KR20240065093A - Cooperation between two methods for geolocating terminals in wireless communication systems - Google Patents

Abstract

The present invention relates to a method (100) for geolocating a terminal (20i) by an access network of a wireless communication system. The invention is based on control of the operating mode of the terminals 20 as well as cooperation between the first and second geolocation methods. When the terminal 20, 20i is configured in the first mode of operation, it allows the access network to estimate 102 the location of the terminal using the first geolocation method. The locations estimated by the first geolocation method are used to train (103) the machine learning algorithm of the second geolocation method. Then, once the algorithm has been trained, it becomes possible to estimate (104) the geographic location of the terminal 20i even when the terminal is not in the first mode of operation. The first geolocation method is more accurate than the second geolocation method, but requires more power consumption and/or radio resources for the terminal 20.

Description

Cooperation between two methods for geolocating terminals in wireless communication systems

The present invention belongs to the field of geolocating terminals of wireless communication systems. The invention is particularly well applied to the geolocation of IOT (Internet of Things) or M2M (Machine-to-Machine) type connected objects.

Currently, many solutions exist for obtaining the geographical location of a terminal in an access network of a wireless communication system.

For example, a terminal may be equipped with a GPS (Global Positioning System) receiver that allows the terminal to determine its geographic location. The terminal may then transmit a message indicating this geographic location to the access network of the wireless communication system. Although satellite geolocation is particularly accurate, it is subject to a number of drawbacks, particularly the cost and power consumption involved in integrating and using a GPS receiver on the object. Additionally, sending messages containing the geographical location of the terminal to the access network also negatively affects the power consumption of the terminal. This is especially true for IoT or M2M type communication systems where messages transmitted by the terminal must be as short as possible due to significant constraints on throughput and power consumption. Additionally, GPS type satellite geolocation methods are known to have relatively low response ratios in closed or obscured areas (eg, hangars, buildings, or dense forest areas). “Response ratio” means the ratio between the number of times an attempt was made to determine a location relative to the number of times the location could be effectively determined.

Geolocation methods also exist based on databases in which an association is made between the identifier of a transmitter device (eg, a WiFi or Bluetooth access point) and the geographic location of the transmitter device. In such a method, the terminal detects the identifier of the transmitter device (the identifier is included in a message transmitted by the transmitter device, eg, on a beacon signal). The terminal may then transmit the detected identifier to the access network. The access network can subsequently query the geolocation server, which contains a database with a table where associations are made between the identifiers of the transmitter devices and their respective geographic locations. The geolocation server may then determine the geographic location associated with the transmitter device and then transmit this information to the access network. The geographic location of the transmitter device corresponds to the estimated geographic location of the terminal. The geographical location of the terminal may possibly be refined according to a signal strength indicator at which the beacon signal is received by the terminal. It is also possible to estimate the geographical location of the terminal according to the geographical location of a plurality of neighboring transmitter devices for which the terminal has detected identifiers. Nevertheless, these geolocation methods here again involve significant power consumption of terminals for listening to beacon signals and transmitting the identifiers of detected neighboring transmitter devices. Moreover, these methods generally have relatively low response ratios in areas with low densities of population and/or economic activity.

In an access network, it is also known to estimate the geographical location of a terminal according to messages transmitted by the terminal and received by one or more base stations of the access network. Such provisions make it possible to reduce the cost of the terminal, in particular by saving energy on the terminal side and by simplifying the terminal (in fact, it is no longer necessary to integrate a GPS receiver or a WiFi or Bluetooth module into the terminal) ).

For example, when the same message is received by multiple base stations of generally known geographic locations, the geographical location of the terminal can be estimated by comparing the received signal strength indicators (RSSI) of the message for each of the base stations. there is. Nevertheless, many parameters (obstacles, multiple trips, etc.) may influence the signal strength indicator of the reception of a message by a base station and, thus, the geographical location of the terminal so estimated. is not always very accurate.

The geographic location of a terminal can also be estimated by comparing the time of arrival (TOA) and/or frequency of arrival (FOA) of the message to various base stations. Nonetheless, this involves synchronizing the base stations with each other in time and/or frequency, and the accuracy of estimating geographic location depends on the accuracy with which the base stations are synchronized. For IoT and/or M2M type applications, it is generally undesirable to implement precise synchronization of base stations to each other, since this would increase the complexity and cost of manufacturing the access network.

Other geolocation methods are based on machine learning techniques. Specifically, this involves building a database that, during the calibration phase, associates radio signatures corresponding to all of the measured RSSIs for terminals at known locations for a set of base stations in the system with known geographic locations. Subsequently, during the discovery phase, the observed radio signature for a terminal located at a known location is compared with all of the signatures in the database to estimate the location of the terminal from the location(s) corresponding to the most similar signature(s). do. Nevertheless, these methods are generally affected by a lack of geolocation accuracy, and especially when the geographical area to be covered is vast, they have quite significant limitations in terms of complexity (capacity and computing time). Additionally, it is necessary to perform calibration steps regularly to keep the database up to date.

Patent applications US2022/053285A1, US2018/279251A1, and US2018/372854A1 each describe using a geolocation method based on machine learning to determine geographic location from radio signatures. These documents also demonstrate that this requires a calibration step using different geolocation methods.

The aim of the present invention is to solve the shortcomings of the prior art, in particular some or all of those listed above, by proposing a solution that allows two different geolocation methods, each with different advantages and disadvantages, to cooperate.

For this purpose and according to a first aspect, the invention proposes a method for geolocating a terminal, referred to as a “terminal of interest” of a wireless communication system, by an access network of said wireless communication system. The method includes the following steps:

- determining criteria for causing the terminal of interest to enter and/or exit the first operating mode;

- For each of a plurality of messages coming from a terminal of interest and possibly from other terminals of the wireless communication system and received by the access network, estimating, by a first geolocation method, the geographical location of the terminal at the origin of the message - Each message of the plurality of messages has a first type and is sent when the terminal at the origin of the message is in a first mode of operation,

- training a machine learning algorithm of a second geolocation method from messages of the first type and associated geographic locations estimated using the first geolocation method, wherein the machine learning algorithm is configured to operate the terminal when the terminal is not in a first mode of operation. Trained to estimate the geographical location of a terminal from a second type of message sent by the terminal when not -,

- Once the machine learning algorithm of the second geolocation method is trained, estimating the geographic location of the terminal of interest using the second geolocation method from a second type of message transmitted by the terminal of interest.

The invention is based on cooperation between a first and a second geolocation method as well as control of the operating mode of the terminals. When the terminal is configured for the first mode of operation, it allows the access network to estimate the location of the terminal using the first geolocation method. The first geolocation method may be based, in particular, on determining the geographical location of one or more neighboring transmitter devices (eg WiFi or Bluetooth access points) detected by the terminal, using a geolocation server. Nonetheless, other geolocation methods may be implemented as the first geolocation method. For example, the geographic location of the terminal may be determined by the terminal using a receiver of a satellite positioning system and then transmitted to the access network. According to another example, the terminal may measure measurements taken by the terminal using one or more sensors (such as an accelerometer, gyroscope, magnetometer, altimeter, temperature or pressure sensor) to enable the access network to estimate the location of the terminal. Can be transmitted to the access network. According to another example, the terminal may explicitly transmit to the access network the arrival time and/or frequency of the radio signal received by the terminal (based on TOA and/or FOA according to measurements taken by the terminal). geolocation method).

The locations estimated by the first geolocation method are used to train the machine learning algorithm of the second geolocation method. Subsequently, once the algorithm is trained, it becomes possible to estimate the geographical location of the terminal even when the terminal is not in the first mode of operation.

The first geolocation method is generally more accurate than the second geolocation method. However, the first geolocation method generally requires higher power consumption for terminals. The second geolocation method may in fact be based on metadata associated with any message received coming from the terminal for which it is desired to estimate the geographical location. This metadata forms the signature of the message. The signature includes, for example, characteristics associated with reception of the message by the base station, for each of a plurality of base stations in an access network (eg, a signal strength indicator at which the message was received by the base station). The signature is determined, for example, by a server in the access network connected to the various base stations. Then, for the second geolocation method, no specific action specific to geolocation is required by the terminal (messages on which the second geolocation method is based are sent to targets other than those on which the terminal is geolocated in particular). (and the fact of sending a conventional message that does not have the primary purpose of geolocating a terminal is not considered a geolocation-specific operation). A single message transmitted by a terminal can be received by multiple base stations, making it possible to form a signature of the message.

It should be noted that the trade-off between geolocation accuracy and power consumption is not necessarily the only trade-off that can be considered in favoring one or the other of the two geolocation methods. Other criteria may be considered, such as response ratio, use of radio resources, etc.

The criteria for allowing the terminal of interest to enter the first operating mode and/or exiting the terminal of interest from the first operating mode may vary depending on whether the exact location of the terminal of interest is required or whether the approximate location of the terminal of interest is sufficient. Depending on whether there is a need to reduce the power consumption of the terminal of interest, whether the first geolocation method is available, whether there is a need to train the machine learning algorithm of the second geolocation method, whether the terminal is moving. It can be defined depending on whether or not.

In certain implementations, the invention may further include one or more of the following features taken alone or in any technically possible combinations.

In certain implementations, the first type of message explicitly includes parameters used by the first geolocation method.

This means, for example, that the message comprises a set of bits that code the data carried by the message, and that at least one part of the bits codes a parameter used by the first geolocation method. In other words, this means that the message includes within its data at least one encoded information item that contributes to determining the geographical location of the terminal.

Nevertheless, the first geolocation method may not require explicit parameters, for example if the first method is based on measurements by the access network of the arrival time and/or arrival frequency of the message to various base stations. It should be noted that there is.

In certain implementations, the parameter is at least part of the identifier of the transmitter device detected by the terminal at the origin of the transmission of the first type of message.

The transmitter device corresponds, for example, to a WiFi or Bluetooth access point, or to an RFID (radio frequency identification) tag.

In one variation, the parameters may also correspond to a geographic location determined by the terminal using a receiver of a GPS type satellite positioning system. According to another variant, the parameter may also correspond to a geographic location estimated by the terminal using measurements taken by one or more sensors of the terminal. According to another variant, the parameter may also correspond to a set of measurements taken by the terminal using one or more sensors (accelerometer, gyroscope, magnetometer, altimeter, temperature or pressure sensor, etc.). The parameter may also correspond to the time of arrival, direction, and/or frequency of the radio signal received by the terminal (geolocation method based on TOA and/or FOA according to measurements taken by the terminal).

In certain implementations, the second type of message does not explicitly include information used by the second geolocation method. In other words, this means that any information encoded in the data carried by the second type of message is not used by the second geolocation method.

In certain implementations, a machine learning algorithm is trained to associate a message's signature with a geographic location. The signature includes, for each of a plurality of base stations in an access network, characteristics associated with reception of the message by that base station.

In certain implementations, the characteristic associated with the reception of a message by a base station is a measurement of a signal strength indicator at which the message is received by the base station.

In certain implementations, transmission of the second type of message requires fewer radio resources and/or less electrical energy for the terminal of interest than transmission of the first type of message.

In certain implementations, the criterion is defined by a configuration stored by the terminal of interest for entering and/or exiting the first mode of operation according to predetermined periods of time.

In certain implementations, the criteria for causing a terminal of interest to enter and/or exit a first mode of operation depend on an indication provided by a sensor of the terminal of interest.

In certain implementations, the indication relates to:

- Start or end of the mobility phase of the terminal of interest, and/or

- Alerts triggered by the fact that a measurement taken by a sensor is greater or less than a predetermined threshold, and/or

- Detection of the impossibility of forming a message of the first type.

In certain implementations, the criteria for causing a terminal of interest to enter and/or exit a first mode of operation are defined by the access network and sent to the terminal of interest by the access network in a configuration message on the downlink. do.

The configuration message makes it possible to enter the terminal of interest into a first operating mode, for example during a learning period programmed by the access network. According to another example, the configuration message enables the terminal of interest to enter a first mode of operation when it is desired to know exactly the location of the terminal of interest. According to another example, a configuration message may be sent to a terminal of interest according to an estimate of the quality level of geolocating said terminal, such as by a second geolocation method.

Configuration messages can be sent by unicast or broadcast connection. Broadcasts may be limited to specific geographic areas.

According to a second aspect, the invention relates to a computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to implement steps of a method according to any one of the preceding implementations. do.

According to a third aspect, the invention relates to a server of an access network of a wireless communication system. The server is configured to do the following:

- For each of a plurality of messages coming from a terminal of interest and possibly from one or more other terminals of the wireless communication system and received by the access network, estimating the geographical location of the terminal at the origin of the message by a first geolocation method. - each message of the plurality of messages has a first type and is sent when the terminal at the origin of the message is in a first mode of operation,

- training a machine learning algorithm of a second geolocation method from messages of a first type and associated geographic locations estimated using the first geolocation method, wherein the machine learning algorithm is configured to operate when the terminal is not in a first mode of operation. Trained to estimate the geographical location of a terminal from a second type of message sent by the terminal when not -,

- determining criteria for causing the terminal of interest to enter and/or exit the first operating mode;

- sending a configuration message to the terminal of interest for causing the terminal of interest to enter and/or exit the first operation mode according to criteria determined accordingly;

- Once the machine learning algorithm of the second geolocation method is trained, estimating the geographic location of the terminal of interest using the second geolocation method from a second type of message transmitted by the terminal of interest.

In certain embodiments, the invention may further include one or more of the following features taken alone or in any technically feasible combinations.

In certain embodiments, the first type of message explicitly includes parameters used by the first geolocation method.

In certain embodiments, the parameter is an identifier of the transmitter device detected by the terminal at the origin of the transmission of the first type of message.

In certain embodiments, the second type of message does not explicitly include information used by the first geolocation method.

In certain embodiments, a machine learning algorithm is trained to associate a signature of a message with a geographic location, wherein the signature represents, for each of a plurality of base stations in an access network, characteristics associated with receipt of the message by the base station. Includes.

In certain implementations, the characteristic associated with the reception of a message by a base station is a measurement of a signal strength indicator at which the message is received by the base station.

In certain embodiments, the criteria for causing a terminal of interest to enter and/or exit a first mode of operation may be determined according to predetermined learning periods, or according to an emergency response for geolocating the terminal of interest. It is determined according to the level of quality, or according to an estimate of the level of quality of geolocating the terminal of interest by a second geolocation method.

According to a fourth aspect, the invention relates to an access network comprising a server according to any one of the preceding embodiments.

In certain embodiments, the access network is a low-power wide area network.

According to a fifth aspect, the invention relates to a terminal of a wireless communication system, the terminal being configured to:

- determining criteria for entering and/or exiting the first mode of operation;

- Only when the terminal is in the first mode of operation, a message of the first type explicitly containing parameters intended to be used by the access network to geolocate the terminal using the first geolocation method is sent to the access network. sending to,

- When the terminal is not in a first mode of operation, sending a second type of message to the access network that can be used by the access network to geolocate the terminal using a second geolocation method—second type. The transmission of a message of the first type requires fewer radio resources and/or less electrical energy than the transmission of a message of the first type.

The invention will be better understood upon reading the following description, given by way of non-limiting example, and with reference to Figures 1 to 3, which illustrate the following.
[Figure 1] Schematic representation of an example of an embodiment of a wireless communication system.
[Figure 2] Schematic representation of an example of an embodiment of a terminal.
[Figure 3] Schematic representation of the main steps of one implementation of a method for geolocating a terminal.
In these drawings, identical reference numbers from one drawing to another designate identical or similar elements. For reasons of clarity, elements shown are not necessarily to scale, unless otherwise specified.

1 schematically shows a wireless communication system 10 including terminals 20 and an access network 30 including a plurality of base stations 31.

The terminals 20 are adapted to transmit messages to the access network 30 via an uplink. Each base station 31 is adapted to receive messages from a terminal 20 when the terminal 20 is within its range. Typically, a message sent by terminal 20 includes an identifier of terminal 20. Each message received by a base station 31 may contain, for example, possibly other information, such as an identifier of the base station 31 that received the message, a received signal strength indicator of the received message, and a time of arrival of the message. , the message is transmitted to the server 32 of the access network 30, accompanied by the frequency at which it was received, etc. Server 32 processes all messages received from, for example, various base stations 31 .

The wireless communication system 10 may be unidirectional, that is, enabling only the exchange of messages on the uplink from the terminals 20 to the access network 30. However, according to other examples, nothing prevents the possibility of two-way exchanges. Where applicable, the access network 30 is also adapted by base stations 31 to transmit messages on the downlink to terminals 20, which are adapted to receive the messages.

Message exchanges on the uplink to access network 30 use a first wireless communication protocol.

In certain embodiments, the first wireless communication protocol is a low-power wide area network (LPWAN) communication protocol. Such wireless communication systems have long ranges (more than a kilometer, or even more than a dozen kilometers), low power consumption (e.g., less than 100 mW, or even less than 50 mW, or even less than 25 mW during transmission or reception of messages). of power consumption), an access network where throughputs are typically less than 1 Mbits/s. Such wireless communication systems are particularly adapted for IoT or M2M type applications.

In an IoT or M2M type communication system, data exchanges are essentially unidirectional, i.e., on the uplink from the terminals 20 to the access network 30 of the wireless communication system 10. In order to minimize the risks of losing a message transmitted by terminal 20, the scheme of the access network is often such that a message transmitted by transmitter device 20 can be received by a plurality of base stations 31. This is done in such a way that a given geographical area is simultaneously covered by a plurality of base stations 31.

In the remainder of the description, as a non-limiting example, the first wireless communication protocol is considered to be an ultra-narrowband and low-power wide area network communication protocol. “Ultra-narrowband” (UNB) means that the instantaneous frequency spectrum of radio signals transmitted by terminals has a frequency width of less than 2 kilohertz, or even less than 1 kilohertz.

The terminal 20 is also adapted to receive messages transmitted by at least one transmitter device 40 in the vicinity of the terminal 20 . Messages transmitted by transmitter device 40 use a second wireless communication protocol that is different from the first wireless communication protocol. It should be noted that transmitter device 40 may be completely independent of wireless communication system 10 and need not support the first wireless communication system.

In the example considered and illustrated in FIG. 1 , terminal 20a is close to two transmitter devices 40 that can receive messages. Terminal 20i is close to another transmitter device 40 that can receive messages.

In certain embodiments, the second wireless communication protocol has a shorter range than the range of the first wireless communication protocol. However, it should be noted that according to other examples, it is also possible to have a second wireless communication protocol whose range is shorter than the first wireless communication protocol.

The second wireless communication protocol is, for example, a wireless local area network (WLAN) communication protocol, for example of the WiFi type (IEEE 802.11 standards), or also of the Bluetooth or BLE (Bluetooth Low Energy) type, etc. It is a wireless personal area network (WPAN) communication protocol. According to another example, the second wireless communication protocol may be a near-field communication protocol based, for example, on NFC (Near Field Communication) technology or RFID (Radio Frequency Identification) technology.

Geolocation server 50 includes a database containing tables that store transmitter device 40 identifiers, referred to as the “geolocation database.” Each transmitter device 40 identifier is associated, in the table, with at least one location information item indicating the geographic location of the transmitter device 40.

The identifier of transmitter device 40 corresponds, for example, to the MAC (medium access control) address of transmitter device 40. Nevertheless, other parameters, such as, for example, the SSID (Service Set Identifier) or BSSID (Basic Service Set Identifier) of the WiFi access point, the identifier of the Bluetooth or BLE access point, the identifier of the RFID tap, etc., are used as identifiers for the transmitter device 40. can play a role as a field.

The location information may be direct coordinates (longitude, latitude, and possibly altitude) of the geographic location of transmitter device 40. Nonetheless, location information may also be context information for estimating the geographic location of transmitter device 40, such as, for example, a postal address, store name, district, region, or country name.

Geolocation server 50 is connected to server 32 of access network 30, for example by an Internet connection.

Figure 2 schematically shows an example of an embodiment of the terminal 20.

As illustrated in FIG. 2 , the terminal 20 includes a first communication module 21 adapted to exchange messages with base stations 31 according to a first wireless communication protocol. The first communication module 21 is, for example, in the form of a radio circuit comprising equipment (antenna, amplifier, local oscillator, mixer, analog filter, etc.).

The terminal 20 also includes a second communication module 22 adapted to receive messages transmitted by the transmitter device of interest 40 according to a second wireless communication protocol. The second communication module 22 is, for example, in the form of a radio circuit comprising equipment (antenna, amplifier, local oscillator, mixer, analog filter, etc.).

Additionally, the terminal 20 also includes a processing circuit 23 connected to the first communication module 21 and the second communication module 22. The processing circuit 23 comprises, for example, one or more processing units and memory means (magnetic hard drive, electronic memory, optical disk, etc.), the memory means including a method for geolocating the terminal (the geolocation method is A computer program product is stored in the form of a set of program instructions to be executed to implement some or all of the steps (as will subsequently be described in detail with reference to FIG. 3).

The server 32 of the access network 30 also comprises one or more processing units and memory means, the memory means comprising a program to be executed for implementing some or all of the steps of the method for geolocating a terminal. A computer program product is stored in the form of a set of code instructions.

The server 32 of the access network 30 is particularly configured to implement a first method for geolocating the terminal of interest 20i. In this first geolocation method, the terminal of interest 20i detects, for at least one neighboring transmitter device 40, an identifier of the transmitter device 40 (the identifier is e.g. included in a message transmitted by transmitter device 40 on the received beacon signal). Terminal of interest 20i may then transmit the detected identifier to server 32 of access network 30. Server 32 may then query geolocation server 50. Geolocation server 50 may then determine the geographic location associated with the transmitter device 40 and then transmit this information to server 32 of access network 30. The geographic location of transmitter device 40 corresponds to the estimated geographic location of terminal of interest 20i. The geographical location of the terminal can possibly be refined according to a signal strength indicator at which the beacon signal is received by the terminal of interest 20i.

For this first geolocation method, it is also possible to estimate the geographical location of the terminal according to the geographical location of a plurality of neighboring transmitter devices 40 for which the terminal has detected identifiers. This is, for example, the case for terminal 20a in the example shown in Figure 1.

This first geolocation method includes one or more transmitter device 40 identifiers transmitted by the terminal of interest 20i and possibly by one or more other terminals 20, 20a of the wireless communication system 10. May be repeated for various messages.

The terminal 20 may be configured to enter a first mode of operation and/or exit a first mode of operation. When terminal 20 is in a first mode of operation, terminal 20 is configured to detect one or more neighboring transmitter device 40 identifiers and transmit the identifiers in one or more messages to access network 30.

A message transmitted by a terminal 20 to the access network 30 and comprising at least one part of a transmitter device 40 detected by the terminal 20 is a first type of message. Accordingly, in the considered example, the first type of message explicitly includes parameters used by the first geolocation method. These explicit parameters correspond to at least part of the transmitter device 40 identifier. This is coded, for example, on a set of bits. Transmission of the first type of message by the terminal 20 has a negative impact on the power consumption of the terminal and the use of radio resources (in the spectral domain and/or time domain) of the wireless communication system 10 . Additionally, when the terminal 20 is in the first mode of operation, it consumes electrical energy to listen for beacon signals of the detected transmitter devices 40 .

Server 32 of access network 30 is also configured to implement a second method for geolocating terminal of interest 20i. This second geolocation method provides a terminal of interest 20i from a reference database built from messages of the first type and associated geographic locations estimated using the first geolocation method and from messages sent by the terminal of interest 20i. It is based on a machine learning algorithm trained to estimate the geographic location of (20i).

The reference database may, for example, identify signature radios corresponding to various signal strength indicators at which messages of the first type were received by various base stations 31 of the access network 30, estimated using the first geolocation method. Associated with each geographical location.

Once the machine learning algorithm has been trained, it becomes possible to estimate the geographic location of the terminal of interest 20i using a second geolocation method. For this purpose, the radio signature of interest is determined from the message transmitted by the terminal of interest. The radio signature of interest is subsequently compared to all of the signatures in the reference database. The geographic location of the terminal of interest 20i may then be estimated from the location(s) corresponding to the signature(s) in the reference database that are most similar to the radio signature of interest.

The accuracy of the second geolocation method is generally lower than that of the first geolocation method, especially if the geographical area to be covered is large and/or the amount of data in the reference database is not large enough (nevertheless, As indicated above, it should be noted that the present invention can also be applied in cases where the accuracy of the second geolocation method is only as good as, or even better than, the accuracy of the first geolocation method.

Nevertheless, the second geolocation method has the advantage that any type of message sent by the terminal of interest 20i can be used to estimate the location of the terminal of interest 20i. In particular, these messages need not explicitly include information used by the second geolocation method. Indeed, in the example considered, the second geolocation method is based on signal strength indicators at which the base stations 31 of the access network 30 received the message, and not on explicit information items contained in the message. . For the second geolocation method, no specific action specific to geolocation is required by the terminal of interest 20i (the message on which the second geolocation method is based is, in particular, directed to other than the goal of geolocating the terminal). may have been sent to the target). Accordingly, to estimate the location of the terminal of interest 20i, the second geolocation method may be based on a second type of message transmitted by the terminal of interest 20i when the terminal of interest is not in the first mode of operation. (Nevertheless, it should be noted that nothing prevents the terminal from being able to transmit messages of the second type when in the first mode of operation). In the example considered, transmission of the second type of message requires fewer radio resources and less electrical energy for the terminal of interest 20i than transmission of the first type of message.

Advantageously, the invention is based on controlling the first mode of operation of the terminals 20 in order to advantageously allow the first geolocation method and the second geolocation method to cooperate. When the terminal is configured for the first mode of operation, it allows the access network to estimate the location of the terminal using the first geolocation method. The locations estimated by the first geolocation method are used to train the machine learning algorithm of the second geolocation method. Subsequently, once the algorithm is trained, it becomes possible to estimate the geographical location of the terminal even when the terminal is not in the first mode of operation.

The criteria for allowing the terminal of interest to enter the first operation mode and/or to exit the terminal of interest 20i from the first operation mode may be determined, for example, depending on whether the exact location of the terminal of interest 20i is required or the terminal of interest 20i It can be defined depending on whether the approximate position of (20i) is sufficient. When the exact location of the terminal of interest 20i is required, the terminal of interest 20i is configured to transmit transmitter devices with which the terminal of interest is neighboring, to allow accurate geolocation of the terminal of interest 20i using the first geolocation method. A first operating mode must be entered to detect 40 and transmit the detected identifiers. When the approximate location of the terminal of interest 20i is sufficient, the terminal of interest 20i may perform 1 You must exit the operating mode.

Criteria for allowing the terminal of interest to enter and/or exit the first operating mode may also be defined according to the need to reduce the power consumption of the terminal of interest.

The criteria for allowing the terminal of interest to enter and/or exit the first operating mode may also be defined depending on the availability of the first geolocation method. For example, if it is known that it may be impossible for the terminal of interest 20i to detect a neighboring transmitter device 40, the terminal of interest 20i should exit the first mode of operation.

The criteria for allowing the terminal of interest 20i to enter and/or exit the first operating mode may also be defined depending on whether there is a need to train the machine learning algorithm of the second geolocation method. For example, if the amount of data in the reference database is insufficient, or if there is a risk that such data will become useless, the terminal of interest 20i will be provided with a first type that will enable the terminal of interest to update the reference database. The first operation mode must be entered to transmit the message.

The criteria for allowing the terminal of interest 20i to enter and/or exit the first operation mode may be defined by a predetermined configuration stored by the terminal of interest 20i.

The criteria may in particular be defined according to predetermined time periods. For example, the terminal of interest 20i may be configured to enter/exit the first operating mode at regular intervals or at cyclical, increasingly less frequent intervals, etc.

According to another example, the criteria for entering and/or exiting the first operating mode of the terminal of interest 20i depend on an indication provided by a sensor of the terminal of interest 20i. This indication may in particular be related to the start or end of a mobility phase of the terminal 20i of interest (e.g. it is of interest to prefer accurate geolocation by activating the first operating mode at the beginning or end of the mobility phase of the terminal). target). The sensor used to determine the start or end of the mobility phase of the terminal of interest 20i may be an accelerometer. In practice, it may be of interest to prefer one or the other of the two geolocation methods depending on whether the terminal of interest is moving. In particular, in the considered example where the first geolocation method is based on collaboration with transmitter devices, geolocation via the first geolocation method is preferred when the terminal is stationary, and the second geolocation method is preferred when the terminal is moving. It may be advantageous to prefer geolocation over machine learning algorithms in the method. According to another example, if the first geolocation method is based on a GPS receiver built into the terminal, geolocation through the first geolocation method is preferred when the terminal is moving, and geolocation through the second geolocation method is preferred when the terminal is not moving. It may be advantageous to prefer geolocation over machine learning algorithms in the method.

This indication may also relate to a warning, which is triggered by the fact that the measurement taken by the sensor is above or below a predetermined threshold (obtaining the correct geolocation of the terminal by activating the first operating mode when the warning is detected) may need to be done).

The criteria for allowing the terminal of interest 20i to enter and/or exit the first mode of operation are also defined by the access network 30 and are sent to the access network 30 in a configuration message on the downlink. It can be transmitted to the terminal of interest (20i). The criteria are in particular the quality of geolocating the terminal of interest 20i according to a predetermined learning period, or according to the level of urgency for geolocating the terminal of interest 20i, or by a second geolocation method. It may be determined according to an estimate of the level (e.g., if the accuracy is insufficient, the terminal may use the first geolocation method to obtain a more accurate geolocation and/or to enrich the reference database of the second geolocation method). 1 operation mode must be entered).

Configuration messages can be sent by unicast or broadcast connection. Broadcasts may be limited to specific geographic areas.

3 schematically shows the main steps of an example of the implementation of a method 100 according to the invention for geolocating a terminal of interest 20i in a communication system 10 as described with reference to FIG. 1 . do.

The method 100 includes determining 101 criteria for causing the terminal of interest 20i to enter and/or exit the first mode of operation, such criteria being as described above. can be decided together. The selection of a particular method for determining these criteria is only one variation of the invention.

The method 100 uses a first geolocation method for each of a plurality of messages received by the access network 30 and coming from the terminal of interest 20i and possibly from other terminals 20, 20a. This includes a step 102 of estimating the geographical location of the terminal at the source of the message. Each message of the plurality of messages is a message of a first type that is transmitted when the terminal at the origin of the message is in a first operation mode.

Method 100 includes training 103 a machine learning algorithm of a second geolocation method. This training is performed from messages of the first type and associated geographic locations estimated using a first geolocation method. A machine learning algorithm is trained to estimate the geographical location of the terminal from any messages sent by the terminal (and in particular a second type of message that does not contain explicit information about the geolocation). Additionally, machine learning algorithms can be trained to determine the accuracy with which the geographic location of the terminal is estimated. This accuracy can be used as a criterion, in particular, for allowing the terminal of interest to enter and/or exit the first operating mode.

Once the machine learning algorithm of the second geolocation method is trained, the method 100 includes a step 104 of estimating the geographic location of the terminal of interest 20i using the second geolocation method. This estimation 104 may be performed in particular from a second type of message sent by the terminal of interest 20i when the terminal of interest is not in the first mode of operation.

The above description, together with the various features of the invention and their advantages, clearly illustrates how the invention achieves its set objectives. In particular, controlling the first operating mode of the terminals advantageously allows the first geolocation method and the second geolocation method to cooperate intelligently so that the power consumption of the terminals and/or the radio resources of the communication system are reduced. Let it be done.

It should be noted that the implementations and embodiments considered above have been described as non-limiting examples, and consequently other variations are possible.

The invention applies particularly advantageously, but not in a limited way, to geolocation of LPWAN type networks and IoT or M2M type connected objects. However, nothing prevents other types of wireless wide area networks (WWANs) from being considered. For example, the first wireless communication protocol may be a standardized communication protocol such as UMTS (Universal Mobile Telecommunications System), LTE (Long Term Evolution), LTE-Advanced Pro, 5G type, etc. there is.

The present invention provides that a first method for geolocating a terminal (20) is based on using a geolocation server (50) to determine the geographic location of one or more neighboring transmitter devices (40) detected by the terminal. It was explained by considering what to do.

Nonetheless, other geolocation methods may be implemented as the first geolocation method. For example, the geographic location of terminal 20 may be determined by the terminal using a receiver of a satellite positioning system and then transmitted to the access network 30. According to another example, the terminal may measure measurements taken by the terminal using one or more sensors (such as an accelerometer, gyroscope, magnetometer, altimeter, temperature or pressure sensor) to enable the access network to estimate the location of the terminal. Can be transmitted to the access network. According to another example, the terminal may transmit to the access network the arrival time and/or frequency of the radio signal received by the terminal (geolocation method based on TOA and/or FOA according to measurements made by the terminal ).

(e.g., if the first geolocation method is a geolocation method based on TOA and/or FOA according to measurements taken by the access network 30). It should also be noted that there is no requirement to include explicit parameters associated with .

The invention has been explained by considering that the second geolocation method uses machine learning algorithms based on radio signatures that indicate signal strength indicators at which messages are received by various base stations 31 of the communication system 10. Nevertheless, nothing will prevent the machine learning algorithm from being based on other characteristics of the message transmitted by terminal 20. For example, the following characteristics: the signal-to-noise ratio of the signal carrying the message, the time or frequency for receiving the message at various base stations, the angle of arrival of the radio waves carrying the message, and the identifier of the base station that received the message. etc. may be considered.

Additionally, various types of machine learning algorithms are possible. This can also relate to classification algorithms as well as regression algorithms. The selection of a specific machine learning algorithm for the second geolocation method is just one variation of the invention.

It should also be noted that not all terminals 20 of the communication system 10 necessarily support the first mode of operation. In fact, it is possible to train the machine learning algorithm of the second geolocation method with only a fraction of the terminals 20 of the access network 30 that support the first mode of operation. As soon as the machine learning algorithm is trained, it becomes possible to geolocate terminals that do not support the first mode of operation using the second geolocation method.

As mentioned above, nothing prevents the terminal from being able to send messages of the second type when it is in the first mode of operation. Moreover, nothing prevents one from being able to estimate the location of a terminal using a second geolocation method by basing it on a first type of message sent by the terminal. In this case, it becomes possible to estimate the location of the terminal from messages of the first type not only using the first geolocation method but also using the second geolocation method. Such provisions may make it possible to compare the estimated positions according to each method, in order to determine a more accurate position from the two estimated positions and/or to improve the accuracy of one or the other of the methods, etc. there is. Such provisions may also make it possible to improve the response ratio for the geolocation of the terminal (e.g. in some cases, where only one of the two methods enables determining the location of the terminal, It is of interest that both methods can estimate the location of the terminal.

Claims (19)

Method (100) for geolocating a terminal (20), referred to as a “terminal of interest” (20i), of a wireless communication system (10) by an access network (30) of the wireless communication system (10). As,
- determining criteria for allowing the terminal of interest (20i) to enter and/or exit the first operating mode (101),
- for each of a plurality of messages coming from the terminal of interest 20i and possibly from other terminals 20, 20a of the wireless communication system 10 and received by the access network 30, a first Step 102: estimating the geographical location of a terminal at the origin of a message using a geolocation method - each message in the plurality of messages has a first type, and the terminal at the origin of the message performs the first operation. Sent while in mode ―,
- training (103) a machine learning algorithm of a second geolocation method from messages of the first type and associated geographic locations estimated using the first geolocation method, wherein the machine learning algorithm is configured to: trained to associate a signature with a geographic location, the signature being able to estimate the geographic location of the terminal from a second type of message sent by the terminal when the terminal is not in the first mode of operation, comprising, for each of a plurality of base stations (31) of the access network (30), features relating to reception of the message by the base station (31);
- Once the machine learning algorithm of the second geolocation method is trained, the geographic location of the terminal of interest 20i is determined using the second geolocation method from the second type of message sent by the terminal of interest 20i. Step 104: Estimating location
Method 100, comprising: According to paragraph 1,
The method (100) wherein the data carried by the first type of message encodes information used by the first geolocation method. According to paragraph 2,
Method (100), wherein the parameter is at least part of an identifier of a transmitter device (40) detected by a terminal (20a) at the origin of the transmission of the first type of message. According to any one of claims 1 to 3,
Method (100) wherein no information encoded in data carried by the second type of message is used by the second geolocation method. According to any one of claims 1 to 4,
The method (100) wherein the characteristic associated with reception of a message by the base station (31) is a signal strength indicator at which the message is received by the base station (31). According to any one of claims 1 to 5,
Method (100), wherein transmission of the second type of message requires fewer radio resources and/or less electrical energy for the terminal of interest (20i) than transmission of the first type of message. According to any one of claims 1 to 6,
The criterion is defined by a configuration stored by the terminal of interest 20i for allowing the terminal of interest 20i to enter and/or exit the first operating mode according to predetermined time periods. , method (100). According to any one of claims 1 to 6,
The method for allowing the terminal of interest (20i) to enter and/or exit the first mode of operation depends on an indication provided by a sensor of the terminal of interest (20i). 100). According to clause 8,
The above indication is,
- the beginning or end of the mobility phase of the terminal of interest 20i, and/or
- an alert triggered by the fact that the measurement taken by said sensor is above or below a predetermined threshold, and/or
- detection of the impossibility of forming a message of the first type
Related to, method 100. According to any one of claims 1 to 9,
The criteria for allowing the interested terminal 20i to enter and/or exit the first operating mode are defined by the access network 30, and are defined by the access network 30 in a configuration message on the downlink. Method (100) transmitted by a network (30) to the terminal of interest (20i). A computer-readable storage medium containing instructions, comprising:
The instructions, when executed by a computer, cause the computer to implement steps of the method (100) according to any one of claims 1 to 10. A server (32) in an access network (30) of a wireless communication system (10), comprising:
- for each of a plurality of messages coming from the terminal of interest 20i and possibly from one or more other terminals 20, 20a of the wireless communication system 10 and received by the access network 30, a first estimating the geographic location of a terminal at the origin of a message by a geolocation method, wherein each message of the plurality of messages has a first type and is transmitted when the terminal at the origin of the message is in a first operation mode; ,
- train a machine learning algorithm of a second geolocation method from messages of the first type and associated geographic locations estimated using the first geolocation method, wherein the machine learning algorithm converts the signature of a message to a geographic location; trained to associate with the access network ( For each of the plurality of base stations 31 (30), comprising features related to reception of the message by the base station (31) -,
- determining criteria for allowing the terminal of interest 20i to enter and/or exit the first operating mode,
- sending a configuration message to the terminal of interest 20i for entering the first operation mode and/or exiting the first operation mode according to the determined criteria,
- Once the machine learning algorithm of the second geolocation method is trained, the geographic location of the terminal of interest 20i is determined using the second geolocation method from the second type of message sent by the terminal of interest 20i. estimate location
A server 32 configured to do so. According to clause 12,
Server (32), wherein the data carried by the first type of message encodes information used by the first geolocation method. According to clause 13,
The parameter is the server 32 identifier of the transmitter device detected by the terminal 20a at the origin of the transmission of the first type of message. According to any one of claims 12 to 14,
Server (32), wherein any information encoded in the data carried by the second type of message is not used by the first geolocation method. According to clause 15,
The characteristic associated with the reception of a message by the base station (31) is a signal strength indicator at which the message is received by the base station (31). According to any one of claims 12 to 16,
The criteria for allowing the terminal of interest 20i to enter the first operation mode and/or exit the first operation mode are, according to predetermined learning periods, or to allow the terminal of interest 20i to Server 32, determined according to the level of urgency for categorizing, or according to an estimate of the level of quality of geolocating the terminal of interest 20i by the second geolocation method. As an access network 30,
An access network (30) comprising a server (32) according to any one of claims 12 to 17. According to clause 18,
The access network 30 is a low-power wide area network.

Images