CN110121891B - Method and apparatus for predicting mobility of a mobile communication device in a cellular communication network - Google Patents
Method and apparatus for predicting mobility of a mobile communication device in a cellular communication network Download PDFInfo
- Publication number
- CN110121891B CN110121891B CN201680091839.8A CN201680091839A CN110121891B CN 110121891 B CN110121891 B CN 110121891B CN 201680091839 A CN201680091839 A CN 201680091839A CN 110121891 B CN110121891 B CN 110121891B
- Authority
- CN
- China
- Prior art keywords
- communication device
- mobile communication
- destination
- trajectory
- location
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/024—Guidance services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Abstract
The present application relates to a method of predicting mobility of a mobile communication device in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, the method comprising: determining location information of the mobile communication device, the location information including a current location L of the mobile communication device in a current network cell; providing destination information for the mobile communication device based on a current location L of the mobile communication device, the destination information including at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; at least a portion of future trajectories of the mobile communication device between the current location L and the possible destination D are predicted based on a subset of the set of recorded local trajectories T, each trajectory in the subset of recorded set of local trajectories being associated with the possible destination D of the mobile communication device.
Description
Technical Field
The present application relates to the field of wireless communications. More particularly, the present application relates to a method and system for predicting mobility of a mobile communication device in a spatial area covered by a cellular communication network.
Background
Prediction of user mobility is a major area of research in wireless networks. With the abundance of location-based services in wireless technology, quickly and accurately identifying user mobility patterns is critical to deploying appropriate solutions at both the network and application levels. The accurate prediction of user mobility enables effective planning and management of bandwidth resources, thereby improving the richness of services provided to mobile users, such as mobile online advertising, map adaptation, traffic information, weather forecast, intelligent handover management, and the like. Furthermore, mobility prediction may be used as a root cause for many optimizations in cellular communication networks.
Many algorithms for user mobility prediction have been reported in the literature. In general, existing mobility prediction approaches can be made in one of two series, i.e., on the one hand, based on a model of a first approach that attempts to predict a user's points of interest-e.g., learning a point of interest map and associated probability of transit for each user, and on the other hand, based on a model of a second approach that attempts to predict future short-term mobility based on past short-term observations. As shown in fig. 1, for example, base station a may record the mobility of the user equipment within its coverage area or cell and attempt to determine whether the user equipment has advanced to area B or area C.
Conventional approaches for user mobility prediction are still hampered by several challenging technical problems. The first approach requires a large amount of personal data to be collected from each user, which is subject to privacy concerns and is very expensive to implement. For the second approach, when the user moves along a constrained path (e.g., a road), past short-term observations often do not provide effective information to predict well future mobility. Thus, due to privacy issues, battery limitations of the user equipment, excessive data, etc., it is often difficult to collect enough individual data to make an accurate prediction, and the complexity of making an accurate prediction remains costly.
Therefore, in view of the above, there is a need for more efficient and accurate methods and devices to achieve an improvement in mobility prediction for mobile communication devices in cellular communication networks.
Disclosure of Invention
It is an object of the present application to provide a more efficient and accurate method and apparatus for mobility prediction of a mobile communication device in a cellular communication network.
The foregoing and other objects are achieved by the presently disclosed subject matter. Further embodiments will be apparent from the description and drawings of the disclosure.
In general, the present application provides a cooperative approach between a mobile communication device (such as a mobile phone) and a communication network entity (such as a base station or an application server of a communication network) that overcomes the major architectural and algorithmic obstacles of wireless user mobility prediction. More specifically, the present application intelligently combines two components: a mobile communication device that maintains a user source location and an estimated destination, and a communication network entity that maintains a distribution of local trajectories and their associated source-destination pairs. The two components may exchange information they maintain to determine the most likely future trajectory that the mobile communication device will follow in order to estimate its next location.
According to the present application, only very little specific data is disclosed, since specific data about the mobility of the user is only known to the mobile communication device, and the communication network entity can only remember aggregated data collected from a plurality of mobile communication devices. The mobile communication device may select an accuracy that it is willing to disclose. In addition, the communication network entity may only access local data. In other words, the present application can also function without global data while maintaining data localization. This feature significantly reduces the cost and complexity of processing the data, and calculating the prediction accordingly.
Thus, according to a first aspect, the application relates to a method of predicting mobility of a mobile communication device in a spatial area covered by a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell. The method comprises the following steps: determining location information of the mobile communication device, wherein the location information comprises a current location L of the mobile communication device in a current network cell; providing destination information of the mobile communication device based on a current location L of the mobile communication device, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; and predicting at least a portion of future trajectories of the mobile communication device between the current location L and the possible destination D based on a subset of the set of recorded local trajectories, wherein each trajectory in the subset of the set of recorded local trajectories is associated with the possible destination D of the mobile communication device.
It will be appreciated that the destination likelihood distribution p (D) may define several equally possible destinations D of the mobile communication device. In an implementation form, the possible destination D may be the most likely destination D. The subset of the set of partial tracks of records may be considered a filtered set of partial tracks of records, i.e., the partial tracks of records associated with the possible destination D are selected from the entire set of partial tracks of records. In one embodiment, the association between the recorded partial tracks and the possible destinations may be achieved by marking each recorded partial track with a destination.
Thus, a more efficient and accurate method is provided enabling an improvement in mobility prediction of a mobile communication device in a cellular communication network. The memory requirements of both the mobile communication device and the cellular communication network are reduced because the mobile communication device only needs to store its own points of interest (i.e. the likely destinations it may visit) and in order to be able to provide a prediction of its destination, the cellular communication network only needs to record the local trajectory T of the mobile communication device (and other mobile communication devices) and not its identity information or points of interest. The memory and complexity are greatly reduced since the tracks are only local tracks and not global tracks.
Furthermore, privacy concerns are alleviated because the mobile communication device can adjust the location accuracy that it is willing to provide to trade-off privacy concerns with performance, and the cellular communication network does not need to store identity information of the mobile communication device.
In a first implementation form of the method according to the first aspect, each trajectory of the subset of the recorded set of local trajectories comprises a first portion, wherein the first portion coincides with a global trajectory between the current location L and the possible destination D of the mobile communication device at least within the current network cell.
In a second implementation form of the method according to the first aspect as such or the first implementation form thereof, the location information further comprises a previous location S of the mobile communication device, e.g. an initial source location, and each trajectory of the subset of the set of recorded local trajectories further comprises a second part between the previous location S and a current location L of the mobile communication device.
In a third implementation form of the method according to the first aspect as such or the first or second implementation form thereof, the location information further comprises a past trajectory H of the mobile communication device between a previous location S and the current location L, and each trajectory of the subset of the set of recorded local trajectories further comprises a second portion corresponding to the past trajectory H of the mobile communication device between the previous location S and the current location L of the mobile communication device.
In a fourth implementation form of the method according to the third implementation form of the first aspect, the step of predicting at least a part of a future trajectory T of the mobile communication device between the current location L and the possible destination D based on the subset of the set of recorded local trajectories comprises: a step of determining the following conditional likelihood distributions:
p*(T|H,L,S)＝ΣDp(D)p*(T|H,L,S-D),
wherein, sigmaDRepresents the sum of all possible destinations, wherein the conditional distribution p (T | H, L, S-D) is based on the following equation:
p*(T|H,L,S-D)＝p*(T,H,L,S-D)/ΣTp*(T,H,L,S-D),
where T represents the local track of the record, p (T, H, L, S-D) represents the distribution over the set of local tracks of the record, and ∑ isTRepresenting the sum of all recorded partial tracks.
In a fifth implementation form of the method according to the third or fourth implementation form of the first aspect, the past trajectory H of the mobile communication device is a past trajectory of the mobile communication device in a current network cell of the cellular communication network, i.e. the previous location S is a location where the mobile communication device has entered the current network cell. In another implementation form, the previous location S is the location where the mobile communication device was initially connected to the cellular communication network, i.e. has attached to the cellular communication network.
In a sixth implementation form of the method according to any of the third to fifth implementation forms of the first aspect, the method further comprises the step of: destination information of the mobile communication device is refined based on a past trajectory H between a previous location S and a current location L of the mobile communication device.
Refining the destination information of the mobile communication device may help to more accurately predict the future trajectory T of the mobile communication device, thus providing a better estimate of the most likely destination D, which may serve as a basis for other prediction services.
In a seventh implementation form of the method according to the sixth implementation form of the first aspect, the step of refining the destination information of the mobile communication device comprises the step of determining a refined destination likelihood distribution based on the following equation:
p*(D|H,L,S)＝ΣTp*(T,H,L,S-D)/ΣD,Tp*(T,H,L,S-D),
p(D)←p(D)p*(D|H,L,S)/ΣDp(D)p*(D|H,L,S)
wherein, sigmaDRepresenting the sum of all possible destinations, T representing the local trajectory of the record, sigmaTRepresenting the sum of all recorded local tracks, ΣD,TRepresenting the sum of all possible destinations and all recorded local tracks.
Thus, feedback from the cellular communication network based on the past trajectory H between the previous location S and the current location L of the mobile communication device is provided, improving the accuracy of the prediction of the destination.
In an eighth implementation form of the method according to the first aspect as such or any one of the first to seventh implementation forms thereof, the future trajectory of the mobile communication device between the current location L and the most probable destination D is predicted by selecting a trajectory of the subset of the set of recorded local trajectories between the current location L and the most probable destination D, based on the subset of the set of recorded local trajectories associated with the probable destination, the trajectory of the subset of the set of local trajectories occurring most frequently in the subset of the set of recorded local trajectories.
Thus, the future trajectory T of the mobile communication device can be accurately predicted using cooperative input from the mobile communication device and the cellular communication network, thereby enabling improvements in user services requiring accurate prediction of user mobility.
In a ninth implementation form of the method according to the first aspect as such or any one of the first to eighth implementation forms thereof, the step of providing destination information of the mobile communication device comprises: selecting a likely destination D of the mobile communication device from a set of points of interest associated with the mobile communication device based on a current location L of the mobile communication device; and/or using a set of points of interest associated with the mobile communication device to determine the destination likelihood distribution p (D) based on the current location L of the mobile communication device.
In a tenth implementation form of the method according to the first aspect as such or any of the first to ninth implementation forms thereof, the method further comprises the step of providing context information associated with the mobile communication device, and wherein the step of predicting at least a part of the future trajectory of the mobile communication device comprises: based on the subset of the recorded set of local trajectories and on the context information, at least a portion of future trajectories of the mobile communication device between the current location L and the possible destination D are predicted. In an implementation form, the context information may include information about the current transmission means of the mobile communication device and/or a user profile associated with the mobile communication device.
Therefore, the context information of the mobile communication device will benefit the cellular communication network to a large extent to improve the accuracy of the prediction of the future trajectory T of the mobile communication device.
According to a second aspect, the application relates to a mobile communication device for communication in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, wherein the mobile communication device comprises: a communication interface for communicating with a communication network entity of a cellular communication network; and a processor for: providing destination information for the mobile communication device based on a current location L of the mobile communication device and/or a previous location S of the mobile communication device in a current network cell, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; providing destination information to a communication network entity through a communication interface; and refining the destination information of the mobile communication device based on refined destination information provided by the communication network entity over the communication interface, wherein the refined destination information comprises at least a part of a future trajectory of the mobile communication device between the current location L and the possible destination D, refined at least one possible destination D of the mobile communication device, and/or refined destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device.
Accordingly, the mobile communication device may provide the source information and the destination information to the communication network entity, thereby improving the accuracy of the prediction of the future mobility of the mobile communication device.
According to a third aspect, the application relates to a communication network entity for predicting mobility of a mobile communication device in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, wherein the communication network entity comprises: a communication interface for receiving destination information from a mobile communication device, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; a memory for storing a recorded set of local tracks; a processor for determining location information of the mobile communication device, wherein the location information comprises a current location L of the mobile communication device in a current network cell, and predicting at least a portion of future trajectories of the mobile communication device between the current location L and a possible destination D based on a subset of the set of recorded local trajectories, wherein each trajectory in the subset of the set of recorded local trajectories is associated with a possible destination D of the mobile communication device.
Accordingly, the communication network entity may receive source information and destination information from the mobile communication device, thereby improving the accuracy of the prediction of future mobility of the mobile communication device. In one implementation form, the communication network entity is a base station or an application server of a cellular communication network.
In a first implementation form of the communication network entity according to the third aspect, each trajectory of the subset of the recorded set of local trajectories comprises a first portion, wherein the first portion coincides with a global trajectory between the current location L and the possible destination D of the mobile communication device at least within the current network cell.
In a second implementation form of the communication network entity according to the third aspect as such or the first implementation form thereof, the location information further comprises a previous location S of the mobile communication device, e.g. an initial source location, and each trajectory of the subset of the set of recorded local trajectories further comprises a second part between the previous location S and the current location L of the mobile communication device.
In a third implementation form of the communication network entity according to the third aspect as such or the first or second implementation form thereof, the location information further comprises a past trajectory H of the mobile communication device between a previous location S and the current location L, and each trajectory of the subset of the set of recorded local trajectories further comprises a second portion corresponding to the past trajectory H of the mobile communication device between the previous location S and the current location L of the mobile communication device.
In a fourth implementation form of the communication network entity according to the third aspect as such or in any of the first to third implementation forms thereof, the processor is further configured to determine a refined estimate of the likely destination D of the mobile communication device and to feed back the refined estimate of the most likely destination D to the mobile communication device via the communication interface and/or the processor is further configured to determine a refined destination likelihood distribution p (D) and to feed back the refined destination likelihood distribution p (D) to the mobile communication device.
Thus, the communication network entity may also benefit by providing the mobile communication device with a refined possible destination D and/or a refined destination likelihood distribution p (D).
In a fifth implementation form of the communication network entity according to the third aspect as such or any of the first to fourth implementation forms thereof, the memory is configured to store each local trajectory of the set of recorded local trajectories and its associated most likely destination D. In other implementations, the memory may store, for example, the source S and/or some other contextual information in addition to the most likely destination D associated with the local trajectory.
According to a fourth aspect, the present application relates to a computer program comprising program code for performing the method according to the first aspect or any one of its implementation forms when executed on a computer.
The present application may be implemented in hardware and/or software.
Drawings
Other embodiments of the present application will be described with reference to the following drawings, in which:
fig. 1 shows a schematic diagram of a cellular communication network illustrating the basic concept of predicting the mobility of a mobile communication device by a base station;
fig. 2 shows a schematic diagram of a communication network comprising a mobile communication device and a communication network entity according to an embodiment.
Fig. 3 shows a schematic diagram of the mobile communication device and the communication network entities of fig. 2 in a first communication phase;
fig. 4 shows a schematic diagram of the mobile communication device and the communication network entities of fig. 2 in a second communication phase;
figure 5 shows a schematic diagram of the interaction between a mobile communication device and a communication network entity according to an embodiment for predicting the mobility of the mobile communication device;
fig. 6 shows a schematic diagram of a method of predicting mobility of a mobile communication device in a cellular communication network according to an embodiment;
fig. 7 shows simulation results of a mobile communication device and a communication network entity according to an embodiment; and
fig. 8 shows simulation results of a mobile communication device and a communication network entity according to an embodiment.
In the various figures, the same reference numerals will be used for identical or at least functionally equivalent features.
Detailed Description
In the following description, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration specific aspects in which the disclosure may be practiced. It is to be understood that other aspects may be utilized and structural or logical changes may be made without departing from the scope of the present application. The following detailed description is, therefore, not to be taken in a limiting sense.
For example, it should be understood that the disclosure in connection with the described method also applies to the corresponding device or system for performing the method, and vice versa. For example, if a particular method step is described, the respective device may comprise means for performing the described method step, even if such means are not explicitly described or shown in the figures.
Furthermore, in the following detailed description, embodiments are described having different functional blocks or processing units, which are connected to or exchange signals with each other. It is to be understood that the present application also covers embodiments comprising additional functional blocks or processing units arranged between the functional blocks or processing units of the embodiments described below.
Finally, it is to be understood that features of the various exemplary aspects described herein may be combined with each other, unless specifically noted otherwise.
Fig. 2 shows a schematic diagram of a cellular communication network 200 comprising a mobile communication device 201 and a communication network entity 202 according to an embodiment. The cellular communication network 200 includes a plurality of network cells, including the network cell in which the mobile communication device 201 is currently located (referred to herein as the current network cell).
The mobile communication device 201 is for cellular communication with a communication network entity 202 of the cellular communication network 200.
As can be seen from the detailed view of the mobile communication device 201 shown in fig. 2, the mobile communication device 201 comprises a communication interface 201a and a processor 201 b. The processor 201b is configured to provide the communication network entity 202 with destination information of the mobile communication device 201 based on the current location L of the mobile communication device 201 in the current network cell. The destination information may include one or more possible destinations D of the mobile communication device 201 and/or a destination likelihood distribution p (D) defining one or more possible destinations D of the mobile communication device 201.
It will be appreciated that the destination likelihood distribution p (D) may define several equally possible destinations D of the mobile communication device 201. In one embodiment, the possible destination D may be the most likely destination D of the mobile communication device 201.
In one embodiment, the processor 201b of the mobile communication device 201 is configured to provide the destination information by: selecting a possible destination D of the mobile communication device 201 from a set of points of interest stored in the mobile communication device 201 based on the current location L of the mobile communication device 201; alternatively, the destination likelihood distribution p (D) is determined using a set of points of interest stored in the mobile communication device 201 based on the current location L of the mobile communication device 201.
The communication network entity 202 is used for predicting mobility, i.e. future trajectories of the mobile communication device 201 in the cellular communication network 200. In one embodiment, the communication network entity 202 is implemented as a base station or a part thereof or as an application server of the cellular communication network 200.
The communication network entity 202 comprises a communication interface 202a for receiving destination information from the mobile communication device 201. Furthermore, the communication network entity 202 comprises a memory 202c for storing a set of recorded local tracks T, which will be explained in further detail below. Finally, the communication network entity 202 comprises a processor 202b for determining location information of the mobile communication device 201, wherein the location information comprises a current location L of the mobile communication device 201 in a current network cell.
Further, the processor 202b of the communication network entity 202 is configured to predict at least a portion of future trajectories of the mobile communication device 201 between the current location L and the possible destination D based on a subset of the set of recorded local trajectories T, wherein each trajectory of the subset of the set of recorded local trajectories is associated with the possible destination D of the mobile communication device 201.
A subset of the set of recorded local tracks T may be considered as a filtered set of recorded local tracks T, i.e. the recorded local tracks associated with the possible destination D of the mobile communication device 201 are selected from the entire set of recorded local tracks T. The association between the recorded partial tracks and the possible destinations D may be carried out in advance, for example, by marking each recorded partial track with its destination.
Each track in the recorded set of local tracks T may define a series of geographical locations/positions, possibly with associated timing information. Different levels of accuracy may be provided for the geographic location/position, or the geographic location/position may be area-based (e.g., road segments, cells of the network).
In one embodiment, the recorded set of local tracks T may be generated in the following manner. In the first stage, the user's points of interest, i.e. the locations where the user spends a lot of time, are identified. In the second phase, the trajectories are segmented such that they begin or end at the identified point of interest. In the third stage, the trajectory is marked by the destination D, and possibly by its source S. In a fourth stage, the trajectory is segmented again according to the area covered by the communication network entity 202 and recorded in the memory 202c of the communication network entity 202.
In a further embodiment, the recorded set of local tracks T may be generated in the following manner. Each time the communication network entity 202 observes a new local trajectory of the mobile communication device, the trajectory is marked with source information S and temporarily lacks destination information D. When the mobile communication device reaches its destination D (which the mobile communication device itself may identify, either by the device or by a communication network entity, i.e. the base station serving the current cell of the mobile communication device), information about the destination D is sent to the base station along the past trajectory of the mobile communication device. These base stations can now also update the destination tag D and incorporate the local trajectory into the database of recorded local trajectories of the base stations.
In a further embodiment, the recorded set of local tracks T may be generated in the following manner. Each time the communication network entity 202 observes a new trajectory for the mobile communication device, it is marked with the source information S and previous destination predictions available from the mobile communication device before the mobile communication device leaves the cell. In this embodiment, some trajectories may be incorrectly marked due to inaccurate prediction of the destination D. However, this improves as the mobile communication device proceeds towards the destination D, as the estimate of the destination D is refined.
In one embodiment, each trajectory in the subset of the recorded set of local trajectories comprises a first portion, wherein the first portion coincides with a global trajectory between the current location L and the possible destination D of the mobile communication device 201 at least within the current network cell.
In one embodiment, the location information further comprises a previous location S of the mobile communication device 201, e.g. an initial source location, and each track of the subset of the set of recorded local tracks further comprises a second part between the previous location S and the current location L of the mobile communication device 201.
In one embodiment, the location information further includes a past trajectory H of the mobile communication device 201 between the previous location S and the current location L, and each trajectory in the subset of the set of recorded local trajectories further includes a second portion corresponding to the past trajectory H of the mobile communication device 201 between the previous location S and the current location L of the mobile communication device 201.
In one embodiment, the processor 202b of the communication network entity 202 is configured to predict a future trajectory of the mobile communication device 201 between the current location L and the possible destination D by selecting a trajectory of the subset of the set of recorded local trajectories T associated with the possible destination D that most commonly occurs in the subset of the set of recorded local trajectories associated with the possible destination D based on the subset of the set of recorded local trajectories T associated with the possible destination D.
In one embodiment, the processor 202b of the communication network entity 202 is further configured to determine a refined estimate of the possible destination D of the mobile communication device 201 and to feed back the refined estimate of the possible destination D to the mobile communication device 201 via the communication interface 202 a. Additionally or alternatively, the processor 202b of the communication network entity 202 is further configured to determine a refined destination likelihood distribution p (D) and to feed back the refined destination likelihood distribution p (D) to the mobile communication device 201 via the communication interface 202 a.
In one embodiment, the processor 201b of the mobile communication device 201 is configured to refine its destination information based on refined destination information provided by the communication network entity 202 through the communication interface 201 a. The refined destination information includes at least a portion of the future trajectory of the mobile communication device 201 between the current location L and the possible destination D, at least one refined possible destination D of the mobile communication device 201, and/or a refined destination likelihood distribution p (D) that defines at least one possible destination D of the mobile communication device 201.
Further embodiments of the mobile communication device 201 and the network communication entity 202 are shown in fig. 3 to 5. In fig. 3, the mobile communication device 201 provides the network communication entity 202 with the destination information, and in fig. 4, the network communication entity 202 provides the mobile communication device 201 with information for refining the destination information.
Fig. 5 shows a schematic diagram of an interaction procedure 500 between a mobile communication device 201 and a communication network entity 202 according to an embodiment.
The first part of the process 500 comprises the step of updating the communication network entity 202 in the cellular communication network 200 with information from the mobile communication device 201 when the mobile communication device 201 moves to a network cell covered by the communication network entity 202, i.e. the current network cell.
In step 501, the communication network entity 202 sends a request to the mobile communication device 201 for destination information and context information, wherein the destination information comprises the source S and destination likelihood distribution p (D) of the journey of the mobile communication device 201.
In step 503 the mobile communication device 201 provides destination information to the communication network entity 202, wherein the destination information comprises the source S and the destination likelihood distribution p (D) of the journey of the mobile communication device 201.
In step 505, the communication network entity 202 computes a bayesian posterior estimate under the assumption that the destination likelihood distribution p (D) is correct, andadding a weight p (D) to a current count Σ of a past trajectory H of the mobile communication device 201 in a context including a current location L, source information S, and a destination likelihood distribution p (D) of the mobile communication device 201Tp (T, H, L, S-D). Furthermore, once the mobile communication device 201 has moved and has observed a future local trajectory T, the communication network entity 202 adds a weight p (D) to the current count p (T, H, L, S-D).
The second part of the process 500 comprises the step of updating the mobile communication device 201 with data determined by the communication network entity 202. These steps may be triggered by the mobile communication device 201 requesting feedback from the communication network entity 202. Such a feedback request may be included in the transmission of the destination in step 503.
In response to the feedback request of the mobile communication device 201, the communication network entity 202 calculates a refined destination likelihood distribution based on the following equation:
p*(D|H,L,S)＝ΣTp*(T,H,L,S-D)/ΣD,Tp*(T,H,L,S-D),
whereinTRepresents the sum of all recorded traces, p × (T, H, L, S-D) represents the distribution over the set of recorded traces T between the current location L of the mobile communication device 201 and the possible destination D, and ΣD,TRepresenting the sum of all destinations and all recorded tracks.
In step 507, the communication network entity 202 sends the refined destination likelihood distribution p x (D | H, L, S) to the mobile communication device 201, wherein the refined destination likelihood distribution may be combined by the mobile communication device 201 with the destination likelihood distribution p (D), or the communication network entity 202 directly sends the combination of the refined destination likelihood distribution and the destination likelihood distribution p (D) to the mobile communication device 201.
In step 509, the destination likelihood distribution p (D) may be updated by the following equation:
p(D)←p(D)p*(D|H,L,S)/ΣDp(D)p*(D|H,L,S),
wherein, sigmaDRepresenting the sum of all destinations.
Fig. 6 shows a schematic diagram of a method 600 of predicting mobility of a mobile communication device, such as the mobile communication device 201 shown in fig. 2, in a spatial area covered by the cellular communication network 200.
The method 600 includes the steps of: 601, determining location information of the mobile communication device 201, wherein the location information includes a current location L of the mobile communication device 201 in a current network cell; 603 providing destination information of the mobile communication device 201 based on the current location L of the mobile communication device 201, wherein the destination information comprises at least one possible destination D of the mobile communication device 201 and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device 201; and 605 predicting at least a portion of future trajectories of the mobile communication device 201 between the current location L and the possible destination D based on a subset of the set of recorded local trajectories T, wherein each trajectory in the subset of the set of recorded local trajectories is associated with the possible destination D of the mobile communication device 201.
Fig. 7 shows a schematic illustration of simulation results of the mobile communication device 201, the communication network entity 202 and the method 600 according to an embodiment of the randomly generated based network 700. In the randomly generated network 700, the nodes represent different cells of the cellular communication network 200 and the edges represent possible handover trajectories between neighboring cells. It is assumed that each node has its own communication network entity 202 and can predict which edge (i.e. possible transition trajectory of the mobile communication device 201 between the source location S and the possible destination D) the mobile communication device 201 will follow to leave the node.
Mobility procedures for one thousand mobile communication devices 201 have been generated in a randomly generated network 700, where each mobile communication device 201 has a set of ten possible destinations (i.e. points of interest), moving from one to another according to some simple mobility procedure (e.g. a first order markov model), and where each mobile communication device 201 may take a different trajectory (i.e. a different sequence of edges) for reasons of non-clarity (e.g. different congestion on the road), but in general short routes are preferred over long routes. Such a randomly generated network 700 is considered to be a reasonable modeling of mobility procedures of the mobile communication device 201 in a cellular communication network in order to evaluate the performance of embodiments of the present application.
In the randomly generated network 700 shown in fig. 7, the eight-fold trajectory that the mobile communication device 201 takes between a particular source location S and a possible destination D is represented by a thick black line.
Fig. 8 shows a diagram illustrating the performance of different embodiments of the present application compared to the prior art approach to mobility prediction in the randomly generated network 700 of fig. 7. Mobility procedures for one thousand mobile communication devices 201 have been generated in a randomly generated network 700, where each mobile communication device 201 has a set of ten possible destinations (i.e. points of interest), moving from one to another according to some simple mobility procedure (e.g. a first order markov model), and where each mobile communication device 201 may take a different trajectory (i.e. a different sequence of edges) for reasons of non-clarity (e.g. different congestion on the road), but in general short routes are preferred over long routes.
As can be seen from the detailed view in fig. 8, the dashed lines represent the existing manner of mobility prediction, and the solid lines 801a and 801b represent the performance of the embodiments of the present application. More specifically, the mobility procedure is not decomposed and coordinated between the mobile communication device 201 and the communication network entity 202 in the existing approach, which provides a lower score for correct prediction than provided by embodiments of the present application, as the existing approach cannot handle too many different possible trajectories that the mobile communication device 201 may follow.
A suitable way of mobility prediction should know when data from multiple mobile communication devices 201, such as source information S, destination likelihood distribution p (D) or any other relevant context, should be aggregated and when not to use statistical benefits for mobility prediction. Existing mobility prediction approaches typically do not aggregate data (or aggregate insufficient data) at all from multiple mobile communication devices 201, and therefore they will require a very long training period before they know all the possible trajectories that the mobile communication device 201 may follow, or they would gather too much data in previous studies, which would compromise the accuracy of the prediction.
As can be seen from fig. 8, the score of correct prediction rises as more trajectories are observed, as the mobile communication device 201 and the communication network entity 202 can aggregate data of mobility procedures, thereby improving the accuracy of the prediction of future mobility of the mobile communication device 201.
While a particular feature or aspect of the disclosure may have been disclosed with respect to only one of several implementations or embodiments, such feature or aspect may be combined with one or more other features or aspects of the other implementations or embodiments as may be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms "includes," has, "" having, "or other variations are used in the detailed description, such terms are intended to be inclusive in a manner similar to the term" comprising. Furthermore, the terms "exemplary," "e.g.," and "such as" are merely examples, and are not preferred or optimal. The terms "coupled" and "connected," along with derivatives, may be used. It should be understood that these terms may be used to indicate that two elements co-operate or interact with each other, whether or not they are in direct physical or electrical contact, or they are not in direct contact with each other.
Although specific aspects have been illustrated and described herein, it will be appreciated by those of ordinary skill in the art that a variety of alternate and/or equivalent implementations may be substituted for the specific aspects shown and described without departing from the scope of the present disclosure. This application is intended to cover any adaptations or variations of the specific aspects discussed herein.
Although elements in the present disclosure are listed in a particular order with corresponding labeling, unless a particular order for implementing some or all of the elements is otherwise implied by the disclosure recitations, the elements are not necessarily intended to be limited to being implemented in that particular order.
Many alternatives, modifications, and variations will be apparent to those skilled in the art in light of the above teachings. Of course, one skilled in the art will readily recognize that there are many applications for this application other than those described herein. While the present application has been described with reference to one or more particular embodiments, those skilled in the art will recognize that many changes may be made thereto without departing from the scope of the present application. It is therefore to be understood that within the scope of the present disclosure and its equivalents, the present application may be practiced otherwise than as specifically described herein.
Claims (19)
1. A method for predicting mobility of a mobile communication device in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, the method comprising:
determining location information of the mobile communication device, wherein the location information comprises a current location L of the mobile communication device in the current network cell;
providing destination information of the mobile communication device to a communication network entity based on the current location L of the mobile communication device, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; and
predicting, by the communication network entity, at least a portion of future trajectories of the mobile communication device between the current location L and the possible destination D based on a subset of a set of recorded local trajectories, wherein each trajectory in the subset of the set of recorded local trajectories is associated with the possible destination D of the mobile communication device.
2. The method of claim 1, wherein each trajectory in the subset of the recorded set of local trajectories comprises a first portion, wherein the first portion coincides with a global trajectory between the current location L and the possible destination D of the mobile communication device at least within the current network cell.
3. The method according to claim 1 or 2, wherein the location information further comprises a previous location S of the mobile communication device, and each track of the subset of the recorded set of local tracks further comprises a second part between the previous location S and the current location L.
4. The method according to claim 1 or 2, wherein the location information further comprises a past trajectory H of the mobile communication device between a previous location S and the current location L of the mobile communication device, and each trajectory in the subset of the recorded set of local trajectories further comprises a second portion corresponding to the past trajectory H of the mobile communication device between the previous location S and the current location L of the mobile communication device.
5. The method of claim 4, wherein the step of predicting at least a portion of a future trajectory of the mobile communication device between the current location L and the possible destination D based on a subset of the recorded set of local trajectories comprises: a step of determining the following conditional likelihood distributions:
p*(T|H,L,S)＝ΣDp(D)p*(T|H,L,S-D),
wherein, sigmaDRepresents the sum of all possible destinations, wherein the conditional distribution p (T | H, L, S-D) is based on the following equation:
p*(T|H,L,S-D)＝p*(T,H,L,S-D)/ΣTp*(T,H,L,S-D),
wherein T represents a local track of a record, p (T, H, L, S-D) represents a distribution over a set of local tracks of the record, and ∑ isTRepresenting the sum of all recorded partial tracks.
6. The method of claim 4, wherein the past trajectory H of the mobile communication device is the past trajectory of the mobile communication device in the current network cell of the cellular communication network.
7. The method according to claim 4, characterized in that the method further comprises the step of: refining the destination information of the mobile communication device based on the past trajectory H between the previous location S and the current location L of the mobile communication device.
8. The method of claim 7, wherein the step of refining the destination information of the mobile communication device comprises the step of determining a refined destination likelihood distribution based on the equation:
p*(D|H,L,S)＝ΣTp*(T,H,L,S-D)/ΣD,Tp*(T,H,L,S-D),
p(D)←p(D)p*(D|H,L,S)/ΣDp(D)p*(D|H,L,S)
wherein, sigmaDRepresenting the sum of all possible destinations, T representing the local trajectory of the record, sigmaTRepresenting the sum of all recorded local tracks, ΣD,TRepresenting the sum of all possible destinations and all recorded local tracks.
9. Method according to claim 1 or 2, characterized in that a future trajectory of the mobile communication device between the current location L and the possible destination D is predicted by selecting a trajectory of the subset of the set of recorded local trajectories based on the subset of the set of recorded local trajectories associated with the possible destination D, the trajectory of the subset of the set of local trajectories occurring most frequently in the subset of the set of recorded local trajectories.
10. The method of claim 1 or 2, wherein the step of providing destination information of the mobile communication device comprises:
selecting the likely destination D of the mobile communication device from a set of points of interest associated with the mobile communication device based on the current location L of the mobile communication device; and/or the presence of a gas in the gas,
determining the destination likelihood distribution p (D) using a set of points of interest associated with the mobile communication device based on the current location L of the mobile communication device.
11. The method of claim 1 or 2, wherein the method further comprises the step of providing context information associated with the mobile communication device, and wherein the step of predicting at least a portion of the future trajectory of the mobile communication device comprises: predicting at least a portion of the future trajectory of the mobile communication device between the current location L and the possible destination D based on a subset of the recorded set of local trajectories and based on the contextual information.
12. A mobile communication device for communicating in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, wherein the mobile communication device comprises:
a communication interface for communicating with a communication network entity of the cellular communication network; and
a processor to:
providing destination information for the mobile communication device based on a current location L of the mobile communication device and/or a previous location S of the mobile communication device in the current network cell, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device; providing the destination information to the communication network entity through the communication interface; and
refining the destination information of the mobile communication device based on refined destination information provided by the communication network entity through the communication interface, wherein the refined destination information comprises at least a part of the future trajectory of the mobile communication device between the current location L and the possible destination D, refined at least one possible destination D of the mobile communication device and/or refined destination likelihood distribution p (D) defining at least one possible destination D of the mobile communication device.
13. A communication network entity for predicting mobility of a mobile communication device in a cellular communication network, the cellular communication network comprising a plurality of network cells including a current network cell, wherein the communication network entity comprises:
a communication interface for receiving destination information from the mobile communication device, wherein the destination information comprises at least one possible destination D of the mobile communication device and/or a destination likelihood distribution p (D) defining the at least one possible destination D of the mobile communication device;
a memory for storing a recorded set of local tracks;
a processor configured to determine location information of the mobile communication device, wherein the location information comprises a current location L of the mobile communication device in the current network cell; and predicting at least a portion of future trajectories of the mobile communication device between the current location L and the possible destination D based on a subset of the recorded set of local trajectories, wherein each trajectory in the subset of the recorded set of local trajectories is associated with the possible destination of the mobile communication device.
14. The communication network entity according to claim 13, wherein each trajectory of the subset of the recorded set of local trajectories comprises a first portion, wherein the first portion coincides with a global trajectory between the current location L and the possible destination D of the mobile communication device at least within the current network cell.
15. The communication network entity according to claim 13 or 14, wherein the location information further comprises a previous location S of the mobile communication device and each trajectory in the subset of the recorded set of local trajectories further comprises a second part between the previous location S and the current location L of the mobile communication device.
16. The communication network entity according to claim 13 or 14, wherein the location information further comprises a past trajectory H of the mobile communication device between a previous location S and the current location L of the mobile communication device, and wherein each trajectory of the subset of the recorded set of local trajectories further comprises a second portion corresponding to the past trajectory H of the mobile communication device between the previous location S and the current location L of the mobile communication device.
17. The communication network entity according to claim 13 or 14, wherein the processor is further configured to determine a refined estimate of the possible destination D of the mobile communication device and to feed back the refined estimate of the possible destination D to the mobile communication device via the communication interface, and/or wherein the processor is further configured to determine a refined destination likelihood distribution p (D) and to feed back the refined destination likelihood distribution p (D) to the mobile communication device via the communication interface.
18. The communication network entity according to claim 13 or 14, wherein the memory is configured to store each local trajectory of the recorded set of local trajectories and a possible destination D associated therewith.
19. A computer-readable storage medium storing a computer program for performing the method of any one of claims 1 to 11.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/EP2016/082387 WO2018113974A1 (en) | 2016-12-22 | 2016-12-22 | Method and devices for predicting mobility of a mobile communication device in a cellular communication network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110121891A CN110121891A (en) | 2019-08-13 |
| CN110121891B true CN110121891B (en) | 2020-06-02 |
Family
ID=57796311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201680091839.8A Active CN110121891B (en) | 2016-12-22 | 2016-12-22 | Method and apparatus for predicting mobility of a mobile communication device in a cellular communication network |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110121891B (en) |
| WO (1) | WO2018113974A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3876559A1 (en) | 2020-03-02 | 2021-09-08 | Nokia Technologies Oy | Future position estimation for improved reliability of connectivity |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008053208A1 (en) * | 2006-10-31 | 2008-05-08 | Trisent Communications Ltd | Location detection |
| CN101635941A (en) * | 2009-07-24 | 2010-01-27 | 南京邮电大学 | Target tracking method based on master/slaver mobile agent in wireless sensor network |
| CN102209294A (en) * | 2010-03-31 | 2011-10-05 | 索尼公司 | Information processing apparatus, behavior prediction display method, and computer program therefor |
| CN105432107A (en) * | 2013-09-17 | 2016-03-23 | 华为技术有限公司 | Method and device in a wireless communication network |
| EP3035255A1 (en) * | 2014-12-19 | 2016-06-22 | HERE Global B.V. | Method and apparatus for providing context-related point-of-interest recommendations |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7355528B2 (en) * | 2003-10-16 | 2008-04-08 | Hitachi, Ltd. | Traffic information providing system and car navigation system |
| US8024112B2 (en) * | 2005-09-29 | 2011-09-20 | Microsoft Corporation | Methods for predicting destinations from partial trajectories employing open-and closed-world modeling methods |
| KR20120094229A (en) * | 2011-02-16 | 2012-08-24 | 삼성전자주식회사 | Apparatus and method for performing cell reselection in portable terminal |
| US9131508B2 (en) * | 2014-01-02 | 2015-09-08 | Qualcomm Incorporated | Dynamic resource adjustment for establishing and maintaining a call of interest |
-
2016
- 2016-12-22 CN CN201680091839.8A patent/CN110121891B/en active Active
- 2016-12-22 WO PCT/EP2016/082387 patent/WO2018113974A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008053208A1 (en) * | 2006-10-31 | 2008-05-08 | Trisent Communications Ltd | Location detection |
| CN101635941A (en) * | 2009-07-24 | 2010-01-27 | 南京邮电大学 | Target tracking method based on master/slaver mobile agent in wireless sensor network |
| CN102209294A (en) * | 2010-03-31 | 2011-10-05 | 索尼公司 | Information processing apparatus, behavior prediction display method, and computer program therefor |
| CN105432107A (en) * | 2013-09-17 | 2016-03-23 | 华为技术有限公司 | Method and device in a wireless communication network |
| EP3035255A1 (en) * | 2014-12-19 | 2016-06-22 | HERE Global B.V. | Method and apparatus for providing context-related point-of-interest recommendations |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018113974A1 (en) | 2018-06-28 |
| CN110121891A (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Mobility prediction: A survey on state-of-the-art schemes and future applications | |
| US8559976B2 (en) | System and method for population tracking, counting, and movement estimation using mobile operational data and/or geographic information in mobile network | |
| Qiao et al. | A hybrid Markov-based model for human mobility prediction | |
| Scellato et al. | Nextplace: a spatio-temporal prediction framework for pervasive systems | |
| CN107018493B (en) | Geographic position prediction method based on continuous time sequence Markov model | |
| CN110213724B (en) | Pseudo base station motion trajectory identification method | |
| CN105704657B (en) | Monitor the method and device of mobile terminal locations | |
| CN109688532B (en) | Method and device for dividing city functional area | |
| US9843920B2 (en) | Monitoring transport systems network traffic using mobile communications network usage records | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| Anagnostopoulos et al. | Intelligent trajectory classification for improved movement prediction | |
| CN116758744A (en) | Smart city operation and maintenance management method, system and storage medium based on artificial intelligence | |
| Holleczek et al. | Traffic measurement and route recommendation system for mass rapid transit (mrt) | |
| Moysen et al. | Learning-based tracking area list management in 4g and 5g networks | |
| Leca et al. | Significant location detection & prediction in cellular networks using artificial neural networks | |
| Amirat et al. | Nextroute: a lossless model for accurate mobility prediction | |
| Amirat et al. | MyRoute: A Graph-Dependency Based Model for Real-Time Route Prediction. | |
| CN110121891B (en) | Method and apparatus for predicting mobility of a mobile communication device in a cellular communication network | |
| EP3073460A1 (en) | Predicting the trajectory of mobile users | |
| US20230007501A1 (en) | Geospatial-based forecasting for access point deployments | |
| CN111050398B (en) | Paging method, paging device, paging equipment and storage medium | |
| Hasbollah et al. | Mobility prediction method for vehicular network using Markov chain | |
| CN110895588B (en) | Data processing method and equipment | |
| CN102158872B (en) | Method and device for replanning TA (Tracking Area) | |
| Liu et al. | Similar user assisted mobility prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211223 Address after: 450046 Floor 9, building 1, Zhengshang Boya Plaza, Longzihu wisdom Island, Zhengdong New Area, Zhengzhou City, Henan Province Patentee after: Super fusion Digital Technology Co.,Ltd. Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Patentee before: HUAWEI TECHNOLOGIES Co.,Ltd. |