CN116266946A - A method, device and equipment for determining the location of a base station - Google Patents

Abstract

The invention discloses a method, a device and equipment for determining the position of a base station, wherein the method for determining the position of the base station comprises the following steps: acquiring position sequence information of at least one mobile terminal; inputting the position sequence information of the at least one mobile terminal into a preset position prediction model for prediction processing to obtain a predicted position of the at least one mobile terminal; clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result; and determining the address of the base station according to the clustering result. By the method, the position of the mobile terminal can be rapidly predicted, the change trend of the number of the regional mobile terminals is known, cluster analysis is carried out by combining the prediction result, the site selection is carried out according to the requirement, and the site selection accuracy of the base station is improved.

Description

A method, device and equipment for determining the location of a base station

technical field

The present invention relates to the field of communication technology, in particular to a method, device and equipment for determining the location of a base station.

Background technique

In the prior art, the location of the base station is often selected after the large-scale event is over, according to the gathering of a large number of user terminals, the site of the base station is selected on site, and the specific configuration of the base station can only be determined by the estimated number of engineers, and the base station The locations tend to be evenly distributed.

In the existing technology, the base station site selection scheme often starts the site selection work after the high load problem occurs, and the processing efficiency is low; the manual site selection is generally uniformly distributed according to the default configuration, and the location of the base station and the location of the base station cannot be determined according to the flow of people. Configuration adjustment; a large number of personnel are required to participate, and there may still be gaps in emergency support points, which require a lot of manpower and material resources.

Contents of the invention

In view of the above problems, embodiments of the present invention are proposed in order to provide a method, device, and equipment for determining the location of a base station that overcome the above problems or at least partially solve the above problems.

According to an aspect of an embodiment of the present invention, a method for determining a base station location is provided, the method comprising:

Acquiring location sequence information of at least one mobile terminal;

Inputting the location sequence information of the at least one mobile terminal into a preset location prediction model for prediction processing to obtain a predicted location of at least one mobile terminal;

clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

According to the clustering result, determine the address to establish the base station.

According to another aspect of the embodiments of the present invention, a device for determining a base station location is provided, the device comprising:

An acquisition module, configured to acquire location sequence information of at least one mobile terminal;

A prediction module, configured to input the location sequence information of the at least one mobile terminal into a preset location prediction model for prediction processing, to obtain a predicted location of at least one mobile terminal;

A clustering module, configured to cluster the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

A determining module, configured to determine the address of the established base station according to the clustering result.

According to still another aspect of the embodiments of the present invention, a computing device is provided, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete the mutual communication via the communication bus. communication between

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the method for determining the location of the base station.

According to still another aspect of the embodiments of the present invention, a computer storage medium is provided, and at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to perform operations corresponding to the method for determining the position of the base station described above. .

According to the solution provided by the above-mentioned embodiments of the present invention, by obtaining the position sequence information of at least one mobile terminal; inputting the position sequence information of the at least one mobile terminal into a preset position prediction model for prediction processing, the prediction of at least one mobile terminal is obtained location: according to the predicted location of the at least one mobile terminal, cluster the mobile terminals to obtain a clustering result; according to the clustering result, determine the address of the base station. In this way, it is possible to quickly predict the location of mobile terminals, understand the changing trend of the number of mobile terminals in the region, perform cluster analysis based on the prediction results, and select sites on demand, which improves the accuracy of base station site selection.

The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and The advantages can be more obvious and understandable, and the specific implementation manners of the embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered as limiting the embodiments of the present invention. Also throughout the drawings, the same reference numerals are used to designate the same parts. In the attached picture:

FIG. 1 shows a flowchart of a method for determining a base station location provided by an embodiment of the present invention;

FIG. 2 shows a flow chart of a specific implementation method of a method for determining the location of a base station provided by another embodiment of the present invention;

FIG. 3 shows a schematic diagram of a preset position prediction model in an embodiment of the present invention;

Fig. 4 shows a schematic diagram of the effect of predicting the mobile position of the terminal by the preset position prediction model in the embodiment of the present invention;

FIG. 5 shows a schematic structural diagram of an apparatus for determining a base station location in an embodiment of the present invention;

Fig. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

FIG. 1 shows a flowchart of a method for determining a base station location provided by an embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

Step 11, obtain the position sequence information of at least one mobile terminal; here, the position sequence information of the mobile terminal, for example, may be a sequence composed of state variables s _ij , s _ij =(u _i , l _ij , t _ij , d); where , u _i represents the identity of user i; l _ij represents the location of user i at time j; t _ij represents the time stamp when user i arrives at this location l _ij , d represents the stay time of user i at location l _ij , the The elements in the sequence are sorted by timestamp;

Step 12, input the position sequence information of the at least one mobile terminal into the preset position prediction model for prediction processing, and obtain the predicted position of at least one mobile terminal; here, the preset position prediction model is based on the track data of the historical mobile terminal Obtained by training, it has a better prediction effect on the predicted position of the terminal;

Step 13, clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

Step 14, according to the clustering result, determine the address of the established base station.

In this embodiment of the present invention, the predicted position of at least one mobile terminal is obtained by inputting the position sequence information of the at least one mobile terminal into the preset position prediction model for prediction processing; according to the predicted position of the at least one mobile terminal , clustering the mobile terminals to obtain a clustering result; according to the clustering result, determine the address of the base station; thereby the location of the mobile terminal can be quickly predicted, the trend of the number of mobile terminals in the region can be understood, and cluster analysis is performed in combination with the prediction results, On-demand site selection improves the accuracy of base station site selection.

In an optional embodiment of the present invention, the preset position prediction model is trained through the following process:

Step 21, obtaining a training set including movement trajectory data of multiple terminals;

Step 22, inputting the moving trajectory data into the target model for processing to obtain at least one hidden state and at least one observed state;

Step 23, obtaining the probability matrix in the hidden state, the transition state matrix of the terminal between the hidden states, and the transition matrix between the hidden state and the observed state;

Step 24: Obtain the preset position prediction model according to the probability matrix in the hidden state, the transition state matrix of the terminal between hidden states, and the transition matrix from hidden state to observed state.

Here, the moving trajectory data of multiple terminals in the training set can be obtained from the user's measurement report MR data and the OTT (including user information and latitude and longitude information obtained from the navigation APP) data used to describe the user's moving trajectory; specifically, using the OTT Correlate the points extracted with MR data, use the accurately associated MR to build a feature library, and perform feature matching on the MR to be positioned to complete the positioning;

Specifically, use soft sampling to obtain MR data (terminal measurement report information) from the wireless side, use probes to collect OTT data from the core network side, and use MR data (initial stay time, stay duration) and OTT data (longitude and latitude data) Perform cleaning, correlation and other processing, send the correlated MR sample points containing latitude and longitude to the fingerprint server, accumulate data for many days, and create a fingerprint database after the sample points are rich enough. Input the MR points to be located and perform feature matching with the fingerprint library, and output the MR points containing longitude and latitude information after positioning, and finally realize the position positioning.

Here, MR and OTT data are associated through reporting time, S1APID (the index field in the S1AP message in the UE context), ENBID (evolved node ID) and other fields to obtain MR sample points containing latitude and longitude, and the associated MR sample points Among them, IMSI (International Mobile Subscriber Identity) corresponds to u _i , latitude and longitude corresponds to l _ij , the initial MR reporting time of a certain location corresponds to the observation time t _ij , and the total reporting time of MR at a certain location corresponds to the stay time d _ij ;

Each location point s _ij of the user can be represented by a quadruple, that is, s _ij =(u _i , l _ij , t _ij , d); where u _i represents the identity of user i; l _ij represents the user i in The position at time j; t _ij represents the time stamp when user i arrives at this position l _ij , d represents the stay time of user i at position l _ij , and the elements in the sequence are sorted according to the time stamp;

In the observation time period T, if s _ij is sorted according to the time stamp l _ij , the user’s movement trajectory data can be expressed as a sequence composed of location points, that is, state variables s _ij , and the construction of the user’s movement trajectory is completed, which describes the user’s Moving between multiple locations and staying in each location.

As shown in Figure 2, based on the above-mentioned mobile trajectory data of users across the network, an intelligent algorithm is used to construct a preset location prediction model for the user's next location. The model can be described by five elements, including 2 state sets and 3 probability matrices. Figure 2 is an example of the model, including:

Hidden state S: usually cannot be obtained through direct observation. s(t) represents the hidden state at time t, and each hidden state represents the user’s stay position and the corresponding start timestamp and stay duration of the position. In the model shown in Figure 2, s(t)∈{s1, s2 , s3}.

Observable state O: It is associated with the implicit state in the model and can be obtained through direct observation. The observable state represents the position information of each user's stay and the corresponding start time and duration of the position. o(t) represents the observable state at time t. In the model shown in Figure 2, there is o(t)∈{o1 , o2, o3}.

Initial state probability vector π: 1×N probability matrix of the hidden state at the initial moment t=1, where N represents the number of hidden states, π=[p(s ₁ ), p(s ₂ ),…, p(s _n )]. Each element p(s _i ) in the vector represents the probability that the user is in a particular hidden state. s(t) represents the hidden state at time t, and each hidden state represents the user's stay location information and the start timestamp and stay duration corresponding to the stay location.

Hidden state transition probability matrix A: represents the transition probability between hidden states in the model, and is an N×N matrix. Among them, A _ij =P(s _j,t+1 |s _i,t ), which represents the probability that the state is s _j at time t+1 under the condition that the state is s _i at time t+1.

Confusion matrix B: Indicates the transition probability between the implicit state and the observable state in the model, which is an N×N matrix, B _ij =P(o _i,t+1 |s _j,t ), 1≤i≤M , 1≤j≤N, represents the probability that the observed state is o _i at time t+1 when the hidden state is s _j at time t. The variable M represents the number of observable states.

A preset position prediction model (ie, HMM) model is represented by a triplet of λ={A, B, π}. The acquisition of the initial state probability vector π, the hidden state transition probability matrix A, and the confusion matrix B is obtained through the parameter learning process.

In this embodiment, MR data and OTT data are used to construct user movement trajectory data, and then an intelligent algorithm is used to predict the location of the terminal, so that the location of the mobile terminal can be quickly predicted, and the trend of the number of mobile terminals in the region can be understood.

In an optional embodiment of the present invention, the above step 12 may include:

Step 121, build a hash table, the hash table includes: a hash key and a hash value, the hash key is a sequence composed of the first k-1 positions in a subsequence with a length of t1, and the hash The value is a linked list, each node in the linked list contains the probability value of the kth element and the predicted position corresponding to the subsequence, 2≤k≤Y;

Step 122, look up the location sequence [ts ₁ , ts ₂ , ..., ts _L ] of the mobile terminal whose length is L as the target hash key in the hash table, if the target hash key is in the hash table exists in the linked list, obtain the predicted position from the linked list; if the target hash key value does not exist in the hash table, subtract 1 from the length of the position sequence of the mobile terminal whose length is L, and use it as the target hash again The key value is looked up in the hash table until a linked list containing at least one predicted position is obtained, where 1≤L≤Y-1;

Step 123 , determining the predicted position corresponding to the maximum value of the corresponding probabilities of the plurality of predicted positions included in the linked list as the final predicted position.

In this embodiment, before location prediction, a hash table is constructed to cache the following information: a sequence of known previous k-1 (2≤k≤10) locations, all possible next access locations, and corresponding The possibility takes the value prob, where prob is the probability of the predicted position.

Table 1 describes an example of a hash table pair. In the hash table, the sequence composed of the first k-1 elements in the subsequence of length t1 is used as the hash key. The value of the hash table is a linked list, and each node in the linked list contains the kth element and the subsequence prob two parts.

Table 1:

After constructing the hash table, use the sequence [ts ₁ , ts ₂ , ..., ts _l ] (1≤l≤9) of the most recently visited locations as the key value key, and predict the user will visit by looking up the hash table next position of

If feasible, the length l of the sequence of initialized recently visited locations can be as high as 9, which is equal to the maximum length of the key value key in the hash table. Once the key value does not exist in the hash table, then the length of the sequence decreases.

Specifically, during position prediction, if the sequence [ts ₁ , ts ₂ , ..., ts _l ] of length l exists in the hash table, the positions that the user may visit will be obtained from the returned linked list. On the contrary, remove the first element in the sequence, obtain a sequence of length l-1, and continue to perform the lookup operation of the hash table until a linked list is returned.

If the returned linked list contains multiple possible locations, the location corresponding to the highest prob value will be judged as the location that the user will visit

As shown in Figure 3, the process of a specific embodiment of the present invention includes:

According to MR data and OTT data, obtain the mobile trajectory data of mobile terminals in the whole network;

Constructing a position prediction model based on the movement trajectory data;

Inputting the position sequence of the terminal in the most recent period into the position prediction model to obtain the predicted position of the terminal;

Based on the predicted position of the terminal, clustering is performed to obtain multiple clusters;

Determine the center of the cluster as the building address of the base station.

The specific algorithm flow is as follows:

Input: [ts ₁ , ts ₂ , ..., ts _l ] a sequence of the most recently visited locations, that is, construct a hash table (seqpattern);

Output: Predict the next position

1: Len=l; placeSeq=[ts ₁ , ts ₂ ,..., ts _l ] (input the sequence formed by the last visited l places)

2: Where Lendo

3: key=placeSeq (determine the key-value sequence of the hash table)

4: if placeSeq in seqpatternthen

5: Linkedlist[possible place, prob] = seqpattern.get(key)

6: ts=Select place of maxprob(Linkedlist) (select the highest prob value among multiple possible positions in the linked list)

7: break

8: else

9: len=len-1, placeSeq=[ts ₁ , ts ₂ , . . . , ts _l ]

10: end if

11: end while

(返回预测位置)。12:

(returns predicted position).

As shown in Figure 4, the comparison diagram of the trajectory formed for the predicted position and the real trajectory.

After the above model is constructed, the prediction accuracy is tested. The prediction accuracy is the ratio of the number of correct predictions for a user to the number of predictions the user has attempted.

Taking the sequence formed by the user's movement trajectory data as input, the above model is used to predict the user's next location. The results show that almost 60% of the users have a prediction accuracy rate exceeding 80%.

In an optional embodiment of the present invention, clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result may include:

Clustering the mobile terminals according to the predicted position of the at least one mobile terminal, the coverage distance of the base station and the number of terminals supported by the base station to obtain a clustering result.

Specifically, this step can include:

Step a, first determine the radius r and the capacity of the base station, where r can be the average effective coverage distance of the base station, and the base station point capacity min Points can be the number of terminals that the base station can support;

Starting from an arbitrary data point that has not been visited, whether the number of data points contained in a circle with the data point as the center and r as the radius is greater than or equal to the capacity of the base station, and if it is greater than or equal to the capacity of the base station, then the data point is marked as a central point, otherwise, the data point is marked as a noise point.

Step b, repeat step a, if a noise point exists in a circle whose center point is the radius, then this data point is marked as an edge point, otherwise it is still a noise point. Repeat step a until all data points have been visited, so that multiple clusters are obtained.

In an optional embodiment of the present invention, step 14 may include:

Determine the center point of the cluster as the address of the base station. In this way, cluster analysis is carried out in combination with prediction results, and sites are selected on demand, which improves the accuracy of site selection for base stations and reduces the cost of site construction.

In the above-mentioned embodiments of the present invention, MR data is obtained from the wireless side, OTT data is collected from the core network side by using probes, MR data and OTT data are cleaned and correlated, and the associated MR sample points containing latitude and longitude are stored in the target Database; input the MR points to be located and perform feature matching with the target database, and output the MR points containing longitude and latitude information after positioning, and finally realize the position positioning; record the user's movement trajectory according to the traffic data; build a position prediction model, and use the user's movement sequence as input , use the location prediction model to predict the next location of the user; select the mobile terminal predicted location library as the data source, and combine the coverage distance of the base station and the number of supported terminals to perform a density-based cluster analysis to obtain multiple clusters and the number of clusters To determine the number of base station points, the center point of the cluster is the position of the base station point. In this way, the location prediction model based on the construction can quickly predict the location of mobile terminals, understand the trend of the number of mobile terminals in the region, perform cluster analysis based on the prediction results, select sites on demand, and get rid of manual site selection, improving the accuracy of base station site selection .

Fig. 5 shows a device 50 for determining the position of a base station provided by an embodiment of the present invention, and the device includes:

An acquisition module 51, configured to acquire location sequence information of at least one mobile terminal;

A prediction module 52, configured to input the location sequence information of the at least one mobile terminal into a preset location prediction model for prediction processing, to obtain a predicted location of at least one mobile terminal;

A clustering module 53, configured to cluster the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

The determination module 54 is configured to determine the address of the established base station according to the clustering result.

Optionally, the preset position prediction model is trained through the following process:

Obtaining a training set comprising movement trajectory data of multiple terminals;

inputting the moving trajectory data into the target model for processing to obtain at least one hidden state and at least one observed state;

Obtain the probability matrix in the hidden state, the transition state matrix of the terminal between the hidden states, and the transition matrix from the hidden state to the observed state;

The preset position prediction model is obtained according to the probability matrix in the hidden state, the transition state matrix of the terminal between hidden states, and the transition matrix from hidden state to observed state.

Optionally, the movement track data of multiple terminals is a sequence composed of state variables s _ij ; s _ij =(u _i , l _ij , t _ij , d);

Among them, u _i represents the identity of user i; l _ij represents the position of user i at time j; t _ij represents the time stamp when user i arrives at this position l _ij , and d represents the stay time of user i at position l _ij , so The elements in the above sequence are sorted by timestamp.

Optionally, the probability matrix π=[p(s ₁ ), p(s ₂ ), ..., p(s _n )] in the hidden state, element p(s _i ) indicates that the user appears in a hidden state The probability of the state, s(t) represents the hidden state at time t, and each hidden state represents the user's stay location information and the start timestamp and stay duration corresponding to the stay location.

Optionally, the transition state matrix of the terminal in the implicit state is A, and the element A _ij = P(s _{j, t+1} |s _{i, t} ) in A indicates that at time t, the state is s _i , the probability that the state is s _j at time t+1.

Optionally, the transition matrix B between the hidden state and the observed state is an N×N matrix, and the elements in B are B _ij =P(o _i,t+1 |s _j,t ), 1≤i≤M , 1≤j≤N, represents the probability that the observed state is o _i at time t+1 when the hidden state is s _j at time t, and the variable M represents the number of observed states.

Optionally, inputting the location sequence information of the at least one mobile terminal into a preset location prediction model for prediction processing to obtain the predicted location of at least one mobile terminal, including:

Build a hash table, the hash table includes: a hash key and a hash value, the hash key is a sequence composed of the first k-1 positions in a subsequence with a length of t1, and the hash value is a Linked list, each node in the linked list contains the probability value of the kth element and the predicted position corresponding to the subsequence, 2≤k≤Y;

The position sequence [ts ₁ , ts ₂ , ..., ts _L ] of the mobile terminal whose length is L is searched in the hash table as the target hash key value, if the target hash key value exists in the hash table, Obtain the predicted position from the linked list; if the target hash key value does not exist in the hash table, the length of the location sequence of the mobile terminal whose length is L is reduced by 1, and used as the target hash key value again in Look up in the hash table until a linked list containing at least one predicted position is obtained, where 1≤L≤Y-1;

The predicted positions corresponding to the maximum values of the corresponding probabilities of the plurality of predicted positions contained in the linked list are determined as the final predicted positions.

It should be noted that the embodiment of the device is a device corresponding to the above-mentioned method embodiment, and all the implementation modes in the above-mentioned method embodiment are applicable to the embodiment of the device, and can also achieve the same technical effect.

An embodiment of the present invention provides a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the cell optimization method in any of the above method embodiments.

FIG. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in FIG. 6 , the computing device may include: a processor (processor), a communication interface (Communications Interface), a memory (memory), and a communication bus.

Wherein: the processor, the communication interface, and the memory complete the mutual communication through the communication bus. The communication interface is used to communicate with network elements of other devices such as clients or other servers. The processor is configured to execute the program, and specifically may execute the relevant steps in the above embodiment of the method for optimizing a cell of a computing device.

Specifically, the program may include program code including computer operation instructions.

The processor may be a central processing unit CPU, or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be of the same type, such as one or more CPUs, or may be different types of processors, such as one or more CPUs and one or more ASICs.

Memory for storing programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program may specifically be used to enable the processor to execute the cell optimization method in any of the foregoing method embodiments. For the specific implementation of each step in the program, refer to the corresponding steps and descriptions in the units in the above cell optimization method embodiment, and details are not repeated here. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the foregoing method embodiments, and details are not repeated here.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present invention are not directed to any particular programming language. It should be understood that various programming languages can be used to implement the contents of the embodiments of the present invention described herein, and the above description of specific languages is for disclosing the best implementation mode of the embodiments of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be understood that in the above description of the exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together in order to simplify the embodiments of the present invention and facilitate understanding of one or more of the various inventive aspects. in a single embodiment, figure, or description thereof. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that although some embodiments herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components according to the embodiments of the present invention. Embodiments of the present invention can also be implemented as a device or apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program implementing an embodiment of the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims (10)

1. A method for determining a location of a base station, the method comprising:

acquiring position sequence information of at least one mobile terminal;

inputting the position sequence information of the at least one mobile terminal into a preset position prediction model for prediction processing to obtain a predicted position of the at least one mobile terminal;

clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

and determining the address of the base station according to the clustering result.

2. The method for determining a base station position according to claim 1, wherein the preset position prediction model is trained by:

acquiring a training set comprising movement track data of a plurality of terminals;

inputting the movement track data into a target model for processing to obtain at least one hidden state and at least one observation state;

obtaining a probability matrix under an implicit state, a transition state matrix of a terminal between the implicit states and a transition matrix between the implicit states and an observation state;

and obtaining the preset position prediction model according to the probability matrix in the hidden state, the transition state matrix of the terminal between the hidden states and the transition matrix from the hidden state to the observation state.

3. The method for determining the position of a base station according to claim 2, wherein the movement trace data of the plurality of terminals is defined by a state variable s _ij A sequence of constructs; s is(s) _ij ＝(u _i ，l _ij ，t _ij ，d)；

Wherein u is _i An identity representing user i; l (L) _ij The position of the user i at the moment j is shown; t is t _ij Indicating that user i arrives at this location l _ij D represents that user i is at location l _ij The elements in the sequence are ordered by time stamp.

4. The method according to claim 2, characterized in that the probability matrix in the implicit state pi= [ p (s ₁ )，p(s ₂ )，…，p(s _n )]Element p(s) _i ) The probability that the user appears in one hidden state is represented, s (t) represents the hidden state at the time t, and each hidden state represents the user stay position information, and the start time stamp and the stay time corresponding to the stay position.

5. The method for determining the position of a base station according to claim 2, wherein the transition state matrix of the terminal in the implicit state is a, and element a in a is a _ij ＝P(s _j，t+1 |s _i，t ) Indicating at time t that the state is s _i Under the condition of (1), the state is s at time t+1 _j Is a probability of (2).

6. The method according to claim 2, wherein the transition matrix B between the hidden state and the observed state is an nxn matrix, and the element B in B is _ij ＝P(o _i，t+1 |s _j，t ) 1.ltoreq.i.ltoreq.M, 1.ltoreq.j.ltoreq.N, indicating that at time t, the implicit state is s _j At time t+1, the observation state is o _i The variable M represents the number of observed states.

7. The method for determining a base station position according to claim 1, wherein inputting the position sequence information of the at least one mobile terminal into a preset position prediction model for prediction processing to obtain a predicted position of the at least one mobile terminal comprises:

constructing a hash table, the hash table comprising: a hash key value and a hash value, wherein the hash key value is a sequence consisting of the first k-1 positions in a subsequence with the length of t1, the hash value is a linked list, and each node in the linked list comprises a k element and a probability value of a predicted position corresponding to the subsequence, and k is more than or equal to 2 and less than or equal to Y;

position sequence of mobile terminal with length L [ ts ] ₁ ，ts ₂ ，…，ts _L ]Searching in a hash table as a target hash key value, and if the target hash key value exists in the hash table, obtaining a predicted position from the linked list; if the target hash key value does not exist in the hash table, subtracting 1 from the length of the position sequence of the mobile terminal with the length L, and searching in the hash table again as the target hash key value until a linked list containing at least one predicted position is obtained, wherein L is more than or equal to 1 and less than or equal to Y-1;

and determining the predicted positions corresponding to the maximum values of the probabilities respectively corresponding to the plurality of predicted positions contained in the linked list as final predicted positions.

8. A base station position determining apparatus, the apparatus comprising:

the acquisition module is used for acquiring the position sequence information of at least one mobile terminal;

the prediction module is used for inputting the position sequence information of the at least one mobile terminal into a preset position prediction model for prediction processing to obtain a predicted position of the at least one mobile terminal;

the clustering module is used for clustering the mobile terminals according to the predicted position of the at least one mobile terminal to obtain a clustering result;

and the determining module is used for determining the address for establishing the base station according to the clustering result.

9. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the method for determining a location of a base station according to any one of claims 1 to 7.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of determining a location of a base station as claimed in any one of claims 1 to 7.

Images