Method, device and medium for searching for missing person

Abstract

The disclosure provides a missing person search and rescue method, device, equipment and medium, relating to the technical field of emergency search and rescue. The method comprises: in a network environment, acquiring offline geographic environment data and historical motion trajectory of a missing person; constructing an environment space model according to the offline geographic environment data, and filtering the space units involved in the environment space model to generate a set of actionable space; wherein the set of actionable space includes a plurality of space units that the missing person can theoretically reach; generating a hot area of the missing person according to the historical motion trajectory and the set of actionable space; generating search and rescue information according to the hot area; wherein the search and rescue information is used to guide search and rescue personnel to search for the missing person.

Description

Technical Field

[0001] This disclosure relates to the field of emergency search and rescue technology, and more specifically, to a method, apparatus, equipment, and medium for searching and rescuing missing persons. Background Technology

[0002] With the continuous development of emergency search and rescue, edge computing and artificial intelligence technologies, the search and rescue of missing persons in complex scenarios such as mountainous areas, underground spaces, mines, earthquake-stricken areas, forests, and inside fire-damaged buildings has become an important application area in the field of public safety.

[0003] The aforementioned scenarios commonly involve the absence of public internet access, cloud services, GNSS signal interruptions, and unavailable online maps, leaving search and rescue equipment reliant on local modules for data collection and processing. However, traditional search and rescue methods heavily depend on satellite positioning, cellular networks, and cloud services, limiting the search area to a fixed range based solely on the last known location of the missing person. This makes them ill-equipped to effectively address issues like missing tracks and failed location predictions in complex offline environments, and also hinders the differentiation of search priorities, resulting in poor overall search and rescue accuracy and operational efficiency. Summary of the Invention

[0004] One objective of this disclosure is to provide a new technical solution for the search and rescue of missing persons.

[0005] According to a first aspect of the present disclosure, a method for searching and rescuing missing persons is provided, the method comprising: In a network-free environment, acquire offline geographic environment data and historical movement trajectories of missing persons; An environmental spatial model is constructed based on the offline geographic environment data, and the spatial units involved in the environmental spatial model are filtered to generate a set of movable spaces; wherein, the set of movable spaces includes multiple spatial units that are theoretically accessible to the missing person; Based on the historical movement trajectory and the set of possible movement spaces, hotspot areas for the missing persons are generated; Search and rescue information is generated based on the hotspot areas; wherein, the search and rescue information is used to guide search and rescue personnel to search for the missing persons.

[0006] Optionally, in a network-free environment, the historical movement trajectory of the missing person can be obtained, including: In a network-free environment, acquire heterogeneous sensing data collected by the missing person's missing terminal: wherein the heterogeneous sensing data includes at least two of the following: motion data, environmental data, and spatial state data; The heterogeneous sensing data is fused to obtain the historical motion trajectory.

[0007] Optionally, an environmental spatial model is constructed based on the offline geographic environment data, including: The environmental spatial model is constructed based on the terrain elevation model, obstacle distribution model, and risk area model in the offline geographic environment data; The environmental space model involves multiple spatial units, each of which has environmental attributes.

[0008] Optionally, the spatial units involved in the environmental spatial model are filtered to generate a set of actionable spaces, including: For each of the spatial units, if the environmental attributes satisfy the corresponding elimination conditions, the spatial unit is marked as unreachable; if the environmental attributes do not satisfy the corresponding elimination conditions, the spatial unit is marked as theoretically reachable. The set of movable spaces is generated based on all the spatial units marked as theoretically reachable.

[0009] Optionally, generating the hotspot area for the missing person based on the historical movement trajectory and the set of movable spaces includes: The behavioral inertial characteristic parameters of the missing persons are extracted based on the historical movement trajectory. Based on the behavioral inertia characteristic parameters and the environmental attributes of each spatial unit in the set of actionable spaces, a comprehensive score is obtained for each spatial unit. Based on the comprehensive score corresponding to each of the spatial units, a spatial probability distribution of the missing persons is generated. The hotspot region is generated based on the spatial probability distribution.

[0010] Optionally, generating the hotspot region based on the spatial probability distribution includes: The spatial units in the spatial probability distribution are classified according to their probability values. Spatial units with probability values ​​greater than a first threshold are identified as high-probability spatial units, spatial units with probability values ​​less than or equal to the first threshold but greater than a second threshold are identified as medium-probability spatial units, and spatial units with probability values ​​less than or equal to the second threshold are identified as low-probability spatial units. Clustering is performed on the high-probability spatial units, the medium-probability spatial units, and the low-probability spatial units respectively, and adjacent spatial units of the same level are merged into the same region, thereby generating high-probability regions, medium-probability regions, and low-probability regions respectively. The hotspot region is generated based on the high-probability region, the medium-probability region, and the low-probability region.

[0011] Optionally, the search and rescue information includes search and rescue routes. The step of generating search and rescue information based on the hotspot areas includes: Prioritize high-probability, medium-probability, and low-probability regions within the hotspot area; Based on the offline geographic environment data, determine the passage cost of each spatial unit in the set of movable spaces; Based on the priorities of the high-probability, medium-probability, and low-probability areas and the travel cost, the optimal search and rescue route passing through the high-probability, medium-probability, and low-probability areas is planned.

[0012] According to a second aspect of the present disclosure, a device for searching and rescuing missing persons is provided, the device comprising: The first generation module is used to construct an environmental spatial model based on the offline geographic environment data, and to filter the spatial units involved in the environmental spatial model to generate a set of movable spaces; wherein, the set of movable spaces includes multiple spatial units that are theoretically accessible to the missing person; The second generation module is used to generate hotspot areas for the missing persons based on the historical movement trajectory and the set of movable spaces. The third generation module is used to generate search and rescue information based on the hotspot area; wherein the search and rescue information is used to guide search and rescue personnel to search for the missing persons.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a memory for storing executable computer instructions; and a processor for executing the method described in accordance with the first aspect above, under the control of the executable computer instructions.

[0014] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, the computer program implementing the method according to the first aspect above when executed by a processor.

[0015] One beneficial effect of this disclosure is that by acquiring offline geographic environment data in a network-free environment and the historical movement trajectory of missing persons, an environmental spatial model is first constructed based on the offline geographic environment data, and spatial units are filtered to generate a set of theoretically accessible actionable spaces for the missing persons. Then, the historical movement trajectory and the set of actionable spaces are integrated to extrapolate the potential location areas of the missing persons, generating hotspot areas for the missing persons, and generating search and rescue information for search and rescue guidance based on these hotspot areas. In this way, by introducing an offline environment autonomous reconstruction and spatial filtering mechanism, based on the actual movement behavior patterns of missing persons and the characteristics of the actual geographic environment, inaccessible areas can be eliminated in advance to narrow the prediction range. This effectively adapts to complex and extreme search and rescue scenarios without public networks, cloud services, and GNSS signal failure, significantly improving the accuracy of missing persons location prediction and the overall efficiency of search and rescue operations.

[0016] Other features and advantages of this specification will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of this specification and, together with their description, serve to explain the principles of this specification.

[0018] Figure 1 This is a schematic diagram of the structure of a missing persons search and rescue system that can be applied to the missing persons search and rescue method of the present disclosure embodiments; Figure 2 This is a flowchart illustrating a method for searching and rescuing missing persons according to some embodiments of this disclosure; Figure 3 This is a schematic diagram of the structure of a search and rescue device for missing persons according to some embodiments of this disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure; Figure label: 1-Missing Person Search and Rescue System; 11-Missing Terminal; 12-Collaborative Terminal; 300-Missing Person Search and Rescue Device; 310-Acquisition Module; 320-First Generation Module; 330-Second Generation Module; 340-Third Generation Module; 400-Electronic Device; 410-Processor; 420-Memory. Detailed Implementation

[0019] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0020] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0021] Technologies and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such technologies and equipment should be considered part of the specification.

[0022] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0024] This disclosure relates to a method for searching and rescuing missing persons. Figure 1 This is a schematic diagram of the structure of a missing persons search and rescue system that can be applied to the missing persons search and rescue method of this disclosure. For example... Figure 1 As shown, the missing persons search and rescue system 1 includes a missing terminal 11 and a collaborative terminal 12.

[0025] In this embodiment, the missing terminal 11 is carried by the missing person and includes a processing module, a data acquisition module, a data storage module, a communication module, and a display module.

[0026] The data acquisition module integrates multiple types of sensors, including an inertial measurement unit (IMU), a global navigation satellite system (GNSS) module, a barometer, a temperature sensor, and an ultra-wideband (UWB) ranging module, to collect heterogeneous sensing data of missing persons. This heterogeneous sensing data includes at least one of motion data, environmental data, and spatial state data.

[0027] The data storage module includes an offline map storage module and a trajectory cache module; the offline map storage module pre-stores offline geographic environment data, and the trajectory cache module is used to save heterogeneous sensing data collected by the data acquisition module.

[0028] The communication module adopts a low-power long-range mesh self-organizing network (LoRa Mesh) module, which can build a temporary self-organizing network at the front end in an offline environment without public network and cloud service interruption, so as to realize offline data interaction and real-time data synchronization between the disconnected terminal 11 and the collaborative terminal 12, and ensure data collaborative transmission in complex scenarios.

[0029] The collaborative terminal 12 is also equipped with a processing module, a data acquisition module, a data storage module, a communication module, and a display module. The collaborative terminal 12 can be operated by search and rescue personnel to combine locally stored offline geographic environment data and heterogeneous sensing data reported by the missing terminal 11 to generate hotspot areas for missing persons; the collaborative terminal 12 can also be held by other missing persons to correct positional deviations through multi-terminal data comparison and assist in the collaborative calibration of hotspot areas.

[0030] Furthermore, the missing persons search and rescue system can also include a search and rescue command platform. In this scenario, the search and rescue command platform can combine offline geographic environment data and heterogeneous sensing data collected by the missing terminal to generate hotspot areas for the missing persons, and generate search and rescue information to be sent to collaborative terminals.

[0031] In related technologies, a fixed search area can typically only be defined based on the last valid location of a missing person, failing to incorporate the missing person's movement patterns and terrain constraints to infer their potential location distribution. To address these issues, this disclosure provides a method for searching and rescuing missing persons. In offline environments without public network connectivity and with limited satellite navigation signals, it utilizes local offline geographic data and the missing person's historical movement trajectory. By filtering spatial units in an environmental spatial model to generate a set of movable spaces, it then infers the potential location area of ​​the missing person based on the historical movement trajectory and the set of movable spaces, generating hotspot areas. Search and rescue information is then generated based on these hotspot areas, thereby achieving intelligent prediction of the missing person's location.

[0032] The following combination Figure 1 The system / application scenarios described herein illustrate various embodiments of this disclosure.

[0033] <Method Implementation> Figure 2 This is a flowchart illustrating some embodiments of the search and rescue method for missing persons disclosed herein. The search and rescue method for missing persons in this embodiment can be executed independently by a collaborative terminal, or it can be executed in conjunction with the collaborative terminal and the missing terminal. When the system includes a search and rescue command platform, it can also be executed independently by the search and rescue command platform, or in conjunction with the search and rescue command platform, the collaborative terminal, and the missing terminal. For example... Figure 2 As shown, the search and rescue method for missing persons in this embodiment may include the following steps S210 to S240: Step S210: In a network-free environment, acquire offline geographic environment data and the historical movement trajectory of the missing person.

[0034] The offline geographic environment data includes terrain elevation models, obstacle distribution models, and risk area models. The terrain elevation model describes the terrain features such as slope and elevation of the region; the obstacle distribution model describes the types and distribution of obstacles in each region; and the risk area model identifies high-risk locations that need to be avoided, such as cliffs, water bodies, and danger zones.

[0035] In some examples, obtaining the historical movement trajectory of a missing person in a network-free environment can be achieved in the following way: In a network-free environment, heterogeneous sensing data collected by the missing person's missing terminal is obtained, and the heterogeneous sensing data is fused to obtain the historical movement trajectory.

[0036] The heterogeneous sensing data includes at least two types: motion data, environmental data, and spatial state data. Motion data, acquired by the inertial measurement unit (IMU), may include acceleration and angular velocity data, used to record the motion state and attitude changes of the missing person. Environmental data may include ambient temperature collected by a temperature sensor and air pressure values ​​collected by a barometer, used to determine the survival conditions and altitude changes of the missing person's environment. Spatial state data, acquired by the GNSS module, outputs absolute position coordinates when satellite signals are available, and calculates relative position coordinates through dead reckoning using the IMU when satellite signals are limited.

[0037] In this example, the lost terminal sends the heterogeneous sensing data stored in the trajectory cache module to the collaborative terminal used by the search and rescue personnel. This collaborative terminal first performs time synchronization processing on the heterogeneous sensing data. Then, it performs noise filtering on the time-synchronized heterogeneous sensing data, and then performs trajectory interpolation and completion processing on the noise-filtered heterogeneous sensing data. Finally, it reconstructs the motion path from the interpolated heterogeneous sensing data, forming a continuous historical motion trajectory sequence.

[0038] Step S220: Construct an environmental spatial model based on offline geographic environmental data, and filter the spatial units involved in the environmental spatial model to generate a set of actionable spaces.

[0039] The movable space set includes multiple spatial units that are theoretically accessible to the missing persons.

[0040] In some examples, constructing an environmental spatial model based on offline geographic environmental data can be achieved in the following ways: constructing an environmental spatial model based on the terrain elevation model, obstacle distribution model, and risk area model in the offline geographic environmental data.

[0041] The environmental space model involves multiple spatial units, each with environmental attributes.

[0042] In this example, an environmental spatial model can be constructed based on the terrain elevation model, obstacle distribution model, and risk area model in the offline geographic environment data. The environmental spatial model is then rasterized at a preset resolution to obtain multiple uniform raster cells, each of which is a spatial unit. Each spatial unit has environmental attributes, including terrain attributes (such as elevation and slope values), obstacle attributes (obstacle types), and risk attributes (risk levels).

[0043] In some examples, filtering spatial units involved in the environmental spatial model to generate a set of actionable spaces can be implemented as follows: for each spatial unit, if the environmental attributes meet the corresponding elimination conditions, the spatial unit is marked as unreachable, and if the environmental attributes do not meet the corresponding elimination conditions, the spatial unit is marked as theoretically reachable; based on all spatial units marked as theoretically reachable, a set of actionable spaces is generated.

[0044] In this example, for each spatial unit, it is determined whether the environmental attributes meet the corresponding elimination criteria. Elimination criteria include at least one of the following: slope value exceeding a slope threshold, elevation value with the elevation difference between the unit and adjacent spatial units exceeding an elevation change threshold, obstacle type being impassable (such as a built-up area, water area, or steep cliff area), or risk level exceeding a risk threshold. If any one of the environmental attributes meets the elimination criteria, the spatial unit is marked as inaccessible; if none of the environmental attributes meet all elimination criteria, the spatial unit is marked as theoretically accessible. After traversing all spatial units, a set of movable spaces is generated based on all spatial units marked as theoretically accessible.

[0045] Step S230: Based on the historical movement trajectory and the set of movable spaces, generate hotspot areas for missing persons.

[0046] In this embodiment, the potential location areas of missing persons can be deduced based on historical movement trajectories and the set of possible movement spaces to obtain hotspot areas for the missing persons. These hotspot areas may include multiple areas with different probability levels, such as high-probability areas, medium-probability areas, and low-probability areas. Areas with different probability levels are used to indicate different search priorities to guide search and rescue personnel to prioritize searching high-probability areas.

[0047] In some examples, step S230, which generates hotspot areas for missing persons based on historical movement trajectories and the set of possible movement spaces, may further include the following steps S231 to S234: Step S231: Extract the behavioral inertial characteristic parameters of the missing persons based on their historical movement trajectories.

[0048] In step S231, behavioral inertial characteristic parameters of the missing persons can be extracted from their historical motion trajectories. These behavioral inertial characteristic parameters include at least one of the following: directional inertial parameters, velocity decay parameters, survival drive parameters, and group behavior parameters.

[0049] Among them, the directional inertia parameter characterizes the strength of the tendency of missing persons to maintain their original direction of movement. The velocity decay parameter characterizes the trend of the movement speed of missing persons gradually decreasing as the duration of disappearance increases. The survival drive parameter characterizes the strength of the tendency of missing persons to move towards water sources, safe havens, or other locations with favorable survival conditions. The group behavior parameter characterizes the tendency of multiple missing persons to converge or cluster together.

[0050] Step S232: Based on the behavioral inertia characteristic parameters and the environmental attributes of each spatial unit in the actionable space set, obtain the comprehensive score of each spatial unit.

[0051] In step S232, for each spatial unit in the set of movable spaces, scores can be given from four dimensions: trajectory inertia consistency, terrain accessibility, survival drive, and group consistency. The scores are then weighted and summed according to preset weights to obtain the comprehensive score of the spatial unit.

[0052] The trajectory inertia consistency score can be calculated based on the directional inertia parameter. It is used to quantify the possibility that the missing person will continue to move to the spatial unit along the historical motion direction. The smaller the deviation between the direction of the spatial unit and the historical motion direction, the higher the score.

[0053] The terrain accessibility score is calculated based on the speed decay parameter and the terrain attributes (slope value, elevation value) and obstacle attributes (obstacle type) of the spatial unit. It is used to quantify the difficulty for a missing person to reach the spatial unit under the current mobility. The smaller the slope and the fewer the obstacles, the higher the score.

[0054] The survival drive score can be calculated based on the survival drive parameters and the risk attributes (risk level) of the space unit. It is used to quantify the survival attractiveness of the space unit to missing persons. The lower the risk level and the more water or shelter resources the space unit contains, the higher the score.

[0055] Among them, the group consistency score can be calculated based on group behavior parameters. It is used to quantify the spatial proximity of the spatial unit to the current location of other missing persons. In the case of multiple missing persons, the closer the spatial unit is to other missing persons and the more similar their directions are, the higher the score.

[0056] The scores of the above four dimensions are weighted and summed according to preset weights to obtain the comprehensive score of the spatial unit. The higher the comprehensive score, the greater the possibility that the missing person is in the spatial unit.

[0057] Step S233: Generate the spatial probability distribution of missing persons based on the comprehensive score corresponding to each spatial unit.

[0058] In step S233, the comprehensive score of all spatial units in the actionable space set can be normalized, converting the comprehensive score of each spatial unit into a corresponding probability value. The higher the probability value, the greater the likelihood that the missing person is in that spatial unit. The probability values ​​of all spatial units together constitute the spatial probability distribution of the missing person in the actionable space set.

[0059] Step S234: Generate hotspot regions based on spatial probability distribution.

[0060] This step S234, generating hotspot regions based on spatial probability distribution, can be implemented as follows: Spatial units in the spatial probability distribution are classified according to their probability values. Spatial units with probability values ​​greater than a first threshold are identified as high-probability spatial units; spatial units with probability values ​​less than or equal to the first threshold but greater than a second threshold are identified as medium-probability spatial units; and spatial units with probability values ​​less than or equal to the second threshold are identified as low-probability spatial units. High-probability, medium-probability, and low-probability spatial units are clustered separately, merging adjacent spatial units of the same level into the same region, thus generating high-probability, medium-probability, and low-probability regions. Hotspot regions are then generated based on these high-probability, medium-probability, and low-probability regions.

[0061] The first and second thresholds can be determined based on search and rescue resources and search and rescue timeliness requirements.

[0062] In this hotspot area, high-probability, medium-probability, and low-probability areas are each represented by different color codes. For example, a hotspot area is composed of these three types of areas, visualized as a heatmap. High-probability areas correspond to a first color code (e.g., red), medium-probability areas to a second color code (e.g., yellow), and low-probability areas to a third color code (e.g., green), allowing search and rescue personnel to easily distinguish search priorities. The high, medium, and low probability areas correspond to search priorities from highest to lowest; search and rescue personnel prioritize high-probability areas, then proceed with searching medium-probability and low-probability areas.

[0063] Through steps S231 to S234 above, hotspot areas for missing persons can be generated based on historical movement trajectories and the set of possible movement spaces. This method integrates behavioral patterns and environmental characteristics to generate probability regions with different search priorities.

[0064] Step S240: Generate search and rescue information based on hotspot areas.

[0065] Among them, search and rescue information is used to guide search and rescue personnel in searching for missing persons. Search and rescue information includes at least one of the following: hotspot areas and search and rescue routes.

[0066] In some examples, search and rescue information includes search and rescue routes. First, the priorities of high-probability, medium-probability, and low-probability areas within a hotspot are identified. Then, based on offline geographic data, the traversal cost of each spatial unit in the actionable space set is determined. Finally, based on the priorities and traversal costs of the high-probability, medium-probability, and low-probability areas, the optimal search and rescue route is planned, passing through these areas. By comprehensively considering the priority of hotspot areas and terrain traversal costs, optimal planning of search and rescue routes is achieved, improving search and rescue coverage efficiency while ensuring the safety of search and rescue personnel.

[0067] In some examples, search and rescue information includes hotspot areas. In this example, hotspot areas in the form of a heat map can be displayed on the display module of the collaborative terminal used by search and rescue personnel, allowing them to intuitively understand the spatial distribution of the potential locations of missing persons.

[0068] In some examples, after the search and rescue information is generated, it can also be synchronized to the search and rescue command platform and / or collaborative terminals through the communication module to achieve multi-terminal collaborative search and rescue.

[0069] This embodiment of the invention acquires offline geographic environment data in a network-free environment and the historical movement trajectory of missing persons. First, an environmental spatial model is constructed based on the offline geographic environment data, and spatial units are filtered to generate a theoretically accessible set of movable spaces for the missing persons. Then, the historical movement trajectory and the set of movable spaces are integrated to extrapolate the potential location areas of the missing persons, generating hotspot areas. Based on these hotspot areas, search and rescue information for guidance is generated. In this way, by introducing an offline environment autonomous reconstruction and spatial filtering mechanism, and based on the actual movement behavior patterns of missing persons and the characteristics of the offline geographic environment, inaccessible areas are pre-emptively eliminated to narrow the prediction range. This effectively adapts to complex and extreme search and rescue scenarios without public networks, cloud services, or GNSS signal failure, significantly improving the accuracy of missing persons location prediction and the overall efficiency of search and rescue operations.

[0070] In some embodiments, after performing the above step S240 to generate search and rescue information based on hotspot areas, the search and rescue method for missing persons in this embodiment may further include: updating historical movement trajectories based on positioning data fed back by the collaborative terminal.

[0071] Specifically, upon receiving location data from the collaborative terminal, the system can correct historical movement trajectories based on the location data; re-extract the behavioral inertial characteristic parameters of the missing person based on the corrected historical movement trajectory; regenerate an updated spatial probability distribution and updated hotspot areas based on the updated behavioral inertial characteristic parameters and the set of possible movement spaces; and update search and rescue information based on the updated hotspot areas. This achieves a closed-loop optimization of prediction → search and rescue → feedback → correction → re-prediction, avoiding the problem of being unable to dynamically adjust based on actual search and rescue progress after a single prediction. Location data may include ranging data measured by a UWB ranging module.

[0072] <Device Embodiment> Figure 3 This is a schematic diagram of the structure of a search and rescue device for missing persons according to some embodiments of this disclosure. For example... Figure 3 As shown, the missing persons search and rescue device 300 may include an acquisition module 310, a first generation module 320, a second generation module 330 and a third generation module 340.

[0073] The acquisition module 310 is used to acquire offline geographic environment data and the historical movement trajectory of missing persons in a network-free environment. The first generation module 320 is used to construct an environmental spatial model based on the offline geographic environment data, and to filter the spatial units involved in the environmental spatial model to generate a set of movable spaces; wherein, the set of movable spaces includes multiple spatial units that are theoretically accessible to the missing person; The second generation module 330 is used to generate hotspot areas for the missing persons based on the historical movement trajectory and the set of movable spaces. The third generation module 340 is used to generate search and rescue information based on the hotspot area; wherein the search and rescue information is used to guide search and rescue personnel to search for the missing persons.

[0074] In one embodiment, the acquisition module 310 is used to acquire heterogeneous sensing data collected by the missing person's terminal in a network-free environment: wherein the heterogeneous sensing data includes at least two types: motion data, environmental data, and spatial state data; and to perform fusion processing on the heterogeneous sensing data to obtain the historical motion trajectory.

[0075] In one embodiment, the first generation module 320 is used to construct the environmental spatial model based on the terrain elevation model, obstacle distribution model, and risk area model in the offline geographic environment data; wherein the environmental spatial model involves multiple spatial units, and each spatial unit has environmental attributes.

[0076] In one embodiment, the first generation module 320 is configured to, for each of the spatial units, mark the spatial unit as unreachable if the environmental attribute satisfies the corresponding elimination condition, and mark the spatial unit as theoretically reachable if the environmental attribute does not satisfy the corresponding elimination condition; and generate the set of movable spaces based on all the spatial units marked as theoretically reachable.

[0077] In one embodiment, the second generation module 330 is configured to extract the behavioral inertial feature parameters of the missing person based on the historical movement trajectory; obtain a comprehensive score for each spatial unit based on the behavioral inertial feature parameters and the environmental attributes of each spatial unit in the set of movable spaces; generate a spatial probability distribution of the missing person based on the comprehensive score corresponding to each spatial unit; and generate the hotspot area based on the spatial probability distribution.

[0078] In one embodiment, the second generation module 330 is used to classify the spatial units in the spatial probability distribution according to their probability values, identifying spatial units with probability values ​​greater than a first threshold as high-probability spatial units, spatial units with probability values ​​less than or equal to the first threshold but greater than a second threshold as medium-probability spatial units, and spatial units with probability values ​​less than or equal to the second threshold as low-probability spatial units; clustering the high-probability spatial units, medium-probability spatial units, and low-probability spatial units respectively, merging adjacent spatial units of the same level into the same region, and generating corresponding high-probability regions, medium-probability regions, and low-probability regions; and generating the hotspot region based on the high-probability regions, medium-probability regions, and low-probability regions.

[0079] In some embodiments, the search and rescue information includes a search and rescue path. A third generation module 340 is used to obtain the priorities of high-probability areas, medium-probability areas, and low-probability areas in the hotspot area; determine the passage cost of each spatial unit in the set of movable spaces based on the offline geographic environment data; and plan the optimal search and rescue path passing through the high-probability areas, medium-probability areas, and low-probability areas based on the priorities of the high-probability areas, medium-probability areas, and low-probability areas and the passage cost.

[0080] <Equipment Example> Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. (Refer to...) Figure 4 The electronic device 400 includes a processor 410 and a memory 420.

[0081] The memory 420 can be used to store executable computer instructions.

[0082] The processor 410 can be used to execute a search and rescue method for missing persons according to an embodiment of the method disclosed herein, under the control of executable computer instructions.

[0083] The electronic device 400 can be as follows: Figure 1 The disconnected device shown can also be a cooperating device; no limitation is made here.

[0084] In another embodiment, the electronic device 400 may include the above-mentioned missing persons search and rescue device 300.

[0085] In one embodiment, each module of the above-mentioned missing persons search and rescue device 300 can be implemented by the processor 410 running computer instructions stored in the memory 420.

[0086] Computer-readable storage media This disclosure also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, perform the search and rescue method for missing persons provided in this disclosure.

[0087] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0088] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0089] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0090] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0091] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0092] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0093] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a portion of an apparatus, segment, or instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It will be known to those skilled in the art that implementation in hardware, implementation in software, and implementation in a combination of software and hardware are equivalent.

[0095] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for searching and rescuing missing persons, characterized in that, The method includes: In a network-free environment, offline geographic environment data and the historical movement trajectory of the missing person are acquired; wherein, in a network-free environment, acquiring the historical movement trajectory of the missing person includes: in a network-free environment, acquiring heterogeneous sensing data collected by the missing person's terminal; wherein, the heterogeneous sensing data includes at least two of the following: motion data, environmental data, and spatial state data; and fusing the heterogeneous sensing data to obtain the historical movement trajectory; An environmental spatial model is constructed based on the offline geographic environment data, and the spatial units involved in the environmental spatial model are filtered to generate a set of movable spaces; wherein, the set of movable spaces includes multiple spatial units that are theoretically accessible to the missing person; Based on the historical movement trajectory and the set of movable spaces, hotspot areas for the missing persons are generated; wherein, generating hotspot areas for the missing persons based on the historical movement trajectory and the set of movable spaces includes: extracting behavioral inertial feature parameters of the missing persons based on the historical movement trajectory; obtaining a comprehensive score for each spatial unit based on the behavioral inertial feature parameters and the environmental attributes of each spatial unit in the set of movable spaces; generating a spatial probability distribution of the missing persons based on the comprehensive scores corresponding to each spatial unit; and generating the hotspot areas based on the spatial probability distribution. Search and rescue information is generated based on the hotspot areas; wherein, the search and rescue information is used to guide search and rescue personnel to search for the missing persons.

2. The method according to claim 1, characterized in that, Constructing an environmental spatial model based on the offline geographic environment data includes: The environmental spatial model is constructed based on the terrain elevation model, obstacle distribution model, and risk area model in the offline geographic environment data; The environmental space model involves multiple spatial units, each of which has environmental attributes.

3. The method according to claim 2, characterized in that, The spatial units involved in the environmental spatial model are filtered to generate a set of movable spaces, including: For each of the spatial units, if the environmental attributes satisfy the corresponding elimination conditions, the spatial unit is marked as unreachable; if the environmental attributes do not satisfy the corresponding elimination conditions, the spatial unit is marked as theoretically reachable. The set of movable spaces is generated based on all the spatial units marked as theoretically reachable.

4. The method according to claim 1, characterized in that, The step of generating the hotspot region based on the spatial probability distribution includes: The spatial units in the spatial probability distribution are classified according to their probability values. Spatial units with probability values ​​greater than a first threshold are identified as high-probability spatial units, spatial units with probability values ​​less than or equal to the first threshold but greater than a second threshold are identified as medium-probability spatial units, and spatial units with probability values ​​less than or equal to the second threshold are identified as low-probability spatial units. Clustering is performed on the high-probability spatial units, the medium-probability spatial units, and the low-probability spatial units respectively, and adjacent spatial units of the same level are merged into the same region, thereby generating high-probability regions, medium-probability regions, and low-probability regions respectively. The hotspot region is generated based on the high-probability region, the medium-probability region, and the low-probability region.

5. The method according to claim 4, characterized in that, The search and rescue information includes search and rescue routes. The step of generating search and rescue information based on the hotspot areas includes: Prioritize high-probability, medium-probability, and low-probability regions within the hotspot area; Based on the offline geographic environment data, determine the passage cost of each spatial unit in the set of movable spaces; Based on the priorities of the high-probability, medium-probability, and low-probability areas and the travel cost, the optimal search and rescue route passing through the high-probability, medium-probability, and low-probability areas is planned.

6. A device for searching and rescuing missing persons, characterized in that, The device includes: The acquisition module is used to acquire offline geographic environment data and the historical movement trajectory of missing persons in a network-free environment; specifically, the acquisition module is used to acquire heterogeneous sensing data collected by the missing person's terminal in a network-free environment: wherein the heterogeneous sensing data includes at least two types of data: motion data, environmental data, and spatial state data; and to perform fusion processing on the heterogeneous sensing data to obtain the historical movement trajectory. The first generation module is used to construct an environmental spatial model based on the offline geographic environment data, and to filter the spatial units involved in the environmental spatial model to generate a set of movable spaces; wherein, the set of movable spaces includes multiple spatial units that are theoretically accessible to the missing person; The second generation module is used to generate hotspot areas for the missing persons based on the historical movement trajectory and the set of movable spaces; specifically, the second generation module is used to extract behavioral inertial feature parameters of the missing persons based on the historical movement trajectory; obtain a comprehensive score for each spatial unit based on the behavioral inertial feature parameters and the environmental attributes of each spatial unit in the set of movable spaces; generate a spatial probability distribution of the missing persons based on the comprehensive scores corresponding to each spatial unit; and generate the hotspot areas based on the spatial probability distribution. The third generation module is used to generate search and rescue information based on the hotspot area; wherein the search and rescue information is used to guide search and rescue personnel to search for the missing persons.

7. An electronic device, characterized in that, include: Memory is used to store executable computer instructions; A processor configured to execute the method according to any one of claims 1-5, under the control of the executable computer instructions.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method according to any one of claims 1-5.

Images