Safety level prediction of users after occurrence of a disaster

The method predicts user safety levels post-disaster by analyzing digital twin anomalies from existing sensor data, addressing the limitations of previous systems by including human factors and providing real-time safety assessments for improved disaster management.

WO2024232841A1PCT designated stage expired Publication Date: 2024-11-14TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/TR2023/050435
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

Current disaster management systems, such as the digital twin-based system, do not account for human beings and are limited to predicting outcomes of simulated disasters, failing to track safety status after a disaster has occurred.

Method used

A method and controller that obtain a current digital twin instance of a user from wireless network data, compute an anomaly score by comparing it to previous instances, and predict the user's safety level post-disaster, incorporating existing sensor data without requiring special-purpose sensors.

Benefits of technology

Enables the tracking of human safety status after a disaster, overcoming limitations of previous systems by encompassing human beings and providing real-time safety assessments without additional sensor infrastructure, facilitating effective rescue operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure TR2023050435_14112024_PF_FP_ABST
    Figure TR2023050435_14112024_PF_FP_ABST
Patent Text Reader

Abstract

There is provided techniques for predicting safety level of a user after occurrence of a disaster. A method is performed by a controller. The method comprises obtaining an indication of a disaster in an area where the user is located. The method comprises, in response thereto, obtaining a current instance of a digital twin of the user from information received over a wireless network from a user equipment associated with the user. The method comprises computing an anomaly score for the user by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user obtained prior to the indication of the disaster. The method comprises predicting the safety level of the user after the disaster has occurred based on the anomaly score for the user.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] SAFETY LEVEL PREDICTION OF USERS AFTER OCCURRENCE OF A DISASTER

[0002] TECHNICAL FIELD

[0003] Embodiments presented herein relate to a method, a controller, a computer program, and a computer program product for predicting safety level of a user after occurrence of a disaster.

[0004] BACKGROUND

[0005] In general terms, a disaster management system is a system that involves a strategical organization of resources to lessen the harm that disasters cause. The disaster management system might then be configured to manage the responsibilities of disaster prevention, preparedness, response, and recovery.

[0006] In the document by Dogan, Ozgiir, Oguzhan §ahin, and Enis Karaarslan entitled “Digital twin based disaster management system proposal: DT-DMS”, published in the Journal of Emerging Computer Technologies 1.2 (2021), pages 25-30, is described a disaster management system based on a digital twin representation of a city. The disaster management system is proposed for the purpose of education and preparation of personnel working in a disaster management center. In the proposed system, sensor data from Internet of Things (loT) devices is gathered and kept updated to continuously update a virtual copy, denoted a digital twin, of a city. Utilizing the digital twin, an emergency event of a disaster can be simulated, and decisions as taken by the personnel working in the disaster management center can be evaluated by analyzing possible outcomes and estimate the best possible action.

[0007] One drawback of the above disclosed disaster management system is that the digital twin does not encompass human beings.

[0008] Another drawback of the above disclosed disaster management system is that it only predicts possible outcomes of simulated disasters.

[0009] Hence, there is still a need for improved disaster management system.

[0010] SUMMARY

[0011] An object is to provide techniques that overcome the above drawbacks. A particular object is to provide techniques where the digital twin encompasses human beings.

[0012] A particular object is to provide techniques that are not limited to prediction of possible outcomes of simulated disasters.

[0013] A particular object is to provide techniques that can be used to track the safety status of human beings, even after a disaster has occurred.

[0014] According to a first aspect there is presented a method for predicting safety level of a user after occurrence of a disaster. The method is performed by a controller. The method comprises obtaining an indication of a disaster in an area where the user is located. The method comprises, in response thereto, obtaining a current instance of a digital twin of the user from information received over a wireless network from a user equipment associated with the user. The method comprises computing an anomaly score for the user by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user obtained prior to the indication of the disaster. The method comprises predicting the safety level of the user after the disaster has occurred based on the anomaly score for the user.

[0015] According to a second aspect there is presented a controller for predicting safety level of a user after occurrence of a disaster. The controller comprises processing circuitiy. The processing circuitiy is configured to cause the controller to obtain an indication of a disaster in an area where the user is located. The processing circuitry is configured to cause the controller to, in response thereto, obtain a current instance of a digital twin of the user from information received over a wireless network from a user equipment associated with the user. The processing circuitry is configured to cause the controller to compute an anomaly score for the user by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user obtained prior to the indication of the disaster. The processing circuitiy is configured to cause the controller to predict the safety level of the user after the disaster has occurred based on the anomaly score for the user. According to a third aspect there is presented a controller for predicting safety level of a user after occurrence of a disaster. The controller comprises an obtain module configured to obtain an indication of a disaster in an area where the user is located. The controller comprises an obtain module configured to, in response thereto, obtain a current instance of a digital twin of the user from information received over a wireless network from a user equipment associated with the user. The controller comprises a compute module configured to compute an anomaly score for the user by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user obtained prior to the indication of the disaster. The controller comprises a predict module configured to predict the safety level of the user after the disaster has occurred based on the anomaly score for the user.

[0016] According to a fourth aspect there is presented a computer program for predicting safety level of a user after occurrence of a disaster. The computer program comprises computer code which, when run on processing circuitry of a controller, causes the controller to perform actions. One action comprises the controller to obtain an indication of a disaster in an area where the user is located. One action comprises the controller to, in response thereto, obtain a current instance of a digital twin of the user from information received over a wireless network from a user equipment associated with the user. One action comprises the controller to compute an anomaly score for the user by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user obtained prior to the indication of the disaster. One action comprises the controller to predict the safety level of the user after the disaster has occurred based on the anomaly score for the user.

[0017] According to a fifth aspect there is presented a computer program product comprising a computer program according to the fourth aspect and a computer readable storage medium on which the computer program is stored. The computer readable storage medium could be a non-transitory computer readable storage medium.

[0018] Advantageously, these aspects overcome the above drawbacks. Advantageously, according to these aspects, the digital twin encompasses human beings.

[0019] Advantageously, these aspects are not limited to prediction of possible outcomes of simulated disasters.

[0020] Advantageously, these aspects can be used to track the safety status of human beings, even after a disaster has occurred.

[0021] Advantageously, these aspects do not require any special-purpose sensors but can rely on sensor data as available from existing sensors. Therefore, a the herein disclosed embodiments can have a lightweight implementation compared to being based on personal digital twins as used in the healthcare domain.

[0022] Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the attached dependent claims as well as from the drawings.

[0023] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / an / the element, apparatus, component, means, module, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, module, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

[0024] BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The inventive concept is now described, by way of example, with reference to the accompanying drawings, in which:

[0026] Fig. 1 is a schematic diagram illustrating a communications network according to embodiments;

[0027] Fig. 2 is a block diagram of a controller according to an embodiment;

[0028] Fig. 3 is a flowchart of methods according to embodiments;

[0029] Fig. 4 schematically illustrates events along a timeline according to an embodiment; Fig. 5 is s sequence diagram of a method according to an embodiment;

[0030] Fig. 6 is a schematic diagram showing functional units of a controller according to an embodiment;

[0031] Fig. 7 is a schematic diagram showing functional modules of a controller according to an embodiment; and

[0032] Fig. 8 shows one example of a computer program product comprising computer readable storage medium according to an embodiment.

[0033] DETAILED DESCRIPTION

[0034] The inventive concept will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments of the inventive concept are shown. This inventive concept may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided byway of example so that this disclosure will be thorough and complete, and will fully convey the scope of the inventive concept to those skilled in the art. Like numbers refer to like elements throughout the description. Any step or feature illustrated by dashed lines should be regarded as optional.

[0035] The embodiments disclosed herein relate to techniques for predicting safety level of a user after occurrence of a disaster. In order to obtain such techniques there is provided a controller, a method performed by the controller, a computer program product comprising code, for example in the form of a computer program, that when run on a controller, causes the controller to perform the method.

[0036] Fig. 1 is a schematic diagram illustrating a communications network too where embodiments presented herein can be applied. The communications network too comprises a wireless network no in which a network node 120 provides network access to user equipment 130. There could be different types of network nodes 120. in some non-limiting examples, the network node is any of a (radio) access network node, radio base station, base transceiver station, node B (NB), evolved node B (eNB), gNB, transmitter and receiver point (TRP), access point, integrated access and backhaul node, or the like. There could be different types of user equipment 130. In some non-limiting examples, the user equipment is any of a portable wireless communication device, mobile station, mobile phone, terminal device, smartphone, laptop computer, tablet computer, or the like. The user equipment 130 is associated with a user 170. In this respect, the user equipment 130 might hold a subscription, or a subscription profile, of the user 170.

[0037] The user 170 might wear one or more sensors 140. The sensors 140 are configured to be in communication with the user equipment 130, and vice versa. The user equipment 130 and the sensors 140 might communicate over a wireless interface, such as over a sidelink, using Bluetooth, etc. or even over a wired interface. Thus, the sensors 140 do not necessarily need to be configured for cellular network access. The number of available sensors 140 and / or the types of sensors 140, might vary. Some non-limiting examples of sensors 140 are user-body sensors and environment sensors such as smart devices, wrist bands, smart home sensors. The sensors 140 might be capable of measuring, registering, or estimating the physical activity of the user 170, the pulse of the user 170, the blood oxygen level of the user 170, etc. In some examples, one or more of the sensors 140 are part of, integrated with, or collocated with, the user equipment 130. In any case, the user equipment 130 is configured to collect available sensor data from the sensors 140 as well as user data and other information such as location, world clock time and date, weather information, etc., and report this data to a controller 160. In some examples, the user equipment 130 is even capable of generating a digital twin of the user 170 based on the available sensor data from the sensors 140, possibly in combination with user data and / or other type of information, and of reporting the digital twin to the controller 160. In this respect, it is assumed that any communication between the user equipment 130 and the controller 160 is end-to-end encrypted. In this way, sensitive user information can be transferred to the controller 160 where it can be securely stored.

[0038] The network node 120 is operatively connected to a controller 160 located in a network 150. The network 150 might be a core network or a service network, such as the Internet, or a dedicated cloud computational environment. Alternatively, the controller 160 is part of, integrated with, or collocated with, the network node 120. In general terms the controller 160 is configured to predict the safety level of the user 170 after occurrence of a disaster. Further aspects of the controller 160 will be disclosed next.

[0039] In Fig. 2 is provided a block diagram of a controller 200. The controller 200 implements a digital safety twin (DST) application function 210 and a DST database 220. In other examples, the DST database 220 is physically separated from the controller 200 but where the controller 200 has access to content stored in the DST database 220. The DST database 220 is a data repository in which n historical instances of digital twins (denoted “Digital twin time 1”, “Digital twin time 2”, ..., “Digital twin time n”,) can be stored for each of N users (denoted “User 1”, “User 2”, ..., “User IV”). The DST application function 210 comprises a process information block 210a configured to obtain information from the user equipment 130 as well as to retrieve information from, and store information in, the DST database 220. The DST application function 210 comprises an obtain digital twin block 210b configured to obtain instances of digital twins of different users 170 and to store the instances in the DST database 220. As will be further disclosed below, the digital twins might be obtained by either being received from the user equipment 130 or being generated based on information received from the user equipment 130. In this way, instances of digital twins can be obtained and stored at regular time intervals, as well as upon a specific need, such as when a disaster occurs. The DST application function 210 comprises an anomaly analysis block 210c configured to compare different instances of digital twins of one and the same user 170 to each other as part of performing an anomaly analysis for this user. As will be further disclosed below, the controller 200 is configured to perform an anomaly analysis for a user upon obtaining an indication that a disaster has occurred in an area where the user 170 is located.

[0040] Fig. 3 is a flowchart illustrating embodiments of methods for predicting safety level of a user 170 after occurrence of a disaster. The methods are performed by the controller 160, 210, 600, 700. The methods are advantageously provided as computer programs 820.

[0041] In general terms, the method is based on predicting the safety status of the user 170 after a disaster has occurred by generating an anomaly score using a digital twin of the user 170, where at least one previous instance of the digital twin is compared to an instance of the digital twin as obtained after the disaster has occurred. S102: The controller 160, 210, 600, 700 obtains an indication of a disaster in an area where the user 170 is located.

[0042] The controller 160, 210, 600, 700 in response thereto, i.e., in response to having obtained the indication in S102, performs actions S104-2 to S104-6.

[0043] S104-2: The controller 160, 210, 600, 700 obtains a current instance of a digital twin of the user 170. The current instance of the digital twin of the user 170 is by the controller 160, 210, 600, 700 obtained from information received over a wireless network 110 from a user equipment 130 associated with the user 170.

[0044] The current instance of the digital twin of the user 170 is thus based on available sensors and the collected user data. This implies that different type of information might be available and used for different users 170.

[0045] An anomaly analysis can then be performed by comparing the current instance of the digital twin to one or more previous instances of the same digital twin.

[0046] S104-4: The controller 160, 210, 600, 700 computes an anomaly score for the user 170. The anomaly score for the user 170 is computed by the controller 160, 210, 600, 700 comparing the current instance of the digital twin to at least one previous instance of the digital twin. The at least one previous instance of the digital twin is defined by sensor data of the user 170 obtained prior to the indication of the disaster.

[0047] The anomaly score for the user 170 can then be used to predict the safety status of the user after the disaster has occurred.

[0048] S104-6: The controller 160, 210, 600, 700 predicts the safety level of the user 170 after the disaster has occurred. The safety level of the user 170 is predicted based on the anomaly score for the user 170.

[0049] In this way, the controller 160, 210, 600, 700 can combine the use of digital twins with a disaster management service to aid critical rescue operations.

[0050] Embodiments relating to further details of predicting safety level of a user 170 after occurrence of a disaster as performed by the controller 160, 210, 600, 700 will now be disclosed with continued reference to Fig. 3. There maybe different ways for the controller 160, 210, 600, 700 to obtain the current instance of the digital twin of the user 170 in S104-2.

[0051] In some aspects the controller 160, 210, 600, 700 is configured to itself generate the current instance of the digital twin of the user 170 based on (raw) sensor data received from the user equipment 130. That is, in some embodiments, the information comprises sensor data of the user 170 as obtained by the user equipment 130 after occurrence of the disaster. The controller 160, 210, 600, 700 is then further configured to perform (optional) action SiO4-2a as part of action S104-2.

[0052] SiO4-2a: The controller 160, 210, 600, 700 obtains the current instance of the digital twin of the user 170 by generating the current instance of the digital twin of the user 170 based on the obtained sensor data.

[0053] In other aspects, the controller 160, 210, 600, 700 receives the current instance of the digital twin of the user 170 from the user equipment 130. That is, in some embodiments, the information comprises the current instance of the digital twin of the user 170 as obtained by the user equipment 130 after occurrence of the disaster.

[0054] Further in this respect, regardless if the information comprises the current instance of the digital twin or not, the information received from the user equipment 130 might comprises further pieces of information. In some non-limiting and illustrative examples, the information received from the user equipment 130 further comprises any, or any combination, of: location information of the user equipment 130, a timestamp for the point in time when the information was collected at the user equipment 130, current weather information for the location of the user equipment 130. In some non-limiting and illustrative examples, the information received from the user equipment 130 additionally or alternatively comprises any, or any combination, of: environmental and geographical data, such as air pollution information (that can effect on human vital information), population density (that can affect the response to a disaster), nearby infrastructure type (that can affect the type of response to disaster), surveillance camera information (that can be used to understand the severity of disaster).This information might be used to assist the controller 160, 210, 600, 700 when performing the anomaly analysis. There are different ways in which the anomaly score is represented. In some embodiments, the anomaly score is represented as a probability value. The predicted safety level can then represent the probability of abnormity of the current instance of the digital twin of the user 170.

[0055] In some aspects, the safety status of the user 170 is shared with a rescue authority. Therefore, in some embodiments, the controller 160, 210, 600, 700 is further configured to perform (optional) action S104-8.

[0056] S104-8: The controller 160, 210, 600, 700 shares the safety level of the user 170 with a rescue management system.

[0057] The rescue management system can then, based on the safety level of the user 170, perform the appropriate action, for example notifying a rescue crew, etc.

[0058] There could be different examples of sensor data. In some non-limiting and illustrative examples, the sensor data comprises any, or any combination, of: physical activity of the user 170, pulse of the user 170, blood oxygen level of the user 170. In some non-limiting and illustrative examples, the sensor data additionally or alternatively comprises any, or any combination, of: body temperature data (that can be vital for the health of the user), ambient light that the user is exposed to (that can give information of the situation of user, e.g., whether the user is located under debris in an earthquake situation, etc.), gyroscope data (that can be indicative of user activity, user orientation, user rotation, etc.). This sensor data might be used to assist the controller 160, 210, 600, 700 when performing the anomaly analysis.

[0059] As noted above, the current instance of the digital twin is compared to at least one previous instance of the digital twin, where the at least one previous instance of the digital twin is defined by sensor data of the user 170 obtained prior to the indication of the disaster. In this respect, the controller 160, 210, 600, 700 might have access to a set of one or more previous instances of the digital twin. Each previous instance of the digital twin is defined by sensor data of the user 170 obtained for a respective time instant. In some embodiments, the current instance of the digital twin is then at least compared to the most recent of the at least one previous instances of the digital twin. Reference is here made to Fig. 4 which shows events occurring at times to, ti, t2, t3, and t4 along a timeline. A disaster is illustrated as occurring at time t3. A disaster occurs at time t3. Events at times to, ti, t2 thus occur before the disaster whilst the event at time t4 occurs after the disaster. At each of times to, ti, t2 the controller 160, 210, 600, 700 obtains a respective instance of the digital twin of the user 170. At least the latest obtained instance of the digital twin of the user 170 is stored. At time t38or shortly thereafter), the controller 160, 210, 600, 700 obtains an indication of the disaster as in action S102. At time t4, in response to the disaster having occurred at time t3, the controller 160, 210, 600, 700 obtains a current instance of a digital twin of the user 170, as in action S104-2 and then performs an anomaly analysis as in actions S104-4 and S104-6 to predict the safety level of the user 170 after the disaster has occurred.

[0060] There may be different ways for the controller 160, 210, 600, 700 to compare the current instance of the digital twin to the at least one previous instance of the digital twin as part of computing the anomaly score for the user 170 in action S104-4.

[0061] In some aspects, the comparison involves the use of statistical based models.

[0062] In particular, in some embodiments, comparing the current instance of the digital twin to the at least one previous instance of the digital twin in action S104-4 comprises performing a statistical comparison between the current instance of the digital twin and the at least one previous instance of the digital twin.

[0063] There could be different examples of statistical comparisons that are performed. In some embodiments, performing the statistical comparison comprises assessing whether the current instance of the digital twin and the at least one previous instance of the digital twin follow a common probability distribution or not.

[0064] That is, a statistical based approach can be carried out by testing if the current instance of the digital twin (say, the instance of the digital twin at the specific time, t) follows the same probability distribution as the distribution of the at least one previous instance of the digital twin, as represented by a training dataset. The training dataset can be created by gathering previous instances of the digital twin during normal conditions, i.e., before the disaster occurred. Therefore, if the instance at time t follows a different distribution than the instances in the training dataset, the instance at time t will be labeled as an anomaly instance. In some aspects, the comparison involves the use of multi-variate time-series analysis.

[0065] In particular, in some embodiments, comparing the current instance of the digital twin to the at least one previous instance of the digital twin in action S104-4 comprises performing multi-variate time-series analysis on the current instance of the digital twin and the at least one previous instance of the digital twin.

[0066] There could be different examples of multi-variate time-series analysis that are performed. In some embodiments, performing the multi-variate time-series analysis comprises comparing the current instance of the digital twin to a prediction of the current instance of the digital twin. The prediction is determined based on the at least one previous instance of the digital twin. The divergence between the predicted value and the actual value can be used to indicate how the current instance of the digital twin differentiates from the at least one previous instance of the digital twin.

[0067] In some aspects, the comparison involves the use of a machine learning (ML) model.

[0068] In further detail, for ML-based approaches any ML-model can be trained by using a dataset defined by historical instances of the digital twin. If the dataset includes normal situation instances (i.e., instances of the digital twin as obtained prior to occurrence of any disaster), any divergence from the dataset is considered as abnormal (i.e., the output is binary-valued); however, if the ML-model is trained with both normal and abnormal instances, the output will be the probability of abnormality.

[0069] One example for predicting the safety level of a user after occurrence of a disaster will be disclosed next with reference to the signaling diagram of Fig. 5.

[0070] S201: Sensor data for one or more users is obtained by one or more user equipment 130 from one or more sensors 140.

[0071] S202: The user equipment 130 generates a respective instance of a digital twin of each user for which sensor data is obtained and provides the digital twins to the controller 160 / 210. S203: The one or more digital twins is / are by the controller 160 / 210 stored in a database 220.

[0072] S204: The controller 160 / 210 checks whether or not a disaster occurs. Step S201 can be entered again for new instances of the digital twins to be generated and stored as long as no disaster occurs. If a disaster has occurred, step S205 is entered. For example, the controller might receive an indication, as in step 8204a, from an emergency system 510 that a disaster has occurred. The indication includes information of the location, and possible other information, where the disaster occurred.

[0073] S205: Sensor data for one or more users is obtained by one or more user equipment 130 from one or more sensors 140.

[0074] S206: The user equipment 130 generates a respective instance of a digital twin of each user for which sensor data is obtained and provides the digital twins to the controller 160 / 210.

[0075] S207: In response to having obtained information that the disaster occurred at a certain location, the controller 160 / 210 tags any new instances of digital twins of users located where the disaster occurred as post-disaster and stores the new instances in the database 220.

[0076] S208: The controller 160 / 210 performs an anomaly analysis, as in S104-2, S104-6, and S104-6, for each user for which a post-disaster instance digital twin has been obtained. The anomaly analysis is performed by comparing the latest received instance (i.e., the instance tagged as post-disaster) of the digital twin to one or more previously stored instances of the same digital twin.

[0077] S209: The controller, for each user for which the anomaly analysis was performed, shares the safety level of the user with a rescue management system 520, as in S104- 8.

[0078] Fig. 6 schematically illustrates, in terms of a number of functional units, the components of a controller 600 according to an embodiment. Processing circuitry 610 is provided using any combination of one or more of a suitable central processing unit (CPU), multiprocessor, microcontroller, digital signal processor (DSP), etc., capable of executing software instructions stored in a computer program product 8io (as in Fig. 8), e.g. in the form of a storage medium 630. The processing circuitry 610 may further be provided as at least one application specific integrated circuit (ASIC), or field programmable gate array (FPGA).

[0079] Particularly, the processing circuitry 610 is configured to cause the controller 600 to perform a set of operations, or steps, as disclosed above. For example, the storage medium 630 may store the set of operations, and the processing circuitry 610 may be configured to retrieve the set of operations from the storage medium 630 to cause the controller 600 to perform the set of operations. The set of operations may be provided as a set of executable instructions.

[0080] Thus the processing circuitry 610 is thereby arranged to execute methods as herein disclosed. The storage medium 630 may also comprise persistent storage, which, for example, can be any single one or combination of magnetic memory, optical memory, solid state memory or even remotely mounted memory. The controller 600 may further comprise a communications (comm.) interface 620 at least configured for communications with other entities, functions, nodes, and devices, as in Fig. 1. As such the communications interface 620 may comprise one or more transmitters and receivers, comprising analogue and digital components. The processing circuitry 610 controls the general operation of the controller 600 e.g. by sending data and control signals to the communications interface 620 and the storage medium 630, by receiving data and reports from the communications interface 620, and by retrieving data and instructions from the storage medium 630. Other components, as well as the related functionality, of the controller 600 are omitted in order not to obscure the concepts presented herein.

[0081] Fig. 7 schematically illustrates, in terms of a number of functional modules, the components of a controller 700 according to an embodiment. The controller 700 of Fig. 7 comprises a number of functional modules; an obtain module 710 configured to perform step S102, an obtain module 720 configured to perform step S104-2, a compute module 740 configured to perform step S104-4, and a predict module 750 configured to perform step S104-6. The controller 700 of Fig. 7 may further comprise a number of optional functional modules, such as any of an obtain module 730 configured to perform step SiO4-2a, and a share module 760 configured to perform step S104-8.

[0082] In general terms, each functional module 710:760 may in one embodiment be implemented only in hardware and in another embodiment with the help of software, i.e., the latter embodiment having computer program instructions stored on the storage medium 630 which when run on the processing circuitiy 610 makes the controller 600 perform the corresponding steps mentioned above in conjunction with Fig 7. It should also be mentioned that even though the modules correspond to parts of a computer program, they do not need to be separate modules therein, but the way in which they are implemented in software is dependent on the programming language used. Preferably, one or more or all functional modules 710:760 maybe implemented by the processing circuitry 610, possibly in cooperation with the communications interface 620 and / or the storage medium 630. The processing circuitiy 610 may thus be configured to from the storage medium 630 fetch instructions as provided by a functional module 7io:76oand to execute these instructions, thereby performing any steps as disclosed herein.

[0083] The controller 160, 210, 600, 700 maybe provided as a standalone device or as a part of at least one further device. For example, the controller 160, 210, 600, 700 may be provided in a node of the radio access network or in a node of the core network. Alternatively, functionality of the controller 160, 210, 600, 700 maybe distributed between at least two devices, or nodes. These at least two nodes, or devices, may either be part of the same network part (such as the radio access network or the core network) or may be spread between at least two such network parts. In general terms, instructions that are required to be performed in real time may be performed in a device, or node, operatively closer to the cell than instructions that are not required to be performed in real time. Thus, a first portion of the instructions performed by the controller 160, 210, 600, 700 maybe executed in a first device, and a second portion of the of the instructions performed by the controller 160, 210, 600, 700 may be executed in a second device; the herein disclosed embodiments are not limited to any particular number of devices on which the instructions performed by the controller 160, 210, 600, 700 maybe executed. Hence, the methods according to the herein disclosed embodiments are suitable to be performed by a controller 160, 210, 600, 700 residing in a cloud computational environment. Therefore, although a single processing circuitry 610 is illustrated in Fig. 6 the processing circuitry 610 may be distributed among a plurality of devices, or nodes. The same applies to the functional modules 710:760 of Fig. 7 and the computer program 820 of Fig. 8.

[0084] Fig. 8 shows one example of a computer program product 810 comprising computer readable storage medium 830. On this computer readable storage medium 830, a computer program 820 can be stored, which computer program 820 can cause the processing circuitry 610 and thereto operatively coupled entities and devices, such as the communications interface 620 and the storage medium 630, to execute methods according to embodiments described herein. The computer program 820 and / or computer program product 810 may thus provide means for performing any steps as herein disclosed.

[0085] In the example of Fig. 8, the computer program product 810 is illustrated as an optical disc, such as a CD (compact disc) or a DVD (digital versatile disc) or a Blu-Ray disc. The computer program product 810 could also be embodied as a memory, such as a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM) and more particularly as a non-volatile storage medium of a device in an external memory such as a USB (Universal Serial Bus) memory or a Flash memory, such as a compact Flash memory. Thus, while the computer program 820 is here schematically shown as a track on the depicted optical disk, the computer program 820 can be stored in any way which is suitable for the computer program product 810.

[0086] The inventive concept has mainly been described above with reference to a few embodiments. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope of the inventive concept, as defined by the appended patent claims.

Claims

CLAIMS1. A method for predicting safety level of a user (170) after occurrence of a disaster, wherein the method is performed by a controller (160, 210, 600, 700), and wherein the method comprises: obtaining (S102) an indication of a disaster in an area where the user (170) is located, and in response thereto: obtaining (S104-2) a current instance of a digital twin of the user (170) from information received over a wireless network (110) from a user equipment (130) associated with the user (170); computing (S104-4) an anomaly score for the user (170) by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user (170) obtained prior to the indication of the disaster; and predicting (S104-6) the safety level of the user (170) after the disaster has occurred based on the anomaly score for the user (170).

2. The method according to claim 1, wherein the information comprises sensor data of the user (170) as obtained by the user equipment (130) after occurrence of the disaster, and wherein the method further comprises: obtaining (SiO4-2a) the current instance of the digital twin of the user (170) by generating the current instance of the digital twin of the user (170) based on the obtained sensor data.

3. The method according to claim 1, wherein the information comprises the current instance of the digital twin of the user (170) as obtained by the user equipment (130) after occurrence of the disaster.

4. The method according to any preceding claim, wherein comparing the current instance of the digital twin to the at least one previous instance of the digital twin comprises performing a statistical comparison between the current instance of the digital twin and the at least one previous instance of the digital twin.

5. The method according to claim 4, wherein performing the statistical comparison comprises assessing whether the current instance of the digital twin and the at least one previous instance of the digital twin follow a common probability distribution or not.

6. The method according to any of claims 1 to 3, wherein comparing the current instance of the digital twin to the at least one previous instance of the digital twin comprises performing multi-variate time-series analysis on the current instance of the digital twin and the at least one previous instance of the digital twin.

7. The method according to claim 6, wherein performing the multi-variate timeseries analysis comprises comparing the current instance of the digital twin to a prediction of the current instance of the digital twin, wherein the prediction is determined based on the at least one previous instance of the digital twin.

8. The method according to any preceding claim, wherein the anomaly score is represented as a probability value.

9. The method according to any preceding claim, wherein the method further comprises: sharing (S104-8) the safety level of the user (170) with a rescue management system.

10. The method according to any preceding claim, wherein the controller (160, 210, 600, 700) has access to a set of at least one previous instances of the digital twin, where each at least one previous instance of the digital twin is defined by sensor data of the user (170) obtained for a respective time instant, and wherein the current instance of the digital twin at least is compared to the most recent of the at least one previous instances of the digital twin.

11. The method according to any preceding claim, wherein the sensor data comprises any, or any combination, of: physical activity of the user (170), pulse of the user (170), blood oxygen level of the user (170).

12. The method according to any preceding claim, wherein the information received from the user equipment (130) further comprises any, or any combination, of:location information of the user equipment (130), a timestamp for the point in time when the information was collected at the user equipment (130), current weather information for the location of the user equipment (130).

13. A controller (160, 210, 600, 700) for predicting safety level of a user (170) after occurrence of a disaster, the controller (160, 210, 600, 700) comprising processing circuitry (610), the processing circuitry being configured to cause the controller (160, 210, 600, 700) to: obtain an indication of a disaster in an area where the user (170) is located, and in response thereto: obtain a current instance of a digital twin of the user (170) from information received over a wireless network (110) from a user equipment (130) associated with the user (170); compute an anomaly score for the user (170) by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user (170) obtained prior to the indication of the disaster; and predict the safety level of the user (170) after the disaster has occurred based on the anomaly score for the user (170).

14. A controller (160, 210, 600, 700) for predicting safety level of a user (170) after occurrence of a disaster, the controller (160, 210, 600, 700) comprising: an obtain module (710) configured to obtain an indication of a disaster in an area where the user (170) is located; an obtain module (720) configured to, in response thereto, obtain a current instance of a digital twin of the user (170) from information received over a wireless network (110) from a user equipment (130) associated with the user (170); a compute module (740) configured to compute an anomaly score for the user (170) by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user (170) obtained prior to the indication of the disaster; anda predict module (750) configured to predict the safety level of the user (170) after the disaster has occurred based on the anomaly score for the user (170).

15. The controller (160, 210, 600, 700) according to claim 13 or 14, further being configured to perform the method according to any of claims 2 to 12.

16. A computer program (820) for predicting safety level of a user (170) after occurrence of a disaster, the computer program comprising computer code which, when run on processing circuitry (610) of a controller (160, 210, 600, 700), causes the controller (160, 210, 600, 700) to: obtain (S102) an indication of a disaster in an area where the user (170) is located, and in response thereto: obtain (S104-2) a current instance of a digital twin of the user (170) from information received over a wireless network (110) from a user equipment (130) associated with the user (170); compute (S104-4) an anomaly score for the user (170) by comparing the current instance of the digital twin to at least one previous instance of the digital twin as defined by sensor data of the user (170) obtained prior to the indication of the disaster; and predict (S104-6) the safety level of the user (170) after the disaster has occurred based on the anomaly score for the user (170).

17. A computer program product (810) comprising a computer program (820) according to claim 16, and a computer readable storage medium (830) on which the computer program is stored.

Citation Information

Patent Citations

  • Providing predictive alerts for workplace safety

    EP3276554A1

  • Method and system for semi-supervised deep anomaly detection for large-scale industrial monitoring systems based on time-series data utilizing digital twin simulation data

    US20210110262A1