An intelligent property resource scheduling optimization method based on the Internet of Things

Abstract

The application belongs to the technical field of resource scheduling, and provides a property intelligent resource scheduling optimization method based on the Internet of Things, which comprises the following steps: acquiring contradictory event labels, events and associated relations of active feedback and passive sensing of property owners, and constructing a contradictory event dataset; constructing a contradictory path model, inputting the dataset, extracting contradictory transmission paths and similar merging, and obtaining multiple and original contradictory paths; extracting property resource allocation imbalance features during the merging of multiple contradictory paths, and identifying whether there is a superposition effect; if there is, filtering the multiple contradictory path area, and extracting a high-frequency superposition area; based on the high-frequency superposition area and real-time passive sensing features, inputting an intelligent resource allocation model, and realizing intelligent prediction and distribution optimization of the imbalanced property resources. Through the integration of multi-source data and intelligent analysis, the application improves the property resource scheduling efficiency, reduces the probability of contradictory events, and has the advantages of forward-looking and intelligent resource allocation.

Description

Technical Field

[0001] This invention belongs to the field of resource scheduling technology, specifically a property intelligent resource scheduling optimization method based on the Internet of Things. Background Technology

[0002] With the popularization of IoT technology and the advancement of smart community construction, the demand for intelligent and refined resource allocation in property management is growing. Traditional property resource allocation mainly relies on manual feedback and experience-driven decision-making, which has many shortcomings.

[0003] Traditional scheduling methods fail to establish a deep correlation between conflicting events and resource allocation, making it impossible to analyze the transmission path of conflicts. For example, how aging equipment leads to delayed maintenance responses, which in turn causes customer dissatisfaction. Resource allocation is often based on static rules, ignoring the transmission effects between different conflicting events and the cumulative impact of resource imbalances, resulting in low scheduling efficiency.

[0004] Existing technologies lack the ability to integrate and analyze multi-source data, making it difficult to quantify resource allocation imbalances in real time and predict imbalance trends. The allocation of property resources relies on human experience, making it impossible to proactively optimize for areas with high-frequency conflicts. This often leads to a vicious cycle of "passively responding to complaints - temporarily allocating resources," limiting improvements in homeowner satisfaction.

[0005] Therefore, the present invention provides a property intelligent resource scheduling optimization method based on the Internet of Things. Summary of the Invention

[0006] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0007] The technical solution adopted by this invention to solve its technical problem is: a property intelligent resource scheduling optimization method based on the Internet of Things, comprising:

[0008] A property intelligent resource scheduling optimization method based on the Internet of Things includes the following steps:

[0009] Acquire the tags and events of conflicts reported proactively and passively by homeowners and property management, as well as the relationships between these conflicts, and construct a dataset of conflict events.

[0010] A conflict path model is constructed by inputting a dataset of conflict events into the model, extracting conflict transmission paths, and performing similarity merging analysis to obtain a multivariate conflict path.

[0011] Extract the characteristics of imbalance in property resource allocation when multiple conflict paths are merged, and identify whether the characteristics of imbalance in property resource allocation have a cumulative effect;

[0012] If there is a superposition effect, regional screening analysis is performed on the multiple conflict paths to extract the high-frequency superposition areas of all multiple conflict paths;

[0013] Based on the identified high-frequency overlay areas, the passive sensing features collected in real time are input into the intelligent resource allocation model to achieve intelligent prediction of unbalanced property resources and optimize the allocation of property resources.

[0014] Furthermore, the method for constructing the contradictory event dataset is as follows:

[0015] Obtain conflict event tags and event resources and property maintenance resources in the conflict event process, and perform association matching to obtain the conflict association relationship of the conflict events;

[0016] The conflict event tags, event resources in the conflict event process, and property maintenance resources are used as conflict event elements;

[0017] Collect all conflict events between the property management company and the owners, and construct a conflict event dataset by identifying the conflict event elements and their relationships.

[0018] Furthermore, the contradictory path model is implemented as follows:

[0019] Preprocess the input dataset of contradictory events;

[0020] Contradictory relationship graphs are constructed based on the preprocessed dataset of contradictory events.

[0021] The contradiction transmission path is extracted based on the contradiction relationship diagram.

[0022] Furthermore, the similarity merging analysis is performed as follows:

[0023] Extract any two contradictory transmission paths as a path comparison group, extract the two longest common sub-paths of the path comparison group, and calculate the length of any two longest common sub-paths.

[0024] Calculate the similarity between the lengths of any two longest common sub-paths. Obtain the similarity between any two longest common sub-paths within the path comparison group.

[0025] If the similarity of the longest common sub-path is higher than the preset similarity threshold, the contradictory transmission paths of the path comparison group will be merged using a clustering algorithm.

[0026] Furthermore, the method for identifying whether the characteristics of imbalance in the allocation of property resources have a cumulative effect is as follows:

[0027] Based on the characteristics of the imbalance in property resource allocation when multiple conflict paths are merged, an autocorrelation analysis of the characteristics of the imbalance in property resource allocation under multiple conflict paths is conducted by constructing a vector autoregression model.

[0028] If the influence coefficient of the autocorrelation analysis is significantly non-zero, then the imbalance in the allocation of property resources has a cumulative effect.

[0029] Furthermore, the method for obtaining the characteristics of the imbalance in the allocation of property resources is as follows:

[0030] From the process of merging multiple contradictory paths, obtain the original contradictory paths that initially correspond to the multiple contradictory paths;

[0031] Identify the property resource imbalance characteristics that are filtered when merging multiple conflicting paths, and supplement the filtered imbalance characteristics into the path mapping table;

[0032] Spatial mismatch rate and time lag rate are extracted from the path mapping table as characteristics of imbalance in property resource allocation.

[0033] Furthermore, the spatial mismatch rate is obtained as follows:

[0034] The spatial mismatch rate is obtained by numerically calculating the maintenance worker density and the actual maintenance worker coverage radius in the original conflict path's conflict occurrence area.

[0035] Furthermore, the time lag rate is obtained as follows:

[0036] The time lag rate is obtained by numerically calculating the standardized time deviation of events in the original contradictory path.

[0037] Furthermore, the method for extracting the high-frequency superposition region of all multi-variable contradictory paths is as follows:

[0038] For multiple conflict paths with superposition effects, summarize the conflict occurrence areas of all multiple conflict paths with superposition effects;

[0039] Calculate the frequency of occurrence of each contradiction occurrence region in different cycles of the multi-contradiction path, and determine the high-frequency superposition region based on the frequency of occurrence of the contradiction occurrence region in different cycles.

[0040] Furthermore, the method for optimizing the allocation of property resources is as follows:

[0041] Based on a defined high-frequency superposition area and passive sensing features collected in real time by IoT devices.

[0042] By inputting the high-frequency superposition area and the passive sensing features collected in real time by IoT devices into the intelligent resource allocation model, it is possible to intelligently predict unbalanced property resources and optimize the allocation of property resources.

[0043] The beneficial effects of this invention are as follows:

[0044] 1. Capture multi-dimensional conflict events to provide a data foundation for intelligent scheduling. Multi-channel conflict collection: By combining proactive feedback and passive perception, explicit complaints and implicit conflicts are transformed into structured conflict event tags, reducing data blind spots from a single channel; Based on IoT positioning technology, conflict events are dynamically bound to the occurrence area, equipment status, and maintenance resources (elements) to form multi-dimensional data associations, providing full-process traceable data support for subsequent path analysis.

[0045] 2. Analyze the contradiction transmission path to achieve differentiated handling of high-frequency and individual problems. By constructing a contradiction association graph and analyzing the longest common sub-path, similar contradiction transmission paths are merged to generate "multi-faceted contradiction paths" representing high-frequency common patterns. Low-frequency atypical events are filtered out, allowing resource scheduling to prioritize repetitive and large-scale problems, improving optimization efficiency. The system distinguishes between "original contradiction paths" and "multi-faceted contradiction paths," reduces the incidence of common problems through large-scale processing, and provides a basis for identifying personalized resource allocation problems, balancing the efficiency and flexibility of problem optimization.

[0046] 3. Quantitative analysis of superposition effects: Identify key areas for resource allocation, extract spatial mismatch rate and time lag rate from the process of merging conflicting paths, and quantify the autocorrelation and cross-influence of spatial mismatch rate and time lag rate through vector autoregression model to identify the superposition effects of single or multi-dimensional imbalances and reduce scheduling decision bias caused by isolated analysis; Based on the results of superposition effect analysis, filter the superposition areas where conflicting events occur frequently through periodic frequency statistics, and combine historical data and real-time sensing data to focus resource scheduling on the core areas that truly need optimization, reducing the inefficiency and waste caused by the average allocation of resources.

[0047] 4. Proactive intelligent prediction and dynamic allocation: From passive response to proactive optimization, the system inputs high-frequency superimposed regional characteristics and real-time IoT data into the intelligent resource allocation model. It learns historical cycle patterns and real-time abnormal fluctuations, predicts imbalances such as maintenance personnel shortages and spare parts insufficiency in advance, and outputs proactive resource optimization strategies to resolve conflicts at the nascent stage. By dynamically optimizing maintenance personnel task allocation and spare parts inventory layout, the system ensures that the spatial and temporal distribution of property resources is highly matched with actual needs, thereby improving the efficiency of intelligent resource scheduling in the property. Attached Figure Description

[0048] The invention will now be further described with reference to the accompanying drawings.

[0049] Figure 1 This is a flowchart of a property intelligent resource scheduling and optimization method based on the Internet of Things according to an embodiment of the present invention;

[0050] Figure 2 This is a flowchart of the contradictory path model described in an embodiment of the present invention;

[0051] Figure 3 This is a block diagram of a property intelligent resource scheduling and optimization system based on the Internet of Things according to an embodiment of the present invention. Detailed Implementation

[0052] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0053] Example 1

[0054] Please see Figure 1 As shown in the embodiment of the present invention, a property intelligent resource scheduling optimization method based on the Internet of Things includes the following steps:

[0055] Step 1: Obtain the tags and events of conflicts that are actively reported and passively perceived by homeowners and property management, as well as the relationships between these conflicts, and construct a dataset of conflict events;

[0056] In some embodiments, by establishing a feedback communication channel between the owner and the property management, feedback from the owner is obtained through the feedback communication channel, and conflict events between the owner and the property management are identified in the feedback.

[0057] It should be explained that the identification of conflicting events is mainly achieved through two channels: proactive feedback and passive perception.

[0058] Proactive feedback is provided through various channels such as the property management mobile app, customer service hotline, and suggestion boxes. By combining technologies such as Natural Language Processing (NLP) and Optical Image Recognition (OCR), explicit complaints from homeowners are transformed into conflict event labels. For example, negative reviews, recorded phone calls, and written suggestions are transformed into conflict event labels such as "delayed repair response" and "poor service quality of workers."

[0059] Passive sensing collects IoT device data such as maintenance time and equipment failure frequency and performs correlation analysis with the maintenance work order system to capture potential conflicting events such as duplicate repair requests and resource mismatch.

[0060] Based on the tags and events of conflict events that are actively fed back and passively perceived, the IoT devices are used to locate the areas where conflicts occur, and to obtain event resources consisting of physical objects, owners, and time in the process of conflict events, as well as to obtain the equipment maintenance rate, maintenance personnel, and maintenance time in the areas where conflicts occur as property maintenance resources.

[0061] The physical items can be faulty equipment, spare parts that need to be replaced, etc.

[0062] Based on the association matching of conflict event tags and event resources and property maintenance resources in the conflict event process, the conflict association relationship of conflict events is obtained;

[0063] The conflict event tags, event resources in the conflict event process, and property maintenance resources are used as conflict event elements;

[0064] Collect all conflict events between the property management company and homeowners, including the conflict event elements and their relationships, to construct a conflict event dataset;

[0065] Preferred methods include collecting conflict information from APP complaints, telephone recordings of residents' proactive feedback, and passive sensing data from equipment sensor data and work order system records. Keywords are extracted from the conflict information using NLP to generate conflict labels such as "service quality" and "delayed response". The IoT positioning is used to determine the area where the conflict occurred and associate it with event resources in that area. For example, on January 1, 2025, in Unit 2, Floor 1 of Building 3, elevator number T-0302 and elevator spare parts usage records, there is a complaint record of an elderly person living alone with the number U-007.

[0066] The basic information, resources, conflict labels, and related evidence (such as mismatch of maintenance personnel skills and equipment aging data) of conflict events are structured and integrated to form conflict event elements including "event - owner - physical object - maintenance - label".

[0067] Based on the dataset of conflicting events, standardized data support is provided for subsequent conflict analysis and resource scheduling optimization.

[0068] Step 2: Construct a contradiction path model. Input the contradiction event dataset into the contradiction path model, extract the contradiction transmission path, and perform similarity merging analysis to obtain the multivariate contradiction path and the original contradiction path.

[0069] like Figure 2 As shown, the method for constructing the contradictory path model is as follows:

[0070] A1. Perform data preprocessing on the input dataset of contradictory events;

[0071] Preferably, data preprocessing includes three steps: data cleaning, data standardization, and data encoding.

[0072] Data cleaning: used to remove duplicate records, erroneous data, and missing values ​​from datasets containing conflicting events;

[0073] For example, if the device number in a feedback comment is empty, which is a missing value and cannot be supplemented by other information, then the feedback comment with the empty device number can be deleted.

[0074] Data standardization: Standardize different types of data in the dataset of conflicting events to facilitate subsequent analysis. For example, normalize numerical data such as equipment maintenance frequency and maintenance time.

[0075] Data encoding: Convert conflict event labels and owner types into numerical data to facilitate subsequent calculations;

[0076] A2. Construct a conflict relationship graph based on the preprocessed dataset of conflicting events;

[0077] The association graph is constructed as follows:

[0078] Extract contradictory event elements from the preprocessed contradictory event dataset as path nodes, and use contradictory relationships as path edges for contradictory event elements;

[0079] A correlation graph is established based on path nodes and conflicting edges using a model association algorithm;

[0080] Preferably, the model algorithm can be a graph database such as Neo4j or NetworkX;

[0081] It should be explained that path nodes can be owners, equipment, conflict event tags, maintenance personnel, spare parts, etc.

[0082] The path edge, or conflict relationship, can be the complaint relationship between the owner and the conflict event, the fault relationship between the equipment and the conflict event, or the handling relationship between the maintenance worker and the owner in the conflict event.

[0083] The model association algorithm connects the path nodes and path edges of the pre-processed dataset of conflicting events to establish a conflict association graph.

[0084] A3. Extract the contradiction transmission path based on the contradiction relationship diagram;

[0085] Preferably, the conflict transmission path is obtained by taking the homeowner as the starting point of the conflict transmission path and extracting the conflict transmission path along the path edges using a graph traversal algorithm.

[0086] It needs to be explained that the purpose of extracting the contradiction transmission path is:

[0087] Function 1: Identify high-frequency common conflict patterns. Through graph traversal algorithms and similarity merging analysis, extract frequently occurring conflict transmission patterns (such as "equipment aging → delayed maintenance response → repeated complaints from owners") from a large number of conflict events, forming "multi-path conflicts". These paths represent large-scale and typical resource allocation problems, which are the core conflicts that need to be addressed first in property resource scheduling.

[0088] Secondly, it distinguishes between common and individual contradictions. During the merging process, similar paths are merged into high-frequency common "multi-faceted contradiction paths," while low-frequency and unique paths that are not merged are retained as "original contradiction paths" (such as skill mismatch of maintenance personnel in specific areas or sudden shortage of spare parts). This allows resource scheduling to optimize high-frequency problems in batches while also taking into account personalized and occasional resource imbalance scenarios, thereby improving the efficiency of scheduling strategies.

[0089] Thirdly, it provides a structured basis for scheduling decisions. The conflict transmission path clarifies the causal chain of conflict events (such as the correlation between owner complaints and equipment failures, and maintenance resource allocation), transforming unstructured conflict events into structured data containing "node-edge-attribute" relationships (such as owner node → equipment failure edge → maintenance worker node). This structured information provides direct input for subsequent analysis of resource allocation imbalance characteristics (such as spatial mismatch rate and time lag rate) and the construction of intelligent scheduling models, making resource optimization strategies more targeted.

[0090] A similarity and overlap analysis is performed on the contradiction transmission paths, and similar contradiction transmission paths are merged.

[0091] The method for analyzing the similarity and overlap of contradiction transmission paths is as follows:

[0092] Extract any two contradictory transmission paths as a path comparison group, extract the two longest common sub-paths of the path comparison group, calculate the lengths of any two longest common sub-paths, and obtain len1 and len2.

[0093] Where len1 represents the length of the longest common sub-path of the first contradiction transmission path within the path comparison group, and len2 represents the length of the longest common sub-path of the second contradiction transmission path within the path comparison group;

[0094] The similarity between any two longest common sub-paths within a path comparison group is obtained using the formula: Sim = len1 / len2.

[0095] Preferably, the length of the longest common sub-path is determined by constructing a two-dimensional table dp using dynamic programming. AB [a][b], dp AB [a][b] represents the length of the longest common sub-path between the first a path nodes of contradiction propagation path A and the first b path nodes of contradiction propagation path B:

[0096] The similarity of the two longest common sub-paths is compared with a preset similarity threshold. If the similarity of the longest common sub-path is higher than the preset similarity threshold, the contradictory transmission paths of the path comparison group are merged by a clustering algorithm.

[0097] It needs to be explained that when merging similar conflict transmission paths using clustering algorithms, the path similarity is first calculated based on the length of the longest common sub-path (LCS) (e.g., LCS length ratio ≥ 60%), and a similarity matrix is ​​constructed. Then, hierarchical clustering or DBSCAN algorithms are used to divide the paths into several clusters according to a threshold. For each path within a cluster, common nodes (such as the same equipment, high-frequency conflict labels) and edges (such as complaint relationships, processing records) are retained, attribute data (such as the cumulative number of owner complaints, weighted average of repairman skill mismatch rate) are merged, and conflict information (such as different repairmen handling the same equipment) is marked as multi-node associations. Finally, representative paths containing core conflict elements are generated to extract high-frequency transmission patterns (such as "equipment aging → delayed maintenance response → repeated owner complaints"), providing structured input for resource scheduling optimization.

[0098] The contradiction transmission paths that are merged are marked as multi-conflict paths, and the contradiction transmission paths that are not merged are marked as original contradiction paths.

[0099] Those skilled in the art will understand that the original conflict path is: representing a unique conflict transmission pattern that has not been clustered, which may include personalized resource allocation issues, such as equipment aging in a specific area and mismatch between maintenance personnel skills, or a single sudden resource shortage;

[0100] The multiple conflict paths refer to patterns of high-frequency common conflicts that have been filtered out by merging low-frequency and atypical resource issues;

[0101] The technical solution of this embodiment is as follows: obtain the labels and events of conflict events actively reported and passively perceived by owners and property management, as well as the relationship between the conflicts, and construct a conflict event dataset; construct a conflict path model, input the conflict event dataset into the conflict path model, extract the conflict transmission path and perform similar merging analysis to obtain multiple conflict paths and original conflict paths; filter low-frequency atypical events so that resource scheduling prioritizes repetitive and large-scale problems, thereby improving optimization efficiency.

[0102] Example 2

[0103] like Figure 1 As shown, a property intelligent resource scheduling optimization method based on the Internet of Things further includes the following steps:

[0104] Step 3: Extract the characteristics of the imbalance in property resource allocation when multiple conflict paths are merged, and identify whether the characteristics of the imbalance in property resource allocation have a cumulative effect;

[0105] The method for identifying the characteristics of imbalanced property resource allocation when multiple conflicting paths are merged is as follows:

[0106] From the process of merging multiple contradictory paths, obtain the original contradictory paths that initially correspond to the multiple contradictory paths;

[0107] It needs to be explained that the original conflict path is a unique conflict transmission pattern that has not been clustered, such as the problem of personalized resource allocation, the mismatch between equipment aging and maintenance personnel skills in a specific area, and a single sudden resource shortage, which represent low-frequency and personalized conflict transmission paths;

[0108] The multi-faceted conflict path is a "representative path" generated by merging high-frequency and common original paths through similarity analysis. It filters out low-frequency and atypical resource problems and focuses on high-frequency conflict patterns, such as "equipment aging leads to delayed maintenance response, resulting in repeated complaints from owners".

[0109] Those skilled in the art will understand that the initial source of the multiple contradictory paths is the original contradictory paths in historical data. The two are related as “individual to group” and “specific to general”, and the merging process conforms to the clustering logic of “from concrete to abstract” in data mining.

[0110] When merging the original contradictory paths into the multivariate contradictory paths, record the original contradictory path number and merging time during cluster merging analysis, and establish a path mapping table from the multivariate contradictory paths to the original path clusters.

[0111] For example, if the multiple conflict paths "equipment aging → delayed maintenance response → owner complaint" correspond to 100 original conflict paths, 90 of them come from the equipment aging area and 10 involve the mismatch of maintenance personnel skills;

[0112] Identify the property resource imbalance characteristics that are filtered when merging multiple conflicting paths, and supplement the filtered imbalance characteristics into the path mapping table;

[0113] It needs to be explained that the filtered imbalance features are added to the path mapping table in the following way: the multiple contradictory paths filter out low-frequency, atypical original paths, which may implicitly contain local resource mismatch or sudden shortage imbalance features.

[0114] Resource mismatch category: The frequency of occurrence of the event label "mismatch between maintenance worker skills and equipment fault type" in the original conflict path. For example, a maintenance worker failed to handle the elevator circuit fault 3 times, but the multi-conflict path only retains the label "delayed maintenance response" and does not reflect the skill mismatch.

[0115] Sudden shortage category: The event tag "single shortage of spare parts inventory leading to maintenance delay" occurs with a low frequency in the original contradiction path and is therefore not merged, but it may occur repeatedly in specific areas;

[0116] Spatial mismatch rate and time lag rate are extracted from the path mapping table as characteristics of imbalance in property resource allocation.

[0117] S1. The spatial mismatch rate is obtained as follows:

[0118] Through the formula: Obtain the Spatial Mismatch Rate (SMR);

[0119] Where, ρ i The maintenance worker density in the conflict-occurring region i of the original conflict path is the ratio of the number of maintenance workers in the conflict-occurring region to the area of ​​the region.

[0120] ρ avg The average maintenance worker density in the multiple conflict paths is obtained by averaging the maintenance worker density of all relevant areas;

[0121] R i R is the actual maintenance personnel coverage radius of region i in the original conflict path where the conflict occurs. std The standard coverage radius is the theoretical coverage radius calculated based on the standard service area per maintenance worker set by the property management company.

[0122] i is the number of the area where the conflict occurred;

[0123] S2. The time lag rate is obtained as follows:

[0124] Through the formula: Obtain the Time Lag Rate (TLR);

[0125] Where M is the total number of event path work orders constructed based on proactive feedback and passive perception of contradictory events in the multi-conflict path, and j is the number of the event path work order.

[0126] It should be explained that the event path work order is established based on conflicting events and is used to assign tasks to maintenance personnel to resolve conflicting events;

[0127] Z j This represents the standardized time deviation value of events in the original conflict path, which is calculated by the percentage deviation between the repairman's repair time and the preset standard time T.

[0128] ΔT j The deviation value is obtained by calculating the difference between the repairman's repair time and the preset standard time T;

[0129] I is an indicator function; it is 1 when the condition is met and 0 otherwise.

[0130] Based on the characteristics of the imbalance in property resource allocation when multiple conflict paths are merged, it is determined whether the characteristics of the imbalance in property resource allocation under multiple conflict paths have a cumulative effect.

[0131] One method for determining whether the imbalance in the allocation of property resources along multiple conflicting paths has a cumulative effect is as follows:

[0132] Through the formula: A vector autoregression model was constructed to conduct autocorrelation analysis on the characteristics of imbalance in property resource allocation through multiple conflict paths;

[0133] Among them, TLR t The time lag rate at time t represents the degree of deviation between the current maintenance time and the standard time.

[0134] α k The TLR lag effect at time t represents the TLR lag effect over period k. t The influence coefficient measures the strength of the influence of the historical values ​​of the TLR on the current value.

[0135] TLR t-k This represents the value of the TLR at time tk, i.e., the historical observation value of the TLR;

[0136] β k This indicates that the SMR lags by k periods relative to the TLR at time t. t The influence coefficient reflects the cross-effect of spatial mismatch rate on time lag rate;

[0137] SMR t-k This represents the value of SMR at time tk, i.e., the historical observation value of SMR;

[0138] ε 1t The random error term in the TLR equation at time t follows a normal distribution with a mean of 0, capturing random factors not explained by the model. t The influence of ε 2t The random error term of the SMR equation at time t follows a normal distribution with a mean of 0, capturing the random factors SMR not explained by the model. t The impact;

[0139] SMR t It represents the spatial mismatch rate at time t, quantifying the degree of imbalance between the current area's maintenance personnel density and coverage radius;

[0140] γ k TLR lag k-period to SMR at time t t The influence coefficient reflects the reverse effect of time lag rate on spatial mismatch rate;

[0141] δ k SMR lag k-period relative to SMR at time t t The influence coefficient characterizes the impact of historical SMR values ​​on the current value;

[0142] q is the lag order of the model, which determines how many past periods' TLR and SMR values ​​are used to explain the current value. It needs to be determined based on the data characteristics and the AIC and BIC criteria of statistical tests.

[0143] t is time t, and k is the number of periods lag;

[0144] It needs to be explained that, For the autoregressive part of the vector autoregressive model, represents the influence of the historical values ​​of the time lag rate and spatial mismatch rate on the current values, respectively;

[0145] If α k or δ k The fact that the value is significantly non-zero indicates that the imbalance feature has autocorrelation over time, meaning that the current degree of imbalance is affected by the past state of imbalance. This reflects the superposition effect of a single imbalance feature over time.

[0146] For example, when α1 = 0.8, it means that the time lag rate of the previous period has a large positive impact on the current time lag rate, and the imbalance of the previous period will continue into the current period, showing an additive trend.

[0147] The intersection part in the formula represents the mutual influence between different imbalance characteristics; if β k or γ k If the value is significantly non-zero, it indicates that different types of imbalance features are correlated over time;

[0148] For example, β1 = 0.6, which means that for every unit increase in the spatial mismatch rate in the previous period, the time lag rate in the previous period will increase by 0.6 units. This reflects the superposition effect of different imbalance characteristics in the time dimension, that is, the deterioration of one imbalance characteristic will further aggravate the degree of another imbalance characteristic.

[0149] It needs to be explained that the purpose of identifying whether there is a cumulative effect is as follows:

[0150] Firstly, it reveals the dynamic correlation of imbalance characteristics, which helps reduce the possibility of isolated analysis. Traditional resource scheduling often analyzes single imbalance problems in isolation (such as focusing only on insufficient maintenance personnel or excessive maintenance time), while superposition effect identification quantifies the autocorrelation (the impact of historical imbalance on the current state) and cross-influence (the interaction between different characteristics) of different imbalance characteristics (such as spatial mismatch rate and time lag rate, TLR) through vector autoregression (VAR) model.

[0151] Function 2: Locating high-frequency and complex imbalance areas and focusing on core contradictions. The existence of superimposed effects usually means that multiple resource imbalance problems in a certain area are exacerbated in a coordinated manner (such as insufficient maintenance personnel + shortage of spare parts + concentrated aging of equipment). Such areas are often high-incidence areas of conflict events. By identifying superimposed effects and screening high-frequency superimposed areas, we can prioritize resource allocation and give priority to investing human and material resources in high-frequency areas with superimposed effects.

[0152] Thirdly, it reduces the incidence of conflict incidents and optimizes resource utilization efficiency. By identifying cumulative effects and making targeted optimizations, it reduces duplicate repair requests and resource waste, thereby improving resource utilization efficiency.

[0153] Step 4: If there is a superposition effect, perform regional screening analysis on the multiple conflict paths and extract the high-frequency superposition areas of all multiple conflict paths.

[0154] If there is a cumulative effect, filter out the multiple contradictory paths that have a cumulative effect from all multiple contradictory paths;

[0155] The method for extracting the high-frequency overlapping regions of all multi-path contradictions is as follows:

[0156] For multiple conflict paths with superposition effects, summarize the conflict occurrence areas of all multiple conflict paths with superposition effects;

[0157] Calculate the frequency of occurrence of each contradiction occurrence region in different cycles of the multi-contradiction path, and compare it with the preset frequency threshold. The contradiction occurrence regions that are higher than or equal to the preset frequency threshold are marked as high-frequency superposition regions.

[0158] As will be understood by those skilled in the art, the preset frequency threshold is obtained by statistical analysis of historical data.

[0159] Step 5: Based on the identified high-frequency overlay area, input the real-time collected passive sensing features into the intelligent resource allocation model to achieve intelligent prediction of unbalanced property resources and optimize the allocation of property resources.

[0160] Based on a defined high-frequency superposition area and passive sensing features collected in real time by IoT devices.

[0161] By inputting the passive sensing features collected in real time by high-frequency superposition areas and IoT devices into the intelligent resource allocation model, it is possible to make intelligent predictions of unbalanced property resources, optimize the allocation of property resources, and help reduce the probability of conflict events.

[0162] Those skilled in the art will understand that the construction of the intelligent resource allocation model requires high-frequency superimposed regional features and real-time passive sensing data from the Internet of Things as core inputs. By integrating the imbalance features of the spatiotemporal dimensions (such as spatial mismatch rate SMR and time lag rate TLR), equipment operating status (failure frequency, spare parts inventory) and maintenance resource distribution (maintenance personnel skills, location), a hybrid architecture of Long Short-Term Memory Network (LSTM) combined with Graph Neural Network (GNN) is used to capture historical periodic patterns and real-time abnormal fluctuations.

[0163] The intelligent resource allocation model learns imbalance patterns in high-frequency areas (such as "nighttime + equipment aging area → insufficient maintenance personnel + spare parts shortage") through training, and outputs dynamic allocation strategies (personnel dispatch, spare parts pre-storage, preventive maintenance), ultimately achieving proactive optimization of resources such as maintenance personnel and spare parts, and reducing the probability of conflict events.

[0164] The technical solution of this embodiment is as follows: Extract the characteristics of imbalanced property resource allocation when multiple conflict paths merge, and identify whether the characteristics of imbalanced property resource allocation have a superposition effect; if a superposition effect exists, perform regional screening analysis on the multiple conflict paths to extract the high-frequency superposition areas of all multiple conflict paths; based on the determined high-frequency superposition areas, input the real-time collected passive sensing features into the intelligent resource allocation model to achieve intelligent prediction of imbalanced property resources and optimize the allocation of property resources; perform forward-looking intelligent prediction and dynamic allocation of imbalanced property resources to achieve a shift from passive response to proactive optimization; input the high-frequency superposition area characteristics and real-time IoT data into the intelligent resource allocation model to learn historical cycle patterns and real-time abnormal fluctuations, predict imbalances such as maintenance personnel shortages and spare parts insufficiency in advance, and output forward-looking resource optimization strategies to resolve conflict events at the nascent stage; by dynamically optimizing maintenance personnel task allocation and spare parts inventory layout, the spatiotemporal distribution of property resources is highly matched with actual needs, improving the efficiency of intelligent property resource scheduling.

[0165] Example 3

[0166] like Figure 3 As shown, a property intelligent resource scheduling and optimization system based on the Internet of Things includes the following modules:

[0167] Conflict Extraction Module: Used to obtain conflict event tags and conflict events actively reported and passively perceived by owners and property management, as well as conflict relationships, and to build a conflict event dataset;

[0168] By establishing feedback and communication channels between homeowners and property management, we can obtain feedback from homeowners and identify conflicts between homeowners and property management within the feedback channels.

[0169] Based on the tags and events of conflict events that are actively fed back and passively perceived, the IoT devices are used to locate the areas where conflicts occur, and to obtain event resources consisting of physical objects, owners, and time in the process of conflict events, as well as to obtain the equipment maintenance rate, maintenance personnel, and maintenance time in the areas where conflicts occur as property maintenance resources.

[0170] The physical items can be faulty equipment, spare parts that need to be replaced, etc.

[0171] Based on the association matching of conflict event tags and event resources and property maintenance resources in the conflict event process, the conflict association relationship of conflict events is obtained;

[0172] The conflict event tags, event resources in the conflict event process, and property maintenance resources are used as conflict event elements;

[0173] Collect all conflict events between the property management company and the owners, and construct a conflict event dataset by identifying the conflict event elements and their relationships.

[0174] Path merging module: Used to construct a conflict path model. Input the conflict event dataset into the conflict path model, extract the conflict transmission path and perform similarity merging analysis to obtain the multivariate conflict path and the original conflict path;

[0175] The construction method of the contradictory path model is as follows:

[0176] A1. Perform data preprocessing on the input dataset of contradictory events;

[0177] Data cleaning: used to remove duplicate records, erroneous data, and missing values ​​from datasets containing conflicting events;

[0178] Data standardization: Standardize different types of data in the dataset of conflicting events to facilitate subsequent analysis. For example, normalize numerical data such as equipment maintenance frequency and maintenance time.

[0179] Data encoding: Convert conflict event labels and owner types into numerical data to facilitate subsequent calculations;

[0180] A2. Construct a conflict relationship graph based on the preprocessed dataset of conflicting events;

[0181] The association graph is constructed as follows:

[0182] Extract contradictory event elements from the preprocessed contradictory event dataset as path nodes, and use contradictory relationships as path edges for contradictory event elements;

[0183] A correlation graph is established based on path nodes and conflicting edges using a model association algorithm;

[0184] The path edge, or conflict relationship, can be the complaint relationship between the owner and the conflict event, the fault relationship between the equipment and the conflict event, or the handling relationship between the maintenance worker and the owner in the conflict event.

[0185] The model association algorithm connects the path nodes and path edges of the pre-processed dataset of conflicting events to establish a conflict association graph.

[0186] A3. Extract the contradiction transmission path based on the contradiction relationship diagram;

[0187] A similarity and overlap analysis is performed on the contradiction transmission paths, and similar contradiction transmission paths are merged.

[0188] The method for analyzing the similarity and overlap of contradiction transmission paths is as follows:

[0189] Extract any two contradictory transmission paths as a path comparison group, extract the two longest common sub-paths of the path comparison group, calculate the lengths of any two longest common sub-paths, and obtain len1 and len2.

[0190] Where len1 represents the length of the longest common sub-path of the first contradiction transmission path within the path comparison group, and len2 represents the length of the longest common sub-path of the second contradiction transmission path within the path comparison group;

[0191] The similarity between any two longest common sub-paths within a path comparison group is obtained using the formula: Sim = len1 / len2.

[0192] The similarity of the two longest common sub-paths is compared with a preset similarity threshold. If the similarity of the longest common sub-path is higher than the preset similarity threshold, the contradictory transmission paths of the path comparison group are merged by a clustering algorithm.

[0193] The contradiction transmission paths that are merged are marked as multi-conflict paths, while the contradiction transmission paths that are not merged are marked as original contradiction paths.

[0194] Overlay analysis module: used to extract the characteristics of property resource allocation imbalance when multiple conflict paths are merged, and to identify whether the characteristics of property resource allocation imbalance have an overlay effect;

[0195] The method for identifying the characteristics of imbalanced property resource allocation when multiple conflicting paths are merged is as follows:

[0196] From the process of merging multiple contradictory paths, obtain the original contradictory paths that initially correspond to the multiple contradictory paths;

[0197] When merging the original contradictory paths into the multivariate contradictory paths, record the original contradictory path number and merging time during cluster merging analysis, and establish a path mapping table from the multivariate contradictory paths to the original path clusters.

[0198] Identify the property resource imbalance characteristics that are filtered when merging multiple conflicting paths, and supplement the filtered imbalance characteristics into the path mapping table;

[0199] Spatial mismatch rate and time lag rate are extracted from the path mapping table as characteristics of imbalance in property resource allocation.

[0200] S1. The spatial mismatch rate is obtained as follows:

[0201] Through the formula: Obtain the Spatial Mismatch Rate (SMR);

[0202] Where, ρ i The maintenance worker density in the conflict-occurring region i of the original conflict path is the ratio of the number of maintenance workers in the conflict-occurring region to the area of ​​the region.

[0203] ρ avg The average maintenance worker density in the multiple conflict paths is obtained by averaging the maintenance worker density of all relevant areas;

[0204] R i R is the actual maintenance personnel coverage radius of region i in the original conflict path where the conflict occurs. std The standard coverage radius is the theoretical coverage radius calculated based on the standard service area per maintenance worker set by the property management company.

[0205] i is the number of the area where the conflict occurred;

[0206] S2. The time lag rate is obtained as follows:

[0207] Through the formula: Obtain the Time Lag Rate (TLR);

[0208] Where M is the total number of event path work orders constructed based on proactive feedback and passive perception of contradictory events in the multi-conflict path, and j is the number of the event path work order.

[0209] It should be explained that the event path work order is established based on conflicting events and is used to assign tasks to maintenance personnel to resolve conflicting events;

[0210] Z j This represents the standardized time deviation value of events in the original conflict path, which is calculated by the percentage deviation between the repairman's repair time and the preset standard time T.

[0211] ΔT j The deviation value is obtained by calculating the difference between the repairman's repair time and the preset standard time T;

[0212] I is an indicator function; it is 1 when the condition is met and 0 otherwise.

[0213] Based on the characteristics of the imbalance in property resource allocation when multiple conflict paths are merged, it is determined whether the characteristics of the imbalance in property resource allocation under multiple conflict paths have a cumulative effect.

[0214] One method for determining whether the imbalance in the allocation of property resources along multiple conflicting paths has a cumulative effect is as follows:

[0215] Through the formula: Constructing a vector autoregression model to analyze the imbalance characteristics of property resource allocation along multiple conflicting paths;

[0216] Among them, TLR t The time lag rate at time t represents the degree of deviation between the current maintenance time and the standard time.

[0217] α k The TLR lag effect at time t represents the TLR lag effect over period k. t The influence coefficient measures the strength of the influence of the historical values ​​of the TLR on the current value.

[0218] TLR t-k This represents the value of the TLR at time tk, i.e., the historical observation value of the TLR;

[0219] β k This indicates that the SMR lags by k periods relative to the TLR at time t. t The influence coefficient reflects the cross-effect of spatial mismatch rate on time lag rate;

[0220] SMR t-k This represents the value of SMR at time tk, i.e., the historical observation value of SMR;

[0221] ε 1t The random error term in the TLR equation at time t follows a normal distribution with a mean of 0, capturing random factors not explained by the model. t The influence of ε 2t The random error term of the SMR equation at time t follows a normal distribution with a mean of 0, capturing the random factors SMR not explained by the model. t The impact;

[0222] SMR t It represents the spatial mismatch rate at time t, quantifying the degree of imbalance between the current area's maintenance personnel density and coverage radius;

[0223] γ k TLR lag k-period to SMR at time t t The influence coefficient reflects the reverse effect of time lag rate on spatial mismatch rate;

[0224] δ k SMR lag k-period relative to SMR at time t t The influence coefficient characterizes the impact of historical SMR values ​​on the current value;

[0225] q is the lag order of the model, which determines how many past periods' TLR and SMR values ​​are used to explain the current value. It needs to be determined based on the data characteristics and the AIC and BIC criteria of statistical tests.

[0226] t is time t, and k is the number of periods lag;

[0227] For the autoregressive part of the vector autoregressive model, represents the influence of the historical values ​​of the time lag rate and spatial mismatch rate on the current values, respectively;

[0228] If α k or δ k The fact that the value is significantly non-zero indicates that the imbalance feature has autocorrelation over time, meaning that the current degree of imbalance is affected by the past state of imbalance. This reflects the superposition effect of a single imbalance feature over time.

[0229] The intersection part in the formula represents the mutual influence between different imbalance characteristics; if β k or γ k If the value is significantly non-zero, it indicates that different types of imbalance features are correlated over time.

[0230] Region filtering module: If there is a superposition effect, it is used to perform region filtering analysis on multiple conflict paths and extract the high-frequency superposition areas of all multiple conflict paths;

[0231] If there is a cumulative effect, filter out the multiple contradictory paths that have a cumulative effect from all multiple contradictory paths;

[0232] The method for extracting the high-frequency overlapping regions of all multi-path contradictions is as follows:

[0233] For multiple conflict paths with superposition effects, summarize the conflict occurrence areas of all multiple conflict paths with superposition effects;

[0234] The frequency of each conflict occurrence region in different cycles is calculated and compared with a preset frequency threshold. Conflict occurrence regions that are higher than or equal to the preset frequency threshold are marked as high-frequency superposition regions.

[0235] Resource optimization module: Based on the determined high-frequency overlay area, it is used to input the passively sensed features collected in real time into the intelligent resource allocation model to realize intelligent prediction of unbalanced property resources and optimize the allocation of property resources;

[0236] Based on a defined high-frequency superposition area and passive sensing features collected in real time by IoT devices.

[0237] By inputting the high-frequency superposition area and the passive sensing features collected in real time by IoT devices into the intelligent resource allocation model, it is possible to intelligently predict unbalanced property resources and optimize the allocation of property resources.

[0238] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A property intelligent resource scheduling optimization method based on the Internet of Things, characterized in that: Includes the following steps: Acquire the tags and events of conflicts reported proactively and passively by homeowners and property management, as well as the relationships between these conflicts, and construct a dataset of conflict events. A conflict path model is constructed by inputting a dataset of conflict events into the model, extracting conflict transmission paths, and performing similarity merging analysis to obtain a multivariate conflict path. The similarity merging analysis method is as follows: Extract any two contradictory transmission paths as a path comparison group, extract the two longest common sub-paths of the path comparison group, and calculate the length of any two longest common sub-paths. Calculate the similarity between the lengths of any two longest common sub-paths to obtain the similarity between any two longest common sub-paths within the path comparison group; If the similarity of the longest common sub-path is higher than the preset similarity threshold, the contradictory transmission paths of the path comparison group will be merged by a clustering algorithm. Extract the characteristics of imbalance in property resource allocation when multiple conflict paths are merged, and identify whether the characteristics of imbalance in property resource allocation have a cumulative effect; The method for obtaining the characteristics of the imbalance in the allocation of property resources is as follows: From the process of merging multiple contradictory paths, obtain the original contradictory paths that initially correspond to the multiple contradictory paths; Identify the property resource imbalance characteristics that are filtered when merging multiple conflicting paths, and supplement the filtered imbalance characteristics into the path mapping table; Spatial mismatch rate and time lag rate are extracted from the path mapping table as characteristics of imbalance in property resource allocation. The method for identifying whether the characteristics of imbalanced allocation of property resources have a cumulative effect is as follows: Based on the characteristics of the imbalance in property resource allocation when multiple conflict paths are merged, an autocorrelation analysis of the characteristics of the imbalance in property resource allocation under multiple conflict paths is conducted by constructing a vector autoregression model. If the impact coefficient of the autocorrelation analysis is significantly non-zero, then the imbalance in the allocation of property resources has a cumulative effect. If there is a superposition effect, regional screening analysis is performed on the multiple conflict paths to extract the high-frequency superposition areas of all multiple conflict paths; Based on the identified high-frequency overlay areas, the passive sensing features collected in real time are input into the intelligent resource allocation model to achieve intelligent prediction of unbalanced property resources and optimize the allocation of property resources.

2. The method for optimizing intelligent property resource scheduling based on the Internet of Things according to claim 1, characterized in that: The method for constructing the contradictory event dataset is as follows: Obtain conflict event tags and event resources and property maintenance resources in the conflict event process, and perform association matching to obtain the conflict association relationship of the conflict events; The conflict event tags, event resources in the conflict event process, and property maintenance resources are used as conflict event elements; Collect all conflict events between the property management company and the owners, and construct a conflict event dataset by identifying the conflict event elements and their relationships.

3. The method for optimizing intelligent property resource scheduling based on the Internet of Things according to claim 1, characterized in that: The contradictory path model is as follows: Preprocess the input dataset of contradictory events; Contradictory relationship graphs are constructed based on the preprocessed dataset of contradictory events. The contradiction transmission path is extracted based on the contradiction relationship diagram.

4. The method for optimizing intelligent resource scheduling in property management based on the Internet of Things according to claim 1, characterized in that: The spatial mismatch rate is obtained as follows: The spatial mismatch rate is obtained by numerically calculating the maintenance worker density and the actual maintenance worker coverage radius in the original conflict path's conflict occurrence area.

5. The method for optimizing intelligent resource scheduling in property management based on the Internet of Things according to claim 1, characterized in that: The time lag rate is obtained as follows: The time lag rate is obtained by numerically calculating the standardized time deviation of events in the original contradictory path.

6. The method for optimizing intelligent resource scheduling in property management based on the Internet of Things according to claim 1, characterized in that: The method for extracting the high-frequency superposition region of all multi-variable contradictory paths is as follows: For multiple conflict paths with superposition effects, summarize the conflict occurrence areas of all multiple conflict paths with superposition effects; Calculate the frequency of occurrence of each contradiction occurrence region in different cycles of the multi-contradiction path, and determine the high-frequency superposition region based on the frequency of occurrence of the contradiction occurrence region in different cycles.

Images