EP3163546A1 - Procédé et dispositif pour détecter un comportement anormal d'un utilisateur - Google Patents

Procédé et dispositif pour détecter un comportement anormal d'un utilisateur Download PDF

Info

Publication number
EP3163546A1
EP3163546A1 EP15306726.9A EP15306726A EP3163546A1 EP 3163546 A1 EP3163546 A1 EP 3163546A1 EP 15306726 A EP15306726 A EP 15306726A EP 3163546 A1 EP3163546 A1 EP 3163546A1
Authority
EP
European Patent Office
Prior art keywords
user
patterns
time
duration
identified
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP15306726.9A
Other languages
German (de)
English (en)
Inventor
Marie Guegan
Anne Lambert
Eric Gautier
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Thomson Licensing SAS
Original Assignee
Thomson Licensing SAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Thomson Licensing SAS filed Critical Thomson Licensing SAS
Priority to EP15306726.9A priority Critical patent/EP3163546A1/fr
Publication of EP3163546A1 publication Critical patent/EP3163546A1/fr
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
    • G08B21/0423—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting deviation from an expected pattern of behaviour or schedule

Definitions

  • the proposed method and apparatus relates to detection of anomalies in the duration of activities of daily living of elderly or handicapped users in their homes or non-medical residences.
  • the proposed method and apparatus uses non-intrusive sensors in the home or non-medical residences to detect deviations in the time spent on activities of daily living. While principally directed to detecting anomalous behavior of elderly or handicapped individuals, the proposed method and apparatus are not so limited and may be employed to monitor prisoners, children or other individuals that find themselves in restricted environments. The description of the proposed method and apparatus uses elderly or handicapped individuals as examples.
  • the proposed method and apparatus Using time-stamped sensor events, the proposed method and apparatus identifies and mines patterns in the sequence of sensor activation signals and records the patterns in a data base. The duration of patterns is then computed. The computed pattern durations are assigned to each pattern in the data base.
  • a new behavior pattern occurs and is assigned an anomaly score based on the similarity of the new pattern's duration to known pattern durations.
  • a care giver is alerted if the anomaly score of the new pattern is above a threshold.
  • the detection of anomalous behavior is used to alert a care giver of the anomalous behavior.
  • the care giver may be a nurse, a doctor, an aide, a family member etc. In a prison or other environment, a care giver may be a person who monitors the activities of the individual being monitored.
  • the alert may be by phone, by email, by text message or any other reasonable means.
  • the proposed method and apparatus use the non-intrusive approach to detect anomalies in the behavior of elderly or handicapped individuals in their homes or non-medical residences.
  • the home or non-medical residences are equipped with sensors such as motion sensors and door contacts (non-intrusive sensors). It would be advantageous to detect anomalous behavior of users using the duration of activities of daily living. Detection of anomalous behavior is crucial to an ability to alert and dispatch help or a caregiver in response to the anomalous behavior. If an elderly or handicapped individual takes significantly more time for a given activity (bathroom, moving from room to room), this is often due to a physical problem (issue) or injury that has slowed the individual down. If the anomalous behavior is detected early enough then a care worker (giver) may be alerted and dispatched to help or provide intervention before the problem worsens and become critical requiring hospitalization or other more intense and costly intervention.
  • a method for detecting anomalous behavior of a user including logging first time-stamped event data of initial behavior of the user from sensors in an environment of the user for a period of time, mining the logged time-stamped event data to identify patterns of life routines of the user, determining which of the identified patterns are frequent patterns of life routines of the user, determining a duration of each of the identified frequent patterns, logging second time-stamped event data of subsequent behavior of the user from the sensors in the environment of the user and identifying a new occurrence of a known pattern of the life routines of the user, detecting anomalous behavior and creating an alert based on the detected anomalous behavior.
  • a server for detecting anomalous behavior of a user including a receive data module, the receive data module logging first time-stamped event data of initial behavior of the user from sensors in an environment of the user for a period of time, an identify patterns module, the identify patterns module mining the time-stamped event data to identify patterns of life routines of the user, the identify patterns module in communication with the receive data module, a determine frequent patterns module, the determine frequent patterns module determining a duration of each of the identified frequent patterns, the determine frequent patterns module in communication with the identify patterns module, the receive data module logging second time-stamped event data of subsequent behavior of the user from the sensors in the environment of the user and identifying a new occurrence of a known pattern of the life routines of the user and an anomaly detection module, the anomaly detection module detecting anomalous behavior and creating an alert based on the detected anomalous behavior.
  • processor or “controller” should not be construed to refer exclusively to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, read only memory (ROM) for storing software, random access memory (RAM), and nonvolatile storage.
  • DSP digital signal processor
  • ROM read only memory
  • RAM random access memory
  • any switches shown in the figures are conceptual only. Their function may be carried out through the operation of program logic, through dedicated logic, through the interaction of program control and dedicated logic, or even manually, the particular technique being selectable by the implementer as more specifically understood from the context.
  • any element expressed as a means for performing a specified function is intended to encompass any way of performing that function including, for example, a) a combination of circuit elements that performs that function or b) software in any form, including, therefore, firmware, microcode or the like, combined with appropriate circuitry for executing that software to perform the function.
  • the disclosure as defined by such claims resides in the fact that the functionalities provided by the various recited means are combined and brought together in the manner which the claims call for. It is thus regarded that any means that can provide those functionalities are equivalent to those shown herein.
  • Fig. 1 shows an exemplary case, where one individual is living in a residence equipped with a non-intrusive data collection infrastructure and where each main room is covered by one omni-directional motion detector installed on the ceiling.
  • These main rooms are labeled the “bedroom”, the “living”, the “kitchen”, the “bedroom2”, the “office” and the corresponding motion sensors are respectively indicated as “mB”, “mL”, “mK”, “mB2", “mO”.
  • one external "door” is equipped with a door contactor indicated as "cD”. It should also be noted that should there be any corridors (halls), these could also be covered with one or more sensors.
  • the sensors emit ON/OFF signals whether they are activated by something moving in front of the sensors (ON) or the sensors become silent (OFF).
  • Door contacts may also be installed on the bedroom door, the office door, the bathroom door and perhaps even the refrigerator door.
  • the door contacts emit OPEN/CLOSE signals whenever the door is opened or closed. All signals are collected in a single time-stamped file, one signal per line.
  • the format includes the date, the time, the sensor identification and the event type (ON/OFF/OPEN/CLOSE).
  • a representation of a time-stamped event includes listing the events corresponding to the sensor activations together with the date and time at which the events occurred.
  • the first step of the proposed method and apparatus includes detecting frequent patterns in the sequence of sensor activations or in the sequence of activities of the daily living (e.g. presence in room). If a pattern has occurred only once, for example, it is may not be useful, for among other reasons, that no typical duration distribution can be calculated (computed) in a later step.
  • the motion sensors and door contacts are not necessarily smart devices and they do not have sufficient processing power to perform the proposed method so the time-stamped event data is transmitted to a server for recordation (storage) and processing.
  • the collected time-stamped event data is, thus, forwarded to a server where the collected time-stamped event data is used to identify the user's life patterns in their home or non-medical residence.
  • a pattern could be:
  • a set (collection) of frequent patterns each being characteristic of an activity of the daily living of the person is obtained by the server and recorded (stored) for further processing. Each pattern is represented by a set of its occurrences in the data set (data base).
  • the frequently occurring pattern occurrences in the dataset and their duration are considered.
  • the duration of the occurrence of a pattern may be computed as the time difference between the time-stamp of the last item in the pattern and the timestamp of the first item in the pattern.
  • a set of known typical durations of the data base (data set) of patterns of activities of daily living is obtained (determined, calculated).
  • the probability of this duration is tested against known typical durations for this pattern. This may be done using statistical hypothesis testing or any other method that would compute a deviation score between the observed duration and the set of typical durations. For example, if a set of typical durations has a Gaussian distribution, then a duration that is greater than the mean plus (or minus) twice the standard deviation is an anomaly (it is outside of the confidence interval of 95% for this pattern). This step produces a confidence anomaly score for this new occurrence.
  • the anomaly score may for instance be a Boolean (yes/no value) or the p-value obtained from the statistical hypothesis test.
  • an anomaly may be detected if the monitored user goes to the bathroom from the bedroom and the usual duration is exceeded.
  • the duration of each pattern is recomputed using the last (latest) occurrence of the pattern. Once the pattern duration exceeds usual durations for the pattern, an anomaly is detected and an alert is sent (transmitted).
  • the monitored person user usually spends half an hour and almost never spends a whole hour in the bathroom after leaving the bedroom, then it would take about an hour to detect the anomaly (incident).
  • the sensitivity of anomaly detection may be adapted according to use cases (for example, it may be preferable to receive too many alerts as opposed to not enough alerts so the anomaly detection sensitivity may be set higher thus anomaly detection may occur earlier and vice versa).
  • a same pattern may be characteristic of several activities of the daily living. For example, going in the kitchen at night to drink water and going in the kitchen at noon to prepare lunch may exhibit similar patterns but very different durations. Thus, a pattern may exhibit several types of duration distributions. This may be detected by modeling the durations of the pattern as a mixture of distributions. These patterns may also be labeled differently based on the time of day at which the pattern occurred. In a last optional step (alert), a threshold may be used to determine which alerts should be raised for care givers. An alert may show the pattern occurrence, the duration observed and the confidence score for the anomaly.
  • Fig. 2 is a schematic diagram of an exemplary embodiment of a proposed method and apparatus
  • the time-stamped event data is received and forwarded to a server for recordation (logging, storage) in a data base (data set).
  • the data base (data set) is mined for frequently occurring patterns.
  • the frequent patterns are stored at the server.
  • the server then calculates (computes) the duration of the patterns.
  • the typical pattern duration distributions are then calculated (computed).
  • a new pattern occurrence is then received by the server and the new pattern is compared to the existing patterns and their durations to determine if there is anomalous behavior (an anomaly).
  • An anomaly score is then calculated (computed).
  • the anomaly score is a confidence anomaly score.
  • a duration that is greater than the mean plus (or minus) twice the standard deviation is an anomaly (it is outside of the confidence interval of 95% for this pattern).
  • the anomaly score may for instance be a Boolean (yes/no value) or the p-value obtained from the statistical hypothesis test.
  • Fig. 3 is a flowchart of an exemplary embodiment of a proposed method.
  • the server mines the time-stamped event data to identify frequent patterns of user life routines. The number of occurrences of the patterns may be compared to a threshold to determine if they are occurring with sufficient frequency. If a pattern has occurred only once, for example, it is not going to be useful for among other reasons no typical duration distribution can be calculated (computed) in a later step. These patterns may be found using known methods of data base (data set) mining. During this step, it is unnecessary to use the time-stamp, although the time-stamp could also be used.
  • a set of frequently occurring patterns each being characteristic of an activity of the daily living of the person is obtained by the server and recorded (logged, stored) for further processing.
  • Each pattern is represented by a set of its occurrences in the data set (data base).
  • the duration of the frequently occurring patterns is calculated (computed).
  • the duration of the occurrence of a pattern may be computed as the time difference between the time-stamp of the last item in the pattern and the time-stamp of the first item in the pattern.
  • Given its set of occurrences, a set of known typical durations of the data base (data set) of patterns of activities of daily living is obtained (determined, calculated).
  • the server receives new time-stamped event data and identifies a new pattern occurrence from the newly received time-stamped event data. Given a new occurrence of an already known pattern, together with its duration, the probability of this duration is tested against known typical durations for this pattern. This may be done using statistical hypotheses testing or any other method that would compute a deviation score between the observed duration and the set of typical durations. For example, if a set of typical durations has a Gaussian distribution, then a duration that is greater than the mean plus (or minus) twice the standard deviation is an anomaly (it is outside of the confidence interval of 95% for this pattern). This step produces a confidence anomaly score for this new occurrence.
  • the anomaly score may for instance be a Boolean (yes/no value) or the p-value obtained from the statistical hypothesis test.
  • the server creates one or more alerts based on the anomalous behavior of the user and at 320 the server forwards the alerts to the care giver.
  • Fig. 4 is a flowchart of an exemplary implementation of step 305 of Fig. 3 .
  • the server receives time-stamped event data for a period of time and logs (records, stores) the received time-stamped data.
  • the period of time for collection of the time-stamped event data is a period of time necessary to collect and identify enough patterns to be statistically meaningful.
  • the server identifies patterns of user life routines.
  • the server uses a threshold to isolate frequently occurring pattern of user life routines. If a pattern has occurred only once, for example, it is not going to be useful for among other reasons no typical duration distribution can be calculated (computed) in a later step.
  • the frequent occurring patterns of user life routines are stored in a data base.
  • Fig. 5 is a flowchart of an exemplary implementation of step 310 of Fig. 3 .
  • the duration for each frequently occurring pattern is calculated (computed). This is accomplished by taking the difference of the time-stamp of the first item of each frequently occurring pattern of the user's life routine from the time-stamp of the last item of the respective frequently occurring pattern of user's life routine.
  • the time duration of each frequently occurring pattern of user's life routine is stored back in the server's data base (data set) along with the corresponding frequently occurring pattern of the user's life routine.
  • Fig. 6 is a flowchart of an exemplary implementation of step 315 of Fig. 3 .
  • the server receives and logs (stores, records) new time-stamped event data and at 610 the server identifies a new pattern. Both 605 and 610 are or can be performed by 405 and 410 of the frequent pattern mining process described above and shown in Fig. 4 .
  • the server determines the duration of the new pattern. This is or can be performed by 505 of the pattern duration computation process described above and shown in Fig. 5 .
  • the server determines if the new pattern is known.
  • Determination of if the new pattern is known can be performed before duration computation or during new pattern identification if a list of known patterns exists to which a new pattern can be compared.
  • the server compares the new known pattern against the typical pattern duration distribution of the pattern.
  • the server determines if there is an anomaly (anomalous behavior). That is, an anomaly score (confidence anomaly score) is calculated (computed, determined) for the new pattern.
  • the server also creates one or more alerts based on the detected anomalous behavior at 630.
  • Fig. 7 is a block diagram of an exemplary server that performs the proposed method.
  • the server has three main modules each of which has submodules.
  • the three main modules are the Frequent Pattern Item Mining Module, the Pattern Duration Computation Module and the Anomaly Detection Module.
  • the Frequent Pattern Item Mining Module logs time-stamped event data of initial behavior of the user for a period of time at the Receive Data Module.
  • the period of time for collection of the time-stamped event data is a period of time necessary to collect and identify enough patterns to be statistically meaningful.
  • the logged time-stamped event data of the initial behavior of the user is forwarded to the Identify Patterns Module which identifies (mines) patterns of user life routines.
  • the Identify Patterns Module forwards the identified patterns of the user's life routine to the Determine Frequent Patterns Module, which uses a threshold to isolate frequently occurring pattern of user life routines. If a pattern has occurred only once, for example, it is not going to be useful for among other reasons no typical duration distribution can be calculated (computed) in a later step.
  • the Determine Frequent Patterns Module forwards the frequent patterns to the Store Frequent Patterns Module which stores the frequent occurring patterns of user life routines in a data base (data set).
  • the Store Frequent Patterns Module is in communication with the Calculate Duration of Each Pattern Occurrence Module which calculates (computes) the duration for each frequently occurring pattern. This is accomplished by taking the difference of the time-stamp of the first item of each frequently occurring pattern of the user's life routine from the time-stamp of the last item of the respective frequently occurring pattern of user's life routine.
  • the Calculate Duration of Each Pattern Occurrence Module forwards the durations of each frequently occurring pattern to the Store Durations Module which stores the time duration of each frequently occurring pattern of user's life routine in the server's data base (data set) along with the corresponding frequently occurring pattern of the user's life routine.
  • the Store Frequent Patterns Module and the Identify Patterns Module are in communication with the Determine if New Pattern is Known Module which determines if the new logged pattern of subsequent behavior of the user is known.
  • the Determine if New Pattern is Known Module forwards the new known pattern to the Compare New Pattern against Typical Pattern Duration Distribution Module which compares the new known pattern against the typical pattern duration distribution of the pattern.
  • the Store Durations Module and the Calculate Duration of Each Pattern Occurrence Module are in communication with the Compare New Pattern against Typical Pattern Duration Distribution Module.
  • the Compare New Pattern against Typical Pattern Duration Distribution Module forwards the results of the comparison to the Detect Anomaly Module which determines if there is an anomaly (anomalous behavior).
  • an anomaly score (confidence anomaly score) is calculated (computed, determined) for the new pattern.
  • the Detect Anomaly Module also creates an alert based on the detected anomalous behavior of the user.
  • the Detect Anomaly Module forwards any detected anomalies and alerts to the Report Anomaly Module which reports detected anomalies to a care giver.
  • the proposed method and apparatus may be implemented in various forms of hardware, software, firmware, special purpose processors, or a combination thereof.
  • Special purpose processors may include application specific integrated circuits (ASICs), reduced instruction set computers (RISCs) and/or field programmable gate arrays (FPGAs).
  • ASICs application specific integrated circuits
  • RISCs reduced instruction set computers
  • FPGAs field programmable gate arrays
  • the proposed method and apparatus is implemented as a combination of hardware and software.
  • the software is preferably implemented as an application program tangibly embodied on a program storage device.
  • the application program may be uploaded to, and executed by, a machine comprising any suitable architecture.
  • the machine is implemented on a computer platform having hardware such as one or more central processing units (CPU), a random access memory (RAM), and input/output (I/O) interface(s).
  • CPU central processing units
  • RAM random access memory
  • I/O input/output
  • the computer platform also includes an operating system and microinstruction code.
  • the various processes and functions described herein may either be part of the microinstruction code or part of the application program (or a combination thereof), which is executed via the operating system.
  • various other peripheral devices may be connected to the computer platform such as an additional data storage device and a printing device.
  • the elements shown in the figures may be implemented in various forms of hardware, software or combinations thereof. Preferably, these elements are implemented in a combination of hardware and software on one or more appropriately programmed general-purpose devices, which may include a processor, memory and input/output interfaces.
  • general-purpose devices which may include a processor, memory and input/output interfaces.
  • the phrase "coupled" is defined to mean directly connected to or indirectly connected with through one or more intermediate components. Such intermediate components may include both hardware and software based components.
EP15306726.9A 2015-10-29 2015-10-29 Procédé et dispositif pour détecter un comportement anormal d'un utilisateur Withdrawn EP3163546A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP15306726.9A EP3163546A1 (fr) 2015-10-29 2015-10-29 Procédé et dispositif pour détecter un comportement anormal d'un utilisateur

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP15306726.9A EP3163546A1 (fr) 2015-10-29 2015-10-29 Procédé et dispositif pour détecter un comportement anormal d'un utilisateur

Publications (1)

Publication Number Publication Date
EP3163546A1 true EP3163546A1 (fr) 2017-05-03

Family

ID=54366167

Family Applications (1)

Application Number Title Priority Date Filing Date
EP15306726.9A Withdrawn EP3163546A1 (fr) 2015-10-29 2015-10-29 Procédé et dispositif pour détecter un comportement anormal d'un utilisateur

Country Status (1)

Country Link
EP (1) EP3163546A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3457635A1 (fr) * 2017-09-18 2019-03-20 Thomson Licensing Procédé et dispositif pour identifier un utilisateur dans un environnement
CN111459797A (zh) * 2020-02-27 2020-07-28 上海交通大学 开源社区中开发者行为的异常检测方法、系统及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001216585A (ja) * 2000-02-03 2001-08-10 Sekisui Chem Co Ltd 異常行動判定システム
US20030059081A1 (en) * 2001-09-27 2003-03-27 Koninklijke Philips Electronics N.V. Method and apparatus for modeling behavior using a probability distrubution function
US20100063774A1 (en) * 2008-09-11 2010-03-11 Washington State University Systems and methods for adaptive smart environment automation
US20110295583A1 (en) * 2010-05-27 2011-12-01 Infrared Integrated Systems Limited Monitoring changes in behavior of a human subject
WO2015127491A1 (fr) * 2014-02-25 2015-09-03 Monash University Système de surveillance

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001216585A (ja) * 2000-02-03 2001-08-10 Sekisui Chem Co Ltd 異常行動判定システム
US20030059081A1 (en) * 2001-09-27 2003-03-27 Koninklijke Philips Electronics N.V. Method and apparatus for modeling behavior using a probability distrubution function
US20100063774A1 (en) * 2008-09-11 2010-03-11 Washington State University Systems and methods for adaptive smart environment automation
US20110295583A1 (en) * 2010-05-27 2011-12-01 Infrared Integrated Systems Limited Monitoring changes in behavior of a human subject
WO2015127491A1 (fr) * 2014-02-25 2015-09-03 Monash University Système de surveillance

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3457635A1 (fr) * 2017-09-18 2019-03-20 Thomson Licensing Procédé et dispositif pour identifier un utilisateur dans un environnement
CN111459797A (zh) * 2020-02-27 2020-07-28 上海交通大学 开源社区中开发者行为的异常检测方法、系统及介质
CN111459797B (zh) * 2020-02-27 2023-04-28 上海交通大学 开源社区中开发者行为的异常检测方法、系统及介质

Similar Documents

Publication Publication Date Title
US10475331B2 (en) Monitoring activity of an individual
US10037669B2 (en) Fall detection and reporting technology
US10311694B2 (en) System and method for adaptive indirect monitoring of subject for well-being in unattended setting
EP3163545A1 (fr) Détection d'une activité anormale pour personnes âgées et personnes handicapées
US10679756B1 (en) Health and wellness management technology
US7589637B2 (en) Monitoring activity of an individual
US10827951B2 (en) Fall detection using sensors in a smart monitoring safety system
Monekosso et al. Behavior analysis for assisted living
Augusto et al. Smart homes can be smarter
US20080228039A1 (en) Semi-passive method and system for monitoring and determining the status of an unattended person
Aghajan et al. Distributed vision-based accident management for assisted living
EP2184724A1 (fr) Système pour suivre la présence de personnes dans un bâtiment, et procédé et produit de programme informatique
US11224358B2 (en) Smart monitoring safety and quality of life system using sensors
US7009497B2 (en) Method of distinguishing the presence of a single versus multiple persons
Forkan et al. An Internet-of-Things solution to assist independent living and social connectedness in elderly
US11114200B2 (en) Smart monitoring safety system using sensors
Moshtaghi et al. Statistical models for unobtrusively detecting abnormal periods of inactivity in older adults
Forkan et al. Halleyassist: A personalised internet of things technology to assist the elderly in daily living
WO2013023067A2 (fr) Système de surveillance et de suivi, procédé, article et dispositif
EP3163546A1 (fr) Procédé et dispositif pour détecter un comportement anormal d'un utilisateur
Jakkula et al. Enhancing anomaly detection using temporal pattern discovery
Dasios et al. Wireless sensor network deployment for remote elderly care monitoring
Floeck et al. An ambient approach to emergency detection based on location tracking
Akbarzadeh et al. Smart aging system
WO2021219467A1 (fr) Détection d'anomalie de capteur

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20171104