A method and system for dynamically calculating cognitive urgency based on continuous physical quantities

Abstract

The application discloses a method and system for dynamically calculating cognitive urgency based on continuous physical quantities, and belongs to the technical field of artificial intelligence and cognitive computing. The method comprises the following steps: obtaining sensor data of an external environment through a sensor interface, and extracting continuous physical quantities related to an event, at least including distance and relative speed; standardizing and packaging the continuous physical quantities and event labels to generate a standardized event data structure; calculating a cognitive urgency value with the continuous physical quantities as independent variables according to a preset continuous urgency function, wherein the cognitive urgency value is a continuous value; dynamically determining the maximum length of a situation transition path in cognitive decision-making according to the cognitive urgency value, selecting a short path for rapid convergence when the urgency is high, and selecting a long path for smooth transition when the urgency is low; and planning the situation transition path according to the maximum length, and executing cognitive decision-making. The application realizes dynamic urgency calculation based on continuous physical quantities and cognitive path planning driven by the urgency, so that the cognitive system can perceive the continuous changes of the physical world and adaptively adjust the reasoning depth, and can be widely applied to embodied intelligent scenes such as automatic driving, robots, intelligent decision-making systems and the like.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence and cognitive computing technology, specifically relating to a method and system for dynamically calculating cognitive urgency based on continuous physical quantities. It can be used in embodied intelligence application scenarios such as autonomous driving, robotics, and intelligent decision-making systems that require real-time adjustment of cognitive decision-making strategies according to the physical environment. Background Technology

[0002] In embodied intelligence systems, the cognitive decision-making layer needs to respond to external environmental events. Existing technologies typically employ a discrete label-based priority classification method when dealing with external events—pre-dividing events into several categories (such as "urgent," "important," and "normal") and assigning a fixed priority or urgency level to each category. This discretization method has the following fundamental drawbacks: (i) Discrete priority cannot reflect the continuous changes in the physical world. In existing technologies, event priorities are typically pre-set fixed values. For example, in autonomous driving systems, "pedestrian crossing" is preset as the highest priority, "red light" as a high priority, and "vehicle ahead slowing down" as a medium priority. However, the urgency of events in the physical world is continuously changing: the urgency of a pedestrian 50 meters away is clearly different from that of a pedestrian 5 meters away; the urgency of a car ahead with a relative speed of 1 m / s is also significantly different from that of a car ahead with a relative speed of 10 m / s. Existing technologies cannot distinguish the differences in urgency of the same type of event under different physical conditions.

[0003] In the field of autonomous driving, while existing technologies employ warning methods based on time-of-collision (TTC) or safe distance, these methods aim to calculate "whether to trigger a warning or braking." The result is a binary or thresholded judgment signal, failing to transmit urgency as a continuous cognitive parameter to higher-level cognitive decision-making layers, and further neglecting its role in driving path planning length or strategy selection in cognitive decision-making. Although some existing technologies utilize "urgency" or "urgency" in information scheduling, their urgency calculations are based on user interaction feedback and decay functions, falling under the category of task scheduling and unrelated to continuous perception of the physical environment.

[0004] (ii) Tagging and classification leads to the system degenerating into a rule engine. Because existing technologies use discrete labels to represent the urgency of events, the system can only respond to events with different labels using "if-else" rules. When faced with new scenarios (such as "a pedestrian 20 meters away at a speed of 5 m / s"), the system cannot automatically calculate its urgency and must rely on manually preset new rules. This causes the system to continuously expand into a huge rule base as the number of scenarios increases, eventually degenerating into a rule engine and losing the adaptive capabilities of a cognitive system.

[0005] (iii) The urgency is disconnected from the cognitive decision-making path In existing cognitive decision-making systems, the urgency of an event is only used to determine "whether to respond" or "response speed," without participating in the path planning of cognitive decision-making. For example, a high-urgency event may trigger a faster response, but the system will not choose a "shorter cognitive path"—that is, skip intermediate reasoning steps and converge directly to the target situation—just because the urgency is high. There is a lack of linkage between the reasoning depth of cognitive decision-making and the urgency of the physical environment.

[0006] While existing technologies include workshop scheduling methods based on "spatiotemporal urgency projection," their urgency is calculated based on workshop resource status and network topology, falling under the category of production scheduling and unrelated to physical environment perception and cognitive decision-making path planning. There are also methods that use "urgency" for autonomous driving safety warnings, but these methods trigger warnings or braking and do not involve dynamic adjustments to cognitive decision-making paths.

[0007] (iv) Lack of a continuous urgency calculation model that integrates multiple physical quantities In real-world physical scenarios, the urgency of an event is determined by multiple physical quantities, such as distance, relative velocity, direction angle, acceleration, and road surface adhesion coefficient. Current technology lacks a universal computational model that can integrate these multiple continuous physical quantities into a single continuous urgency value, making it impossible for cognitive systems to comprehensively assess the true urgency of an event.

[0008] In summary, there is an urgent need for a method and system that can dynamically calculate cognitive urgency based on continuous physical quantities, enabling cognitive systems to perceive continuous changes in the physical world and use urgency as a continuous parameter to drive cognitive decision-making path planning, thus preventing the system from degenerating into a rule engine. Summary of the Invention

[0009] (a) Purpose of the invention The purpose of this invention is to provide a method and system for dynamically calculating cognitive urgency based on continuous physical quantities, in order to solve the technical problems in the prior art, such as the inability of discrete labels to reflect the continuous changes in the physical world, the degradation of the system to a rule engine due to label classification, the disconnect between urgency and cognitive decision-making path, and the lack of a continuous urgency calculation model that integrates multiple physical quantities.

[0010] Specific objectives include: (1) A method for dynamically calculating cognitive urgency based on continuous physical quantities is provided, so that the system can calculate the urgency value of an event in real time based on continuous physical quantities such as distance, speed, angle, and acceleration.

[0011] (2) Provides a multi-physical quantity fusion urgency calculation model, which maps multiple physical quantities into a single urgency value through a continuous function, so that the cognitive system can comprehensively judge the true urgency of an event.

[0012] (3) Provides a dynamic programming method for cognitive paths driven by urgency, enabling the system to dynamically adjust the reasoning depth of cognitive decisions based on continuous urgency values—selecting a shorter cognitive path when the urgency is high (rapid convergence) and selecting a longer cognitive path when the urgency is low (smooth transition).

[0013] (4) Provide a standardized event-physical quantity data structure so that the perception layer can transmit physical quantity information and event labels to the cognition layer together, providing a data foundation for continuous urgency calculation.

[0014] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: 1. System Architecture A method and system for dynamically calculating cognitive urgency based on continuous physical quantities, comprising a processor, a memory, and a sensor interface connected to the processor, wherein the processor is configured to implement the following modules by executing program instructions stored in the memory: (1) Physical quantity sensing module The physical quantity sensing module is used to acquire sensor data of the external environment through the sensor interface and extract continuous physical quantities related to the event from the sensor data.

[0015] The continuous physical quantity includes, but is not limited to, one or a combination of the following parameters: - Distance parameter: Spatial distance between the event source and the agent (unit: meters); - Velocity parameter: The relative velocity of the event source with respect to the agent (unit: meters per second); - Angle parameter: The direction angle of the event source relative to the direction of motion of the agent (unit: degrees); - Acceleration parameter: The acceleration or relative acceleration of the event source (unit: m / s²); - Confidence parameter: The confidence level of the sensor in detecting the event (value range: 0 to 1).

[0016] The physical quantity sensing module encapsulates the extracted continuous physical quantities in a standardized format and transmits them to the cognitive decision-making module along with event tags.

[0017] (2) Urgency Calculation Module The urgency calculation module is used to receive continuous physical quantities transmitted by the physical quantity sensing module and calculate the cognitive urgency value of the current event according to a preset continuous urgency function.

[0018] The cognitive urgency value is a continuous value, and the value range is a preset interval (preferably 1.0 to 5.0). The higher the value, the more urgent the event, and the lower the value, the less urgent the event.

[0019] The continuous urgency function is a multivariate continuous function, using the continuous physical quantity as the independent variable, and outputs the cognitive urgency value. The continuous urgency function has the following characteristics: - As the distance parameter decreases, the cognitive urgency value increases monotonically; - As the relative speed parameter increases, the cognitive urgency value increases monotonically; - When the orientation angle parameter approaches zero (i.e., the event source is directly in the direction of the agent's movement), the cognitive urgency value increases monotonically. - As the acceleration parameter increases, the cognitive urgency value increases monotonically.

[0020] Preferably, the continuous urgency function is: urgency=base+w_d×f_d(distance)+w_v×f_v(rel_speed)+w_a×f_a(angle)+w_acc×f_acc(acceleration) in: -base is the baseline urgency value (preferably 1.0); -w_d, w_v, w_a, and w_acc are the preset weighting coefficients for each physical quantity; -f_d, f_v, f_a, and f_acc are monotonic mapping functions for each physical quantity, mapping the physical quantity to the urgency contribution value.

[0021] The mapping function is a continuously differentiable function, preferably taking one of the following forms: - Inverse proportional function: f(x) = k / (x + ε), where k is the scaling factor and ε is the decimal point to prevent division by zero; - Exponential decay function: f(x) = A × (1 - e^(-λx)), where A is the upper limit of amplitude and λ is the decay rate; -S-type function: f(x)=A / (1+e^(-k(x-x0))), where x0 is the threshold center.

[0022] (3) Event-Physical Quantity Standardization Module The event-physical quantity standardization module is used to standardize and encapsulate the continuous physical quantities extracted by the physical quantity sensing module with the corresponding event tags, and generate a standardized event data structure.

[0023] The standardized event data structure shall contain at least the following fields: - Event type: The semantic label of the event (such as "pedestrian", "red light", "obstacle"); - Physical quantity dictionary: contains key-value pairs of continuous physical quantities such as distance, relative velocity, direction angle, and acceleration; - Timestamp: The time when the event occurred or was detected; - Metadata: Additional information such as sensor origin and detection confidence level.

[0024] (4) Cognitive Decision Module The cognitive decision-making module receives the standardized event data structure and dynamically adjusts the reasoning depth and path length of the cognitive decision-making based on the cognitive urgency value.

[0025] The cognitive decision-making module includes a situational path planning unit, which is used to plan a migration path from the current situation to the target situation in a preset situational space.

[0026] The situational path planning unit dynamically determines the maximum length of the migration path based on the cognitive urgency value: - When the cognitive urgency value is higher than the first urgency threshold, the maximum length of the migration path is set to the first length value (preferably 2 to 3 steps) to achieve rapid convergence; - When the cognitive urgency value is between the first urgency threshold and the second urgency threshold, the maximum length of the migration path is set to the second length value (preferably 3 to 4 steps) to achieve normal convergence; When the cognitive urgency value is lower than the second urgency threshold, the maximum length of the migration path is set to a third length value (preferably 5 to 6 steps) to achieve a smooth transition.

[0027] The first urgency threshold is higher than the second urgency threshold. Preferably, the first urgency threshold is 3.5 and the second urgency threshold is 2.0.

[0028] 2. Method and Flow A method for dynamically calculating cognitive urgency based on continuous physical quantities includes the following steps: Step S1: Physical quantity sensing and extraction Sensor data of the external environment is acquired through a sensor interface, and continuous physical quantities related to the event are extracted from the sensor data.

[0029] The continuous physical quantities include at least distance parameters and relative velocity parameters.

[0030] Step S2: Standardize event encapsulation The extracted continuous physical quantities and their corresponding event labels are standardized and encapsulated to generate a standardized event data structure.

[0031] Step S3: Calculation of Continuous Urgency Based on a preset continuous urgency function, the cognitive urgency value of the current event is calculated using the continuous physical quantities in the standardized event data structure as independent variables.

[0032] The cognitive urgency value is a continuous value, and its range is a preset interval.

[0033] The continuous urgency function is calculated as follows: urgency=1.0+4.0 / (1+distance / D0)+k_v×|rel_speed|+k_a×cos(angle) in: -distance represents the distance between the event source and the agent; -D0 is the distance scale parameter (preferably 3.0 meters); -rel_speed is the relative speed of the event source with respect to the agent; -angle is the directional angle of the event source relative to the direction of motion of the agent; -k_v and k_a are preset weighting coefficients.

[0034] Step S4: Determining the path length driven by urgency Based on the cognitive urgency value, the maximum length of the situational transition path in cognitive decision-making is dynamically determined: - When the cognitive urgency value is higher than the first urgency threshold, the maximum length of the migration path is set to the first length value; - When the cognitive urgency value is between a first urgency threshold and a second urgency threshold, the maximum length of the migration path is set to the second length value; - When the cognitive urgency value is lower than the second urgency threshold, the maximum length of the migration path is set to the third length value.

[0035] Step S5: Situational Path Planning and Cognitive Decision Making Based on the maximum length, a migration path from the current situation to the target situation is planned in a preset situation space, and a cognitive decision is executed.

[0036] 3. Preferred Implementation Method of Standardized Event Data Structure The preferred standardized event data structure is: { "event_type":"pedestrian", "physics":{ "distance":12.5, "relative_speed": 1.2, "angle":5.0, "acceleration":0.3, "confidence": 0.92 }, "timestamp":1699200000.0, "metadata":{ "source":"camera", "sensor_id":"CAM_01" } } 4. Specific Implementation Examples of Urgency Calculation In a preferred embodiment, the specific form of the continuous urgency function is as follows: urgency=1.0+3.0 / (1+distance / 3.0)+0.5×|rel_speed|+0.3×cos(angle×π / 180) in: - The unit of distance is meters, and the larger the value, the smaller the contribution. -rel_speed is measured in meters per second, and a larger value contributes more to speed. -Angle is in degrees. It contributes 0 when the angle is 0 degrees and 0.3 when the angle is 90 degrees.

[0037] When distance = 5.0m, rel_speed = 2.0m / s, and angle = 10°: urgency=1.0+3.0 / (1+5.0 / 3.0)+0.5×2.0+0.3×cos(10°) =1.0 + 3.0 / 2.667 + 1.0 + 0.3 × 0.985 =1.0+1.125+1.0+0.2955 =3.4205 When distance = 30.0m, rel_speed = 0.5m / s, and angle = 45°: urgency=1.0+3.0 / (1+30.0 / 3.0)+0.5×0.5+0.3×cos(45°) =1.0 + 3.0 / 11.0 + 0.25 + 0.3 × 0.707 =1.0+0.273+0.25+0.2121 =1.7351 The above calculation results verify that the continuous urgency function can generate continuous urgency values ​​based on the continuous changes in physical quantities.

[0038] 5. The Correspondence Between Urgency and Path Length In a preferred embodiment, the relationship between the urgency threshold and the path length is as follows: urgency ≥ 4.0 2 steps Direct jump, minimal reasoning 3.0≤urgency<4.0 3 steps Shortest path, fast convergence 2.0≤urgency<3.0 4 steps Normal path, standard convergence urgency<2.0 5-6 steps Long path, smooth transition (III) Beneficial Effects Compared with the prior art, the present invention has the following beneficial effects: (1) Dynamic urgency calculation based on continuous physical quantities is realized. This invention maps continuous physical quantities such as distance, speed, and angle into continuous urgency values ​​through a continuous urgency function, enabling the system to perceive continuous changes in the physical world and avoiding the defect of discrete labels being unable to distinguish different degrees of urgency for the same event.

[0039] (2) It avoids the system degenerating into a rule engine. Since the urgency is calculated continuously, the system does not need to preset rules for each scenario, but rather calculates adaptively under a unified continuous function framework, which fundamentally avoids the infinite expansion of the rule base.

[0040] (3) Urgency-driven cognitive path dynamic programming is realized. The present invention directly uses the calculated continuous urgency value to drive the path length selection in cognitive decision-making—selecting a short path (fast convergence) when the urgency is high and selecting a long path (smooth transition) when the urgency is low, so that the reasoning depth of cognitive decision-making matches the urgency of the physical environment.

[0041] (4) A standardized physical quantity transmission mechanism is provided. This invention enables the perception layer to transmit continuous physical quantities and event tags together to the cognition layer through a standardized event data structure, providing a unified data foundation for the cognition layer to calculate the continuous urgency.

[0042] (5) Significantly innovative compared to existing technologies. In existing technologies, urgency is used either for resource urgency deduction in workshop scheduling (based on discrete events and network topology), for safety warnings in autonomous driving (based on threshold judgment to determine whether braking is triggered), or for task urgency in information scheduling (based on user interaction feedback). This invention is the first to use continuous physical quantities as the core input for urgency calculation, and directly uses the calculated continuous urgency values ​​to drive the dynamic programming of path length for cognitive decision-making, forming a complete technical link of "physical quantity perception → continuous urgency calculation → cognitive path dynamic programming", which is of pioneering significance in the field of cognitive decision-making. Attached Figure Description

[0043] Figure 1The overall flowchart of the method for dynamically calculating cognitive urgency based on continuous physical quantities described in this invention.

[0044] Figure 2 : Schematic diagram of standardized event data structure (standardized event data structure includes event type, physical quantity dictionary, timestamp and metadata).

[0045] Figure 3 : Schematic diagram of the physical quantity-urgency mapping relationship of the continuous urgency function.

[0046] Figure 4 : A diagram illustrating the relationship between urgency and cognitive path length.

[0047] Figure 5 : Module architecture diagram of the system described in this invention.

[0048] Figure 6 Example diagram of urgency calculation under different combinations of physical quantities. Detailed Implementation

[0049] It should be understood that the following embodiments are used to illustrate the technical solutions of the present invention and not to limit them. Those skilled in the art can implement the complete technical solutions of the present invention based on the teachings of this specification.

[0050] Example 1: Standardized Event Encapsulation This embodiment demonstrates how the system encapsulates the physical quantities detected by the sensors into a standardized event data structure.

[0051] The sensor (camera) detected a pedestrian ahead, while the lidar measured a distance of 12.5 meters, a relative speed of 1.2 meters per second, and a directional angle of 5 degrees.

[0052] The physical quantity sensing module extracts the above continuous physical quantities, and the event-physical quantity standardization module generates the following standardized event data structure: { "event_type": "pedestrian", "physics": { "distance": 12.5, "relative_speed": 1.2, "angle": 5.0, "acceleration": 0.3, "confidence": 0.92 }, "timestamp": 1699200000.0, "metadata": { "source": "camera", "sensor_id": "CAM_01 } } The standardized event data structure is transmitted to the urgency calculation module and the cognitive decision-making module.

[0053] Example 2: Calculation of Continuous Urgency This embodiment demonstrates how the system calculates the cognitive urgency value based on continuous physical quantities.

[0054] Following Example 1, the system obtains the following physical quantities from the standardized event data structure: distance=12.5m, rel_speed=1.2m / s, angle=5°.

[0055] The urgency calculation module calculates based on the continuous urgency function: urgency=1.0+3.0 / (1+12.5 / 3.0)+0.5×1.2+0.3×cos(5°) =1.0 + 3.0 / 5.167 + 0.6 + 0.3 × 0.996 =1.0 + 0.581 + 0.6 + 0.299 =2.48 The calculated cognitive urgency score is 2.48, which is considered to be in the lower-middle range (between 2.0 and 3.0).

[0056] Those skilled in the art will understand that the weighting coefficients and scale parameters of each physical quantity in the above continuous urgency function can be adjusted according to specific application scenarios. Using other continuously differentiable monotonic mapping functions that meet the conditions to replace each item in the above function are all equivalent embodiments of the present invention.

[0057] Example 3: Calculation of High-Urgency Scenarios This embodiment demonstrates the system's ability to calculate urgency in close-range, high-relative-speed scenarios.

[0058] The sensor detected a pedestrian suddenly crossing the road at a distance of 5.0 meters, with a relative speed of 3.0 meters per second and a direction angle of 10 degrees.

[0059] Urgency calculation module calculates: urgency=1.0+3.0 / (1+5.0 / 3.0)+0.5×3.0+0.3×cos(10°) =1.0 + 3.0 / 2.667 + 1.5 + 0.3 × 0.985 =1.0+1.125+1.5+0.296 =3.92 The calculated cognitive urgency score is 3.92, which is considered high urgency (above 3.0).

[0060] Example 4: Calculation of Low-Urgency Scenarios This embodiment demonstrates the system's ability to calculate urgency in long-distance, low-relative-speed scenarios.

[0061] The sensor detected a pedestrian in the distance ahead, at a distance of 40.0 meters, with a relative speed of 0.3 meters per second and a direction angle of 30 degrees.

[0062] Urgency calculation module calculates: urgency=1.0+3.0 / (1+40.0 / 3.0)+0.5×0.3+0.3×cos(30°) =1.0 + 3.0 / 14.333 + 0.15 + 0.3 × 0.866 =1.0+0.209+0.15+0.260 =1.62 The calculated cognitive urgency score is 1.62, which is considered low urgency (below 2.0).

[0063] Example 5: Urgency-Driven Path Length Determination This embodiment demonstrates how the system dynamically determines the cognitive path length based on the calculated continuous urgency value.

[0064] Scenario 1: High urgency scenario (urgency=3.92) The system determines that the urgency value is higher than the first urgency threshold of 3.5. The situational path planning unit sets the maximum length of the migration path to 2 steps.

[0065] The system's transition path from the current situation to the target situation is limited to no more than two steps, enabling rapid convergence. For example, when a pedestrian is detected crossing at close range, the system path is "current situation → target situation (abrupt stop)," skipping intermediate situations and converging directly.

[0066] Scenario 2: Medium urgency scenario (urgency=2.48) The system determines that the urgency value falls between the first urgency threshold of 3.5 and the second urgency threshold of 2.0. The situational path planning unit sets the maximum length of the migration path to 4 steps.

[0067] The system uses normal path length for cognitive reasoning. For example, when a pedestrian is detected at a medium distance, the system path is "current situation → intermediate situation 1 → intermediate situation 2 → target situation (decelerate and observe)".

[0068] Scenario 3: Low urgency scenario (urgency=1.62) The system determines that the urgency value is below the second urgency threshold of 2.0. The situational path planning unit sets the maximum length of the migration path to 6 steps.

[0069] The system uses long paths for smooth transitions. For example, when a pedestrian is detected at a distance, the system path is "current situation → intermediate situation 1 → intermediate situation 2 → intermediate situation 3 → intermediate situation 4 → target situation (slow deceleration)", achieving a smooth and gradual cognitive transition.

[0070] Example 6: Comparison of Urgency under Different Physical Conditions for the Same Event Type This embodiment demonstrates the essential difference between the present invention and existing discrete labeling methods.

[0071] Existing technology: Pedestrian events are uniformly marked as "high priority", and all pedestrian events trigger the same response strategy.

[0072] This invention: dynamically calculates urgency based on continuous physical quantities. Pedestrians crossing at close range 5m 3.0m / s 10° 3.92 2-step (emergency stop) Pedestrian standing, at a medium distance 15m 0.5m / s 5° 2.05 4 steps (slow down and observe) Pedestrians walking, long distance 40m 0.3m / s 30° 1.62 6 steps (gradually slow down) The same event type, "pedestrian," produces completely different urgency values ​​and cognitive path lengths under different physical conditions. This invention achieves fine-grained perception and differentiated response to continuous changes in the physical world, which existing discrete labeling methods cannot do.

[0073] Example 7: Angle Limiting Effect In the calculation of the continuous urgency function, the angle parameter angle ranges from -180° to 180°. When the event source is located behind or to the side of the agent (i.e., |angle|>90°), if the angle parameter is not processed, the angle term cos(angle) may produce a negative value, causing the urgency to decrease instead of increase.

[0074] As a preferred implementation, an effective angle parameter θ_eff is introduced for amplitude limiting: When |angle| ≤ 90° (the event source is located within ±90° in front), the angle contribution is calculated normally as 0.3 × cos(θ_eff); When |angle| > 90° (the event source is located to the side or rear), the angle contribution is truncated to 0, and no negative deviation is generated in the urgency calculation.

[0075] Specifically: -angle=0° (directly in front) → θ_eff=0°, the contribution is 0.3 × cos(0°) = 0.3 (maximum); -angle=90° (positive lateral) → θ_eff=90°, contribution is 0.3 × cos(90°) = 0; -angle=120° (side and back) → θ_eff=90°, is truncated, contributes 0, and does not produce a negative value.

[0076] Through the above-mentioned limiting process, events located behind the agent will not contribute unreasonable urgency, thus ensuring the physical rationality of urgency calculation.

[0077] Example 8: Comparison with the prior art This embodiment further illustrates the inventiveness of the present invention by comparing it with the prior art.

[0078] Existing technology 1 (Autonomous driving rear-end collision avoidance warning system): Calculates the safe following distance and warning speed based on the distance between the two vehicles, relative speed, and acceleration. A warning is triggered when the actual distance is less than the safe distance. This technology only outputs a binary warning signal (triggered / not triggered), does not output a continuous urgency value, and the warning signal is only used to trigger a warning or braking, not for driving path planning that drives cognitive decision-making.

[0079] Existing technology 2 (autonomous driving safety warning method): Obtain environmental information analysis to determine the urgency of the vehicle, but the urgency is calculated based on the type, position, speed and other factors of obstacles and is directly used to trigger the warning. Its output is still a discrete warning signal and does not involve the linkage between urgency and cognitive path length.

[0080] Existing technology three (workshop scheduling method based on spatiotemporal urgency): calculates resource urgency and network coupling urgency, but this technology belongs to the field of production scheduling, and its urgency is based on workshop resource status and network topology, and is unrelated to physical environment perception and cognitive decision-making.

[0081] The essential difference between this invention and the aforementioned prior art lies in: (1) Different technical paths: The existing technology is "physical quantity → threshold judgment → trigger action", while the present invention is "physical quantity → continuous urgency calculation → cognitive path dynamic planning → situation convergence".

[0082] (2) The nature of urgency is different: the urgency of the prior art is discrete (triggered / not triggered) or domain-specific, while the urgency output by the present invention is continuous (1.0~5.0), which can be directly used as a parameter for cognitive decision-making.

[0083] (3) Different application levels: The urgency of existing technologies is used for low-level control (braking, early warning, scheduling), while the urgency of this invention is used for high-level cognitive decision-making (path length planning, reasoning depth adjustment).

[0084] (4) Different core mechanisms: The existing technology does not use continuous urgency as a dynamic adjustment parameter for cognitive path length, and does not form a complete calculation link of "physical quantity → urgency → path length".

Claims

1. A method for dynamically calculating cognitive urgency based on continuous physical quantities, characterized in that, Includes the following steps: Step S1: Acquire sensor data of the external environment through the sensor interface, and extract continuous physical quantities related to the event from the sensor data. The continuous physical quantities include at least distance parameters and relative velocity parameters. Step S2: Standardize and encapsulate the extracted continuous physical quantities and their corresponding event labels to generate a standardized event data structure; Step S3: Based on the preset continuous urgency function, using the continuous physical quantity in the standardized event data structure as the independent variable, calculate the cognitive urgency value of the current event. The cognitive urgency value is a continuous value and its range is a preset interval. Step S4: Based on the cognitive urgency value, dynamically determine the maximum length of the situational transition path in cognitive decision-making, wherein when the cognitive urgency value is higher than a first urgency threshold, the maximum length is set to a first length value, and when the cognitive urgency value is lower than a second urgency threshold, the maximum length is set to a second length value, wherein the first length value is less than the second length value, and the first urgency threshold is higher than the second urgency threshold; Step S5: Based on the maximum length, plan the migration path from the current situation to the target situation in the preset situation space, and execute cognitive decision-making.

2. The method according to claim 1, characterized in that, The continuous physical quantity also includes at least one of the angle parameter and the acceleration parameter; the continuous pressure function is a multivariable continuous function with the following characteristics: - As the distance parameter decreases, the cognitive urgency value increases monotonically; - As the relative speed parameter increases, the cognitive urgency value increases monotonically; - When the angle parameter approaches zero, the cognitive urgency value increases monotonically; The continuous urgency function is: urgency=1.0+3.0 / (1+distance / 3.0)+0.5×|rel_speed|+0.3×cos(angle×π / 180) Wherein, distance is the distance parameter, rel_speed is the relative speed parameter, and angle is the angle parameter.

3. The method according to claim 1, characterized in that, In step S4, the first urgency threshold is 3.5, and the second urgency threshold is 2.0; the first length value is 2 to 3 steps, and the second length value is 5 to 6 steps; when the cognitive urgency value is between the first urgency threshold and the second urgency threshold, the maximum length is set to a third length value, and the third length value is between the first length value and the second length value.

4. The method according to claim 1, characterized in that, In step S2, the standardized event data structure includes at least an event type field and a physical quantity dictionary field, wherein the physical quantity dictionary field stores the continuous physical quantities in key-value pair format.

5. The method according to claim 1, characterized in that, The preset situation space contains sixty-four basic situation types, each of which corresponds to a unique six-dimensional binary encoding vector; the migration path consists of a series of intermediate situation types, and the encoding vectors between two adjacent situation types in the path differ in only one dimension.

6. A system for dynamically calculating cognitive urgency based on continuous physical quantities, characterized in that, The processor includes a processor, a memory, and a sensor interface connected to the processor. The processor is configured to implement the following modules by executing program instructions stored in the memory: The physical quantity sensing module is used to acquire sensor data of the external environment through the sensor interface and extract continuous physical quantities related to the event from the sensor data; The event-physical quantity standardization module is used to standardize and encapsulate the extracted continuous physical quantities with their corresponding event labels to generate a standardized event data structure. The urgency calculation module is used to calculate the cognitive urgency value of the current event based on a preset continuous urgency function, using the continuous physical quantities in the standardized event data structure as independent variables. The cognitive decision-making module is used to dynamically determine the maximum length of the situational transition path in cognitive decision-making based on the cognitive urgency value, and to plan the transition path from the current situation to the target situation in a preset situational space based on the maximum length, and to execute the cognitive decision-making.

7. The system according to claim 6, characterized in that, In the urgency calculation module, the continuous urgency function is: urgency=1.0+3.0 / (1+distance / 3.0)+0.5×|rel_speed|+0.3×cos(angle×π / 180) Where distance is the distance parameter, rel_speed is the relative speed parameter, and angle is the angle parameter.

8. The system according to claim 6, characterized in that, In the cognitive decision-making module: - When the cognitive urgency value is higher than the first urgency threshold, the maximum length of the migration path is set to the first length value; - When the cognitive urgency value is lower than the second urgency threshold, the maximum length of the migration path is set to the second length value; - The first length value is less than the second length value, and the first urgency threshold is higher than the second urgency threshold.

9. The system according to claim 6, characterized in that, The preset situation space contains sixty-four basic situation types, each of which corresponds to a unique six-dimensional binary encoding vector.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

Images