The present invention relates to an apparatus and a method for adaptively managing event-related data. In particular, this invention relates to adaptive monitoring and analyzing of real-time event-related data in a control room.
The explosive growth and widespread variety of spatio-temporal data collection from sensor devices in a surveillance system has raised the demand in spatio-temporal data analytic approaches. There are various useful and important information included in the huge collections of data which could provide valuable knowledge that can advance an understanding of the complex phenomena to be observed in a surveillance system. Finding ways to harness the useful information that lies hidden in these large data repositories and turning these into knowledge and action is of major interest to key stakeholders such as the government bodies and corporations to enable faster sensing, analysis and response to abnormal situations in control room operations.
Spatio-temporal data consists of three main components: spatial (location), time and multivariate categorical attributes describing various properties of an event. These various components of the spatio-temporal data makes it difficult, if not impossible, to use standard techniques of statistical analysis. Particularly, various research papers have highlighted the problems and difficulties of analysing spatio-temporal data due to spatial and temporal dependencies where standard statistical analysis techniques only assume independence among observations. Furthermore, the complex dependencies, heterogeneity and large volume of multivariate spatio-temporal data make behaviour (patterns and structure) exploration and analysis challenging. Two key considerations include computational efficiency and visual effectiveness problems. Conventional techniques are unable to break down the high volume of data to each component to analyze accurately.
In addition to volume and variety that characterize much of the modern real-world data, velocity and volatility are key attributes of streaming data. High-velocity data leads to frequent updates that are hard for a human to track while high volatility of the data implies unknown baseline behaviour that can make it difficult for analysts to understand the causes and implications of the changes.
As stated in the above, most of the monitoring and exploratory analysis techniques have limited ability to handle streaming (continuous) and fragmentary (incomplete and uncertain) large-scale spatio-temporal data in a real-time situation. Many existing analysis and visualization methods rely on pre-processed, cleaned up, static data sets which only work in the absence of corrupted, missing, outlier data points. Hence, adaptively processing real-time data results in major challenges for visual analysis methods because there is neither time nor the whole dataset available to perform manual pre-processing.
It is an object of the present invention to substantially overcome, or at least ameliorate, one or more existing problems.
According to a first aspect of the present disclosure, there is provided a method for adaptively managing events in a control room, the method comprising receiving, from an input capturing device, an input relating to an event; determining a location information and a time information in response to the receipt of the input; determining a pre-determined attribute of the input, the pre-determined attribute determining at least a type of the event; and determining a presentation of the event in response to the determination of the location information, the time information and the pre-determined attribute of the input.
According to a second aspect of the present disclosure, there is provided an apparatus for adaptively managing events in a control room, the apparatus comprising a memory in communication with a processor, the memory storing a computer program recorded therein, the computer program being executable by the processor to cause the apparatus at least to receive, from a plurality of input capturing devices, a plurality of inputs, each of the plurality of inputs relating to at least one event; determine a plurality of location information and a plurality of time information in response to the receipt of the plurality of inputs, each of the plurality of location information and the plurality of time information corresponding to one of the plurality of the inputs; determine a plurality of pre-determined attributes of the plurality of inputs, each of the plurality of pre-determined attributes determining at least a type of the at least one event; and determine a plurality of presentation of the one or more events in response to the determination of the plurality of location information, the plurality of time information and the plurality of pre-determined attribute of the plurality of inputs.
According to yet another aspect of the present disclosure, there is provided a system for adaptively managing events, the system comprising the apparatus in the second aspect and at least one of an input capturing device and a peripheral device in communication with the processor, wherein the peripheral device is configured to generate alerts in the control room.
Other embodiments are also disclosed.
Embodiments of the invention will be better understood and readily apparent to one of ordinary skill in the art from the following written description, which provides examples only, and in conjunction with the drawings in which:
Overview
Embodiments of the present invention will be described, by way of example only, with reference to the drawings. Like reference numerals and characters in the drawings refer to like elements or equivalents.
Some portions of the description which follows are explicitly or implicitly presented in terms of algorithms and functional or symbolic representations of operations on data within a computer memory. These algorithmic descriptions and functional or symbolic representations are the means used by those skilled in the data processing arts to convey most effectively the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of steps leading to a desired result. The steps are those requiring physical manipulations of physical quantities, such as electrical, magnetic or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated.
Unless specifically stated otherwise, and as apparent from the following, it will be appreciated that throughout the present specification, discussions utilizing terms such as “scanning”, “calculating”, “determining”, “replacing”, “generating”, “initializing”, “outputting”, “receiving”, “retrieving”, “identifying”, “predicting” or the like, refer to the action and processes of a computer system, or similar electronic device, that manipulates and transforms data represented as physical quantities within the computer system into other data similarly represented as physical quantities within the computer system or other information storage, transmission or display devices.
The present specification also discloses apparatus for performing the operations of the methods. Such apparatus may be specially constructed for the required purposes, or may comprise a computer or other device selectively activated or reconfigured by a computer program stored in the computer. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various machines may be used with programs in accordance with the teachings herein. Alternatively, the construction of more specialized apparatus to perform the required method steps may be appropriate. The structure of a computer will appear from the description below.
In addition, the present specification also implicitly discloses a computer program, in that it would be apparent to the person skilled in the art that the individual steps of the method described herein may be put into effect by computer code. The computer program is not intended to be limited to any particular programming language and implementation thereof. It will be appreciated that a variety of programming languages and coding thereof may be used to implement the teachings of the disclosure contained herein. Moreover, the computer program is not intended to be limited to any particular control flow. There are many other variants of the computer program, which can use different control flows without departing from the spirit or scope of the invention.
Furthermore, one or more of the steps of the computer program may be performed in parallel rather than sequentially. Such a computer program may be stored on any computer readable medium. The computer readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with a computer. The computer readable medium may also include a hard-wired medium such as exemplified in the Internet system, or wireless medium such as exemplified in the GSM mobile telephone system. The computer program when loaded and executed on such a computer effectively results in an apparatus that implements the steps of the preferred method.
It is to be noted that the discussions contained in the “Background” section and that above relating to conventional methods relate to discussions of devices which form public knowledge through their use. Such should not be interpreted as a representation by the present inventor(s) or the patent applicant that such devices in any way form part of the common general knowledge in the art.
Various embodiments provide apparatuses and methods for adaptively managing event-related data in a control room.
The following disclosure provides a solution for addressing or mitigating at least one of the above discussed problems. One solution is to use an apparatus to adaptively manage events in a control room by analyzing the spatial (location), time and categorical attribute information (or pre-determined attributes) that are derived from the inputs related to the events. It is to be appreciated that inputs relate to image patterns, audio information, estimated number of a crowd information, density information of a crowd and movement information of a crowd. It will become apparent in subsequent description that the categorical attributes used for analysis in various embodiments are a set of user pre-determined attributes.
Conventionally, the processing, integration, and analysis of spatial (location) data is both constrained and underpinned by the fundamental concept of spatial (location) dependence, resulting in spatial (location) correlation where characteristics at proximal locations tend to be correlated. Spatial (location) dependence is weakened by the heterogeneity and relative degree of uniqueness of the geographical space across locations and thus, such dependence inhibits the use of standard techniques of statistical analysis.
Further, by convention, time has an inherent semantic structure with hierarchical system of granularities. There are two specific aspects of the dimensions of time which have to be taken into account when devising analytical methods for temporal and spatio-temporal data.
First, the temporal dimension which is composed of time points (instant in time) or time intervals (temporal primitive with an extent).
Secondly, the temporal structures such as time in an orderly manner (linear and cyclic time) as well as time in a branching manner and multiple perspectives which is particularly relevant for planning or prediction.
Similar concepts of temporal dependence and temporal correlation exist for relationships in time where observations that are collected closer together in time have a strong likelihood of being more closely correlated to one another.
Typically, large volumes of spatio-temporal data could be collected from diverse application domains such as public safety, transportation, social media, healthcare, and environment. These high dimensional data may be composed of many correlated attributes of numeric, ordinal and categorical values describing various states/properties of places and spatial (location) objects. For example, weather measurement data may include temperature, humidity, amount of rainfall and category (e.g. fine, cloudy, rainy) and demonstrates cyclical pattern over time. However, the complex dependencies, heterogeneity and large volume of multivariate spatio-temporal data makes behavior (patterns and structure) exploration and analysis challenging. Two key considerations include computational efficiency and visual effectiveness problems. Conventional techniques are unable to break down the high volume of data to each component to analyze accurately.
The solution provided in this disclosure addresses these problems by adaptively managing event-related data. In an embodiment, this may include using group partitioning on pre-determined (categorical) attributes and producing alert generation and involves methods of interaction in areas of stream and big data mining for real time monitoring, exploration and analysis, through the following:
An adaptive approach for monitoring and analyzing location-referenced dynamic categorical data given frequency and time of the changes.
An alert generation method to display salient changes to the data in such a way that analysts in a control room can understand the context and relevance of the changes, and reason about their causes and implications in real time by keeping their mental model about the data in sync with the evolving stream.
Embodiments of the present invention will be described, by way of example only, with reference to the drawings. Like reference numerals and characters in the drawings refer to like elements or equivalents.
The system 100 comprises an input capturing device 102 in communication with the apparatus 104. In an implementation, the apparatus 104 may be generally described as a physical device comprising at least one processor 108 and at least one memory 106 including computer program code. The at least one memory 106 and the computer program code are configured to, with the at least one processor 108, cause the physical device to perform the operations described in
In an example, the input capturing device 102 may be one which sends an event-related data. In specific implementations, the input capturing device 102 may include at least one of an input capturing device and location-aware sensor device. The input capturing device 102 may be a device, such as a closed-circuit television (CCTV), a camera on remotely-operated or autonomous unmanned aerial vehicle, or a body-worn camera. The input capturing device 102 provides a variety of spatio-temporal data of which location information, time information and pre-determined attributes that may be derived from the related events. While one input capturing device 102 is shown in
In an implementation, location information may include at least one of an input capturing device location information such as building, floor, zone and room information; time information may include at least one of a date information such as year, month, week, day, date, hours, minutes information; and pre-determined attributes information may include at least one of an alert information of event categories such as suspicious list (e.g. detecting suspicious persons, abandoned objects, etc.), watch list (e.g. blacklist, whitelist, unknown list, etc.), type of event (e.g. shouting, glass breaking, device tampering, etc.), type of crowd (e.g. crowd gathering, crowd running away, crowd congestion, etc.) or risk level information (e.g. high, medium, low risk). Each of the location information, time information and pre-determined attributes corresponds to a category of information of the data.
In an embodiment, the pre-determined attributes may be a set of user-defined attributes of which the corresponding information of a watch list includes image patterns such as facial information relating to either a blacklist, a whitelist or an unknown list, etc., which is provided by the user and stored in memory 106 or of the apparatus 104 or a database accessible by the apparatus 104. Additionally or alternatively, the pre-determined attributes may be a set of user-defined attributes of which the corresponding information of an event type includes image patterns such as audio sound waves information relating to either a shouting event, glass breaking event or a device tampering event, etc., which is provided by the user. Further, the pre-determined attributes may be a set of user-defined attributes of which the corresponding information of a crowd type includes a number of a crowd information, density information of a crowd, and a movement information of a crowd, etc., which is provided by the user.
The apparatus 104 may be configured to communicate with the input capturing device 102 and the peripheral device 110. In an example, the apparatus 104 may receive, from the input capturing device 102, event-related data and, after processing by the processor 108 in apparatus 104, generate an alert or send an output to the peripheral device 110.
In turn, the peripheral device 110 may be configured to communicate with the apparatus 104 to generate alerts. Additionally or alternatively, the peripheral device 110 may receive, from the processor 108 of the apparatus 104, an output of the processed event-related data and generate alerts as output.
Referring to
Prior to step 222, the processor 108 of the apparatus 104 is configured to identify image patterns such as facial information and/or audio information, estimated number of a crowd, density information of a crowd and movement information of a crowd from each input at steps 208, 262, 268, 270 and 272. Subsequently, at step 214, it is determined by the processor 108 whether the identified facial information matches at least one facial information that corresponds to a target pre-determined attribute information. For example, the processor 108 may retrieve a target pre-determined attribute information from a database and compare it to the identified facial information. The target pre-determined attribute may be a facial feature that is specific to the target, for example, a facial mole.
In an example, if the identified facial information does not match any of the facial information of the pre-determined attribute information, the identified facial information may be associated with a pre-determined attribute information such as “unknown” in the watch list which is assigned with a lower weightage at step 216. If however, for example, the identified facial information matches at least one facial information that corresponds to a target pre-determined attribute information such as that of a blacklist in the watch list, the pre-determined attribute of the identified facial information will be determined by the processor 108 as one that may be in a blacklist in step 222.
Other than the identification of image patterns at step 208, audio information is also indentified at step 262. Subsequently, at step 264, it is determined by the processor 108 what is the type of event based on the segment of audio recording of the audio information identified from each input at step 262. Further, at step 274, it is also determined by the processor 108 what is the type of crowd based on the estimated number of the crowd, density of the crowd and movement of the crowd identified from each input at steps 268, 270 and 272 respectively.
At steps 210, 212 and 224, the method further comprises the steps of grouping the location information, time information or pre-determined attributes respectively in accordance to one of their corresponding building/floor information, day/hour information and event type/risk level information and then calculating an event importance score of each of the groups at steps 218, 220 and 226 respectively. An event importance score is the final importance score that represents the importance of an event by taking into account the custom weights (a user-defined weightage score indicating the importance/priority of an event type) as well as the recency effects (i.e. same type of events happening consecutively will be scored higher). Details regarding how the event importance score is calculated will be shown in
The method further comprises step 228 where the event importance score of each of the groups are ranked according to a set of pre-determined rules. In an implementation, the set of pre-determined rules may cause the events to be grouped according to similarity/correlation into representational groups, then an occurrence score of 1 is assigned to every corresponding representational group that represents the event type information that has occurred based on change detection; otherwise, an occurrence score of 0 is assigned. As mentioned earlier, the event importance score takes into account recency effects which is accounted for by a recency score which is one that is calculated based on the occurrence score, with the recency score being higher when there are consecutive occurrences of the same event type. More details regarding the formula of recency score will be discussed below together with
To illustrate how the event importance score flags out events of higher importance, take for example, events may be grouped by the same suspicious person detected, at the same location based on event correlation. Then if there is high occurrences of the same suspicious person being detected at the same location, the corresponding recency score will be high. If that particular location happens to have a high weightage score since it is prioritized as an area of interest, the event importance score will be even higher. A representational group with a higher event importance score will be ranked higher than one with a lower event importance score. This allows the high occurrences of a suspicious person detected at the same location of particular interest to be flagged out from the other event types which may have lower occurrences and are not of particular interest to the analyst in the control room.
The processor 108 may generate alerts based on the consolidation of the grouping established in step 230 or send the consolidation of the grouping to the peripheral device 110 which may be configured to generate alerts as output in a control room in response to a receipt of the grouping consolidation information in step 232.
While
As stated earlier, the processor 108 of the apparatus 104 is configured to identify image patterns such as facial information from each input at step 208. After which, the facial information associated with the event-related data from the input capturing devices 302 are assigned to the appropriate event category such as suspicious list (e.g. detecting suspicious persons, abandoned objects, etc.), watch list (e.g. blacklist, whitelist, unknown list, etc.) or risk level (e.g. high, medium, low risk) by the classifier 304 if the identified facial information matches at least one facial information that corresponds to a target pre-determined attribute information as in step 214.
Further, steps 210, 212 and 224 which are the steps of grouping the location information, time information or pre-determined attributes respectively in accordance to one of their corresponding building/floor information, day/hour information and event type/risk level information and the steps of determining an occurrence score of each of the groups at steps 218, 220 and 226 respectively are processed by the aggregator 306.
The change monitor 308 analyzes change and detects unusual anomalous behaviours by tracking both change in value of the occurrence scores and ranking to enhance ranking and prioritization mechanism in step 228.
Event correlation is a technique that relates various events describing or relating to activities in a system to identifiable patterns. It can be defined as a process for consolidating events to increase their information quality, while reducing the quantity of events to provide clear contextual information at a glance. This is processed by the correlation engine 310 at step 228 whereby events are grouped according to similarity/correlation into representational groups.
An analyst's capacity in handling the high velocity, volume and variety of event-related data is limited. Thus, a ranking and prioritization engine 312 to highlight interesting “cluster of events” for further study or exploration is introduced in step 228. “Cluster of events” refers to a group of events with at least one commonality such as a re-occurrence at the same location or a re-appearance of the same target (who could be a loiterer). The ranking mechanism leverages inputs from the change monitor 308 (e.g. the changes in occurrence scores) as one of its key prioritization signals. In an implementation, there is a list of ranking and prioritization rules set by the user which will be run through during the calculation of event importance scores of representational groups by the ranking and prioritization engine 312. For example, the representational groups derived from correlation engine 310 may first have an occurrence score tabulated by the aggregator 306 based on the number of event occurrences. Subsequently, a ranking and prioritization rule may cause the representational groups to have a recency score calculated based on how recent and how frequent the events have occurred. Based on the recency scores and a user-defined weightage scores assigned to each event type, an event importance score is calculated for each representational group and the representational groups are then ranked according to their overall event importance score.
Event tracking engine 314 provides a structured workflow mechanism to process incoming event-related data. Such engine typically provides a way of describing the order of execution and dependent relationships between pieces of short- or long-running work from start to finish to be executed by the system functions.
316, 318 and 320 are software modules that define how location information, time information and pre-determined attribute information may be grouped. An example of how software modules 316, 318 and 320 work, correspond to
In an implementation, there is an adaptive event management solution illustrated in
Simultaneous processing and categorization (grouping) of event-related data received by the input capturing devices in accordance to their corresponding location information, time information and pre-determined attribute information is essential in the method of adaptively managing event-related data in a control room. Many of the existing methods for streaming (real-time) event-related data categorization (grouping) cannot enable on-the-fly separation of event clusters (groups) from the noise and immediate presentation of signification clusters (groups) and their evolution. A multilevel grouping approach is introduced in the adaptive event management method to allow clear and efficient separation of event clusters (groups) and easy tracking and presentation of the evolution of the signification clusters (groups). An example of a multilevel grouping approach is to organise the information in a hierarchical data structure, allowing information to be broken down into smaller granularities. The following illustrations further describe the components of the data layer 434 that store and manage incoming real-time data stream.
As shown in
Further, as shown in
As shown in
Basic data 608 shows an example of how event data may be grouped according to a conventional method while enriched data 610 shows an example of how event data may be grouped according to an embodiment which advantageously enhances the representation of the data by providing relationship information of the events within the groups. By various embodiments of the invention, the input may be further processed and represented in various categories like “Location” 602, “Time” 604 and “Pre-determined Attributes” 606.
The analytics layer of an adaptive event management system in an embodiment is further described below. A fundamental capability for real-time analytics in a surveillance system is to analyze change and detect unusual, anomalous behaviours to pick up valuable insights for prompt action and control. Furthermore, in applications that process real-time events, a common requirement is to perform some set-based computation (i.e. aggregation) or other operations over subsets of events that fall within some period of time. The data aggregation provides mechanism to track aggregate data across groupings or multi-levels instead of just based on pure groupings by time only. This process is required by adaptive control to enable interactive query in identifying events that require attention based on specific level of interest. Also, the ranking and prioritization mechanism in an embodiment highlights interesting cluster of events for further study or exploration. This can be accomplished by the recency score where a higher score is derived from a more recent event, and repeated events of a similar type (e.g. higher score for same person detected multiple times within short period of time). Lastly, the event tracking engine in an embodiment provides structured workflow mechanism to handle lifecycle of event-related data from creation until removal.
To take the recency effect of the occurrences into consideration, a recency score is introduced.
Take for example event E2 from
For example, to determine the levels (take for example Level 1 to Level 5 in 1106) to group the event types:
A time decay factor of 0.75 and weightage scores as indicated in score table 704 are used in the following examples. In
Unless specifically stated otherwise, and as apparent from the following, it will be appreciated that throughout the present specification, discussions utilizing terms such as “scanning”, “calculating”, “analyzing”, “determining”, “replacing”, “generating”, “initializing”, “outputting”, “receiving”, “retrieving”, “identifying”, “predicting” or the like, refer to the action and processes of a computer system, or similar electronic device, that manipulates and transforms data represented as physical quantities within the computer system into other data similarly represented as physical quantities within the computer system or other information storage, transmission or display devices.
It will be appreciated by a person skilled in the art that numerous variations and/or modifications may be made to the present invention as shown in the specific embodiments without departing from the spirit or scope of the invention as broadly described. For example, the above description mainly presenting alerts on a visual interface, but it will be appreciated that another type of alert presentation, such as sound alert, can be used in alternate embodiments to implement the method. Some modifications, e.g. adding an access point, changing the log-in routine, etc., may be considered and incorporated. The present embodiments are, therefore, to be considered in all respects to be illustrative and not restrictive.
For example, the whole or part of the exemplary embodiments disclosed above can be described as, but not limited to, the following supplementary notes.
(Supplementary Note 1)
A method for adaptively managing events in a control room, comprising:
(Supplementary Note 2)
The method of note 1, further comprising:
(Supplementary Note 3)
The method of note 2, wherein each of the plurality of location information has a corresponding at least one of a device location information, including a building information or a floor information, and wherein the step of determining location information in response to the receipt of the inputs comprises:
(Supplementary Note 4)
The method of note 2, wherein each of the plurality of time information has a corresponding at least one of a date information, including a day information or an hour information, and wherein the step of determining time information in response to the receipt of the inputs comprises:
(Supplementary Note 5)
The method of note 2, wherein each of the plurality of pre-determined attributes has a corresponding at least one of an alert information, including an event type information or a risk level information, and wherein the step of determining pre-determined attributes in response to the receipt of the inputs comprises:
(Supplementary Note 6)
The method of note 3, wherein the step of determining location information in response to the receipt of the inputs comprises:
(Supplementary Note 7)
The method of note 4, wherein the step of determining time information in response to the receipt of the inputs comprises:
(Supplementary Note 8)
The method of note 5, wherein the step of determining pre-determined attributes in response to the receipt of the inputs comprises:
(Supplementary Note 9)
The method of note 5, wherein the step of grouping the pre-determined attributes of the inputs comprises:
(Supplementary Note 10)
The method of note 5, wherein the step of grouping the pre-determined attributes of the inputs comprises:
(Supplementary Note 11)
The method of note 5, wherein the step of grouping the pre-determined attributes of the inputs comprises:
(Supplementary Note 12)
The method of any one of notes 6, 7, 8, wherein the step of determining the presentation of the input in response to the event comprises:
(Supplementary Note 13)
An apparatus for adaptively managing events in a control room, the apparatus comprising:
(Supplementary Note 14)
The apparatus of note 13, wherein each of the plurality of location information has a corresponding at least one of a device location information, including a building information or a floor information and wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 15)
The apparatus of note 13, wherein each of the plurality of time information has a corresponding at least one of a date information, including a day information or an hour information and wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 16)
The apparatus of note 13, wherein each of the plurality of pre-determined attributes has a corresponding at least one of an alert information, including an alert type information or a risk level information, and wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 17)
The apparatus of note 14, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 18)
The apparatus of note 15, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 19)
The apparatus of note 16, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 20)
The apparatus of note 16, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 21)
The apparatus of note 16, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 22)
The apparatus of note 16, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 23)
The apparatus of any one of notes 17, 18 or 19, wherein the memory and the computer program is executed by the processor to cause the apparatus further to:
(Supplementary Note 24)
A system for adaptively managing events, the system comprising:
This application is based upon and claims the benefit of priority from Singapore Patent Application No. 10201807628X, filed on Sep. 5, 2018, the disclosure of which is incorporated herein in its entirety by reference.
Number | Date | Country | Kind |
---|---|---|---|
10201807628X | Sep 2018 | SG | national |
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/JP2019/032162 | 8/16/2019 | WO | 00 |