JP2021090088A - Device, program, and method for identifying terminal on the basis of correspondence between communication type and target type - Google Patents

Abstract

To provide a device capable of determining a correspondence between a terminal and a target existing in an environment in which the terminal can exist by using information related to communication with the terminal, without relying on each other's positional relationship or only the positional relationship.SOLUTION: A terminal identification device includes communication type determining means that determines communication type information which is information related to a type of communication with a terminal on the basis of information related to communication acquired from communication means that communicates with at least one terminal, target type determination means that acquires environmental information which is information related to an environment from a sensor that senses the environment in which the terminal can exist, and determines target type information which is information related to at least one target type detected from the environmental information, and correspondence relationship determination means that determines information related to a correspondence relationship between the terminal related to the determined communication type information and the target related to the determined target type information on the basis of the type correspondence information which is the information that associates the information related to the communication type with the information related to the target type.SELECTED DRAWING: Figure 1

Description

The present invention relates to a technique for acquiring information about a terminal as a communication target, particularly a technique for identifying the terminal.

The upcoming 5th generation mobile communication system (5G) will make it possible to realize high-performance communication such as high speed, large capacity, low delay, and multi-terminal connection by using radio waves in the millimeter wave band. Here, millimeter waves have high straightness and are less likely to be diffracted, and there is a high possibility that their propagation will be blocked or attenuated by an object existing between the terminal and the base station. Therefore, in 5G, there is a big problem that the received power is sharply lowered due to the intervention of such an object, and the communication quality is significantly deteriorated.

On the other hand, if it is possible to predict a decrease in received power due to such an object, it is possible to maintain communication quality by controlling the communication path of the terminal. As a technique for predicting the received power, for example, Non-Patent Document 1 uses time-series three-dimensional environment information acquired by an RGB-D camera capable of generating a depth image in addition to an RGB image, and is used in a communication device by machine learning. A method for predicting received power is disclosed.

Specifically, in this method, for the time-series environmental information that is the result of imaging the communication environment, the time-series information of the received power measured (at the same time as imaging) at the terminal that received the radio wave from the transmitting station is used as the correct answer data. A machine learning model is constructed using the associated teacher data, and the predicted value of the received power at the receiving terminal is determined from the time-series environmental information acquired by the RGB-D camera using the constructed machine learning model. ing.

Further, for example, Patent Document 1 is a technique for improving the estimation accuracy of communication quality in the initial operation stage of a system or in a communication environment where the frequency of occurrence is low in the communication quality prediction processing by machine learning as disclosed in Non-Patent Gazette 1. Is disclosed. Specifically, in the virtual space formed from the measurement results of the communication environment, the information by the RGB-D camera is virtually generated, and the communication quality of the receiving terminal in the virtual space is estimated by the propagation simulation. It is said that it is possible to generate a large amount of training data above and build a machine learning model with improved estimation accuracy.

JP-A-2018-148297 Japanese Unexamined Patent Publication No. 2016-212675 Japanese Unexamined Patent Publication No. 2019-144941 Japanese Unexamined Patent Publication No. 2019-082363

Rishi Nishio, "Wireless Communication Quality Prediction and Communication Control by Machine Learning", Shingaku Giho, Vol. 118, No. 57, SR2018-1, pp. 1-8, 2018

However, in the prior art as disclosed in Non-Patent Document 1 described above, for example, in a normal situation where a plurality of objects are included in the time-series environmental information, when the correct answer data is obtained among these objects. It is not possible to identify the terminal corresponding to the received power information of the series. As a result, it becomes very difficult to build a machine learning model with high estimation accuracy that can be used in actual operation. That is, it is determined whether or not the object (which may include the terminal) captured by the RGB-D camera and the terminal related to the measured received power are the same target (whether or not they have a corresponding relationship). Since it cannot be done, it is not possible to generate highly reliable training data in the first place.

Even if a machine learning model as disclosed in Non-Patent Document 1 is applied, for example, an object (terminal) detected from time-series environmental information generated by an RGB-D camera is the machine learning model. It is completely unknown whether or not it is related to the received power predicted by, and therefore, even on the transmitting station side, which terminal is connected to the predicted received power, and even In the first place, it becomes impossible to determine even whether or not the predicted received power is related to any terminal.

In this regard, in the technique disclosed in Patent Document 1, the correspondence relationship between the terminal imaged by the RGB-D camera and the measured received power can be determined in the virtual space, so that, for example, a situation in which a plurality of terminals can move. It is possible to build a machine learning model corresponding to. However, even if such a model is applied, the terminal cannot be identified after all in the scene of predicting the received power in the actual operation, and the same problem as that of Non-Patent Gazette 1 as described above occurs.

Here, Patent Document 2 discloses an object recognition system that grasps the behavior of a mobile terminal and associates the mobile terminal with a moving object detected by a computer. In this system, each mobile terminal sequentially detects various state quantities such as acceleration acting on its own terminal, transmits the time-series detection result to the server as terminal behavior data, and the server receives an image input from the camera. The behavior of moving objects existing in the shooting range is monitored based on the signal, and data indicating the time change of the state amount related to the behavior of each moving object is stored in the server-side storage unit as estimation result history data. Next, by comparing the terminal behavior data transmitted from the mobile terminal with the estimation result history data for each mobile body, the correspondence relationship between the mobile body existing in the shooting range and the mobile terminal is specified.

However, in the system according to Patent Document 2, the only criterion for specifying the correspondence is the physical state quantity caused by the behavior of the mobile body, and each mobile terminal is a base station, which is a matter of concern. No information related to the communication to be performed is used. In addition, since it is necessary for the mobile terminal side to acquire information on a predetermined state that changes due to its own behavior, equipment such as a sensor capable of detecting the predetermined state is indispensable for each mobile terminal. Furthermore, since it becomes necessary to sequentially transmit the detection results, it becomes a technically troublesome situation.

Further, Patent Document 3 describes the flow line information of a person acquired by using a camera or the like in an environment in which one or more persons possessing a wireless receiver are staying or moving, and the wireless reception. A technique for associating with a machine (a person who owns it) is disclosed. Specifically, this technology identifies the time zone in which the person is staying in the predetermined area from the flow line information of the person, and the wireless transmitter installed at the position corresponding to the predetermined area and the receiver possessed by the person. From the reception history information generated by communication with and, a person who is likely to be staying in a predetermined area in that time zone is determined, and the person is associated with the flow line information that specifies the time zone. It has become a thing.

However, in the technique of Patent Document 3, in order to associate the flow line information of the person who possesses the wireless receiver with the flow line information of the person acquired by the camera, it is a major premise that the person stays in a predetermined area. It has become. Of course, by setting a large number of predetermined areas, the probability that the person will stay in the predetermined area increases, but in that case, it becomes necessary to install wireless transmitters in each of the large number of predetermined areas.

Further, in Patent Document 4, in order to estimate the position of the terminal that received the radio wave from the radio wave source, the radio wave attenuation of the environment is determined based on the object distribution of the environment estimated from the camera image or the like, and the radio wave attenuation is reflected. A technique for determining the position of a terminal based on the existence probability density function with the amount of the received radio wave of the terminal as a variable is disclosed.

However, in the technique of Patent Document 4, the association between the terminal related to the received radio wave information and the object (terminal) constituting the object distribution basically reflects the degree of radio wave attenuation at each position in the environment. Since it is performed based on the existence probability at each position, for example, when a large number of objects exist in the vicinity of the determined terminal position, especially when the degree of radio wave attenuation at each object position is similar. The possibility of incorrect mapping increases. Further, in actual operation, it is necessary to arrange a plurality of beacons in the area, and it is not realistic to apply them to the entire general communication area.

Therefore, the present invention provides information related to communication with the terminal without relying on the mutual positional relationship or only the positional relationship for the correspondence relationship between the terminal and the object existing in the environment in which the terminal can exist. It is intended to provide devices, programs and methods that can be utilized and determined.

According to the present invention
A communication type determining means for determining communication type information, which is information related to the type of communication with the terminal, based on information related to communication acquired from a communication means that communicates with at least one terminal.
Target type that acquires environmental information that is information related to the environment from a sensor that senses the environment in which the terminal can exist, and determines target type information that is information related to at least one target type detected from the environment information. Determining means and
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification device having a correspondence relationship determining means for determining information related to a correspondence relationship with an object is provided.

In the terminal identification device according to the present invention, the communication type determining means is
(A) Communication method type including at least one of eMBB (enhanced Mobile BroadBand) compatible communication method, URLLC (Ultra-Reliable and Low Latency Communications) compatible communication method, and mMTC (massive Machine Type Communication) compatible communication method. By selection from the group or
(B) By selecting from a communication data type group including at least one of voice call data, video distribution data, web page data, e-mail data, posting data, application data, device control data, and sensor data. ,
It is also preferable to determine the communication type information.

Further, as one embodiment of the terminal identification device according to the present invention, at least a part of the type correspondence information is information related to one-to-many, many-to-one, or many-to-many correspondence.
The correspondence relationship determination means is a terminal that uniquely determines the correspondence, a greedy algorithm that sequentially determines the correspondence relationship from a set of objects, or a combinatorial optimization algorithm that can solve the maximum flow problem of graph theory. It is also preferable to determine the information related to the correspondence with the target.

Further, as another embodiment of the terminal identification device according to the present invention, the above-mentioned communication means acquires the target type information from the terminal holding the target type information related to itself.
The terminal identification device uses the acquired target type information and the communication type information determined for the terminal holding the target type information to generate at least a part of the type correspondence information. It is also preferable to have more portions.

Further, as a further other embodiment of the terminal identification device according to the present invention, the target type determining means is a novel target in which a target detected at a certain time point is not detected or cannot be detected at a previous time point. Judge whether or not
Regarding the target type information of the new target, the correspondence relationship determining means is based on the type correspondence relationship information, and the communication type information of the terminal newly connected by communication within the predetermined time range including the certain time point or the certain time point. It is also preferable to determine only the correspondence with the terminal and determine the information related to the correspondence relationship with the terminal for the new target.

Further, in the above-described embodiment of the new target determination, the target type determining means is determined from the detection position and / or the change of the detection position of the target detected at the certain time point, and the position and / or of the target. It is also preferable to determine whether or not this target is a new target based on the speed information.

Further, as a further other embodiment of the terminal identification device according to the present invention, the target type determining means determines whether or not the target detected at a certain time point is the same as the target detected at the previous time point. ,
In the correspondence relationship determination means, it is determined that the target detected at the certain time point is the same as the target detected at the previous time point, and the target detected at the previous time point and a certain terminal correspond to each other. When it is determined that there is a relationship, it is also preferable that the target detected at that time point is determined to have a corresponding relationship with the certain terminal.

Further, as a further embodiment of the terminal identification device according to the present invention, the communication type determining means determines the position and / or speed of the terminal based on the information related to the radio wave of the communication as the information related to the communication. The terminal status information, which is the relevant information, is also determined.
The target type determining means also determines the target state information, which is information related to the position and / or speed of the target, from the detection position and / or the change of the detection position of the target.
The correspondence relationship determining means calculates the state correspondence degree, which is the degree of correspondence between the determined terminal state information and the determined target state information, and based on the state correspondence degree, the terminal and the target It is also preferable to determine the information related to the correspondence.

Further, as a further embodiment of the terminal identification device according to the present invention, the communication type determining means also includes terminal communication state information which is information related to the communication state with the terminal based on the information related to the communication. Decide and
The target type determination means also determines the target communication status information, which is information related to the communication status that will be realized with the target if the target includes a terminal, from the environment information.
The correspondence relationship determining means calculates the communication state correspondence degree, which is the degree to which the determined terminal communication state information and the determined target communication state information correspond, and based on the communication state correspondence degree, with the terminal. It is also preferable to determine the information related to the correspondence with the target.

Furthermore, as yet another embodiment of the terminal identification apparatus according to the present invention, the above-mentioned sensors are a plurality of sensors provided at different positions from each other.
The target type determining means acquires a plurality of environmental information from each of the plurality of sensors, determines the target type information from each of the plurality of environmental information, and among the determined target type information, the target type. Target type information for objects whose detection positions are close to a predetermined value or higher, and / or for objects whose feature amounts in the target detection area related to the target type information are similar to a predetermined value or higher. Is also preferably related to the same object.

Further, as a further embodiment of the terminal identification device according to the present invention, the target type determining means is derived from another terminal identification device existing in the vicinity, or from a sensor different from the above sensor in the other terminal identification device. Acquire the target type information determined from the acquired environment information,
It is also preferable that the correspondence relationship determining means also determines the information related to the correspondence between the acquired target type information and the terminal related to the determined communication type information based on the type correspondence information.

Furthermore, as yet another embodiment of the terminal identification device according to the present invention, the terminal includes a plurality of terminals installed or carried on a mobile body, and the terminal identification device is a terminal identification device.
An approach target identification means for identifying a plurality of targets that are estimated to approach each other later than a predetermined value based on the detection positions of the plurality of detected targets.
Information relating to the fact that it is presumed to approach at least one of at least one terminal determined to have a correspondence relationship with any of the plurality of identified targets by the correspondence relationship determination means. It is also preferable to further have a communication control means for transmitting the signal.

According to the present invention, the learning data includes the environmental information and the information related to the target detected from the environmental information, and the terminal identification device described above has a correspondence relationship with the target. Provided is a learning model for estimating terminal radio wave information, which is constructed by learning data in which information related to a communication state with a determined terminal is used as correct answer data.

According to the present invention, further, data including the environment information and information related to the target detected from the environment information is input to the above-mentioned learning model, and the communication state of the terminal output by the learning model is input. A terminal communication state estimation means that estimates information related to the communication state of this target as a terminal based on the information related to
A communication relay device is provided which has a communication control means for determining whether or not to switch the communication path of the target as a terminal based on the information related to the estimated communication state.

According to the present invention, further, it is a program that functions a computer capable of determining a correspondence relationship between at least one terminal and at least one object.
A communication type determining means for determining communication type information, which is information related to the type of communication with the terminal, based on information related to communication acquired from the communication means communicating with the terminal.
Target type determination means that acquires environmental information that is information related to the environment from a sensor that senses the environment in which the terminal can exist, and determines target type information that is information related to the type of the target detected from the environment information. When,
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification program that makes a computer function as a correspondence relationship determining means for determining information related to a correspondence relationship with an object is provided.

According to the present invention, further, it is a terminal identification method in a computer capable of determining a correspondence relationship between at least one terminal and at least one object.
Based on the information related to the communication acquired from the communication means that communicates with the terminal, the communication type information that is the information related to the type of communication with the terminal is determined, while the environment in which the terminal can exist is determined. A step of acquiring environmental information which is information related to the environment from a sensor to be sensed and determining target type information which is information related to the type of the target detected from the environmental information.
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification method is provided that includes a step of determining information relating to a correspondence between the subject and the subject.

According to the terminal identification device, the program and the method of the present invention, the correspondence between the terminal and the object existing in the environment in which the terminal can exist is the said, without relying on the mutual positional relationship or only the positional relationship. It is possible to make a decision using information related to communication with the terminal.

It is a schematic diagram which shows one Embodiment of the terminal identification apparatus by this invention. It is a schematic diagram which shows the specific example of the type correspondence relation information which concerns on this invention. It is a schematic diagram for demonstrating one Embodiment of the process in the communication type determination unit, the target type determination unit, and the correspondence relationship determination unit which concerns on this invention. It is a schematic diagram for demonstrating another embodiment in the processing in the communication type determination unit, the target type determination unit, and the correspondence relationship determination unit which concerns on this invention. It is a schematic diagram for demonstrating further other embodiment in the processing in the communication type determination unit, the target type determination unit, and the correspondence relationship determination unit which concerns on this invention. It is a schematic diagram for demonstrating further other embodiment in the processing in the communication type determination unit, the target type determination unit, and the correspondence relationship determination unit which concerns on this invention. It is a schematic diagram for demonstrating one application example of the terminal identification method by this invention. It is a schematic diagram for demonstrating one Embodiment of processing in the model construction part and the terminal radio wave information estimation part which concerns on this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[Terminal identification device]
FIG. 1 is a schematic view showing an embodiment of a terminal identification device according to the present invention.

The base station 1 as the terminal identification device according to the present invention shown in FIG. 1 is a communication relay device compatible with 5G (fifth generation mobile communication system) in the present embodiment, and is also a communication terminal compatible with 5G. It is a device capable of performing communication with a plurality of terminals 2. Further, in the present embodiment, the base station 1 includes a camera 103, which is an RGB-D camera capable of capturing a situation in a communication area with a predetermined angle of view.

The (RGB and depth) image data (video data) generated by the camera 103 includes
(A) A person who possesses or carries a terminal 2
(B) Moving objects such as automobiles, motorcycles, railroad cars, robots, drones, etc. equipped with, including, or boarding the terminal 2, and (c) goods, equipment, facilities, buildings to which the terminal 2 is attached / installed. , Fixed objects may be included (imaged), and people, moving objects, articles, equipment, facilities, buildings, etc. (trees, etc.) that are not related to the terminal 2 may be included. It can also include "objects" such as fixed objects (including plants).

By the way, while such an "object" can determine the correspondence with the terminal 2 to be identified, it also becomes an obstacle to communication radio waves because it exists between the terminal 2 and the base station 1. obtain. In particular, 5G, which is the communication method of the present embodiment, uses radio waves in the millimeter wave band for communication, but the millimeter wave has high straightness and is less likely to be diffracted, so that the terminal 2 and the base station 1 are used. There is a high possibility that the propagation will be blocked or attenuated by the "object" that exists between and.

Therefore, in 5G, it is a big problem that the received signal power at the base station 1 is drastically reduced due to the intervention of such an "object", and the communication quality is significantly deteriorated. Here, if it is possible to predict the decrease in the received signal power at the base station 1 due to such an "object", it is possible to maintain the communication quality by controlling the communication path of the terminal 2 or the like.

Therefore, the base station 1 of the present embodiment not only determines the correspondence between the terminal 2 and the "target", but also predicts the received signal power and controls the communication path, as will be described later. It is a device that makes it possible.

Similarly, in FIG. 1, the base station 1 first determines the correspondence between the terminal 2 and the "target", as a specific feature thereof.
(A) Information related to communication (for example, communication history information) acquired from a communication means (in this embodiment, a communication interface 101, a communication control unit 114, and a communication history information storage unit 102) that communicate with at least one terminal 2. ), A communication type determination unit 111 that determines "communication type information" which is information related to the type of communication with the terminal 2.
(B) At least one "environmental information" detected from the "environmental information" obtained from the sensor (camera 103 in the present embodiment) that senses the possible environment of the terminal 2 is acquired. Target type determination unit 112 that determines "target type information", which is information related to the type of "target", and
(C) The terminal 2 related to the determined "communication type information" is determined based on the "type correspondence information" which is the information in which the information related to the communication type and the information related to the target type are associated with each other. It also has a correspondence relationship determination unit 113 that determines "terminal target correspondence information" which is information related to the correspondence relationship with the "target" related to the "target type information".

Here, the "communication type information" in (A) above is, for example, a communication method specified in 5G (possibly specified or set for 5G).
(A) eMBB (enhanced Mobile BroadBand, high-speed, large-capacity) compatible communication method,
At least one of (b) URLLC (Ultra-Reliable and Low Latency Communications) compatible communication method and (c) mMTC (massive Machine Type Communication) compatible communication method. It can be the information of the communication method type selected from the included communication method type group.

Alternatively, the "communication type information" is a communication data type group including at least one of voice call data, video distribution data, web page data, e-mail data, posting data, application data, device control data, and sensor data. It may be the information of the communication data type (or data use type) selected from the above. Further, as this "communication type information", it is possible to adopt information of various other types of communication, for example, type information of a wireless communication standard other than 5G.

On the other hand, the "target type information" in the above (B) is information that identifies the type of the "target" such as "person", "automobile", and "cardboard (packed baggage)". In the present embodiment, when a "target" is detected from camera image data as "environmental information" by a known image recognition technology, the "class" set as a detection target may be set as "target type information". it can.

Further, the "type correspondence information" in (C) above may be prepared as general-purpose information common to general communication areas, but identifies terminals such as urban areas and factory premises areas. It is also preferable that the setter sets the communication type and the target type in advance in association with each other according to the communication in the predetermined area to be and the situation of the target. Alternatively, as will be described later, it is also possible for the type correspondence management unit 121 (FIG. 1) to automatically generate at least a part of the “type correspondence information”.

As described above, according to the base station 1 as the terminal identification device according to the present invention, the terminal 2 and the "object" existing in the environment in which the terminal 2 can exist (detected from the "environmental information"). The correspondence can be determined based on the correspondence of the type information (communication type information and target type information) related to each. That is, it is possible to determine the "terminal target correspondence information" by considering the correspondence relationship of the type information related to each of the terminal 2 and the "target" without depending on the mutual positional relationship.

As will be described later, the base station 1 may take an embodiment in which "terminal target correspondence information" is determined based not only on the type information related to the terminal 2 and the "target" but also on the mutual positional relationship. It is possible. However, in any case, the base station 1 can determine the correspondence relationship between the terminal 2 and the "target" without relying only on the mutual positional relationship.

Therefore, for example, when a large number of "objects" exist in the vicinity of the terminal 2 to be identified (when detected), an erroneous correspondence is determined because the difference in position between them is small. It is also possible to reduce the risk of being identified by considering the type information that is not related to the position.

Although 5G is adopted as the communication method between the base station 1 and the terminal 2 in the present embodiment, naturally other communication methods such as LTE may be used, and the terminal identification according to the present invention. The communication between the device and the terminal may be based on various other wireless communication standards.

For example, even in a communication method in which the problem of shielding by an object is not as remarkable as 5G, there are not a few situations in which it is desired to accurately identify a subordinate terminal using an "object" detected from "environmental information". For example, there are various terminal identification needs, such as determining the relationship between the browsing page of a user who is determined to have a corresponding relationship with a certain terminal and the flow line of the user and utilizing it for marketing and management. On the other hand, according to the terminal identification device according to the present invention, it is possible to carry out such a terminal identification process with high accuracy.

Further, the terminal identification device according to the present invention is not limited to a communication relay device such as a base station. For example, as a dedicated device for terminal identification processing, it may be provided in a form of being connected to a communication relay device / equipment such as a base station. Further, as the terminal identification device according to the present invention, it is also possible to use a cloud server, a non-cloud server device, a personal computer (PC), a notebook computer, a tablet computer, or the like equipped with the terminal identification program according to the present invention. is there.

Furthermore, a form in which at least one of the above (A) to (C), which is a component of the terminal identification device (base station 1) according to the present invention, is included in a device different from the other components. It is not impossible to take. For example, it is possible to realize the above-mentioned functions (A) to (C) by the whole of a plurality of servers. Here, even in such a case, all of these can be regarded as a terminal identification device or system that implements the terminal identification method according to the present invention.

[Functional configuration of terminal identification device, terminal identification program]
Similarly, in the functional block diagram of FIG. 1, the base station 1 has a communication interface 101, a communication history information storage unit 102, a camera 103, and a camera image storage as an embodiment of the terminal identification device and the communication relay device according to the present invention. It has a unit 104 and a processor memory. Here, the processor memory stores an embodiment of a communication relay program including the terminal identification program according to the present invention, and also has a computer function, and by executing this communication relay program, Perform terminal identification processing and communication relay processing.

Further, the processor memory has a communication type determination unit 111 including a terminal state determination unit 111a and a terminal communication state determination unit 111b, and a target type determination unit including the target state determination unit 112a and the target communication state determination unit 112b as functional components. It has a unit 112, a correspondence relationship determination unit 113, a communication control unit 114, a type correspondence relationship management unit 121, an approach target identification unit 131, a model construction unit 141, and a terminal radio wave information estimation unit 142. Note that these functional components can be regarded as the functions of the terminal identification program and the communication relay program stored in the processor memory, and arrows are drawn between the functional components of the base station 1 in the functional block diagram of FIG. The process flow shown in connection with is also understood as an embodiment of the terminal identification method and the communication relay method according to the present invention.

Similarly, in the functional block diagram of FIG. 1, the communication control unit 114 functions as a base station by controlling the wireless communication operation between the communication interface 101 and each terminal 2, and further, between each terminal 2. Acquires and records various information related to the communication carried out in the above, generates communication history information in which the information is arranged in chronological order, and stores and manages the communication history information storage unit 102.

Here, the communication control unit 114 naturally recognizes the communication method of communication with each terminal 2, and in the present embodiment, the communication history information is the terminal ID (identifier) of the terminal 2 for each terminal 2. ) And the communication method (corresponding standard) in 5G communication implemented between the terminal 2 and specifically, including a record associating with any one of eMBB, URLLC and mMTC. There is.

<Determination of communication type information>
The communication type determination unit 111 acquires communication history information from the communication history information storage unit 102, and describes the terminal ID of the terminal 2 to be identified and the communication method (corresponding standard) between the terminal 2 and the specific. The communication type information, which is the information associated with any one of eMBB, URLLC, and mMTC, is determined.

<Determining terminal status information (terminal position information, terminal speed information)>
Further, although it is a preferred embodiment in which the terminal identification process is performed in consideration of the position and / or speed of the terminal 2, which will be described later, the terminal state determination unit 111a of the communication type determination unit 111 is a communication history information storage unit. Based on the information related to the communication radio wave included in the communication history information acquired from 102 (or generated from the communication history information), for example, the received signal power (RSSI) of the radio wave signal received from the terminal 2, the terminal 2 It is also preferable to determine the terminal position information, which is the information related to the position.

Here, not only the received signal power of the base station 1 but also
(A) Received signal power measurement values at a plurality of base stations existing around the base station 1 and
(B) The terminal position, which is the time-series information of the location position of the terminal 2, is obtained by acquiring the received signal power measurement value of the terminal 2 that has received radio waves from a plurality of base stations, for example, by communication, and by using a well-known base station positioning technology. Information can be determined.

Further, the terminal state determination unit 111a can also calculate the time change portion of the terminal position from the terminal position information to determine the terminal speed information which is the time series information of the speed of the terminal 2. Hereafter, these determined terminal position information and terminal speed information will be collectively referred to as terminal state information.

By the way, as a change mode, regarding the above terminal speed information,
(A) Frequency shift of radio waves received from terminal 2,
(B) Fluctuation of received signal power (RSSI) of radio waves received from terminal 2 per hour,
(C) It is also preferable that the determination is based on the speed of the terminal 2 derived from at least one of the hourly fluctuations of the RTT in communication with the terminal 2.

Of these, regarding (a) above, time-series information of the deviation Δf_t from the frequency f0_t originally set for communication is generated from the time-series information of the frequency f_t of the received radio wave, and the deviation Δf_t is obtained. For example, by applying an object velocity measurement method using the Doppler effect, which is well known in the field of radio wave engineering, time-series information of the velocity vector v_e of the terminal 2 may be generated and used as the terminal velocity information.

Regarding (b) above, the fris transmission formula, which is well known in the field of radio frequency engineering, is used from the time series information of the received signal power (variable) E_t and the transmission signal strength from the terminal 2 set in advance. Therefore, time-series information of the distance D_t to the terminal 2 may be generated, and time-series information of the speed vector v_e of the terminal 2 may be generated from the time change of the distance D_t, and this may be used as the terminal speed information.

Further, regarding (c) above, when the communication distance (R_t * V / 2) is obtained by multiplying the RTTR_t by the radio wave propagation velocity V and the coefficient 0.5 that divides the RTT into one way from the time series information of RTTR_t. The series information may be generated, and the time series information of the speed vector v_e of the terminal 2 may be generated from the time change of the communication distance, and this may be used as the terminal speed information.

The velocity vector v_e described above is, in some cases or more accurately, a projection vector in a predetermined direction of the velocity vector of the terminal 2 (for example, the direction connecting the base station 1 and the terminal 2).

<Determining terminal communication status information>
Further, although it is a preferred embodiment in which the terminal identification process is performed in consideration of the communication state with the terminal 2, which will be described later, the terminal communication state determination unit 111b of the communication type determination unit 111 is used for communication history information. Communication history information is acquired from the storage unit 102, and the terminal communication status information, which is information related to the communication status with the terminal 2, is determined based on the communication history information.

Here, in the present embodiment, this terminal communication state information is
(Α) Information related to the presence or absence of a communication connection with the terminal 2, and (β) Received signal power (RSSI) of the radio wave signal received from the terminal 2.
Either one or both.

Of these, with respect to the above (α), the terminal communication state determination unit 111b provides time-series information as to whether or not a communication connection with the terminal 2 is established at each time point, that is, when communication is established at the time point t. 1. Two-value communication connection presence / absence variable that takes a value of -1 when it is not established:
(1) B_t ∈ {−1, 1}
Time series information of may be generated.

Further, regarding the above (β), the terminal communication state determination unit 111b may generate time-series information of the received signal power variable E_t indicating the signal power value at the time point t of the radio wave signal received from the terminal 2. Further, as described above, the terminal communication state determination unit 111b, as a preferred embodiment, provides the terminal communication state information including both the time series information of the communication connection presence / absence variable B_t and the time series information of the received signal power variable E_t. It is also preferable to determine.

Similarly, in the functional block diagram of FIG. 1, the camera 103 may be a photographing device compatible with visible light, near infrared rays, or infrared rays including a solid-state image sensor such as a CCD image sensor or a CMOS image sensor, and the web (Web). It can also be a camera, a stereo camera, an omnidirectional (omnidirectional) camera, or the like. Of course, instead of the camera 103, it is also possible to adopt a sensor that can sense the environment in which the terminal 2 can exist and generate environmental information, such as a LiDAR, a laser / infrared positioning device, a TOF camera, and a thermography device. is there.

Here, in the present embodiment, the camera 103 is an RGB-D camera capable of generating an RGB image and a depth image as environmental information, and the generated environmental information (RGB image data and depth image data) is a camera image. It is stored and managed by the storage unit 104.

Although the camera 103 is installed in the base station 1 in the present embodiment, for example, it is a camera installed at a position separated from the base station 1, for example, a surveillance camera in the city, and communicates with the base station 1. It may be connected. Further, as will be described later, it is also possible to take an embodiment in which a plurality of cameras 103 are provided at different positions regardless of whether the base station 1 is inside or outside.

<Determination of target type information>
The target type determination unit 112
(A) Acquire (RGB and depth) image data (environmental information) from the camera image storage unit 104, and obtain it.
(B) From the acquired image data, a "target" that may include the terminal 2 is detected.
(C) The "class" related to the detected "target" such as "person", "automobile" or "cardboard" is determined as the target type information which is the information related to the type of the target.

Here, specifically, the target type information in (c) above can be information in which the target ID given to the detected "target" and the "class" related to the "target" are associated with each other. ..

In addition, the "target" in (a) above is, for example,
(A) Person (user) who owns a mobile terminal,
(B) A car equipped with a terminal 2 having a drive recorder function, a CAN information transfer function, an interface function for automatic driving control by a server, and the like.
(C) An autonomous mobile robot or an autonomous flight drone equipped with a terminal 2 having an interface function for autonomous movement control by a server, and further.
(D) A person, a moving body, an article, or the like that may include the terminal 2 that is the communication destination related to the communication history information, such as an article attached / installed by the terminal 2 having a sensor information transfer function. it can. In some cases, equipment, facilities, buildings, fixed objects, etc. that may include the terminal 2 may also be "targeted".

Further, as the target detection process from the image data in the above (a), for example, a model for target detection is constructed based on a machine learning algorithm (for example, an algorithm using a neural network) known for various image recognition, and the target detection process is performed. Using the model, identify the detection area (for example, bounding box) in the image data where the "target" corresponding to the set "class" is presumed to exist, and further, the certainty that the detection area is the target. It is possible to adopt a well-known image recognition process such as calculating a score indicating the above and determining a detection region having a high score sufficient to satisfy a predetermined condition as a target region. Further, in this case, the detection position of the "target" can be a representative point (for example, the center of gravity or the midpoint of the lower end) of the determined target area.

By the way, when an RGB camera or a stereo camera is adopted as the camera 103, for example, non-patent documents: Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng for the camera image data which is the generated environmental information. -Yang Fu, Alexander C. Berg, “SSD: single shot multibox detector”, European Conference on Computer Vision, Computer Vision-ECCV 2016, pp. 21-37, by applying the object detector described in 2016. It is possible to determine the target area and the detection position.

When LiDAR is used as the sensor according to the present invention instead of the camera 103, for example, Charles R. Qi, Hao Su, Kaichun Mo, Leonidas are used for the point cloud (point cloud) which is the generated environmental information. J. Guibas, “PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation”, Journal of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77-85, using the object detector described in 2016 Thereby, the target area and the detection position can be determined.

Further, for example, it is also possible to apply the technique disclosed in Japanese Patent Application Laid-Open No. 2019-174164 to estimate the position of an object (which may include a communication terminal) from an RGB camera image using a machine learning algorithm.

Further, when the target type determination unit 112 does not detect the "target" from the environmental information, that is, when even one "target" is not measured (sensed), or when it is measured but is not detected due to the influence of noise or the like. It is also preferable to end the target type determination process for the environmental information.

Further, in the target detection process in the target type determination unit 112, the position (detection position) of the detected target can also be determined as described above, but in the present embodiment, the target is further determined for each detected target. Time-series information (movement history information) of the target position is generated after associating with the detection area (detection position) at each time point. This also makes it possible to track each detected object individually.

Here, for such a target tracking process, for example, a Kalman filter, which is a well-known state estimation method, is applied to the determined target area (bounding box), and the target detection area (from the state at the past time point to the current time point) ( The bounding box) is predicted, and the target area is determined based on the evaluation value using the overlapped area between the predicted detection area (bounding box) and the detection area (bounding box) detected at the present time as an evaluation value. It is also preferable.

By the way, such target tracking processing is described in, for example, non-patent documents: Alex Bewley, Zongyuan Ge, Lionel Ott, Fabio Ramos, Ben Upcroft, “Simple Online and Realtime Tracking”, Journal of 2016 IEEE International Conference on Image Processing (ICIP), Pp. 3464-3468, 2016.

Further, although in a preferred embodiment of the terminal identification process described later, in the target type determination unit 112, the target detected at a certain time point t is the previous time point, for example, the previous time point (t-1). It is also preferable to determine whether or not the target is a new object that has not been detected or cannot be detected in (), and notify the correspondence determination unit 113 of the determination result.

Here, the target type determination unit 112 creates a list of targets (target IDs) detected or tracked at each time point, and by referring to this list, the target detected at a certain time point t. It is also possible to determine whether or not is a new object. Further, as a modification mode, the target is a new target based on the information related to the position and / or speed of the target determined from the detection position and / or the change of the detection position detected at a certain time point t. It is also possible to determine whether or not this target is a new entry into the environment of the terminal identification target.

For example, specifically, when the distance from the boundary of the image data range (shooting range of the camera 103) by the camera 103 to the position of this target is less than a predetermined threshold value, it is determined that this target is a new target. You may. Or, in addition to this condition, if the velocity of this object has a component oriented within the image data range in the direction orthogonal to the closest boundary, it is determined that this object is a new object. Is also preferable.

Furthermore, as another embodiment, when a plurality of sensors other than the camera 103 or the above-mentioned camera are provided at different positions inside or outside the base station 1, the target type determination unit 112 determines the target type.
(A) Obtaining a plurality of environmental information from each of the plurality of cameras 103 (or sensors),
(B) Target type information is determined from each of these plurality of environmental information, and the target type information is determined.
(C) Of the determined target type information
(C1) For objects whose detection positions related to the target type information are closer than a predetermined value (for example, those whose distances are less than a predetermined threshold value) and / or
(C2) For those whose image feature amounts in the target detection area (bounding box) related to the target type information are similar to each other more than a predetermined value (for example, those whose distances from each other in the image feature amount space are less than a predetermined threshold value). ,
It is also preferable that the target type information relates to the same target. Further, in this case, the representative value (for example, the average value) of the detection position group for the target related to the target type information may be treated as the position of the same target.

As a result, it is possible to avoid a situation in which a certain terminal 2 is not included in the acquired environmental information, and as a result, the identification process of the terminal 2 fails. For example, with respect to the environmental information obtained by one camera 103 (or sensor), one object is located behind another object and is shielded by the other object, so that the environmental information is not included in the environmental information (not imaged). The situation will occur not a little. For example, from one camera 103, it is quite possible that the person holding the terminal 2 is obstructed by the stopped bus and cannot be seen.

On the other hand, if environmental information from a plurality of cameras 103 (or sensors) having different installation positions is used, an object that is not included in one environmental information is included in other environmental information that has a different sensing (measurement) viewpoint. As a result, it is fully possible to avoid the above-mentioned concerns.

By the way, as a typical example of using the target type information related to the plurality of cameras 103 (or sensors) as described above, the base station 1 is each of the other one or more base stations 1 existing around itself. Therefore, the same target determination process may be performed by receiving / acquiring the target type information generated by the camera 103 (or sensor) installed in the base station 1. In this case, it is possible for a plurality of base stations 1 to cooperate with each other to more preferably carry out the terminal identification process according to the present invention.

<Determination of target status information (target position information, target speed information)>
Furthermore, although it is a preferred embodiment in which the terminal identification process is performed in consideration of the position and / or speed of the terminal 2, which will be described later, the target state determination unit 112a of the target type determination unit 112 is the detected target. From the detection position and / or the change of the detection position, the information related to the position and / or velocity of the target, for example, the time series information of the position (target position information) and / or the time series information of the velocity vector (target velocity information). It is also preferable to determine the target state information.

By the way, this target velocity vector is combined with the velocity vector determined by the terminal state determination unit 111a as a projection vector in a predetermined direction (for example, the direction connecting the base station 1 and the terminal 2) of the target velocity vector. It may be decided.

<Determination of target communication status information>
Further, although it is a preferred embodiment in which the terminal identification process is performed in consideration of the communication state with the terminal 2, which will be described later, the target communication state determination unit 112b of the target type determination unit 112 may be used.
(A) Image data (environmental information) from the camera image storage unit 104 (RGB and depth) that includes not only the target for identifying the terminal but also the target that may interfere with communication (hereinafter, also referred to as the fault target). Acquire image data (environmental information) that can be included,
(B) From the acquired image data, it is also preferable to determine the target communication state information, which is the information related to the communication state to be embodied with the detected target if the detected target includes the terminal.

In the present embodiment, when a certain "object" is detected from one image data, the other object detected from the image data is treated as an "obstacle target" for the certain "object". ..

Here, the target communication status information determined in (a) above is
(Α') Communication connection enable / disable information (time-series information of communication connection enable / disable variable B'_t described later) and (β') Received radio field intensity information (time-series information of received power equivalent variable E'_t described later)
Either one or both of the above can be used.

First, in the case of the above (α'), the target communication state determination unit 112b determines the detection position of the "target" detected from the acquired image data, and when the "failure target" is detected, the "failure target". Based on the detection position of
(A) Determine the straight line connecting the "target" and base station 1 (antenna),
(B) Communication connection availability information (shielding presence / absence information) whether or not the "failure target" is located on this straight line or within a predetermined area including this straight line, or whether or not this straight line is blocked. Is calculated,
(C) The calculated communication connection availability information can be determined as the target communication status information.

More specifically, as the communication connection availability information in (b) above, the detection position of any "failure target" is the above straight line at a certain point in time t (= k, k + 1, ..., k + M). A binary communication connection enable / disable variable that takes a value of -1 if it is located on a minute or within a rotating body region of a predetermined size that includes this straight line as a rotation axis, and 1 if it is not.
(2) B'_t ∈ {−1, 1}
Time series information of is generated, and this may be used as the target communication state information. Here, the rotating body region may be a cylindrical region, or may be formed by rotating a predetermined curve around a rotation axis such as an ellipsoid.

Further, as a modification mode, the target communication state determination unit 112b sets a predetermined size (cross-sectional area at the detection position) in advance for the "failure target" according to the type (class), and any of the "failure targets". When the "obstacle target" blocks the above straight line portion by its size (cross-sectional area) at the detection position (the above straight line portion penetrates the cross section of the "obstacle target"), -1, If this is not the case, B'_t in (2) above may be defined as a communication connection availability variable that takes a value of 1.

On the other hand, in the case of the above (β'), the target communication state determination unit 112b has the detection position of the "target" detected from the acquired image data, and when the "failure target" is detected, the "failure target". Based on the detection position of
(A) Determine the straight line connecting the "target" and base station 1 (antenna),
(B) Calculate the degree of shielding information related to the degree to which the "obstacle target" blocks a predetermined area including this straight line.
(C) From the calculated degree of shielding information, it is also preferable to determine as the target communication state information the information related to the strength of the radio wave that will be received from the "target" if the "target" includes the terminal 2. Here, specifically, the shielding degree information in (b) above is calculated as follows.

First, a predetermined size (cross-sectional area at a detection position having a predetermined area) is set in advance for the "obstacle target" according to the type (class), and further, the above straight line portion is used as the rotation axis. After setting a rotating body region of a predetermined size to be included as, at a certain point in time t (= k, k + 1, ..., k + M),
(B1) In any of the "obstacle targets", a part of the cross-sectional region is not included in the above-mentioned rotating body region at the detection position (the cross-sectional region of the obstacle target and the rotating body region have an overlapping portion). If not) then take a value of 1, while
(B2) In any of the "obstacle targets", a part of the cross-sectional region is included in the above-mentioned rotating body region at the detection position (the cross-sectional region of the obstacle target and the rotating body region have an overlapping portion). ) in this case, the following equation _{(3) R = (S a} ∩S b -) / S a
The time series information of the variable E'_t that takes the R value calculated by can be used as the shielding degree information. Incidentally, also in the case of the above (b1), the case where the R value is 1 (although the R value calculation process does not need to be executed) can be included in the above equation (3) after all.

Here, in the above equation (3), S _a is a set (for example, a unit point forming the region) representing a cross-sectional region (perpendicular to the rotation axis) at the detection position of the "obstacle target" in the rotating body region. A set of regions), and S _b is a set representing a cross-sectional region at the detection position of the “obstacle target” (for example, a set of unit point regions forming the region). Further, S _b ^- is _{a complement of S b} , and "/" is the area value of the cross-sectional area related to the set of molecules (for example, the number of unit point regions) and the area value of the cross-sectional area related to the denominator (for example, the unit). It is an operator that indicates division by the number of point domains).

Next, the target communication state determination unit 112b displays the time-series information of the variable E'_t (or the variable E'_t multiplied by a predetermined constant) if the "target" includes the terminal 2. The information related to the strength of the radio wave to be received from "" is used as the target communication status information. Incidentally, hereinafter, the variable E'_t will be referred to as a received power equivalent variable in order to distinguish it from the above-mentioned received signal power variable E_t.

When there are two or more "obstacle targets" that take the above R value, S _b is the region formed by the entire cross-sectional region of these "obstacle targets", that is, the union of these cross-sectional regions. It may be a represented area. Further, the rotating body region may be a cylindrical region, or may be formed by rotating a predetermined curve around a rotation axis such as an ellipsoid.

Further, as a modification mode, the target communication state determination unit 112b uses a trained "target radio wave information estimation model" that outputs information related to the strength of the received radio wave according to the input image data, and obtains an image. From the data, if the "target" includes the terminal 2, the information related to the strength of the radio wave that will be received from the "target" is derived, and the information related to the strength of the radio wave is determined as the target communication state information. You may.

Here, as the above-mentioned "target radio wave information estimation model", a known machine learning model as disclosed in Non-Patent Document 1 can be adopted. Specifically, the image data at a certain time point t (= k, k + 1, ..., k + M) is input to this model, the estimated value of the received signal power is output, and this estimated value is equivalent to the received power. As the variable E'_t value, the time series information of the received power equivalent variable E'_t is used as the target communication state information.

Similarly, in the functional block diagram of FIG. 1, the type correspondence management unit 121 includes information related to the type of communication and information related to the type of target used in the terminal identification process in the correspondence relationship determination unit 113, which will be described later. Saves and manages the type correspondence information, which is the information associated with.

FIG. 2 is a schematic diagram showing a specific example of the type correspondence information according to the present invention. Here, in this specific example, the type correspondence relationship information is a type correspondence relationship table.

First, in the type correspondence relationship table shown in FIG. 2 (A), the communication type "URLLC" is associated with the target type "automobile", and the communication type "eMBB" corresponds to the target type "person". Further, the communication type "mMTC" is associated with the target type "cardboard". That is, in this case, the communication type associated with the target type is the communication method type (in 5G).

On the other hand, in the type correspondence table shown in FIG. 2B, the communication type "control information communication" is associated with the target type "robot", and the communication type "video distribution" is associated with the target type "person". Is associated, and further, the communication type "sensor information transfer" is associated with the target type "cardboard". That is, in this case, the communication type associated with the target type is the communication data type (or data usage type).

In the type correspondence relationship table described above, a one-to-one correspondence is made between the target type and the communication type, but unlike that, at least a part thereof is related to a one-to-many, many-to-one, or many-to-many correspondence. It is also possible to set and use the information type correspondence table.

For example, in the type correspondence table shown in FIG. 2C, the communication type "URLLC" is associated with all of the target types "automobile", "drone", and "robot", and there is a many-to-one correspondence. Includes relationships.

Further, in the type correspondence table shown in FIG. 2 (D), two communication types "URLLC" and "eMBB" are associated with the target type "automobile", and two target types "person" are also associated with each other. The communication types "eMBB" and "mMTC" are associated with each other, while the communication type "eMBB" is associated with two target types "automobile" and "person", and the communication type" mMTC" is associated with 2 It can be considered that the two target types "person" and "cardboard" are associated with each other, and in the end, the type correspondence table shown in FIG. 2 (D) includes a many-to-many correspondence. ing.

As described above, regarding the specific type correspondence relationship as shown in FIGS. 2 (A) to 2 (D), the setter communicates in a predetermined area where the terminal should be identified, such as an area in the city or an area in the factory premises. It can be set according to the situation of the target. Further, depending on the situation, a one-to-one correspondence may be made between the target type and the communication type, or at least a part thereof may have a one-to-many, many-to-one, or many-to-many correspondence. It is possible.

For example, in a certain area to be identified as a terminal, communication with the robot may be performed by both mMTC for transferring sensor information and URLLC for control information communication. In addition, there may be a situation in which both the person and the robot perform communication by eMBB for transmitting and receiving moving images.

Further, as a preferred modification mode, it is also preferable that the type correspondence management unit 121 automatically generates at least a part of these type correspondence tables. For example
(A) The terminal 2 holds the target type information related to itself (for example, "cardboard" in the case of the terminal 2 attached to the cardboard), and the target type information held by the terminal 2 is used as a base at the time of communication connection or as appropriate. Send to station 1
(B) The communication control unit 114 acquires the target type information related to the terminal 2 from such a terminal 2 via the communication interface 101.
(C) The type correspondence management unit 121 determines the acquired target type information and the terminal 2 (source of the target type information) that holds the target type information (in the communication type determination unit 111). It is also preferable to generate at least a part of the type correspondence table by using the communication type information.

<Determination of correspondence: Use communication type information and target type information>
Returning to the functional block diagram of FIG. 1, the correspondence relationship determination unit 113 is a terminal 2 related to the communication type information determined based on the "type correspondence relationship information" stored and managed by the type correspondence storage unit 121. And the terminal target correspondence information with the target related to the determined target type information (for example, the terminal target correspondence table in which the correspondence relationship between the terminal ID and the target ID is recorded) is determined.

FIG. 3 is a schematic diagram for explaining an embodiment of processing in the communication type determination unit 111, the target type determination unit 112, and the correspondence relationship determination unit 113.

In the embodiment shown in FIG. 3, the base station 1 is
(A) Terminal 2_001, which is affixed to the cardboard and has a terminal ID of 001,
(B) Terminal 2_002 with a terminal ID of 002 mounted on a car, and (c) Terminal 2_003 with a terminal ID of 003 possessed by a person.
Is communicating with. Incidentally, the terminal ID of each terminal is given to the terminal when the base station 1 establishes a communication connection with each terminal.

Here, the communication type determination unit 111 acquires information relating to the type of communication being performed with each terminal, associates the communication type "mMTC" with the terminal 2_001 (terminal ID = 001), and terminals 2_002 (terminal 2_002). A communication type table (communication type information) is generated in which the communication type "URLLC" is associated with the terminal ID = 002) and the communication type "eMBB" is associated with the terminal 2_003 (terminal ID = 003).

On the other hand, the target type determination unit 112 uses the image data obtained by the camera 103 to obtain the automobile (b), the person (c), and the corrugated cardboard (a) as "automobile", "person", and "person", respectively. It is detected as "cardboard", and 001, 002 and 003 are assigned as target IDs to each.

Next, the target type determination unit 112 associates the target type "automobile" with the automobile (target ID = 001) and corresponds to the target type "person" with the person (target ID = 002) by summarizing these processing results. Further, a target type table (target type information) in which the target type "cardboard" is associated with the cardboard (target ID = 003) is generated.

Finally, the correspondence relationship determination unit 113 is generated by using the type correspondence relationship table which is the type correspondence relationship information in which the target type and the communication type are associated one-to-one (as shown in FIG. 3). The terminal target correspondence table is generated from the communication type table and the target type table.

Here, specifically, the correspondence relationship determination unit 113
(A1) In the communication type table, one communication type (for example, "mMTC") associated with the terminal ID (for example, terminal ID = 001) of one terminal (for example, terminal 2_001) to be identified is read out.
(A2) In the type correspondence table of FIG. 3, one target type (for example, "cardboard") corresponding to one communication type (for example, "mMTC") read in the above (a1) is read out.
(A3) In the target type table, one target ID (for example, target ID = 003) associated with one target type (for example, “cardboard”) read in (a2) above is read out.
(A4) The terminal ID (for example, terminal ID = 001) of one terminal (for example, terminal 2_001) to be identified in the above (a1) and one target ID (for example, target ID = 003) read in the above (a3). Generate one record that was recorded in association with
(A5) For each terminal (terminal 2_001, terminal 2_002, and terminal 2_003) to be identified, the steps (a1) to (a4) above are repeated to create a terminal target correspondence table (as shown in FIG. 3, for example). It is also preferable to generate.

Incidentally, the correspondence relationship determination unit 113 can also generate the terminal target correspondence table by the procedure completely opposite to the steps (a1) to (a4) above. That is,
(A1') In the target type table, one target type (for example, "automobile") associated with the target ID (for example, target ID = 001) of one target (for example, automobile) that is a candidate for the terminal identification destination is read out. ,
(A2') In the type correspondence table of FIG. 3, one communication type (for example, "URLLC") corresponding to one target type (for example, "automobile") read in the above (a1') is read out.
(A3') In the communication type table, one communication ID (for example, communication ID = 002) associated with one communication type (for example, "URLLC") read in the above (a2') is read out.
(A4') The target ID (for example, target ID = 001) of one target (for example, an automobile) that is a candidate for the terminal identification destination in the above (a1') and one communication ID (for example, the communication ID read in the above (a3')). Generate one record recorded in association with communication ID = 002),
(A5') For each target (automobile, person, and cardboard) that is a candidate for the terminal identification destination, the steps (a1') to (a4') above are repeated to support the terminal target (as shown in FIG. 3). It is also preferable to generate a table.

The processing when the type correspondence relationship table (type correspondence information) is information in which a one-to-one correspondence is made between the communication type and the target type has been described above. In response to this, processing when at least a part of the type correspondence relationship table (type correspondence relation information) is information related to one-to-many, many-to-one, or many-to-many correspondence will be described below.

In this case as well, basically, based on the type correspondence table, the process of investigating the correspondence between the communication type table (communication type information) and the target type table (target type information) is performed, but the correspondence relationship is determined. As one preferable method, the terminal 113 (FIG. 1) may generate a terminal target correspondence table by a greedy algorithm that sequentially determines a correspondence relationship from a terminal 2 in which the correspondence is uniquely determined and a set of targets. preferable.

Specifically, the correspondence relationship determination unit 113
(A) In the target type table (or communication type table), the target type (or the terminal ID of one terminal 2 to be identified) associated with the target ID of one target that is a candidate for the terminal identification destination (or the terminal ID of one terminal 2 that is the identification target). (Communication type) is read,
(B) In the type correspondence table, read out the communication type (or target type) that has a correspondence relationship with the read target type (or communication type).
(C) In the communication type table, the processes (a) to (c) for specifying the terminal ID associated with the read communication type (or target type) are particularly the steps (b) and (c). It is also preferable to sequentially carry out the target ID (or terminal ID) that can be uniquely read (specified) in the above.

As another preferred method, the correspondence relationship determination unit 113 may generate a terminal target correspondence table by a combinatorial optimization algorithm that can solve the maximum flow problem of graph theory. In particular,
(A) A bipartite graph is constructed with each element (record) of the communication type table and each element (record) of the target type table as a node.
(B) A maximum flow problem (from source to sink) in which the maximum flow rate of each link is defined by providing a source sword (start point node) and a sink node (end point node) with the bipartite graph of (a) above in between. Set the graph of (problem to find the maximum total flow rate),
(C) Correspondence between each element (record) of the communication type table and each element (record) of the target type table using the Ford-Fulkerson algorithm well known in the field of graph theory. Determine the relationship (generate the terminal target correspondence table)
It is also preferable. Of course, it is also possible to generate a terminal target correspondence table by using another combinatorial optimization algorithm.

FIG. 4 is a schematic diagram for explaining other embodiments in the processing by the communication type determination unit 111, the target type determination unit 112, and the correspondence relationship determination unit 113.

In the embodiment shown in FIG. 4, as in the embodiment of FIG. 3, the base station 1 is (a) a terminal 2_001 attached to a corrugated cardboard and having a terminal ID of 001, and (b) a terminal mounted on an automobile. It communicates with terminal 2_002 having an ID of 002 and (c) terminal 2_003 possessed by a person and having a terminal ID of 003.

Here, the communication type determination unit 111 acquires information relating to the type of communication being performed with each terminal, associates the terminal 2_001 (terminal ID = 001) with "mMTC", and terminals 2_002 (terminal ID). = 002) is associated with "URLLC", and terminal 2_003 (terminal ID = 003) is associated with "eMBB" to generate a communication type table.

On the other hand, the target type determination unit 112 uses the image data obtained by the camera 103 to obtain the automobile (b), the person (c), and the corrugated cardboard (a) as "automobile", "person", and "person", respectively. It is detected as "cardboard", and 001, 002 and 003 are assigned as target IDs to each.

Next, the target type determination unit 112 associates the automobile (target ID = 001) with the "automobile", associates the person (target ID = 002) with the "person", and further corrugates cardboard by summarizing these processing results. Generate a target type table in which "cardboard" is associated with (target ID = 003).

Finally, the correspondence relationship determination unit 113 uses the type correspondence relationship table in which the correspondence relationship between the target type and the communication type is not necessarily one-to-one (as shown in FIG. 4), and the communication type table and the communication type table are generated. The terminal target correspondence table is generated from the target type table.

Here, specifically, the correspondence relationship determination unit 113 first,
(A1) In the type correspondence relationship table of FIG. 4, the target type "corrugated cardboard" in which the communication type having a correspondence relationship is uniquely determined is recognized, and further, the communication type "mMTC" having a correspondence relationship with this is specified.
(A2) In the target type table, the target ID (target ID = 003) associated with the recognized target type "cardboard" is specified.
(A3) In the communication type table, the terminal ID (terminal ID = 001) associated with the communication type "mMTC" specified in (a1) above is specified.
(A4) A record recorded by associating the specified target ID (target ID = 003) with the specified terminal ID (terminal ID = 001) is generated and used as a part of the terminal target correspondence table.

Next, the correspondence relationship determination unit 113
(B1) In the communication type table, it is recognized that the communication types other than "mMTC" for which the correspondence destination has already been determined are "URLLC" and "eMBB".
(B2) In the type correspondence table of FIG. 4, the target type "person" may have a correspondence relationship only with "eMBB" among the "URLLC" and "eMBB" recognized in (b1) above (that is, "eMBB". Recognizing that it has a unique correspondence except for "mMTC")
(B3) In the target type table, the target ID (target ID = 002) associated with the target type "person" recognized in (b2) above is specified.
(B4) In the communication type table, the terminal ID (terminal ID = 003) associated with the communication type "eMBB" recognized in (b2) above is specified.
(B5) A record recorded by associating the specified target ID (target ID = 002) with the specified terminal ID (terminal ID = 003) is generated and used as a part of the terminal target correspondence table.

Finally, the correspondence relationship determination unit 113
(C1) The target type "automobile" associated with the target ID (target ID = 001) whose correspondence destination has not yet been determined in the target type table, and the communication ID whose correspondence destination has not yet been determined in the communication type table (c1). Recognizing that the communication type "URLLC" associated with the communication ID = 002) has a correspondence relationship in the type correspondence table of FIG.
(C2) A record recorded by associating the target ID (target ID = 001) recognized in the above (c1) with the terminal ID (terminal ID = 002) is generated to complete the terminal target correspondence table. ..

By the way, in the above processing, the processing is initially started from the step of recognizing the target type "corrugated cardboard" in which the communication type having a correspondence relationship is uniquely determined.
(A1') In the type correspondence relationship table of FIG. 4, the process can be started from the step of recognizing the communication type "URLLC" in which the target type having a correspondence relationship is uniquely determined. That is, in the above step, the terminal target correspondence table can be generated by the exact reverse procedure regarding the target type and the communication type.

In this way, even when using the type correspondence table (type correspondence information) including the one-to-many, many-to-one, or many-to-many correspondence that can be sufficiently configured depending on the situation of the terminal and the target, the terminal target It is possible to generate a correspondence table (terminal target correspondence information) and facilitate the completion of the terminal identification process.

The embodiment of the terminal identification process when at least a part of the type correspondence relationship table (type correspondence relationship information) is information related to one-to-many, many-to-one, or many-to-many correspondence has been described above. Hereinafter, other embodiments in the terminal identification process using such a type correspondence table (type correspondence information) will be described.

As described above, when at least a part of them uses the type correspondence table related to the one-to-many, many-to-one, or many-to-many correspondence, a plurality of "communication types" are used for the "target type" of the detected target. Is in a correspondence relationship, or a plurality of "target types" are in a correspondence relationship with the "communication type" of the terminal 2 to be identified, and there is a possibility that the terminal identification process will eventually fail. ..

On the other hand, in an environment in which terminals should be identified, a plurality of objects of different types have a terminal 2 that performs the same type of communication, or a plurality of objects of the same type each perform different types of communication. Since a situation in which a plurality of terminals 2 are provided can occur frequently, the failure of the terminal identification process as described above must be avoided as much as possible.

Therefore, the target type determination unit 112 (FIG. 1) determines whether or not the target detected at a certain time point t is the same as the target detected at the previous time point, for example, the previous time point (t−1). (Determine whether or not the target is being tracked with one target ID), notify the determination result to the correspondence relationship determination unit 113 (FIG. 1), and the correspondence relationship that received the notification. The determination unit 113
(A) The target detected at the time point t is determined to be the same as the target detected at the previous time point (for example, the time point (t-1)) (the target tracked with one target ID). And (b) at the previous time point (for example, time point (t-1)), when it is determined that the detected target and a certain terminal 2 have a corresponding relationship.
It is also preferable to determine that the target detected at the certain time point t has a correspondence relationship with the certain terminal 2.

As a result, for example, even if a plurality of objects of the same type are detected at a certain time, the target that has succeeded in associating with the terminal 2 in the past is regarded as being continuously tracked, and the terminal 2 is the same as the past. (Terminal ID) can be associated with each other. Here, in the target type table and the communication type table, the reference target is narrowed down by excluding the set (record) of the target and the terminal 2 that have been successfully associated with each other, so that the remaining association can be easily succeeded. You can also do it.

However, even with the method described above, the terminal identification process may not be completed depending on the situation. For example, as described above, when a plurality of objects of the same type are detected at a certain time, and then none of these objects are identified as the terminal 2 and continue to stay in this environment, the above-mentioned It becomes difficult to proceed with the terminal identification process only by the method.

Therefore, (a) the target type determination unit 112 (FIG. 1) may not detect or detect the target detected at a certain time point t at the previous time point, for example, the previous time point (t-1). Determine if it is not a "new target" and
(B) The correspondence relationship determination unit 113 (FIG. 1) determines the target type information of this “new target” at the time point t or at the predetermined time including the time point t based on the type correspondence relationship table (type correspondence relationship information). It is also possible to take an embodiment in which only the correspondence with the communication type information of the newly connected terminal 2 is determined within the range, and the information related to the correspondence relationship with the terminal 2 regarding the "new target" is determined. preferable.

As a result, for example, in a situation where a plurality of objects of the same type are detected at a certain time, even if the association with these terminals 2 is not successful, they are newly detected (identify the terminal). For the target (which has entered the environment where it should be), it is possible to succeed in associating with the terminal 2 which is also newly connected by communication.

FIG. 5 is a schematic diagram for explaining further other embodiments in the processing by the communication type determination unit 111, the target type determination unit 112, and the correspondence relationship determination unit 113.

In the embodiment shown in FIG. 5, the base station 1 is at time T in the same manner as in the embodiment of FIG.
(A) Terminal 2_001, which is affixed to the cardboard and has a terminal ID of 001,
(B) Terminal 2_002 with a terminal ID of 002 mounted on a car, and (c) Terminal 2_003 with a terminal ID of 003 possessed by a person.
At the next time (T + 1), in addition to these terminals, a new one
(D) Terminal 2_004 mounted on a car and having a terminal ID of 004
Is also communicating with. Incidentally, the terminal ID of each terminal is given to the terminal when the base station 1 establishes a communication connection with each terminal.

Here, in the present embodiment, the same type correspondence table as in the embodiment of FIG. 3 is used. Therefore, the communication type determination unit 111 and the target type determination unit 112 generate the same communication type table and target type table as those shown in FIG. 3 at time T, respectively, and as a result, at this time T, FIG. A terminal target correspondence table similar to that shown in 3 is generated.

Next, at the subsequent time (T + 1), the communication type determination unit 111 records a record in which the terminal ID (terminal ID = 004) of the newly connected terminal 2_004 and the communication type "URLLC" are associated with each other. , Add to the already generated communication type table and add a new flag to this record. On the other hand, the target type determination unit 112 adds a record associating the newly detected target ID (target ID = 004) with the target type "automobile" to the already generated target type table. Similarly, a new flag is added to this record.

Next, the correspondence relationship determination unit 113
(A1) In the communication type table, the communication type "URLLC" associated with the terminal ID (terminal ID = 004) of the terminal 2_004 to be identified with the new flag is read out.
(A2) In the type correspondence table of FIG. 5, the target type "automobile" having a correspondence relationship with the communication type "URLLC" read in the above (a1) is read out.
(A3) In the target type table, the target ID (target ID = 004) of the target (record) to which the target type "automobile" read in (a2) above is associated and a new flag is added is read. ,
(A4) A record is generated in which the terminal ID (terminal ID = 004) of the terminal 2_004 to be identified in the above (a1) is associated with the target ID (target ID = 004) read in the above (a3). Then, it is added to the already generated terminal target correspondence table (the terminal target correspondence table is updated).

By the way, the correspondence relationship determination unit 113 can also generate the terminal target correspondence table by the procedure opposite to the above step. That is,
(A1') In the target type table, it is also possible to start from the step of reading the target type "automobile" associated with the target ID (target ID = 004) of the target that is a candidate for the terminal identification destination to which the new flag is given. It is possible.

<Determination of correspondence: Terminal status information and target status information are also used>
As described above, various embodiments of the terminal identification process based on the communication type information and the target type information have been described with reference to FIGS. 3 to 5, but hereinafter, the terminal using the “terminal state information” and the “target state information”. An embodiment in which the identification process is preferably performed will be described.

As described in detail above, the terminal state determination unit 111a (FIG. 1) of the communication type determination unit 111 has "terminal state information" which is information related to the position and / or speed of the terminal 2, for example, the position of the terminal 2. Time-series information (terminal position information) and time-series information (terminal speed information) of the speed vector of the terminal 2 can be determined. On the other hand, the target state determination unit 112a (FIG. 1) of the target type determination unit 112 is "target state information" which is information related to the position and / or speed of the target, for example, time series information (target position information) of the target position. And the time series information (target velocity information) of the target velocity vector can be determined.

Next, the correspondence relationship determination unit 113 (FIG. 1) calculates the "state correspondence degree" which is the degree of correspondence between the determined "terminal state information" and the "target state information", and this "state correspondence degree". It is also preferable to generate terminal target correspondence information (terminal target correspondence table) based on the above.

Here, the position correspondence degree LC as the "state correspondence degree" between the terminal position information (time series information of the position of the terminal 2) and the target position information (time series information of the target position) is, for example, a predetermined time interval. It can be a representative value (for example, an average value) in the predetermined time interval for the reciprocal of the absolute value (distance) of the difference between the position of the terminal 2 and the target position at each time point.

Further, the speed correspondence degree VC as the "state correspondence degree" between the terminal speed information (time series information of the speed vector of the terminal 2) and the target speed information (time series information of the target speed vector) is, for example, a predetermined time interval. It can be a representative value (for example, an average value) in the predetermined time interval for the inverse of the magnitude of the difference between the speed vector of the terminal 2 and the target speed vector at each time point.

The correspondence relationship determination unit 113 is here.
(A) There is a possibility that there is a correspondence relationship according to the terminal target correspondence table (although it cannot be uniquely associated only with the terminal target correspondence table) (the corresponding communication type and the corresponding target type in the table are Of the (supported) terminal 2 and the target group
(B) The "state correspondence" (position correspondence LC and / or speed correspondence VC) exceeds a predetermined threshold (position correspondence threshold LC_th and / or speed correspondence threshold VC_th) ((LC> LC_th) and / Or (VC> VC_th)) pairs are assumed to correspond to each other
(C) It is also preferable to add the set of records to the terminal target correspondence table.

FIG. 6 is a schematic diagram for explaining further other embodiments in the processing by the communication type determination unit 111, the target type determination unit 112, and the correspondence relationship determination unit 113.

In the embodiment shown in FIG. 6, the base station 1 is similar to the situation at the time (T + 1) in the embodiment of FIG.
(A) Terminal 2_001, which is affixed to the cardboard and has a terminal ID of 001,
(B) Terminal 2_002, which is installed in an automobile and has a terminal ID of 002,
(C) Terminal 2_003 possessed by a person and having a terminal ID of 003, and (d) Terminal 2_004 mounted on a car and having a terminal ID of 004.
Is communicating with.

Here, the communication type determination unit 111 acquires and determines the communication type of communication with the terminal and the terminal position (terminal status information) of the terminal for each terminal, and terminal 2_001 (terminal ID = 001). ) Is associated with the communication type "mMTC" and the terminal position (100,200,50) (x, y and z coordinate values in the xyz spatial coordinate system, respectively), and the terminal 2_002 (terminal ID = 002) is associated with the communication type "URLLC". Corresponds to the terminal position (50,150,100), associates the communication type "eMBB" with the terminal 2_003 (terminal ID = 003) and the terminal position (100,230,130), and further associates the communication type "eMBB" with the terminal 2_004 (terminal ID = 004). Generates a communication type table that associates with the terminal position (200,150,100).

On the other hand, from the image data obtained by the camera 103, the target type determination unit 112 selects the automobile of the above (b), the person of the above (c), the cardboard of the above (a), and the automobile of the above (d), respectively. It is detected as "," person "," cardboard "and" automobile ", and 001, 002, 003 and 004 are assigned as target IDs to each, and each detection position is assigned to each target position (target state information). decide.

Further, the target type determination unit 112 associates the target type "automobile" with the target position (50,150,100) with the vehicle (target ID = 001) by summarizing these processing results, and assigns the person (target ID = 002). The target type "person" is associated with the target position (100,230,130), the cardboard (target ID = 003) is associated with the target type "cardboard" and the target position (100,200,50), and the automobile (target ID = 004). Generate a target type table that associates the target type "automobile" with the target position (200,150,100).

Here, the correspondence relationship determination unit 113 first,
(A1) In the type correspondence relationship table of FIG. 6, the target type "cardboard" in which the communication type having a correspondence relationship is uniquely determined is recognized, and further, the communication type "mMTC" having a correspondence relationship with this is specified.
(A2) In the target type table, the target ID (target ID = 003) associated with the recognized target type "cardboard" is specified.
(A3) In the communication type table, the terminal ID (terminal ID = 001) associated with the communication type "mMTC" specified in (a1) above is specified.
(A4) A record recorded by associating the specified target ID (target ID = 003) with the specified terminal ID (terminal ID = 001) is generated and used as a part of the terminal target correspondence table.

Next, the correspondence relationship determination unit 113 recognizes that the remaining correspondence cannot be performed depending on the type correspondence relationship table of FIG.
(B1) The reciprocal of the distance (position correspondence) between the target position (50,150,100) of the automobile (target ID = 001) in the target type table and the terminal position (50,150,100) of the terminal 2_002 (terminal ID = 002) in the communication type table. Degree: In this case, the calculated value is infinite, which is the maximum value that the position correspondence variable can take in the program), and recognizes that it exceeds the predetermined threshold.
(B2) A record recorded by associating the target ID (target ID = 001) recognized in the above (b1) with the terminal ID (terminal ID = 002) is generated, and a part of the terminal target correspondence table is generated. To do.

Next, the correspondence relationship determination unit 113 further recognizes that the remaining correspondence cannot be performed depending on the type correspondence relationship table of FIG.
(C1) The reciprocal of the distance (position correspondence) between the target position (200,150,100) of the automobile (target ID = 004) in the target type table and the terminal position (200,150,100) of the terminal 2_004 (terminal ID = 004) in the communication type table. Degree: In this case as well, the calculated value is infinite, which is the maximum value that the position correspondence variable can take in the program), and it is recognized that it exceeds the predetermined threshold value.
(C2) A record recorded by associating the target ID (target ID = 004) recognized in the above (c1) with the terminal ID (terminal ID = 004) is generated, and a part of the terminal target correspondence table is generated. To do.

Finally, the correspondence relationship determination unit 113
(D1) The target type "person" associated with the target ID (target ID = 002) whose correspondence destination has not yet been determined in the target type table, and the communication ID whose correspondence destination has not yet been determined in the communication type table (d1). Recognizing that the communication type "eMBB" associated with the communication ID = 003) has a correspondence relationship in the type correspondence table of FIG.
(D2) A record recorded by associating the target ID (target ID = 002) recognized in the above (d1) with the terminal ID (terminal ID = 003) is generated to complete the terminal target correspondence table. ..

By the way, the correspondence relationship determination unit 113 replaces (d1) above.
(D1') The reciprocal of the distance (position) between the target position (100,230,130) of the person (target ID = 002) in the target type table and the terminal position (100,230,130) of the terminal 2_003 (terminal ID = 003) in the communication type table. Correspondence: In this case as well, it is possible to adopt a step of recognizing that the calculated value is infinite and the maximum value that the position correspondence variable can take in the program) exceeds a predetermined threshold. is there.

Further, in the above processing, the processing is initially started from the step of recognizing the target type "corrugated cardboard" in which the communication type having a correspondence relationship is uniquely determined.
(A1') In the type correspondence relationship table of FIG. 6, the process can be started from the step of recognizing the communication type "mMTC" in which the target type having a correspondence relationship is uniquely determined. That is, in the above step, the terminal target correspondence table can be generated by the exact reverse procedure regarding the target type and the communication type.

In this way, when using the type correspondence table (type correspondence information) including the one-to-many, many-to-one, or many-to-many correspondence that can be sufficiently configured depending on the terminal and the situation of the target, the communication type and the communication type and Even in a situation where the terminal identification process cannot be completed only by investigating the correspondence between the target types, the terminal identification process is performed by performing the identification process of as many terminals 2 as possible by using the target state information and the terminal state information. Can be easily completed.

<Determination of correspondence: Terminal communication status information and target communication status information are also used>
As described above, various embodiments of the terminal identification process using the terminal state information and the target state information have been described with reference to FIG. 6, but hereinafter, the “terminal communication state information” and the “target communication state information” will be used. , An embodiment in which the terminal identification process is preferably performed will be described.

As described in detail above, the terminal communication state determination unit 111b (FIG. 1) of the communication type determination unit 111 is used for "terminal communication state information", for example, time series information of the communication connection presence / absence variable B_t and / or the received signal power variable E_t. Time series information, can be determined. On the other hand, the target communication state determination unit 112b (FIG. 1) of the target type determination unit 112 contains "target communication status information", for example, time series information of the communication connection enable / disable variable B'_t, and / or the received power equivalent variable E'_t. Time series information, can be determined.

Next, the correspondence relationship determination unit 113 (FIG. 1) calculates the "communication state correspondence degree" which is the degree of correspondence between the determined "terminal communication state information" and the "target communication state information", and this "communication state correspondence degree" is calculated. It is also preferable to generate terminal target correspondence information (terminal target correspondence table) based on "communication state correspondence degree".

Here, the communication connection compatibility as the "communication status correspondence" between the time series information (terminal communication status information) of the communication connection presence / absence variable B_t and the time series information (target communication status information) of the communication connection availability variable B'_t. CC is, for example, the intercorrelation between the communication connection availability variable B_t and the communication connection availability variable B'_t at each time point t in a predetermined time interval (time interval from t = k to k + M) as the following equation (4) CC. = Σ _{t = k} ^{k + M} B_t * B'_t
May be calculated using.

In addition, the received power correspondence degree PC as the "communication state correspondence degree" of the time series information (terminal communication state information) of the received signal power variable E_t and the time series information (target communication state information) of the received power equivalent variable E'_t. Is, for example, the cross-correlation between the received signal power variable E_t at each time point t in a predetermined time interval (time interval of t = k to k + M) and the time series information of the received power equivalent variable E'_t. 5) PC = Σ _{t = k} ^{k + M} E_t * E'_t
May be calculated using. Here, in the above equations (4) and (5), Σ _{t = k} ^{k + M} is an operator indicating the summation of the time point t (= k, k + 1,…, k + M). ..

Correspondence relationship determination unit 113 then
(A) There is a possibility that there is a correspondence relationship according to the terminal target correspondence table (although it cannot be uniquely associated only with the terminal target correspondence table) (the corresponding communication type and the corresponding target type in the table are Of the (supported) terminal 2 and the target group
(B) The "communication status correspondence" (communication connection correspondence CC and / or reception power correspondence PC) exceeds a predetermined threshold (communication connection correspondence threshold CC_th and / or reception power correspondence threshold PC_th) ((( CC> CC_th) and / or (PC> PC_th)) pairs are assumed to correspond to each other.
(C) It is also preferable to add the set of records to the terminal target correspondence table.

In this way, when using the type correspondence table (type correspondence information) including the one-to-many, many-to-one, or many-to-many correspondence that can be sufficiently configured depending on the terminal and the situation of the target, the communication type and the communication type and Even in a situation where the terminal identification process cannot be completed only by investigating the correspondence of the target types, by using the target communication status information and the terminal communication status information, as many terminals 2 as possible can be identified and the terminals can be identified. It is possible to facilitate the completion of the identification process.

Although various embodiments of the terminal identification process have been described above, an embodiment in which a plurality of base stations 1 cooperate to perform the terminal identification process will be described here. In this embodiment, at least one base station 1 exists around the base station 1, and each base station 1 determines the target type information from the environmental information obtained by its own camera 103, and further determines the target type information by itself. It is possible to exchange the target type information with each other.

Here, the target type determination unit 112 (FIG. 1) acquires the target type information determined by the surrounding base station 1, and the correspondence relationship determination unit 113 (FIG. 1) further acquires the target acquired in this way. It is also preferable to determine the correspondence relationship between the type information and the communication type information determined (at its own base station 1), generate and update the terminal target correspondence table, and perform the terminal identification process.

In this case, it is possible to carry out the terminal identification process similar to the terminal identification process performed in the embodiment in which the base station 1 is connected to the plurality of cameras 103 as described above. Further, as a result, since a certain terminal 2 is not included in the environmental information by its own camera 103, it is not detected, and as a result, the base station 1 fails in the identification process of the terminal 2. It is also possible to avoid the situation.

Further, in the various embodiments described above, the "type correspondence information" is set and used as the type correspondence table, but this "type correspondence information" is set without taking the form of an individual table. Such embodiments are also possible.

For example, as described above, in the embodiment in which the terminal 2 holds the target type information related to itself and the base station 1 acquires the target type information from the terminal 2.
(A) The communication type determination unit 111 adds the acquired target type information to the communication type information determined for the terminal 2 to be identified (specifically, the terminal ID of the terminal 2 together with the communication type). , Correspond to the target type of the acquired target type information),
(B) The correspondence relationship determination unit 113 identifies the target ID corresponding to the same target type as the target type of the acquired target type information in the target type information determined by the target type determination unit 112. The terminal target correspondence information in which the specified target ID is associated with the terminal ID of the above (a) may be generated.

By the way, in this case, it can be considered that "type correspondence information" (the part that functions as) is automatically generated in the communication type information to which the acquired target type information is added.

[Application example of terminal identification processing]
Hereinafter, an application example of the terminal identification process described above will be described.

In the functional block diagram of FIG. 1, the approach target identification unit 131 is set at the detection position of a plurality of targets detected by the target type determination unit 112 in a situation where there are a plurality of movable terminals 2 in the communication area environment. Based on this, a plurality of objects that are presumed to come closer to each other later than a predetermined value are identified.

For example, the approach target identification unit 131 uses the current detection position of each detected object and the velocity vector calculated from the past time change of the detection position as a basis for each of the detection positions at a future time point after a predetermined time elapses. It is also preferable to estimate the position of the target and specify the target whose distance from each other at the future time point is equal to or less than a predetermined threshold as the approach target group.

In this case, the communication control unit 114 receives the information of the plurality of targets specified by the approach target identification unit 131, and the correspondence relationship determination unit 113 determines that the communication control unit 114 has a correspondence relationship with any of these plurality of targets. Identify (at least one) terminal 2 and address it to at least one of the identified terminals 2 with information related to the presumption that it will approach more than a predetermined value, such as approach / collision alarms, encounter / encounter forecasts, etc. It is transmitted (from the communication interface 101).

FIG. 7 is a schematic diagram for explaining an application example of the terminal identification method according to the present invention.

According to the application example of FIG. 7, the base station 1 remotely monitors an automobile (or a drone, a robot, etc.) connected by communication with 5G. Specifically, the base station 1 is in communication connection with the terminal 2_001 having the terminal ID 001 and the terminal 2_002 having the terminal ID 002, and further, the correspondence relationship determination unit 113 of the base station 1 is
(A) The terminal 2_001 and the detected automobile 3_002 having the target ID 002 are in a corresponding relationship (that is, the terminal 2_001 is mounted on the automobile 3_002).
(B) The terminal 2_002 and the detected automobile 3_003 having the target ID of 003 are in a corresponding relationship (that is, the terminal 2_002 is mounted on the automobile 3_003).
It is decided that this is done, and a terminal target correspondence table that records that fact is generated.

On the other hand, the approach target identification unit 131 specifies the automobile 3_003 and the driver 4_001 whose target ID is 001 as one element of the approach target group, and the automobile 3_003 and the driver 4_001 are one approach target group. The approach target group information, which is the information to be included in, is output to the communication control unit 114. In this application example, the driver 4_001 is in a situation where the building standing along the road becomes an obstacle and cannot be recognized by the sensor mounted on the automobile 3_003.

In such a situation, the communication control unit 114
(A) Based on the approach target group information, the terminal 2_002 having a correspondence relationship with the automobile 3_003 included in the approach target group is determined as the approach alarm notification destination from the acquired terminal target correspondence table.
(B) The alarm information that "the vehicle 4_001 (also included in the approach target group) is approaching" is transmitted to the terminal 2_002 determined as the notification destination.

In addition, the approach target identification unit 131 also transmits the detection position information of the pedestrian 4_001 to the terminal 2_002 in accordance with this alarm information, and sets the current position (and its flow line) of the pedestrian 4_001 to the road on the screen of the terminal 2. It is also preferable to highlight it on the map.

By carrying out the processing as described above, for example, it is possible to promote safe driving by the driver and safe walking / running of a person, and to prevent a collision accident caused by a moving object such as an automobile. In particular, a dangerous situation for a certain automobile, however, a dangerous situation that cannot be detected or predicted by the in-vehicle sensor (camera) can be notified to this automobile, which is the very party concerned, via the identified terminal 2. It will be possible.

[Communication relay processing, communication relay program]
Although various embodiments related to the identification process of the terminal 2 have been described above, the communication relay in the base station 1 realized by using the functional block diagram of FIG. 1 and FIG. 8 and the identification process is described below. An embodiment of the process will be described. Note that FIG. 8 is a schematic diagram for explaining an embodiment of processing in the model building unit 141 and the terminal radio wave information estimation unit 142, which will be described later.

In the functional block diagram of FIG. 1, the model building unit 141 builds a learning model for estimating terminal radio wave information. Specifically, in the present embodiment, the model building unit 141 is as shown in FIG. 8 (A).
(A) Time-series image data (environmental information) generated by the camera 103 (which may include an object related to the terminal 2 and an object which may be an electromagnetic interference obstacle) and
(B) Learning data including information related to a predetermined target detected from this time-series image data, for example, information related to a detection position of the target (target position information).
(C) Received radio wave information (at each time point or representative time point of the environmental information in (a) above) related to the terminal 2 determined to have a correspondence relationship with this predetermined target by the correspondence relationship determination unit 113, for example, a received signal. Training data using power as correct data is generated, and the training data is used to generate machine learning algorithms well-known in the field of image recognition (for example, a plurality of convolutional layers in a neural network algorithm and their outputs). The terminal radio wave information estimation model is constructed by using the combination with the Fully-Connected Layers).

Here, as already described in detail, in the conventional machine learning model as disclosed in Non-Patent Document 1, for example, an object detected from time-series environmental information generated by a camera is this machine learning model. It is not possible to determine whether or not it corresponds to the terminal related to the received signal power predicted by.

On the other hand, the terminal radio wave information estimation model constructed by the model building unit 141 is information related to the target (determined to be in a corresponding relationship) that is exactly associated with the received radio wave information as the correct answer data, for example, the target position. The information is included in the learning data and constructed. Therefore, the received radio wave information predicted by this terminal radio wave information estimation model, for example, the received signal power, can be interpreted as a predicted value for a predetermined target determined as the identification destination of the terminal 2 related to the received radio wave information. .. That is, the estimation process of the received radio wave information by the terminal radio wave information estimation model surely solves the unsolved problem of surely identifying the corresponding target in the estimation process by the conventional machine learning model.

Next, the terminal radio wave information estimation unit 142 estimates the received radio wave information of the terminal 2, for example, the received signal power, using the terminal radio wave information estimation model constructed by the model construction unit 141. Specifically, in the present embodiment, the terminal radio wave information estimation unit 142 has, as shown in FIG. 8B,
(A) Time-series image data (environmental information) generated by the camera 103, which includes the terminal 2 which is the estimation target and may include an object which may be an electromagnetic interference.
(B) The target position information of the predetermined target detected from the time-series image data and determined to have a corresponding relationship with the terminal 2 which is the estimation target is applied to the terminal radio wave information estimation model. As an input, based on the received signal power (as estimated information) output from the terminal radio wave information estimation model by this input, the predicted value of the received signal power (at the estimated time point or time interval) of the terminal 2 to be estimated is calculated. decide.

Finally, the communication control unit 114 (FIG. 1), which has acquired the predicted value of the received signal power of the terminal 2 (having high estimation accuracy as described above), uses the predicted value as a basis for the terminal 2 (or the terminal 2). It is determined whether or not to switch the communication path of (a predetermined target corresponding to). For example, when the predicted value in a predetermined future time point or time interval is equal to or less than a predetermined power threshold value, communication with the terminal 2 may be passed to another adjacent base station 1.

Here, also in another adjacent base station 1, the predicted value of the received signal power in the same terminal 2 is determined, and the predicted value is shared among the base stations 1 to specify the largest predicted value. It is also preferable to switch the communication path to the base station 1 that has determined the specified maximum predicted value.

As described above, according to the base station 1 of the present embodiment, by using the terminal radio wave information estimation model constructed by using the terminal identification processing result, the communication failure due to the communication path obstruction which becomes a big problem in 5G. In particular, it is possible to carry out communication relay processing that can surely solve the problem of temporary communication failure due to a moving obstruction.

As described in detail above, according to the present invention, the correspondence between the terminal and the target existing in the environment in which the terminal can exist is based on the correspondence between the type information (communication type and target type) related to each. It becomes possible to decide. That is, the terminal target correspondence information can be determined by considering the correspondence relationship of the type information related to each, without relying on the mutual positional relationship between the terminal and the target or only the positional relationship.

Further, the terminal identification process according to the present invention solves the problem of communication failure due to the communication path obstruction in the coming 5G, and notifies / warns the vehicle equipped with the terminal of the approach of a person or another vehicle. Furthermore, it is applied in various situations and fields, such as determining the relationship between the browsing page of a user who is determined to have a corresponding relationship with a certain terminal and the flow line of the user and utilizing it for marketing and management. It is possible.

In the various embodiments of the present invention described above, various changes, modifications and omissions in the technical idea and the scope of the present invention can be easily made by those skilled in the art. The above explanation is just an example and does not attempt to restrict anything. The present invention is limited only to the scope of claims and their equivalents.

1 Base station (terminal identification device, communication relay device)
101 Communication interface 102 Communication history information storage unit 103 Camera 104 Camera image storage unit 111 Communication type determination unit 111a Terminal status determination unit 111b Terminal communication status determination unit 112 Target type determination unit 112a Target status determination unit 112b Target communication status determination unit 113 Correspondence Relationship determination unit 114 Communication control unit 121 Type correspondence Relationship management unit 131 Approach target identification unit 141 Model construction unit 142 Terminal radio wave information estimation unit 2, 2_001, 2_002, 2_003, 2_004 Terminal 3_002, 3_003 Automobile 4_001 Traveler

Claims (16)

A communication type determining means for determining communication type information, which is information related to the type of communication with the terminal, based on information related to communication acquired from a communication means that communicates with at least one terminal.
Target type that acquires environmental information that is information related to the environment from a sensor that senses the environment in which the terminal can exist, and determines target type information that is information related to at least one target type detected from the environment information. Determining means and
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification device having a correspondence relationship determining means for determining information related to a correspondence relationship with an object. The communication type determining means uses at least one of an eMBB (enhanced Mobile BroadBand) compatible communication method, a URLLC (Ultra-Reliable and Low Latency Communications) compatible communication method, and an mMTC (massive Machine Type Communication) compatible communication method. By selecting from the included communication method type group, or at least one of voice call data, video distribution data, web page data, e-mail data, posting data, application data, device control data, and sensor data. The terminal identification device according to claim 1, wherein the communication type information is determined by selecting from the communication data type group including the communication data type group. At least a part of the type correspondence information is information related to one-to-many, many-to-one, or many-to-many correspondence.
The correspondence relationship determining means is a terminal whose correspondence is uniquely determined, a greedy algorithm that sequentially determines a correspondence relationship from a set of objects, or a combinatorial optimization algorithm that can solve the maximum flow problem of graph theory. The terminal identification device according to claim 1 or 2, wherein the information relating to the correspondence between the device and the object is determined. The communication means acquires the target type information from a terminal that holds the target type information related to itself, and obtains the target type information.
The terminal identification device uses the acquired target type information and the communication type information determined for the terminal holding the target type information to generate at least a part of the type correspondence information. The terminal identification device according to any one of claims 1 to 3, further comprising a unit. The target type determining means determines whether or not the target detected at a certain time point is a new target that has not been detected or cannot be detected at the previous time point.
Regarding the target type information of the new target, the correspondence relationship determining means is based on the type correspondence relationship information, and the communication type of the terminal newly connected by communication within a predetermined time range including the certain time point or the certain time point. The terminal identification device according to any one of claims 1 to 4, wherein only the correspondence with the information is determined, and the information relating to the correspondence relationship with the terminal for the new target is determined. The target type determining means is determined from the detection position and / or the change of the detection position of the target detected at the certain time point, and the target is new based on the information related to the position and / or speed of the target. The terminal identification apparatus according to claim 5, wherein it is determined whether or not the device is the target of the above. The target type determining means determines whether or not the target detected at a certain time point is the same as the target detected at the previous time point.
In the correspondence relationship determining means, it is determined that the target detected at the certain time point is the same as the target detected at the previous time point, and the target detected at the previous time point and the terminal are The present invention according to any one of claims 1 to 6, wherein when it is determined that there is a correspondence relationship, the target detected at that time point is determined to have a correspondence relationship with the certain terminal. Terminal identification device. The communication type determining means also determines terminal state information, which is information related to the position and / or speed of the terminal, based on the information related to the radio wave of the communication as the information related to the communication.
The target type determining means also determines the target state information, which is information related to the position and / or speed of the target, from the detection position and / or the change of the detection position of the target.
The correspondence relationship determining means calculates a state correspondence degree which is a degree of correspondence between the determined terminal state information and the determined target state information, and based on the state correspondence degree, the terminal and the target The terminal identification device according to any one of claims 1 to 7, wherein the information relating to the correspondence relationship of the above is determined. The communication type determining means also determines the terminal communication status information, which is the information relating to the communication status with the terminal, based on the information relating to the communication.
The target type determining means also determines the target communication state information, which is information related to the communication state to be embodied with the target if the target includes a terminal, from the environment information.
The correspondence relationship determining means calculates the communication state correspondence degree, which is the degree to which the determined terminal communication state information and the determined target communication state information correspond, and the terminal is also based on the communication state correspondence degree. The terminal identification device according to any one of claims 1 to 8, wherein the information relating to the correspondence between the device and the target is determined. The sensors are a plurality of sensors provided at different positions from each other.
The target type determining means acquires a plurality of environmental information from each of the plurality of sensors, determines the target type information from each of the plurality of environmental information, and among the determined target type information, the target. Target types of objects whose detection positions are close to a predetermined value or higher and / or whose feature amounts of the target detection areas related to the target type information are similar to a predetermined value or higher. The terminal identification device according to any one of claims 1 to 9, wherein the information relates to the same object. The target type determination means acquires target type information determined from environmental information acquired from a sensor other than the sensor in the other terminal identification device from other terminal identification devices existing in the vicinity.
The correspondence relationship determining means is characterized in that, based on the type correspondence relationship information, information relating to the correspondence relationship between the acquired target type information and the terminal related to the determined communication type information is also determined. The terminal identification device according to any one of claims 1 to 10. The terminal includes a plurality of terminals installed or carried on a mobile body.
The terminal identification device is
An approach target identification means for identifying a plurality of targets that are estimated to approach each other later than a predetermined value based on the detection positions of the plurality of detected targets.
It is presumed that the correspondence relationship determination means approaches at least one of at least one terminal determined to have a correspondence relationship with any of the specified objects and approaches the predetermined value or more. The terminal identification device according to any one of claims 1 to 11, further comprising a communication control means for transmitting information. Learning data including the environmental information and information related to the target detected from the environmental information, which is in a corresponding relationship with the target by the terminal identification device according to any one of claims 1 to 12. A learning model for estimating terminal radio wave information, which is constructed by learning data in which information related to a communication state with a terminal determined to be the correct answer data is used as correct answer data. Data including the environmental information and information related to the target detected from the environmental information is input to the learning model according to claim 13, and the information related to the communication state of the terminal output by the learning model is used. Based on the terminal communication state estimation means for estimating the information related to the communication state of the target as the terminal,
A communication relay device comprising a communication control means for determining whether or not to switch the target communication path as a terminal based on information related to an estimated communication state. A program that operates a computer that can determine the correspondence between at least one terminal and at least one target.
A communication type determining means for determining communication type information, which is information related to the type of communication with the terminal, based on information related to communication acquired from the communication means communicating with the terminal.
Target type determination means that acquires environmental information that is information related to the environment from a sensor that senses the environment in which the terminal can exist, and determines target type information that is information related to the type of the target detected from the environment information. When,
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification program characterized in that a computer functions as a correspondence relationship determining means for determining information related to a correspondence relationship with an object. A terminal identification method in a computer capable of determining the correspondence between at least one terminal and at least one target.
Based on the information related to the communication acquired from the communication means that communicates with the terminal, the communication type information that is the information related to the type of communication with the terminal is determined, while the environment in which the terminal can exist is determined. A step of acquiring environmental information which is information related to the environment from a sensor to be sensed and determining target type information which is information related to the type of the target detected from the environmental information.
The terminal related to the determined communication type information and the determined target type information based on the type correspondence information which is the information in which the information related to the communication type and the information related to the target type are associated with each other. A terminal identification method comprising a step of determining information relating to a correspondence relationship with an object.

Images