Community life service-oriented supply and demand intelligent scheduling method and system

Abstract

This invention provides a method and system for intelligent supply and demand scheduling of community life services, applicable to the field of management data processing. By constructing a community supply and demand state space and uniformly mapping multi-source supply and demand state data, this invention enables resident order information, service personnel status information, community environment information, and historical scheduling information to form a computable unified state expression basis. On this basis, a state change threshold judgment mechanism is used to achieve dynamic trigger recognition of continuously changing scenarios, thereby avoiding the problem of traditional one-time matching strategies failing quickly under environmental disturbances.

Description

Technical Field

[0001] This invention relates to the field of management data processing, and in particular to a method and system for intelligent supply and demand scheduling of community life services. Background Technology

[0002] With the continuous development of smart community construction and digital life services, community life service platforms are gradually integrating various service resources such as housekeeping, repair and maintenance, errand running, elderly care, community delivery, and convenience services. These platforms utilize mobile internet to enable residents to post needs, service personnel to accept orders, and provide service evaluations. However, community life services are characterized by diverse needs, high timeliness requirements, high staff mobility, and relatively concentrated service areas with dynamically changing demand distributions. This necessitates real-time scheduling of supply and demand resources by the platform to improve service efficiency and user satisfaction.

[0003] Currently, most community life service platforms primarily use methods such as distance-based priority, first-come-first-served order processing, fixed-rule matching, or simple weighted scoring to match supply and demand and schedule services. When service demand is low, these methods can meet basic business needs; however, as the community expands, service types increase, and the number of demands continues to grow, service orders exhibit significant dynamism, suddenness, and spatiotemporal aggregation, making it difficult for traditional scheduling methods to balance service efficiency, resource utilization, and user experience. Summary of the Invention

[0004] This invention aims to address the problem that continuous changes in orders, service personnel status, and environmental factors in community life services cause traditional one-time matching results to quickly become invalid, making it impossible to achieve continuous dynamic optimization and scheduling of supply and demand resources. It provides a method and system for intelligent supply and demand scheduling for community life services.

[0005] The present invention employs the following technical means to solve the technical problem: This invention provides a method for intelligent supply and demand scheduling of community life services, including: Based on the community supply and demand status space preset by the life service platform, supply and demand status data in the life service platform are collected, and the supply and demand status data from different sources are uniformly mapped to the community supply and demand status space. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information, and historical scheduling information. Determine whether the state change of the community supply and demand state space exceeds a preset change threshold; If so, the dynamic event type that caused the state change is identified, and a corresponding event description object is generated according to the dynamic event type. The event impact range of the event description object is calculated, and a dynamic local scheduling network of the community supply and demand state space is established based on the event impact range. The change in revenue of the supply and demand matching scheme after rescheduling is obtained. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. Determine whether the change in revenue is lower than the preset disturbance cost; If the value is not lower than the target value, then based on the resource competition index pre-calculated by the life service platform, the corresponding node information is identified. According to the local supply and demand influence domain of the dynamic local scheduling network, the order scheduling priority of the local supply and demand influence domain is recalculated, and a local scheduling execution sequence is output. Based on the local scheduling execution sequence, the supply and demand correspondence in the local supply and demand influence domain is dynamically adjusted, and the supply and demand correspondence is synchronously updated to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

[0006] Furthermore, before the step of identifying the type of dynamic event that causes the state change, and generating a corresponding event description object based on the type of dynamic event, the method further includes: Based on the real-time operation data pre-collected by the life service platform, the state change process of the corresponding subject within a preset period is collected, and the state change process is connected in series to construct a corresponding state change association chain. Determine whether the state change association chain has a continuous evolutionary trend; If so, then according to the order of state changes, a directed connection relationship is established between state nodes, the change transmission relationship between adjacent state nodes is calculated, a state evolution trajectory is obtained, repeated change states in the state evolution trajectory are detected, the repeated change states are merged, abnormal state nodes caused by sampling errors are dynamically removed, a standard event evolution trajectory is generated, the change combination relationship between the standard event evolution trajectories is statistically analyzed, and the change combination relationship is mapped to a pre-established event pattern library respectively.

[0007] Furthermore, the steps of calculating the event impact range of the event description object, establishing a dynamic local scheduling network of the community supply and demand state space based on the event impact range, and obtaining the change in revenue of the supply and demand matching scheme after rescheduling, further include: Based on the record identifier in the event description object, the target resource directly affected by the event is identified. Taking the target resource as the starting node, the resource association relationship in the community supply and demand state space is recursively searched to obtain the associated resource nodes that have a resource dependency relationship with the target resource. The corresponding resource propagation structure is generated. According to the resource propagation structure, the propagation contribution value of each resource node is calculated. The record identifier specifically includes event attributes, associated resources, and event occurrence process. Determine whether the propagation contribution value meets the preset propagation conditions; If not, the current resource node is divided into a propagation boundary node, the propagation analysis of the corresponding resource branch is interrupted, and a corresponding event propagation region is established based on the preset propagation boundary node. The resource association relationships in the event propagation region are reorganized to construct a resource influence topology. Through the resource influence topology, the resource association characteristics between different resource nodes are collected to generate a dynamic resource collaboration relationship set. The resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

[0008] Furthermore, the step of recalculating the order scheduling priority of the local supply and demand influence domain based on the local supply and demand influence domain of the dynamic local scheduling network and outputting the local scheduling execution sequence further includes: Based on the task dependency relationship between each order node within the local supply and demand influence domain, the dynamic execution window corresponding to each order node is calculated. According to the overlap relationship between the dynamic execution windows, several candidate scheduling sequences are generated, and the sequence conflict evaluation results corresponding to each candidate scheduling sequence are constructed respectively. Determine whether the sequence conflict evaluation result meets the preset sequence feasibility conditions; If not, locate the conflict constraint node that causes the sequence conflict, obtain the associated execution node with a direct execution relationship from the conflict constraint node, establish the corresponding conflict association subgraph based on the associated execution node, and identify the adjacent order nodes that cause the conflict to spread in the conflict association subgraph. The associated execution node specifically includes the preceding order node, the following order node, and the shared resource node.

[0009] Furthermore, the step of determining whether the state change of the community supply and demand state space exceeds a preset change threshold also includes: Based on the historical change trajectory of each state variable in the community supply and demand state space, a corresponding state stability interval is constructed, and the degree of deviation of the current state variable in the state stability interval is calculated. Determine whether the degree of offset exceeds a preset offset threshold; If so, the deviation distance between the current state and the boundary of the stable state region is obtained. Based on the deviation distance, the corresponding state breakout direction is identified. Through the state breakout direction, a state deviation trajectory is constructed. Based on the state deviation trajectory, the state reconstruction region of the corresponding state variable is regenerated.

[0010] Furthermore, the step of determining whether the change in revenue is lower than the preset disturbance cost also includes: Based on the historical scheduling revenue data pre-collected by the life service platform, a corresponding revenue fluctuation range is constructed, and a revenue buffer is generated according to the revenue fluctuation range. Determine whether the current change in revenue exceeds the revenue buffer. If so, the profit deviation of the current profit change in the profit buffer is calculated, and the profit change value is dynamically corrected based on the profit deviation to generate a profit correction result. The corresponding profit disturbance ratio is calculated using the profit correction result, and the comparison result between the profit disturbance ratio and the preset disturbance cost is obtained.

[0011] Furthermore, the step of collecting supply and demand status data from the life service platform based on the community supply and demand status space preset by the life service platform, and uniformly mapping the supply and demand status data from different sources to the community supply and demand status space, further includes: The state correlation between the supply and demand state data is collected from different sources. Based on the state correlation, a state fusion trusted domain is constructed, wherein the state fusion trusted domain is used to characterize the trusted fusion range of each supply and demand state data in a unified state space. Determine whether the state fusion trusted domain satisfies the preset trusted mapping conditions; If not, identify conflicting supply and demand status objects, dynamically adjust the mapping relationship of the corresponding supply and demand status data based on the supply and demand status objects, and update the status fusion trusted domain to the life service platform in real time.

[0012] This invention also provides an intelligent supply and demand scheduling system for community life services, including: The data collection module is used to collect supply and demand status data from the life service platform based on the community supply and demand status space preset by the life service platform, and to uniformly map the supply and demand status data from different sources to the community supply and demand status space. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information and historical scheduling information. The judgment module is used to determine whether the state change of the community supply and demand state space exceeds a preset change threshold; The execution module is used to identify the dynamic event type that causes the state change if the state change is true, generate a corresponding event description object according to the dynamic event type, calculate the event impact range of the event description object, establish a dynamic local scheduling network of the community supply and demand state space based on the event impact range, and obtain the change in revenue of the supply and demand matching scheme after rescheduling. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. The second judgment module is used to determine whether the change in revenue is lower than the preset disturbance cost; The second execution module is used to identify the corresponding node information based on the resource competition index pre-calculated by the life service platform if the resource competition index is not lower than the local supply and demand influence domain of the dynamic local scheduling network, recalculate the order scheduling priority of the local supply and demand influence domain, output a local scheduling execution sequence, dynamically adjust the supply and demand correspondence in the local supply and demand influence domain according to the local scheduling execution sequence, and synchronously update the supply and demand correspondence to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

[0013] Furthermore, it also includes: The construction module is used to collect the state change process of the corresponding subject within a preset period based on the real-time operation data pre-collected by the life service platform, and to connect the state change processes in series to construct the corresponding state change association chain. The third judgment module is used to determine whether the state change association chain has a continuous evolution trend; The third execution module is used to, if yes, establish directed connections between state nodes according to the order of state changes, calculate the change propagation relationship between adjacent state nodes, obtain the state evolution trajectory, detect repeated changes in the state evolution trajectory, merge the repeated changes, dynamically remove abnormal state nodes caused by sampling errors, generate standard event evolution trajectories, statistically analyze the change combination relationships between the standard event evolution trajectories, and map the change combination relationships to a pre-established event pattern library.

[0014] Furthermore, the execution module also includes: The calculation submodule is used to identify the target resource directly affected by the event based on the record identifier in the event description object, recursively search the resource association relationship in the community supply and demand state space with the target resource as the starting node, obtain the associated resource nodes that have a resource dependency relationship with the target resource, generate the corresponding resource propagation structure, and calculate the propagation contribution value of each resource node according to the resource propagation structure. The record identifier specifically includes event attributes, associated resources, and event occurrence process. The judgment submodule is used to determine whether the propagation contribution value has reached the preset propagation condition; The execution submodule is used to, if not, divide the current resource node into a propagation boundary node, interrupt the propagation analysis of the corresponding resource branch, establish a corresponding event propagation region based on the preset propagation boundary node, reorganize the resource association relationships in the event propagation region, construct a resource influence topology, collect resource association characteristics between different resource nodes through the resource influence topology, and generate a dynamic resource collaboration relationship set, wherein the resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

[0015] This invention provides a method and system for intelligent supply and demand scheduling of community life services, which has the following beneficial effects: This invention constructs a community supply and demand state space and maps multi-source supply and demand state data in a unified manner, enabling resident order information, service personnel status information, community environment information, and historical scheduling information to form a computable unified state expression basis. On this basis, a state change threshold judgment mechanism is used to achieve dynamic trigger recognition of continuously changing scenarios, thereby avoiding the problem of traditional one-time matching strategies failing quickly under environmental disturbances. At the same time, through dynamic event recognition and event description object construction, complex changes are transformed into structured event units. A dynamic local scheduling network is established in combination with the event impact range, limiting the scheduling range to the affected area, thereby reducing the global recomputation overhead. Furthermore, a comparison mechanism between revenue changes and disturbance costs is introduced to achieve effective screening of scheduling revenue and avoid ineffective rescheduling. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an embodiment of the intelligent supply and demand scheduling method for community life services according to the present invention. Figure 2 This is a structural block diagram of an embodiment of the intelligent supply and demand scheduling system for community life services of the present invention. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. The realization of the purpose, functional features, and advantages of the invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings.

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Reference Appendix Figure 1 The method for intelligent supply and demand scheduling of community life services according to one embodiment of the present invention includes: S1: Based on the community supply and demand status space preset by the life service platform, collect the supply and demand status data in the life service platform, and map the supply and demand status data from different sources to the community supply and demand status space in a unified manner. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information and historical scheduling information. S2: Determine whether the state change of the community supply and demand state space exceeds a preset change threshold; S3: If so, identify the dynamic event type that causes the state change, generate a corresponding event description object according to the dynamic event type, calculate the event impact range of the event description object, establish a dynamic local scheduling network of the community supply and demand state space based on the event impact range, and obtain the revenue change of the supply and demand matching scheme after rescheduling. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. S4: Determine whether the change in revenue is lower than the preset disturbance cost; S5: If not lower than the resource competition index pre-calculated by the life service platform, the corresponding node information is identified. According to the local supply and demand influence domain of the dynamic local scheduling network, the order scheduling priority of the local supply and demand influence domain is recalculated, and a local scheduling execution sequence is output. Based on the local scheduling execution sequence, the supply and demand correspondence in the local supply and demand influence domain is dynamically adjusted, and the supply and demand correspondence is synchronously updated to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

[0020] In this embodiment, the system collects supply and demand status data from a pre-defined virtual space for community supply and demand status on the life service platform. This data includes resident order information, service personnel status information, community environment information, and historical scheduling information. The system maps supply and demand status data from different sources to the community supply and demand status space. Then, the system determines whether the status change in this space exceeds a pre-set threshold and executes corresponding steps accordingly. For example, if the system determines that the status change in the community supply and demand status space does not exceed the pre-set threshold, it considers the existing supply and demand relationship to be sufficient to meet current service needs, without triggering a rescheduling process. The system maintains the current supply and demand matching scheme and synchronously updates the collected supply and demand status data to the historical status cache corresponding to the community supply and demand status space to correct the status baseline. Conversely, if the system determines that the status change in the community supply and demand status space exceeds the pre-set threshold, it considers the existing supply and demand relationship insufficient to meet current service needs and requires a rescheduling process. The system identifies the dynamic event types that cause the status change. These dynamic event types specifically include new... The system generates corresponding event description objects based on different dynamic event types, including order events, service personnel offline events, service personnel location abnormality events, user order cancellation events, user appointment time modification events, community traffic abnormality events, and service timeout events. It calculates the event impact range of these event description objects and establishes a dynamic local scheduling network for the community supply and demand state space based on different event impact ranges. This allows the system to obtain the change in revenue after rescheduling of supply and demand matching schemes. By reorganizing resource relationships within the event impact area through the dynamic local scheduling network, the system can reduce computational scale, lower scheduling complexity, and improve the real-time response capability of the system in community life service scenarios. Simultaneously, it maintains the continuity and stability of scheduling schemes in unaffected areas. Furthermore, by pre-evaluating the rescheduling revenue, the system can prioritize scheduling schemes with higher optimization value, avoiding resource waste and scheduling oscillations caused by frequent adjustments to supply and demand relationships due to low revenue. This enables the community life service platform to dynamically optimize supply and demand resource allocation based on continuous changes in orders, service personnel, and environmental factors. Finally, the system determines whether the change in revenue after rescheduling of the supply and demand matching scheme is lower than a pre-set disturbance cost, and then executes the corresponding steps.For example, when the system determines that the change in revenue after rescheduling of the supply-demand matching scheme is lower than the pre-set disturbance cost, the system will consider that the scheduling optimization benefits brought by the current rescheduling are insufficient to offset the disturbance costs such as service resource reallocation, order execution order adjustment, and service personnel path changes during the rescheduling process. The system will maintain the current supply-demand correspondence and supply-demand matching scheme unchanged, and record the revenue change result and the corresponding event description object to the scheduling decision history database, while updating the continuous impact status of the corresponding event, and continuing to monitor the dynamic local scheduling network in real time. For example, when the system determines that the change in revenue after rescheduling of the supply-demand matching scheme is not lower than the pre-set disturbance cost, the system will consider that the scheduling optimization benefits brought by the current rescheduling can offset the disturbance costs incurred during the rescheduling process. The system will identify the corresponding node information based on the resource competition index pre-calculated by the life service platform. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the estimated completion time, and the window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes, according to the dynamic local scheduling network. The system recalculates the order scheduling priorities within the local supply and demand influence domain of the dispatch network. These priorities consider factors such as order urgency, remaining service window time, service skill scarcity, user waiting time, remaining service personnel capacity, and the balance of community resources. This recalculation outputs a local scheduling execution sequence. Based on this sequence, the system dynamically adjusts the supply and demand relationships within the local influence domain and synchronously updates these relationships to the community supply and demand state space. By introducing a comprehensive evaluation mechanism between revenue changes and disturbance costs, the system ensures that rescheduling is based on actual optimization value, effectively reducing the probability of ineffective and over-scheduling. This improves the scientific rigor and stability of the community life service platform's dynamic scheduling decisions. Furthermore, through local optimization and global synchronization, the system achieves continuous dynamic optimization of community supply and demand resources without disrupting the stable operation of unaffected areas. This allows the life service platform to continuously adjust supply and demand relationships as orders, service personnel status, and the community environment change, thereby improving resource utilization, order fulfillment efficiency, and the overall scheduling stability and continuity of community life services.

[0021] It should be noted that the process involves identifying the types of dynamic events that cause the state changes, generating corresponding event description objects based on these event types, calculating the event impact range of the event description objects, establishing a dynamic local scheduling network for the community supply and demand state space based on the event impact range, and obtaining the change in revenue of the supply and demand matching scheme after rescheduling. Specifically: The system compares and analyzes currently collected resident order information, service personnel status information, community environment information, and historical dispatch information with the data corresponding to the previous dispatch cycle, identifying the corresponding dynamic event type based on the source of the status change. For example, when the system detects a new housekeeping order in a community, and all existing service personnel are in task execution status, this status change is identified as a new order event; if a service personnel's current location and work status cannot be updated due to device offline or voluntarily withdrawing from accepting orders, it is identified as a service personnel offline event; if a service personnel deviates from their original service route due to road construction, traffic congestion, etc., it is identified as a service personnel location anomaly event; if a user cancels a reservation, it is identified as a user order cancellation event; if a user temporarily modifies the reserved service time, it is identified as a user reservation time modification event; if there are road closures or traffic congestion around the community, it is identified as a community traffic anomaly event; if a service personnel anticipates being unable to complete the current service task within the agreed time, it is identified as a service timeout event. By classifying different events, the subsequent dispatch process can adopt targeted processing strategies, rather than using a uniform dispatch method. After identifying dynamic event types, the system generates corresponding event description objects based on different event types. These event description objects do not merely record the event type; rather, they transform dynamic events into unified data objects capable of participating in subsequent scheduling calculations. These objects contain descriptive information such as event number, event type, event occurrence time, event location, event duration, associated orders, associated service personnel, associated community area, affected resources, and event severity. For example, when a resident adds a new on-site repair order, the system generates a corresponding event description object, recording the event type as "new order event," the event occurrence time as 09:30, the event location as Building 3, Community A, the associated order as "repair order 001," the associated community area as Community A, the estimated service duration as 60 minutes, and the service request type as "home appliance repair." Similarly, when service personnel Zhang goes offline due to vehicle malfunction, the system generates a corresponding event description object, recording the service personnel number, offline time, original executed order, estimated recovery time, and the number of affected orders. This ensures that dynamic events from different sources can participate in subsequent analysis using a unified data structure, improving data consistency and processing efficiency throughout the scheduling process. Subsequently, the system calculates the corresponding scope of event impact based on the event description object. Specifically, the system first reads the event attributes from the event description object and, combined with the supply and demand relationship in the community supply and demand state space, analyzes the orders, service personnel, and community areas that the event may affect, identifying the supply and demand objects directly affected by the event. Then, using the directly affected object as the starting node, it further analyzes its relationship with other orders and service personnel, identifies the supply and demand objects that the event may indirectly affect, and continuously expands the impact area according to the event propagation path until there are no new affected objects, thus forming a complete scope of event impact. For example, when a service personnel is temporarily offline, the system not only identifies that their currently executed orders are affected, but also further analyzes whether the service personnel's subsequent appointment orders are delayed as a result, and analyzes whether other service personnel can take over the corresponding orders, and determines the scope of orders and service personnel that need to be rescheduled. As another example, when a main road in the community experiences traffic congestion, the system not only determines that service personnel currently passing through the road are affected, but also analyzes whether service personnel who need to pass through the road to perform tasks are at risk of delay, and includes the relevant orders and service personnel in the scope of event impact, thereby avoiding local adjustments only for a single order and improving the completeness of scheduling analysis. After determining the scope of the event's impact, the system establishes a dynamic local scheduling network corresponding to the community's supply and demand state space based on the scope of the event's impact. Specifically, the system uses resident orders, service personnel, and related community areas within the scope of the event's impact as network nodes, and uses order service relationships, service execution relationships, service time constraints, and resource competition relationships as network connection relationships. Only the local scheduling network is constructed within the area affected by the event, while unaffected areas continue to maintain their original supply and demand correspondence. For example, when a new order only affects community A, the system only includes the relevant orders and service personnel within community A in the dynamic local scheduling network, while unaffected areas such as communities B and C maintain their original scheduling schemes. This avoids the large amount of computational overhead and resource disturbance caused by traditional global rescheduling, thereby improving scheduling efficiency.

[0022] It should be added that, based on the resource competition index pre-calculated by the life service platform, the corresponding node information is identified. According to the local supply and demand influence domain of the dynamic local scheduling network, the order scheduling priority of the local supply and demand influence domain is recalculated, and a local scheduling execution sequence is output. Based on the local scheduling execution sequence, the supply and demand correspondence in the local supply and demand influence domain is dynamically adjusted, and the supply and demand correspondence is synchronously updated to the community supply and demand state space. Specifically: The system reads the resource competition index pre-calculated by the life service platform. The resource competition index is calculated by taking into account factors such as the number of service orders, the number of service personnel, the current task load, the estimated completion time, and the degree of window overlap. Based on this, the system identifies competing resource nodes and bottleneck order nodes. For example, in community A, there are currently 20 pending service orders, but only 6 service personnel are available. Among them, 4 service personnel are already handling 4 orders each, with a task load of 100%, and the other 2 service personnel are handling 2 orders each, with a task load of approximately 50%. At the same time, the appointment service time of 8 orders is concentrated between 14:00 and 15:00, with a window overlap of 80%. Based on this, the system determines that the resource competition index is high during this time period, identifies the nodes corresponding to the 4 service personnel who are handling full-load tasks as competing resource nodes, and identifies the 3 orders with less than 20 minutes left before the appointment deadline as bottleneck order nodes. Subsequently, the system determines the local supply and demand impact domain based on the dynamic local scheduling network, and recalculates the order scheduling priority only for this local supply and demand impact domain. Specifically, the system recalculates the order priority by comprehensively considering factors such as order reservation time, order urgency, service personnel's current location, estimated arrival time, and current task load, generating a new local scheduling execution sequence. For example, service personnel A is only 500 meters away from the bottleneck order and is expected to arrive in 3 minutes, but there is currently one ordinary order waiting to be executed; service personnel B is about 2.8 kilometers away from the bottleneck order and is expected to arrive in 12 minutes, but their subsequent order reservation time is more flexible. After recalculating the priority, the system prioritizes the bottleneck order and assigns it to service personnel A, while adjusting the ordinary order originally planned to be executed by service personnel A to be executed by service personnel B, so that urgent orders can be completed first, while avoiding multiple orders from timed out consecutively. Finally, the system dynamically adjusts the supply and demand correspondence in the local supply and demand influence domain based on the local scheduling execution sequence, and synchronously updates the community supply and demand state space. For example, after the adjustment, service personnel A is responsible for executing the original bottleneck order, and the estimated completion time is brought forward from 14:35 to 14:18; service personnel B takes over executing ordinary orders, and the estimated completion time is adjusted from 14:40 to 14:48. The system synchronously updates the current location, task load, estimated completion time, and order execution status of the two service personnel, and updates the service personnel number and execution order of the corresponding orders, so that the community supply and demand state space always remains consistent with the actual scheduling results. When new orders are added or dynamic events such as service personnel going offline or traffic abnormalities occur, the system can directly continue to execute local dynamic scheduling based on the updated community supply and demand state space without rebuilding the global supply and demand relationship, thereby improving scheduling efficiency and reducing system computational overhead.

[0023] In this embodiment, before step S3, which identifies the type of dynamic event causing the state change and generates a corresponding event description object based on the type of dynamic event, the method further includes: S301: Based on the real-time operation data pre-collected by the life service platform, collect the state change process of the corresponding subject within a preset period, connect the state change processes in series, and construct the corresponding state change association chain. S302: Determine whether the state change association chain has a continuous evolution trend; S303: If so, then according to the order of state changes, establish directed connections between state nodes, calculate the change propagation relationship between adjacent state nodes, obtain the state evolution trajectory, detect repeated changes in the state evolution trajectory, merge the repeated changes, dynamically remove abnormal state nodes caused by sampling errors, generate standard event evolution trajectories, statistically analyze the change combination relationships between the standard event evolution trajectories, and map the change combination relationships to the pre-established event pattern library respectively.

[0024] In this embodiment, the system collects the state change process of the corresponding subject within a pre-set period based on real-time operational data pre-collected by the life service platform. This state change process is then chained together to construct a corresponding state change correlation chain. The system then determines whether these state change correlation chains have a continuous evolution trend, and executes corresponding steps accordingly. For example, if the system determines that these state change correlation chains do not have a continuous evolution trend, it considers the current state change of the subject to be only a short-term fluctuation or occasional change, without forming a continuous propagation or expansion trend. The system marks the current state change correlation chain as a transient change correlation chain and stores the corresponding state change process in the historical evolution database. Simultaneously, it updates the normal change baseline and fluctuation characteristic parameters of the corresponding subject according to this state change correlation chain, and continues to collect real-time operational data of the corresponding subject according to the pre-set collection period. Subsequently collected state change processes are then added to the state change correlation chain for incremental updates. Conversely, if the system determines that these state change correlation chains have a continuous evolution trend, it considers the current state change of the subject to have formed a continuous propagation or expansion trend. The system establishes directed connections between state nodes based on the order of state changes, calculates the change propagation relationship between adjacent state nodes, obtains the state evolution trajectory, detects repeated changes in the state evolution trajectory, merges these repeated changes, dynamically removes abnormal state nodes caused by sampling errors, generates standard event evolution trajectories, statistically analyzes the change combination relationships between these standard event evolution trajectories, and maps these change combination relationships to a pre-established event pattern library. By standardizing the event evolution process, the system not only avoids interference from repeated and abnormal states on event identification results, but also improves the authenticity and stability of event evolution trajectories. This allows subsequent scheduling decisions to be based on more accurate and reliable state evolution information, reducing the probability of misjudgment and misscheduling. Compared to the traditional approach of responding solely based on the current state, the system can fully utilize historical event experience to improve the system's identification efficiency and predictive ability for complex dynamic events. This provides a more accurate decision-making basis for subsequent local scheduling strategy generation and dynamic optimization of supply and demand resources, enhancing the adaptability of the community life service platform to continuously changing scenarios.

[0025] It should be noted that, based on the order of state changes, directed connections are established between state nodes, the change propagation relationship between adjacent state nodes is calculated, and a state evolution trajectory is obtained. Repeated changes in the state evolution trajectory are detected, and these repeated changes are merged. Abnormal state nodes caused by sampling errors are dynamically removed, generating standard event evolution trajectories. The change combination relationships between these standard event evolution trajectories are statistically analyzed, and these change combination relationships are mapped to a pre-established event pattern library. Specifically: The system first sorts the state changes according to their occurrence time, abstracting each state change into a state node, and then establishes directed connections between state nodes according to their time sequence. Each directed connection indicates that the previous state change can lead to the occurrence of the next state change, thus forming a continuous state propagation chain. For example, in a community, if an order O1 is added at 9:00, service personnel S1 accepts the order at 9:03, the community road is congested at 9:10, the service personnel's estimated arrival time is delayed at 9:18, and the order is expected to time out at 9:25, the system generates state nodes N1 to N5 respectively, and establishes directed connections N1→N2→N3→N4→N5, so that the entire development process of the event can be recorded completely in chronological order. Subsequently, the system calculates the change transmission relationship between adjacent state nodes. Specifically, the system comprehensively considers the time interval, affected objects, change direction, and state change magnitude between adjacent state nodes to calculate the degree of influence of the previous state on the next state, and forms a state evolution trajectory accordingly. For example, in the above embodiment, due to traffic congestion in the community, the service personnel's expected arrival time is delayed from 9:15 to 9:28, a delay of 13 minutes. The system determines that state node N3 has a strong change transmission relationship with state node N4. At the same time, the extended arrival time also causes the expected order completion time to be adjusted from 9:40 to 9:53, exceeding the user's reservation time by 10 minutes. Therefore, a change transmission relationship is established from state node N4 to state node N5, ultimately forming a complete state evolution trajectory. After forming the state evolution trajectory, the system performs repeated detection on the state nodes in the trajectory. If multiple state nodes are detected describing the same continuous state change, they are merged. For example, if the system collects service personnel location information every 30 seconds and detects the state change "road congestion leading to speed decrease" in three consecutive sampling processes at 9:10, 9:10:30, and 9:11, the system will merge the three repeated state nodes into a unified state node to avoid recording the same event repeatedly. On the other hand, if a service personnel instantaneous location offset of 500 meters is collected at 9:12, and the location returns to normal in the next sampling, the system will determine that the node belongs to an abnormal state node caused by GPS sampling error based on the continuity of the previous and subsequent states, and dynamically remove it, thereby generating a more realistic and continuous standard event evolution trajectory. Finally, the system statistically analyzes the changing combinations among multiple standard event evolution trajectories and maps these combinations to a pre-established event pattern library. For example, after long-term operation, the system found that among 1000 historical scheduling events, 280 exhibited an evolution trajectory of "new order → service personnel accepting the order → traffic congestion → estimated arrival delay → order timeout," while 190 exhibited an evolution trajectory of "service personnel offline → order reallocation → increased load on nearby service personnel → subsequent order delay." The system then establishes these changing combinations as event patterns M1 and M2, respectively, and stores them in the event pattern library. When the same or highly similar state evolution trajectories reappear, the system can quickly complete event pattern matching, predict the subsequent evolution trend of the event, and generate corresponding local scheduling strategies in advance. This reduces event analysis time and improves the efficiency of the community life service platform in identifying complex dynamic events and its ability to dynamically schedule supply and demand resources.

[0026] In this embodiment, step S3, which involves calculating the event impact range of the event description object, establishing a dynamic local scheduling network for the community supply and demand state space based on the event impact range, and obtaining the change in revenue of the supply and demand matching scheme after rescheduling, further includes: S31: Based on the record identifier in the event description object, identify the target resource directly affected by the event, and recursively search the resource association relationship in the community supply and demand state space with the target resource as the starting node to obtain the associated resource nodes that have a resource dependency relationship with the target resource, generate the corresponding resource propagation structure, and calculate the propagation contribution value of each resource node according to the resource propagation structure. The record identifier specifically includes event attributes, associated resources, and event occurrence process. S32: Determine whether the propagation contribution value meets the preset propagation conditions; S33: If not, the current resource node is divided into a propagation boundary node, the propagation analysis of the corresponding resource branch is interrupted, and a corresponding event propagation region is established based on the preset propagation boundary node. The resource association relationships in the event propagation region are reorganized to construct a resource influence topology. Through the resource influence topology, the resource association characteristics between different resource nodes are collected to generate a dynamic resource collaboration relationship set. The resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

[0027] In this embodiment, the system identifies target resources directly affected by the event based on the record identifier corresponding to the event description object. The record identifier specifically includes event attributes, associated resources, and the event occurrence process. Using these target resources as starting nodes, the system recursively searches for resource relationships in the community supply and demand state space to obtain associated resource nodes that have resource dependencies on these target resources. Corresponding resource propagation structures are generated. Based on different resource propagation structures, the system calculates the propagation contribution value of each resource node. Then, the system determines whether these propagation contribution values ​​meet pre-set propagation conditions to execute corresponding steps. For example, when the system determines that the propagation contribution value of each resource node can reach... When pre-defined propagation conditions are met, the system considers the event to have evolved from a local impact event into an extended impact event with propagation effects. The system marks resource nodes whose propagation contribution values ​​exceed a threshold as key propagation nodes and performs hierarchical clustering of key propagation paths based on the resource propagation structure to form a multi-level resource impact subgraph. Simultaneously, high-contribution nodes are prioritized for use as a basis for resource allocation in subsequent scheduling calculations. For example, if the system determines that the propagation contribution values ​​of various resource nodes cannot meet the pre-defined propagation conditions, the system considers the current event's impact on the resource association structure in the community supply and demand state space to be limited to the local target resource and its first-order neighboring resource nodes. At this point, the system will classify the current resource node as a propagation boundary node, interrupt the propagation analysis of the corresponding resource branch, establish a corresponding event propagation region based on the pre-defined propagation boundary node, reorganize the resource relationships within this event propagation region, and construct a corresponding resource impact topology. Through this resource impact topology, the system collects the resource association characteristics between different resource nodes. These characteristics specifically include resource substitution capability, resource competition capability, and resource coordination capability, generating a dynamic set of resource coordination relationships. Through the resource impact topology, the system can extend the relationships between resource nodes from simple adjacency relationships to structured network relationships, thereby more accurately depicting the local supply and demand impact range. By identifying the resource interaction characteristics within the scope, the system improves its ability to express and analyze local structural changes in the supply and demand status of the community. At the same time, by introducing a propagation boundary node mechanism, the system can clearly define the spatial boundary of the event's impact, making the division of the event propagation area clearer. This avoids the problem of over-expansion of resource association analysis caused by continuous recursive search in traditional methods, improving the accuracy and computational efficiency of the overall propagation modeling. Furthermore, based on the resource impact topology, the system collects the resource association characteristics between different resource nodes, including resource substitution ability, resource competition ability, and resource collaboration ability, and generates a dynamic resource collaboration relationship set, enabling the system to characterize the functional and interactive relationships between resources from a multi-dimensional perspective.

[0028] It should be noted that the current resource node is divided into a propagation boundary node, the propagation analysis of the corresponding resource branch is interrupted, and a corresponding event propagation region is established based on the preset propagation boundary node. The resource association relationships in the event propagation region are reorganized to construct a resource influence topology. Through the resource influence topology, the resource association characteristics between different resource nodes are collected to generate a dynamic resource collaboration relationship set, specifically: The system classifies resource nodes whose propagation contribution value is lower than the propagation condition as propagation boundary nodes and terminates the continued propagation analysis of that resource branch, ensuring that the event propagation analysis only covers the actually affected resources. For example, after a domestic service worker S1 temporarily goes offline in community A, the system recursively analyzes and finds a total of 12 resource nodes associated with S1. The propagation contribution values ​​of service orders O1, O2, O3 and service workers S2, S3 are 0.82, 0.76, 0.71, 0.69 and 0.65, respectively, while the propagation contribution values ​​of orders O4, O5 and service workers S4, S5 are only 0.28, 0.23, 0.19 and 0.15, respectively. The preset propagation condition is 0.60. Therefore, the system classifies O4, O5, S4 and S5 as propagation boundary nodes and stops the propagation analysis along these resource nodes, thereby preventing the scope of the event's impact from being expanded indefinitely. Subsequently, the system establishes corresponding event propagation areas based on propagation boundary nodes. Specifically, the system uses the event source node and all resource nodes whose propagation contribution values ​​meet the propagation conditions as the core of the area, and the propagation boundary nodes as the outer boundary of the area. The resource nodes within the propagation boundary are then reclassified into the same event propagation area. For example, in the above embodiment, the system ultimately determines that the event propagation area includes service personnel S1, S2, and S3, as well as orders O1, O2, and O3, forming an event propagation area containing 6 core nodes. Orders O4 and O5, and service personnel S4 and S5, are located outside the propagation boundary and are no longer included in the scope of this local event analysis, thus making the event propagation area closer to the actual impact range. After establishing the event propagation region, the system reorganizes the resource relationships within it, constructing a resource influence topology. Specifically, the system uses resource nodes as topology nodes and order allocation relationships, service collaboration relationships, resource competition relationships, and task succession relationships as topology connecting edges to reorganize the original resource relationships. For example, in the event propagation region, a service execution relationship is established between order O1 and service personnel S1, and order O2 can also be executed by S2, thus establishing a resource substitution relationship; both order O2 and order O3 require service personnel S2, thus establishing a resource competition relationship; service personnel S2 can continue to execute O3 after completing O2, thus establishing a task succession relationship; ultimately, a resource influence topology containing multiple nodes and various connecting edges is formed, transforming the interaction relationships between different resources from simple associations into a hierarchical topology network. Finally, the system collects resource association characteristics between different resource nodes through resource influence topology and generates a dynamic resource collaboration relationship set. These resource association characteristics include resource substitution capability, resource competition capability, and resource collaboration capability. For example, the system analysis found that service personnel S2 and S3 both possess housekeeping and cleaning qualifications, and their resource substitution capability score reaches 0.92. Orders O2 and O3 both compete for service personnel S2, with a resource competition capability score reaching 0.88. After completing order O2, service personnel S2 can directly proceed to execute order O3, and the path between the two orders... With a distance of only 350 meters, the resource coordination capability score reached 0.81. Based on this, the system generates a dynamic resource coordination relationship set, such as {S2→S3, substitution capability 0.92}, {O2↔O3, competition capability 0.88}, {O2→O3, coordination capability 0.81}, and other relationship data. When performing local scheduling in the future, the system can prioritize resource combinations with higher substitution capability, lower competition level, and stronger coordination capability based on the dynamic resource coordination relationship set, so as to realize the rapid reorganization and optimized allocation of resources and improve the efficiency and stability of local dynamic scheduling in community life service scenarios.

[0029] In this embodiment, step S5, which involves recalculating the order scheduling priority of the local supply and demand influence domain based on the local supply and demand influence domain of the dynamic local scheduling network and outputting the local scheduling execution sequence, further includes: S51: Based on the task dependency relationship between each order node in the local supply and demand influence domain, calculate the dynamic execution window corresponding to each order node, generate several candidate scheduling sequences according to the overlap relationship between the dynamic execution windows, and construct the sequence conflict evaluation result corresponding to each candidate scheduling sequence respectively. S52: Determine whether the sequence conflict evaluation result meets the preset sequence feasibility conditions; S53: If not, locate the conflict constraint node that causes the sequence conflict, obtain the associated execution node with a direct execution relationship from the conflict constraint node, establish the corresponding conflict association subgraph according to the associated execution node, identify the adjacent order node that causes the conflict to spread in the conflict association subgraph, wherein the associated execution node specifically includes the preceding order node, the following order node and the shared resource node.

[0030] In this embodiment, the system calculates the dynamic execution window corresponding to each order node based on the task dependency relationship between each order node within the local supply and demand influence domain. Based on the overlap relationship between these dynamic execution windows, several candidate scheduling sequences are generated. Sequence conflict evaluation results are constructed for each candidate scheduling sequence. The system then determines whether the sequence conflict evaluation result meets the preset sequence feasibility conditions to execute the corresponding steps. For example, when the system determines that the sequence conflict evaluation result meets the preset sequence feasibility conditions, the system considers the current candidate scheduling sequence to have executability and time consistency, and can be used as an effective local scheduling execution scheme. The system selects the candidate scheduling sequence that meets the preset sequence feasibility conditions as the target local scheduling execution sequence. Based on the target local scheduling execution sequence, the order nodes within the local supply and demand influence domain are sequentially fixed, and the service resource allocation relationship corresponding to each order node is locked. The service personnel path planning and task execution order are synchronously adjusted according to the execution sequence to generate the final local scheduling execution scheme. For example, when the system determines that the sequence conflict evaluation result does not meet the preset sequence feasibility conditions, the system considers that there is a conflict in the current candidate scheduling sequence. In cases of unavoidable resource occupation conflicts, task execution time conflicts, or task dependency conflicts, where the dynamic execution windows between order nodes within a local supply and demand influence domain cannot form a continuous execution relationship that satisfies scheduling constraints, the system will locate the conflict constraint nodes that cause sequence conflicts. From these conflict constraint nodes, it will obtain the associated execution nodes with direct execution relationships. The associated execution nodes specifically include preceding order nodes, subsequent order nodes, and shared resource nodes. Based on different associated execution nodes, a corresponding conflict association subgraph will be established. In this conflict association subgraph, adjacent order nodes that cause conflict propagation will be identified. Through the conflict association subgraph, the system can intuitively reflect the association paths and influence ranges between conflict nodes, accurately describe the propagation relationship of conflicts within the local supply and demand influence domain, provide more complete data support for subsequent conflict repair and scheduling optimization, and improve the analysis accuracy of local scheduling schemes. At the same time, by identifying the conflict propagation path in advance, the system can simultaneously optimize the execution order of related orders and resources during subsequent local scheduling processes, preventing local conflicts from further propagating into large-scale scheduling conflicts, and improving the local scheduling stability, resource coordination capabilities, and overall supply and demand optimization effect of the community life service platform in a dynamic environment.

[0031] It should be noted that the process involves locating the conflict constraint nodes that cause sequence conflicts, obtaining the associated execution nodes with direct execution relationships from these conflict constraint nodes, establishing a corresponding conflict association subgraph based on these associated execution nodes, and identifying adjacent order nodes in the conflict association subgraph that facilitate conflict propagation. Specifically: The system first performs a node-by-node analysis on the candidate scheduling sequences to locate the conflict constraint nodes that cause sequence conflicts. The conflict constraint nodes are the key nodes that prevent the current scheduling sequence from executing normally. The corresponding conflict reasons can be resource occupation conflicts, task execution time conflicts, or task dependency conflicts. For example, in a community, there are 8 pending orders (O1 to O8) and 3 service personnel (S1, S2, S3). Service personnel S1 originally planned to execute tasks in the order of O1→O3→O6. However, a new order O8 requires service to be completed between 14:10 and 14:30. At this time, the appointment time of O3 is 14:00 to 14:20, and the appointment time of O8 is 14:10 to 14:30. Both orders can only be completed by service personnel S1 who has professional repair qualifications. Therefore, the system determines that the node corresponding to service personnel S1 is a conflict constraint node, and the conflict reason is a shared resource occupation conflict. After locating the conflict constraint node, the system uses that node as the center to obtain related execution nodes that have a direct execution relationship with it. These related execution nodes include preceding order nodes, following order nodes, and shared resource nodes. Preceding order nodes represent orders that must be completed before the current order, following order nodes represent orders that depend on the completion of the current order before they can begin execution, and shared resource nodes represent service resources shared by multiple orders. For example, in the above scenario, order O1 is the preceding order node, order O6 is the following order node, and service personnel S1 is the shared resource node. Simultaneously, since the newly added order O8 also occupies service personnel S1, order O8 is also included in the analysis scope as a related execution node. The system fully recovers the local execution relationships formed by the conflict through these related execution nodes, rather than only analyzing the single order that caused the conflict. Subsequently, the system establishes a corresponding conflict association subgraph based on the acquired associated execution nodes. Order nodes and service personnel nodes are respectively used as nodes in the graph, and task execution order, resource sharing, and task dependency relationships are used as connections between nodes. For example, in this embodiment, the system establishes a conflict association subgraph containing O1, O3, O6, O8, and S1, where O1→O3→O6 represents the task execution order relationship, and O3—S1 and O8—S1 represent resource sharing relationships. Through this conflict association subgraph, the system can intuitively reflect the association relationships between different orders caused by shared resources and the conflict propagation path, providing a data foundation for subsequent conflict resolution. Finally, the system identifies adjacent order nodes in the conflict association subgraph that are affected by the spread of the conflict. Specifically, the system uses the conflict constraint node as the starting node and searches layer by layer along the conflict association subgraph for order nodes that are directly or indirectly related to it, analyzing whether the current conflict will cause delays in the execution time of subsequent orders, duplicate resource usage, or scheduling time conflicts. For example, in the above embodiment, because the execution time of order O3 is expected to be extended by 15 minutes, the expected start time of subsequent order O6 is delayed from 14:40 to 14:55, while the scheduling deadline for order O6 is 15:00. Therefore, the system determines that order O6 has been affected by the spread of the conflict. When service personnel S1 is unable to execute the new order O8, the system further analyzes whether service personnel S2, who is only 700 meters away from O8, can take over the execution. If S2's adjustment affects the order O5 that he originally planned to execute, then order O5 is also identified as an adjacent order node in the conflict propagation. By identifying adjacent order nodes in the conflict propagation, the system can fully grasp the scope of the conflict's impact, providing a more accurate basis for decision-making in subsequent local scheduling sequence reconstruction, resource reallocation, and supply and demand relationship optimization. At the same time, it avoids the generation of new chain conflicts by only dealing with conflict nodes, thereby improving the stability and execution efficiency of the dynamic scheduling of community life services.

[0032] In this embodiment, step S2, which determines whether the state change of the community supply and demand state space exceeds a preset change threshold, further includes: S21: Based on the historical change trajectory of each state variable in the community supply and demand state space, construct the corresponding state stability interval and calculate the degree of deviation of the current state variable in the state stability interval. S22: Determine whether the degree of offset exceeds a preset deviation threshold; S23: If so, obtain the deviation distance between the current state and the boundary of the stable state region, identify the corresponding state breakthrough direction based on the deviation distance, construct the state deviation trajectory through the state breakthrough direction, and regenerate the state reconstruction region of the corresponding state variable based on the state deviation trajectory.

[0033] In this embodiment, the system constructs a corresponding stable interval based on the historical change trajectory of each state variable in the community supply and demand state space, calculates the deviation of the current state variable within this stable interval, and then determines whether the deviation exceeds a preset deviation threshold to execute corresponding steps. For example, if the system determines that the deviation of the current state variable within the stable interval does not exceed the preset deviation threshold, the system considers it to be within the stable operating interval of the community supply and demand state space and will not cause a continuous imbalance in the supply and demand relationship or a significant change in the scheduling structure. The system marks the current state variable as a stable state variable and adaptively corrects the corresponding stable interval based on the current state variable to ensure that the stable interval reflects the latest normal operating state. Simultaneously, the system adds the historical change trajectory corresponding to the current state variable to the historical trajectory set. For example, if the system determines that the deviation of the current state variable within the stable interval exceeds the preset deviation threshold, the system considers the current state variable to have deviated from the historical normal operating state. The fluctuation range indicates that a significant change has occurred in the local operating state within the community supply and demand state space. This change is no longer a random fluctuation or short-term disturbance, but rather has a trend of continuous development or further expansion. The system acquires the deviation distance between the current state and the boundary of the stable zone of that state. Based on different deviation distances, it identifies the corresponding state breakout direction and constructs the corresponding state deviation trajectory. Based on these state deviation trajectories, it regenerates the state reconstruction region for the corresponding state variables. Through the state deviation trajectory, the system can not only reflect the direction and magnitude of state changes, but also accurately grasp the development speed, duration, and evolution trend of state changes. This effectively distinguishes between continuously evolving abnormal states and short-term fluctuation states, improving the completeness and accuracy of the community supply and demand state space operating state analysis. At the same time, through the dynamic updating of the state reconstruction region, the community supply and demand state space can adapt in a timely manner to long-term operating characteristics such as changes in order scale, fluctuations in service resources, and changes in the community environment, ensuring that subsequent state judgments and dynamic event identification are always based on the current operating state.

[0034] It should be noted that the process involves obtaining the deviation distance between the current state and the boundary of the stable state region, identifying the corresponding state breakout direction based on the deviation distance, constructing a state deviation trajectory using the state breakout direction, and regenerating the state reconstruction region of the corresponding state variable based on the state deviation trajectory. Specifically: The system reads the real-time value of the current state variable and determines the upper and lower boundaries of its corresponding stable interval. If the current state variable is higher than the upper boundary of the stable interval, the system calculates the difference between the current state value and the upper boundary; if it is lower than the lower boundary of the stable interval, the system calculates the difference between the current state value and the lower boundary, and uses this difference as the deviation distance. For example, in Community A from 14:00 to 15:00, the historical statistics show that the stable interval for the number of orders to be assigned is 80 to 100. The system collects 116 orders to be assigned in real time. Therefore, the deviation distance between the current state and the upper boundary of the stable interval (100 orders) is 16 orders. Similarly, if the stable interval for the number of online service personnel is 28 to 35, and only 24 are currently online, the system calculates the deviation distance from the lower boundary as 4 people. Subsequently, the system identifies the corresponding state breakthrough direction based on the deviation distance. Specifically, the system combines the direction of the deviation distance, the rate of change, and continuous sampling results to determine the development direction of the state variable. When the state variable is continuously higher than the upper boundary of the stable state region, it is identified as an upward breakthrough direction; when the state variable is continuously lower than the lower boundary of the stable state region, it is identified as a downward breakthrough direction. If the deviation distance continues to increase over multiple sampling periods, it is determined that the breakthrough trend is still strengthening. For example, in five consecutive sampling periods, the number of orders to be allocated was 103, 108, 111, 114, and 116, with corresponding deviation distances of 3, 8, 11, 14, and 16, respectively. The system identifies the state breakthrough direction as a continuous upward breakthrough. At the same time, the number of online service personnel was 27, 26, 25, 24, and 24, respectively, with the deviation distance gradually increasing. The system identifies the state breakthrough direction as a continuous downward breakthrough, indicating that the imbalance between supply and demand in the community is continuously expanding. After identifying the direction of the state deviation, the system correlates the continuously collected state values ​​in chronological order to construct a state deviation trajectory. This trajectory records not only the direction of change of state variables but also the deviation distance, rate of change, and duration at each sampling moment, thus forming a complete state evolution process. For example, for the number of orders to be assigned, the system generates a state deviation trajectory of "103→108→111→114→116" and calculates that the number of orders increases by approximately 3 per sampling period on average. For the number of online service personnel, a state deviation trajectory of "27→26→25→24→24" is generated, reflecting a continuous decrease in service resources but with a gradually slowing rate of decline. Through the state deviation trajectory, the system can identify whether the current state is a short-term, drastic change or a sustained, slow change, providing a basis for subsequent state adjustments. Finally, the system regenerates the state reconstruction zone for the corresponding state variables based on the state deviation trajectory. Specifically, the system comprehensively analyzes the deviation magnitude, breakthrough direction, duration, and rate of change in the state deviation trajectory, dynamically corrects the original stable state zone, and generates a state reconstruction zone that better reflects the current operating state. For example, based on the state deviation trajectory over a recent period, the system finds that the number of orders to be allocated has remained stable between 110 and 125 orders for a long time. Therefore, the original stable state range is adjusted from 80 to 100 orders to a new state reconstruction zone of 108 to 126 orders. At the same time, the number of online service personnel has remained consistently between 22 and 27 people. Therefore, the original stable state range is adjusted from 28 to 35 people to a new state reconstruction zone of 22 to 28 people. After the adjustment, the system uses the state reconstruction zone as a new state reference benchmark to continue calculating the degree of deviation for subsequently collected state variables. This allows the community supply and demand state space to adaptively update with long-term changes in order scale, service resources, and the community environment, thereby improving the accuracy and stability of dynamic event recognition and supply and demand resource scheduling.

[0035] In this embodiment, step S4, which determines whether the change in revenue is lower than the preset disturbance cost, further includes: S41: Based on the historical scheduling revenue data pre-collected by the life service platform, construct a corresponding revenue fluctuation range, and generate a revenue buffer according to the revenue fluctuation range; S42: Determine whether the current change in revenue exceeds the revenue buffer; S43: If so, calculate the profit deviation of the current profit change in the profit buffer, dynamically correct the profit change value based on the profit deviation, generate a profit correction result, calculate the corresponding profit disturbance ratio through the profit correction result, and obtain the comparison result of the profit disturbance ratio and the preset disturbance cost.

[0036] In this embodiment, the system constructs a corresponding revenue fluctuation range based on historical scheduling revenue data pre-collected by the life service platform. Based on this revenue fluctuation range, a corresponding revenue buffer is generated. The system then determines whether the current revenue change exceeds the revenue buffer to execute the corresponding steps. For example, if the system determines that the current revenue change does not exceed the revenue buffer, it considers the current scheduling optimization behavior to be an acceptable minor fluctuation adjustment, rather than a critical disturbance requiring revenue-driven rescheduling. The system records the current revenue change value in the historical revenue fluctuation dataset for dynamic updates to the revenue fluctuation range and revenue buffer, while maintaining the current supply-demand matching scheme and scheduling execution sequence unchanged, only continuing to monitor the revenue change trend in subsequent periods. Conversely, if the system determines that the current revenue change exceeds the revenue buffer, it considers the current scheduling result to have deteriorated in terms of resource utilization efficiency, order completion efficiency, or service matching quality. When a significant deterioration or abnormal optimization signal is detected, the system calculates the deviation of the current revenue change from the revenue buffer. Based on different revenue deviations, it dynamically corrects the revenue change value, generating a revenue correction result. Using these correction results, it calculates the corresponding revenue disturbance ratio and compares this ratio with a pre-set disturbance cost. By introducing revenue deviation as an intermediate quantitative indicator, the system can distinguish between different revenue deviation scenarios, such as mild, moderate, and severe out-of-bounds errors. This avoids the misjudgment problems caused by the "one-size-fits-all" anomaly judgment in traditional methods, thereby improving the accuracy and fine-grained analysis capability of identifying abnormal revenue fluctuations. Compared to judging solely based on revenue increases or decreases, the system can simultaneously consider the revenue changes brought about by scheduling adjustments and the system disturbance cost, thus more accurately determining whether it is worthwhile to trigger rescheduling or local optimization adjustments. This improves the cost sensitivity and overall resource allocation efficiency of the community life service system during dynamic scheduling.

[0037] It should be noted that the calculation involves the deviation of the current revenue change from the revenue buffer, and based on this deviation, the revenue change value is dynamically adjusted to generate a revenue adjustment result. Using this adjustment result, the corresponding revenue disturbance ratio is calculated, and a comparison between this ratio and a preset disturbance cost is obtained. Specifically: The system reads the change in revenue after the current rescheduling and obtains the upper and lower boundaries of the corresponding revenue buffer. It calculates the revenue deviation based on the extent to which the current revenue change exceeds the boundaries. For example, if the revenue buffer established by the system is 8% to 12% based on historical scheduling revenue statistics, and the revenue change after the current rescheduling reaches 16%, then the system calculates the current revenue deviation as 4%. Or, if the revenue buffer is -5% to 5%, and the current revenue change is -9%, then the system calculates the revenue deviation as 4%. The revenue deviation can intuitively reflect the degree to which the current revenue change deviates from the historical normal revenue range. Subsequently, the system dynamically adjusts the revenue change value based on the revenue deviation, generating a revenue adjustment result. Specifically, the system adjusts the original revenue change value according to the revenue deviation, so that the revenue evaluation considers not only the magnitude of revenue increase or decrease, but also the stability of the revenue change relative to historical fluctuation levels. When the revenue deviation is small, the system only makes a small adjustment; when the revenue deviation continues to increase, the weight of the revenue change value on the scheduling decision is appropriately reduced to avoid misjudgment caused by extreme revenue data. For example, in the above embodiment, the current revenue change is 16%, and the revenue deviation is 4%. The system adjusts the revenue change to 14.5% according to the preset adjustment rules. If the revenue change of another scheduling scheme reaches 22%, corresponding to a revenue deviation of 10%, the system adjusts it to 17%, avoiding overestimation of the actual value of the scheduling scheme due to abnormal revenue fluctuations, thereby obtaining a revenue adjustment result that is more consistent with the system's operating state. After obtaining the revenue correction result, the system further calculates the corresponding revenue disturbance ratio. Specifically, the system considers the revenue correction result and disturbance factors such as the scale of resource adjustments, the number of order reallocations, and the number of service path changes caused by the rescheduling to calculate the proportional relationship between revenue improvement and scheduling disturbance. For example, if a rescheduling results in a revenue correction of 14.5%, involving the reallocation of 18 orders, adjustments to 6 service personnel, and 12 new path adjustments, the system calculates a revenue disturbance ratio of 1.82. Another scheduling scheme, while achieving a revenue correction of 17%, requires the reallocation of 45 orders and adjustments to 16 service personnel, resulting in a final revenue disturbance ratio of only 0.96. Then, the system compares the revenue perturbation ratio with the pre-set perturbation cost. For example, if the minimum revenue perturbation ratio corresponding to the preset perturbation cost is 1.20, then the first scheme, since 1.82 > 1.20, indicates that the revenue increase can cover the perturbation cost brought by the rescheduling, and subsequent scheduling optimization can continue. However, the second scheme, since 0.96 < 1.20, indicates that the revenue increase is insufficient to offset the scheduling perturbation cost, and the system abandons the rescheduling scheme and maintains the existing supply and demand matching relationship. Through the above processing, the system can comprehensively consider the revenue increase effect and scheduling cost, avoid making decisions based solely on the magnitude of revenue changes, and improve the economy, stability, and overall optimization efficiency of the dynamic scheduling of the community life service platform.

[0038] In this embodiment, step S1, which involves collecting supply and demand status data from the life service platform based on a preset community supply and demand status space and mapping the supply and demand status data from different sources to the community supply and demand status space, further includes: S11: Collect the state correlation relationship between the supply and demand state data from different sources, and construct a state fusion trusted domain based on the state correlation relationship, wherein the state fusion trusted domain is used to characterize the trusted fusion range of each supply and demand state data in a unified state space; S12: Determine whether the state fusion trusted domain satisfies the preset trusted mapping condition; S13: If not, identify conflicting supply and demand status objects, dynamically adjust the mapping relationship of the corresponding supply and demand status data based on the supply and demand status objects, and update the status fusion trusted domain to the life service platform in real time.

[0039] In this embodiment, the system collects state correlations between supply and demand state data from different sources. Based on these correlations, it constructs corresponding state fusion trusted domains. These domains characterize the trusted fusion range of each supply and demand state data within a unified state space. The system then determines whether the trusted fusion domain meets pre-defined trusted mapping conditions to execute corresponding steps. For example, if the system determines that the trusted fusion domain meets pre-defined trusted mapping conditions, it considers the current state fusion result to have the conditions for effective mapping to the community supply and demand state space, and it can serve as the basic data input for subsequent scheduling and analysis. The system determines the final trusted fusion state based on the trusted fusion domain, performs weighted fusion or consistency mapping on the supply and demand state data from different sources according to their corresponding state correlations, generates a unified state expression result, and maps this unified state result to the corresponding state variable nodes in the preset community supply and demand state space. It updates the current values ​​and correlations of each state variable, enabling the state space to reflect the changes in the supply and demand state data. The system reflects the actual operating state after fusion. For example, if the system determines that the fused state trust domain cannot meet the pre-set trust mapping conditions, it will consider that the consistency of supply and demand state data from different sources in the unified state space is insufficient, and there are significant deviations, conflicts, or weak correlations between the data sources, resulting in the fused state information not forming a stable and consistent expression result. The system will identify the conflicting supply and demand state objects, and based on these supply and demand state objects, dynamically adjust the mapping relationship of the corresponding supply and demand state data, and update the fused state trust domain to the life service platform in real time. Through the dynamic mapping adjustment mechanism, the system can continuously maintain the state fusion capability under the condition of fluctuations in the quality or structural changes of multi-source data, improve the robustness and flexibility of multi-source heterogeneous data fusion, and at the same time, after adjusting the mapping relationship, the updated fused state trust domain is sent back to the life service platform in real time, so that the trust domain structure can be dynamically corrected and iteratively updated according to the latest conflict resolution results, thus forming a closed-loop optimization mechanism of "identifying conflicts - adjusting mappings - updating trust domains".

[0040] It should be noted that, in order to identify conflicting supply and demand status objects, the mapping relationship of the corresponding supply and demand status data is dynamically adjusted based on the supply and demand status objects, and the status fusion trusted domain is updated to the life service platform in real time. Specifically: The system first compares the supply and demand status data participating in the integration item by item to identify conflicting supply and demand status objects. These objects include status subjects such as resident orders, service personnel, community resources, and the community environment. The system integrates the timestamps, attribute information, and relationships of the status objects from various data sources to determine the specific objects causing the conflict. For example, in a community, platform location data indicates that service personnel S1 is near Building 3 of Community A, while the location uploaded by the service personnel's mobile terminal shows that they are located in Commercial Street B, approximately 2.5 kilometers from Community A. Similarly, order O1 is displayed as "pending service" in the order management system, while the service personnel's terminal has reported "service completed." Based on these differences, the system identifies service personnel S1 and order O1 as conflicting supply and demand status objects and records the corresponding conflict type and source. Subsequently, the system dynamically adjusts the mapping relationship of the corresponding supply and demand status data based on the identified supply and demand status objects. Specifically, the system re-establishes the mapping relationship for each supply and demand status data according to the update time, historical reliability, and consistency of the associated status of different data sources, so that the state space prioritizes data with higher reliability. For example, in the above embodiment, the platform location data update time is 14:20:05, while the mobile terminal location update time is 14:20:28. The system determines that the mobile terminal data has higher real-time performance, so it switches the location mapping relationship of service personnel S1 from platform location data to mobile terminal location data. For order O1, since the service completion status simultaneously uploads electronic receipt records and user confirmation information, but the order management system has not yet been updated synchronously, the system adjusts the order status mapping relationship to use the service completion record as the current valid status, and synchronously corrects the supply and demand association relationship between the order and the service personnel. By dynamically adjusting the mapping relationship, the system can eliminate state conflicts between different data sources, making the state expression in the unified state space more accurate. After the mapping relationship adjustment is completed, the system updates the state fusion trusted domain to the life service platform in real time. Specifically, the system recalculates the consistency and trusted fusion range between each supply and demand state object based on the new mapping relationship, and generates the latest state fusion trusted domain. For example, in the original state fusion trusted domain, the location trustworthiness of service personnel S1 was only 0.58, and the status trustworthiness of order O1 was 0.61, which did not meet the trusted mapping conditions set by the platform. After the mapping adjustment is completed, the location trustworthiness of service personnel S1 is increased to 0.93, and the status trustworthiness of order O1 is increased to 0.96. Based on this, the system regenerates the updated state fusion trusted domain and updates it synchronously to the community supply and demand status space in the life service platform. Subsequently, when the platform performs status change detection, dynamic event recognition, and supply and demand resource scheduling, it directly analyzes based on the updated state fusion trusted domain, thereby ensuring that supply and demand status data from different sources are always consistent, trustworthy, and traceable, improving the accuracy of multi-source data fusion in the community life service platform and the reliability of subsequent dynamic scheduling decisions.

[0041] Reference Appendix Figure 2 A supply and demand intelligent scheduling system for community life services, as described in one embodiment of the present invention, includes: The data acquisition module 10 is used to collect supply and demand status data in the life service platform based on the community supply and demand status space preset by the life service platform, and to uniformly map the supply and demand status data from different sources to the community supply and demand status space. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information and historical scheduling information. The judgment module 20 is used to determine whether the state change of the community supply and demand state space exceeds a preset change threshold. The execution module 30 is used to identify the dynamic event type that causes the state change if the state change is true, generate a corresponding event description object according to the dynamic event type, calculate the event impact range of the event description object, establish a dynamic local scheduling network of the community supply and demand state space based on the event impact range, and obtain the change in revenue of the supply and demand matching scheme after rescheduling. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. The second judgment module 40 is used to determine whether the change in revenue is lower than the preset disturbance cost; The second execution module 50 is used to identify the corresponding node information based on the resource competition index pre-calculated by the life service platform if the resource competition index is not lower than the local supply and demand influence domain of the dynamic local scheduling network, recalculate the order scheduling priority of the local supply and demand influence domain, output a local scheduling execution sequence, dynamically adjust the supply and demand correspondence in the local supply and demand influence domain according to the local scheduling execution sequence, and synchronously update the supply and demand correspondence to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

[0042] In this embodiment, the acquisition module 10 collects supply and demand status data from the community supply and demand status virtual space pre-set in the life service platform. This data specifically includes resident order information, service personnel status information, community environment information, and historical scheduling information. Supply and demand status data from different sources are uniformly mapped to the community supply and demand status space. Then, the judgment module 20 determines whether the status change of the community supply and demand status space exceeds a pre-set threshold, and executes corresponding steps accordingly. For example, if the system determines that the status change of the community supply and demand status space does not exceed the pre-set threshold, the system considers the existing supply and demand relationship to be able to continue to meet the current service demand, without triggering a rescheduling process. The system maintains the current supply and demand matching scheme unchanged and synchronously updates the acquired supply and demand status data to the historical status cache corresponding to the community supply and demand status space to correct the status baseline of the community supply and demand status space. Conversely, if the system determines that the status change of the community supply and demand status space exceeds the pre-set threshold, the execution module 30 considers the existing supply and demand relationship to be unable to meet the current service demand, requiring a rescheduling process. The system identifies the dynamic event type that caused the status change. The specific events include new order events, service personnel offline events, service personnel location abnormality events, user order cancellation events, user appointment time modification events, community traffic abnormality events, and service timeout events. Based on different dynamic event types, corresponding event description objects are generated, and the event impact range of these event description objects is calculated. Based on different event impact ranges, a dynamic local scheduling network for the community supply and demand state space is established to obtain the change in revenue after rescheduling of the supply and demand matching scheme. Then, the second judgment module 40 judges whether the change in revenue after rescheduling of the supply and demand matching scheme is lower than a pre-set disturbance cost, and executes the corresponding steps accordingly. For example, when the system determines that the change in revenue after rescheduling of the supply and demand matching scheme is lower than the pre-set disturbance cost, the system considers that the scheduling optimization benefits brought by the current rescheduling are insufficient to offset the disturbance costs generated during the rescheduling process, such as service resource reallocation, order execution order adjustment, and service personnel path changes. The system will maintain the current supply and demand correspondence and supply and demand matching scheme unchanged, and record the current revenue change result and the corresponding event description object in the scheduling decision history database, while updating the continuous impact status of the corresponding event, and continuing to monitor the dynamic local scheduling network in real time.For example, when the system determines that the change in revenue after rescheduling of the supply-demand matching scheme is not lower than the pre-set disturbance cost, the second execution module 50 will consider that the scheduling optimization benefits brought by the current rescheduling can offset the disturbance cost generated during the rescheduling process. The system will then identify the corresponding node information based on the resource competition index pre-calculated by the life service platform. This index specifically includes the number of service orders, the number of service personnel, the current task load, the estimated completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes. Based on the local supply-demand influence domain of the dynamic local scheduling network, the system will recalculate the order scheduling priority of the local supply-demand influence domain (the scheduling priority considers factors such as order urgency, remaining service time window time, service skill scarcity, user waiting time, remaining service personnel capacity, and the degree of resource balance in the community area). The system will then output a local scheduling execution sequence. Based on this local scheduling execution sequence, the system will dynamically adjust the supply-demand correspondence in the local supply-demand influence domain and synchronously update this correspondence in the community supply-demand state space.

[0043] In this embodiment, it also includes: The construction module is used to collect the state change process of the corresponding subject within a preset period based on the real-time operation data pre-collected by the life service platform, and to connect the state change processes in series to construct the corresponding state change association chain. The third judgment module is used to determine whether the state change association chain has a continuous evolution trend; The third execution module is used to, if yes, establish directed connections between state nodes according to the order of state changes, calculate the change propagation relationship between adjacent state nodes, obtain the state evolution trajectory, detect repeated changes in the state evolution trajectory, merge the repeated changes, dynamically remove abnormal state nodes caused by sampling errors, generate standard event evolution trajectories, statistically analyze the change combination relationships between the standard event evolution trajectories, and map the change combination relationships to a pre-established event pattern library.

[0044] In this embodiment, the system collects real-time operational data pre-collected by the life service platform, gathers the state change process of the corresponding subject within a pre-set period, strings these state change processes together to construct corresponding state change correlation chains, and then determines whether these state change correlation chains have a continuous evolution trend in order to execute the corresponding steps. For example, when the system determines that these state change correlation chains do not have a continuous evolution trend, the system will consider the current state change of the subject to be only a short-term fluctuation or occasional change, without forming a continuous propagation or continuous expansion trend. The system will mark the current state change correlation chain as a transient change correlation chain, store the corresponding state change process in the historical evolution database, and update the normal change baseline and fluctuation characteristic parameters of the corresponding subject according to the state change correlation chain, and continue to collect data according to the pre-set schedule. The system periodically collects real-time operational data of the corresponding entity and continuously updates the state change process obtained later by connecting it to the state change association chain. For example, when the system determines that these state change association chains have a continuous evolution trend, the system will consider that the current entity's state change has formed a continuous propagation or continuous expansion trend. The system will establish directed connection relationships between state nodes according to the order of state change occurrence, calculate the change transmission relationship between adjacent state nodes, obtain the state evolution trajectory, detect repeated change states in the state evolution trajectory, merge these repeated change states, dynamically remove abnormal state nodes caused by sampling errors, generate standard event evolution trajectories, statistically analyze the change combination relationships between these standard event evolution trajectories, and map these change combination relationships to a pre-established event pattern library.

[0045] In this embodiment, the execution module further includes: The calculation submodule is used to identify the target resource directly affected by the event based on the record identifier in the event description object, recursively search the resource association relationship in the community supply and demand state space with the target resource as the starting node, obtain the associated resource nodes that have a resource dependency relationship with the target resource, generate the corresponding resource propagation structure, and calculate the propagation contribution value of each resource node according to the resource propagation structure. The record identifier specifically includes event attributes, associated resources, and event occurrence process. The judgment submodule is used to determine whether the propagation contribution value has reached the preset propagation condition; The execution submodule is used to, if not, divide the current resource node into a propagation boundary node, interrupt the propagation analysis of the corresponding resource branch, establish a corresponding event propagation region based on the preset propagation boundary node, reorganize the resource association relationships in the event propagation region, construct a resource influence topology, collect resource association characteristics between different resource nodes through the resource influence topology, and generate a dynamic resource collaboration relationship set, wherein the resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

[0046] In this embodiment, the system identifies target resources directly affected by the event based on the record identifier corresponding to the event description object. The record identifier specifically includes event attributes, associated resources, and the event occurrence process. Using these target resources as starting nodes, the system recursively searches for resource relationships in the community supply and demand state space to obtain associated resource nodes that have resource dependencies on these target resources. A corresponding resource propagation structure is generated, and the propagation contribution value of each resource node is calculated based on different resource propagation structures. The system then determines whether these propagation contribution values ​​meet pre-set propagation conditions to execute corresponding steps. For example, when the system determines that the propagation contribution values ​​of each resource node meet the pre-set propagation conditions, the system considers the event to have evolved from a locally impactful event into an extended impactful event with a propagation effect. The system marks resource nodes with propagation contribution values ​​exceeding a threshold as key propagation nodes and, based on the resource propagation structure, assigns key propagation nodes to appropriate propagation nodes. The propagation path is subjected to hierarchical clustering to form a multi-level resource influence subgraph. At the same time, high-contribution nodes are marked with priority to be used as the basis for resource priority allocation in subsequent scheduling calculations. For example, when the system determines that the propagation contribution value of each resource node cannot reach the pre-set propagation conditions, the system will consider that the impact of the current event on the resource association structure in the community supply and demand state space is still limited to the local target resource and its first-order neighboring resource nodes. The system will divide the current resource node into a propagation boundary node, interrupt the propagation analysis of the corresponding resource branch, establish the corresponding event propagation region based on the pre-set propagation boundary node, reorganize the resource association relationship in the event propagation region, and construct the corresponding resource influence topology. Through this resource influence topology, the resource association characteristics between different resource nodes are collected. The resource association characteristics specifically include resource substitution ability, resource competition ability, and resource coordination ability, generating a dynamic resource coordination relationship set.

[0047] In this embodiment, the second execution module further includes: A submodule is constructed to calculate the dynamic execution window corresponding to each order node based on the task dependency relationship between each order node in the local supply and demand influence domain, generate several candidate scheduling sequences according to the overlap relationship between the dynamic execution windows, and construct the sequence conflict evaluation result corresponding to each candidate scheduling sequence respectively. The second judgment submodule is used to determine whether the sequence conflict evaluation result meets the preset sequence feasibility conditions; The second execution submodule is used to locate the conflict constraint node that causes the sequence conflict if not, obtain the associated execution node with a direct execution relationship from the conflict constraint node, establish a corresponding conflict association subgraph based on the associated execution node, and identify the adjacent order node that causes the conflict to spread in the conflict association subgraph. The associated execution node specifically includes the preceding order node, the following order node, and the shared resource node.

[0048] In this embodiment, the system calculates the dynamic execution window corresponding to each order node based on the task dependency relationship between each order node within the local supply and demand influence domain. Based on the overlap relationship between these dynamic execution windows, several candidate scheduling sequences are generated. Sequence conflict evaluation results are constructed for each candidate scheduling sequence. The system then determines whether the sequence conflict evaluation result meets the preset sequence feasibility conditions to execute the corresponding steps. For example, when the system determines that the sequence conflict evaluation result meets the preset sequence feasibility conditions, the system considers the current candidate scheduling sequence to have executability and time consistency, and can be used as an effective local scheduling execution scheme. The system selects the candidate scheduling sequence that meets the preset sequence feasibility conditions as the target local scheduling execution sequence. Based on this target local scheduling execution sequence, the order nodes within the local supply and demand influence domain are sequentially fixed, and the system simultaneously locks the order nodes' dependencies. Based on the corresponding service resource allocation relationship, the system synchronously adjusts the path planning of service personnel and the order of task execution according to the execution sequence to generate the final local scheduling execution plan. For example, when the system determines that the sequence conflict evaluation result cannot meet the preset sequence feasibility conditions, the system will consider that there are inescapable resource occupation conflicts, task execution time conflicts, or task dependency conflicts in the current candidate scheduling sequence. The dynamic execution windows between the order nodes in the local supply and demand influence domain cannot form a continuous execution relationship that satisfies the scheduling constraints. The system will locate the conflict constraint nodes that cause the sequence conflict and obtain the associated execution nodes with direct execution relationships from these conflict constraint nodes. The associated execution nodes specifically include the preceding order nodes, the following order nodes, and the shared resource nodes. Based on the different associated execution nodes, a corresponding conflict association subgraph is established. In this conflict association subgraph, the adjacent order nodes that cause the conflict to spread are identified.

[0049] In this embodiment, the determination module further includes: The calculation submodule is used to construct a corresponding stable interval based on the historical change trajectory of each state variable in the community supply and demand state space, and to calculate the degree of deviation of the current state variable in the stable interval. The third judgment submodule is used to determine whether the degree of offset exceeds a preset deviation threshold. The third execution submodule is used to, if yes, obtain the deviation distance between the current state and the boundary of the stable state region, identify the corresponding state breakthrough direction based on the deviation distance, construct the state deviation trajectory through the state breakthrough direction, and regenerate the state reconstruction region of the corresponding state variable based on the state deviation trajectory.

[0050] In this embodiment, the system constructs a corresponding stable state interval based on the historical change trajectory of each state variable in the community supply and demand state space. It calculates the deviation of the current state variable within this stable state interval and then determines whether the deviation exceeds a preset deviation threshold to execute corresponding steps. For example, if the system determines that the deviation of the current state variable within the stable state interval does not exceed the preset deviation threshold, the system considers it to be within the stable operating range of the community supply and demand state space and unlikely to cause a continuous imbalance in supply and demand or significant changes in the scheduling structure. The system then marks the current state variable as a stable state variable and adaptively corrects the corresponding stable state interval based on the current state variable, ensuring that the stable state interval reflects the latest positive trend. In normal operation, the system simultaneously appends the historical change trajectory corresponding to the current state variable to the historical trajectory set. For example, when the system determines that the deviation of the current state variable in the stable range of the state exceeds the preset deviation threshold, the system will consider that the current state variable has deviated from the normal historical fluctuation range, and the local operating state in the community supply and demand state space has changed significantly. Moreover, this change is no longer a random fluctuation or short-term disturbance, but has a trend of continuous development or further expansion. The system will obtain the deviation distance between the current state and the boundary of the stable region of the state, identify the corresponding state breakthrough direction based on different deviation distances, construct the corresponding state deviation trajectory through the state breakthrough direction, and regenerate the state reconstruction region of the corresponding state variable based on these state deviation trajectories.

[0051] In this embodiment, the second determination module further includes: The generation submodule is used to construct a corresponding revenue fluctuation range based on the historical scheduling revenue data pre-collected by the life service platform, and generate a revenue buffer based on the revenue fluctuation range. The fourth judgment submodule is used to determine whether the current change in revenue exceeds the revenue buffer. The fourth execution submodule is used to calculate the profit deviation of the current profit change in the profit buffer if the condition is met, dynamically correct the profit change value based on the profit deviation, generate a profit correction result, calculate the corresponding profit disturbance ratio based on the profit correction result, and obtain the comparison result between the profit disturbance ratio and the preset disturbance cost.

[0052] In this embodiment, the system constructs a corresponding revenue fluctuation range based on historical scheduling revenue data pre-collected by the life service platform. Based on this revenue fluctuation range, a corresponding revenue buffer is generated. The system then determines whether the current revenue change exceeds the revenue buffer to execute corresponding steps. For example, if the system determines that the current revenue change does not exceed the revenue buffer, it considers the current scheduling optimization behavior to be an acceptable minor fluctuation adjustment, rather than a critical disturbance requiring revenue-driven rescheduling. The system records the current revenue change value in the historical revenue fluctuation dataset for dynamic updates to the revenue fluctuation range and revenue buffer. The system maintains the current supply and demand matching scheme and scheduling execution sequence unchanged, and only continues to monitor the revenue change trend in subsequent cycles. For example, when the system determines that the current revenue change exceeds the revenue buffer, the system will consider that the current scheduling result has shown obvious deterioration or abnormal optimization signals in terms of resource utilization efficiency, order completion efficiency or service matching quality. The system will calculate the revenue deviation of the current revenue change in the revenue buffer, dynamically correct the revenue change value according to different revenue deviations, generate revenue correction results, calculate the corresponding revenue disturbance ratio through these revenue correction results, and obtain the comparison result of the revenue disturbance ratio with the pre-set disturbance cost.

[0053] In this embodiment, the acquisition module further includes: The second construction submodule is used to collect the state correlation between the supply and demand state data from different sources, and construct a state fusion trusted domain based on the state correlation, wherein the state fusion trusted domain is used to characterize the trusted fusion range of each supply and demand state data in a unified state space. The fifth judgment submodule is used to determine whether the state fusion trust domain satisfies the preset trust mapping conditions; The fifth execution submodule is used to identify conflicting supply and demand status objects if no conflict exists, dynamically adjust the mapping relationship of the corresponding supply and demand status data based on the supply and demand status objects, and update the status fusion trusted domain to the life service platform in real time.

[0054] In this embodiment, the system collects state correlations between supply and demand state data from different sources. Based on these correlations, it constructs corresponding state fusion trust domains. These trust domains characterize the trustworthy fusion range of each supply and demand state data within a unified state space. The system then determines whether the state fusion trust domain meets pre-defined trustworthy mapping conditions to execute corresponding steps. For example, if the system determines that the state fusion trust domain meets pre-defined trustworthy mapping conditions, it considers the current state fusion result to have the conditions for effective mapping to the community supply and demand state space, and it can serve as the basic data input for subsequent scheduling and analysis. The system determines the final trustworthy fusion state based on the state fusion trust domain and performs weighted fusion or consistency fusion of supply and demand state data from different sources according to their corresponding state correlations. The mapping process generates a unified state representation result, which is then mapped to the corresponding state variable nodes in the preset community supply and demand state space. The current values ​​of each state variable and their relationships are updated so that the state space can reflect the actual operating state after fusion. For example, if the system determines that the trusted domain of the state fusion cannot meet the preset trusted mapping conditions, the system will consider that the consistency of supply and demand state data from different sources in the unified state space is insufficient, and there are significant deviations, conflicts, or weak correlations between the data sources, resulting in the inability of the fused state information to form a stable and consistent representation result. The system will identify the conflicting supply and demand state objects, dynamically adjust the mapping relationship of the corresponding supply and demand state data based on these supply and demand state objects, and update the trusted domain of the state fusion to the life service platform in real time.

[0055] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent supply and demand scheduling of community life services, characterized in that, Includes the following steps: Based on the community supply and demand status space preset by the life service platform, supply and demand status data in the life service platform are collected, and the supply and demand status data from different sources are uniformly mapped to the community supply and demand status space. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information, and historical scheduling information. Determine whether the state change of the community supply and demand state space exceeds a preset change threshold; If so, the dynamic event type that caused the state change is identified, and a corresponding event description object is generated according to the dynamic event type. The event impact range of the event description object is calculated, and a dynamic local scheduling network of the community supply and demand state space is established based on the event impact range. The change in revenue of the supply and demand matching scheme after rescheduling is obtained. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. Determine whether the change in revenue is lower than the preset disturbance cost; If the value is not lower than the target value, then based on the resource competition index pre-calculated by the life service platform, the corresponding node information is identified. According to the local supply and demand influence domain of the dynamic local scheduling network, the order scheduling priority of the local supply and demand influence domain is recalculated, and a local scheduling execution sequence is output. Based on the local scheduling execution sequence, the supply and demand correspondence in the local supply and demand influence domain is dynamically adjusted, and the supply and demand correspondence is synchronously updated to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

2. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, Before the step of identifying the type of dynamic event that causes the state change and generating a corresponding event description object based on the dynamic event type, the method further includes: Based on the real-time operation data pre-collected by the life service platform, the state change process of the corresponding subject within a preset period is collected, and the state change process is connected in series to construct a corresponding state change association chain. Determine whether the state change association chain has a continuous evolutionary trend; If so, then according to the order of state changes, a directed connection relationship is established between state nodes, the change transmission relationship between adjacent state nodes is calculated, a state evolution trajectory is obtained, repeated change states in the state evolution trajectory are detected, the repeated change states are merged, abnormal state nodes caused by sampling errors are dynamically removed, a standard event evolution trajectory is generated, the change combination relationship between the standard event evolution trajectories is statistically analyzed, and the change combination relationship is mapped to a pre-established event pattern library respectively.

3. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, The steps of calculating the event impact range of the event description object, establishing a dynamic local scheduling network for the community supply and demand state space based on the event impact range, and obtaining the change in revenue of the supply and demand matching scheme after rescheduling, further include: Based on the record identifier in the event description object, the target resource directly affected by the event is identified. Taking the target resource as the starting node, the resource association relationship in the community supply and demand state space is recursively searched to obtain the associated resource nodes that have a resource dependency relationship with the target resource. The corresponding resource propagation structure is generated. According to the resource propagation structure, the propagation contribution value of each resource node is calculated. The record identifier specifically includes event attributes, associated resources, and event occurrence process. Determine whether the propagation contribution value meets the preset propagation conditions; If not, the current resource node is divided into a propagation boundary node, the propagation analysis of the corresponding resource branch is interrupted, and a corresponding event propagation region is established based on the preset propagation boundary node. The resource association relationships in the event propagation region are reorganized to construct a resource influence topology. Through the resource influence topology, the resource association characteristics between different resource nodes are collected to generate a dynamic resource collaboration relationship set. The resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

4. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, The step of recalculating the order scheduling priority of the local supply and demand influence domain based on the local supply and demand influence domain of the dynamic local scheduling network and outputting the local scheduling execution sequence further includes: Based on the task dependency relationship between each order node within the local supply and demand influence domain, the dynamic execution window corresponding to each order node is calculated. According to the overlap relationship between the dynamic execution windows, several candidate scheduling sequences are generated, and the sequence conflict evaluation results corresponding to each candidate scheduling sequence are constructed respectively. Determine whether the sequence conflict evaluation result meets the preset sequence feasibility conditions; If not, locate the conflict constraint node that causes the sequence conflict, obtain the associated execution node with a direct execution relationship from the conflict constraint node, establish the corresponding conflict association subgraph based on the associated execution node, and identify the adjacent order nodes that cause the conflict to spread in the conflict association subgraph. The associated execution node specifically includes the preceding order node, the following order node, and the shared resource node.

5. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, The step of determining whether the state change of the community supply and demand state space exceeds a preset change threshold further includes: Based on the historical change trajectory of each state variable in the community supply and demand state space, a corresponding state stability interval is constructed, and the degree of deviation of the current state variable in the state stability interval is calculated. Determine whether the degree of offset exceeds a preset offset threshold; If so, the deviation distance between the current state and the boundary of the stable state region is obtained. Based on the deviation distance, the corresponding state breakout direction is identified. Through the state breakout direction, a state deviation trajectory is constructed. Based on the state deviation trajectory, the state reconstruction region of the corresponding state variable is regenerated.

6. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, The step of determining whether the change in revenue is lower than the preset disturbance cost further includes: Based on the historical scheduling revenue data pre-collected by the life service platform, a corresponding revenue fluctuation range is constructed, and a revenue buffer is generated according to the revenue fluctuation range. Determine whether the current change in revenue exceeds the revenue buffer. If so, the profit deviation of the current profit change in the profit buffer is calculated, and the profit change value is dynamically corrected based on the profit deviation to generate a profit correction result. The corresponding profit disturbance ratio is calculated using the profit correction result, and the comparison result between the profit disturbance ratio and the preset disturbance cost is obtained.

7. The intelligent supply and demand scheduling method for community life services according to claim 1, characterized in that, The step of collecting supply and demand status data from the life service platform based on the community supply and demand status space preset by the life service platform, and uniformly mapping the supply and demand status data from different sources to the community supply and demand status space, further includes: The state correlation between the supply and demand state data is collected from different sources. Based on the state correlation, a state fusion trusted domain is constructed, wherein the state fusion trusted domain is used to characterize the trusted fusion range of each supply and demand state data in a unified state space. Determine whether the state fusion trusted domain satisfies the preset trusted mapping conditions; If not, identify conflicting supply and demand status objects, dynamically adjust the mapping relationship of the corresponding supply and demand status data based on the supply and demand status objects, and update the status fusion trusted domain to the life service platform in real time.

8. A smart supply and demand scheduling system for community life services, characterized in that, include: The data collection module is used to collect supply and demand status data from the life service platform based on the community supply and demand status space preset by the life service platform, and to uniformly map the supply and demand status data from different sources to the community supply and demand status space. The supply and demand status data specifically includes resident order information, service personnel status information, community environment information and historical scheduling information. The judgment module is used to determine whether the state change of the community supply and demand state space exceeds a preset change threshold; The execution module is used to identify the dynamic event type that causes the state change if the state change is true, generate a corresponding event description object according to the dynamic event type, calculate the event impact range of the event description object, establish a dynamic local scheduling network of the community supply and demand state space based on the event impact range, and obtain the change in revenue of the supply and demand matching scheme after rescheduling. The dynamic event type specifically includes new order event, service personnel offline event, service personnel location abnormal event, user order cancellation event, user appointment time modification event, community traffic abnormal event, and service timeout event. The second judgment module is used to determine whether the change in revenue is lower than the preset disturbance cost; The second execution module is used to identify the corresponding node information based on the resource competition index pre-calculated by the life service platform if the resource competition index is not lower than the local supply and demand influence domain of the dynamic local scheduling network, recalculate the order scheduling priority of the local supply and demand influence domain, output a local scheduling execution sequence, dynamically adjust the supply and demand correspondence in the local supply and demand influence domain according to the local scheduling execution sequence, and synchronously update the supply and demand correspondence to the community supply and demand status space. The resource competition index specifically includes the number of service orders, the number of service personnel, the current task load, the expected completion time, and the degree of window overlap. The node information specifically includes competing resource nodes and bottleneck order nodes.

9. The intelligent supply and demand scheduling system for community life services according to claim 8, characterized in that, Also includes: The construction module is used to collect the state change process of the corresponding subject within a preset period based on the real-time operation data pre-collected by the life service platform, and to connect the state change processes in series to construct the corresponding state change association chain. The third judgment module is used to determine whether the state change association chain has a continuous evolution trend; The third execution module is used to, if yes, establish directed connections between state nodes according to the order of state changes, calculate the change propagation relationship between adjacent state nodes, obtain the state evolution trajectory, detect repeated changes in the state evolution trajectory, merge the repeated changes, dynamically remove abnormal state nodes caused by sampling errors, generate standard event evolution trajectories, statistically analyze the change combination relationships between the standard event evolution trajectories, and map the change combination relationships to a pre-established event pattern library.

10. The intelligent supply and demand scheduling system for community life services according to claim 8, characterized in that, The execution module further includes: The calculation submodule is used to identify the target resource directly affected by the event based on the record identifier in the event description object, recursively search the resource association relationship in the community supply and demand state space with the target resource as the starting node, obtain the associated resource nodes that have a resource dependency relationship with the target resource, generate the corresponding resource propagation structure, and calculate the propagation contribution value of each resource node according to the resource propagation structure. The record identifier specifically includes event attributes, associated resources, and event occurrence process. The judgment submodule is used to determine whether the propagation contribution value has reached the preset propagation condition; The execution submodule is used to, if not, divide the current resource node into a propagation boundary node, interrupt the propagation analysis of the corresponding resource branch, establish a corresponding event propagation region based on the preset propagation boundary node, reorganize the resource association relationships in the event propagation region, construct a resource influence topology, collect resource association characteristics between different resource nodes through the resource influence topology, and generate a dynamic resource collaboration relationship set, wherein the resource association characteristics specifically include resource substitution capability, resource competition capability, and resource collaboration capability.

Images