Intelligent community service management platform for business handling

Abstract

The invention provides an intelligent community service management platform for business handling, and relates to the technical field of intelligent management. Target maintenance information received by the platform is acquired, the target maintenance information is identified, and a key data set is determined; inputting the service type and the fault attribute into an operation and maintenance association database to perform first-layer matching, determining a first-layer idle personnel set, if the first-layer idle personnel set is not 0, obtaining real-time position information of first-layer idle personnel, performing intelligent decision-making based on the real-time position information and a preset personnel score, determining a first maintenance personnel, and determining a second maintenance personnel; and the target maintenance information is sent to the first maintenance personnel, and the target maintenance task is executed based on the fault coordinates, so that the technical problem of low community maintenance service efficiency and maintenance quality caused by poor intelligent community management in the prior art is solved. The technical effects of efficiently managing and optimizing the maintenance service and improving the maintenance efficiency and quality are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a smart community service management platform for business handling. Background Art

[0002] The smart community business processing service platform includes a series of services and management functions, among which the management and execution of community maintenance services are crucial to ensuring the normal operation of community facilities, improving the quality of life of residents, and maintaining the safety and cleanliness of the community environment. However, with the acceleration of urbanization and the continuous expansion of community scale, community maintenance services are facing growing demands and challenges. Traditional maintenance service models often have problems such as inefficiency, slow response, uneven service quality, and irregular management. Not only can they not meet the residents' demand for efficient, convenient, and high-quality maintenance services, they may also have a negative impact on the overall operation of the community. Therefore, how to achieve efficient management and optimization of maintenance services and improve maintenance efficiency, quality, and residents' satisfaction has become a problem in the current smart community management.

[0003] From the above, it can be seen that the existing technology has technical problems such as inadequate management of smart communities, resulting in low efficiency and quality of community maintenance services. Summary of the invention

[0004] This application provides a smart community service management platform for business processing, which is used to solve the technical problems in the existing technology that the smart community management is not in place, resulting in low efficiency and quality of community maintenance services.

[0005] In view of the above problems, the present application provides a smart community service management platform for business processing, and the platform includes: a target maintenance information identification module, the target maintenance information identification module is used to obtain the target maintenance information received by the platform, identify the target maintenance information, and determine the key data set, wherein the key data set includes business type, fault attribute, fault coordinates and scheduled maintenance time; a first-layer matching module, the first-layer matching module is used to determine if the scheduled maintenance time is the current node, input the business type and the fault attribute into the operation and maintenance related database for a layer of matching, and determine the first-layer idle personnel set; an intelligent decision-making module, the intelligent decision-making module is used to determine if the first-layer idle personnel set is not 0, obtain the real-time location information of the first-layer idle personnel, make an intelligent decision based on the real-time location information and the preset personnel score, and determine the first maintenance personnel; a task execution module, the task execution module is used to send the target maintenance information to the first maintenance personnel, and execute the target maintenance task based on the fault coordinates.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The smart community service management platform for business handling provided by the embodiment of the present application obtains the target maintenance information received by the platform, identifies the target maintenance information, determines the key data set, judges if the scheduled maintenance time is the current node, inputs the business type and the fault attribute into the operation and maintenance related database for a layer of matching, determines the first layer of idle personnel set, and if the first layer of idle personnel set is not 0, obtains the real-time location information of the first layer of idle personnel, makes intelligent decisions based on the real-time location information and the preset personnel score, determines the first maintenance personnel, and sends the target maintenance information to the first maintenance personnel, and performs the target maintenance task based on the fault coordinates. The technical effect of achieving efficient management and optimization of maintenance services, improving maintenance efficiency and quality, and providing residents with a better quality and more convenient community living environment is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the structure of the smart community service management platform used for business processing provided for this application.

[0009] Figure 2 This is a structural diagram of a layer matching module in the smart community service management platform used for business processing provided in this application.

[0010] Explanation of the reference numerals: target maintenance information identification module 10, first-layer matching module 20, intelligent decision-making module 30, task execution module 40, data acquisition unit 21, information matching unit 22, relationship establishment unit 23, operation and maintenance related database construction unit 24. DETAILED DESCRIPTION

[0011] This application provides a smart community service management platform for business handling, which is used to solve the technical problems of inadequate smart community management, low efficiency and quality of community maintenance services in the existing technology. It achieves efficient management and optimization of maintenance services, improves maintenance efficiency and quality, and provides residents with a better and more convenient community living environment.

[0012] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0013] like Figure 1As shown, this application provides a smart community service management platform for business handling, which includes:

[0014] The target maintenance information identification module 10 is used to obtain the target maintenance information received by the platform, identify the target maintenance information, and determine a key data set, wherein the key data set includes a business type, a fault attribute, a fault coordinate, and a scheduled maintenance time.

[0015] Specifically, the smart community business service platform includes a series of services and management functions, among which the management and execution of community maintenance services are crucial to ensuring the normal operation of community facilities, improving the quality of life of residents, and maintaining the safety and cleanliness of the community environment.

[0016] In order to achieve efficient management and optimization of maintenance services, the target maintenance information identification module 10 first receives target maintenance information from the target smart community service platform. The target maintenance information includes multiple channels such as telephone repair reports from residents, online repair reporting systems, and mobile applications. Then, the information content of the received target maintenance information is analyzed and identified, and key data sets related to maintenance are extracted from complex text data. The key data sets include business type, fault attributes, fault coordinates, and scheduled maintenance time. Among them, the business type refers to the type of maintenance service, such as water and electricity maintenance, furniture maintenance, and home appliance maintenance, which helps the platform to quickly determine the required service resources and skill types. The fault attribute refers to the nature and manifestation of a specific fault, such as water pipe leakage, circuit short circuit, air conditioning failure, etc., which helps maintenance personnel understand the fault situation, prepare maintenance tools and materials, etc. The fault coordinates refer to the specific location where the fault occurs, including detailed address information such as house number, floor number, specific geographical location, etc., which helps maintenance personnel accurately find the fault site and plan the itinerary route. The scheduled maintenance time refers to the maintenance time or time period expected by community residents, such as processing as soon as possible, within a specific time period, etc., which helps the platform to reasonably arrange the working time and task allocation of maintenance personnel. Through the application of the target maintenance information identification module 10, the community service platform can handle various maintenance requests more efficiently and accurately, thereby improving service quality and residents' satisfaction.

[0017] A first-layer matching module 20 is used to determine if the scheduled maintenance time is the current node, input the business type and the fault attribute into the operation and maintenance related database for a first-layer matching, and determine the first-layer idle personnel set.

[0018] Specifically, the first-layer matching module 20 receives the key data set determined by the target maintenance information identification module 10, and determines whether the scheduled maintenance time point in the key data set is the current time node. When it is determined that the scheduled maintenance time belongs to the current time node, that is, the current time point is aligned with the scheduled maintenance time point, the first-layer matching module 20 then uses the business type and fault attribute in the key data set as input, and inputs it into the operation and maintenance associated database that stores the operation and maintenance personnel, personnel skills, and personnel current work status. Through the business type and fault attribute, the data in the operation and maintenance associated database is searched and matched to find a set of personnel who can handle the current task and are idle at the current time point, that is, the first-layer idle personnel set, which contains the personnel's ID, name, skills and other information. The first-layer matching module 20 can quickly and accurately match maintenance needs with maintenance resources in an intelligent way, thereby improving the efficiency and quality of maintenance services.

[0019] The intelligent decision-making module 30 is used to determine if the first layer of idle personnel set is not 0, obtain the real-time location information of the first layer of idle personnel, make an intelligent decision based on the real-time location information and preset personnel scores, and determine the first maintenance personnel.

[0020] Specifically, the intelligent decision-making module 30 checks whether the first-layer idle personnel set exists, that is, determines whether the number in the first-layer idle personnel set is greater than 0. When it is determined that the first-layer idle personnel set is not empty, it indicates that there are available maintenance personnel to perform the maintenance task at the scheduled maintenance time. Next, the real-time location information of each idle personnel in the first-layer idle personnel set is determined. The real-time location information comes from the GPS positioning device, WiFi positioning, Bluetooth, etc. carried by the maintenance personnel. Finally, the intelligent decision-making module 30 performs calculations and analysis based on the real-time location information of the first-layer idle personnel and the preset personnel scores to determine the most suitable person to perform the current maintenance task. Among them, the preset personnel score refers to the comprehensive acquisition based on the skill level, historical maintenance records, response time, customer satisfaction, etc. of the maintenance personnel in advance. By evaluating the preset personnel, the platform can help more accurately evaluate the ability and efficiency of the maintenance personnel.

[0021] The task execution module 40 is used to send the target maintenance information to the first maintenance personnel and perform the target maintenance task based on the fault coordinates. Specifically, after the intelligent decision-making module 30 determines the first maintenance personnel, the task execution module 40 sends the target maintenance information, including business type, fault attributes, fault coordinates, and scheduled maintenance time, to the first maintenance personnel. The information can be sent through mobile application push, SMS or email. After receiving the task information, the first maintenance personnel arrives at the fault location according to the fault coordinates and performs the target maintenance task, thereby achieving efficient management and optimization of maintenance services, improving maintenance efficiency and quality, providing residents with a better service experience, and improving residents' satisfaction and the efficiency of the maintenance team.

[0022] In a possible implementation, the target maintenance information identification module 10 further includes: an indicator configuration unit, which is used to configure data identification indicators, wherein the data identification indicators at least include business type, fault attributes, location information and maintenance time; an information extraction unit, which is used to collect community operation and maintenance data online, obtain a community operation and maintenance data set, and extract information from the community operation and maintenance data set based on the data identification indicators to obtain an identification data set; a channel training unit, which is used to train a data analysis channel constructed based on a multidimensional operator using the community operation and maintenance data set and the identification data set as training data sets to obtain a convergent data analysis channel, and identify the target maintenance information through the convergent data analysis channel.

[0023] Specifically, the indicator configuration unit is responsible for defining and setting key indicators for data identification. The data identification indicators include at least business type, fault attributes, location information and maintenance time. Through the comprehensive use of these indicators, the timeliness and quality of community services can be ensured. The information extraction unit first collects data from different operation and maintenance data sources through network interfaces, such as API calls and database connections, to form a community operation and maintenance data set. The different operation and maintenance data sources include monitoring equipment, sensor equipment, resident reports and maintenance records. Then, according to the data identification indicators set by the indicator configuration unit, text parsing, pattern matching and other technologies are used to extract information related to the identification indicators from the community operation and maintenance data set to form an identification data set. Next, the channel training unit constructs a data analysis channel based on multidimensional operators, such as support vector machines, BP neural networks, random forests and long short-term memory networks, where multidimensional operators refer to different machine learning or deep learning algorithms that can capture key features and patterns in the data. Then, the community operation and maintenance data set and the identification data set are used as training data to train the data analysis channel. When the performance of the channel reaches the expected standard or reaches the predetermined number of iterations, the training is stopped and the current channel is used as a converged data analysis channel. Finally, the convergent data analysis channel is used to process and analyze the community operation and maintenance data to obtain the target maintenance information. Through the joint action of the indicator configuration unit, information extraction unit and channel training unit, the community operation and maintenance data can be accurately collected, effectively extracted and intelligently analyzed, providing strong data support for improving the efficiency and service quality of community operation and maintenance.

[0024] In a possible implementation, the channel training unit further includes: an analysis sub-channel construction unit, the analysis sub-channel construction unit is used to construct multiple analysis sub-channels based on multidimensional operators, wherein the multidimensional operators include support vector machines, BP neural networks, random forests and long short-term memory networks; a training data set equal division unit, the training data set equal division unit is used to divide the training data set into N parts, wherein N is the number of the multidimensional operators, to obtain N training sets; an analysis sub-channel selection unit, the analysis sub-channel selection unit is used to select a first analysis sub-channel from the multiple analysis sub-channels, and randomly select N times without replacement from the N training sets to obtain a first A training set; a convergence analysis sub-channel obtaining unit, the convergence analysis sub-channel obtaining unit is used to take the community operation and maintenance data as input and the identification data as supervision, and perform supervised training and feedback verification on the first analysis sub-channel through the first training set to obtain a first convergence analysis sub-channel that meets the expected convergence constraints, and use the N training sets to perform supervised training and feedback verification on other analysis sub-channels respectively to obtain multiple convergence analysis sub-channels; a convergence data analysis channel construction unit, the convergence data analysis channel construction unit is used to construct the convergence data analysis channel based on multiple convergence analysis sub-channels, wherein the output of the convergence data analysis channel is the mode of the multiple convergence analysis sub-channels.

[0025] Specifically, the analysis sub-channel construction unit is responsible for creating multiple analysis sub-channels and constructing multiple sub-analysis channels using multi-dimensional operators, including support vector machines, BP neural networks, random forests, and long short-term memory networks. By constructing multiple analysis channels using multi-dimensional operators including different machine learning or deep learning algorithms, it is possible to better process multi-source data, extract useful feature information, and improve the performance and scalability of the model. Then, the training data set equalization unit evenly divides the training data set including the community operation and maintenance data set and the identification data set into N parts to obtain N training sets, where N is the number of multi-dimensional operators, and N is a positive integer that can provide training samples of the same data for each algorithm.

[0026] Next, the analysis sub-channel selection unit randomly selects a sub-channel from multiple analysis sub-channels as the first analysis sub-channel, and randomly selects N times without replacement from the N training sets to obtain the first training set, ensuring that each selected training set is independent and each training set is only selected once, avoiding overfitting. The convergence analysis sub-channel acquisition unit uses the community operation and maintenance data as input and the identification data as supervision information, selects the first training set to train the first analysis sub-channel, and uses the identification data as a label for supervision and verification. Through continuous iteration and optimization, until the predetermined convergence conditions are met, the first convergence analysis sub-channel that meets the expected convergence constraints is obtained. At the same time, the remaining N-1 training sets in the N training sets are used to perform supervised training and feedback verification on other analysis sub-channels in the same way to obtain multiple convergence analysis sub-channels. Finally, the convergence data analysis channel construction unit integrates the multiple convergence analysis sub-channels obtained by the convergence analysis sub-channel acquisition unit to form a final convergence data analysis channel. Each convergent analysis subchannel in the convergent data analysis channel will analyze the input data and generate an output. The final output of the convergent data analysis channel is the mode of all convergent analysis subchannel outputs, that is, the output with the most occurrences. By combining the advantages of multiple algorithms, training multiple analysis subchannels, and integrating them into a convergent data analysis channel, the data can be understood more comprehensively, the accuracy and robustness of the output data can be improved, and the timeliness and accuracy of subsequent community service management can be improved.

[0027] In one embodiment, Figure 2 As shown, the first-layer matching module 20 further includes: a data acquisition unit 21, the data acquisition unit is used to acquire basic information of operation and maintenance personnel and expected business types, wherein the expected business type includes multiple fault attributes; an information matching unit 22, the information matching unit is used to select a first fault attribute of a first business type, perform matching analysis on the basic information of the operation and maintenance personnel based on the first business type, determine a set of matching personnel, and screen the set of matching personnel according to the first fault attribute to determine a first set of matching personnel; a relationship establishment unit 23, the relationship establishment unit is used to establish a first mapping relationship between the first business type, the first fault attribute and the first matching personnel set; an operation and maintenance associated database construction unit 24, the operation and maintenance associated database construction unit is used to construct the operation and maintenance associated database according to the first mapping relationship based on the decision tree principle.

[0028] Specifically, the data acquisition unit obtains the basic information and expected business type of the operation and maintenance personnel from the community's internal human resources database or employee archive database. The basic information of the operation and maintenance personnel includes name, education, repairable type, experience, professional quality, etc. The expected business type includes multiple fault attributes, such as repair parts, fault level, fault complexity, etc. The information matching unit selects any one of the multiple expected business types as the first business type, and selects the first fault attribute corresponding to the first business type. Then, according to the selected first business type, the basic information of the operation and maintenance personnel is matched and analyzed to determine the operation and maintenance personnel suitable for handling the business type as a set of matching personnel. Then, the first fault attribute of the first business type is used as a screening condition to further screen the set of matching personnel to ensure that the screened operation and maintenance personnel have the ability to handle the fault, forming a first set of matching personnel. The relationship establishment unit determines the first set of matching personnel corresponding to the first business type and the first fault attribute, establishes and stores this mapping relationship, that is, each business type and fault attribute corresponds to a matching operation and maintenance personnel, which is convenient for subsequent rapid retrieval and allocation of operation and maintenance personnel. Finally, the operation and maintenance associated database construction unit uses the decision tree principle to construct the operation and maintenance associated database according to the first mapping association, wherein the decision tree represents the decision rules through a tree structure, is used to classify new data, uses historical operation and maintenance data and mapping relationships as training data, generates a decision tree model through algorithm learning, and constructs an operation and maintenance associated database based on the decision tree model to store and manage the association between business types, fault attributes and operation and maintenance personnel. Through the operation and maintenance associated database, the operation and maintenance personnel suitable for handling specific business types and fault attributes can be quickly located, effectively supporting the allocation and management of operation and maintenance personnel, and improving the efficiency and accuracy of operation and maintenance work.

[0029] In a possible implementation, the mapping relationship establishing unit includes: a personnel information acquisition unit, the personnel information acquisition unit is used to acquire first basic information of multiple first matching personnel in the first matching personnel set, wherein the first basic information includes academic qualifications, professional skills, historical maintenance times, historical maintenance time averages, and customer rating averages; a weight setting unit, the weight setting unit is used to use a coefficient of variation method to set weight coefficients for the academic qualifications, the professional skills, the historical maintenance times, the historical maintenance time averages, and the customer rating averages, and obtain multiple first scoring information of the multiple first matching personnel by weighting based on the weight coefficients; an information screening unit, the information screening unit is used to screen the multiple first scoring information according to a preset scoring threshold, add the first matching personnel corresponding to the first scoring information that meets the preset scoring threshold into a first-layer personnel matching set, and add the first matching personnel corresponding to the first scoring information that does not meet the preset scoring threshold into a second-layer personnel matching set; a mapping relationship establishing unit, the mapping relationship establishing unit is used to establish a first mapping relationship between the first business type, the first fault attribute, the first-layer personnel matching set, and the second-layer personnel matching set.

[0030] Specifically, the personnel information acquisition unit obtains the first basic information of each first matching personnel from the first matching personnel set, including key data such as education, professional skills, historical maintenance times, historical maintenance time average, and customer score average for evaluating the comprehensive ability and service quality of the operation and maintenance personnel, wherein the historical maintenance times are the historical maintenance times for the first fault attribute. Then, the weight setting unit uses the coefficient of variation method to set the weight coefficient for each basic information indicator. The coefficient of variation method is a statistical method that determines the weight by calculating the standard deviation of each indicator and its mean, and is used to quantify the importance of each indicator for the evaluation of the ability of the operation and maintenance personnel. Next, the weight setting unit performs weighted processing on the basic information according to the set weight coefficient to obtain the first score information of each first matching personnel. Next, the information screening unit screens the first score information of each operation and maintenance personnel according to the preset score threshold. The preset score threshold is set according to business needs and goals. When there is an operation and maintenance personnel who meets the preset score threshold, it means that the score of the operation and maintenance personnel is greater than or equal to the preset score threshold and belongs to a priority matching object, and then the operation and maintenance personnel who meet the preset score threshold are added to a layer of personnel matching set. For the operation and maintenance personnel who do not meet the preset scoring threshold, they are added to the second-layer personnel matching set as an alternative. Finally, the mapping relationship establishment unit associates each business type and fault attribute with the corresponding first-layer personnel matching set and second-layer personnel matching set. By establishing an effective mapping relationship, the platform can quickly retrieve the most suitable operation and maintenance personnel when facing different business types and fault attributes, whether it is the first-layer personnel matching set as the first choice or the second-layer personnel matching set as the backup option, which improves the flexibility and efficiency of resource allocation, realizes efficient management and optimization of maintenance services, and improves maintenance efficiency and quality.

[0031] In a possible implementation, the weight setting unit further includes: a recent score acquisition unit, which is used to configure a score update cycle, collect the historical maintenance times, the average historical maintenance time and the average customer score of the first matching personnel in the most recent period based on the score update cycle, and weight them to obtain multiple first recent score information; a gradual weight setting unit, which is used to set the gradual weight based on the sequence of the score update cycle, and perform weighted calculation on the first recent score information and multiple historical score information according to the gradual weight to obtain updated score information to periodically update and replace the first score information.

[0032] Specifically, the smart community service management platform for business handling also includes a recent score acquisition unit and a gradual weight setting unit. The recent score acquisition unit is responsible for configuring the score update cycle and collecting relevant data at the end of each cycle, that is, setting the update cycle, such as in units of weeks, months, years, etc., to obtain the relevant data of the first matching person in the cycle, including the historical maintenance times, historical maintenance time average and customer score average of the first matching person, and then weighted calculation of the collected data to obtain multiple first recent score information. The gradual weight setting unit sets the gradual weight based on the order of the score update cycle. By setting the gradual weight, the platform can regularly update and re-evaluate the recommended priority of the maintenance personnel. The more recent data will be given a higher weight, while the more distant data will gradually reduce the weight. Then, according to the gradual weight, the first recent score information and the score information in multiple historical periods are weighted and calculated to generate a new updated score information that comprehensively considers recent performance and historical records. Finally, the updated score information obtained by calculation is used to periodically replace the original first score information to ensure that the scoring system always remains up to date and accurate. By setting gradual weights, we can ensure that the scoring information can timely reflect the current performance of the operation and maintenance personnel, while not completely ignoring their past achievements. This will help the management platform dynamically evaluate the performance of the operation and maintenance personnel and adjust resource allocation in a timely manner to adapt to the ever-changing business needs and the actual working status of the operation and maintenance personnel, thereby achieving efficient management and optimization of community maintenance services, improving maintenance efficiency and quality, and providing residents with a better and more convenient community living environment.

[0033] In a possible implementation, the intelligent decision-making module 30 further includes: a simulated maintenance path acquisition unit, which is used to obtain the real-time location information of multiple first-layer idle personnel, perform maintenance path simulation based on the real-time location information and the fault coordinates, and determine multiple simulated maintenance paths; a fitness analysis unit, which is used to perform fitness analysis based on the multiple simulated maintenance paths and multiple preset personnel scores, and set the first-layer idle personnel with the highest fitness as the first maintenance personnel.

[0034] Specifically, the simulated maintenance path acquisition unit obtains the real-time location information of multiple idle personnel in the first layer through GPS or other positioning technology, and uses a path planning algorithm, such as Dijkstra algorithm, A* algorithm or other algorithms suitable for real-time path planning, to simulate multiple paths from idle personnel to the current fault location according to the real-time location information and the fault coordinates, so as to form multiple simulated maintenance paths. Then, the fitness analysis unit receives multiple simulated maintenance paths from the simulated maintenance path acquisition unit, and assigns weights to the simulated maintenance path of each idle personnel and the preset personnel score of the corresponding idle personnel. For example, the shorter the path length and the expected arrival time, the higher the weight, and the better the maintenance quality, the higher the weight. Then, according to the simulated maintenance path and preset score of each idle personnel, weighting is performed according to their respective weights to calculate a comprehensive score, i.e., fitness. Compare the comprehensive scores of all idle personnel in the first layer, and select the person with the highest score as the first maintenance personnel. The person not only has the shortest path or the shortest expected arrival time, but also has the highest preset score. Through fitness analysis, it is possible to ensure that the most suitable maintenance personnel are dispatched to complete the maintenance task in the shortest time and with the highest efficiency, thereby improving customer satisfaction and the overall effectiveness of the platform.

[0035] In a possible implementation, the intelligent decision-making module 30 further includes: a prediction coefficient output unit, the prediction coefficient output unit is used to judge if the first layer of idle personnel set is 0, input the business type and the fault attribute into the risk prediction channel to perform maintenance urgency prediction, and output the urgency prediction coefficient; a prediction coefficient comparison unit, the prediction coefficient comparison unit is used to judge if the urgency prediction coefficient is greater than a preset urgency coefficient threshold, then match the second layer of idle operation and maintenance personnel to obtain the second layer of idle personnel set; a maintenance task determination unit, the maintenance task determination unit is used to make intelligent decisions based on the real-time location information of the second layer of idle personnel and the preset personnel score, and determine the second maintenance personnel to perform the target maintenance task.

[0036] Specifically, when the intelligent decision-making module 30 determines that the first-layer idle personnel set is 0, that is, there is no suitable first-layer idle personnel available for dispatch, the first prediction coefficient output unit is input into the risk prediction channel according to the current business type and fault attribute. The risk prediction channel predicts the urgency of the maintenance task according to the historical data of the business type and fault attribute, business characteristics, fault severity and other factors, and outputs the urgency prediction coefficient. The risk prediction channel is constructed based on data analysis and machine learning technology, and can receive input information such as business type and fault attribute, and predict the urgency of the maintenance task based on this information. The prediction coefficient comparison unit compares the urgency prediction coefficient output by the prediction coefficient output unit with the preset urgency coefficient threshold, and the preset urgency coefficient threshold is set in advance and is used to determine whether the urgency of the maintenance task has reached the level that requires immediate action. If the urgency prediction coefficient is greater than the preset urgency coefficient threshold, it indicates that the maintenance task is very urgent, and then the second-layer idle operation and maintenance personnel are matched, and the second-layer idle personnel set is obtained according to the availability, location, skills and other information of the second-layer idle personnel. Finally, the maintenance task determination unit obtains the most suitable second maintenance personnel based on the comprehensive score of the real-time location information of the second-layer idle personnel and the corresponding preset personnel scores, and then makes intelligent decisions based on the comprehensive score of each personnel to obtain the most suitable second maintenance personnel, that is, the second-layer idle personnel with the highest score and the shortest path among the second-layer idle personnel. The target maintenance task is performed according to the determined second maintenance personnel to ensure that when the first-layer idle personnel are unavailable, the management platform can also respond quickly and dispatch suitable maintenance personnel to ensure the efficient execution of maintenance tasks and provide residents with a better and more convenient community living environment.

[0037] In a possible implementation, the task execution module 40 further includes: a dynamic maintenance table update unit, which is used to determine if the scheduled maintenance time is an expected node, and then insert the scheduled maintenance time, the business type, the fault attribute and the fault coordinates into the dynamic maintenance table to complete the real-time update of the dynamic maintenance table; a maintenance operation determination unit, which is used to perform daily maintenance operations of operation and maintenance personnel based on the dynamic maintenance table.

[0038] Specifically, when the dynamic maintenance table update unit determines that the scheduled maintenance time is an expected node, it will immediately insert the key data set of the target maintenance information, the scheduled maintenance time, the business type, the fault attribute and the fault coordinates into the dynamic maintenance table. The expected node refers to a pre-set time point or time period. At this time point or time period, the platform expects to perform a certain maintenance task. The dynamic maintenance table is a table updated in real time, which can reflect the current and recent maintenance needs and status. By inserting the key data set into the dynamic maintenance table, the real-time update of the dynamic maintenance table is completed, ensuring the real-time and accuracy of the dynamic maintenance table. The maintenance operation determination unit obtains the data in the dynamic maintenance table in real time, understands the current maintenance needs and status, and then selects the appropriate operation and maintenance personnel based on the information in the dynamic maintenance table to perform the daily maintenance operations of the operation and maintenance personnel. Through the collaborative work of the dynamic maintenance table update unit and the maintenance operation determination unit, the intelligent community operation and maintenance management system can achieve efficient management of maintenance tasks and reasonable scheduling of operation and maintenance personnel, thereby improving the quality and efficiency of maintenance services.

[0039] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0040] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A smart community service management platform for business handling, characterized by: The management platform includes: A target maintenance information identification module, the target maintenance information identification module is used to obtain the target maintenance information received by the platform, identify the target maintenance information, and determine a key data set, wherein the key data set includes a business type, a fault attribute, a fault coordinate, and a scheduled maintenance time; A first-layer matching module, wherein the first-layer matching module is used to determine if the scheduled maintenance time is the current node, input the business type and the fault attribute into the operation and maintenance association database for first-layer matching, and determine a first-layer idle personnel set; An intelligent decision-making module, wherein the intelligent decision-making module is used to determine if the first layer of idle personnel set is not 0, obtain the real-time location information of the first layer of idle personnel, make an intelligent decision based on the real-time location information and the preset personnel score, and determine the first maintenance personnel; A task execution module, wherein the task execution module is used to send the target maintenance information to the first maintenance personnel and execute the target maintenance task based on the fault coordinates.

2. The management platform according to claim 1, characterized in that: The target maintenance information identification module includes: An indicator configuration unit, the indicator configuration unit is used to configure data identification indicators, wherein the data identification indicators at least include business type, fault attributes, location information and maintenance time; An information extraction unit, the information extraction unit is used to collect community operation and maintenance data online, obtain a community operation and maintenance data set, and extract information from the community operation and maintenance data set based on the data identification index to obtain an identification data set; A channel training unit is used to train a data analysis channel constructed based on a multidimensional operator using the community operation and maintenance data set and the identification data set as training data sets to obtain a convergent data analysis channel, and identify the target maintenance information through the convergent data analysis channel.

3. The management platform according to claim 2, characterized in that: The channel training unit comprises: An analysis subchannel construction unit, the analysis subchannel construction unit is used to construct a plurality of analysis subchannels based on a multidimensional operator, wherein the multidimensional operator includes a support vector machine, a BP neural network, a random forest, and a long short-term memory network; A training data set dividing unit, the training data set dividing unit is used to divide the training data set into N equal parts, wherein N is the number of the multidimensional operators, to obtain N training sets; An analysis subchannel selection unit, the analysis subchannel selection unit is used to select a first analysis subchannel from the plurality of analysis subchannels, and randomly select N times without replacement from the N training sets to obtain a first training set; A convergence analysis subchannel obtaining unit, the convergence analysis subchannel obtaining unit is used to use the community operation and maintenance data as input and the identification data as supervision, to perform supervised training and feedback verification on the first analysis subchannel through the first training set, to obtain a first convergence analysis subchannel that meets the expected convergence constraint, and to use the N training sets to perform supervised training and feedback verification on other analysis subchannels respectively, to obtain multiple convergence analysis subchannels; A convergence data analysis channel construction unit is used to construct the convergence data analysis channel based on a plurality of convergence analysis sub-channels, wherein the output of the convergence data analysis channel is the mode of the plurality of convergence analysis sub-channels.

4. The management platform according to claim 1, characterized in that: The first-layer matching module comprises: A data acquisition unit, the data acquisition unit is used to acquire basic information of the operation and maintenance personnel and the expected business type, wherein the expected business type includes multiple fault attributes; An information matching unit, the information matching unit being used to select a first fault attribute of a first business type, perform matching analysis on the basic information of the operation and maintenance personnel based on the first business type to determine a set of matching personnel, and screen the set of matching personnel according to the first fault attribute to determine a first set of matching personnel; A relationship establishing unit, the relationship establishing unit being used to establish a first mapping relationship between the first service type, the first fault attribute and the first matching personnel set; An operation and maintenance related database construction unit is used to construct the operation and maintenance related database according to the first mapping relationship based on a decision tree principle.

5. The management platform according to claim 4, characterized in that: The mapping relationship establishing unit comprises: A personnel information acquisition unit, the personnel information acquisition unit is used to acquire first basic information of a plurality of first matching persons in the first matching person set, wherein the first basic information includes education background, professional skills, historical maintenance times, historical maintenance time average, and customer rating average; A weight setting unit, the weight setting unit is used to set weight coefficients for the academic qualifications, the professional skills, the historical maintenance times, the historical maintenance time average, and the customer score average, respectively, by using a coefficient of variation method, and to obtain a plurality of first score information of the plurality of first matching persons by weighting based on the weight coefficients; an information screening unit, the information screening unit being used to screen the plurality of first scoring information according to a preset scoring threshold, add the first matching persons corresponding to the first scoring information satisfying the preset scoring threshold into a first-layer matching set of persons, and add the first matching persons corresponding to the first scoring information not satisfying the preset scoring threshold into a second-layer matching set of persons; A mapping relationship establishing unit, wherein the mapping relationship establishing unit is used to establish a first mapping relationship between the first service type, the first fault attribute, the first-layer personnel matching set, and the second-layer personnel matching set.

6. The management platform according to claim 5, characterized in that: The weight setting unit comprises: A recent score obtaining unit, the recent score obtaining unit is used to configure a score update cycle, collect the historical maintenance times, the historical maintenance time average and the customer score average of the first matching personnel in the most recent cycle based on the score update cycle, and perform weighted calculations to obtain a plurality of first recent score information; A gradual weight setting unit is used to set a gradual weight based on the order of the score update cycle, perform weighted calculation on the first recent score information and multiple historical score information according to the gradual weight, obtain updated score information, and periodically update and replace the first score information.

7. The management platform according to claim 1, characterized in that: The intelligent decision-making module includes: A simulated maintenance path acquisition unit, the simulated maintenance path acquisition unit is used to acquire real-time location information of a plurality of idle personnel on the first layer, perform maintenance path simulation based on the real-time location information and the fault coordinates, and determine a plurality of simulated maintenance paths; A fitness analysis unit is used to perform fitness analysis based on the multiple simulated maintenance paths and multiple preset personnel scores, and set the first-layer idle personnel with the highest fitness as the first maintenance personnel.

8. The management platform according to claim 1, characterized in that: The intelligent decision-making module further includes: A prediction coefficient output unit, the prediction coefficient output unit is used to determine if the first layer of idle personnel set is 0, input the business type and the fault attribute into the risk prediction channel to perform maintenance urgency prediction, and output an urgency prediction coefficient; A prediction coefficient comparison unit, wherein the prediction coefficient comparison unit is used to determine if the urgency prediction coefficient is greater than a preset urgency coefficient threshold, then perform a second-layer idle operation and maintenance personnel match to obtain a second-layer idle personnel set; A maintenance task determination unit is used to make intelligent decisions based on the real-time location information of the second-level idle personnel and the preset personnel scores to determine that the second maintenance personnel performs the target maintenance task.

9. The management platform according to claim 1, characterized in that: The task execution module also includes: A dynamic maintenance table updating unit, wherein the dynamic maintenance table updating unit is used to determine if the scheduled maintenance time is an expected node, insert the scheduled maintenance time, the service type, the fault attribute and the fault coordinates into a dynamic maintenance table, and complete the real-time update of the dynamic maintenance table; A maintenance operation determination unit is used to perform daily maintenance operations of operation and maintenance personnel based on the dynamic maintenance table.

Images