AI-based intelligent park housing operation strategy optimization method

Abstract

The application discloses an AI-based intelligent park house source operation and maintenance strategy optimization method, and relates to the field of artificial intelligence strategy optimization. The method comprises the following steps: collecting house source structure density, facility composite grade, historical operation and maintenance events and function switching data to form a basic attribute set; generating a house source joint complexity index based on the attribute set; calculating the state disturbance amplitude and combining the complexity index to generate a risk response sensitive factor; generating a future use trend factor based on historical data, combining the resource pool state to form a resource tension index; generating a scheduling priority threshold by comprehensively combining the above factors; fusing multi-strategy scheduling results, priority and index to output control instructions; collecting execution feedback to build a bias evaluation factor, adjusting the fusion parameters to realize strategy self-adaptive evolution. Through multi-dimensional data fusion to build comprehensive indexes, the resource load is scientifically evaluated, and combined with multi-strategy fusion mapping, the precision, efficiency and intelligence of house source operation and maintenance scheduling are realized.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence strategy optimization, specifically to an AI-based method for optimizing the operation and maintenance strategies of smart park properties. Background Technology

[0002] With the rapid development of smart parks, the operation and maintenance management of properties within the parks has become a crucial aspect of ensuring their stable and efficient operation. Traditional property operation and maintenance methods rely heavily on manual experience and static rules, making it difficult to dynamically adapt to the complex and ever-changing park environment and multi-dimensional operation and maintenance needs. This leads to problems such as uneven resource allocation, low operation and maintenance efficiency, and slow risk response.

[0003] Currently, most existing operation and maintenance management solutions focus on the analysis of a single data dimension, such as monitoring energy consumption or equipment status, lacking a comprehensive assessment of the complexity of the building's internal structure, the interconnection of facilities, and the switching behavior of multiple functions. Furthermore, existing operation and maintenance strategies typically fail to fully utilize the temporal characteristics of historical operation and maintenance events and function switching trajectories, making it difficult to accurately predict future resource demands and usage trends, and thus unable to achieve dynamic optimization and scheduling of resources.

[0004] Meanwhile, regarding risk control in property operation and maintenance, most methods lack dynamic comparative analysis of the latest and historical operational statuses, failing to effectively capture changes in status disturbances and their impact on operational risks, resulting in insufficient risk response capabilities. In terms of resource scheduling, existing technologies fail to comprehensively consider the combined impact of resource pool status and property usage evolution paths, and resource tension assessment lacks scientific structural fusion model support.

[0005] At the strategy fusion level, existing solutions typically use fixed weights or simple weighting to merge the scheduling results of multiple strategies. They lack a feedback-based adaptive adjustment mechanism, which makes it impossible to achieve dynamic optimization and evolution of scheduling strategies, thus affecting the overall intelligence level and responsiveness of the operation and maintenance system.

[0006] Therefore, there is an urgent need for an AI-based method to optimize the operation and maintenance strategy of housing resources in smart parks. This method should be able to systematically collect multi-dimensional attributes and historical operation and maintenance data of housing resources, construct comprehensive housing resource complexity indicators and risk response factors, scientifically assess resource tension, and combine multi-strategy integration and dynamic feedback adjustment to achieve intelligent optimization and adaptive evolution of housing resource operation and maintenance strategies, thereby improving the accuracy, efficiency and robustness of housing resource management in smart parks. Summary of the Invention

[0007] Based on the shortcomings of the existing technology described above, the purpose of this invention is to provide an AI-based smart park property management strategy optimization method to solve the aforementioned technical problems.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an AI-based smart park property management strategy optimization method, comprising:

[0009] Collect structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data of housing units in the smart park to form a set of basic housing attributes;

[0010] Based on the basic attribute set of housing resources, feature coupling transformation is performed on structural density factor, facility composite factor and behavioral distribution factor to generate housing resource joint complexity index.

[0011] Based on the operating status parameters of the latest cycle and historical cycles, the state disturbance amplitude is calculated, and the disturbance amplitude is combined with the housing joint complexity index to generate a housing risk response sensitivity factor.

[0012] Based on historical operation and maintenance event sequences and function switching trajectories, future usage trend factors are generated. At the same time, resource pool status is collected to generate resource density index. The future usage trend factors and resource density index are combined to generate housing scheduling resource tension index.

[0013] By combining housing risk response sensitivity factors, housing scheduling resource tension indicators, and housing joint complexity indicators, a housing scheduling priority threshold is generated to prioritize scheduling requests.

[0014] The scheduling results of path optimization strategy, risk avoidance strategy and resource balancing strategy are integrated with housing scheduling priority threshold, risk response sensitivity factor and resource tension index to output housing control instructions;

[0015] The system collects the execution results and actual status feedback of housing control commands, constructs feedback deviation evaluation factors, and adjusts the strategy fusion control parameters based on the feedback deviation evaluation factors to achieve adaptive evolution of the strategy model.

[0016] The present invention is further configured such that the basic attribute set of the housing resources includes structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data, wherein:

[0017] The structural density parameter is used to characterize the distribution density of the subsystem layout within a building;

[0018] The facility composite level parameter is used to reflect the degree of functional integration and the complexity of the interconnection structure among the multifunctional facilities in the housing configuration;

[0019] Historical maintenance event sequences are used to record the types of maintenance operations, time points, and event frequencies of properties over multiple periods;

[0020] Function switching trajectory data is used to characterize the transition path and temporal sequence of each functional state of a property during continuous use.

[0021] The present invention is further configured such that the housing resource joint complexity index is generated by feature coupling of structural density factor, facility composite factor and behavioral distribution factor, wherein:

[0022] The structural density factor is constructed based on the arrangement relationship between the internal spatial structure and component units of the building;

[0023] The facility integration factor is constructed based on facility function categories, quantity levels, and interaction relationships;

[0024] The behavior distribution factor is constructed based on the frequency of behavior, function activity, and transfer intensity in historical operation and maintenance event sequences and function switching trajectories;

[0025] The three factors are combined into a unified property joint complexity index through a combination mapping method, which is used to characterize the overall complexity of property in terms of structure, configuration and behavior.

[0026] The present invention is further configured such that the generation of housing risk response sensitivity factors includes:

[0027] Obtain the operating status parameters of smart park housing units in the latest cycle and a historical cycle. The operating status parameters include energy consumption density, temperature control load, environmental disturbance response and usage activity saturation ratio.

[0028] Based on the operating state parameters, construct a state change relationship structure and extract the current cycle state differences and historical cycle change trends;

[0029] Construct the state perturbation amplitude based on the state differences;

[0030] The magnitude of state disturbance is correlated with the joint complexity index of housing resources to generate a risk response sensitivity factor that characterizes the dynamic risk response level of housing resources.

[0031] The present invention is further configured such that the generated housing resource scheduling tension index includes:

[0032] Based on the operation and maintenance event sequence and function switching trajectory of a property within a preset number of historical periods, the frequency of function status switching, the duration of status and the event time density are extracted to construct the evolution path of property function usage.

[0033] Based on the evolution path of housing function usage and the resource consumption characteristics of each functional state, generate usage trend factors of various resources of housing in the future cycle;

[0034] Collect the distribution structure, allocation ratio, occupancy structure and surplus status of resources in the current resource pool, and extract the resource density index to characterize the resource utilization tension.

[0035] By structurally integrating the future resource usage trend factor of housing resources with the resource density index, a housing resource scheduling tension index is generated, which is used to characterize the resource load intensity corresponding to scheduling requests.

[0036] The present invention is further configured such that the construction of the housing resource function using the evolution path is based on a time slice sequence, and the operation and maintenance events and function switching behaviors are divided into equal time intervals.

[0037] The functional state transition behavior within each time period is structurally labeled, and high-frequency transition structures in the functional evolution path are extracted by the density sequence and path coupling sequence of state transition nodes.

[0038] Resource mapping and identification are performed on path segments based on the resource consumption gradient of functional status.

[0039] The present invention is further configured such that the generated housing allocation scheduling priority threshold includes:

[0040] Based on the structural coupling relationship between housing risk response sensitivity factors, housing scheduling resource tension indicators, and housing joint complexity indicators, a nonlinear fusion driving factor is constructed to express the priority driving intensity of housing scheduling needs.

[0041] By introducing a historical periodic state perturbation structure and extracting the perturbation trend sequence, a scheduling evolution response potential is constructed to characterize the periodic evolution of scheduling demand.

[0042] By combining the nonlinear fusion driving factor and the scheduling evolution response potential, a housing scheduling priority threshold is generated, which serves as the basis for ranking housing scheduling requests.

[0043] The present invention is further configured such that the output housing control command includes:

[0044] Obtain the housing allocation results corresponding to the path optimization strategy, risk avoidance strategy, and resource balancing strategy;

[0045] Collect housing allocation priority thresholds, housing risk response sensitivity factors, and housing allocation resource tension indicators;

[0046] A fusion structure model is constructed based on the results of the three types of strategies and scheduling indicators to form a multi-strategy joint scheduling mapping relationship;

[0047] The joint scheduling mapping relationship is structurally integrated to generate housing control instructions, which are used to indicate the execution path of housing operation and maintenance behavior under multiple policy conditions.

[0048] The present invention is further configured such that the adaptive evolution of the implementation strategy model includes:

[0049] Collect the execution results and actual status feedback information after the control commands for each property are issued;

[0050] Based on the execution results and the pre-control state, a feedback deviation structure is constructed, and a feedback deviation evaluation factor is generated.

[0051] Model the deviation correlation between the feedback deviation evaluation factor and the fusion output of multiple scheduling strategies, and extract the deviation response performance of each strategy in the current period.

[0052] The strategy integrates control parameters based on deviation response performance, updates control factors in the strategy model, and inputs the updated parameters into the next scheduling cycle to achieve the adaptive evolution process of the strategy model.

[0053] The present invention is further configured such that the construction of the feedback deviation evaluation factor adopts a path-by-path difference extraction method, and after collecting the control execution status feedback, the feedback status is compared with the scheduling intensity structure generated by the initial scheduling strategy at the path level.

[0054] A feedback deviation structure is constructed based on the degree of difference in path execution. Structural difference segments are extracted from the feedback deviation structure as a subset of deviation features. Various strategy control factors are then adjusted in a targeted manner based on the subset of deviation features.

[0055] This invention provides an AI-based method for optimizing the operation and maintenance strategy of housing units in smart parks. The method collects structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data of housing units within the smart park to form a basic attribute set for the housing units. Based on this basic attribute set, feature coupling transformation is performed on structural density factors, facility composite factors, and behavioral distribution factors to generate a joint complexity index for the housing units. According to the latest and historical periodic operating status parameters, the state disturbance amplitude is calculated, and the disturbance amplitude is combined with the joint complexity index to generate a housing unit risk response sensitivity factor. Future usage trend factors are generated based on historical operation and maintenance event sequences and function switching trajectories, while simultaneously collecting resource pool status data. A resource density index is generated, and future usage trend factors are combined with the resource density index to produce a housing resource scheduling tension index. A housing scheduling priority threshold is generated by combining housing risk response sensitivity factors, housing scheduling resource tension index, and housing joint complexity index to prioritize scheduling requests. The scheduling results of path optimization strategies, risk avoidance strategies, and resource balancing strategies are fused with the housing scheduling priority threshold, risk response sensitivity factors, and resource tension index to output housing control commands. The execution results and actual status feedback of the housing control commands are collected to construct a feedback deviation assessment factor. Based on the feedback deviation assessment factor, the strategy fusion control parameters are adjusted to achieve adaptive evolution of the strategy model. The beneficial effects include:

[0056] 1. Multi-dimensional attribute fusion to enhance the ability to characterize property complexity: By collecting and fusing multi-dimensional parameters such as structural density, facility composite level and behavior distribution, a joint property complexity index is constructed to achieve a comprehensive characterization of the internal structure and operation and maintenance behavior of the property, thereby improving the pertinence and accuracy of operation and maintenance strategies.

[0057] 2. Scientific resource tension assessment and optimized resource allocation: Based on the evolution path of housing function and resource pool status, and by integrating future usage trend factors and resource density index, a resource tension index is constructed to accurately characterize the resource load intensity and promote the rational allocation and efficient utilization of resources.

[0058] 3. Multi-strategy fusion mapping enhances the comprehensiveness of scheduling decisions: By integrating path optimization, risk avoidance, and resource balancing strategies with scheduling indicators, a multi-strategy joint scheduling mapping relationship is constructed to achieve refined generation of housing control instructions and improve the rationality and flexibility of operation and maintenance execution paths.

[0059] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] In the attached diagram:

[0062] Figure 1 The flowchart illustrates an AI-based smart park property management strategy optimization method as an exemplary embodiment of the present invention. Detailed Implementation

[0063] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0064] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0065] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0066] Example 1:

[0067] AI-based optimization methods for smart park property operation and maintenance strategies, such as Figure 1 As shown, it includes:

[0068] Collect structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data of housing units in the smart park to form a set of basic housing attributes;

[0069] Based on the basic attribute set of housing resources, feature coupling transformation is performed on structural density factor, facility composite factor and behavioral distribution factor to generate housing resource joint complexity index.

[0070] Based on the operating status parameters of the latest cycle and historical cycles, the state disturbance amplitude is calculated, and the disturbance amplitude is combined with the housing joint complexity index to generate a housing risk response sensitivity factor.

[0071] Based on historical operation and maintenance event sequences and function switching trajectories, future usage trend factors are generated. At the same time, resource pool status is collected to generate resource density index. The future usage trend factors and resource density index are combined to generate housing scheduling resource tension index.

[0072] By combining housing risk response sensitivity factors, housing scheduling resource tension indicators, and housing joint complexity indicators, a housing scheduling priority threshold is generated to prioritize scheduling requests.

[0073] The scheduling results of path optimization strategy, risk avoidance strategy and resource balancing strategy are integrated with housing scheduling priority threshold, risk response sensitivity factor and resource tension index to output housing control instructions;

[0074] The system collects the execution results and actual status feedback of housing control commands, constructs feedback deviation evaluation factors, and adjusts the strategy fusion control parameters based on the feedback deviation evaluation factors to achieve adaptive evolution of the strategy model.

[0075] The present invention is further configured such that the basic attribute set of the housing resources includes structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data, wherein:

[0076] Structural density parameters are used to characterize the distribution density of the internal subsystem layout of a building. Specifically, the layout information of the internal components of the building is extracted from the Building Information Model (BIM) or space management database, and a layout diagram of the building's subsystems is constructed based on the spatial adjacency relationship between the components. By calculating the distribution density of the subsystem components per unit area, a set of structural density parameters for the building is formed.

[0077] The facility composite level parameter is used to reflect the degree of functional integration and the complexity of the interconnection structure among the multifunctional facilities in the housing configuration; specifically, it obtains the functional category identifier of each facility unit in the housing, the connection information between its subsystem and functional module; based on the degree of interconnection and the hierarchical relationship of functional types, a facility composite level scoring model is constructed to obtain the composite level parameter representing the complexity of facility integration;

[0078] Historical maintenance event sequences are used to record the maintenance operation types, time nodes, and event frequencies of properties over multiple cycles. Specifically, maintenance logs and operation records of properties from multiple historical operation cycles are retrieved, and the occurrence time, type tag, and facility association identifier of each event are extracted. Events are arranged in chronological order to form an event sequence, and the occurrence frequency, time density, and functional coverage of event types are extracted to form a structured maintenance event sequence.

[0079] Function switching trajectory data is used to characterize the transition path and temporal sequence of each functional state of a property during continuous use. Specifically, based on the property's function scheduling history, the switching path between different functional states of the property is recorded during continuous operation. The start state, target state, and duration of each function switching event are labeled to construct multiple functional state transition trajectories. The trajectories are segmented and structurally labeled to extract temporal sequence and state duration information, forming a function switching trajectory dataset.

[0080] The structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data are tagged and encoded.

[0081] A unified format for representing basic property attributes is constructed to form a set of basic input attributes for subsequent property complexity calculation and strategy scheduling modeling.

[0082] The present invention is further configured such that the housing resource joint complexity index is generated by feature coupling of structural density factor, facility composite factor and behavioral distribution factor, wherein:

[0083] The structural density factor is constructed based on the arrangement relationship between the internal spatial structure and component units of the building; specifically, the formula for calculating the structural density factor is: ,in, This refers to the number of effective component units within the property. For the usable area of ​​the property, This is a spatial local complexity index, calculated using a spatial clustering algorithm, which enhances its reflection of local complex structures. This is a moderating factor that adjusts the weight of the impact of local spatial complexity on the overall system. This is a density nonlinear adjustment index, used to adjust the degree of influence of density on the factor;

[0084] The facility integration factor is constructed based on facility function categories, quantity levels, and interaction relationships; specifically, it defines the number of facility function categories. Construct a facility function interaction diagram ,node Represents facility unit, edge The weighted connectivity index of the computation graph represents the functional dependencies or collaborative relationships between facilities. It reflects the coupling strength of the facility network and calculates the facility hierarchical complexity based on weighted degree centrality or modularity metrics. The formula for calculating the facility compositeness factor, which measures the depth and uniformity of facility distribution at functional levels, is as follows: ,in, , , This serves as a weighting index to adjust the contributions of different dimensions. It is a non-linear amplification index. The larger the value, the greater the functional versatility. The tighter the coupling between characterization facilities, the higher the functional dependency complexity. It reflects the complexity of the hierarchical distribution structure of the facilities; the deeper the hierarchy, the more complex the management and interaction.

[0085] The behavior distribution factor is constructed based on the frequency of behaviors, functional activity, and transfer intensity in historical operation and maintenance event sequences and function switching trajectories; specifically, the historical operation and maintenance event sequences are divided into... Calculate the event frequency distribution for each time segment. , Representing the set of event categories, construct a state transition matrix for the function switching trajectory. ,element Indicates from state to state The formula for calculating the transition probability and the behavioral distribution factor is: ,in, To use the Minkowski norm for calculating frequency distributions, highlighting the impact of low-frequency events, The weights for the nonlinear amplification frequency distribution, This is the exponent used to calculate the power of the deviation of the transition probability from the mean. To adjust the contribution weight of the transfer entropy, The target state The mean transition probability;

[0086] The three factors are combined into a unified property joint complexity index through a combination mapping method. This index is used to characterize the overall complexity of a property in terms of its structure, configuration, and behavior. Specifically, the formula for calculating the property joint complexity index is as follows: , Describes the nonlinear coupling between structure and configuration. It represents the contribution of dynamic behavioral response to the enhancement of system structure; it realizes unified modeling of three-dimensional attributes of housing structure, configuration and behavior, and improves the accuracy of overall housing status response assessment.

[0087] The present invention is further configured such that the generation of housing risk response sensitivity factors includes:

[0088] Obtain the operating status parameters of smart park housing units in the latest cycle and a historical cycle. The operating status parameters include energy consumption density, temperature control load, environmental disturbance response and usage activity saturation ratio.

[0089] Based on the operating state parameters, construct a state change relationship structure and extract the current cycle state differences and historical cycle change trends;

[0090] The state perturbation amplitude is constructed based on the state differences; specifically, a state change function is constructed. The nonlinear offset reflecting the historical and current operating states is defined as follows: ,in, For the current cycle, For historical cycles, For period energy density, For period Temperature control load, For period Environmental disturbance response For period Use of activity saturation ratio, This is a perturbation expansion factor used to increase the weight of nonlinear mutations;

[0091] The magnitude of state disturbance is correlated with the joint complexity index of housing resources to generate a risk response sensitivity factor that characterizes the dynamic risk response level of housing resources. Specifically, the calculation formula for the risk response sensitivity factor is as follows: ,in, This is the perturbation-complexity difference amplification factor. This is the sensitivity overall response intensity adjustment factor, calibrated experimentally.

[0092] The present invention is further configured such that the generated housing resource scheduling tension index includes:

[0093] Based on the operation and maintenance event sequence and function switching trajectory of a property within a preset number of historical periods, the frequency of function status switching, the duration of status and the event time density are extracted to construct the evolution path of property function usage.

[0094] Based on the evolution path of property use functions and the resource consumption characteristics of each functional state, usage trend factors for various resources of the property in the future period are generated; specifically, resource use trend factors are generated based on the evolution path sequence. , indicating housing listings Future cycles for resource types Trend strength: , Indicates the first Fragments affect resources during function state switching Resource consumption per unit time period The density of functional states in this slice. This refers to the path coupling degree; a higher degree indicates a high degree of linkage between function switching. This is a resource trend amplification factor, dynamically set based on resource importance;

[0095] The system collects the distribution structure, allocation ratio, occupancy structure, and surplus status of resources in the current resource pool, and extracts a resource density index to characterize resource utilization stress. Specifically, it defines a certain type of resource in the resource pool. density index ,in, The current allocation ratio, Given the current resource usage and structural complexity, This represents the current remaining available resources. This represents the dispersion of current resource allocation among various housing units. This serves as an adjustment factor for the resource stress index; a resource pool density index is introduced to dynamically characterize resource pressure and avoid scheduling conflicts.

[0096] By structurally fusing future resource usage trend factors of housing units with resource density indices, a housing unit scheduling resource tension index is generated. This index is used to characterize the resource load intensity corresponding to scheduling requests. Specifically, the final housing unit... In resource type On the scheduling resource tension index , For trend-density bias response factor, As a global adjustment factor for tension intensity, the resource tension index can be extended to multiple resource dimensions, providing a quantitative basis for joint strategy scheduling.

[0097] The present invention is further configured such that the construction of the housing resource function using the evolution path is based on a time slice sequence, dividing operation and maintenance events and function switching behaviors into equal time intervals; specifically, historical operation and maintenance cycles are used. Divided into equally spaced time periods ,get Segment slice;

[0098] Structural annotation is performed on the functional state transition behaviors within each time period. High-frequency transition structures in the functional evolution path are extracted through the density sequence and path coupling sequence of state transition nodes. Specifically, for each segment... Mark the corresponding functional status With event log Functional status is the functional identifier of the property, such as "office", "meeting", "vacant", etc.; event logs indicate facility start / stop, abnormal alarms, maintenance operations, etc.; and a state transition node density sequence is constructed. This indicates that a certain function is in the slice. State concentration in constructing path coupling sequences The function of reflection is from arrive The degree of transfer coupling at that time.

[0099] Resource mapping and identification are performed on path segments based on the resource consumption gradient of functional state, and each segment in the path is mapped and identified. Based on the types of resources required for its functional status (such as electricity, water, heating and cooling loads), the resource consumption gradient is marked. .

[0100] The present invention is further configured such that the generated housing allocation scheduling priority threshold includes:

[0101] Based on the structural coupling relationship between housing risk response sensitivity factors, housing allocation resource tension indicators, and housing joint complexity indicators, a nonlinear fusion driving factor is constructed to express the priority driving intensity of housing allocation demand; specifically, a housing allocation driving intensity factor is constructed. ,in, As a driving force for nonlinear amplification, this factor reflects the urgency of comprehensive scheduling under the multidimensional coupling of housing structure, resources, and risks, and has strong discriminative power.

[0102] By introducing a historical periodic state perturbation structure and extracting the perturbation trend sequence, a scheduling evolution response potential is constructed to characterize the periodic evolution of scheduling demands; specifically, the perturbation trend sequence... This represents the nonlinear evolution intensity of housing status disturbances in the historical cycle, within the periodic sequence. The above statistics show the increase or dramatic change in its perturbation structure; an evolutionary response potential is constructed. , For period The increase or intensity of internal disturbance. The coefficient of the periodic evolution index. The rise coefficient of the scheduling response potential;

[0103] By combining nonlinear fusion driving factors and scheduling evolution response potential, a housing allocation priority threshold is generated, which serves as the basis for ranking housing allocation requests. Specifically, the housing allocation priority threshold... Defined as , For housing The scheduling priority threshold, The perturbation response bias factor. By amplifying the response factor using a threshold, the resulting priority threshold can be flexibly adapted to various scheduling strategy models such as path optimization, risk avoidance, and resource balancing, and has high versatility.

[0104] The present invention is further configured such that the output housing control command includes:

[0105] Obtain the housing allocation results corresponding to the path optimization strategy, risk avoidance strategy, and resource balancing strategy; specifically, define the allocation path strength under the path optimization strategy for the three types of allocation strategy results. Scheduling inhibition factor under risk aversion strategy Resource buffer coefficient under resource balancing strategy ;

[0106] Priority threshold for housing resource allocation Sensitive factors for housing risk response Housing allocation resource tension index ;

[0107] A fusion structure model is constructed based on the results of three types of policies and scheduling indicators to form a multi-policy joint scheduling mapping relationship; specifically, a fusion mapping function is constructed. Nonlinearly mapping all strategies and indicators to control the genome ,in, This is the path optimization value, representing the topology efficiency of the operation and maintenance path. The lower the level of risk mitigation, the stronger the risk aversion. The strength of the resource buffer reflects the ability to reallocate housing resources. To map the index factor and control the intensity of the fusion incentive, the results of the three types of strategies are deeply integrated with dynamic indicators to avoid the problem of unstable results under single-strategy scheduling.

[0108] The joint scheduling mapping relationship is structurally fused to generate housing control instructions, which are used to indicate the execution path of housing operation and maintenance behavior under multi-strategy conditions. Specifically, the final control instructions are expressed as housing scheduling vectors. This indicates the behavioral direction, execution sequence, and activation intensity of the property under the integrated control of the strategy. The control commands can take into account path efficiency, risk avoidance and resource flexibility, avoiding the two types of problems of "resource waste" and "scheduling lag".

[0109] The present invention is further configured such that the adaptive evolution of the implementation strategy model includes:

[0110] Collect the execution results and actual status feedback information after the control commands for each property are issued;

[0111] Based on the execution results and the pre-control state, a feedback deviation structure is constructed, and a feedback deviation evaluation factor is generated. Specifically, scheduling execution feedback is collected and a feedback deviation structure is constructed for each property number. In the current scheduling cycle Internal record: Post-execution state structure Such as the actual set of completed task paths, energy consumption trajectories, etc.; the target scheduling structure generated by the strategy. Such as the control structure of the three-strategy fusion output. The execution feedback deviation structure is defined as follows: ,in, This represents the path structure difference extraction operation, which models the path behavior level difference map between strategy generation and actual execution, such as task not executed, jump anomalies, resource loading offsets, etc.; based on the feedback deviation structure... Generate feedback deviation assessment factors ;

[0112] A model is constructed to investigate the correlation between the feedback deviation evaluation factor and the fusion output of multiple scheduling strategies, and the deviation response performance of each strategy in the current period is extracted. Specifically, the three strategy control factors are set as path optimization factors. Risk aversion factor Resource balance factor Historical feedback sequence Construct a bias response function based on the usage of strategy factors. By backpropagating the structural residual gradient, the contribution trend of each strategy factor to the current deviation is estimated, which serves as the basis for adjusting the control parameters.

[0113] Based on the deviation response performance, the strategy fusion control parameters are adjusted, the control factors in the strategy model are updated, and the updated parameters are input into the next scheduling cycle to realize the adaptive evolution process of the strategy model. Specifically, the updated strategy control factors are as follows. , ,in, To update the step size coefficient, Adjust the response sensitivity factor for the property strategy (which can be adjusted based on property stability).

[0114] The present invention is further configured such that the construction of the feedback deviation evaluation factor adopts a path-by-path difference extraction method, and after collecting the control execution status feedback, the feedback status is compared with the scheduling intensity structure generated by the initial scheduling strategy at the path level.

[0115] A feedback deviation structure is constructed based on the degree of path execution difference. Structural difference segments are extracted from this structure as a subset of deviation features. These feature subsets are then used to target and adjust various strategy control factors. Specifically, this adjustment is performed based on the feedback deviation structure. Extract path fragment set Each of them This represents a structural difference segment. Construct feedback bias assessment factors. ,in, For fragments The corresponding resource consumption error range, For fragments The timing delay magnitude, The impact weight of the residual fragment on the critical path of the system (derived from graph structure centrality), For housing In the cycle The number of structural deviation segments identified in the data. This is a feedback deviation assessment factor used to characterize the deviation response of housing control strategies during this period.

[0116] It should be noted that the specific methods for executing operations of each module and unit in the AI-based smart park property operation and maintenance strategy optimization method provided in the above embodiments have been described in detail in the method embodiments and will not be repeated here. In practical applications, the AI-based smart park property operation and maintenance strategy optimization method provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above, and this is not a limitation here.

[0117] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0118] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0119] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0120] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0122] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0124] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0126] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An AI-based method for optimizing the operation and maintenance strategy of smart park properties, characterized in that, include: Collect structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data of housing units in the smart park to form a set of basic housing attributes; Based on the basic attribute set of housing resources, feature coupling transformation is performed on structural density factor, facility composite factor and behavioral distribution factor to generate housing resource joint complexity index. Based on the operating status parameters of the latest cycle and historical cycles, the state disturbance amplitude is calculated, and the disturbance amplitude is combined with the housing joint complexity index to generate a housing risk response sensitivity factor. Based on historical operation and maintenance event sequences and function switching trajectories, future usage trend factors are generated. At the same time, resource pool status is collected to generate resource density index. The future usage trend factors and resource density index are combined to generate housing scheduling resource tension index. By combining housing risk response sensitivity factors, housing scheduling resource tension indicators, and housing joint complexity indicators, a housing scheduling priority threshold is generated to prioritize scheduling requests. The scheduling results of path optimization strategy, risk avoidance strategy and resource balancing strategy are integrated with housing scheduling priority threshold, risk response sensitivity factor and resource tension index to output housing control instructions; The system collects the execution results and actual status feedback of housing control commands, constructs feedback deviation evaluation factors, and adjusts the strategy fusion control parameters based on the feedback deviation evaluation factors to achieve adaptive evolution of the strategy model.

2. The AI-based smart park property operation and maintenance strategy optimization method according to claim 1, characterized in that, The basic attribute set of the property includes structural density parameters, facility composite level parameters, historical operation and maintenance event sequences, and function switching trajectory data, among which: The structural density parameter is used to characterize the distribution density of the subsystem layout within a building; The facility composite level parameter is used to reflect the degree of functional integration and the complexity of the interconnection structure among the multifunctional facilities in the housing configuration; Historical maintenance event sequences are used to record the types of maintenance operations, time points, and event frequencies of properties over multiple periods; Function switching trajectory data is used to characterize the transition path and temporal sequence of each functional state of a property during continuous use.

3. The AI-based smart park property operation and maintenance strategy optimization method according to claim 2, characterized in that, The property resource joint complexity index is generated by feature coupling of structural density factor, facility composite factor, and behavioral distribution factor, where: The structural density factor is constructed based on the arrangement relationship between the internal spatial structure and component units of the building; The facility integration factor is constructed based on facility function categories, quantity levels, and interaction relationships; The behavior distribution factor is constructed based on the frequency of behavior, function activity, and transfer intensity in historical operation and maintenance event sequences and function switching trajectories; The three factors are combined into a unified property joint complexity index through a combination mapping method, which is used to characterize the overall complexity of property in terms of structure, configuration and behavior.

4. The AI-based smart park property operation and maintenance strategy optimization method according to claim 3, characterized in that, The risk response sensitivity factors for generating housing listings include: Obtain the operating status parameters of smart park housing units in the latest cycle and a historical cycle. The operating status parameters include energy consumption density, temperature control load, environmental disturbance response and usage activity saturation ratio. Based on the operating state parameters, construct a state change relationship structure and extract the current cycle state differences and historical cycle change trends; Construct the state perturbation amplitude based on the state differences; The magnitude of state disturbance is correlated with the joint complexity index of housing resources to generate a risk response sensitivity factor that characterizes the dynamic risk response level of housing resources.

5. The AI-based smart park property operation and maintenance strategy optimization method according to claim 4, characterized in that, The generated housing resource allocation tension indicators include: Based on the operation and maintenance event sequence and function switching trajectory of a property within a preset number of historical periods, the frequency of function status switching, the duration of status and the event time density are extracted to construct the evolution path of property function usage. Based on the evolution path of housing function usage and the resource consumption characteristics of each functional state, generate usage trend factors of various resources of housing in the future cycle; Collect the distribution structure, allocation ratio, occupancy structure and surplus status of resources in the current resource pool, and extract the resource density index to characterize the resource utilization tension. By structurally integrating the future resource usage trend factor of housing resources with the resource density index, a housing resource scheduling tension index is generated, which is used to characterize the resource load intensity corresponding to scheduling requests.

6. The AI-based smart park property operation and maintenance strategy optimization method according to claim 5, characterized in that, The construction of the property listing function evolution path is based on time slice sequence, dividing operation and maintenance events and function switching behaviors into equal time intervals; The functional state transition behavior within each time period is structurally labeled, and high-frequency transition structures in the functional evolution path are extracted by the density sequence and path coupling sequence of state transition nodes. Resource mapping and identification are performed on path segments based on the resource consumption gradient of functional status.

7. The AI-based smart park property operation and maintenance strategy optimization method according to claim 5, characterized in that, The priority thresholds for generating housing allocation include: Based on the structural coupling relationship between housing risk response sensitivity factors, housing scheduling resource tension indicators, and housing joint complexity indicators, a nonlinear fusion driving factor is constructed to express the priority driving intensity of housing scheduling needs. By introducing a historical periodic state perturbation structure and extracting the perturbation trend sequence, a scheduling evolution response potential is constructed to characterize the periodic evolution of scheduling demand. By combining the nonlinear fusion driving factor and the scheduling evolution response potential, a housing scheduling priority threshold is generated, which serves as the basis for ranking housing scheduling requests.

8. The AI-based smart park property operation and maintenance strategy optimization method according to claim 7, characterized in that, Outputting property control commands includes: Obtain the housing allocation results corresponding to the path optimization strategy, risk avoidance strategy, and resource balancing strategy; Collect housing allocation priority thresholds, housing risk response sensitivity factors, and housing allocation resource tension indicators; A fusion structure model is constructed based on the results of the three types of strategies and scheduling indicators to form a multi-strategy joint scheduling mapping relationship; The joint scheduling mapping relationship is structurally integrated to generate housing control instructions, which are used to indicate the execution path of housing operation and maintenance behavior under multiple policy conditions.

9. The AI-based smart park property operation and maintenance strategy optimization method according to claim 8, characterized in that, Achieving adaptive evolution of the policy model includes: Collect the execution results and actual status feedback information after the control commands for each property are issued; Based on the execution results and the pre-control state, a feedback deviation structure is constructed, and a feedback deviation evaluation factor is generated. Model the deviation correlation between the feedback deviation evaluation factor and the fusion output of multiple scheduling strategies, and extract the deviation response performance of each strategy in the current period. The strategy integrates control parameters based on deviation response performance, updates control factors in the strategy model, and inputs the updated parameters into the next scheduling cycle to achieve the adaptive evolution process of the strategy model.

10. The AI-based smart park property operation and maintenance strategy optimization method according to claim 9, characterized in that, The feedback deviation evaluation factor is constructed by a path-by-path difference extraction method. After collecting the control execution status feedback, the feedback status is compared with the scheduling intensity structure generated by the initial scheduling strategy at the path level. A feedback deviation structure is constructed based on the degree of difference in path execution. Structural difference segments are extracted from the feedback deviation structure as a subset of deviation features. Various strategy control factors are then adjusted in a targeted manner based on the subset of deviation features.

Images