Information source configuration and price decoupling method and system based on dynamic pricing mechanism

Abstract

The invention relates to the field of electric digital data processing, and discloses an information source configuration and price decoupling method and system based on a dynamic pricing mechanism, and the method comprises the steps: defining a time recovery entropy for representing the time required for recovering to an ideal idle state for an information source; constructing a virtual opportunity cost field based on the entropy value; abstracting a service request into logic particles propagating in the field, and determining a propagation path and an end point information source according to a minimum action quantity principle; and generating a final price according to the path attribute. According to the method, through a coupling mechanism of the time recovery entropy and the opportunity cost field, the resource configuration decision endogenesis considers the future flexibility value, the self-adaptive decoupling of the price signal and the information source selection is realized, and the ability of the system to deal with the sudden high-value task is improved.

Description

Technical Field

[0001] The present invention relates to a method and system for decoupling information source configuration and price based on a dynamic pricing mechanism, and belongs to the technical field of electronic digital data processing. Background Art

[0002] In the field of electronic digital data processing, dynamic pricing and signal source configuration mainly rely on real-time load indicators (such as CPU utilization and network traffic) to establish a direct mapping mechanism between price and resources. This approach meets immediate needs through reactive adjustment, but generally ignores the opportunity cost dimension implicit in resource configuration - that is, the strategic flexibility to respond to high-value tasks is lost after the signal source is occupied by low-value tasks. Taking the cloud platform that simultaneously handles delay-sensitive AI training and batch data processing as an example, the existing technology prioritizes the expansion of low-priced resources under high load, resulting in high-flexibility nodes being deeply occupied by low-value tasks; when a sudden high-value task request occurs, the system is forced to delay response or migrate at high cost due to lack of available resources, exposing the rigid coupling defect of resource allocation and price signals.

[0003] The industry has attempted to introduce predictive models to optimize scheduling, but these approaches are still limited by three fundamental contradictions: 1. Price signals only reflect historical / current supply and demand and cannot quantify the time cost of restoring a flexible state; 2. Multi-source monitoring data is simplified into single-dimensional price instructions, severing the connection between resource selection and opportunity cost; 3. Prediction algorithms and feedback loops added to compensate for these deficiencies exacerbate system latency and computing power overhead.

[0004] While existing methods have improved resource utilization efficiency to a certain extent, they still cannot effectively measure the responsiveness of information sources to future tasks through price mechanisms. This results in a lack of strategic consideration for potentially high-value tasks during resource scheduling. Furthermore, due to their over-reliance on real-time monitoring and complex computation, they are unable to adapt to the large-scale deployment requirements of edge computing nodes. Therefore, the technical problem to be solved by this invention is how to construct an information source configuration mechanism based on endogenous opportunity cost evaluation, achieving adaptive decoupling of price signals and resource allocation while avoiding high-frequency monitoring and complex computation. Summary of the Invention

[0005] The present invention provides a method and system for decoupling information source configuration and price based on a dynamic pricing mechanism. Its main purpose is to solve the problem in the existing technology that the lack of opportunity cost assessment leads to the rigid coupling of resource configuration and price signals, thereby restricting the system's strategic responsiveness.

[0006] To achieve the above objectives, the present invention provides a method for decoupling information source configuration from price based on a dynamic pricing mechanism, the method comprising the following steps: Step a: For each source in the source pool, determine a time recovery entropy (TRE). The time recovery entropy is a scalar value that represents the time required for the source to be released from its current service state and restored to an idle state capable of accepting new tasks of any type. The determination of the time recovery entropy is based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes. Step b: constructing a dynamic virtual opportunity cost field in the cloud controller based on the time recovery entropy value of the information source, wherein the time recovery entropy value determines the potential energy corresponding to the information source in the opportunity cost field; Step c: When a service request and its initial quote are received, the service request is abstracted into a logical particle, the initial quote carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; Step d: Determine the final propagation path of the logical particle in the opportunity cost field according to the principle of least action. The principle of least action minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change. In step e, the information source corresponding to the end point of the final propagation path is determined as the configuration target of the service request, and the final service price is determined according to the kinetic energy consumed by the logical particles along the final propagation path, thereby achieving decoupling of information source configuration and price.

[0007] Preferably, the determination of the time recovery entropy in step a is performed based on the estimated recovery time contained in the metadata of the task currently carried by the source; the estimated recovery time is a predefined value, which can indicate the reload time or context switching time after the cache is invalidated, and the update frequency of the time recovery entropy value is less than once per minute.

[0008] Preferably, the construction of the dynamic virtual opportunity cost field in step b includes: the cloud controller periodically collects the time recovery entropy values of all sources in the source pool, and uses the inverse distance weighted interpolation algorithm to generate discretized potential field data on the logical grid according to the time recovery entropy values of the sources and their logical positions to form an opportunity cost field.

[0009] Preferably, the propagation rule of the logical particles in the opportunity cost field in step c is: the logical particles tend to move to the area with lower potential energy in the opportunity cost field; when the logical particles pass through the area with higher potential energy during the propagation process, their kinetic energy is consumed.

[0010] Preferably, the final propagation path that follows the principle of least action in step d is found by a variant of the A* algorithm (A star algorithm), where the cost function of the A* algorithm is Incorporating physical distance costs and potential energy change costs , and the relationship can be expressed as: , in, To adjust the preset coefficients of the relative weights of physical distance cost and potential energy change cost, is the total potential energy change experienced by the logical particle along the path.

[0011] Preferably, It is a preset coefficient with a value range of 0.1 to 100, and the value can be configured and adjusted according to the system manager's weight preference for the system's future responsiveness and short-term benefits.

[0012] Preferably, determining the final service price includes combining the kinetic energy consumed by the logic particles along the final propagation path with the initial bid of the service request to obtain a final settlement price.

[0013] Preferably, the signal sources in the signal source pool include virtual machines, containers, physical servers, and network slice resource units; the types of service requests include data cleaning tasks, AI model training tasks, data analysis tasks, and high real-time business tasks.

[0014] Preferably, the source node side only maintains one scalar value, time recovery entropy, and the update of the scalar value is triggered only when the type of task carried by the source changes, thereby reducing the computational overhead and communication overhead on the source node side.

[0015] A system for decoupling information source configuration from price based on a dynamic pricing mechanism, the system comprising: The source node is configured to determine and maintain a time recovery entropy (TRE). The time recovery entropy is a scalar value that represents the time required for the source to be released from the current service state and restored to an idle state where it can accept new tasks of any type. The determination of the time recovery entropy is based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes; The cloud controller is in communication with the source node and is configured to: construct a dynamic virtual opportunity cost field based on the time-recovery entropy value of the source node, wherein the time-recovery entropy value determines the potential energy corresponding to the source in the opportunity cost field; when a service request and its initial quotation are received, the service request is abstracted into a logical particle, and the initial quotation carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; determine the final propagation path of the logical particle in the opportunity cost field in accordance with the principle of least action, which minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change; determine the source corresponding to the end point of the final propagation path as the configuration target of the service request, and determine the final service price based on the kinetic energy consumed by the logical particle along the final propagation path, thereby achieving decoupling of source configuration and price.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The source node only needs to update a single scalar value (TRE) when switching tasks. This value is derived from the preset recovery time parameter in the task metadata. This avoids the computing power consumption of continuously monitoring multi-dimensional indicators in traditional solutions, allowing edge nodes to operate with near-zero computing overhead. When the cloud controller constructs an opportunity cost field based on discrete TRE values, the system naturally forms the ability to quantify the strategic elasticity of resources. High-TRE sources form high-potential energy areas in the virtual potential field, while low-TRE sources form low-potential energy channels. This design eliminates the reliance on complex predictive models for resource allocation decisions. Instead, it uses physical field principles to spontaneously guide service requests to bypass high-stickiness resources, reserving space for agile responses for sudden high-value tasks.

[0017] 2. The initial quote carried in the service request is converted into the initial kinetic energy of a logical particle, which propagates in the potential field constructed by the TRE value. The process of consuming kinetic energy as the particle travels through high-potential energy areas essentially converts the opportunity cost of resources into a price adjustment factor. When the particle reaches its endpoint according to the principle of least action, its path automatically points to the signal source with the optimal overall cost, and the kinetic energy consumption directly corresponds to the final service price. This mechanism integrates the two previously separate decision-making processes of resource selection and price generation into a natural motion process in a single physical field, avoiding the rigid coupling of price signals and resource allocation in traditional solutions.

[0018] 3. The cloud controller uses the inverse distance weighted interpolation method, which only requires low-frequency TRE broadcasts from the source node to generate the global opportunity cost field. When a service request comes in, the A* algorithm variant uses a composite cost function that combines physical distance cost and potential energy change cost ( ), quickly outputting the optimal path on the logical grid. This process transforms the opportunity cost evaluation in economics into a standard path planning problem, allowing the system to simultaneously complete resource matching and dynamic price adjustment without deploying a dedicated pricing model, thereby reducing the decision-making complexity of the central node.

[0019] 4. The value of time recovery entropy depends solely on the state recovery characteristics of the task itself, such as cache loading time and context switching time, and is unrelated to the specific service type. When the system accesses new signal sources, such as network slicing or carries unknown tasks, it can be integrated into the existing scheduling framework by simply presetting the TRE parameters during the task deployment phase. This design, which abstracts service characteristics into standardized metrics, enables the solution to maintain consistent resource allocation strategies through a unified potential field mechanism even when facing heterogeneous loads such as AI training and real-time services. Logical particles continuously consume kinetic energy as they propagate through high-potential energy areas. This means that when a service request attempts to occupy a high-TRE resource, its effective bid is automatically attenuated. This mechanism creates a built-in price damping effect: competitive demand for scarce and flexible resources is self-suppressed due to kinetic energy consumption, avoiding the impulsive price fluctuations caused by traditional bidding models. The system achieves market equilibrium through physical principles rather than external regulation, thereby reducing the risk of frequent resource allocation switches caused by price fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of information source configuration and dynamic pricing of the present invention; Figure 2 A comparison chart of pricing responses for service requests of the present invention; Figure 3 This is a high-value request response sequence diagram of the present invention.

[0021] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0023] The present invention provides a method and system for decoupling information source configuration and price based on a dynamic pricing mechanism. The method includes the following steps: Step a: For each source in the source pool, determine a time recovery entropy (TRE). The time recovery entropy is a scalar value that represents the time required for the source to be released from its current service state and restored to an idle state capable of accepting new tasks of any type. The determination of the time recovery entropy is based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes. Step b: constructing a dynamic virtual opportunity cost field in the cloud controller based on the time recovery entropy value of the information source, wherein the time recovery entropy value determines the potential energy corresponding to the information source in the opportunity cost field; Step c: When a service request and its initial quote are received, the service request is abstracted into a logical particle, the initial quote carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; Step d: Determine the final propagation path of the logical particle in the opportunity cost field according to the principle of least action. The principle of least action minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change. In step e, the information source corresponding to the end point of the final propagation path is determined as the configuration target of the service request, and the final service price is determined according to the kinetic energy consumed by the logical particles along the final propagation path, thereby achieving decoupling of information source configuration and price.

[0024] Preferably, the determination of the time recovery entropy in step a is performed based on the estimated recovery time contained in the metadata of the task currently carried by the source; the estimated recovery time is a predefined value, which can indicate the reload time or context switching time after the cache is invalidated, and the update frequency of the time recovery entropy value is less than once per minute.

[0025] Preferably, the construction of the dynamic virtual opportunity cost field in step b includes: the cloud controller periodically collects the time recovery entropy values of all sources in the source pool, and uses the inverse distance weighted interpolation algorithm to generate discretized potential field data on the logical grid according to the time recovery entropy values of the sources and their logical positions to form an opportunity cost field.

[0026] Preferably, the propagation rule of the logical particles in the opportunity cost field in step c is: the logical particles tend to move to the area with lower potential energy in the opportunity cost field; when the logical particles pass through the area with higher potential energy during the propagation process, their kinetic energy is consumed.

[0027] Preferably, the final propagation path that follows the principle of least action in step d is found by a variant of the A* algorithm, where the cost function of the A* algorithm is Incorporating physical distance costs and potential energy change costs , and the relationship can be expressed as: , in, To adjust the preset coefficients of the relative weights of physical distance cost and potential energy change cost, is the total potential energy change experienced by the logical particle along the path.

[0028] Preferably, It is a preset coefficient with a value range of 0.1 to 100, and the value can be configured and adjusted according to the system manager's weight preference for the system's future responsiveness and short-term benefits.

[0029] Preferably, determining the final service price includes combining the kinetic energy consumed by the logic particles along the final propagation path with the initial bid of the service request to obtain a final settlement price.

[0030] Preferably, the signal sources in the signal source pool include virtual machines, containers, physical servers, and network slice resource units; the types of service requests include data cleaning tasks, AI model training tasks, data analysis tasks, and high real-time business tasks.

[0031] Preferably, the source node side only maintains one scalar value, time recovery entropy, and the update of the scalar value is triggered only when the type of task carried by the source changes, thereby reducing the computational overhead and communication overhead on the source node side.

[0032] A system for decoupling information source configuration from price based on a dynamic pricing mechanism, the system comprising: The source node is configured to determine and maintain a time recovery entropy (TRE). The time recovery entropy is a scalar value that represents the time required for the source to be released from the current service state and restored to an idle state where it can accept new tasks of any type. The determination of the time recovery entropy is based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes; The cloud controller is in communication with the source node and is configured to: construct a dynamic virtual opportunity cost field based on the time-recovery entropy value of the source node, wherein the time-recovery entropy value determines the potential energy corresponding to the source in the opportunity cost field; when a service request and its initial quotation are received, the service request is abstracted into a logical particle, and the initial quotation carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; determine the final propagation path of the logical particle in the opportunity cost field in accordance with the principle of least action, which minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change; determine the source corresponding to the end point of the final propagation path as the configuration target of the service request, and determine the final service price based on the kinetic energy consumed by the logical particle along the final propagation path, thereby achieving decoupling of source configuration and price.

[0033] In the specific implementation of the present invention, the propagation process of logical particles refers to having clear discrete scheduling behaviors and operation paths in the system. Once a service request is generated, it is given a resource allocation intention with an initial budget weight. This intention is converted into a series of scheduling attempt actions in the controller logic. The controller calculates the sum of the costs of the service request from the current position to each candidate source based on the current state of the opportunity cost field. The cost mainly includes dimensions such as resource status update delay, scheduling channel queue length estimation, and system load trend feedback. Each step of the scheduling attempt is equivalent to a logical particle jumping in a certain direction once. The path planning process is actually a finite-step search performed by the controller in the logical coordinate grid, and its path selection is based on the target cost. The principle of minimum sum is adopted. At the same time, in order to achieve optimal control of path selection, the present invention introduces the principle of minimum action path into the scheduling engine. The calculation of the action mainly refers to the reachability cost of the source on the request propagation path and the difference in resource scarcity level across the logical distance. This information comes from the system's statistical average of the historical response delay of each source and the resource recovery capability estimation table. Without the help of continuous mathematical formulas, the system maintains a discrete resource response cost table and a set of movement offset rules based on resource level gradients to ensure that each path jump has clear selection logic and execution conditions. It does not rely on an external physical simulation system, and can complete the propagation decision with the shortest path and the best resources.

[0034] Example 1: The present invention provides a method for decoupling source configuration and price based on a dynamic pricing mechanism. By coupling the time recovery entropy (TRE) mechanism with the opportunity cost field, the method optimizes resource allocation decisions and achieves the decoupling of source configuration and service price. The method mainly includes the following steps: determining the time recovery entropy (TRE) for each source in the source pool, which represents the time required for the source to recover from the current task state to the idle state; constructing a dynamic virtual opportunity cost field in the cloud controller based on the time recovery entropy; abstracting service requests into logical particles and giving them initial kinetic energy based on the initial bid, and propagating them in the opportunity cost field; determining the propagation path based on the principle of least action to minimize the amount of action required during the propagation process; determining the final source configuration, and determining the final service price based on the kinetic energy consumption of the logical particles; Time recovery entropy (TRE) is a scalar value that represents the time required for a source to recover from its current service state to an idle state capable of taking on new tasks. This value is calculated based on the recovery time parameter of the source's current task and is updated when the source's task type changes. The main function of this feature is to provide a method for quantifying the flexibility of the source. This indicator can describe the time required for the source to recover from the occupied state of the current task to the idle state, thereby determining the potential energy of the source in the dynamic virtual opportunity cost field. The specific implementation method is that the determination of time recovery entropy is based on the estimated recovery time of the source's current task, such as cache reloading, context switching time, etc., and the accuracy of this value is maintained by regularly updating the source's status through the system. The update frequency of this value is usually set to less than once a minute to reduce computing and communication overhead.

[0035] In the cloud controller, a dynamic virtual opportunity cost field is constructed based on the time recovery entropy value of the information source. This field guides the selection of information sources by reflecting the corresponding potential energy of the recovery entropy of each information source in the virtual potential field. The specific implementation method is that the system periodically collects the time recovery entropy values of all information sources in the information source pool, and uses the inverse distance weighted interpolation algorithm to generate discretized potential field data on the logical grid, thereby forming an opportunity cost field. The design of this potential field can reflect the opportunity cost of resources, so that information sources with high recovery entropy form high potential energy areas, and information sources with low recovery entropy form low potential energy areas, thereby providing flexibility in resource selection; service requests are abstracted as The initial quotation serves as the initial kinetic energy of the propagating logical particles. During particle propagation, the path that minimizes the propagation path is selected by following the principle of minimum action. The total action of this path includes the physical distance cost and the potential energy change cost. Specifically, during the propagation process, logical particles tend to move to areas with lower potential energy and consume their kinetic energy in areas with high potential energy. Through a variant of the A* algorithm, the system combines the cost function of the physical distance cost and the potential energy change cost to quickly determine the optimal path. Finally, when the particle reaches the end point, the source corresponding to the end point is determined as the configuration target of the service request, and the kinetic energy consumption directly corresponds to the final service price. The principle of least action is applied to the path propagation of particles, so that the particles move from the initial point to the end point along the path of least action. This process combines the opportunity cost of resources with the price adjustment factor, avoiding the rigid coupling of traditional pricing and resource allocation. The specific implementation method is that a variant of the A* algorithm is used to determine the minimum action path. The cost function of this path combines the physical distance cost and the potential energy change cost, and the preset coefficient in the cost function adjusts the relative weights of the physical distance cost and the potential energy change cost. This method determines the final service price by calculating the kinetic energy consumed by the particles along the path, thereby naturally integrating the decision-making process of resource allocation and price generation.

[0036] Example 2: In this example, in order to improve the dynamic response capability of resources and reduce the risk of high-flexibility sources being occupied by low-value tasks, the system uses the following five stages to decouple source configuration and price decision-making: First, the system sets and maintains a scalar value called time recovery entropy on the source node side, which is used to quantify the time required for the source node to recover from the current task state to the idle state. The setting basis of this value includes the recovery time parameters preset in the metadata attached to the task, mainly involving indicators such as cache reloading time and context switching time. After normalization, this value is expressed as a unified time scale and is updated at a low frequency when the task type changes, thereby ensuring its stability and practical maintainability at the system level, avoiding the communication and computing overhead caused by frequent state fluctuations; secondly, the cloud controller periodically collects the time recovery entropy value of each node in the source pool, and constructs a dynamic virtual opportunity cost field on the logical topology map. This process is based on a regular logical grid, maps the logical position of the source and its recovery entropy value into potential energy weights, and through The inverse distance weighted interpolation algorithm generates a discretized potential energy field data structure across the entire grid. The distribution characteristics of this potential energy field reflect the opportunity cost levels corresponding to different information sources. Information source regions corresponding to high time recovery entropy values form high potential energy zones, while regions corresponding to low time recovery entropy values form low potential energy channels, providing a quantitative basis for subsequent resource scheduling. Next, after receiving a service request, the system abstracts the request into a logical particle, using the initial bid carried by the request as its initial kinetic energy. The logical particle propagates discretely within the potential energy field, and its propagation path is dynamically determined based on the principle of minimum action. Specifically, each time a particle propagates, the system comprehensively considers the path cost to each neighboring grid point. This cost is composed of the basic cost generated by physical distance and the potential energy change experienced by the jump. To regulate the relative influence of these two costs in path decision-making, the system introduces an adjustable coefficient as a weighting factor. Its value can be configured within a preset range to reflect the platform's preference between resource response flexibility and short-term communication costs.

[0037] Kinetic energy is continuously consumed during particle propagation, and the corresponding path cost is deducted for each jump until the kinetic energy is exhausted or the maximum number of hops allowed is reached. To ensure the efficiency of path calculation, the system uses a variant of the A* algorithm based on a heuristic function to search for the path. The heuristic function design uses the logical distance between the current position of the particle and the low potential energy area as the estimation indicator, thereby seeking the global optimal solution for the path between resource cost and opportunity value; after the particle propagation is completed, the system uses the source node corresponding to its final landing point as the resource allocation target for the service request, and determines the final settlement price based on the difference between the kinetic energy consumption of the particle in the path and its initial quotation. Since high potential energy areas will cause the logical particle kinetic energy to decay rapidly, the source with a high recovery entropy value forms a natural damping effect in the price mechanism, making it difficult to achieve path arrival when the demand for scarce resources is not supported by high quotations, thereby effectively avoiding the irrational occupation of highly flexible resources in traditional solutions. The present invention maps task scheduling decisions into particle propagation path calculations and embeds the pricing mechanism into the physical potential field construction, thereby achieving adaptive decoupling of signal source selection and service pricing, helping to improve the stability and response efficiency of resource scheduling, and having the ability to expand to multiple application scenarios such as edge computing and multi-tenant scenarios.

[0038] Example 3: This example aims to verify the source configuration and price decoupling method based on the dynamic pricing mechanism disclosed in the present invention, and its effectiveness in improving the system's responsiveness to high-value tasks and optimizing resource allocation efficiency; the experiment is carried out in a cloud-native computing platform, which includes a cloud controller and a group of heterogeneous source nodes. The source node types include: computing source nodes (based on container technology, suitable for short-term high-concurrency tasks), storage source nodes (simulating distributed storage services, focusing on data persistence and access performance), and hybrid source nodes (integrating computing and storage capabilities, with a certain degree of flexibility).

[0039] The parameters are set as follows: Each source in the source pool is configured with time recovery entropy (TRE), which is a scalar value used to characterize the time required for the source to be released from the current service state and restored to an idle state that can undertake any type of new task. The determination of this value is based on the estimated recovery time parameters of the task currently carried by the source, such as cache reloading time or context switching time; in this experiment, for different task types, the recovery time parameters can be reasonably set based on the statistical analysis of historical task data and engineering experience. For example, high real-time business tasks can be set to lower recovery time parameters (such as about 50 milliseconds), while AI model training tasks can be set to lower recovery time parameters (such as about 50 milliseconds). The recovery time parameter is set to a relatively high value (such as about 500 milliseconds). The value of the time recovery entropy is updated at a low frequency only when the type of task carried by the source changes. The update frequency is usually less than once a minute to effectively control the computing and communication overhead. The cloud controller periodically collects the time recovery entropy values of all sources in the source pool, and generates discretized potential field data on the logical grid through the inverse distance weighted interpolation algorithm, combined with the logical position of the source node, to form a dynamic virtual opportunity cost field. The time recovery entropy value of the source determines its corresponding potential energy in the opportunity cost field. The relative weight of the physical distance cost and the potential energy change cost is determined by the preset coefficient Make adjustments, the The value can be configured and adjusted based on the system's preference for future responsiveness and short-term benefits. It can be set within a range of 0.1 to 100 based on actual needs to balance physical distance with the value of future flexibility. A service request is abstracted as a logical particle carrying an initial bid. The initial bid serves as the initial kinetic energy for the logical particle to propagate in the opportunity cost field. During propagation, the logical particle tends to move toward areas of lower potential energy in the opportunity cost field. When crossing areas of higher potential energy, its kinetic energy is consumed. The logical particle follows the principle of least action in the opportunity cost field to determine its final propagation path. The principle of least action minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change. Path search is performed using a variant of the A* algorithm, whose cost function incorporates physical distance cost and potential energy change cost. Ultimately, the source corresponding to the final propagation path is determined as the configuration target for the service request. The final service price is determined based on the kinetic energy consumed by the logical particle along the final propagation path, thereby decoupling source configuration from price.

[0040] The experiment is divided into two phases: benchmark testing and verification of the method of the present invention. In this phase, a traditional direct mapping mechanism based on real-time load indicators (such as CPU utilization and network traffic) is used to build price signals. The system selects sources and generates prices based on the current load situation. The test scenario simulates an environment with gradually increasing load. Initially, low-value, long-running data cleaning tasks are mainly deployed, and then high-priority, high-value tasks with high real-time requirements are gradually introduced, such as high-real-time business tasks. In this phase, the focus is on the response delay and resource allocation efficiency of the system in processing high-value tasks under high load. In this phase, the dynamic pricing mechanism based on time recovery entropy and opportunity cost field proposed in this invention is enabled. The test scenario is consistent with the benchmark test to ensure the fairness of the comparison. In this phase, the focus is on observing the response performance of the system in processing high-value tasks under high load.

[0041] By comparing the data from the benchmark test and the verification phase of the method of the present invention, the following phenomena and trends were observed: in the simulation of high-concurrency, high-real-time business scenarios, the average allocation delay of high-value tasks in the system using the method of the present invention was perceptibly lower than that of the traditional coupling pricing mechanism under the benchmark test. This improvement is mainly due to the fact that the present invention quantifies the future flexibility value of the information source through time recovery entropy, and represents the high-flexibility information source as a high-potential energy area in the opportunity cost field. Logical particles (service requests) tend to avoid high-potential energy areas during the propagation process, thereby guiding high-value tasks to more suitable resources, so as to reserve key resources to cope with sudden high-value tasks. The results of the observations It shows that after the application of the method of the present invention, the situation in which the high time recovery entropy signal source is deeply occupied by low-value tasks during the high-load period of the system is reduced. The analysis of the service request propagation path shows that logical particles carrying higher initial kinetic energy (high priority) can complete the crossing by consuming kinetic energy even in the face of some high potential energy areas, but their final service price will reflect the cost of occupying high-flexibility resources. Logical particles carrying lower initial kinetic energy (low priority) are more inclined to choose low potential energy areas, that is, signal sources that are currently idle and have lower recovery entropy, thereby reducing resource competition with high-value tasks. This dynamic guidance mechanism helps to improve the strategic flexibility of resource scheduling. Experimental results show that the present invention abstracts service requests into logical particles and propagates them in the opportunity cost field according to the principle of least action, thereby integrating the source selection and price generation processes into a unified physical field movement. The kinetic energy consumed by the logical particles along the path is combined with the initial quotation to naturally generate the final service price. This automatic price adjustment forms a price damping effect, which helps to curb blind competition for scarce and flexible resources, thereby enabling the system to achieve market equilibrium in a dynamic environment. Compared with traditional dynamic pricing methods that require continuous monitoring of multi-dimensional indicators and frequent updates, the present invention only requires low-frequency updates of a single scalar value time recovery entropy on the source node side, and the cloud controller periodically constructs the opportunity cost field, which helps to reduce the computing overhead and communication burden on the source node side, and is particularly suitable for large-scale, edge deployment needs.

[0042] Example 4: This example combines Figures 1 to 3 , the method and system for decoupling source configuration and price based on dynamic pricing mechanism are described. Figure 1As shown in the figure, the time recovery entropy (TRE) module first determines the time required for a source to recover to an idle state, and a low-frequency update mechanism is adopted to reduce system overhead. On this basis, the system constructs a virtual opportunity cost field, in which TRE determines the potential energy, so that sources with high TRE form high-potential energy areas and sources with low TRE form low-potential energy channels. Inverse distance weighted interpolation is used to achieve spatial continuity of the potential field. Subsequently, service requests are abstracted into logical particles, which carry initial bids and serve as initial kinetic energy to enter the virtual opportunity cost field. They move in a physically simulated manner in the propagation environment. The propagation of particles follows the principle of least action, which is optimized through a variant of the A* algorithm and a composite cost function to minimize the total path action. The cloud controller tracks the logical particles, determines the paths, and calculates the costs. Based on the movement results of the logical particles, the system ultimately completes the two tasks of source configuration and dynamic pricing. Source configuration implements the decoupling of destination source selection and adaptiveness, while dynamic pricing calculates the price by kinetic energy consumption and reflects the price damping effect, effectively preventing high-value resources from being occupied by low-value tasks.

[0043] like Figure 2 As shown in the figure, the vertical axis is service requests, including high-value request A, high-value request B, high-value request C, low-value request D, low-value request E and low-value request F; the horizontal axis is price (unit: cost), with a scale from 0 to 180. The figure also distinguishes the three elements of allocated source type, price type and price: among them, high-TRE sources are represented by solid lines, low-TRE sources are represented by dotted lines, initial quotations are represented by solid dots, and final prices are represented by diamond symbols. High-value requests A, B, and C tend to be allocated to high-TRE sources, and their price curves are solid lines, which show that the kinetic energy consumption is higher based on the initial quotation, and the corresponding final prices are much higher than the initial values; while low-value requests D, E, and F are more allocated to low-TRE sources, and their price curves are dotted lines, with relatively less kinetic energy consumption, and the final prices have limited differences from the initial quotations.

[0044] like Figure 3As shown, first, the cloud controller activates the logical particles (injects logical particles with initial kinetic energy) and calls the path planning engine (variant A) to initiate path cost evaluation, that is, requesting the path costs of adjacent nodes. In the subsequent path traversal, the logical particles judge in turn whether they are crossing a high potential energy area or a low potential energy area. The former will return a high path cost and trigger a large consumption of particle kinetic energy, while the latter will return a low path cost and trigger a small consumption of particle kinetic energy. After the path traversal is completed, the path planning engine (variant A) returns the optimal path and total kinetic energy consumption to the cloud controller. The cloud controller executes the path scheduling and price generation process based on the path division results; then enters the parallel processing (execution processing) stage, initiates a request to calculate the final service price in the price generation module, and outputs the final service price based on the calculation of kinetic energy consumption and initial quotation. At the same time, the cloud controller issues a target resource allocation instruction based on the path endpoint, and confirms the configuration success at the target source end.

[0045] Example 5: In the edge intelligent platform, the system needs to dynamically respond to a large number of real-time data processing requests from various emergency subsystems, including streaming analysis of public security surveillance videos, road traffic congestion prediction, emergency image recognition and other tasks. The platform is deployed on multiple physical area nodes, and each node has a source pool composed of several virtualized computing resources. The source types include container-type resource nodes, edge micro-server nodes and lightweight computing power units. Each source has heterogeneous performance and task adaptability. This example focuses on describing the scheduling process of the system in processing an emergency traffic accident image recognition request scenario, and demonstrates how the dynamic pricing mechanism driven by time recovery entropy of the present invention can coordinate with the source configuration logic to operate efficiently and ensure the natural decoupling of price signals and resource selection.

[0046] When the platform detects an emergency, it will automatically generate an image recognition service request marked as high priority, and attach initial budget information, which will be uploaded to the cloud controller through the edge node. The controller will abstract the request into logical particles in real time to start the scheduling process. Its initial kinetic energy is the kinetic energy scalar mapped by the system to the budget value according to the standard conversion factor. The selection of this mapping factor is combined with the historical scheduling cost range of this platform and the estimation of the average path consumption of emergency task processing to ensure that the logical particles have enough kinetic energy to pass through some high potential energy areas without wasting resources. At this time, the status of the source pool in the platform has been reported to the controller at a low frequency by the source node side. The key indicator is the time recovery entropy. The entropy value is obtained according to the type of current task on the node and the typical estimation table established by the historical task state transition delay samples. Specifically, The class task defines an expected recovery delay value, and the cache release delay and context cleanup time are integrated and normalized according to the weight to form a unified measurement indicator. The weight value is seven to three, which is an empirical setting based on the retrospective analysis of task scheduling within the system, which shows that the release of cache items in typical container-type nodes has a greater impact on the scheduling delay of new tasks. The controller constructs a virtual opportunity cost field in the logical space based on the time recovery entropy values held by all source nodes. The field is expressed as a logical grid, and each grid point corresponds to one or more source nodes. Its potential energy value is the mean or weighted value of the time recovery entropy of the source in the grid point. To achieve spatial continuity, the controller uses the inverse distance weighted interpolation algorithm to fill in areas without direct data points, so that the entire potential field has a computable gradient feature, thereby having directional selectivity when guiding the propagation path of logical particles. During the propagation process, each time a logical particle jumps a grid, it has to pay a propagation path cost. This cost is composed of the physical jump distance and the potential energy change. The physical jump is a unit distance constant, and the potential energy change is determined by the potential energy difference between the current and target grid points. The system has an adjustment coefficient to balance the influence of the two on the propagation direction decision. This coefficient is preset to 20 in this scenario. The selection of this value is verified by the platform through simulation of a large number of historical behaviors of emergency request scheduling. It aims to suppress the risk of particles crossing high potential energy areas in the early stage, resulting in rapid consumption of kinetic energy, thereby retaining greater path flexibility to cope with diverse target choices.

[0047] The path planning of logical particles is performed by a path search module driven by a heuristic function in the controller. The heuristic function is based on the logical grid distance estimation between the current position of the particle and the lowest potential energy point. The path search algorithm is a simplified variant of the A* algorithm, which removes the high dependence on the path pruning strategy to accelerate the response of high-priority tasks. This design takes into account that in emergency task scenarios, the search response delay takes priority over the path optimality guarantee. Platform tests show that after removing the pruning mechanism, the system search delay drops by about 30%, and the performance loss is within an acceptable range. The final end point of the particle path falls on a lightweight computing power node with low time recovery entropy in a certain area. The current task of this node is low-priority log analysis, and its estimated cleanup time is extremely short. Therefore, it appears as a low potential energy point when constructing the potential field, and the particle landing point is the service The controller sends a scheduling instruction to the target source based on the configuration target of the service request. At the same time, it calculates the total kinetic energy loss of the particles in the path according to the total potential energy increase and physical distance experienced by the particles. The system subtracts the loss value from the remaining kinetic energy under the original quotation mapping relationship to obtain the actual price output. This price is the service fee and is recorded synchronously by the system for modeling the perception of price fluctuation trends in subsequent scheduling behaviors. It should be pointed out that in order to enhance the adaptability of this mechanism in different scenarios, the system also monitors the particle kinetic energy decay rate during the path planning process. When the system recognizes that the kinetic energy consumption rate is too fast and the particles have not yet entered the low potential energy band, it automatically triggers a secondary path re-exploration mechanism. This mechanism expands the reachable area by reducing the adjustment coefficient, allowing particles to jump back, and other strategies to avoid scheduling failures of high-priority tasks due to resource stickiness.

[0048] Example 6: In this example, when constructing a logical particle path propagation model, the path cost is composed of a physical distance cost and a potential energy change cost. The physical distance cost is used to measure the basic communication cost required for each hop of a service request in a logical grid. The cost can be set based on engineering experience such as the average hop delay of the network topology or the fixed transit time between nodes. It does not rely on real-time monitoring values and only requires static configuration of the logical structure during deployment. It has engineering simplicity and scenario adaptability. The potential energy change cost is directly related to the time recovery entropy value held by the source node, and is manifested as the indirect cost of a service request in the process of crossing different resource flexibility levels, reflecting the internal resource protection mechanism built by the system to maintain the availability of key resources. In the path cost In the price function, in order to achieve a dynamic balance between the above two types of costs, an adjustable proportional coefficient is introduced to reflect the platform's preferred configuration of future responsiveness and current communication efficiency under different operating strategies. In actual use, the value of this coefficient is not the only optimal one. Instead, it is set by the administrator within a preset range in the initial stage of system launch based on the platform design goals and load characteristics. It can also be periodically adjusted based on platform operation feedback. In actual engineering implementation, the basis for setting this coefficient may include the path cost distribution of historical tasks, node resource scheduling offset statistics, or path fluctuation stability of typical service types. However, it does not rely on real-time training or external algorithm support and can be statically loaded by the system management logic to ensure low complexity and high certainty in deployment and operation and maintenance.

[0049] In order to avoid parameter mismatch during the actual deployment process, the system maintains a unified measurement scale for various parameters and adopts a normalization strategy in the path cost calculation to unify all cost factors into a dimensionless ratio system, so that the propagation process of logical particles can maintain consistent control logic under any topological scale. The path search module does not rely on the precise comparison of absolute cost values, but uses a heuristic estimation function to evaluate the remaining propagation distance and potential energy gradient, thereby ensuring that even in the case of short-term fluctuations in the status of some nodes, the system can still output the resource allocation path with a stable strategy to avoid the problem of violent path oscillation or premature exhaustion of kinetic energy of particles. In addition, the particle propagation terminal is also checked during the implementation process. The point determination method is designed with a mechanism. After the path planning is completed, the system not only configures the service according to the source node corresponding to the final landing point of the logical particle, but also synchronously records the total amount of logical kinetic energy consumed by the particle during the propagation process. This total amount is obtained by deducting the path propagation cost from the initial budget value. The system generates the final service settlement price based on this, so that the price generation and path propagation have a consistent internal logic. This logic is reflected at the mechanism level as pricing feedback on the consumption of resource flexibility by service requests, so that the use of high-flexibility resources is superimposed with a natural inhibition mechanism, thereby controlling the allocation rhythm of high-value resources through path planning itself and constructing a price damping effect within the system.

[0050] Example 7: This example further illustrates how the present invention ensures that the globally optimal source configuration target is found during the logical particle path planning process. For example, after a service request is abstracted as a logical particle carrying initial kinetic energy and enters the dynamic virtual opportunity cost field, determining its propagation path is key to decoupling source configuration from dynamic pricing. Specific optimization strategies include: First, a multi-path parallel evaluation mechanism was introduced. When a logical particle faces multiple optional path branches at a certain node, the system does not immediately select the single path that currently appears to be the best. Instead, it simultaneously evaluates and tracks several suboptimal paths within a certain range, for example, based on a preset path exploration breadth coefficient. This parallel tracking allows particles to follow the general trend toward low-potential energy areas during initial exploration, while retaining the possibility of exploring nearby high-potential energy areas that may lead to more optimal global low-potential energy channels. Ultimately, the path with the lowest total action among all tracked paths is determined as the final globally optimal propagation path. Secondly, the heuristic function of the A* algorithm can be optimized with global potential gradient guidance. The traditional heuristic function may focus more on estimating the physical distance from the current position to the target point. In the present invention, the potential energy distribution trend of the global opportunity cost field is integrated into the heuristic function, so that it is not only an estimate of the physical distance, but also a prediction of the direction of the potential energy depression. For example, the heuristic function will combine the average potential energy of the current area, the average potential energy of the target source, and the logical topology to guide the particles to the direction that is more likely to lead to a large area of low potential energy, even if this may mean crossing a small area of high ground in the short term. Furthermore, in order to deal with extreme situations, for example, a dynamic adjustment and backtracking mechanism can be used. If the kinetic energy consumption rate of the logical particle is abnormally fast during the path propagation process, indicating that it may fall into a high potential energy quagmire, the system will trigger a dynamic adjustment logic. At this time, you can temporarily reduce The weight of the particle is set, or the particle is allowed to make limited backtracking attempts to re-explore different path branches. This dynamic adaptability ensures that even if the initial path selection is not ideal, the system still has the opportunity to correct errors and re-find the global optimal path.

[0051] On the Cost Function in the Principle of Least Action In the composition of It represents the physical distance cost, specifically the basic resource overhead required for each jump of a logical particle in the virtual field. It can be regarded as communication delay, scheduling link occupancy, or consumption of basic computing resources. This cost is usually relatively stable and can be set empirically according to the logical topology and network performance during system deployment. This ensures that when resource availability is similar, the system will give priority to signal sources with closer distances and higher transmission efficiency.

[0052] The cost of potential energy change is quantified. It is the total potential energy change experienced by the logic particle along its propagation path. It directly comes from the potential energy determined by the time recovery entropy of the signal source. When the logic particle passes from a low potential energy area to a high potential energy area, it occupies a currently busy signal source with a long recovery time. The value is positive and large, which will make the total action The significant increase intuitively reflects the additional burden brought by occupying the high opportunity cost signal source. On the contrary, if the particles mainly move in the low potential energy area, If the value is small or even negative (if the potential energy decreases), its contribution to the total action is also small.

[0053] is a preset adjustment coefficient, which is used to balance the relative weights of physical distance cost and potential energy change cost in path decision making. When the value is high, the system will pay more attention to the future flexibility value of the source and tend to avoid high potential energy areas, even if it means the physical distance will be slightly longer; on the contrary, when When it is low, the physical distance cost becomes dominant, and the system may be more inclined to choose the nearest source even if its opportunity cost is slightly higher. Therefore, the cost function It is not just a simple addition. By assigning weights to the potential energy changes, the system can endogenously consider and quantify the opportunity cost implied by occupying the source when selecting the source for the service request. The kinetic energy consumed by the logical particle along the path is the total action of the path. This mechanism ensures the occupation of information sources with high opportunity costs (high time recovery entropy) and will provide feedback through higher kinetic energy consumption and final prices, thereby forming an adaptive price damping effect, effectively guiding resource demand and avoiding the unreasonable occupation of high-value resources by low-value tasks. These are all extended implementation methods known to ordinary technicians in this field.

[0054] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for decoupling information source configuration and price based on a dynamic pricing mechanism, characterized in that: The method comprises the following steps: Step a: For each source in the source pool, determine a time recovery entropy. The time recovery entropy is a scalar value that represents the time required for the source to be released from its current service state and restored to an idle state capable of accepting new tasks of any type. The determination of the time recovery entropy is based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes. Step b: constructing a dynamic virtual opportunity cost field in the cloud controller based on the time recovery entropy value of the information source, wherein the time recovery entropy value determines the potential energy corresponding to the information source in the opportunity cost field; Step c: When a service request and its initial quote are received, the service request is abstracted into a logical particle, the initial quote carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; Step d: Determine the final propagation path of the logical particle in the opportunity cost field according to the principle of least action. The principle of least action minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change. In step e, the information source corresponding to the end point of the final propagation path is determined as the configuration target of the service request, and the final service price is determined according to the kinetic energy consumed by the logic particles along the final propagation path.

2. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The determination of the time recovery entropy in step a is based on the estimated recovery time contained in the metadata of the task currently carried by the source; the estimated recovery time is a predefined value that can indicate the reload time or context switching time after the cache is invalidated, and the time recovery entropy value is updated less than once per minute.

3. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The construction of the dynamic virtual opportunity cost field in step b includes: the cloud controller periodically collects the time-recovery entropy values of all sources in the source pool, and uses the inverse distance weighted interpolation algorithm to generate discretized potential field data on the logical grid according to the time-recovery entropy values of the sources and their logical positions to form an opportunity cost field.

4. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The propagation rule of the logical particles in the opportunity cost field in step c is: the logical particles tend to move to the area with lower potential energy in the opportunity cost field; when the logical particles pass through the area with higher potential energy during the propagation process, their kinetic energy is consumed.

5. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The final propagation path that follows the principle of least action in step d is found by a variant of the A-star algorithm, where the cost function of the A-star algorithm is Incorporating physical distance costs and potential energy change costs , and the relationship can be expressed as: ， in, To adjust the preset coefficients of the relative weights of physical distance cost and potential energy change cost, is the total potential energy change experienced by the logical particle along the path.

6. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 5, characterized in that: It is a preset coefficient, and its value range is from 0.1 to 100.

7. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The determination of the final service price includes combining the kinetic energy consumed by the logic particles along the final propagation path with the initial bid of the service request to obtain the final settlement price.

8. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The signal sources in the signal source pool include virtual machines, containers, physical servers, and network slice resource units; the types of service requests include data cleaning tasks, AI model training tasks, data analysis tasks, and high-real-time business tasks.

9. The method for decoupling information source configuration and price based on a dynamic pricing mechanism according to claim 1, characterized in that: The source node only maintains a scalar value, the time recovery entropy, and the update of the scalar value is only triggered when the task type carried by the source changes.

10. A system for decoupling information source configuration and price based on a dynamic pricing mechanism, characterized in that: The system comprises: The source node is configured to determine and maintain a time recovery entropy, which is a scalar value used to represent the time required for the source to be released from the current service state and restored to an idle state capable of accepting new tasks of any type. The time recovery entropy is determined based on the estimated state recovery time parameter of the task currently carried by the source, and the value of the time recovery entropy is only updated at a low frequency when the type of task carried by the source changes; The cloud controller is in communication with the source node and is configured to: construct a dynamic virtual opportunity cost field based on the time-recovery entropy value of the source node, wherein the time-recovery entropy value determines the potential energy corresponding to the source in the opportunity cost field; when a service request and its initial quotation are received, the service request is abstracted into a logical particle, and the initial quotation carried by the logical particle is used as its initial kinetic energy, and propagated in the opportunity cost field; determine the final propagation path of the logical particle in the opportunity cost field in accordance with the principle of least action, which minimizes the total action of the final propagation path, which includes the action of physical distance and the action of potential energy change; determine the source corresponding to the end point of the final propagation path as the configuration target of the service request, and determine the final service price based on the kinetic energy consumed by the logical particle along the final propagation path.

Images