CN110505688B - Paging method, apparatus, system, network device and storage medium - Google Patents

Abstract

The invention discloses a paging method, a paging device, a paging system, network equipment and a storage medium. The method comprises the following steps: determining a paging range using paging optimization information of a User Entity (UE); the paging optimization information is obtained by performing machine learning on the historical paging area information of the UE according to network slicing granularity by network data analysis (NWDA); the paging optimization information characterizes movement of the UE within a particular time period; and paging the UE according to the determined paging range.

Description

Paging method, apparatus, system, network device and storage medium

technical field

The present invention relates to the field of wireless communication, and in particular, to a paging method, apparatus, system, network device and storage medium.

Background technique

Currently, in a Long Term Evolution (LTE, Long Term Evolution) network, the network can page a user entity (UE, User Entity) in an idle state and a connected state. When the network paging the UE, the current location of the UE is tracked through a mobility management entity (MME, Mobility Management Entity).

However, in the above-mentioned paging process, the periodic tracking area update (TAU) process and the process of expanding the paging range of the UE that cannot be paged through the tracking area list will be very wasteful of base station resources.

SUMMARY OF THE INVENTION

In order to solve the existing technical problems, the embodiments of the present invention provide a paging method, apparatus, system, network device and storage medium.

The technical solution of the embodiment of the present invention is realized as follows:

An embodiment of the present invention provides a paging method, which is applied to an access and mobility management function (AMF) and includes:

Use the paging optimization information of the UE to determine the paging range; the paging optimization information is obtained by performing machine learning on the historical paging area information of the UE according to the granularity of network slices by network data analysis (NWDA, NetWork Data Analytics). ; the paging optimization information characterizes the movement of the UE within a specific time period;

The UE is paged according to the determined paging range.

In the above scheme, the method also includes:

Obtain the paging optimization information from one of the following network elements:

NWDA;

User Data Management (UDM, User Data Management);

User Data Repository (UDR);

Policy Control Function (PCF, Policy Control Function).

In the above solution, obtaining the paging optimization information from the UDM or UDR includes:

Receive the paging optimization information sent by the UDM or the UDR; the received paging optimization information is sent after the UDM or the UDR determines that the UE has the paging optimization information by using the subscription data of the UE.

In the above solution, the obtaining the paging optimization information from the PCF includes:

sending a policy acquisition request to the PCF;

Receive the paging optimization information sent by the PCF; the received paging optimization information is that the PCF uses the subscription data of the UE to determine that the UE has paging optimization information, and obtains the paging optimization information from one of the following network elements Sent after:

UDM;

UDR;

NWDA.

In the above solution, the paging optimization information at least includes: UE id periodic registration timer allocation and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

The determining the paging range by using the paging optimization information of the UE includes:

Determine the access network by using one of the cell list and the tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are based on the UE The id is periodically updated by the registration timer allocation.

In the above scheme, the method also includes:

When paging fails according to the determined paging range, the UE is paged using the tracking area list.

In the above scheme, the method also includes:

Record this paging event as an abnormal event, and store the corresponding abnormal event for the NWDA to update the paging optimization information of the UE.

The embodiment of the present invention also provides a paging method, which is applied to NWDA, including:

Obtain a data sample of the UE; the data sample is the historical paging area information of the UE;

According to the granularity of network slices, using the data samples and combining machine learning algorithms, determine the paging optimization information of the UE in a specific time period; the determined paging optimization information is used for the AMF to determine the paging range and according to the paging The UE is paged within the range; the determined optimization information characterizes the movement of the UE within a specific time period.

In the above scheme, the method also includes:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

In the above scheme, the method also includes:

Push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage at regular intervals:

UDM;

UDR;

AMF.

An embodiment of the present invention further provides a paging device, including:

a first determining unit, configured to determine the paging range by using the paging optimization information of the UE; the paging optimization information is obtained by NWDA performing machine learning on the historical paging area information of the UE according to the granularity of network slices; The paging optimization information represents the movement of the UE within a specific time period;

a paging unit, configured to page the UE according to the determined paging range.

In the above solution, the paging unit is also used for:

When paging fails according to the determined paging range, the UE is paged using the tracking area list.

In the above scheme, the device also includes:

A storage unit, configured to record this paging event as an abnormal event, and store the corresponding abnormal event, so that the NWDA can update the paging optimization information of the UE.

The embodiment of the present invention also provides a paging device, including:

an acquisition unit, configured to acquire a data sample of the UE; the data sample is the historical paging area information of the UE;

The second determining unit is configured to determine the paging optimization information of the UE within a specific time period by using the data samples according to the granularity of the network slice and combining with the machine learning algorithm; the determined paging optimization information is used for the AMF to determine the paging optimization information. and paging the UE according to the paging range; the determined optimization information represents the movement of the UE within a specific time period.

In the above scheme, the second determining unit is also used for:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

In the above scheme, the device also includes:

A push unit, configured to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

An embodiment of the present invention further provides a network device, including:

a first communication interface;

a first processor, configured to determine the paging range by using the paging optimization information of the UE; the paging optimization information is obtained by NWDA performing machine learning on the historical paging area information of the UE according to the granularity of network slices; The paging optimization information represents the movement of the UE within a specific time period; and the UE is paging through the first communication interface according to the determined paging range.

In the above solution, the first processor is also used for:

When the paging fails according to the determined paging range, the UE is paged through the first communication interface using the tracking area list.

In the above scheme,

The first processor is further configured to record this paging event as an abnormal event, so that the NWDA can update the paging optimization information of the UE.

The embodiment of the present invention also provides a network device, including:

a second communication interface;

The second processor is configured to obtain data samples of the UE through the second communication interface; the data samples are the historical paging area information of the UE; according to the granularity of network slices, the data samples are used and combined with machine learning algorithm to determine the paging optimization information of the UE within a specific time period; the determined paging optimization information is used for the AMF to determine the paging range and paging the UE according to the paging range; the determined optimization information represents the Movement of the UE during a specific time period.

In the above solution, the second processor is also used for:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

In the above solution, the second communication interface is also used to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

An embodiment of the present invention further provides a network device, comprising: a first processor and a first memory for storing a computer program that can be executed on the processor,

Wherein, the first processor is configured to execute the steps of any method on the AMF side when running the computer program.

An embodiment of the present invention further provides a network device, comprising: a second processor and a second memory for storing a computer program that can be executed on the processor,

Wherein, the second processor is configured to execute the steps of any method on the NWDA side when running the computer program.

An embodiment of the present invention further provides a paging system, including:

NWDA is used to obtain data samples of the UE; the data samples are the historical paging area information of the UE; according to the granularity of network slices, the data samples are used and combined with machine learning algorithms to determine that the UE is in a specific time period Intra-paging optimization information; the determined optimization information represents the movement of the UE within a specific time period;

The AMF is configured to determine a paging range by using the paging optimization information of the UE determined by the NWDA; and paging the UE according to the determined paging range.

In the above scheme, the system further includes: UDM, UDR, PCF;

The AMF is further used to obtain the paging optimization information from one of the following network elements:

NWDA;

UDM;

UDR;

PCF.

In the above solution, the UDM or the UDM is further configured to notify the NWDA and/or the AMF when it is determined by using the subscription data of the UE that the UE has paging optimization information.

In the above scheme, the AMF is used to send a policy acquisition request to the PCF;

The PCF is configured to obtain the paging optimization information of the UE from one of the following network elements when it is determined that the UE has paging optimization information by using the subscription data of the UE after receiving the policy acquisition request: UDM; UDR ; NWDA; and sent to the AMF;

The AMF is configured to receive the paging optimization information sent by the PCF.

In the above solution, the AMF is further configured to use the tracking area list to page the UE when the paging fails according to the determined paging range.

In the above solution, the AMF is also used to: record this paging event as an abnormal event, so that the NWDA can update the paging optimization information of the UE;

The NWDA is also used to update the data samples of the UE by using the recorded abnormal events when the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold; and according to the network slice granularity, use the updated data samples, and combined with a machine learning algorithm, to re-determine the paging optimization information of the UE within a specific time period.

In the above solution, the NWDA is also used to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

Embodiments of the present invention further provide a storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of any method on the AMF side, or implements the steps of any method on the NWDA side.

In the paging method, device, system, network equipment, and storage medium provided by the embodiments of the present invention, NWDA obtains data samples of the UE; the data samples are the historical paging area information of the UE and according to the granularity of network slices, using the data samples of the UE data samples, and combined with machine learning algorithms to determine the paging optimization information of the UE within a specific time period; AMF uses the paging optimization information of the UE determined by the NWDA to determine the paging range; according to the determined paging range The UE performs paging, determines the paging range based on the paging optimization information predicted by NWDA, that is, predicts the paging area, and then uses the predicted paging area to page the UE. Reduce the waste of base station resources.

Description of drawings

1 is a schematic diagram of a 5G network architecture according to an embodiment of the present invention;

2 is a schematic flowchart of a paging method on an AMF side according to an embodiment of the present invention;

3 is a schematic flowchart of a paging method on an NWDA side according to an embodiment of the present invention;

4 is a schematic flowchart of a paging method according to an embodiment of the present invention;

5 is a schematic flowchart of a paging method according to an application embodiment of the present invention;

FIG. 6 is a schematic flowchart of a paging method according to an application embodiment 2 of the present invention;

FIG. 7 is a schematic flowchart of a paging method according to Embodiment 3 of the present invention;

8 is a schematic structural diagram of a paging apparatus according to an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of another paging apparatus according to an embodiment of the present invention;

10 is a schematic structural diagram of a network device according to an embodiment of the present invention;

11 is a schematic structural diagram of another network device according to an embodiment of the present invention;

FIG. 12 is a schematic structural diagram of a paging system according to an embodiment of the present invention.

Detailed ways

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

Currently, in an LTE network, the network can page the UE in the idle state and the connected state to obtain the location of the UE; specifically, the network side tracks the current location of the UE through the MME.

When the UE registers with the network, the MME will allocate a set of tracking area lists (Tracking Area List) to the UE, and the MME can use the allocated Tracking Area List to page the UE.

In the process of paging, there will be a waste of base station resources, which is embodied in:

In the first case, when the UE is in the Evolved Packet System (ESP) mobility management-registered (EMM-REGISTERED) state, after a periodic TAU time expires, the UE will perform TAU, and the periodic TAU will be very Waste base station resources.

In the second case, when the UE is in the ESP connectivity management-idle (ECM-IDLE) state, in this case, the MME knows the location of the UE through the tracking area list, then when paging (ie paging) , the base stations of all tracking areas registered by the UE under ECM-IDLE should be considered by the MME. At this time, the UE may be registered in multiple tracking areas, and all the tracking areas registered by the UE on the tracking area list are used by the same MME. service; and, once the MME cannot page the UE through the tracking area list, it will continue to page the UE in an expanded range. The process of paging the UE by using the tracking area list will waste the resources of the base station.

On the other hand, in a 5G network, there will be different types of UEs, such as smartphones, IoT devices, V2X devices, etc., which have different mobility characteristics. Moreover, UEs of the same type may have different movement behaviors, for example, a smart terminal used by office workers and a smart terminal used by freelancers have different movement trajectories. Clearly, 5G networks should not serve them with a unified mobility management scheme.

At the same time, UEs serving different communication scenarios may also have different services with different communication modes/models. For example, smart terminal users may have fewer calls/communications at noon; another example is the frequent use of water meter equipment or frequent small data transmission. ; Another example, V2X devices require reliable or low-latency communication. To ensure user experience and improve network resource utilization efficiency, 5G networks should be able to customize mobility management for different UEs in different communication modes/modes.

Third, in the 5G network, it is necessary to meet massive connections and higher rate requirements of users. Therefore, the 5G network adopts a new network architecture. Under this new network architecture, as shown in Figure 1, NWDA is a new A network element with the following characteristics:

(1) NWDA is defined as an operator-managed network analysis logic function module.

(2) The function of NWDA is to provide specific network data analysis according to the granularity of slices (which can be understood as according to services), and can provide the PCF through the N23 interface.

(3) NWDA can analyze the specific network information status of subscribed users to PCF according to slice granularity, and PCF can also directly collect all required user information from NWDA; then PCF makes policy decisions on the overall network according to these data.

Among them, the interface between NWDA and other network elements is collectively called Nnwdaf, which is a service interface. Through this interface, other network elements can obtain the following information:

Network slice instance identifier;

Load information of network slice instances.

Here, it should be noted that since the interface between NWDA and PCF has been defined as N23, the interface between NWDA and PCF uses a specific interface name, that is, the interface between NWDA and PCF is N23 interface .

Through the above analysis, it can be obtained that the function of NWDA can be used to track and manage the mobility mode of the UE.

Based on this, in various embodiments of the present invention: NWDA predicts the paging optimization information of the UE within a specific time period according to the collected paging area information of the UE and based on a machine learning algorithm; the network utilizes the predicted specific time The paging optimization information in the segment is determined, the paging range is determined, and the UE is paged.

The solution provided by the embodiment of the present invention determines the paging range based on the paging optimization information predicted by NWDA, that is, predicts the paging area, and then uses the predicted paging area to page the UE. Since the paging range is determined, it is possible to Greatly reduce the waste of base station resources.

An embodiment of the present invention provides a paging method, which is applied to AMF. As shown in FIG. 2 , the method includes:

Step 201: Determine the paging range by using the paging optimization information of the UE;

Here, the paging optimization information is obtained after the NWDA performs machine learning on the historical paging area information of the UE according to the granularity of network slices; the paging optimization information represents the movement of the UE in a specific time period.

That is, the paging optimization information is the paging area of the UE within a specific time period predicted by NWDA.

The functions of the AMF are mainly: responsible for user network access control, registration management, connection management, mobility management, and the like.

Wherein, the specific time period can be set as required.

In practical application, AMF needs to obtain paging optimization information.

Based on this, in an embodiment, before performing step 101, the method further includes:

Obtain the paging optimization information from one of the following network elements:

NWDA;

UDM;

UDR;

PCF.

Wherein, in an embodiment, acquiring the paging optimization information from the UDM or UDR includes:

Receive the paging optimization information sent by the UDM or the UDR; the received paging optimization information is sent after the UDM or the UDR determines that the UE has the paging optimization information by using the subscription data of the UE.

Here, in practical application, after the UE is registered, the UDM or UDR will use the UE's subscription data to determine whether the UE has paging optimization information. When the UDM or UDR uses the UE's subscription data After the data determines that the UE has paging optimization information, it will send the paging optimization information to the AMF; in addition, when the paging optimization information is updated, it will send the updated paging optimization information to the AMF.

It should be noted that: in practical application, UDM or UDR can be selected as needed to store the UE's subscription data (UDM or UDR can obtain UE's subscription data from NWDA), and then the selected network element determines Whether there is paging optimization information, and send the paging optimization information to the AMF.

In an embodiment, the obtaining the paging optimization information from the PCF includes:

sending a policy acquisition request to the PCF;

Receive the paging optimization information sent by the PCF; the received paging optimization information is that the PCF uses the subscription data of the UE to determine that the UE has paging optimization information, and obtains the paging optimization information from one of the following network elements Sent after:

UDM;

UDR;

NWDA.

Here, in practical application, the PCF may query the UDM or UDR for a request; after receiving the request, the UDM or UDR determines whether the UE has paging optimization information according to the subscription data of the UE, and obtains the corresponding paging optimization information. query results, and return the corresponding query results (whether the UE has paging optimization information) to the PCF.

It should be noted that: in practical application, UDM or UDR can be selected to store the subscription data of the UE, and the PCF determines whether the UE has paging optimization information by sending a query request to the selected network element .

In an embodiment, the paging optimization information at least includes: UE id periodic registration timer allocation and one of a cell list and a tracking area list corresponding to the UE within the specific time period;

Correspondingly, determining the paging range by using the paging optimization information of the UE includes:

Determine the access network by using one of the cell list and the tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are based on the UE The id is periodically updated by the registration timer allocation.

That is to say, the cell list and tracking area list corresponding to the UE in the predicted specific time period have a life cycle, and the life cycle is the duration of the UE id periodic registration timer. In other words, NWDA predicts a specific time After the cell list and tracking area list corresponding to the UE in the segment, the UE id periodic registration timer will start timing. After the timer expires, it is necessary to re-predict the cell list and tracking area list corresponding to the UE. That is, the cell list and the cell in the tracking area list corresponding to the UE are updated, so that the paging range can be accurately determined when the UE is subsequently paged.

In addition, in practical application, the duration of the UE id periodic registration timer can be updated according to the behavior of the UE (such as the mobility of the UE). For example, when the mobility of the UE is very frequent, the duration of the UE id periodic registration timer needs to be shortened. If the UE does not move frequently, the duration of the UE id periodic registration timer can be longer, that is, the cell The cells in the list and the tracking area list can be updated once in a long time.

Step 202: Paging the UE according to the determined paging range.

Here, after the access network is determined, the UE is paged through the determined access network.

In practical application, when the paging fails according to the determined paging range, the UE can be paged by using the tracking area list.

That is to say, when the paging fails according to the determined paging range, the UE may continue to be paged by using the normal paging manner.

At this time, it means that the paging area predicted by NWDA is inaccurate, and it is necessary to re-predict the paging area according to the failure information.

Based on this, in one embodiment, the method may further include:

Record this paging event as an abnormal event, and store the corresponding abnormal event for the NWDA to update the paging optimization information of the UE.

Here, in practical application, the AMF may store the abnormal event locally or store it in the NWDA.

When stored locally, when the number of abnormal events recorded within a preset time period exceeds the threshold, the AMF will upload the recorded number of abnormal events and the corresponding abnormal events to the NWDA; the reported information is used for the NWDA to update The paging optimization information of the UE.

When the abnormal event is stored in the NWDA, when the number of abnormal events recorded by the AMF (which can also be understood as the events stored in the NWDA) exceeds the threshold within a preset time period, the NWDA will use the recorded abnormal events to update the paging of the UE Optimization information.

Correspondingly, an embodiment of the present invention also provides a paging method, which is applied to NWDA. As shown in FIG. 3 , the method includes:

Step 301: obtain data samples of the UE;

Here, the data sample is the historical paging area information of the UE.

Step 302: According to the granularity of network slices, using the data samples and combining with a machine learning algorithm, determine the paging optimization information of the UE in a specific time period.

Here, the determined paging optimization information is used for the AMF to determine a paging range and to page the UE according to the paging range; the determined optimization information represents the movement of the UE within a specific time period.

That is to say, NWDA uses the collected historical paging area information of the UE, including the paging range corresponding to the user at a certain time, and based on the machine learning algorithm, predicts the paging optimization information of the UE in a specific time period, that is, accurate prediction. UEs have regular mobility patterns and associated UE tracking areas.

The network slice granularity may also be called network slice, which is a relatively abstract concept. In the past, the network layout used network elements as the basic unit to process all service types (without distinguishing services). The service-oriented network framework structure introduces the concept of network slicing, which can realize the function of network elements to be segmented according to services. Each network element function is a server that provides a specific function service, and the service corresponding to each specific network segmentation appears in the form of a network element segmentation instance. To put it simply, corresponding to those target services in the 5G system, such as enhanced mobile broadband (eMBB) services, ultra-reliable and low-latency communication (uRLLC) services, massive machine-type communication (mMTC) services, etc. It can be called network slice instance identifier) can inform the network what specific type of service is provided, so that the network can provide customized services according to different service characteristics.

In practical applications, a machine learning algorithm can be selected for prediction as needed. For example, a machine learning algorithm can be selected, trained on data samples to obtain a linear regression model, and then the obtained model can be used to predict paging optimization information (paging zones) within a specific time period.

The specific time period can be determined as needed.

In practical application, when the AMF fails to page the UE according to the paging range determined by the determined paging optimization information, the AMF will record the abnormal event; while the NWDA needs to re-predict the paging area in a specific time period.

Based on this, in one embodiment, the method may further include:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

Among them, the abnormal events recorded by the AMF can be stored locally or stored in the NWDA.

When stored locally, when the number of abnormal events recorded within a preset time period exceeds the threshold, the AMF will upload the recorded number of abnormal events and the corresponding abnormal events to the NWDA; the reported information is used for the NWDA to update The paging optimization information of the UE.

When the abnormal event is stored in the NWDA, when the number of abnormal events recorded by the AMF (which can also be understood as the events stored in the NWDA) exceeds the threshold within a preset time period, the NWDA will use the recorded abnormal events to update the paging of the UE Optimization information.

The abnormal event can be expressed by the position of the UE and the corresponding time.

Specifically, when updating, the updated data samples need to be trained to update the parameters in the model, and then the updated model is used to re-predict the paging area within a specific time period.

The preset duration may be set as required, such as one month, two months, and the like.

The threshold can be set as required, such as 6 times or 7 times.

In an embodiment, the NWDA may push the paging optimization information of the UE determined by itself to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

In this way, on the one hand, its own storage space can be saved, and on the other hand, the AMF can quickly obtain the paging optimization information of the UE, and then can quickly page the UE.

Of course, the NWDA can also store the paging optimization information of the UE locally.

The embodiment of the present invention also provides a paging method, as shown in FIG. 4 , the method includes:

Step 401: NWDA obtains data samples of UE;

Here, the data sample is the historical paging area information of the UE.

Step 402: The NWDA determines the paging optimization information of the UE within a specific time period by using the data samples and combining with a machine learning algorithm according to the granularity of network slices;

Here, the determined optimization information represents the movement of the UE within a specific time period.

Step 403: The AMF determines a paging range by using the paging optimization information of the UE determined by the NWDA; and paging the UE according to the determined paging range.

Wherein, the AMF obtains the paging optimization information from one of the following network elements:

NWDA;

UDM;

UDR;

PCF.

Wherein, the method may also include:

The UDM or the UDM notifies the NWDA and/or the AMF when it is determined by using the subscription data of the UE that the UE has paging optimization information.

When the AMF acquires the paging optimization information of the UE from the PCF (that is, the AMF acquires the mobility management policy from the PCF), the AMF sends a policy acquisition request to the PCF; after receiving the policy acquisition request, the PCF uses the When the subscription data of the UE determines that the UE has paging optimization information, obtain the paging optimization information of the UE from one of the following network elements: UDM; UDR; NWDA; and send it to the AMF; the AMF receives the the paging optimization information sent by the PCF.

In one embodiment, the AMF uses the tracking area list to page the UE when the paging fails according to the determined paging range.

In addition, the AMF will record this paging event as an abnormal event, so that the NWDA can update the paging optimization information of the UE;

When the number of abnormal events recorded by the AMF within a preset time period exceeds the threshold, the NWDA updates the data samples of the UE using the recorded abnormal events; and according to the granularity of network slices, uses the updated data samples, combined with A machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

It should be noted that: the processing process of each network element has been described in detail above, and will not be repeated here.

In the paging method provided by the embodiment of the present invention, NWDA obtains the data samples of the UE; the data samples are the historical paging area information of the UE and according to the granularity of network slices, the data samples are used in combination with the machine learning algorithm to determine The UE paging optimization information within a specific time period; the AMF uses the paging optimization information of the UE determined by the NWDA to determine a paging range; paging the UE according to the determined paging range, predicting based on the NWDA The paging optimization information is used to determine the paging range, that is, predict the paging area, and then use the predicted paging area to page the UE. Since the paging range is determined, the waste of base station resources can be greatly reduced.

In addition, when the paging fails according to the determined paging range, the AMF can use the tracking area list to page the UE, that is, continue to page the UE in the normal way, so that the UE can be guaranteed to be paged, and the service is provided. Assure.

In addition, the AMF records this paging event as an abnormal event, and stores the corresponding abnormal event. When the number of abnormal events recorded by the AMF (which can also be understood as events stored in NWDA) exceeds the threshold within the preset time period , NWDA will use the recorded abnormal events to update the paging optimization information of the UE, and the paging optimization information is re-predicted according to the movement of the UE, which can further accurately determine the paging range and greatly reduce the waste of base station resources.

The present invention will be further described in detail below in conjunction with application examples.

Application Example 1

In this application embodiment, the network delivers a mobility management policy (paging optimization policy) to the AMF, so as to implement paging of the UE.

The paging method of this application embodiment, as shown in FIG. 5 , includes the following steps:

Step 500: The NWDA regularly pushes the paging optimization information of the UE to the UDM/UDR; and the UDM/UDR obtains the UE's subscription information (which can also be understood as subscription data) from the NWDA;

Here, the UDM/UDR may be called a network function service caller (NF network function), which fetches user subscription information from NWDA by calling the Nnwdaf_Analytics_Info_Request service (a program).

NWDA regularly pushes the UE's paging optimization information (UE id periodic registration timer allocation, corresponding cell list or TAlist in a certain period of time) to the UDM/UDR by calling the Nnwdaf_Analytics_Info_Response service (a program).

Of course, the NWDA can also store the paging optimization information of the UE locally. When the UDM/UDR finds that the registered UE has paging optimization information, it will notify the NWDA, and the NWDA will push the paging optimization information of the registered UE to the AMF.

Step 501: After the UE is registered (attached) to the network, the UDM/UDR finds that the registered UE has paging optimization information from the user subscription information of the registered UE (by optimizing the paging indicator bit), and optimizes the paging of the registered UE. The information is pushed to AMF;

Here, since UDM/UDR does not have PCF id, UDM is directly pushed to AMF.

When there is paging optimization information, it also indicates that the UE has a corresponding NWDA that provides slice granularity services for the UE.

Step 502: the AMF determines the paging area range by using the paging optimization information, and paging the UE based on the paging area range;

Here, in fact, due to the function of the paging optimization information, it can be understood that: according to the behavior of the UE in the past statistics, it can be known that the activity of the UE is regular at a certain time. For example, a UE user goes to work during the day and goes home at night. Therefore, when the UE is paged during the day, the UE can be paged directly through the base station near the user's work place of the UE, instead of the traditional need to find the location of the UE's last call to page the UE, so AMF can use the The paging optimization information is directly located to an access network (AN), specifically a radio access network (RAN), and the UE is paged through the located AN network.

Step 503: The paging is successful, and the data is transmitted.

Application Example 2

In this application embodiment, the AMF obtains the mobility management policy from the PCF, so as to implement paging of the UE.

In this application embodiment, the paging is triggered by downlink data, and the tracking area list and timer information have been saved on the AMF at this time. (Configured on AMF, common to the entire network). Specifically, after receiving the data packet, the UPF sends the data packet to the SMF, and the SMF buffers the data packet, and then the SMF notifies the AMF of the paging data to page the corresponding UE.

The paging method of this application embodiment, as shown in FIG. 6 , includes the following steps:

Step 601: After the UE registers with the network, the UPF discovers the downlink data, notifies the AMF of the paging data, and the AMF obtains the mobility management policy from the PCF;

Step 602: the PCF sends a request to the UDM/UDR to determine whether there is paging optimization information in the UE subscription data;

Here, when there is paging optimization information, it also indicates that the UE has a corresponding NWDA that provides slice granularity services for the UE.

Step 603: when the UDM/UDR determines that the UE has paging optimization information according to the subscription data of the UE, push the paging optimization information of the UE to the PCF;

Step 604: After receiving the paging optimization information, the PCF sends the paging optimization information (UE id periodic registration timer allocation, cell list or TAlist corresponding to a certain period of time) to the AMF;

Step 605: the AMF paging optimization information determines the paging area range, and paging the UE based on the paging area range;

Here, in fact, due to the function of the paging optimization information, it can be understood that: according to the behavior of the UE in the past statistics, it can be known that the activity of the UE is regular at a certain time. For example, a UE user goes to work during the day and goes home at night. Therefore, when the UE is paged during the day, the UE can be paged directly through the base station near the user's work place of the UE, instead of the traditional need to find the location of the UE's last call to page the UE, so AMF can use the The paging optimization information is directly located to the AN, specifically the RAN, and paging to the UE through the located AN network.

During the paging process, the downlink data will be sent to the UE, that is, when the paging is successful, the UE will also receive the downlink data.

Step 606: The paging is successful, and data is sent.

Application Example 3

In this application embodiment, when the UE cannot be paged by using the paging optimization information, that is, when the UE fails to be paged by using the paging optimization information, the process of how the network side pages the UE.

As shown in Figure 7, the paging process includes:

Step 701: AMF obtains paging optimization information;

Here, it can be obtained by applying the method of the first embodiment, or it can be obtained by the method of the second embodiment. specifically,

Step 701a: the UDM/UDR proactively delivers the paging optimization information to the AMF (the network side directly delivers the paging optimization information);

Step 701b: The PCF delivers the paging optimization information to the AMF (the AMF obtains the paging optimization information from the PCF).

Step 702: the AMF paging the UE within the paging area determined by using the paging optimization information;

Step 703: When the UE is not paged, the AN replies to the AMF that the UE is not paged (paging ACK is returned), and the paging fails;

Steps 704-705: The AMF immediately switches to the normal paging mode and re-pages the UE according to the TAlist.

Steps 706 to 707: the paging is successful;

Step 708: AMF records that this event is an abnormal value, that is, an abnormal event, and stores it;

Step 709: within a certain period of time, when the number of occurrences of abnormal events reaches the threshold M, upload data (including the number of abnormal values in the statistics, the abnormal values in the local cache) to the NWDA to notify the NWDA to update the algorithm of the paging optimization information;

Here, the specific time period can be set as required, such as one month, two months, and the like.

Step 710: The NWDA records the corresponding events and updates the UE paging optimization information.

It can be seen from the above description that in the solution provided by the embodiments of the present invention, the AMF uses the paging optimization information (TAlist or Cell list) to page the UE, which can directly locate the AN, thereby reducing the paging of the base station (such as the gNB). Load (page load) and save the corresponding processing resources.

Among them, the network side (NWDA) can obtain a regular curve by using the historical paging area information, so as to predict the mobility of the UE according to the regular curve, that is, predict and optimize the paging information. The AMF cannot page the UE by using the paging optimization information, indicating that the location information of the UE at this time is an abnormal value that deviates from this regular curve, and the AMF will remember this event. When this outlier reaches the threshold, it is reported to NWDA. The NWDA records the location information of the UE at a specific time. When the next abnormal event occurs, the NWDA will automatically change the entire paging strategy, that is, update the paging optimization information, such as reassigning base stations.

In practical application, when the UE is in IDLE mode, the network side automatically allocates the TAlist or Cell list and the corresponding timer, that is, the UE periodic registration timer, according to the algorithm it learns from the behavior of the UE. For example, according to past paging experience, as long as the UE stays in the same series of cell lists for a fixed period of time, the network will gradually shrink the cell list allocated to the UE. If the monitored UE is in a fixed location area for a certain period of time, the network will extend the time for triggering the TAU procedure next time.

In order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides a paging device, which is set in the AMF. As shown in FIG. 8 , the device includes:

The first determining unit 81 is configured to determine the paging range by using the paging optimization information of the UE; the paging optimization information is obtained by NWDA performing machine learning on the historical paging area information of the UE according to the granularity of network slices; The paging optimization information represents the movement of the UE within a specific time period;

The paging unit 82 is used for paging the UE according to the determined paging range.

In practical application, AMF needs to obtain paging optimization information.

Based on this, in an embodiment, as shown in FIG. 8 , the apparatus may further include:

The obtaining unit 83 is configured to obtain the paging optimization information from one of the following network elements:

NWDA;

UDM;

UDR;

PCF.

In practical application, when the paging fails according to the determined paging range, the UE can be paged by using the tracking area list.

Based on this, in an embodiment, the paging unit 82 is further configured to:

When paging fails according to the determined paging range, the UE is paged using the tracking area list.

That is to say, when the paging fails according to the determined paging range, the UE may continue to be paged by using the normal paging manner.

At this time, it means that the paging area predicted by NWDA is inaccurate, and it is necessary to re-predict the paging area according to the failure information.

Based on this, in an embodiment, the apparatus may further include:

A storage unit, configured to record this paging event as an abnormal event, and store the corresponding abnormal event, so that the NWDA can update the paging optimization information of the UE.

In practical application, the first determining unit 81 and the storage unit may be implemented by a processor in the paging device, and the paging unit 82 and the acquiring unit 83 may be implemented by a processor in the paging device combined with a communication interface.

It should be noted that: when the paging apparatus provided in the above embodiment performs paging, only the division of the above program modules is used as an example for illustration. That is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the paging apparatus and the paging method embodiments provided by the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiments, which will not be repeated here.

In order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides a paging device, which is set in the NWDA. As shown in FIG. 9 , the device includes:

an obtaining unit 91, configured to obtain a data sample of the UE; the data sample is the historical paging area information of the UE;

The second determining unit 92 is configured to determine the paging optimization information of the UE within a specific time period by using the data samples and the machine learning algorithm according to the granularity of network slices; the determined paging optimization information is used for the AMF to determine paging a range and paging the UE according to the paging range; the determined optimization information characterizes the movement of the UE within a specific time period.

In practical application, when the AMF fails to page the UE according to the paging range determined by the determined paging optimization information, the AMF will record the abnormal event; while the NWDA needs to re-predict the paging area in a specific time period.

Based on this, in an embodiment, the second determining unit 92 is further configured to:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

In an embodiment, the apparatus may further include: a pushing unit, configured to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

In this way, on the one hand, its own storage space can be saved, and on the other hand, the AMF can quickly obtain the paging optimization information of the UE, and then can quickly page the UE.

In practical application, the acquiring unit 91 and the pushing unit may be implemented by a processor in the paging device in combination with a communication interface; the second determining unit 92 may be implemented by a processor in the paging device.

It should be noted that: when the paging apparatus provided in the above embodiment performs paging, only the division of the above program modules is used as an example for illustration. That is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the paging apparatus and the paging method embodiments provided by the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiments, which will not be repeated here.

Based on the above hardware implementation, in order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides a network device, which is an AMF. As shown in FIG. 10 , the network device 100 includes:

The first communication interface 101, capable of information interaction with other network devices;

The first processor 102 is connected to the first communication interface 101 to implement information exchange with other network devices, and is used to execute the methods provided by one or more technical solutions on the AMF side when running a computer program. And the computer program is stored on the first memory 103 .

Specifically, the first processor 102 is configured to use the paging optimization information of the UE to determine the paging range; the paging optimization information is that NWDA performs a machine-based process of the historical paging area information of the UE according to the granularity of network slices. obtained after learning; the paging optimization information represents the movement of the UE within a specific time period; and the UE is paging through the first communication interface 101 according to the determined paging range.

Wherein, in practical application, the AMF needs to obtain paging optimization information.

Based on this, in an embodiment, the first processor 102 is further configured to obtain the paging optimization information from one of the following network elements through the first communication interface 101:

NWDA;

UDM;

UDR;

PCF.

In practical application, when the paging fails according to the determined paging range, the UE can be paged by using the tracking area list.

Based on this, in an embodiment, the first processor is further configured to:

When the paging fails according to the determined paging range, the UE is paged through the first communication 101 interface using the tracking area list.

That is to say, when the paging fails according to the determined paging range, the UE may continue to be paged by using the normal paging manner.

At this time, it means that the paging area predicted by NWDA is inaccurate, and it is necessary to re-predict the paging area according to the failure information.

Based on this, in an embodiment, the first processor 101 is further configured to record this paging event as an abnormal event, so that the NWDA can update the paging optimization information of the UE.

It should be noted that: the specific processing process of the first processor 102 can be found in the method embodiment, which is not repeated here.

Of course, in practical application, various components in the network device 100 are coupled together through the bus system 104 . It will be appreciated that the bus system 104 is used to implement connection communication between these components. In addition to the data bus, the bus system 104 also includes a power bus, a control bus, and a status signal bus. However, for clarity of illustration, the various buses are labeled as bus system 104 in FIG. 10 .

The first memory 103 in the embodiment of the present invention is used to store various types of data to support the operation of the network device 100 . Examples of such data include: any computer program used to operate on network device 100 .

The methods disclosed in the above embodiments of the present invention may be applied to the first processor 102 or implemented by the first processor 102 . The first processor 102 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above-mentioned method may be completed by an integrated logic circuit of hardware in the first processor 102 or an instruction in the form of software. The above-mentioned first processor 102 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The first processor 102 may implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, and the storage medium is located in the first memory 103, and the first processor 102 reads the information in the first memory 103, and completes the steps of the foregoing method in combination with its hardware.

In an exemplary embodiment, the network device 100 may be implemented by one or more Application Specific Integrated Circuit (ASIC, Application Specific Integrated Circuit), DSP, Programmable Logic Device (PLD, Programmable Logic Device), Complex Programmable Logic Device (CPLD, Complex Programmable Logic Device), Field-Programmable Gate Array (FPGA, Field-Programmable Gate Array), general-purpose processor, controller, microcontroller (MCU, Micro Controller Unit), microprocessor (Microprocessor), or other electronic components implementation for performing the aforementioned method.

Based on the hardware implementation of the above device, in order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides a network device. As shown in FIG. 11 , the network device 110 includes:

The second communication interface 111 is capable of information interaction with other network devices;

The second processor 112 is connected to the second communication interface 111 to implement information interaction with other network devices, and is used to execute the methods provided by one or more technical solutions on the NWDA side when running a computer program. And the computer program is stored on the second memory 113 .

Specifically, the second processor 112 is configured to obtain a data sample of the UE through the second communication interface 111; the data sample is the historical paging area information of the UE; according to the granularity of the network slice, use the data sample , and in combination with a machine learning algorithm, determine the paging optimization information of the UE within a specific time period; the determined paging optimization information is used for the AMF to determine a paging range and paging the UE according to the paging range; The determined optimization information characterizes the movement of the UE within a specific time period.

In practical application, when the AMF fails to page the UE according to the paging range determined by the determined paging optimization information, the AMF will record the abnormal event; while the NWDA needs to re-predict the paging area in a specific time period.

Based on this, in an embodiment, the second processor 112 is further configured to:

When the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold, the data sample of the UE is updated by using the recorded abnormal events; the abnormal events represent that the AMF uses the determined paging optimization information paging the UE fails;

According to the granularity of the network slice, the updated data samples are used in combination with the machine learning algorithm to re-determine the paging optimization information of the UE within a specific time period.

In an embodiment, the second communication interface 111 is further configured to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF.

In this way, on the one hand, its own storage space can be saved, and on the other hand, the AMF can quickly obtain the paging optimization information of the UE, and then can quickly page the UE.

It should be noted that: the specific processing process of the second processor 112 can be found in the method embodiment, which is not repeated here.

Of course, in practical applications, various components in the network device 110 are coupled together through the bus system 114 . It will be appreciated that the bus system 114 is used to implement the connection communication between these components. In addition to the data bus, the bus system 114 also includes a power bus, a control bus, and a status signal bus. However, for clarity of illustration, the various buses are labeled as bus system 114 in FIG. 11 .

It should be noted that: the specific processing process of the second processor 112 can be found in the method embodiment, which is not repeated here.

The second memory 113 in the embodiment of the present invention is used for storing various types of data to support the operation of the network device 110 . Examples of such data include: any computer program used to operate on network device 110 .

The methods disclosed in the above embodiments of the present invention may be applied to the second processor 112 or implemented by the second processor 112 . The second processor 112 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above-mentioned method may be completed by an integrated logic circuit of hardware in the second processor 112 or an instruction in the form of software. The above-mentioned second processor 112 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The second processor 112 may implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, and the storage medium is located in the second memory 113, and the second processor 112 reads the information in the second memory 113, and completes the steps of the foregoing method in combination with its hardware.

In an exemplary embodiment, the network device 110 may be implemented by one or more ASICs, DSPs, PLDs, CPLDs, FPGAs, general purpose processors, controllers, MCUs, Microprocessors, or other electronic components for performing the aforementioned methods.

It can be understood that the memory (the first memory 103 and the second memory 113 ) in this embodiment of the present invention may be a volatile memory or a nonvolatile memory, and may also include both volatile and nonvolatile memory. Among them, the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory) Memory), Electrically Erasable Programmable Read-Only Memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), Magnetic Random Access Memory (FRAM, ferromagnetic randomaccess memory), Flash Memory, Magnetic Surface Memory, Optical Disc, Or compact disc read-only memory (CD-ROM, Compact Disc Read-Only Memory); magnetic surface memory can be magnetic disk memory or tape memory. The volatile memory may be random access memory (RAM, Random Access Memory), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory ( DRAM, Dynamic Random Access Memory), Synchronous Dynamic Random Access Memory (SDRAM, Synchronous Dynamic Random Access Memory), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), Enhanced Synchronous Dynamic Random Access Memory Random Access Memory (ESDRAM, Enhanced SynchronousDynamic Random Access Memory), Synchronous Link Dynamic Random Access Memory (SLDRAM, SyncLinkDynamic Random Access Memory), Direct Memory Bus Random Access Memory (DRRAM, Direct Rambus Random Access Memory). The memory described in the embodiments of the present invention is intended to include, but not be limited to, these and any other suitable types of memory.

The embodiment of the present invention also provides a paging system, as shown in FIG. 12 , the system includes:

The NWDA 121 is used to obtain data samples of the UE; the data samples are historical paging area information of the UE; according to the granularity of network slices, the data samples are used and combined with a machine learning algorithm to determine the UE at a specific time Intra-segment paging optimization information; the determined optimization information represents the movement of the UE within a specific time period;

The AMF 122 is configured to determine a paging range by using the paging optimization information of the UE determined by the NWDA 121; and paging the UE according to the determined paging range.

Wherein, in an embodiment, the system may further include: UDM, UDR, PCF;

The AMF 122 is further configured to obtain the paging optimization information from one of the following network elements:

NWDA 121;

UDM;

UDR;

PCF.

In an embodiment, the UDM or the UDM is further configured to notify the NWDA 121 and/or the AMF 122 when it is determined by using the subscription data of the UE that the UE has paging optimization information.

In an embodiment, the AMF 122 is configured to send a policy acquisition request to the PCF;

The PCF is configured to obtain the paging optimization information of the UE from one of the following network elements when it is determined that the UE has paging optimization information by using the subscription data of the UE after receiving the policy acquisition request: UDM; UDR ; NWDA 121; and send to the AMF;

The AMF 122 is configured to receive the paging optimization information sent by the PCF.

In an embodiment, the AMF 122 is further configured to use the tracking area list to page the UE when the paging fails according to the determined paging range.

In one embodiment, the AMF 122 is further configured to: record this paging event as an abnormal event, so that the NWDA 121 can update the paging optimization information of the UE;

The NWDA 121 is further configured to use the recorded abnormal event to update the data sample of the UE when the number of abnormal events recorded by the AMF within a preset time period exceeds a threshold; and according to the network slice granularity, use the updated data sample. The data samples, combined with the machine learning algorithm, re-determine the paging optimization information of the UE within a specific time period.

In an embodiment, the NWDA 121 is further configured to periodically push the determined paging information of the UE within a specific time period to at least one of the following network elements for storage:

UDM;

UDR;

AMF 122.

It should be noted that: the specific processing process of each network element is shown in the method embodiment, which will not be repeated here.

In an exemplary embodiment, an embodiment of the present invention further provides a storage medium, that is, a computer storage medium, specifically a computer-readable storage medium, for example, including a first memory 103 that stores a computer program, and the above-mentioned computer program can be stored by the network device 100 The first processor 102 executes the steps of the aforementioned AMF side method. Another example includes the second memory 113 storing a computer program, and the computer program can be executed by the second processor 112 of the network device 110 to complete the steps of the aforementioned NWDA-side method. The computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.

It should be noted that the technical solutions described in the embodiments of the present invention may be combined arbitrarily unless there is a conflict.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention.

Claims (31)

1. A method for paging, comprising:

determining a paging range by using paging optimization information of a User Entity (UE); the paging optimization information is obtained by performing machine learning on the historical paging area information of the UE according to network slicing granularity by network data analysis (NWDA); the paging optimization information characterizes movement of the UE within a particular time period;

paging the UE according to the determined paging range;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determining the paging range by using the paging optimization information of the UE includes:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

2. The method of claim 1, further comprising:

obtaining the paging optimization information from one of the following network elements:

NWDA；

a User Data Management (UDM);

a user data repository, UDR;

a policy control function PCF.

3. The method of claim 2, wherein obtaining the paging optimization information from the UDM or UDR comprises:

receiving paging optimization information sent by the UDM or the UDR; and the received paging optimization information is sent after the UDM or the UDR determines that the paging optimization information exists in the UE by using the subscription data of the UE.

4. The method of claim 2, wherein obtaining the paging optimization information from the PCF comprises:

sending a policy acquisition request to the PCF;

receiving paging optimization information sent by the PCF; the received paging optimization information is sent by the PCF after the PCF determines that the UE has the paging optimization information by utilizing the subscription data of the UE and acquires the paging optimization information from one of the following network elements:

UDM；

UDR；

NWDA。

5. the method of claim 1, further comprising:

and when the paging fails according to the determined paging range, paging the UE by using the tracking area list.

6. The method of claim 5, further comprising:

and recording the paging event as an abnormal event, and storing the corresponding abnormal event for the NWDA to update the paging optimization information of the UE.

7. A method for paging, comprising:

acquiring a data sample of UE; the data sample is historical paging area information of the UE;

according to the network slice granularity, determining paging optimization information of the UE in a specific time period by using the data sample and combining a machine learning algorithm; the determined paging optimization information is used for an access and mobility management function (AMF) to determine a paging range and page the UE according to the paging range; the determined optimization information characterizes movement of the UE within a particular time period;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determined paging optimization information is used for an access and mobility management function (AMF) to determine a paging range, and comprises the following steps:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

8. The method of claim 7, further comprising:

when the number of abnormal events recorded by the AMF in a preset time length exceeds a threshold value, updating the data sample of the UE by using the recorded abnormal events; the abnormal event represents that the AMF fails to page the UE by using the determined paging optimization information;

and according to the network slice granularity, re-determining paging optimization information of the UE in a specific time period by using the updated data sample and combining a machine learning algorithm.

9. The method according to claim 7 or 8, characterized in that the method further comprises:

and regularly pushing the determined paging information of the UE in a specific time period to at least one of the following network elements for storage:

UDM；

UDR；

AMF。

10. a paging device, comprising:

a first determining unit, configured to determine a paging range by using paging optimization information of the UE; the paging optimization information is obtained by performing machine learning on the historical paging area information of the UE by the NWDA according to the network slice granularity; the paging optimization information characterizes movement of the UE within a particular time period;

the paging unit is used for paging the UE according to the determined paging range;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determining the paging range by using the paging optimization information of the UE includes:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

11. The apparatus of claim 10, wherein the paging unit is further configured to:

and when the paging fails according to the determined paging range, paging the UE by using the tracking area list.

12. The apparatus of claim 11, further comprising:

and the storage unit is used for recording the current paging event as an abnormal event and storing the corresponding abnormal event so that the NWDA can update the paging optimization information of the UE.

13. A paging device, comprising:

an obtaining unit, configured to obtain a data sample of a UE; the data sample is historical paging area information of the UE;

a second determining unit, configured to determine, according to a network slicing granularity, paging optimization information of the UE in a specific time period by using the data sample and combining a machine learning algorithm; the determined paging optimization information is used for the AMF to determine a paging range and page the UE according to the paging range; the determined optimization information characterizes movement of the UE within a particular time period;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determined paging optimization information is used for an access and mobility management function (AMF) to determine a paging range, and comprises the following steps:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

14. The apparatus of claim 13, wherein the second determining unit is further configured to:

when the number of abnormal events recorded by the AMF in a preset time length exceeds a threshold value, updating the data sample of the UE by using the recorded abnormal events; the abnormal event represents that the AMF fails to page the UE by using the determined paging optimization information;

and according to the network slice granularity, re-determining paging optimization information of the UE in a specific time period by using the updated data sample and combining a machine learning algorithm.

15. The apparatus of claim 13 or 14, further comprising:

a pushing unit, configured to push the determined paging information of the UE in a specific time period to at least one of the following network elements for storage:

UDM；

UDR；

AMF。

16. a network device, comprising:

a first communication interface;

a first processor for determining a paging range using paging optimization information of a UE; the paging optimization information is obtained by performing machine learning on the historical paging area information of the UE by the NWDA according to the network slice granularity; the paging optimization information characterizes movement of the UE within a particular time period; paging the UE through the first communication interface according to the determined paging range;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determining the paging range by using the paging optimization information of the UE includes:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

17. The device of claim 16, wherein the first processor is further configured to:

and when the paging fails according to the determined paging range, paging the UE through the first communication interface by using a tracking area list.

18. The apparatus of claim 17,

the first processor is further configured to record the current paging event as an abnormal event, so that the NWDA updates paging optimization information of the UE.

19. A network device, comprising:

a second communication interface;

a second processor for obtaining data samples of the UE through the second communication interface; the data sample is historical paging area information of the UE; according to the network slice granularity, determining paging optimization information of the UE in a specific time period by using the data sample and combining a machine learning algorithm; the determined paging optimization information is used for the AMF to determine a paging range and page the UE according to the paging range; the determined optimization information characterizes movement of the UE within a particular time period;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determined paging optimization information is used for an access and mobility management function (AMF) to determine a paging range, and comprises the following steps:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

20. The apparatus of claim 19,

the second processor is further configured to:

when the number of abnormal events recorded by the AMF in a preset time length exceeds a threshold value, updating the data sample of the UE by using the recorded abnormal events; the abnormal event represents that the AMF fails to page the UE by using the determined paging optimization information;

and according to the network slice granularity, re-determining paging optimization information of the UE in a specific time period by using the updated data sample and combining a machine learning algorithm.

21. The apparatus of claim 19 or 20, wherein the second communication interface is further configured to periodically push the determined paging information of the UE in a specific time period to at least one of the following network elements for storage:

UDM；

UDR；

AMF。

22. a network device, comprising: a first processor and a first memory for storing a computer program capable of running on the processor,

wherein the first processor is adapted to perform the steps of the method of any one of claims 1 to 6 when running the computer program.

23. A network device, comprising: a second processor and a second memory for storing a computer program capable of running on the processor,

wherein the second processor is adapted to perform the steps of the method of any of claims 7 to 9 when running the computer program.

24. A paging system, comprising:

the NWDA is used for obtaining data samples of the UE; the data sample is historical paging area information of the UE; according to the network slice granularity, determining paging optimization information of the UE in a specific time period by using the data sample and combining a machine learning algorithm; the determined optimization information characterizes movement of the UE within a particular time period;

the AMF is used for determining a paging range by utilizing the paging optimization information of the UE determined by the NWDA; paging the UE according to the determined paging range;

the paging optimization information at least includes: allocating a UE id periodic registration timer and one of a cell list and a tracking area list corresponding to the UE in the specific time period;

the determined paging optimization information is used for an access and mobility management function (AMF) to determine a paging range, and comprises the following steps:

determining an access network by using one of a cell list and a tracking area list corresponding to the UE in the specific time period; the cell list and the tracking area list corresponding to the UE in the specific time period are updated according to the UE id periodic registration timer allocation.

25. The system of claim 24, further comprising: UDM, UDR, PCF;

the AMF is further configured to: obtaining the paging optimization information from one of the following network elements:

NWDA；

UDM；

UDR；

PCF。

26. the system of claim 25, wherein the UDM or UDM is further configured to notify the NWDA and/or AMF when it is determined that paging optimization information exists for the UE using subscription data of the UE.

27. The system of claim 25 wherein said AMF is configured to send a policy acquisition request to said PCF;

the PCF is configured to, after receiving the policy acquisition request, acquire paging optimization information of the UE from one of the following network elements when determining that the paging optimization information exists for the UE using the subscription data of the UE: UDM; UDR; NWDA; and sending to the AMF;

and the AMF is used for receiving the paging optimization information sent by the PCF.

28. The system of claim 24, wherein the AMF is further configured to page the UE with a tracking area list when paging fails according to the determined paging range.

29. The system of claim 28, wherein the AMF is further configured to: recording the paging event as an abnormal event for the NWDA to update the paging optimization information of the UE;

the NWDA is further used for updating the data sample of the UE by using the recorded abnormal event when the number of the abnormal events recorded by the AMF in a preset time length exceeds a threshold value; and according to the network slice granularity, the paging optimization information of the UE in a specific time period is re-determined by using the updated data sample and combining a machine learning algorithm.

30. The system according to any of claims 24 to 29, wherein said NWDA is further configured to periodically push and store the determined paging information of said UE in a specific time period to at least one of the following network elements:

UDM；

UDR；

AMF。

31. a storage medium having stored thereon a computer program for performing the steps of the method of any one of claims 1 to 6 or for performing the steps of the method of any one of claims 7 to 9 when executed by a processor.

Images