An uncertain state coding module, method, device, and medium for situational awareness

Abstract

This application discloses an uncertain state encoding module, method, device, and medium for situational awareness. A feature receiving unit acquires target feature data; a state space definition unit defines a state space containing multiple situation-related states; an uncertain state construction unit calculates the weights of each state in the state space based on the target feature data and / or the target's historical feature information to construct an uncertain state vector representing the coexistence of multiple states; and a state evolution update unit updates the target's current state representation according to the temporal changes of the uncertain state vector. This application can effectively express the ambiguity and multiple possibilities of the target state, describe its gradual evolution process, thereby improving the stability and continuity of the state representation of the situational awareness system and reducing the risk of misjudgment.

Description

Technical Field

[0001] This application relates to the field of intelligent sensing technology, and more specifically, to an uncertain state coding module, method, device, and medium for situational awareness. Background Technology

[0002] In the fields of situational awareness and target analysis, the current state of a target is typically represented by discrete classification labels or single probability values. These methods simplify the target's state to a definite category or an estimate of the probability of belonging to a certain category, providing a basis for subsequent decision-making and analysis.

[0003] However, the aforementioned representations have significant limitations. First, they are ineffective at characterizing the inherent ambiguity of the target state and the complex situations where multiple potential states coexist. Second, these methods cannot clearly reflect the continuous and gradual evolution of the target state over time. Furthermore, in situations with insufficient information or high environmental uncertainty, relying on such representations can easily lead to early misjudgments of the target state or decision-making delays due to waiting for clear information.

[0004] Therefore, existing target state representation techniques often struggle to achieve stable, continuous, and robust representations of target states when dealing with dynamic, uncertain, and complex environments. This limits the analytical effectiveness and decision reliability of related systems at critical moments. Summary of the Invention

[0005] The purpose of this application is to overcome the shortcomings of existing technologies and provide an uncertain state coding module, method, device and medium for situational awareness, which can effectively express the ambiguity and multiple possibilities of the target state and describe its progressive evolution process, thereby improving the stability and continuity of the state representation of the situational awareness system and reducing the risk of misjudgment.

[0006] The objective of this application is achieved through the following technical solution: Firstly, this application proposes an uncertain state coding module for situational awareness, comprising: Feature receiving unit, used to acquire target feature data; A state space definition unit is used to define a state space, which contains multiple situation-related states. Uncertainty state construction unit is used to calculate the state weights of the target in the state space based on the target feature data and / or the target's historical feature information, so as to construct the uncertainty state vector, which represents the coexistence of multiple states; The state evolution update unit is used to update the current state representation of the target based on the changes in the uncertainty state vector over time.

[0007] In one possible implementation, the uncertainty state building unit is used for: The unnormalized weight values ​​are calculated using the state mapping function based on the target feature vector and / or the target's historical feature information. The unnormalized weight values ​​represent the probability of the target being in each state. Normalize the unnormalized weight values ​​to obtain weights that satisfy the normalization constraints, thus forming an uncertain state vector.

[0008] In one possible implementation, the state space includes: non-threat state, abnormal behavior state, potential threat state, and threat state.

[0009] In one possible implementation, the formula for updating the uncertain state vector by the state evolution update unit is: ,in Let be the uncertainty state vector from the previous time step. The state vector is recalculated based on the latest features. This is the smoothing coefficient.

[0010] In one possible implementation, the state evolution update unit is also used to calculate the state entropy, and the formula for calculating the state entropy is: ,in For state entropy, The first uncertain state vector is the first uncertain state vector. The weights of each state.

[0011] In one possible implementation, the target feature data includes the target's spatial location features, the target's motion features, the target's shape or outline features, and the target's relative relationship with the environment or other targets.

[0012] Secondly, this application proposes an uncertain state coding method for situational awareness, the method comprising: Obtain target feature data; Define a state space, which contains multiple situation-related states; Based on target feature data and / or historical feature information of the target, calculate the state weight of the target in the state space to construct an uncertainty state vector, which represents the coexistence of multiple states; The current state representation of the target is updated based on the changes in the uncertainty vector over time.

[0013] In one possible implementation, the step of updating the current state representation of the target includes: Based on the smoothing coefficient, the historical uncertainty state vector is weighted and fused with the state vector recalculated based on the latest features to obtain the updated uncertainty state vector.

[0014] Thirdly, this application also proposes a computer device comprising a processor and a memory, wherein the memory stores a computer program, which is loaded and executed by the processor to implement the uncertain state coding module as described in any of the first aspects.

[0015] Fourthly, this application also proposes a computer-readable storage medium storing a computer program that is loaded and executed by a processor to implement the uncertain state coding module as described in any of the first aspects.

[0016] The main solution and its various further alternatives described above can be freely combined to form multiple solutions, all of which are solutions that can be adopted and are claimed in this application; furthermore, the (non-conflicting alternatives) can also be freely combined with each other and with other alternatives. Those skilled in the art, after understanding the solution of this application, will realize from the prior art and common general knowledge that there are many combinations, all of which are technical solutions to be protected in this application, and will not be exhaustively listed here.

[0017] This application discloses an uncertain state encoding module, method, device, and medium for situational awareness. A feature receiving unit acquires target feature data; a state space definition unit defines a state space containing multiple situation-related states; an uncertain state construction unit calculates the weights of each state in the state space based on the target feature data and / or the target's historical feature information to construct an uncertain state vector representing the coexistence of multiple states; and a state evolution update unit updates the target's current state representation according to the temporal changes of the uncertain state vector. This application can effectively express the ambiguity and multiple possibilities of the target state, describe its gradual evolution process, thereby improving the stability and continuity of the state representation of the situational awareness system and reducing the risk of misjudgment. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic diagram of an uncertain state coding module for situational awareness proposed in an embodiment of this application is shown. Detailed Implementation

[0020] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0021] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] To address the problems in the prior art, embodiments of this application propose an uncertain state encoding module, method, device, and medium for situational awareness, which can effectively express the ambiguity and multiple possibilities of the target state and describe its progressive evolution process, thereby improving the stability and continuity of the state representation of the situational awareness system and reducing the risk of misjudgment.

[0023] Please refer to Figure 1 , Figure 1 A schematic diagram of an uncertain state coding module for situational awareness proposed in an embodiment of this application is shown, including: The feature receiving unit is used to acquire target feature data.

[0024] In the uncertainty state coding module, the feature receiving unit obtains the basic information necessary for subsequent analysis and calculation of the target state from the upstream sensing system or data preprocessing module. This unit receives and integrates multi-dimensional, multi-source target feature data, which constitutes the original basis for situational understanding and uncertainty modeling of the target.

[0025] Target feature data includes the target's spatial location features, the target's motion features, the target's shape or outline features, and the target's relative relationship with the environment or other targets.

[0026] Target feature data includes, but is not limited to: the target's spatial location features (e.g., coordinates, altitude), the target's motion features (e.g., velocity, acceleration, heading), the target's morphological or contour features (e.g., size, shape parameters), and the target's relative relationship with the environment or other targets (e.g., distance, azimuth, affiliation). To facilitate subsequent processing by the computational unit, these diverse and heterogeneous features are uniformly organized and represented as mathematical feature vectors, i.e. This includes the time... For the Observed by each target Each feature metric is used. Through the work of this unit, the raw sensing data is transformed into a structured, standardized input that can be directly used by subsequent state-space mapping and uncertain state construction units.

[0027] The state space definition unit is used to define the state space, which contains multiple situation-related states.

[0028] The state space includes: non-threat state, abnormal behavior state, potential threat state, and threat state.

[0029] The state space definition unit is the rule definition and framework construction part of the uncertain state coding module. Its technical purpose is to establish a complete and structured set of state references for the entire system, encompassing the complete evolution path of the target from harmless to a clearly defined threat. This unit explicitly defines a state space consisting of multiple discrete states, denoted as […]. According to the embodiments provided in the invention, the space includes at least four core technical states closely related to threat assessment: a non-threat state ( ), abnormal behavior status ( ), potential threat status ( ) and threat status ( It is important to note that each state defined here is not a simple classification label, but rather a state with clear technical implications, corresponding to the target's specific behavioral characteristics, intent cues, and different stages of threat escalation. For example, an abnormal behavior state may correspond to a stage where the target's movement patterns deviate from the norm but its intent is unclear, while a potential threat state may correspond to a stage where the target exhibits clear hostile intent but has not yet taken direct offensive action.

[0030] The uncertainty state construction unit is used to calculate the state weights of the target in the state space based on the target feature data and / or the target's historical feature information, so as to construct the uncertainty state vector. The uncertainty state vector represents the coexistence of multiple states.

[0031] The uncertain state construction unit overcomes the limitations of traditional situational awareness in assigning a single, definite state label to the target, instead expressing the target state as a quantified uncertain state with multiple possibilities coexisting. This unit is based on the current target feature vector provided by the feature receiving unit. In addition, it incorporates historical feature information that reflects the target's behavioral patterns. It performs the core state mapping calculation.

[0032] Uncertainty state building blocks, used for: The unnormalized weight values ​​are calculated using the state mapping function based on the target feature vector and / or the target's historical feature information. The unnormalized weight values ​​represent the probability of the target being in each state. Normalize the unnormalized weight values ​​to obtain weights that satisfy the normalization constraints, thus forming an uncertain state vector.

[0033] This unit is based on the set of states established by the state-space definition unit. For each of these states Calculate a corresponding weight value This weight value is obtained through a designed state mapping function. Obtain, that is Its value reflects the probability that the target is in the k-th state based on current and historical feature information. The initial calculation generates a set of unnormalized weight values, which are then normalized to satisfy the constraints. This ultimately forms a standardized uncertainty state vector. The state mapping function The specific implementation is flexible and can employ rule-based weighted computation, probabilistic models, or machine learning models. Ultimately, the uncertainty state vector output by this unit mathematically represents the confidence distribution of the target belonging to each possible state in the state space at a specific moment, thus achieving a quantitative expression of multiple states coexisting.

[0034] The state evolution update unit is used to update the current state representation of the target based on the changes in the uncertainty state vector over time.

[0035] The state evolution update unit is a crucial component of the uncertain state encoding module, responsible for handling temporal continuity and achieving smooth state transitions and evolution. The core technical solution of this unit is based on a time-series update model. It receives a new uncertain state vector calculated by the uncertain state construction unit based on the latest features at the current moment. Meanwhile, the system internally stores the historical uncertainty state vector output from the previous calculation cycle. .

[0036] The formula for updating the uncertain state vector by the state evolution update unit is: ,in Let be the uncertainty state vector from the previous time step. The state vector is recalculated based on the latest features. This is the smoothing coefficient.

[0037] This unit uses a smoothing coefficient. (The value is between 0 and 1) The two are weighted and fused, and the updated current state vector is generated. .in The coefficient determines the degree to which the system remembers historical states. The larger the value, the smoother the state change and the stronger the inertia; The smaller the value, the more sensitive the system is to the latest observation results.

[0038] The state evolution update unit is also used to calculate the state entropy, and the formula for calculating the state entropy is: ,in For state entropy, The first uncertain state vector is the first uncertain state vector. The weights of each state.

[0039] In addition, to quantify the degree of uncertainty or disorder in the target behavior, this unit also introduces state entropy. As an important indicator, a higher state entropy value indicates a more uniform distribution of the target state across all possibilities, and a less clear and unstable behavioral intention. Conversely, a lower entropy value indicates that the state is concentrated in one or a few states, and the behavior is more certain. Ultimately, the updated uncertain state vector output by this unit serves two purposes: firstly, it represents the stable and continuous final state of this module and is output to the downstream situation modeling or decision-making module; secondly, this output will be fed back to this unit as a new historical state vector at the next moment, thus forming a closed-loop update process with time memory, enabling continuous tracking and description of the target's dynamic behavior.

[0040] The following presents a possible implementation of an uncertain state coding method for situational awareness, applied to an uncertain state coding unit. This method includes: Obtain target feature data; Define a state space, which contains multiple situation-related states; Based on target feature data and / or historical feature information of the target, calculate the state weight of the target in the state space to construct an uncertainty state vector, which represents the coexistence of multiple states; The current state representation of the target is updated based on the changes in the uncertainty vector over time.

[0041] The steps for updating the current state representation of the target include: Based on the smoothing coefficient, the historical uncertainty state vector is weighted and fused with the state vector recalculated based on the latest features to obtain the updated uncertainty state vector.

[0042] Compared with the prior art, the embodiments of this application have the following beneficial effects: First, through the core design of the uncertainty state vector, the target state is expanded from a traditional single determination result to a set of normalized weight distributions on a predefined state space. This enables the system to quantitatively characterize the possibility that a target simultaneously belongs to multiple states such as non-threat, abnormal behavior, and potential threat, thus more realistically reflecting the ambiguity and uncertainty of the target's intentions in complex environments.

[0043] Second, by using state evolution update units and their time-series update models, historical state vectors are weighted and fused with new state vectors calculated based on the latest observations. This mechanism ensures that the target's state representation does not change abruptly due to noise from a single observation, but rather changes smoothly and continuously over time, thus clearly depicting the gradual evolution trajectory of the target's behavior from normal to abnormal and then to threatening.

[0044] Third, the aforementioned evolutionary update mechanism acts as a filter, effectively suppressing state jumps caused by sensor noise or transient interference. Simultaneously, introducing state entropy as an auxiliary indicator allows for the quantitative assessment of the target behavior's instability. The combination of these two aspects ensures that the system's output state representation not only changes continuously over time but also exhibits robustness against transient disturbances, resulting in a more stable and reliable overall output.

[0045] Fourth, when the target's behavioral characteristics are unclear or in a transitional phase, traditional single-classification models may be forced to make a binary, potentially erroneous judgment. This invention allows the system to retain all reasonable possibilities in a multi-state coexistence manner before the final decision, providing richer and more nuanced input information for subsequent situation modeling or threat assessment modules, thereby fundamentally reducing the risk of misjudgment or delayed judgment caused by early hard decisions.

[0046] This preferred embodiment provides a computer device that can implement the steps of any embodiment of the uncertain state coding method provided in this application. Therefore, it can achieve the beneficial effects of the uncertain state coding method provided in this application. For details, please refer to the previous embodiments, which will not be repeated here.

[0047] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. Therefore, embodiments of this application provide a storage medium storing multiple instructions that can be loaded by a processor to execute the steps of any embodiment of the undetermined state coding method provided in this application.

[0048] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0049] Since the instructions stored in the storage medium can execute the steps in any of the uncertain state coding method embodiments provided in this application, the beneficial effects that any of the uncertain state coding methods provided in this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0050] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An uncertain state coding module for situational awareness, characterized in that, include: Feature receiving unit, used to acquire target feature data; A state space definition unit is used to define a state space, which contains multiple situation-related states. Uncertainty state construction unit is used to calculate the state weights of the target in the state space based on the target feature data and / or the target's historical feature information, so as to construct the uncertainty state vector, which represents the coexistence of multiple states; The state evolution update unit is used to update the current state representation of the target based on the changes in the uncertainty state vector over time.

2. The uncertainty state coding module as described in claim 1, characterized in that, Uncertainty state building blocks, used for: The unnormalized weight values ​​are calculated using the state mapping function based on the target feature vector and / or the target's historical feature information. The unnormalized weight values ​​represent the probability of the target being in each state. Normalize the unnormalized weight values ​​to obtain weights that satisfy the normalization constraints, thus forming an uncertain state vector.

3. The uncertainty state coding module as described in claim 1, characterized in that, The state space includes: non-threat state, abnormal behavior state, potential threat state, and threat state.

4. The uncertainty state coding module as described in claim 1, characterized in that, The formula for updating the uncertain state vector by the state evolution update unit is: ,in Let be the uncertainty state vector from the previous time step. The state vector is recalculated based on the latest features. This is the smoothing coefficient.

5. The uncertainty state coding module as described in claim 1, characterized in that, The state evolution update unit is also used to calculate the state entropy, and the formula for calculating the state entropy is: ,in For state entropy, The first uncertain state vector is the first uncertain state vector. The weights of each state.

6. The uncertainty state coding module as described in claim 1, characterized in that, Target feature data includes the target's spatial location features, the target's motion features, the target's shape or outline features, and the target's relative relationship with the environment or other targets.

7. An uncertain state coding method for situational awareness, characterized in that, The method includes: Obtain target feature data; Define a state space, which contains multiple situation-related states; Based on target feature data and / or historical feature information of the target, calculate the state weight of the target in the state space to construct an uncertainty state vector, which represents the coexistence of multiple states; The current state representation of the target is updated based on the changes in the uncertainty vector over time.

8. The uncertainty state coding method as described in claim 7, characterized in that, The steps for updating the current state representation of the target include: Based on the smoothing coefficient, the historical uncertainty state vector is weighted and fused with the state vector recalculated based on the latest features to obtain the updated uncertainty state vector.

9. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program that is loaded and executed by the processor to implement the uncertain state coding module as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which is loaded and executed by a processor to implement the uncertain state coding module as described in any one of claims 1-6.

Images