Data analysis system and method for intelligent community service platform

Abstract

The invention relates to the technical field of community service platform management, in particular to a data analysis system and method for an intelligent community service platform, and the system comprises a platform data collection module, a to-be-coordinated target screening module, a maintenance progress analysis module and a work order coordination planning module. Equipment maintenance reservation data and equipment maintenance work order receiving data on a community service platform are acquired through a platform data acquisition module, a maintenance delay risk coefficient of maintenance personnel is analyzed through a to-be-coordinated target screening module, and a maintenance work order to-be-coordinated target is preliminarily screened out; a maintenance progress prediction model is established through the maintenance progress analysis module, the maintenance condition of the preliminarily screened maintenance work order to-be-coordinated targets is predicted, the final maintenance work order to-be-coordinated targets are secondarily screened through the work order coordination planning module, and the maintenance work orders received by the screened targets are prompted and coordinated. And the life equipment use problem of community residents can be solved in time.

Description

Technical Field

[0001] The present invention relates to the technical field of community service platform management, and in particular to a data analysis system and method for an intelligent community service platform. Background Art

[0002] The smart community service platform mainly provides services for residents and community managers, including living payment, parking space data sharing, service appointment processing, emergency warning and notification services, which bring convenience to the lives of community residents. Among them, the service appointment processing service includes equipment warranty service. If the equipment used by community residents fails and needs repair, residents can log in to the community service platform for warranty. After the residents enter the equipment failure problem, scheduled repair time and other information on the platform, the community service platform will generate an equipment maintenance work order. Relevant maintenance personnel can choose to receive and process some maintenance work orders after logging in to the platform. After the platform completes the identity review, they can go to the equipment failure location for equipment maintenance. The platform can also assign maintenance work orders to relevant maintenance personnel for processing according to actual conditions. For the maintenance personnel who choose to receive maintenance work orders on their own, some maintenance personnel may choose to process too many maintenance work orders or maintenance work orders with too concentrated maintenance time because they are not clear about the time required for equipment maintenance. It is easy for this situation to cause the maintenance personnel to be unable to go to the fault location for equipment maintenance in time according to the appointment time. For this special situation, if the platform does not remind and coordinate in time, it will not be conducive to helping to solve the problem of living equipment use of community residents in a timely manner, and bring inconvenience to residents' lives.

[0003] Therefore, people need a data analysis system and method for an intelligent community service platform to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a data analysis system and method for an intelligent community service platform to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a data analysis system for an intelligent community service platform, the system comprising: a platform data acquisition module, a target screening module for coordination, a maintenance progress analysis module and a work order coordination planning module; The platform data collection module collects equipment maintenance reservation data and equipment maintenance work order receipt data on the community service platform; The to-be-coordinated target screening module analyzes the maintenance delay risk coefficient of the maintenance personnel based on the equipment maintenance work order receiving data, and preliminarily screens the to-be-coordinated targets of the maintenance work order based on the maintenance delay risk coefficient; A maintenance progress prediction model is established through the maintenance progress analysis module to predict the maintenance status of the maintenance work orders to be coordinated, and to predict whether the targets can complete the received equipment maintenance work on time; The work order coordination planning module screens out the final maintenance work order targets to be coordinated for a second time based on the prediction results, and prompts and coordinates the maintenance work orders received by the screened targets.

[0006] Preferably, the platform data collection module includes a fault information collection unit, a reservation information collection unit and a work order data collection unit; When a device used by community residents breaks down, the residents log in to the community service platform and fill in the device failure information on the platform to make an appointment for device maintenance. After a successful appointment, the platform will generate a device maintenance work order. The maintenance personnel can log in to the platform to receive the appointment information and choose to receive the device maintenance work order. After receiving and passing the platform review, they will go to the equipment for maintenance. The platform review refers to the community service platform reviewing the identity information of the maintenance personnel. After the review is passed, the maintenance personnel can go to the maintenance location to repair the equipment and collect the equipment failure data previously filled in on the platform through the fault information collection unit; The appointment information collection unit collects the appointment time information of the equipment maintenance work orders that have been booked and have not started equipment maintenance on the current platform; The work order data collection unit collects scheduled maintenance time information on equipment maintenance work orders currently received by all maintenance personnel on the platform; All of the above information is collected after users who log in to the community service platform grant permission. Users refer to community residents and maintenance personnel.

[0007] Preferably, the target screening module to be coordinated includes a risk coefficient analysis unit and a target screening unit; The risk coefficient analysis unit counts the number of equipment maintenance work orders currently received by different maintenance personnel and the scheduled maintenance time intervals on the work orders based on the scheduled maintenance time information on the equipment maintenance work orders currently received by all maintenance personnel on the platform, and analyzes the maintenance delay risk coefficients of different maintenance personnel based on the statistical results; The target screening unit compares the maintenance delay risk coefficients of different maintenance personnel and preliminarily screens out maintenance personnel who need to be prompted and coordinated with the received maintenance work orders. The corresponding screened maintenance personnel are the preliminarily screened maintenance work order coordination targets.

[0008] Preferably, the maintenance progress analysis module includes a progress prediction model building unit, a maintenance time analysis unit and a progress on-time situation prediction unit; The progress prediction model establishment unit obtains historical equipment maintenance work orders generated on the platform, obtains the time data spent by maintenance personnel to complete the equipment maintenance work on the historical equipment maintenance work orders, analyzes the difficulty coefficient of the equipment maintenance work on the historical equipment maintenance work orders, performs fitting training on the difficulty coefficient and the time data spent, and establishes a maintenance progress prediction model; The maintenance time analysis unit analyzes the difficulty coefficient of the maintenance personnel repairing the faulty equipment corresponding to each maintenance work order currently received, substitutes the difficulty coefficient into the maintenance progress prediction model, and predicts the time required for the maintenance personnel to repair the faulty equipment corresponding to each maintenance work order currently received; The progress prediction unit sorts the maintenance work orders from the front to the back according to the equipment maintenance appointment time on the maintenance work orders received by the maintenance personnel, calculates the time interval between the equipment maintenance appointments on two adjacent maintenance work orders, compares the time interval with the predicted time required to repair the faulty equipment corresponding to the previous maintenance work order, and predicts whether the corresponding maintenance personnel can complete the received equipment maintenance work on time based on the comparison result.

[0009] Preferably, the work order coordination planning module includes a target secondary screening unit and a work order prompt coordination unit; The target secondary screening unit screens out the maintenance personnel who need to remind and coordinate the received maintenance work orders for final confirmation; The work order prompt coordination unit sends a prompt message to the terminal where the screened maintenance personnel are located. The prompt message is: reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all currently received maintenance work orders on time, and suggesting that the corresponding maintenance personnel cancel the acceptance of the designated maintenance work order. After the corresponding maintenance personnel cancels the acceptance of the designated maintenance work order, the maintenance work on the designated maintenance work order will be arranged to the remaining maintenance personnel.

[0010] A data analysis method for an intelligent community service platform comprises the following steps: Z1: Collect equipment maintenance appointment data and equipment maintenance work order receipt data on the community service platform; Z2: Analyze the maintenance delay risk coefficient of maintenance personnel, and preliminarily select the maintenance work orders to be coordinated based on the maintenance delay risk coefficient; Z3: Establish a maintenance progress prediction model to predict the maintenance status of the maintenance work orders to be coordinated, and predict whether the target can complete the received equipment maintenance work on time; Z4: Based on the prediction results, the final maintenance work order to be coordinated is screened out for the second time, and the maintenance work orders received by the screened targets are prompted and coordinated.

[0011] Preferably, step Z1: collect the equipment failure data previously filled in on the community service platform, collect the appointment time information of the equipment maintenance work orders that have been booked but have not started equipment maintenance on the current platform, and obtain the number of equipment maintenance work orders currently received by all maintenance personnel on the platform as F={F1, F2, ..., F n The equipment maintenance work order currently received refers to the maintenance work order received by the maintenance personnel within one day. The equipment maintenance appointment time on the equipment maintenance work orders currently received by all maintenance personnel is collected, and the equipment maintenance work orders currently received by each maintenance personnel are arranged in order from the front to the back according to the equipment maintenance appointment time. The equipment maintenance appointment time interval set of two adjacent work orders currently received by a random maintenance personnel is obtained as T={T1, T2, ..., T v}, n represents the number of maintenance personnel, corresponding to the maintenance personnel who received a total of v+1 equipment maintenance work orders, T v It indicates the time interval between the equipment maintenance appointments on the v+1th equipment maintenance work order and the vth equipment maintenance work order after sorting.

[0012] Preferably, step Z2: Calculate the maintenance delay risk coefficient P of a random maintenance worker according to the following formula: i : P i =(F i ) / ∑ n i=1 (F i )+1 / [(∑ v j=1 ((T j )-∑ v j=1 (T j ) / v) 2 ) / v] 1 / 2 ; The maintenance delay risk coefficient set of n maintenance personnel is calculated as {P1, P2, ..., P i , ..., P n}, arrange the maintenance delay risk coefficients of n maintenance personnel in ascending order, and after the sorting is completed, randomly assign the maintenance delay risk coefficients of n maintenance personnel to u data sets, where each maintenance delay risk coefficient in the previous data set is smaller than each maintenance delay risk coefficient in the next data set, and obtain a random assignment result. The mean set of all maintenance delay risk coefficients in each data set is {p1, p2, ... p u}, according to X=[∑ u e=1 ((p e )-∑ u e=1 (pe ) / u) 2 ] / uAnalyze the difference degree X of the maintenance delay risk coefficients between data sets in a random allocation result, compare the difference degrees of the maintenance delay risk coefficients between data sets in different allocation results, select the allocation result with the largest difference degree, and preliminarily select the maintenance work order to be coordinated from the selected allocation results: all the remaining maintenance personnel except the maintenance personnel corresponding to the maintenance delay risk coefficient in the first data set; Taking into account that for some maintenance personnel who receive a small number of maintenance work orders in a day and whose appointment times on the maintenance work orders are relatively scattered, it is highly likely that they will not be unable to arrive at the next faulty equipment location for maintenance in time. By collecting the number of maintenance work orders currently received by different maintenance personnel and the corresponding equipment maintenance appointment times, the maintenance delay risk coefficient is analyzed in combination with the number of maintenance work orders and the concentration of appointment times. The more maintenance work orders and the more concentrated the appointment times are, the greater the risk of the above abnormal situations. Some maintenance personnel who are highly likely to not be unable to arrive at the next faulty equipment location for maintenance in time are screened out, which reduces the workload of maintenance work management and increases the necessity of subsequent reminders and coordination of maintenance work orders.

[0013] Preferably, step Z3: obtaining historical equipment maintenance work orders generated in the past on the community service platform, and obtaining a set of working time of maintenance personnel who received each historical equipment maintenance work order as {t1, t2, ..., t r ..., t k}, where k represents the number of historical equipment maintenance work orders, and the time taken by maintenance personnel to complete the equipment maintenance work on the corresponding historical equipment maintenance work order is {t1 ’ , t2 ’ , ..., t r ’ ..., t k ’}, according to the formula W r =1 / t r +(t r ’ ) / ∑ k r=1 (t r ’ ) Calculate the difficulty coefficient W of the equipment maintenance work on a random work order among k work orders r , the difficulty coefficient set of the equipment maintenance work on the k work orders is calculated as {W1, W2, ..., W r , ..., W k}, generate training data set {(W1, t1 ’ ), (W2, t2 ’ ), ..., (W k, t k ’ )}, after performing a straight line fitting on the data in the training data set, a maintenance progress prediction model is established: y=β*x+γ, where * represents the multiplication sign, β and γ are fitting coefficients, and r represents the rth historical equipment maintenance work order. The equipment failure data on the equipment maintenance work order currently received by the maintenance personnel who have been initially screened are retrieved, and the maintenance work orders are sorted in order from the front to the back according to the equipment maintenance appointment time on the maintenance work order currently received by the corresponding maintenance personnel. The equipment failure data on the first equipment maintenance work order currently received by the maintenance personnel who have been initially screened is used as the specified data. The DSSM algorithm is used to calculate the semantic similarity between the specified data and the equipment failure data on the historical equipment maintenance work orders previously generated on the platform, and the historical equipment maintenance work orders with the highest semantic similarity between the equipment failure data and the specified data are screened out. The time spent by the maintenance personnel who received the corresponding screened historical equipment maintenance work order to complete the equipment maintenance work on the corresponding work order is obtained as R, and the working time of the current maintenance personnel is obtained as J. The difficulty coefficient w of the corresponding maintenance personnel repairing the faulty equipment corresponding to any maintenance work order currently received is analyzed, w=1 / J+R / ∑ k r=1 (t r ’ ), substitute w into the maintenance progress prediction model: let x=w, and predict that the time required for the corresponding maintenance personnel to repair the faulty equipment corresponding to the first maintenance work order currently received is Q1, Q1=β*w+γ, and the interval between the appointment time on the second maintenance work order currently received by the corresponding maintenance personnel and the appointment time on the first maintenance work order is T1, and compare Q1 and T1: if Q1≤T1, it is predicted that the corresponding maintenance personnel can complete the maintenance work of the received equipment on time, and no work order reminder or coordination processing is made for the corresponding maintenance personnel; if Q1>T1, it is predicted that the corresponding maintenance personnel cannot complete the maintenance work of the received equipment on time.

[0014] Preferably, step Z4: if Q1>T1, the corresponding maintenance personnel are selected as the final maintenance work order to be coordinated, the first maintenance work order currently received by the corresponding maintenance personnel is used as the designated maintenance work order, and a prompt message is sent to the terminal where the corresponding maintenance personnel is located, reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all the currently received maintenance work orders on time, and suggesting that the corresponding maintenance personnel cancel the designated maintenance work order. After the corresponding maintenance personnel cancels the designated maintenance work order, the maintenance work on the designated maintenance work order is arranged to other maintenance personnel; After initially screening out the maintenance personnel who need to manage maintenance work orders, in order to predict whether the maintenance personnel can complete the received equipment maintenance work on time, that is, to predict whether they can go to the location of the faulty equipment on time according to the appointment time to perform equipment maintenance work based on their current actual situation, by collecting and analyzing the historical equipment maintenance work orders generated on the platform, taking into account the maintenance work experience of maintenance personnel, more experienced personnel may find it easier to handle maintenance work and spend less time, and combine the actual time spent on completing maintenance work in the past and the qualifications of the personnel who completed the corresponding work, that is, the time they have been engaged in maintenance work to analyze the difficulty coefficient of the equipment maintenance work on the historical equipment maintenance work order, and compare the difficulty coefficient with the historical time spent The training data is used as training data to fit and establish a maintenance progress prediction model. The qualification data of the current maintenance personnel and the historical equipment failure repair time data that is highly consistent with the equipment failure problems on the work orders received by the current maintenance personnel are input into the model to predict whether the current maintenance personnel can perform equipment maintenance work on time, thereby improving the accuracy of the prediction results. When it is predicted that the maintenance personnel cannot perform equipment maintenance work on time, work order risk warnings and coordination work are promptly carried out, reducing the probability of maintenance personnel blindly accepting inappropriate maintenance work orders and failing to go to the equipment for maintenance at the time scheduled by some residents. This is conducive to helping to promptly solve the problem of living equipment use by community residents and brings convenience to residents' lives.

[0015] Compared with the prior art, the beneficial effects achieved by the present invention are: The present invention collects the number of maintenance work orders currently received by different maintenance personnel and the corresponding equipment maintenance appointment time, analyzes the maintenance delay risk factor in combination with the number of maintenance work orders and the concentration of appointment time, and screens out some maintenance personnel who are unlikely to be unable to rush to the next faulty equipment location for maintenance in time, thereby reducing the workload of maintenance work management and increasing the necessity of subsequent reminders and coordination of maintenance work orders; After initially screening out the maintenance personnel who need to manage maintenance work orders, in order to predict whether the maintenance personnel can complete the received equipment maintenance work on time, that is, to predict whether they can go to the location of the faulty equipment on time according to the appointment time to perform equipment maintenance work based on their current actual situation, by collecting and analyzing the historical equipment maintenance work orders generated on the platform, combined with the actual time spent on completing maintenance work in the past and the qualifications of the personnel who completed the corresponding work, that is, the time they have been engaged in maintenance work, the difficulty coefficient of the equipment maintenance work on the historical equipment maintenance work orders is analyzed, and the difficulty coefficient and the historical time spent are used as training data, the training data is fitted and a maintenance progress prediction is established. The model inputs the qualification data of the current maintenance personnel and the historical equipment failure repair time data that is highly consistent with the equipment failure problems on the work orders received by the current maintenance personnel into the model, which is used to predict whether the current maintenance personnel can perform equipment maintenance work on time, thereby improving the accuracy of the prediction results. When it is predicted that the maintenance personnel cannot perform equipment maintenance work on time, timely work order risk warnings and coordination work are carried out, reducing the probability that the maintenance personnel will be unable to perform equipment maintenance at the scheduled time for some residents due to blindly accepting inappropriate maintenance work orders. This is conducive to helping to promptly solve the problem of living equipment use of community residents and brings convenience to residents' lives. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural diagram of a data analysis system for an intelligent community service platform of the present invention; Figure 2 It is a flow chart of a data analysis method for an intelligent community service platform of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Combine the following Figure 1-Figure 2 The present invention is further described with reference to the accompanying drawings and specific embodiments.

[0019] Embodiment 1: Figure 1 As shown, this embodiment provides a data analysis system for a smart community service platform, the system comprising: a platform data acquisition module, a target screening module to be coordinated, a maintenance progress analysis module and a work order coordination planning module; The output end of the platform data acquisition module is connected to the input end of the target screening module to be coordinated and the maintenance progress analysis module, the output end of the target screening module to be coordinated is connected to the input end of the maintenance progress analysis module, and the output end of the maintenance progress analysis module is connected to the input end of the work order coordination planning module; The platform data collection module collects equipment maintenance reservation data and equipment maintenance work order receipt data on the community service platform; The target screening module to be coordinated analyzes the maintenance delay risk coefficient of the maintenance personnel based on the equipment maintenance work order receiving data, and preliminarily screens the targets to be coordinated for the maintenance work orders based on the maintenance delay risk coefficient; Establish a maintenance progress prediction model through the maintenance progress analysis module to predict the maintenance status of the maintenance work orders to be coordinated, and predict whether the targets can complete the received equipment maintenance work on time; The work order coordination planning module screens out the final targets for coordination of maintenance work orders based on the prediction results, and prompts and coordinates the maintenance work orders received by the screened targets.

[0020] The platform data collection module includes a fault information collection unit, a reservation information collection unit, and a work order data collection unit; The output end of the reservation information collection unit is connected to the input end of the work order data collection unit; When a device used by community residents breaks down, residents can make an appointment for equipment maintenance by logging into the community service platform and filling in the equipment failure information on the platform. After a successful appointment, the platform will generate an equipment maintenance work order. Maintenance personnel can log into the platform to receive the appointment information and choose to receive the equipment maintenance work order. After receiving and passing the platform review, they can go to the equipment for maintenance. Platform review refers to the community service platform reviewing the identity information of the maintenance personnel. After the review is passed, the maintenance personnel can go to the maintenance location to repair the equipment and collect the equipment failure data previously filled in on the platform through the fault information collection unit; The appointment information collection unit collects the appointment time information of the equipment maintenance work orders that have been booked on the current platform but have not started equipment maintenance; The work order data collection unit collects the scheduled maintenance time information on the equipment maintenance work orders currently received by all maintenance personnel on the platform.

[0021] The target screening module to be coordinated includes a risk factor analysis unit and a target screening unit; The input end of the risk factor analysis unit is connected to the output end of the work order data collection unit, and the output end of the risk factor analysis unit is connected to the input end of the target screening unit; The risk factor analysis unit counts the number of equipment maintenance work orders currently received by different maintenance personnel and the scheduled maintenance time intervals on the work orders based on the scheduled maintenance time information on the equipment maintenance work orders currently received by all maintenance personnel on the platform, and analyzes the maintenance delay risk factors of different maintenance personnel based on the statistical results; The target screening unit compares the maintenance delay risk factors of different maintenance personnel and preliminarily screens out the maintenance personnel who need to be prompted and coordinated with the received maintenance work orders. The corresponding screened maintenance personnel are the preliminarily screened maintenance work order coordination targets.

[0022] The maintenance progress analysis module includes a progress prediction model building unit, a maintenance time analysis unit, and a progress on-time situation prediction unit; The input end of the progress prediction model establishment unit is connected to the output ends of the target screening unit and the fault information collection unit, the output end of the progress prediction model establishment unit is connected to the input end of the maintenance time analysis unit, and the output end of the maintenance time analysis unit is connected to the input end of the progress on time situation prediction unit; The progress prediction model establishment unit obtains the historical equipment maintenance work orders generated on the platform, obtains the time data spent by maintenance personnel to complete the equipment maintenance work on the historical equipment maintenance work orders, analyzes the difficulty coefficient of the equipment maintenance work on the historical equipment maintenance work orders, performs fitting training on the difficulty coefficient and the time data, and establishes a maintenance progress prediction model; The maintenance time analysis unit analyzes the difficulty coefficient of the maintenance personnel repairing the faulty equipment corresponding to each maintenance work order currently received, substitutes the difficulty coefficient into the maintenance progress prediction model, and predicts the time required for the maintenance personnel to repair the faulty equipment corresponding to each maintenance work order currently received; The progress prediction unit sorts the maintenance work orders from the front to the back according to the equipment maintenance appointment time on the maintenance work orders received by the maintenance personnel, calculates the time interval between the equipment maintenance appointments on two adjacent maintenance work orders, compares the time interval with the predicted time required to repair the faulty equipment corresponding to the previous maintenance work order, and predicts whether the corresponding maintenance personnel can complete the received equipment maintenance work on time based on the comparison result.

[0023] The work order coordination planning module includes a target secondary screening unit and a work order prompt coordination unit; The input end of the target secondary screening unit is connected to the output end of the progress on-time situation prediction unit, and the output end of the target secondary screening unit is connected to the input end of the work order prompt coordination unit; The maintenance personnel who need to remind and coordinate the received maintenance work orders are screened out through the target secondary screening unit for final confirmation; A prompt message is sent to the terminal where the screened maintenance personnel are located through the work order prompt coordination unit. The prompt message is: reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all currently received maintenance work orders on time, and suggesting that the corresponding maintenance personnel cancel the acceptance of the designated maintenance work order. After the corresponding maintenance personnel cancels the acceptance of the designated maintenance work order, the maintenance work on the designated maintenance work order will be arranged to the remaining maintenance personnel.

[0024] Embodiment 2: Figure 2 As shown, this embodiment provides a data analysis method for an intelligent community service platform, which is implemented based on the data analysis system in the embodiment and specifically includes the following steps: Z1: Collect equipment maintenance appointment data and equipment maintenance work order receiving data on the community service platform: Collect the equipment failure data previously filled in on the community service platform, collect the appointment time information of equipment maintenance work orders that have been booked but not started on the current platform, and obtain the number of equipment maintenance work orders currently received by all maintenance personnel on the platform as F={F1, F2, ..., F n}, collect the equipment maintenance appointment time on the equipment maintenance work orders currently received by all maintenance personnel, arrange the equipment maintenance work orders currently received by each maintenance personnel in order from the front to the back according to the equipment maintenance appointment time, and obtain the equipment maintenance appointment time interval set of two adjacent work orders currently received by a random maintenance personnel as T={T1, T2, ..., T v}, n represents the number of maintenance personnel, corresponding to the maintenance personnel who received a total of v+1 equipment maintenance work orders, T v It indicates the time interval between the equipment maintenance appointments on the v+1th equipment maintenance work order and the vth equipment maintenance work order after sorting; Z2: Analyze the maintenance delay risk coefficient of the maintenance personnel, and preliminarily select the maintenance work orders to be coordinated based on the maintenance delay risk coefficient: Calculate the maintenance delay risk coefficient P of a random maintenance personnel according to the following formula i : P i =(F i ) / ∑ n i=1 (F i )+1 / [(∑ v j=1 ((T j )-∑ v j=1 (T j ) / v) 2 ) / v] 1 / 2 ; The maintenance delay risk coefficient set of n maintenance personnel is calculated as {P1, P2, ..., P i , ..., Pn}, arrange the maintenance delay risk coefficients of n maintenance personnel in ascending order, and after the sorting is completed, randomly assign the maintenance delay risk coefficients of n maintenance personnel to u data sets, where each maintenance delay risk coefficient in the previous data set is smaller than each maintenance delay risk coefficient in the next data set, and obtain a random assignment result. The mean set of all maintenance delay risk coefficients in each data set is {p1, p2, ... p u}, according to X=[∑ u e=1 ((p e )-∑ u e=1 (p e ) / u) 2 ] / uAnalyze the difference degree X of the maintenance delay risk coefficients between data sets in a random allocation result, compare the difference degrees of the maintenance delay risk coefficients between data sets in different allocation results, select the allocation result with the largest difference degree, and preliminarily select the maintenance work order to be coordinated from the selected allocation results: all the remaining maintenance personnel except the maintenance personnel corresponding to the maintenance delay risk coefficient in the first data set; Z3: Establish a maintenance progress prediction model to predict the maintenance status of the maintenance work orders to be coordinated, and predict whether the target can complete the received equipment maintenance work on time: obtain the historical equipment maintenance work orders generated on the community service platform, and obtain the working time set of the maintenance personnel who received each historical equipment maintenance work order as {t1, t2, ..., t r ..., t k}, where k represents the number of historical equipment maintenance work orders, and the time taken by maintenance personnel to complete the equipment maintenance work on the corresponding historical equipment maintenance work order is {t1 ’ , t2 ’ , ..., t r ’ ..., t k ’}, according to the formula W r =1 / t r +(t r ’ ) / ∑ k r=1 (t r ’ ) Calculate the difficulty coefficient W of the equipment maintenance work on a random work order among k work orders r , the difficulty coefficient set of the equipment maintenance work on the k work orders is calculated as {W1, W2, ..., W r , ..., W k}, generate training data set {(W1, t1’ ), (W2, t2 ’ ), ..., (W k , t k ’ )}, after performing a straight line fitting on the data in the training data set, a maintenance progress prediction model is established: y=β*x+γ, where * represents the multiplication sign, β and γ are fitting coefficients, and r represents the rth historical equipment maintenance work order. The equipment failure data on the equipment maintenance work order currently received by the maintenance personnel who have been initially screened are retrieved, and the maintenance work orders are sorted in order from the front to the back according to the equipment maintenance appointment time on the maintenance work order currently received by the corresponding maintenance personnel. The equipment failure data on the first equipment maintenance work order currently received by the maintenance personnel who have been initially screened is used as the specified data. The DSSM algorithm is used to calculate the semantic similarity between the specified data and the equipment failure data on the historical equipment maintenance work orders previously generated on the platform, and the historical equipment maintenance work orders with the highest semantic similarity between the equipment failure data and the specified data are screened out. The time spent by the maintenance personnel who received the corresponding screened historical equipment maintenance work order to complete the equipment maintenance work on the corresponding work order is obtained as R, and the working time of the current maintenance personnel is obtained as J. The difficulty coefficient w of the corresponding maintenance personnel repairing the faulty equipment corresponding to any maintenance work order currently received is analyzed, w=1 / J+R / ∑ k r=1 (t r ’ ), substitute w into the maintenance progress prediction model: let x=w, predict that the time required for the corresponding maintenance personnel to repair the faulty equipment corresponding to the first maintenance work order currently received is Q1, Q1=β*w+γ, and the interval between the appointment time on the second maintenance work order currently received by the corresponding maintenance personnel and the appointment time on the first maintenance work order is T1, and compare Q1 and T1: if Q1≤T1, it is predicted that the corresponding maintenance personnel can complete the maintenance work of the received equipment on time, and no work order reminder and coordination processing is made for the corresponding maintenance personnel; if Q1>T1, it is predicted that the corresponding maintenance personnel cannot complete the maintenance work of the received equipment on time, and the method for judging whether the maintenance personnel can perform the maintenance work on the remaining maintenance work orders currently received on time is the same as the above method; Z4: The final maintenance work order to be coordinated is screened out for the second time based on the prediction result, and the maintenance work orders received by the screened out targets are prompted and coordinated: If Q1>T1, the corresponding maintenance personnel are screened out as the final maintenance work order to be coordinated, and the first maintenance work order currently received by the corresponding maintenance personnel is used as the designated maintenance work order, and a prompt message is sent to the terminal where the corresponding maintenance personnel is located, reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all the maintenance work orders currently received on time, and suggesting that the corresponding maintenance personnel cancel the designated maintenance work order. After the corresponding maintenance personnel cancel the designated maintenance work order, the maintenance work on the designated maintenance work order is arranged to the remaining maintenance personnel; For example, to establish a maintenance progress prediction model: y=22x+19.2, the time set taken by maintenance personnel to complete the equipment maintenance work on the corresponding historical equipment maintenance work order is {t1 ’ , t2 ’ , t3 ’ , t4 ’ , t5 ’}={20, 60, 125, 30, 32}, the unit is minutes, the equipment failure data on the first equipment maintenance work order currently received by the maintenance personnel after preliminary screening is taken as the specified data, and the semantic similarity between the specified data and the equipment failure data on the historical equipment maintenance work orders previously generated on the platform is calculated using the DSSM algorithm, and the historical equipment maintenance work order with the highest semantic similarity between the equipment failure data and the specified data is screened out as t2 ’ Corresponding historical equipment maintenance work orders, the time taken by the maintenance personnel who received the corresponding filtered historical equipment maintenance work orders to complete the equipment maintenance work on the corresponding work orders is R=t2 ’ =60, the current maintenance personnel’s working time is 8 years, according to w=1 / J+R / ∑ k r=1 (t r ’) Calculate the difficulty coefficient of the corresponding maintenance personnel repairing the faulty equipment corresponding to any maintenance work order currently received as 0.35, substitute w into the maintenance progress prediction model: Let x=w=0.35, and predict that the time it takes for the corresponding maintenance personnel to repair the faulty equipment corresponding to the first maintenance work order currently received is about 27 minutes. It is obtained that the interval between the appointment time on the second maintenance work order currently received by the corresponding maintenance personnel and the appointment time on the first maintenance work order is 20 minutes, 27>20, and it is predicted that the corresponding maintenance personnel cannot perform the maintenance work on the second maintenance work order according to the appointment time, that is, the maintenance work of the received equipment cannot be completed on time. The first maintenance work order is used as the designated maintenance work order, and a prompt message is sent to the terminal where the corresponding maintenance personnel is located, reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all the currently received maintenance work orders on time, and suggesting that the corresponding maintenance personnel cancel the acceptance of the designated maintenance work order. After the corresponding maintenance personnel cancels the acceptance of the designated maintenance work order, the maintenance work on the designated maintenance work order is arranged to the remaining maintenance personnel.

[0025] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data analysis system for an intelligent community service platform, characterized in that: The system includes: a platform data acquisition module, a target screening module to be coordinated, a maintenance progress analysis module and a work order coordination planning module; The platform data collection module collects equipment maintenance reservation data and equipment maintenance work order receipt data on the community service platform; The to-be-coordinated target screening module analyzes the maintenance delay risk coefficient of the maintenance personnel based on the equipment maintenance work order receiving data, and preliminarily screens the to-be-coordinated targets of the maintenance work order based on the maintenance delay risk coefficient; A maintenance progress prediction model is established through the maintenance progress analysis module to predict the maintenance status of the maintenance work orders to be coordinated, and to predict whether the targets can complete the received equipment maintenance work on time; The work order coordination planning module screens out the final maintenance work order targets to be coordinated for a second time based on the prediction results, and prompts and coordinates the maintenance work orders received by the screened targets.

2. A data analysis system for an intelligent community service platform according to claim 1, characterized in that: The platform data collection module includes a fault information collection unit, a reservation information collection unit and a work order data collection unit; When a device used by community residents breaks down, the residents log in to the community service platform and fill in the device failure information on the platform to make an appointment for device maintenance. After a successful appointment, the platform will generate a device maintenance work order. The maintenance personnel can log in to the platform to receive the appointment information and choose to receive the device maintenance work order. After receiving and passing the platform review, they will go to the equipment for maintenance. The platform review refers to the community service platform reviewing the identity information of the maintenance personnel. After the review is passed, the maintenance personnel can go to the maintenance location to repair the equipment and collect the equipment failure data previously filled in on the platform through the fault information collection unit; The appointment information collection unit collects the appointment time information of the equipment maintenance work orders that have been scheduled but have not started equipment maintenance on the platform; The work order data collection unit collects scheduled maintenance time information on equipment maintenance work orders received by all maintenance personnel on the platform.

3. A data analysis system for an intelligent community service platform according to claim 2, characterized in that: The target screening module to be coordinated includes a risk coefficient analysis unit and a target screening unit; The risk coefficient analysis unit counts the number of equipment maintenance work orders currently received by different maintenance personnel and the scheduled maintenance time intervals on the work orders based on the scheduled maintenance time information on the equipment maintenance work orders currently received by all maintenance personnel on the platform, and analyzes the maintenance delay risk coefficients of different maintenance personnel based on the statistical results; The target screening unit compares the maintenance delay risk factors of different maintenance personnel and preliminarily screens out maintenance personnel who need to be reminded and coordinated with the received maintenance work orders.

4. A data analysis system for an intelligent community service platform according to claim 3, characterized in that: The maintenance progress analysis module includes a progress prediction model building unit, a maintenance time analysis unit and a progress on-time situation prediction unit; The progress prediction model establishment unit obtains historical equipment maintenance work orders generated on the platform, obtains the time data spent by maintenance personnel to complete the equipment maintenance work on the historical equipment maintenance work orders, analyzes the difficulty coefficient of the equipment maintenance work on the historical equipment maintenance work orders, performs fitting training on the difficulty coefficient and the time data spent, and establishes a maintenance progress prediction model; The maintenance time analysis unit analyzes the difficulty coefficient of the maintenance personnel repairing the faulty equipment corresponding to each maintenance work order currently received, substitutes the difficulty coefficient into the maintenance progress prediction model, and predicts the time required for the maintenance personnel to repair the faulty equipment corresponding to each maintenance work order currently received; The progress prediction unit sorts the maintenance work orders from the front to the back according to the equipment maintenance appointment time on the maintenance work orders received by the maintenance personnel, calculates the time interval between the equipment maintenance appointments on two adjacent maintenance work orders, compares the time interval with the predicted time required to repair the faulty equipment corresponding to the previous maintenance work order, and predicts whether the corresponding maintenance personnel can complete the received equipment maintenance work on time based on the comparison result.

5. A data analysis system for an intelligent community service platform according to claim 4, characterized in that: The work order coordination planning module includes a target secondary screening unit and a work order prompt coordination unit; The target secondary screening unit screens out the maintenance personnel who need to remind and coordinate the received maintenance work orders for final confirmation; The work order prompt coordination unit sends a prompt message to the terminal where the screened maintenance personnel are located. The prompt message is: reminding the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all currently received maintenance work orders on time, and suggesting that the corresponding maintenance personnel cancel the acceptance of the designated maintenance work order. After the corresponding maintenance personnel cancels the acceptance of the designated maintenance work order, the maintenance work on the designated maintenance work order will be arranged to the remaining maintenance personnel.

6. A data analysis method for an intelligent community service platform, characterized in that: The following steps are involved: Z1: Collect equipment maintenance appointment data and equipment maintenance work order receipt data on the community service platform; Z2: Analyze the maintenance delay risk coefficient of maintenance personnel, and preliminarily select the maintenance work orders to be coordinated based on the maintenance delay risk coefficient; Z3: Establish a maintenance progress prediction model to predict the maintenance status of the maintenance work orders to be coordinated, and predict whether the target can complete the received equipment maintenance work on time; Z4: Based on the prediction results, the final maintenance work order to be coordinated is screened out for the second time, and the maintenance work orders received by the screened targets are prompted and coordinated.

7. A data analysis method for a smart community service platform according to claim 6, characterized in that: Step Z1: Collect the equipment failure data previously filled in on the community service platform, collect the appointment time information of the equipment maintenance work orders that have been booked but not started on the current platform, and obtain the number of equipment maintenance work orders currently received by all maintenance personnel on the platform as F={F1, F2, ..., F n }, collect the equipment maintenance appointment time on the equipment maintenance work orders currently received by all maintenance personnel, arrange the equipment maintenance work orders currently received by each maintenance personnel in order from the front to the back according to the equipment maintenance appointment time, and obtain the equipment maintenance appointment time interval set of two adjacent work orders currently received by a random maintenance personnel as T={T1, T2, ..., T v }, n represents the number of maintenance personnel, corresponding to the maintenance personnel receiving a total of v+1 equipment maintenance work orders, T v It indicates the time interval between the equipment maintenance appointments on the v+1th equipment maintenance work order and the vth equipment maintenance work order after sorting.

8. A data analysis method for a smart community service platform according to claim 7, characterized in that: Step Z2: Calculate the maintenance delay risk coefficient P of a random maintenance worker according to the following formula: i : P i =(F i ) / ∑ n i=1 (F i )+1 / [(∑ v j=1 ((T j )-∑ v j=1 (T j ) / v) 2 ) / v] 1 / 2 ; The maintenance delay risk coefficient set of n maintenance personnel is calculated as {P1, P2, ..., P i , ..., P n }, arrange the maintenance delay risk coefficients of n maintenance personnel in ascending order, and after the sorting is completed, randomly assign the maintenance delay risk coefficients of n maintenance personnel to u data sets, where each maintenance delay risk coefficient in the previous data set is smaller than each maintenance delay risk coefficient in the next data set, and obtain a random assignment result. The mean set of all maintenance delay risk coefficients in each data set is {p1, p2, ... p u }, according to X=[∑ u e=1 ((p e )-∑ u e=1 (p e ) / u) 2 ] / uAnalyze the difference degree X of the maintenance delay risk coefficients between data sets in a random allocation result, compare the difference degrees of the maintenance delay risk coefficients between data sets in different allocation results, screen out the allocation result with the largest difference, and preliminarily screen out the maintenance work order to be coordinated from the screened allocation results: all the remaining maintenance personnel except the maintenance personnel corresponding to the maintenance delay risk coefficient in the first data set.

9. A data analysis method for a smart community service platform according to claim 8, characterized in that: Step Z3: Obtain the historical equipment maintenance work orders generated on the community service platform, and obtain the working time set of the maintenance personnel who received each historical equipment maintenance work order as {t1, t2, ..., t r ..., t k }, where k represents the number of historical equipment maintenance work orders, and the time taken by maintenance personnel to complete the equipment maintenance work on the corresponding historical equipment maintenance work order is {t1 ’ , t2 ’ , ..., t r ’ ..., t k ’ }, according to the formula W r =1 / t r +(t r ’ ) / ∑ k r=1 (t r ’ ) Calculate the difficulty coefficient W of the equipment maintenance work on a random work order among k work orders r , the difficulty coefficient set of the equipment maintenance work on the k work orders is calculated as {W1, W2, ..., W r , ..., W k }, generate training data set {(W1, t1 ’ ), (W2, t2 ’ ), ..., (W k , t k ’ )}, after performing a straight line fitting on the data in the training data set, a maintenance progress prediction model is established: y=β*x+γ, β and γ are fitting coefficients, r represents the rth historical equipment maintenance work order, retrieve the equipment failure data on the equipment maintenance work order currently received by the maintenance personnel who have been initially screened, sort the maintenance work orders from front to back according to the equipment maintenance appointment time on the maintenance work order currently received by the corresponding maintenance personnel, take the equipment failure data on the first equipment maintenance work order currently received by the maintenance personnel who have been initially screened as the specified data, use the DSSM algorithm to calculate the semantic similarity between the specified data and the equipment failure data on the historical equipment maintenance work orders previously generated on the platform, screen out the historical equipment maintenance work orders with the highest semantic similarity between the equipment failure data and the specified data, obtain the time R spent by the maintenance personnel who received the corresponding screened historical equipment maintenance work order to complete the equipment maintenance work on the corresponding work order, obtain the working time of the current maintenance personnel as J, analyze and obtain the difficulty coefficient w of the corresponding maintenance personnel repairing the faulty equipment corresponding to any maintenance work order currently received, w=1 / J+R / ∑ k r=1 (t r ’ ), substitute w into the maintenance progress prediction model: let x=w, and predict that the time required for the corresponding maintenance personnel to repair the faulty equipment corresponding to the first maintenance work order currently received is Q1, Q1=β*w+γ, and the interval between the appointment time on the second maintenance work order currently received by the corresponding maintenance personnel and the appointment time on the first maintenance work order is T1, and compare Q1 and T1: if Q1≤T1, it is predicted that the corresponding maintenance personnel can complete the maintenance work of the received equipment on time, and no work order reminder or coordination processing is made for the corresponding maintenance personnel; if Q1>T1, it is predicted that the corresponding maintenance personnel cannot complete the maintenance work of the received equipment on time.

10. A data analysis method for a smart community service platform according to claim 9, characterized in that: Step Z4: If Q1>T1, select the corresponding maintenance personnel as the final maintenance work order to be coordinated, and use the first maintenance work order currently received by the corresponding maintenance personnel as the designated maintenance work order. Send a prompt message to the terminal where the corresponding maintenance personnel is located to remind the corresponding maintenance personnel that there is a risk of not being able to complete the maintenance work on all the currently received maintenance work orders on time, and suggest the corresponding maintenance personnel to cancel receiving the designated maintenance work order. After the corresponding maintenance personnel cancels receiving the designated maintenance work order, the maintenance work on the designated maintenance work order will be arranged to the remaining maintenance personnel.

Images