Communication management device and communication management method

Abstract

To grasp the access trends of users on a base station basis in order to reduce transmission delay time.SOLUTION: A communication management device 1 includes: a learning unit 12 that estimates, by Bayesian estimation, a probability distribution of a communication terminal 2 accessing a first website under the condition that the communication terminal is located in the communication area of each of base stations BS0 to BSn, which is a posterior distribution obtained by updating a prior distribution with a likelihood function, where the probability distribution of the communication terminal 2 having accessed the first website is used as a prior distribution and the probability distribution of the communication terminal being located in the communication area of each of the base stations BS0 to BSn under the condition of the communication terminal 2 being accessing the first website, which is obtained based on first observation data, is used as a likelihood function; and an identification unit 13 that identifies a base station BS of a communication area where the communication terminal 2 is located in a posterior distribution where an estimated value of the posterior distribution is maximum.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a communication management device and a communication management method. [Background technology]

[0002] Conventionally, there has been known a technique for identifying files on a cloud to which each communication terminal has made an access request by analyzing access logs of the cloud or the like. According to the technique disclosed in Patent Document 1, an estimation device that centrally manages a server such as a web server or multiple servers records access logs, and analyzes the access trends of each of multiple communication terminals that have accessed a specific website or the like. The results of such an analysis of access trends are used by providers of services such as websites to provide more personalized services to users.

[0003] However, the access log disclosed in Patent Document 1 does not record access to any of multiple websites that each communication terminal can access. Furthermore, the access log disclosed in Patent Document 1 does not record which websites were accessed from each base station that switches as the communication terminal moves on the radio access network (RA) or core network side. Therefore, it has been difficult to utilize the access log disclosed in Patent Document 1 and its analysis results in edge computing, such as MEC (Multi-access Edge Computing), for reducing transmission delay time. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-156385 Summary of the Invention [Problem to be solved by the invention]

[0005] As described above, according to the conventional technology, it is not possible to grasp the access trends of users on a base station basis in order to reduce transmission delay time.

[0006] The present invention has been made to solve the above-mentioned problems, and has as its object to grasp the access trends of users on a base station basis in order to reduce transmission delay time. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, the communication management device of the present invention comprises a first acquisition unit configured to acquire first observation data indicating the number of times a communication terminal is present in the communication area of each base station under the condition that it is accessing a first website; a learning unit configured to estimate, by Bayesian estimation, a probability distribution of the communication terminal accessing the first website under the condition that it is present in the communication area of each base station, where the probability distribution of the communication terminal accessing the first website is a prior distribution and the probability distribution of the communication terminal being present in the communication area of each base station under the condition that it is accessing the first website, obtained based on the first observation data, is a likelihood function, and the posterior distribution is updated with the likelihood function for the prior distribution; an identification unit configured to identify the base station in the communication area in which the communication terminal is present in the posterior distribution in which the value of the estimated posterior distribution is maximum; and an output unit configured to output information about the identified base station as communication control information.

[0008] In addition, the communication management device of the present invention may further include a second acquisition unit configured to acquire second observation data indicating the number of times the communication terminal has accessed the first website, and the prior distribution may be set based on the second observation data.

[0009] In addition, in the communication management device of the present invention, the learning unit may estimate, based on the first observation data, parameters that maximize the likelihood function estimated using a maximum likelihood estimation method as parameters that maximize the posterior distribution.

[0010] In addition, the communication management device of the present invention may further include a third acquisition unit configured to acquire information about the cloud of a cloud location that is the shortest physical distance from the identified base station among the clouds of multiple cloud locations that provide the first website based on the communication control information, and a communication control unit configured to instruct a core network of a specified communication standard to connect the communication terminal to the cloud of the cloud location, depending on the information about the cloud of the cloud location acquired by the third acquisition unit.

[0011] In addition, the communication management device of the present invention may further include a first collection unit configured to collect from a core network of a specified communication standard a presence log indicating the base station in the communication area in which the communication terminal having subscriber identification information was located and the time the communication terminal was located; a second collection unit configured to collect from the core network the terminal IP address assigned to the subscriber identification information contained in the presence log acquired by the first collection unit; and a third collection unit configured to collect from the core network an access log including the access time to a website having a site IP address for each subscriber identification information based on the terminal IP address collected by the second collection unit, wherein the first acquisition unit acquires the first observation data based on the presence log collected by the first collection unit and the access log collected by the third collection unit, and the second acquisition unit acquires the second observation data based on the access log collected by the third collection unit.

[0012] In order to solve the above-mentioned problems, the communication management method of the present invention includes a first acquisition step of acquiring first observation data indicating the number of times a communication terminal is within the communication area of each base station under the condition that it is accessing a first website; a learning step of estimating, by Bayesian estimation, a probability distribution of the communication terminal accessing the first website under the condition that it is within the communication area of each base station, where the probability distribution of the communication terminal accessing the first website is a prior distribution and the probability distribution of the communication terminal being within the communication area of each base station under the condition that it is accessing the first website, obtained based on the first observation data, is a likelihood function, and the posterior distribution is updated with the likelihood function; an identification step of identifying a base station in the communication area where the communication terminal is located in the posterior distribution where the value of the estimated posterior distribution is maximum; and an output step of outputting information about the identified base station as communication control information.

[0013] In addition, the communication management method of the present invention may further include a second acquisition step of acquiring second observation data indicating the number of times the communication terminal has accessed the first website, and the prior distribution may be set based on the second observation data.

[0014] In addition, in the communication management method of the present invention, the learning step may estimate the posterior distribution by estimating the parameters that maximize the likelihood function, estimated using a maximum likelihood estimation method based on the first observation data, as the parameters that maximize the posterior distribution.

[0015] In addition, the communication management method of the present invention may further include a third acquisition step of acquiring, based on the communication control information, information on the cloud of a cloud site that is the shortest physical distance from the identified base station among the clouds of multiple cloud sites that provide the first website, and a communication control step of instructing a core network of a specified communication standard to connect the communication terminal to the cloud of the cloud site, depending on the information on the cloud of the cloud site acquired in the third acquisition step.

[0016] In addition, the communication management method of the present invention further includes a first collection step of collecting from a core network of a predetermined communication standard a presence log indicating the base station in the communication area in which the communication terminal having subscriber identification information was located and the time the communication terminal was located; a second collection step of collecting from the core network the terminal IP addresses assigned to the subscriber identification information included in the presence log acquired in the first collection step; and a third collection step of collecting from the core network an access log including the access time to a website having a site IP address for each subscriber identification information based on the terminal IP addresses collected in the second collection step, wherein the first acquisition step acquires the first observation data based on the presence log collected in the first collection step and the access log collected in the third collection step, and the second acquisition step acquires the second observation data based on the access log collected in the third collection step. [Effects of the Invention]

[0017] According to the present invention, the probability distribution of a communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station is estimated by Bayesian estimation, where the probability distribution of a communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station is used as a prior distribution and a likelihood function is used as a probability distribution of a communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station, and the posterior distribution is updated by the likelihood function to the prior distribution. As a result, it is possible to grasp user access trends on a base station-by-base station basis in order to reduce transmission delay time. [Brief explanation of the drawings]

[0018] [Figure 1] FIG. 1 is a block diagram showing the configuration of a communication management system including a communication management device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the configuration of the collection unit included in the communication management device according to this embodiment. [Figure 3] FIG. 3 is a diagram for explaining the data structure of the visit log collected from the AMF by the communication management device according to this embodiment. [Figure 4] FIG. 4 is a diagram for explaining the data structure of a table in which terminal IP addresses collected from SMF by the communication management device according to this embodiment are stored. [Figure 5] FIG. 5 is a diagram for explaining the data structure of the access log collected from DNS by the communication management device according to the present embodiment. [Figure 6] FIG. 6 is a diagram illustrating a data structure of the second storage unit stored in the communication management device according to the present embodiment. [Figure 7] FIG. 7 is a block diagram showing the hardware configuration of the communication management device according to this embodiment. [Figure 8] FIG. 8 is a flowchart showing the estimation process performed by the communication management device according to this embodiment. [Figure 9] FIG. 9 is a flowchart showing the estimation process performed by the communication management device according to this embodiment. [Figure 10]FIG. 10 is a sequence diagram showing a communication control process by the communication management system according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0019] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will now be described in detail with reference to FIGS.

[0020] [Communication Management System Configuration] 1 is a block diagram showing the configuration of a communication management system including a communication management device 1 according to an embodiment of the present invention. The communication management system according to this embodiment is provided in, for example, a 5G mobile communication network, and when a communication terminal 2 performing mobile communication accesses a specific website, it estimates, based on a probabilistic model, which base station BS the communication terminal 2 will use to access the website. Furthermore, the communication management system controls communication so that the communication terminal 2 communicates with the cloud 50 at the cloud site that is closest in physical distance to the identified base station BS.

[0021] The communication management system includes a communication management device 1 including an estimation device 1A and a communication control device 1B, a communication terminal 2 compatible with 5G mobile communication, a plurality of base stations BS0 to BSn, a core network 4, and a plurality of clouds 50.

[0022] The communication terminal 2 includes a SIM 20 and is realized as a mobile communication terminal such as a smartphone, a tablet computer, a laptop computer, or the like. The contract profile of the SIM 20 stores the user's subscriber identification information, and includes identifier information such as an International Mobile Subscriber Identity (IMSI) number assigned to a mobile phone line contract, a mobile subscriber international subscriber directory number (MSISDN) of the subscriber user, and an integrated circuit card identifier (ICCID) number. The communication terminal 2 is uniquely identified by the IMSI of the SIM 20.

[0023] Each communication terminal 2 is further assigned a terminal IP address that uniquely identifies the terminal. The terminal IP address can be a local IP address or a global IP address. There are m communication terminals 2 (m is a positive integer).

[0024] Base stations BS0 to BSn (n is a positive integer) are configured as wireless base stations compatible with the 5G system, and relay communications between communication terminals 2 present in their communication areas and a core network 4. Base stations BS0 to BSn are connected to the core network 4 via a network L such as a backhaul link. Hereinafter, when there is no need to distinguish between base stations BS1 to BSn, they may be collectively referred to as base station BS.

[0025] The core network 4 is connected to the communication management device 1 via a network NW such as a LAN or WAN. The core network 4 includes multiple UPFs (User Plane Functions) 40 in the U-plane, multiple AMFs (Access and Mobility Management Functions) 41 which are nodes in the C-plane, an SMF (Session Management Function) 42, and a DNS (Domain Name System) 43. Note that other functions included in the core network 4 are not shown in the figure.

[0026] The UPF 40 is a user plane function that processes data packets between a radio access network (RAN) and a data network such as the Internet. In this embodiment, a single C-plane can control multiple UPFs 40. The multiple UPFs 40 are devices located at different physical locations in a 5G mobile communication network. Each UPF 40 is connected to a cloud 50 on the Internet, and the communication terminal 2 can access websites provided by each cloud 50 via each UPF 40.

[0027] The AMF 41 is an access and mobility management device, and manages the registration and wireless connection of the communication terminal 2 that has moved to each area. In this embodiment, a plurality of AMFs 41 are provided, each having a communication interface 41a for communicating with the communication management device 1. FIG. 3 shows a presence log table 410 managed by the AMF 41. The presence log is information in which the IMSI of the communication terminal 2, the base station BS of the communication area in which the communication terminal 2 has been present, and a timestamp indicating the time of presence are associated with each other. For example, the IMSI1 of the communication terminal 2 records, as timestamps, the base stations BS0 to BSn that have been switched to as the communication terminal 2 has moved, and the time at which the communication terminal 2 has been present at each of the base stations BS0 to BSn.

[0028] The SMF 42 is a session management function that establishes, modifies, releases, etc., PDU (Packet Data Unit) sessions between the communication terminal 2 and a data network such as the Internet. The SMF 42 according to this embodiment includes a communication interface 42a for communicating with the communication management device 1. The SMF 42 also stores information that associates the IMSI of the communication terminal 2, the terminal IP address assigned to the IMSI, and the UPF 40 used by the communication terminal 2, as shown in table 420 in FIG. 4 .

[0029] The DNS 43 is a domain name system that associates domain names with IP addresses and manages them on an IP network. The DNS 43 according to this embodiment includes a communication interface 43a and communicates with the communication management device 1 via the communication interface 43a. The DNS 43 according to this embodiment also stores an access log of the site IP addresses of websites requested by the communication terminal 2. As shown in FIG. 5, the DNS 43 stores a table 430 that associates the terminal IP address of the communication terminal 2, the site IP addresses of the websites, and a timestamp indicating the time when the site IP address was accessed by the terminal IP address.

[0030] Cloud 50 provides predetermined websites, web applications, etc., and each cloud 50 has cloud bases that are geographically separated from one another. A cloud base refers to a geographical location or area where the physical devices that make up each cloud 50 are located. Each cloud 50 can be an edge server such as a server, a data center, or an MEC server. In the example of FIG. 1, cloud 1, cloud 2, and cloud Z (Z is a positive integer) are each distributed and located in geographically separated locations as cloud bases that provide a first website with a site IP address "site IP1."

[0031] For example, as shown in FIG. 1, a communication terminal 2 assigned IMSI1 and terminal IP1 is located in the communication area of base station BS0. The communication terminal 2 connects to one of clouds 50 via base station BS0 and UPF 40 and accesses the first website "www.111" of site IP1. In the example of FIG. 1, the distance between base station BS0, UPF 40, and cloud 50 is as follows: [distance R1 between base station BS0, UPF_1, and cloud 1] > [distance R2 between base station BS0, UPF_2, and cloud 2] > [distance RZ between base station BS0, UPF_Z, and cloud Z]. Therefore, when communication terminal 2 accesses the first website of site IP1, it can reduce latency by using MEC by communicating with cloud Z via UPF_N, which takes the shortest route from base station BS0.

[0032] On the other hand, depending on the user's access tendency, the communication terminal 2 may access a specific website more frequently via a specific base station BS. For example, in recent years, with the trend toward remote work, a user associated with the communication terminal 2 accesses a specific website of the company where the user works while at home. In such a case, the user accesses the company's website more frequently via a base station BS closer to home rather than via a base station BS located at the company's location. The communication management system according to this embodiment estimates the data network access tendency for each user, i.e., for each communication terminal 2, by Bayesian estimation, and identifies the intermediate base station BS with the highest probability that the communication terminal 2 will access the specific website. Furthermore, the communication management system controls communication so that the communication terminal 2 communicates with the cloud 50, which is a cloud base located on the shortest route from the identified base station BS.

[0033] [Communication management device functional block] The communication management device 1 includes an estimation device 1A and a communication control device 1B. The estimation device 1A uses Bayesian estimation to estimate the probability distribution of access to a specific website when each communication terminal 2 is located within the communication area of each base station BS, and identifies the intermediate base station BS with the highest probability that each communication terminal 2 will access the specified website based on the estimation result. The communication control device 1B controls communication so that each communication terminal 2 communicates with the cloud 50 at the cloud site with the shortest distance from the base station BS identified by the estimation device 1A.

[0034] In the following, an example will be described in which the communication management device 1 identifies the base station BS that is most likely to be passed through by a communication terminal 2, among m communication terminals 2, to which IMSI1 and terminal IP1 are assigned, when accessing the first website among the first to kth websites.

[0035] The estimation device 1A includes a collection unit 10, a first acquisition unit 11A, a second acquisition unit 11B, a learning unit 12, an identification unit 13, an output unit 14, and a first storage unit 15. As shown in FIG. 2 , the collection unit 10 includes a first collection unit 10A, a second collection unit 10B, and a third collection unit 10C.

[0036] The collection unit 10 collects a visit log of the communication terminal 2 at regular intervals and a website access log of the communication terminal 2. The collection unit 10 can collect logs for any period set, such as daily or monthly.

[0037] The first collection unit 10A collects a visit log indicating base stations BS0 to BSn in a communication area where a communication terminal 2 having an IMSI that is subscriber identification information has visited and the time of visit, from the core network 4. More specifically, the first collection unit 10A refers to a table 410 (FIG. 3) stored in the AMF 41 of the core network 4, and collects a visit log for each communication terminal 2.

[0038] The second collection unit 10B collects, from the core network 4, terminal IP addresses assigned to the IMSIs included in the presence logs of the communication terminals 2 collected by the first collection unit 10A. More specifically, the second collection unit 10B refers to the table 420 (FIG. 4) stored in the SMF 42 of the core network 4, and collects the terminal IP addresses assigned to the IMSIs of the communication terminals 2.

[0039] Based on the terminal IP addresses of the communication terminals 2 collected by the second collection unit 10B, the third collection unit 10C collects access logs including access times to each website having a site IP address for each IMSI from the core network 4. More specifically, the third collection unit 10C refers to the table 430 (FIG. 5) stored in the DNS 43 included in the core network 4, and collects the access logs using the terminal IP addresses of the communication terminals 2 as a key.

[0040] The first acquisition unit 11A acquires first observation data indicating the number of times that the communication terminal 2 is present in the communication area of each of the base stations BS0 to BSn under the condition that the communication terminal 2 is accessing a first website. The first acquisition unit 11A acquires the first observation data based on the presence log collected by the first collection unit 10A and the access log collected by the third collection unit 10C. Furthermore, the first acquisition unit 11A can acquire a sufficient number of first observation data that meets certain conditions as training data to be used in estimation processing in the learning unit 12, which will be described later.

[0041] The second acquisition unit 11B acquires second observation data indicating the number of times the communication terminal 2 has accessed the first website. The second acquisition unit 11B acquires the second observation data based on the access log collected by the third collection unit 10C. The base station BS through which the communication terminal 2 accesses the first website may be any of the multiple base stations BS0 to BSn, and the base station BS is not specified in the second observation data.

[0042] The learning unit 12 uses the probability distribution of communication terminal 2 accessing the first website as a prior distribution, and the probability distribution of communication terminal 2 being within the communication area of each of base stations BS0 to BSn under the condition that communication terminal 2 is accessing the first website as a likelihood function, which is obtained based on the first observation data, and estimates, by Bayesian estimation, the probability distribution of communication terminal 2 accessing the first website under the condition that communication terminal 2 is within the communication area of each of base stations BS0 to BSn, which is a posterior distribution updated with the likelihood function for the prior distribution. The learning unit 12 may set the prior distribution based on second observation data.

[0043] In this embodiment, the learning unit 12 further estimates the posterior distribution of the probability model by estimating, under certain conditions, the parameters that maximize the likelihood function estimated using the maximum likelihood estimation method as the parameters that maximize the posterior distribution.

[0044] As described above, the communication management device 1 according to this embodiment employs Bayesian estimation, which estimates a posterior distribution based on likelihood and a probability model, i.e., a prior distribution of parameters, using Bayes' theorem. The following describes the parameters of the probability model used by the learning unit 12 in Bayesian estimation.

[0045] The learning unit 12 first defines event X as an event that has a certain cause. Furthermore, event Y is defined as an event that is assumed to have occurred due to a certain cause. Events X and Y are treated as random variables. Specifically, event X is defined as an event in which a communication terminal 2 that has been assigned a certain IMSI and terminal IP address accesses a specific website. As an example, event X is explained as an event in which a communication terminal 2 that has been assigned IMSI1 and terminal IP1 accesses a first website of site IP1 among the first to k-th websites.

[0046] On the other hand, event Y is defined as an event in which a communication terminal 2 assigned a certain IMSI and terminal IP address is present in the communication area of each base station BS0 to BSn. For example, event Y is explained as an event in which a communication terminal 2 assigned IMSI1 and terminal IP1 is present in the communication area of base station BS0 among multiple base stations BS0 to BSn.

[0047] The learning unit 12 sets the probability distribution P(X) that the event X occurs as a prior distribution, which is the distribution of parameters before the observation data is given. For example, the learning unit 12 can set the probability distribution P(X) that the communication terminal 2 accesses the first website based on the second observation data acquired by the second acquisition unit 11B.

[0048] Specifically, the learning unit 12 can set the prior distribution P(X) based on the value obtained by dividing the number of times the communication terminal 2 accesses the first website (second observation data) over a certain period of time by the number of times all websites from the first to the kth website are accessed. The number of times all websites from the first to the kth website are accessed is a value obtained from the access log of the communication terminal 2 collected by the third collection unit 10C. The learning unit 12 can set the prior distribution P(X) for an arbitrarily set period, such as one day or one month.

[0049] The learning unit 12 further sets a likelihood function P(Y|X), which is a method of expressing the observation data. The likelihood function P(Y|X) indicates how likely an event Y in the observation data is to occur from the model when the parameter values are conditioned. Specifically, it is expressed as a probability distribution of whether communication terminal 2 is located within the communication area of base station BS0 under the condition that communication terminal 2 is accessing the first website.

[0050] When setting the likelihood function P(Y|X), the learning unit 12 can set it based on a value obtained by dividing the number of times (first observation data) that the communication terminal 2 is present in the communication area of the base station BS0 under the condition that the communication terminal 2 is accessing the first website, acquired by the first acquisition unit 11A, by the number of times the communication terminal 2 accesses the first website. The number of times the communication terminal 2 accesses the first website is counted based on the logs collected by the third collection unit 10C.

[0051] The learning unit 12 utilizes Bayes' theorem to reflect the likelihood function, the prior distribution, and information obtained from the first observation data and the second observation data, and can estimate the posterior distribution P(X|Y), which is the probability that event X occurs under the condition that event Y occurs. As described above, the posterior distribution P(X|Y) is the probability distribution of accessing the first website under the condition that communication terminal 2, to which IMSI1 and terminal IP1 are assigned, is located within the communication area of base station BS0. In this embodiment, the posterior distribution P(X|Y) is estimated based on the Bayesian estimation formula expressed in the following formula (2), which is based on Bayes' theorem of the following formula (1).

[0052]

number

[0053] In the denominator of the above equation (1), P(Y) = Σ X Substituting P(Y|X)P(X), the following equation (2) is obtained.

[0054]

number

[0055] The "number of times a user is present in the communication area of base station BS0 while accessing a site other than the first website," illustrated in the denominator of the Bayesian estimation formula in the lower part of formula (2), is counted based on a comparison between the timestamp of the presence log collected by first collection unit 10A using IMSI as a key and the timestamp of the access log collected by third collection unit 10C. Also, the "number of times a user is accessing a site other than the first website" is a value counted based on the access log collected by third collection unit 10C.

[0056] In Bayes' theorem (1) above and the Bayesian estimation formula (2) above, generally, when the number of data N in the training data is sufficiently large (N → ∞), the likelihood function P(Y|X) becomes dominant over the prior distribution P(X), and therefore coincides with the parameters obtained by the maximum likelihood estimation method. In other words, the posterior distribution P(X|Y) can be approximated as having a relationship of ≒ likelihood function P(Y|X). Therefore, the learning unit 12 can estimate the posterior distribution P(X|Y) as a regression problem of the likelihood function P(Y|X).

[0057] In this case, the learning unit 12 approximates the event Y, which is the number of times that the communication terminal 2 is present in the communication area of the base station BS0, with the observation value t at the observation point x, by a function f(x) expressed as an M-th degree polynomial in the following equation (3).

number

[0058] In the above equation (3), x is a set of observation points. The parameter w in the above equation (3) is expressed by the following equation (4).

number

[0059] In the above equation (4), Φ is expressed by the following equation (5).

number

[0060] t in the above equation (4) n is the observation point x n The event Y calculated for each of the above, that is, the vector t that lists the objective variables included in the observed data n =(t1, ,t N ) T Specifically, the first observation data is expressed as n If communication terminal 2 accesses the first website and is in the communication area of base station BS0, t = 1, otherwise t = 0. For example, if the number of observation points is 4 (N = 4), t is expressed as t = (1, 0, 0, 1), etc.

[0061] The learning unit 12 can use, for example, 10,000 (1-minute units) as the number N of observation points x. In this case, (x1,...,x N ) = (1, . . . , 10000). More specifically, the observation values t at 10,000 observation points x include all combinations of cases in which communication terminal 2 accesses the first to k-th websites and is located in the communication areas of base stations BS0 to BSn. Specifically, of the observation values t at 10,000 observation points x, for example, 2,000 observation values t may indicate that communication terminal 2 accesses the first website and is located in the communication area of base station BS0. In this case, for example, another 3,000 observation values t out of the 10,000 may indicate that communication terminal 2 accesses the second website and is located in the communication area of another base station BS1.

[0062] Here, the observed value t n Variance σ 2 is expressed by the following equation (6).

number

[0063] For example, the learning unit 12 may calculate the number of observation points x per minute in a cycle of N. nObservation value t n Based on the probability of obtaining the following, the posterior distribution P(X|Y) of the period N is estimated by the following equation (7): n Observation value t n The probability of taking follows the normal distribution of the following equation (7).

[0064]

number

[0065] Therefore, the learning unit 12 calculates P(t|f(x n ), σ 2 ) is maximized at the observation point x. n For example, the posterior distribution P(X|Y) at the observation point x in the above equation (7) is n The value of the observed value t at is assigned as 0 or 1, and the value with the highest probability P is the observed value t n , i.e., an estimate of the posterior distribution P(X|Y).

[0066] The learning unit 12 changes the setting of the event Y for each of the plurality of base stations BS0 to BSn and estimates the posterior distribution P(X|Y) for each of the base stations BS0 to BSn. Furthermore, the learning unit 12 can also change the setting of the event X and the event Y for each of the m communication terminals 2 and the first to kth websites and estimate the posterior distribution P(X|Y) for each case.

[0067] The identification unit 13 identifies the base station BS in the communication area where the communication terminal 2 is located in the posterior distribution P(X|Y) where the value of the posterior distribution P(X|Y) estimated by the learning unit 12 is maximum. Specifically, the identification unit 13 compares the values of the posterior distribution P(X|Y) corresponding to each of the base stations BS to BSn estimated by the learning unit 12, and identifies the base station BS in the posterior distribution P(X|Y) where the value of the posterior distribution P(X|Y) is maximum.

[0068] For example, the identification unit 13 compares the values of a first posterior distribution P(X|Y) for communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of base station BS0, a second posterior distribution P(X|Y) for communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of base station BS1, and an nth posterior distribution P(X|Y) for communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of base station BSn. If the first posterior distribution P(X|Y) has a maximum value, the identification unit 13 can identify the corresponding base station BS0.

[0069] The output unit 14 outputs the information on the identified base station BS as communication control information. Specifically, the output unit 14 sends the communication control information to the communication control device 1B.

[0070] The first storage unit 15 stores the Bayesian estimation formula of the above formula (2) and the formulas related to the maximum likelihood estimation method of the above formulas (3) to (7). The first storage unit 15 also stores the first observation data and the second observation data.

[0071] Next, we will explain the configuration of the communication control device 1B included in the communication management device 1. As shown in Fig. 1, the communication control device 1B includes a third acquisition unit 16, a second storage unit 17, and a communication control unit 18. The communication control device 1B performs communication control processing for the communication terminal 2 based on the communication control information output from the estimation device 1A.

[0072] Based on the communication control information from the output unit 14, the third acquisition unit 16 acquires information on the cloud 50 at the cloud base station that is the shortest physical distance from the base station BS0 identified by the identification unit 13, among the clouds 50 at the multiple cloud base stations that provide the first website. The third acquisition unit 16 acquires, from the second storage unit 17, information on the cloud 50 at the cloud base station on the shortest route.

[0073] The second storage unit 17 stores the table 170 of Fig. 6. The table 170 stores the physical distances between each of the base stations BS0 to BSn, each of the UPF_1 to UPF_N, and cloud 1 to cloud Z, which are cloud bases that provide each of the sites IP1 to IPk. The sites IP1 to IPk are identification information corresponding to the first to k-th websites. The table 170 is information shared by a plurality of communication terminals 2. Here, as an example, consider a case where the transit base station BS through which the communication terminal 2 accesses the site IP1 is estimated to be base station BS0.

[0074] In this case, the third acquisition unit 16 compares the distance of 30 km between base station BS0-UPF_1-Cloud 1, the distance of 20 km between base station BS0-UPF_2-Cloud 2, and the distance of 3 km between base station BS0-UPF_Z-Cloud Z, which are shown in the dashed line area in table 170 shown in FIG. 6. Note that Cloud 1 to Cloud Z are each cloud bases of site IP1. As shown in FIG. 6, the communication terminal 2 takes the shortest route when communicating with Cloud Z from base station BS0 via UPF_N. Therefore, the third acquisition unit 16 acquires information on UPF_N from the second storage unit 17.

[0075] The communication control unit 18 instructs the core network 4 to set the connection destination of the communication terminal 2 to cloud Z, in accordance with the information on cloud Z acquired by the third acquisition unit 16. More specifically, the communication control unit 18 sends an instruction to the SMF 42 of the core network 4 to cause the communication terminal 2 associated with IMSI1 to communicate via UPF_N. Through the communication control by the communication control unit 18, the communication terminal 2 can access the site IP1 via the shortest route from the base station BS0 by communicating with cloud Z, which is the cloud base of the site IP1, from the base station BS0 via UPF_N.

[0076] [Hardware configuration of communication management device] Next, an example of a hardware configuration for realizing the communication management device 1 having the above-described functions will be described with reference to FIG.

[0077] As shown in Figure 7, the communication management device 1 can be realized, for example, by a computer having a processor 102, a main memory device 103, a communication interface 104, an auxiliary memory device 105, and an input / output (I / O) 106 connected via a bus 101, and a program that controls these hardware resources.

[0078] The main memory device 103 pre-stores programs for the processor 102 to perform various controls and calculations. The processor 102 and the main memory device 103 implement the functions of the communication management device 1, such as the collection unit 10, first acquisition unit 11A, second acquisition unit 11B, learning unit 12, and identification unit 13 of the estimation device 1A, and the third acquisition unit 16 and communication control unit 18 of the communication control device 1B, shown in FIG.

[0079] The communication interface 104 is an interface circuit for connecting the communication management device 1 to various external electronic devices via a network.

[0080] The auxiliary storage device 105 is composed of a readable / writable storage medium and a drive for reading and writing various information such as programs and data from and to the storage medium. The auxiliary storage device 105 can use a semiconductor memory such as a hard disk or flash memory as the storage medium.

[0081] The auxiliary storage device 105 has a program storage area for storing the Bayesian estimation and maximum likelihood estimation programs executed by the communication management device 1. The auxiliary storage device 105 also has an area for storing a communication control program for controlling communication of the communication terminal 2. The auxiliary storage device 105 realizes the first storage unit 15 and the second storage unit 17 described in FIG. 1. Furthermore, for example, the auxiliary storage device 105 may have a backup area for backing up the above-mentioned data, programs, etc.

[0082] The input / output I / O 106 is an input / output device that inputs signals from external devices and outputs signals to external devices.

[0083] The display device 107 is configured by a display such as an organic EL display or a liquid crystal display.

[0084] The estimating device 1A and the communication control device 1B may each have a separate hardware configuration, in which case each of the estimating device 1A and the communication control device 1B has the hardware configuration shown in FIG.

[0085] [Operation of the communication management device] Next, the operation of the communication management device 1 having the above-described configuration will be described with reference to the flowcharts of Figures 8 and 9. Figures 8 and 9 are flowcharts showing the estimation process performed by the estimation device 1A.

[0086] 8, the first collector 10A included in the collector 10 collects a presence log of the communication terminal 2 from the AMF 41 (step S1). More specifically, the first collector 10A refers to the table 410 of the AMF 41, and collects the base stations BS0 to BSn in the communication area where the IMSI 1 assigned to the communication terminal 2 is present, and the timestamps indicating the presence times.

[0087] Next, the second collection unit 10B included in the collection unit 10 acquires the terminal IP address of the communication terminal 2 from the SMF 42 (step S2). Specifically, the second collection unit 10B refers to the table 420 of the SMF 42, and acquires the terminal IP1 assigned to the IMSI1 of the communication terminal 2.

[0088] Next, the third collector 10C included in the collector 10 collects, from the DNS 43, an access log of the website by the communication terminal 2 (step S3). More specifically, the third collector 10C refers to the table 430 stored in the DNS 43, and collects the site IP address designation of the website by the terminal IP1 acquired in step S2 and the timestamp.

[0089] Next, the first acquisition unit 11A acquires second observation data indicating the number of times the communication terminal 2 is present in the communication area of each base station BS0 to BSn under the condition that the communication terminal 2 is accessing the first website (step S4). The first acquisition unit 11A acquires the first observation data based on the presence log collected by the first collection unit 10A and the access log collected by the third collection unit 10C. Furthermore, the first acquisition unit 11A can acquire a sufficient number of first observation data that satisfies predetermined conditions as training data used in estimation processing in the learning unit 12, which will be described later. A likelihood function P(Y|X) is set based on the first observation data.

[0090] The second acquisition unit 11B acquires second observation data indicating the number of times the communication terminal 2 has accessed a specific website (step S5). The second acquisition unit 11B acquires the second observation data based on the access log collected by the third collection unit 10C. In the second observation data, the base station BS through which the communication terminal 2 accesses the first to k-th websites may be any of the multiple base stations BS0 to BSn, and does not need to be specified. The second observation data can be used to set a prior distribution P(X).

[0091] Next, learning unit 12 defines the probability distribution of communication terminal 2 accessing the first website, obtained based on the second observation data, as prior distribution P(X), and defines the probability distribution of communication terminal 2 being located in the communication area of each base station BS0 to BSn under the condition that communication terminal 2 is accessing the first website, obtained based on the first observation data, as likelihood function P(Y|X), and estimates a posterior distribution P(X|Y) by updating prior distribution P(X) with likelihood function P(Y|X) (step S6). The posterior distribution P(X|Y) is the probability distribution of communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of each base station BS0 to BSn.

[0092] Here, the estimation process of the posterior distribution P(X|Y) using the maximum likelihood estimation method by the learning unit 12 will be described with reference to Fig. 9. First, the learning unit 12 approximates the observed value t of the event Y with the function f(x) of the above equation (3) (step S60). Also, in step S12, the learning unit 12 calculates the variance σ 2 Calculate.

[0093] Next, the learning unit 12 calculates the distribution of the observation point x n Observation value t n Using the probability P of obtaining n Specifically, the learning unit 12 sequentially substitutes values in increments of 0.1 (0.1, 0.2, . . . , 0.9, 1) into the above equation (7) as the values of the observed value t, and determines the value with the highest probability as the observed value t. n and the observed value t n The posterior distribution P(X|Y) is estimated based on the following equation: Then, the process proceeds to step S7 in FIG.

[0094] 8, when the learning unit 12 calculates the posterior distribution P(X|Y) for all base stations BS0 to BSn (step S7: YES), the identifying unit 13 identifies the base station BS with the maximum value of the posterior distribution P(X|Y) (step S8). On the other hand, when the learning unit 12 has not calculated the posterior distribution P(X|Y) for all base stations BS0 to BSn (step S7: NO), the learning unit 12 repeats the processes from step S4 to step S6.

[0095] Thereafter, the output unit 14 outputs the information on the base station BS identified in step S8 to the communication control device 1B as communication control information (step S9).

[0096] [Operation sequence of the communication management system] Next, the communication control process of the communication control device 1B included in the communication management device 1 will be described with reference to the operation sequence of the communication management system in Fig. 10. First, the communication terminal 2 communicates with the cloud 1 via the base station BS0 in the communication area where the communication terminal 2 is located and further via UPF_1, and accesses the first website of the site IP1 (step S100). Note that in step S100, the communication terminal 2 connects to the cloud 1 via UPF_1, which was randomly assigned when the communication terminal 2 started communication.

[0097] Next, the SMF 42 included in the core network 4 notifies the communication management device 1 of information that the communication terminal 2 having IMSI 1 is accessing the site IP1 via UPF_1 (step S101). The SMF 42 makes the notification by referring to the table 420. The first acquisition unit 11A and the second acquisition unit 11B of the communication management device 1 acquire the notification from the SMF 42.

[0098] Next, the communication control device 1B included in the communication management device 1 acquires the communication control information output from the output unit 14 of the estimation device 1A (step S102). For example, the acquired communication control information indicates that the value of the probability distribution of accessing the first website of the site IP1 is the highest when the communication terminal 2 is located in the communication area of the base station BS0.

[0099] Next, the third acquisition unit 16 of the communication control device 1B acquires information on the UPF_N connected to cloud Z, the cloud base that is the shortest physical distance from base station BS0, among the clouds 50 that provide the first website of site IP1, based on the information on base station BS0 acquired in step S102 (step S103). Specifically, the third acquisition unit 16 refers to the table 170 stored in the second storage unit 17, and selects the UPF_N that is the shortest physical distance between base station BS0-UPF 40-cloud 50, among clouds 1 to Z that are the cloud bases of the first website of site IP1.

[0100] Next, the communication control unit 18 of the communication control device 1B sends to the SMF 42 a communication control instruction indicating that the communication terminal 2 associated with IMSI1 should communicate using the UPF_N (step S104). Subsequently, in response to the communication control instruction, the SMF 42 sends to the UPF_N an instruction to establish a session with the communication terminal 2 of IMSI1 (step S105). Next, the UPF_N that has received the session establishment instruction establishes a session with the communication terminal 2 (step S106).

[0101] Thereafter, UPF_N sends a notification to SMF42 indicating that a session has been established with communication terminal 2 (step S107). Next, SMF42 instructs communication terminal 2 associated with IMSI1 to communicate with UPF_N (step S108). Thereafter, in response to the communication instruction, communication terminal 2 communicates with UPF_N and cloud Z from base station BS0, and accesses the first website of site IP1 (step S109).

[0102] As described above, the communication management device 1 according to this embodiment estimates the probability distribution of communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of each base station BS0 to BSn, which is a posterior distribution obtained by updating the prior distribution with the likelihood function, using the probability distribution of communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of each base station BS0 to BSn as a prior distribution and the probability distribution of communication terminal 2 accessing the first website under the condition that communication terminal 2 is located in the communication area of each base station BS0 to BSn, which is obtained based on the first observation data, as a likelihood function. Therefore, in order to reduce transmission delay time, it is possible to grasp the access trends of users for each base station BS0 to BSn.

[0103] Furthermore, the communication management device 1 according to this embodiment identifies the base station BS0 that is most likely to cause the communication terminal 2 to access the first website. Therefore, by using MEC, communication management can be performed so that the communication terminal 2 communicates with the cloud 50 at the cloud site that is the shortest distance from the base station BS0. As a result, transmission delays in the communication of the communication terminal 2 can be reduced.

[0104] Furthermore, according to the communication management device 1 of this embodiment, the maximum likelihood estimation method is used in a special case of Bayesian estimation, so that the posterior distribution P(X|Y) can be estimated based on the observed data of the event X and the likelihood function P(Y|X).

[0105] In the above-described embodiment, a communication management system conforming to 5G has been exemplified, but the communication management system may also conforming to 6G or the like.

[0106] Furthermore, in the above-described communication management device 1, the case where the estimation device 1A and the communication control device 1B are provided within a single device has been described. However, the estimation device 1A and the communication control device 1B may be configured as independent devices distributed over a network. This also includes the case where each functional unit provided in the estimation device 1A and the communication control device 1B is configured as being distributed over a network.

[0107] The above describes the embodiments of the communication management device and communication management method of the present invention, but the present invention is not limited to the described embodiments, and various modifications that a person skilled in the art can imagine are possible within the scope of the invention described in the claims. [Explanation of symbols]

[0108] 1...communication management device, 1A...estimation device, 1B...communication control device, 10...collection unit, 10A...first collection unit, 10B...second collection unit, 10C...third collection unit, 11A...first acquisition unit, 11B...second acquisition unit, 12...learning unit, 13...identification unit, 14...output unit, 15...first memory unit, 16...third acquisition unit, 17...second memory unit, 18...communication control unit, 2...communication terminal, 20...SIM, 4...core network, 40...UPF, 41...AMF, 42...SMF, 43...DNS, 50...cloud, 101...bus, 102...processor, 103...main memory device, 41a, 42a, 43a, 104...communication interface, 105...auxiliary memory device, 106...input / output I / O, BS0 to BSn...base station, L, NW...network.

Claims

1. a first acquisition unit configured to acquire first observation data indicating the number of times the communication terminal is within the communication area of each base station under the condition that the communication terminal is accessing a first website; a learning unit configured to estimate, by Bayesian estimation, a probability distribution of the communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station, the probability distribution being a prior distribution and a likelihood function being a probability distribution of the communication terminal being located in the communication area of each base station under the condition that the communication terminal is accessing the first website, the probability distribution being a posterior distribution obtained by updating the prior distribution with the likelihood function; an identification unit configured to identify a base station in a communication area in which the communication terminal is located, in a posterior distribution in which a value of the estimated posterior distribution is maximized; an output unit configured to output information about the identified base station as communication control information; A communication management device comprising:

2. 2. The communication management device according to claim 1, a second acquisition unit configured to acquire second observation data indicating the number of times the communication terminal has accessed the first website; The prior distribution is set based on the second observation data. A communication management device characterized by:

3. 2. The communication management device according to claim 1, The learning unit estimates the posterior distribution by estimating, based on the first observation data, parameters that maximize the likelihood function estimated using a maximum likelihood estimation method as parameters that maximize the posterior distribution. A communication management device characterized by:

4. 2. The communication management device according to claim 1, a third acquisition unit configured to acquire, based on the communication control information, information on a cloud at a cloud site that is the shortest physical distance from the specified base station, among the clouds at multiple cloud sites that provide the first website; a communication control unit configured to instruct a core network of a predetermined communication standard to set the connection destination of the communication terminal to the cloud at the cloud site, in accordance with the cloud information at the cloud site acquired by the third acquisition unit; A communication management device comprising:

5. 3. The communication management device according to claim 2, a first collection unit configured to collect, from a core network of a predetermined communication standard, a presence log indicating a base station in a communication area in which the communication terminal having the subscriber identification information is present and a time when the communication terminal is present; a second collection unit configured to collect, from the core network, a terminal IP address assigned to the subscriber identification information included in the visit log acquired by the first collection unit; a third collection unit configured to collect, from the core network, an access log including an access time to a website having a site IP address for each of the subscriber identification information based on the terminal IP addresses collected by the second collection unit; and Equipped with the first acquisition unit acquires the first observation data based on the presence log collected by the first collection unit and the access log collected by the third collection unit; The second acquisition unit acquires the second observation data based on the access log collected by the third collection unit. A communication management device characterized by:

6. a first acquisition step of acquiring first observation data indicating the number of times the communication terminal is within the communication area of each base station under the condition that the communication terminal is accessing the first website; a learning step of estimating, by Bayesian estimation, a probability distribution of the communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station, the probability distribution being a prior distribution and being a likelihood function obtained based on the first observation data, the probability distribution of the communication terminal accessing the first website under the condition that the communication terminal is located in the communication area of each base station; the posterior distribution being an updated prior distribution with the likelihood function; a step of identifying a base station in a communication area where the communication terminal is located in a posterior distribution in which a value of the estimated posterior distribution is maximized; an output step of outputting information about the identified base station as communication control information; A communication management method comprising:

7. 7. The communication management method according to claim 6, further comprising a second obtaining step of obtaining second observation data indicating the number of times the communication terminal has accessed the first website; The prior distribution is set based on the second observation data. A communication management method comprising:

8. 7. The communication management method according to claim 6, The learning step estimates the posterior distribution by estimating, based on the first observation data, parameters that maximize the likelihood function estimated using a maximum likelihood estimation method, as parameters that maximize the posterior distribution. A communication management method comprising:

9. 7. The communication management method according to claim 6, a third acquisition step of acquiring, based on the communication control information, information on a cloud at a cloud site that is the shortest physical distance from the specified base station, from among the clouds at multiple cloud sites that provide the first website; a communication control step of instructing a core network of a predetermined communication standard to set the connection destination of the communication terminal to the cloud at the cloud site, according to the cloud information at the cloud site acquired in the third acquisition step; A communication management method comprising:

10. 8. The communication management method according to claim 7, a first collection step of collecting, from a core network of a predetermined communication standard, a visit log indicating a base station in a communication area where the communication terminal having the subscriber identification information has visited and a time when the communication terminal has visited the base station; a second collection step of collecting, from the core network, a terminal IP address assigned to the subscriber identification information included in the visit log acquired in the first collection step; a third collection step of collecting from the core network an access log including an access time to a website having a site IP address for each of the subscriber identification information based on the terminal IP address collected in the second collection step; Equipped with the first acquisition step acquires the first observation data based on the visit log collected in the first collection step and the access log collected in the third collection step; The second acquisition step acquires the second observation data based on the access log collected in the third collection step. A communication management method comprising:

Images