded punishment measures are taken for UE leaving the limited area. Based on the behavioral characteristics of the terminal user, the offline time gradually increases with the number of times it leaves the limited area, and the UE that fails to return to the limited area is kept offline; on the other hand, the user behavior characteristics are learned, and flexible location limitation is adopted for UE that moves regularly.

[0035] Furthermore, the online and offline scheduling system of the user equipment recorded in the exemplary embodiment of the present disclosure is explained and illustrated. Specifically, as shown in reference to FIG2 , the online and offline scheduling system of the user equipment may include a user equipment 210, an access and mobility management function (AMF, Access and Mobility Management Function) network element 220 and an NWDAF (Network Data Analytics Function, Network Data Analysis Function) network element; wherein, the user equipment can be connected to the access and mobility management function network element in a communication manner through a wired network or a wireless network, and the access and mobility management function network element is connected to the network data analysis function network element. In the actual application process, the user equipment is used to report device feature information to the access and mobility management function network element, and the access and mobility management function network element is used to send the received device feature information to the network data analysis function network element; at the same time, the network data analysis function network element is used to schedule the online and offline status of the user equipment according to the device feature information and historical trajectory information.

[0036] The following will further explain and illustrate the method for scheduling user equipment online and offline shown in FIG1 in conjunction with FIG2. Specifically:

[0037] In step S110, first device feature information and historical trajectory information of the user device are obtained, and a device movement trend of the user device is determined based on the first device feature information;

[0038] In this example embodiment, first, first, the first device characteristic information and historical trajectory information of the user equipment are obtained; specifically, it can be achieved in the following way: the access and mobility management function network element receives the first device characteristic information of the user equipment sent by the user equipment; wherein, the first device characteristic information includes the location information of the user equipment, the moving speed of the user equipment and at least one of the wireless measurement information of the user equipment, the location information includes the cell information where the user equipment is currently located, the coordinate position of the user equipment and at least one of the location measurement of the user equipment; the wireless measurement information includes at least one of the current reference signal reception power, the current reference signal reception quality and the current signal to interference plus noise ratio; the access and mobility management function network element sends the first device characteristic information of the user equipment to the network data analysis function network element, and the network data analysis function network element obtains the historical trajectory information of the user equipment based on the device identification of the user equipment.

[0039] That is, in the actual application process, first, the first device characteristic information uploaded by the user equipment can be received through the access and mobility management function (AMF) network element; wherein, the first device characteristic information recorded here may include the UE's location information, the UE's moving speed, and the UE's wireless measurement information; at the same time, the UE's location information may at least include the UE's current cell information, the UE's coordinate position, the UE's location measurement, etc. The UE's wireless measurement information includes at least RSRP (Reference Signal Receiving Power), RSRQ (Reference Signal Receiving Quality), and SINR (Signal to Interference plus Noise Ratio) and other measurement values; then, when the AMF receives the first device characteristic information, it can send the first device characteristic information to the NWDAF (Network Data Analytics Function) network element, and implement the specific trajectory prediction process in the NWDAF.

[0040] Furthermore, in the NWDAF network element, first, it is necessary to obtain the historical trajectory information of the user device based on the device identifier; wherein the historical trajectory information can be obtained from the user plane function network element; secondly, the device movement trend of the user device is determined based on the first device characteristic information; wherein the specific process of determining the device movement trend can be implemented as follows: the device movement trend of the user device is determined based on the location information and movement speed in the first device characteristic information. That is, the device movement trend of the user device in the current time period can be determined based on the location information and movement speed at multiple consecutive moments; wherein, in the process of determining the device movement trend, the user device can be located on the map based on the location information, and then the device movement trend can be obtained based on the routes included in the map, the multiple different location points where the user device appears on the map, and the movement speed of the device.

[0041] In step S120, the predicted trajectory information of the user device is determined based on the device movement trend and historical trajectory information, and whether the current movement behavior of the user device is normal is determined based on the predicted trajectory information and historical trajectory information.

[0042] Specifically, in the process of determining the predicted trajectory information, it is necessary to implement it based on the corresponding trajectory prediction model. At the same time, referring to Figure 3, the trajectory prediction model may include an input layer 310, a long short-term memory network (LSTM) 320, a convolutional neural network (CNN) model 330, a feature splicing layer 340, a bidirectional long short-term memory network 350 integrated with an attention mechanism, and an output layer 360; wherein, the input layer is connected to the long short-term memory network model and the convolutional neural network model respectively; the long short-term memory network model and the convolutional neural network model are respectively connected to the feature splicing layer, and the feature splicing layer, the bidirectional long short-term memory network integrated with the attention mechanism, and the output layer are connected in sequence. At the same time, the specific uses of each part of the trajectory prediction model will be described one by one later, and no further limitations are given here.

[0043] In an exemplary embodiment, as shown in FIG4 , determining the predicted trajectory information of the user device based on the device movement trend and historical trajectory information may include the following steps:

[0044] Step S410 , segmenting the historical trajectory information to obtain original trajectory data segments, and using a preset long short-term memory network to update the cell state in each original trajectory data segment to obtain a local time feature.

[0045] In this exemplary embodiment, historical trajectory information is first segmented to obtain multiple raw trajectory data segments. Specifically, during the segmentation process, the historical trajectory information can be segmented at fixed time intervals to obtain multiple raw trajectory data segments. Simultaneously, each raw trajectory data segment is sorted according to its order in the historical trajectory information so that each raw trajectory data segment can reflect the spatiotemporal characteristics within the segment. Secondly, a preset long-short-term memory network is used to update the cell state in each raw trajectory data segment to obtain a local temporal feature. The specific process of generating the local temporal feature can be implemented as follows: first, the raw trajectory data segment is processed using the forget gate to obtain an information retention rate, and then the raw trajectory data segment is processed using the input gate to obtain a candidate state. Second, the cell state is updated based on the information retention rate and the candidate state to obtain an updated cell state. Based on the updated cell state, the local temporal feature is calculated using the output gate.

[0046] In an exemplary embodiment, as shown in FIG5 , the long short-term memory network described herein may include a forget gate 501, an input gate 502, and an output gate 503. That is, in actual applications, the control of the memory unit can be implemented based on the forget gate, the input gate, and the output gate. For example, for an original trajectory data segment, in the process of processing the original trajectory data segment through three gate control units to obtain local temporal features, the forget gate is first used to determine how much information to discard. For example, the forget gate reads the output of the previous hidden layer unit and the current input, and then outputs a value between 0 and 1 to represent the information retention rate. Then, the input gate determines how much new information to add to the current state. In actual applications, this step can be completed in two parts: one part is: the activation function sigmoid layer calculates the total amount of information update, and then the tanh layer generates candidate states; the other part is: the updated cell state is obtained based on the candidate state; finally, the output gate obtains the local temporal features based on the updated cell state.

[0047] In step S420 , a preset convolutional neural network model is used to extract features from the original trajectory data segments to obtain local spatial features, and local temporal features and local spatial features of each of the original trajectory data segments are concatenated to obtain local spatiotemporal features.

[0048] In this example embodiment, first, a preset convolutional neural network model is used to extract features from the original trajectory data segments to obtain local spatial features. Specifically, this can be achieved by: performing image processing on the original trajectory data segments to obtain a two-dimensional matrix image, and then performing convolution and pooling processing on the two-dimensional matrix image using a preset convolutional neural network model to obtain the local spatial features. That is, in actual applications, simply extracting global spatial features cannot reflect the differences in the trajectory in the time dimension; therefore, it is also necessary to select local spatial features for each original trajectory data segment with the same time span after segmentation.

[0049] In an exemplary embodiment, the original trajectory data segments are imaged to obtain a two-dimensional matrix image, which can be achieved as follows: first, the midpoint of the line connecting the starting point and the end point of each original trajectory data segment is used as the center point of the two-dimensional matrix image; second, the geographic space to which each original trajectory data segment belongs is evenly divided to obtain a grid space, and the trajectory in the original trajectory data segment is represented in the grid space with predefined pixel values ​​to obtain the two-dimensional matrix image. That is, before performing local spatial feature extraction, the original trajectory data segments need to be imaged first; wherein, during the image processing, the midpoint of the line connecting the starting point and the end point of the original trajectory data segment can be used as the image center point, and then the geographic space to which each original trajectory data segment belongs is evenly divided into a grid space, and then the two-dimensional matrix image is obtained based on the image midpoint and the grid space.

[0050] In an exemplary embodiment, the two-dimensional matrix image is convolved and pooled using a preset convolutional neural network model to obtain the local spatial features, which can be achieved as follows: first, the two-dimensional matrix image is convolved and pooled using a first convolutional layer and a first pooling layer to extract low-level spatial features in the two-dimensional matrix image; second, the low-level spatial features are convolved and pooled using a second convolutional layer and a second pooling layer to extract high-level spatial features of the two-dimensional matrix image; then, the high-level spatial features are feature folded using the feature folding layer to obtain the local spatial features. Specifically, as shown in Figure 6, the convolutional neural network model described herein may include a first convolutional layer 601, a first pooling layer 602, a second convolutional layer 603, a second pooling layer 604, and a feature folding layer 605, and the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, and the feature folding layer are connected in sequence.

[0051] In step S430, a preset bidirectional long short-term memory network with an attention mechanism is used to capture the bidirectional dependencies in the local spatiotemporal features to obtain global spatiotemporal features, and the predicted trajectory information of the user device is determined based on the global spatiotemporal features and the device movement trend.

[0052] Specifically, the bidirectional long short-term memory network constructed with the attention mechanism is used to capture the bidirectional dependency in the local spatiotemporal features to obtain global spatiotemporal features, and the predicted trajectory information of the user device is determined based on the global spatiotemporal features and the first device feature information. This can be achieved in the following way: first, the local spatiotemporal features are input into the forward long short-term memory network hidden layer unit to obtain the first unit output, and the local spatiotemporal features are input into the backward long short-term memory network hidden layer unit to obtain the second unit output; secondly, the first unit output and the second unit output are spliced ​​to obtain the global spatiotemporal features, and the global spatiotemporal feature information is input into the attention layer to obtain the second weight of each of the original trajectory data segments; then, the second weight and the device movement trend are input into the fully connected layer to obtain the predicted trajectory information of the user device. Specifically, as shown in Figure 7, the bidirectional long short-term memory network incorporating the attention mechanism described herein may include a forward long short-term memory network hidden layer unit 701, a backward long short-term memory network hidden layer unit 702, an attention layer 703, and a fully connected layer 704; wherein the forward long short-term memory network hidden layer unit and the backward long short-term memory network hidden layer unit are respectively connected to the attention layer, and the attention layer is connected to the fully connected layer.

[0053] It should be noted that, in actual applications, the inputs to the hidden layer units of the forward long short-term memory network and the backward long short-term memory network are local spatiotemporal features, the inputs to the attention layer are the outputs of the first and second units, and the inputs to the fully connected layer are the feature information of the first device and the output of the attention layer. In other words, in determining the predicted trajectory information of the user device, it is necessary to consider both the device movement trend of the user device and the historical trajectory information to obtain the predicted trajectory information. In this way, the accuracy of the obtained predicted trajectory information is greatly improved.

[0054] After further obtaining the predicted trajectory information of the user device, it is possible to determine whether the current movement behavior of the user device is normal movement behavior based on the predicted trajectory information and the historical trajectory information. The specific judgment process may include: determining whether the predicted trajectory information is included in the historical trajectory information; if the predicted trajectory information is included in the historical trajectory information, and the number of occurrences of the historical trajectory information within a specific time period is greater than a certain threshold, then the current movement behavior can be considered normal movement behavior; if the predicted trajectory information is included in the historical trajectory information, but the number of occurrences of the historical trajectory information within a specific time period is less than the above threshold, then the current movement behavior can be considered abnormal movement behavior; or, if the predicted trajectory information is not included in the historical trajectory information, then the current movement behavior can be considered abnormal movement behavior.

[0055] In step S130, if the current movement behavior of the user equipment is normal movement behavior, the user equipment is controlled to remain in an online state, and the current online limited area of ​​the user equipment is updated according to the predicted trajectory information to obtain a target online limited area.

[0056] Specifically, if it is a normal movement behavior, the user device does not need to be offlined, and the existing online restricted area is updated based on the predicted trajectory information to obtain the target online restricted area. It should be noted here that in actual application, if the user frequently travels between different areas, the target online restricted area can be expanded according to the number of times of travel; that is, there may be a situation where the user's device is offline as soon as it leaves area A when the user first starts traveling between different areas; however, after a period of frequent travel, the user device can also be online in area B; in this way, the transition from the device being offline to the flexible restriction of the online restricted area can be achieved, thereby achieving the purpose of improving the user experience.

[0057] Of course, in a possible example embodiment, in order to save communication resources, the target online limited area of ​​the user device will also be updated at specific time intervals. The specific updating method is: at specific time intervals, the number of times the user device travels to all sub-areas included in the target online limited area within the specific time period is counted; areas with too few visits can be deleted, thereby achieving the purpose of saving resources.

[0058] In step S140, if the current movement behavior of the user equipment is abnormal, the user equipment is offlined.

[0059] In this example embodiment, the offline processing of the user device can be specifically implemented in the following manner: first, the number of times the user device leaves the currently online limited area is calculated, and the device offline time of the user device is determined based on the number of departure behaviors; second, the offline termination time node of the user device is determined based on the device offline time and the departure time node of the user device leaving the currently online limited area; finally, the user device is controlled to be in an offline state within the time period between the departure time node and the offline termination time node. Determining the device offline time of the user device based on the number of departure behaviors can be implemented in the following manner: first, configuring a weight value for each device departure behavior of the user device leaving the currently online limited area based on the number of departure behaviors; second, determining the device offline time of the user device based on the standard offline time of the device departure behavior and the weight value.

[0060] That is, in actual application, if the user device leaves the current online restricted area for the first time, a standard device offline time can be set; if it leaves the current online restricted area multiple times, a weight value can be configured for each departure behavior. The more times the user leaves, the greater the weight value of the later departure behavior. On this basis, the standard device offline time and the weight value corresponding to each departure behavior are weighted and summed to obtain the device offline time, thereby controlling the user device to be offline during the device offline time period. It should be noted here that the reason for setting the weight value is to adopt graded penalty measures; that is, the penalty level is determined according to the number of departures; of course, when the number of departures meets certain conditions, the current online restricted area can be expanded. In this way, the user experience is further improved.

[0061] It should be further explained here that in the process of user equipment offline processing, it can be achieved in the following way: First, when the NWDAF network element determines that the current mobility behavior of the user equipment is abnormal mobility behavior, it directly calculates the device offline time of the user equipment and sends the device offline time to the AMF. After receiving the device offline time, the AMF can notify the user equipment to go offline.

[0062] In an exemplary embodiment, the method for scheduling user device online and offline further includes: after detecting that the offline termination time node has expired, obtaining second device characteristic information of the user device at the time corresponding to the offline termination time node; determining whether the user device has returned to the currently online limited area based on the second device characteristic information; if the user device has returned to the currently online limited area, controlling the user device to be online; if the user device has not returned to the currently online limited area, controlling the user device to be offline until the user device returns to the currently online limited area. That is, after monitoring the expiration of the device offline time, it can again determine whether the user device has returned to the currently online limited area based on the location information in the second device characteristic information uploaded by the user device; if so, notifying the user device that it can go online; if not, continuing to offline the device until the user device returns to the currently online limited area; and if the user device returns to the currently online limited area during the device offline time period, it cannot go online. Among them, the user equipment can be implemented in the following way during the online process: AMF detects whether the user equipment returns to the current online limited area at the interval of the device offline time; if it returns, the user equipment is notified to go online.

[0063] The following will further explain and illustrate the method for scheduling user equipment online and offline according to the exemplary embodiment of the present disclosure in conjunction with Figure 8. Specifically, with reference to Figure 8, the method for scheduling user equipment online and offline may include the following steps:

[0064] Step S801: Acquire first device feature information and historical trajectory information of a user device, and determine a device movement trend of the user device based on the first device feature information;

[0065] Step S802: Determine predicted trajectory information of the user device based on the device movement trend and historical trajectory information;

[0066] Step S803: Determine whether the current movement behavior of the user device is normal based on the predicted trajectory information and the historical trajectory information; if so, jump to step S804; if not, jump to step S805;

[0067] Step S804: controlling the user device to remain online, and updating the current online limited area of ​​the user device according to the predicted trajectory information to obtain a target online limited area;

[0068] Step S805: Count the number of times the user device leaves the currently online restricted area, and determine the device offline time of the user device according to the number of times the user device leaves the area.

[0069] Step S806: Determine the offline termination time of the user device according to the device offline time and the departure time of the user device leaving the currently online restricted area, and control the user device to be offline during the time period between the departure time and the offline termination time.

[0070] That is, in actual application, when the UE location changes, the terminal user's historical behavior characteristics and UE movement trends are combined to judge whether the behavior of the UE that is about to leave (or has left) the restricted area is reasonable; if it is unreasonable, a graded penalty measure is taken against the UE, and the offline time gradually increases with the number of times it leaves the restricted area; at the same time, it is judged whether the UE returns to the restricted area after the offline time ends; if it returns, the UE is allowed to go online, otherwise the UE is not allowed to go online until it returns to the restricted area; further, if it is reasonable, the UE is included in the flexible location limitation, that is, the restricted area of ​​the UE is expanded.

[0071] At this point, the method for scheduling the online and offline of user equipment recorded in the exemplary embodiment of the present disclosure has been fully implemented. Based on the above-mentioned content, it can be known that the method for scheduling the online and offline of the device recorded in the exemplary embodiment of the present disclosure, on the one hand, the exemplary embodiment of the present disclosure proposes a hierarchical penalty measure and a flexible location limit, and can realize the dynamic conversion of the hierarchical penalty measure to the flexible location limit (that is, when the number of exchanges reaches a certain threshold, the current online limited area is expanded), thereby solving the problem that the prior art does not perform a hierarchical penalty operation on the offline time of the UE and does not mention the problem of flexible location limit; on the other hand, when the UE location changes, the terminal user's historical behavior characteristics and UE movement trend can be combined to judge whether the behavior of the UE that is about to leave (or has left) the limited area is reasonable. If it is reasonable, it will be included in the flexible location limit and the limited area will be expanded. Otherwise, the UE will be subject to hierarchical penalty measures; at the same time, for the UE that is about to leave (or has left) the limited area and whose behavior is unreasonable, hierarchical penalty measures will be taken, and the offline time will gradually increase with the number of times it leaves the limited area; further, it can also be judged whether the UE that is subject to hierarchical penalty will return to the limited area after the offline time ends. If it returns, the UE is allowed to go online. Otherwise, the UE is not allowed to go online until it returns to the restricted area.

[0072] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0073] The exemplary embodiments of the present disclosure also provide a user device online and offline scheduling device. Specifically, as shown in FIG9 , the user device online and offline scheduling device may include a device movement trend determination module 910, a current movement behavior determination module 920, a current online limited area update module 930, and a device offline processing module 940.

[0074] The device movement trend determination module 910 may be configured to obtain first device feature information and historical trajectory information of a user device, and determine a device movement trend of the user device based on the first device feature information;

[0075] The current movement behavior determination module 920 may be configured to determine the predicted trajectory information of the user device based on the device movement trend and historical trajectory information, and determine whether the current movement behavior of the user device is normal based on the predicted trajectory information and historical trajectory information;

[0076] The current online limited area updating module 930 may be configured to control the user equipment to remain online if the current movement behavior of the user equipment is normal, and update the current online limited area of ​​the user equipment according to the predicted trajectory information to obtain a target online limited area;

[0077] The device offline processing module 940 may be configured to offline the user equipment if the current movement behavior of the user equipment is abnormal.

[0078] In an exemplary embodiment of the present disclosure, obtaining first device characteristic information and historical trajectory information of a user device includes: an access and mobility management function network element receives the first device characteristic information of the user device sent by the user device; wherein, the first device characteristic information includes the location information of the user device, the moving speed of the user device and at least one of the wireless measurement information of the user device, the location information includes the cell information where the user device is currently located, the coordinate position of the user device and at least one of the location measurement of the user device; the wireless measurement information includes at least one of the current reference signal received power, the current reference signal received quality and the current signal to interference plus noise ratio; the access and mobility management function network element sends the first device characteristic information of the user device to the network data analysis function network element, and the network data analysis function network element obtains the historical trajectory information of the user device based on the device identification of the user device.

[0079] In an exemplary embodiment of the present disclosure, determining the device movement trend of the user device according to the first device characteristic information includes: determining the device movement trend of the user device according to the location information and movement speed in the first device characteristic information.

[0080] In an exemplary embodiment of the present disclosure, offline processing is performed on the user device, including: calculating the number of times the user device leaves the currently online limited area, and determining the device offline time of the user device based on the number of departure behaviors; determining the offline termination time node of the user device based on the device offline time and the departure time node of the user device leaving the currently online limited area; and controlling the user device to be in an offline state within the time period between the departure time node and the offline termination time node.

[0081] In an exemplary embodiment of the present disclosure, the online and offline scheduling device of the user equipment further includes:

[0082] The second device characteristic information acquisition module may be configured to acquire the second device characteristic information of the user device at a time corresponding to the offline termination time node after detecting that the offline termination time node has ended;

[0083] The user equipment area determination module may be configured to determine whether the user equipment has returned to the currently online restricted area based on the second device feature information;

[0084] A first device control module may be configured to control the user device to be in an online state if the user device has returned to the current online limited area;

[0085] The second device control module may be configured to control the user equipment to be in an offline state if the user equipment does not return to the currently online limited area until the user equipment returns to the currently online limited area.

[0086] In an exemplary embodiment of the present disclosure, determining the device offline time of the user device based on the number of leaving behaviors includes: configuring a weight value for the device leaving behavior of the user device each time it leaves the currently online limited area based on the number of leaving behaviors; and determining the device offline time of the user device based on the standard offline time of the device leaving behavior and the weight value.

[0087] In an exemplary embodiment of the present disclosure, the predicted trajectory information of the user device is determined based on the device movement trend and historical trajectory information, including: segmenting the historical trajectory information to obtain original trajectory data segments, and using a preset long short-term memory network to update the cell state in each of the original trajectory data segments to obtain local temporal features; using a preset convolutional neural network model to extract features from the original trajectory data segments to obtain local spatial features, and splicing the local temporal features and local spatial features of each of the original trajectory data segments to obtain local spatiotemporal features; using a preset bidirectional long short-term memory network incorporating an attention mechanism to capture bidirectional dependencies in the local spatiotemporal features to obtain global spatiotemporal features, and determining the predicted trajectory information of the user device based on the global spatiotemporal features and the device movement trend.

[0088] In an exemplary embodiment of the present disclosure, the long short-term memory network includes a forget gate, an input gate, and an output gate; wherein, the cell state in each of the original trajectory data segments is updated using a preset long short-term memory network to obtain a local time feature, including: processing the original trajectory data segment using the forget gate to obtain an information retention rate, and processing the original trajectory data segment using the input gate to obtain a candidate state; updating the cell state according to the information retention rate and the candidate state to calculate an updated cell state, and based on the updated cell state, calculating the local time feature using the output gate.

[0089] In an exemplary embodiment of the present disclosure, a preset convolutional neural network model is used to perform feature extraction on the original trajectory data segment to obtain local spatial features, including: imaging the original trajectory data segment to obtain a two-dimensional matrix image, and convolution and pooling the two-dimensional matrix image using a preset convolutional neural network model to obtain the local spatial features.

[0090] In an exemplary embodiment of the present disclosure, the original trajectory data segments are image-processed to obtain a two-dimensional matrix image, including: using the midpoint of the line connecting the starting point and the end point in each of the original trajectory data segments as the center point of the two-dimensional matrix image; evenly dividing the geographic space to which each of the original trajectory data segments belongs to obtain a grid space, and representing the trajectory in the original trajectory data segment with predefined pixel values ​​in the grid space to obtain the two-dimensional matrix image.

[0091] In an exemplary embodiment of the present disclosure, the preset convolutional neural network model includes a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer and a feature folding layer; wherein, the preset convolutional neural network model is used to perform convolution and pooling processing on the two-dimensional matrix image to obtain the local spatial features, including: using the first convolutional layer and the first pooling layer to perform convolution and pooling processing on the two-dimensional matrix image to extract low-level spatial features in the two-dimensional matrix image; using the second convolutional layer and the second pooling layer to perform convolution and pooling processing on the low-level spatial features to extract high-level spatial features of the two-dimensional matrix image; using the feature folding layer to perform feature folding on the high-level spatial features to obtain the local spatial features.

[0092] In an exemplary embodiment of the present disclosure, the bidirectional long short-term memory network incorporating an attention mechanism includes a forward long short-term memory network hidden layer unit, a backward long short-term memory network hidden layer unit, an attention layer, and a fully connected layer; wherein, the constructed bidirectional long short-term memory network incorporating an attention mechanism is used to capture the bidirectional dependency in the local spatiotemporal features to obtain global spatiotemporal features, and based on the global spatiotemporal features and the first device feature information, the predicted trajectory information of the user device is determined, including: inputting the local spatiotemporal features into the forward long short-term memory network hidden layer unit to obtain a first unit output, and inputting the local spatiotemporal features into the backward long short-term memory network hidden layer unit to obtain a second unit output; splicing the first unit output and the second unit output to obtain a global spatiotemporal feature, and inputting the global spatiotemporal feature information into the attention layer to obtain a second weight of each of the original trajectory data segments; and inputting the second weight and the device movement trend into the fully connected layer to obtain the predicted trajectory information of the user device.

[0093] The specific details of each module in the above-mentioned online and offline scheduling device for user equipment have been described in detail in the corresponding online and offline scheduling method for user equipment, and will not be repeated here.

[0094] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0095] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0096] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0097] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0098] The electronic device 1000 according to this embodiment of the present disclosure is described below with reference to Figure 10. The electronic device 1000 shown in Figure 10 is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0099] As shown in FIG10 , electronic device 1000 is implemented as a general-purpose computing device. Components of electronic device 1000 may include, but are not limited to, the aforementioned at least one processing unit 1010, the aforementioned at least one storage unit 1020, a bus 1030 connecting various system components (including storage unit 1020 and processing unit 1010), and a display unit 1040.

[0100] The storage unit stores program code, which can be executed by the processing unit 1010, so that the processing unit 1010 performs the steps described in the "Exemplary Method" section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 1010 may perform step S110 as shown in FIG1: obtaining first device feature information and historical trajectory information of a user device, and determining a device movement trend of the user device based on the first device feature information; step S120: determining predicted trajectory information of the user device based on the device movement trend and historical trajectory information, and determining whether the current movement behavior of the user device is normal based on the predicted trajectory information and historical trajectory information; step S130: if the current movement behavior of the user device is normal, controlling the user device to remain online, and updating the current online limited area of ​​the user device based on the predicted trajectory information to obtain a target online limited area; step S140: if the current movement behavior of the user device is abnormal, offline processing of the user device.

[0101] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 10201 and / or a cache memory unit 10202 , and may further include a read-only memory unit (ROM) 10203 .

[0102] The storage unit 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0103] Bus 1030 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0104] The electronic device 1000 can also communicate with one or more external devices 1100 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1000, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 1050. Furthermore, the electronic device 1000 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 1060. As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 via a bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 1000, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0105] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0106] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present disclosure.

[0107] According to an embodiment of the present disclosure, a program product for implementing the above-mentioned method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0108] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0109] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0111] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0112] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0113] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modifications, uses, or variations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not invented herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A method for scheduling online and offline operations of a user equipment, comprising: Acquire first device characteristic information and historical track information of a user device, and determine a device movement trend of the user device according to the first device characteristic information; Determine the predicted trajectory information of the user device according to the device movement trend and the historical trajectory information, and judge whether the current movement behavior of the user device is normal movement behavior according to the predicted trajectory information and the historical trajectory information; If the current movement behavior of the user equipment is a normal movement behavior, the user equipment is controlled to remain in an online state, and the current online limited area of ​​the user equipment is updated according to the predicted trajectory information to obtain a target online limited area; If the current movement behavior of the user equipment is an abnormal movement behavior, the user equipment is offlined.

2. The method for scheduling online and offline operations of a user equipment according to claim 1, wherein: Obtaining first device feature information and historical track information of a user device, including: The access and mobility management function network element receives first device characteristic information of a user equipment sent by the user equipment; wherein the first device characteristic information includes at least one of location information of the user equipment, a moving speed of the user equipment, and wireless measurement information of the user equipment, the location information includes at least one of cell information where the user equipment is currently located, a coordinate position of the user equipment, and a location metric of the user equipment; the wireless measurement information includes at least one of a current reference signal received power, a current reference signal received quality, and a current signal to interference plus noise ratio; The access and mobility management function network element sends the first device characteristic information of the user equipment to the network data analysis function network element, and the network data analysis function network element obtains the historical track information of the user equipment according to the device identifier of the user equipment.

3. The method for scheduling online and offline operations of a user equipment according to claim 1, wherein: Determining a device movement trend of the user device according to the first device characteristic information includes: A device movement trend of the user device is determined according to the location information and the movement speed in the first device characteristic information.

4. The method for scheduling online and offline operations of a user equipment according to claim 1, wherein: Performing offline processing on the user equipment includes: Calculating the number of times the user device leaves the currently online limited area, and determining a device offline time of the user device according to the number of times the user device leaves the area; Determining an offline termination time node of the user equipment according to the offline time of the device and a departure time node of the user equipment leaving the currently online limited area; The user equipment is controlled to be in an offline state within a time period between the leaving time node and the offline termination time node.

5. The method for scheduling online and offline operations of a user equipment according to claim 4, wherein: The method for scheduling online and offline operations of the user equipment further includes: After detecting that the offline termination time node has ended, obtaining second device characteristic information of the user device at a time corresponding to the offline termination time node; Determining whether the user device has returned to the current online restricted area according to the second device characteristic information; If the user equipment has returned to the current online limited area, controlling the user equipment to be in an online state; If the user equipment does not return to the currently online limited area, the user equipment is controlled to be in an offline state until the user equipment returns to the currently online limited area.

6. The method for scheduling online and offline operations of a user equipment according to claim 4, wherein: Determining the device offline time of the user device according to the number of leaving behaviors includes: According to the number of leaving behaviors, a weight value is configured for each time when the user device leaves the currently online limited area; The device offline time of the user device is determined according to the standard offline time of the device leaving behavior and the weight value.

7. The method for scheduling online and offline operations of a user equipment according to claim 1, wherein: Determining predicted trajectory information of the user device according to the device movement trend and historical trajectory information includes: Segmenting the historical trajectory information to obtain original trajectory data segments, and using a preset long short-term time memory network to update the cell state in each of the original trajectory data segments to obtain local time features; Using a preset convolutional neural network model to extract features from the original trajectory data segments to obtain local spatial features, and concatenating local time features and local spatial features of each of the original trajectory data segments to obtain local spatiotemporal features; A preset bidirectional long short-term memory network with an attention mechanism is used to capture the bidirectional dependencies in the local spatiotemporal features to obtain the global spatiotemporal features, and the predicted trajectory information of the user device is determined based on the global spatiotemporal features and the device movement trend.

8. The method for scheduling online and offline operations of a user equipment according to claim 7, wherein: The long short-term memory network includes a forget gate, an input gate and an output gate; The cell states in each of the original trajectory data segments are updated using a preset long short-term memory network to obtain local time features, including: Using the forget gate to process the original trajectory data segment to obtain an information retention rate, and using the input gate to process the original trajectory data segment to obtain a candidate state; The cell state is updated according to the information retention rate and the candidate state, an updated cell state is calculated, and based on the updated cell state, the local time feature is calculated using the output gate.

9. The method for scheduling online and offline operations of a user equipment according to claim 7, wherein: The original trajectory data segment is subjected to feature extraction using a preset convolutional neural network model to obtain local spatial features, including: The original trajectory data segment is image-processed to obtain a two-dimensional matrix image, and the two-dimensional matrix image is convolved and pooled using a preset convolutional neural network model to obtain the local spatial features.

10. The method for scheduling online and offline operations of a user equipment according to claim 9, wherein: The original trajectory data segment is image-processed to obtain a two-dimensional matrix image, including: Taking the midpoint of the line between the starting point and the end point in each of the original trajectory data segments as the center point of the two-dimensional matrix image; The geographic space to which each of the original trajectory data segments belongs is evenly divided to obtain a grid space, and the trajectories in the original trajectory data segments are represented in the grid space with predefined pixel values ​​to obtain the two-dimensional matrix image.

11. The method for scheduling online and offline operations of a user equipment according to claim 9, wherein: The preset convolutional neural network model includes a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer and a feature folding layer; The two-dimensional matrix image is convolved and pooled using a preset convolutional neural network model to obtain the local spatial features, including: Using a first convolutional layer and a first pooling layer to perform convolution and pooling processing on the two-dimensional matrix image to extract low-level spatial features in the two-dimensional matrix image; Using a second convolutional layer and a second pooling layer to perform convolution and pooling processing on the low-level spatial features to extract high-level spatial features of the two-dimensional matrix image; The feature folding layer is used to perform feature folding on the high-level spatial features to obtain the local spatial features.

12. The method for scheduling online and offline operations of a user equipment according to claim 7, wherein: The bidirectional long short-term memory network incorporating the attention mechanism comprises a forward long short-term memory network hidden layer unit, a backward long short-term memory network hidden layer unit, an attention layer, and a fully connected layer; The bidirectional long short-term memory network constructed with the attention mechanism is used to capture the bidirectional dependency relationship in the local spatiotemporal features to obtain the global spatiotemporal features, and the predicted trajectory information of the user device is determined according to the global spatiotemporal features and the first device feature information, including: Inputting the local spatiotemporal features into a hidden layer unit of a forward long short-term memory network to obtain a first unit output, and inputting the local spatiotemporal features into a hidden layer unit of a backward long short-term memory network to obtain a second unit output; splicing the first unit output and the second unit output to obtain a global spatiotemporal feature, and inputting the global spatiotemporal feature information into an attention layer to obtain a second weight of each of the original trajectory data segments; The second weight and the device movement trend are input into a fully connected layer to obtain predicted trajectory information of the user device.

13. A user equipment online and offline scheduling device, comprising: a device movement trend determination module, configured to obtain first device feature information and historical track information of a user device, and determine a device movement trend of the user device according to the first device feature information; The current movement behavior determination module may be used to determine the predicted trajectory information of the user device according to the movement trend of the device and the historical trajectory information, and to judge whether the current movement behavior of the user device belongs to normal movement behavior according to the predicted trajectory information and the historical trajectory information; a current online limited area updating module, configured to control the user equipment to remain online if the current movement behavior of the user equipment belongs to normal movement behavior, and update the current movement behavior of the user equipment according to the predicted trajectory information; The online limited area is updated to obtain the target online limited area; The device offline processing module is used to perform offline processing on the user equipment if the current movement behavior of the user equipment is abnormal movement behavior.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for scheduling online and offline operations of a user equipment according to any one of claims 1 to 12.

15. An electronic device, comprising: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for scheduling online and offline operations of a user equipment according to any one of claims 1 to 12 by executing the executable instructions.

Images