A property service risk prediction method, system, device and medium

Abstract

The application relates to a property service risk prediction method, system, device and medium, and relates to the technical field of property management. The method comprises the following steps: obtaining a record uploaded by an enterprise, preprocessing and standardizing the record, and establishing a service file of each enterprise; defining service risks and quality indexes based on industry standards and service specifications; predicting the occurrence of service risks and the substandard conditions of the quality indexes of the service file according to a risk assessment model; generating a risk report according to the service risks and the substandard conditions of the quality of the service file, and visually displaying the risk report; starting an internal improvement process according to the risk report, collecting feedback information in the improvement process, and importing the feedback information into the risk assessment model for continuous training and optimization. The application can utilize industry standards and service specifications to monitor and analyze various property service data in real time, predict potential service risks, and take measures in advance, so that the quality of property services is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of property management, in particular to a property service risk prediction method, system, device and medium. BACKGROUND

[0002] With the acceleration of urbanization, the property service industry has developed rapidly. At present, most property service enterprises still adopt traditional management methods, lacking the ability to predict and prevent potential risks in the service process. Existing risk assessment methods rely mainly on manual experience and qualitative analysis, lacking scientificity and accuracy.

[0003] At present, some property service enterprises try to introduce information means for risk management, but mainly focus on post-recording and processing, lacking pre-risk prediction and real-time risk control during the process.

[0004] The technical defects of the prior art are that the prior art cannot accurately predict property service risks, and the risk response strategy is often lagging, affecting service quality and customer satisfaction. SUMMARY

[0005] The present application aims to provide a property service risk prediction method that can use industry standards and service specifications to monitor and analyze various property service data in real time, predict potential service risks and develop response measures in advance, thereby improving property service quality.

[0006] The present application provides a property service risk prediction method, which adopts the following technical solution:

[0007] A property service risk prediction method, comprising:

[0008] Obtaining the uploaded evidence records of the enterprise, preprocessing and standardizing, and establishing the service archives of the enterprise according to the evidence records;

[0009] Based on industry standards and service specifications, define service risk and quality indicators to identify whether there are service abnormal problems in the service archives;

[0010] According to the risk assessment model, predict the service risk and quality indicators of the service archives that do not meet the standards;

[0011] According to the service risk and quality indicators of the service archives that do not meet the standards, generate a risk report and visually display it;

[0012] According to the risk report, start an internal improvement process, collect feedback information in the improvement process and import it into the risk assessment model for continuous training and optimization.

[0013] By adopting the technical solution, the evidence storage record is preprocessed and standardized, the uploaded data is kept accurate and consistent, data basis is provided for subsequent identification and judgment of whether the service archives exist service abnormal problems, and the accuracy and reliability of the risk prediction model are improved; the service risk and quality indicators are defined, the standardized risk assessment system is established, the property service quality and risk identification can be kept objective and consistent; the risk assessment model can predict potential service risks, provides a warning mechanism for property management, helps the property service enterprises to take measures in advance, avoids the service risk as much as possible, and improves the service quality; the collected feedback information is used for continuous training and optimization of the model, improves the accuracy and effectiveness of risk prediction, and promotes the continuous improvement of service quality.

[0014] In a preferred example, the application can be further configured to: the industry standard and service specification include a plurality of historical service archives of the enterprise, and the step of defining service risk and quality indicators based on the industry standard and service specification to identify whether the service archives exist service abnormal problems includes:

[0015] According to the plurality of historical service archives of the enterprise, service record data of the service abnormal problems is obtained, and the service record data of the service abnormal problems is defined as the service risk and quality indicators;

[0016] The plurality of historical service archives of the enterprise are integrated in chronological order to generate time series data;

[0017] According to the cross matching analysis of the plurality of historical service archives of the enterprise and the time series data, whether the service archives exist service abnormal problems is judged based on the service risk and quality indicators.

[0018] By adopting the technical solution, the plurality of historical service archives of the enterprise are integrated in chronological order, whether the service archives exist service abnormal problems is judged according to the specific data and change trend of the service archives of each time stage of the enterprise, risk warning is made in advance, and basis is provided for taking preventive measures.

[0019] In a preferred example, the application can be further configured to: the industry standard and service specification include a plurality of historical service archives of the enterprise, and the step of defining service risk and quality indicators based on the industry standard and service specification to identify whether the service archives exist service abnormal problems includes:

[0020] According to the plurality of historical service archives of the enterprise, service record data of the service abnormal problems is obtained, and the service record data of the service abnormal problems is defined as the service risk and quality indicators;

[0021] Integrate a plurality of historical service archives of the enterprise in chronological order to generate time series data;

[0022] According to cross matching analysis of a plurality of historical service archives and time series data of the enterprise, it is judged whether the service archives have service abnormal problems based on the service risk and quality indicators.

[0023] By adopting the above technical scheme, the service record data of all service archives of the enterprise is included in the preset service request data set, some of which have similar service record data but different service enterprises. According to the processing of similar service record data, it is judged whether the service record data of the currently uploaded service archive is abnormal, which enhances the sensitivity of judging the current property service abnormality. By continuously monitoring the number of times of abnormality of service record data in a period of time, it is judged whether the currently uploaded service archive has the problem of service unfairness or resource allocation inequality, so that the risks existing in property service can be understood in time.

[0024] In a preferred example, the application can be further configured to: the service record data of the plurality of service archives of different enterprises is judged according to the processing of the service request in the preset service request data set, if the service record data of the service archive has service abnormal problem, the service archive has the problem of service unfairness or resource allocation inequality, the step includes:

[0025] Obtain the average value of each type of service record data in the preset service request data set;

[0026] Compare the service record data in the plurality of service archives of different enterprises with the average value of the corresponding service record data, if the service record data is higher than the average value, the service archive has the problem of service unfairness or resource allocation inequality.

[0027] By adopting the above technical scheme, the average value of each type of service record data in the preset service request data set is taken as the reference standard, that is, the average value of the service record data with similar service behavior is taken as the reference standard. When the uploaded service record data is higher than the corresponding average value, it is judged that the service archive to which the service record data belongs has the problem of unfairness or resource allocation inequality, which promotes the property service enterprise to improve the processing mode of the service in time.

[0028] In a preferred example, the application can be further configured to: the step of identifying the service archive that has the situation of not meeting the service risk and quality indicators includes:

[0029] Using a machine learning model, the service archive is analyzed to predict the trend of service record data of the service archive that has service abnormal problems.

[0030] By adopting the above technical solution, the risk of property services can be judged based on the changing trend of service record data showing service anomalies in the service archives. When an abnormal changing trend appears, it is judged that the current property services are in a risky state, and the property service company needs to improve the current service handling methods.

[0031] In a preferred embodiment, this application can be further configured as follows: the step of using a machine learning model to analyze the service archive and predict the trend of service record data in the service archive that shows service anomalies includes:

[0032] Using statistical methods or anomaly detection algorithms, outliers in the service record data of several service files from different enterprises are identified. If an outlier is found, the service file is considered to have a service anomaly.

[0033] By adopting the above technical solution, service data can be monitored in real time. Statistical methods and anomaly detection algorithms can be used to effectively identify outliers in service record data and regard them as service anomalies in the service file. This allows for the timely discovery of potential service anomalies and improves service response speed.

[0034] In a preferred embodiment, this application can be further configured as follows: the steps of obtaining the evidence storage records uploaded by the enterprise, performing preprocessing and standardization, and organizing and establishing the enterprise's service files based on the evidence storage records include:

[0035] Upload evidence records according to the evidence preservation standards, convert the evidence records into a consistent data format, perform text denoising on the evidence records, and organize and establish the enterprise's service file data.

[0036] By adopting the above technical solutions, the evidence records are converted into a consistent data format, making the data standardized and consistent, providing a reliable foundation for subsequent data analysis and processing; text denoising of the evidence records removes irrelevant or redundant information, improving data quality, making data analysis more accurate, and enhancing data effectiveness.

[0037] Secondly, this application provides a property service risk prediction system, which adopts the following technical solution:

[0038] Data processing module: The data processing module is used to acquire the evidence storage records uploaded by the enterprise, perform preprocessing and standardization, and organize and establish the enterprise's service file based on the evidence storage records;

[0039] Anomaly identification module: the anomaly identification module is used for defining service risk and quality indicators based on industry standards and service specifications to identify whether the service profile has service anomaly problems;

[0040] Anomaly prediction module: the anomaly prediction module is used for predicting the situation that the service profile has service risk and quality indicators that do not meet the standards according to a risk assessment model;

[0041] Report generation module: the report generation module is used for generating a risk report and visualizing the report according to the situation that the service profile has service risk and quality indicators that do not meet the standards;

[0042] Model training module: the model training module is used for starting an internal improvement process according to the risk report, collecting feedback information in the improvement process and importing the feedback information into the risk assessment model for continuous training and optimization.

[0043] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0044] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the property service risk prediction method.

[0045] In a fourth aspect, the present application provides a computer storage medium, which adopts the following technical solution:

[0046] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the property service risk prediction method.

[0047] In summary, the present application has the following beneficial technical effects:

[0048] The present application preprocesses and standardizes the evidence records to ensure the accuracy and consistency of the uploaded data, improve the accuracy and reliability of the risk prediction model, monitor and analyze various property service data through the uploaded evidence records, define service risk and quality indicators through industry standards and service specifications, establish a unified risk assessment system, ensure the objectivity and consistency of property service quality and risk identification, and predict potential service risks through the risk assessment model to provide an early warning mechanism for property management, so that property service enterprises can take actions in advance to avoid property service risks as much as possible, thereby improving the overall service quality, collecting feedback information for continuous training and optimization of the risk assessment model, formulating countermeasures in advance, improving the accuracy and effectiveness of risk prediction of property service enterprises, and promoting continuous improvement of service quality. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 is a flowchart of a property service risk prediction method structure in one embodiment of the present application.

[0050] Figure 2 is a flowchart of a sub-step of step S2 in one embodiment of the present application.

[0051] Figure 3 is a flowchart of a sub-step of step S22 in one embodiment of the present application.

[0052] Figure 4 is a flowchart of a sub-step of step S220 in one embodiment of the present application.

[0053] Figure 5 is a flowchart of a sub-step of step S3 in one embodiment of the present application.

[0054] Figure 6 is a flowchart of a sub-step of step S30 in one embodiment of the present application.

[0055] Figure 7 is a flowchart of a sub-step of step S1 in one embodiment of the present application.

[0056] Figure 8 is a structural diagram of a property service risk prediction system in one embodiment of the present application.

[0057] Figure 9 is a principle block diagram of an electronic device in one embodiment of the present application.

[0058] Reference signs: 1, data processing module; 2, anomaly identification module; 3, anomaly prediction module; 4, report generation module; 5, model training module. DETAILED DESCRIPTION

[0059] The following will be described in detail below in combination with the accompanying drawings. Figures 1-9 The present application will be further described in detail.

[0060] Reference Figure 1 A property service risk prediction method, specifically comprising:

[0061] S1, obtaining the uploaded evidence record of the enterprise, preprocessing and standardizing, and establishing the service archives of the enterprise according to the evidence record.

[0062] Specifically, the evidence record includes but is not limited to service request record, service completion report, satisfaction survey, etc. The uploaded evidence record is automatically parsed and standardized data format for subsequent processing.

[0063] S2, define service risk and quality indicators based on industry standards and service specifications to identify whether there is a service exception problem in the service file.

[0064] Specifically, it is clear which service record data is considered a service exception problem, such as response time timeout, multiple complaints about the same problem without solution, service evaluation below a certain threshold, etc.

[0065] S3, according to the risk assessment model, predict the situation that the service risk and quality indicators of the service file do not meet the standards.

[0066] S4, according to the service risk and quality of the service file, generate a risk report and visualize it.

[0067] Specifically, it can automatically generate a detailed report listing the identified service risks and specific cases of not meeting the standards, including problem summary, impact analysis and suggested improvement measures, and use charts and dashboards to visually display service risk distribution, trend changes, etc. to quickly understand the current situation of each service enterprise.

[0068] S5, according to the risk report, start the internal improvement process, collect feedback information in the improvement process and import it into the risk assessment model for continuous training and optimization.

[0069] Specifically, the analysis results of the risk report are timely notified to the relevant service personnel and management personnel, and the internal improvement process is started to establish a mechanism to track the progress of problem solving, ensure that the rectification measures are effectively implemented, and collect feedback information for continuous training and optimization of the model.

[0070] In this embodiment, the evidence record is preprocessed and standardized to make the uploaded evidence record data accurate and consistent. The service file of the enterprise is constructed, and when the property service enterprise records the service, through the risk assessment model, not only can the potential risks in the service process be predicted to provide an early warning mechanism for property management, take action in a timely manner before the risk occurs, prevent the occurrence of service risks, and thus improve the service quality, but also through the collection of feedback information, continuous training and optimization of the risk assessment model, further improve the accuracy and efficiency of risk prediction, and promote the continuous improvement of service quality.

[0071] Reference Figure 2 Further, in one embodiment, the industry standards and service specifications include a number of historical service files of each enterprise, and step S2 is refined into the following substeps:

[0072] S20, according to a number of historical service files of the enterprise, obtain service record data with service exception problems, and define service record data with service exception problems as service risk and quality indicators.

[0073] Specifically, taking a number of historical service archives of enterprises as industry standards and service specifications can not only improve different service contents of enterprises, but also more accurately predict service risks.

[0074] S21, integrating a number of historical service archives of enterprises in chronological order to generate time series data.

[0075] S22, cross-matching analysis according to a number of historical service archives of enterprises and time series data, judging whether there is a service abnormal problem in the service archive based on service risk and quality indicators.

[0076] In this embodiment, the historical service archives of enterprises are integrated in chronological order, which includes arranging each service record data of the historical service archives of service enterprises in chronological order, identifying possible abnormal problems in property services by analyzing each service record data of the service archives and its change trend, which helps to issue risk early warning in advance and provides important reference for formulating risk prevention measures.

[0077] In addition, referring to Figure 3 , further, in one embodiment, step S22 is refined into the following sub-steps:

[0078] S220, judging whether there is service record data of service abnormal problem in the service record data of a number of service archives of different enterprises according to the service request processing situation in the preset service request data set, if there is service record data of service abnormal problem in the service archive, the service archive has the problem of service unfairness or uneven resource allocation.

[0079] Specifically, in the preset service request data set, a number of collections of similar service record data in the historical service archives of enterprises are arranged.

[0080] In this embodiment, each service record data has a code, and the composition of the code is the enterprise type of the service object and the service content. The enterprise type of the service object can be numbered according to enterprise size + ownership structure + business scope.

[0081] When setting the number of service content, the service enterprise can number according to service frequency + service purpose. The service purpose is divided into safety management, environmental management and facility maintenance, and the service frequency is numbered according to the arrangement of each month.

[0082] Therefore, an encoding contains the enterprise type of the service object and the service content, which will constitute similar codes and be integrated into a collection of similar service record data. For example, service records with the same enterprise size, ownership structure and service purpose, but different business scope and service frequency are integrated into a collection of similar service record data.

[0083] The service processing of similar service record data is also basically similar, and the service processing scoring mechanism is unified, so that whether there is a service injustice or resource allocation inequality problem in the service archive is judged according to the preset service request data set, and the sensitivity of service risk prediction is improved.

[0084] S221, according to the time series data and the number of service record data in the service archive of the same enterprise that appears service abnormal problem, whether there is a service standard decline or a continuous unsolved problem is judged.

[0085] Specifically, by analyzing the frequency of service abnormal problems in the time series data, whether the service standard declines can be effectively monitored, and continuous problems can be found and solved in time, so that the stability of service quality and standard is maintained.

[0086] In the embodiment, by analyzing the processing of similar service records, whether the service record data in the uploaded service archive appears abnormal can be judged, the sensitivity of property service abnormality judgment can be improved, and the frequency of service record data appearing abnormal in service time is continuously monitored, which provides a basis for continuously optimizing service process, adjusting resource allocation, improving service efficiency and quality for property service enterprises, and helps to identify service injustice or resource allocation inequality problems in time and find service risks in time.

[0087] In addition, with reference to Figure 4 , further, in one embodiment, step S220 is refined into the following sub-steps:

[0088] S2200, obtaining the average value of each type of service record data in the preset service request data set.

[0089] Specifically, a scoring system is designed to assign scores to the results of service processing feedback of each type of service record data in the preset service request data set to provide data support for subsequent risk prediction work.

[0090] S2201, comparing the service record data in the service archives of different enterprises with the average value of the corresponding service record data, if the service record data is higher than the average value, the service archive has a service injustice or resource allocation inequality problem.

[0091] In the embodiment, the average value of each type of service record data in the preset service request data set is used as a reference. Specifically, the service content feedback by the enterprise is scored to obtain the average value of the score. Since the enterprise feedbacks the service by scoring the service content directly, in the embodiment, when integrating similar service record data, the service record data with the same service content number is preferentially integrated.

[0092] If the score system of the service record data in the service file exceeds the average value, the service file may have problems of service unfairness or resource allocation unevenness, and timely discovery of service abnormal problems can improve the response speed and efficiency of the property service enterprise to risks.

[0093] In addition, with reference to Figure 5 , further, in one of the embodiments, step S3 is refined into the following sub-steps:

[0094] S30, using a machine learning model, analyzing the service file to predict the trend of service record data in the service file that appears service abnormal problems.

[0095] Specifically, the machine learning model can be selected as a decision tree, a random forest or a neural network.

[0096] In the embodiment, by analyzing the change trend of the service record data in the service file, the risk of the property service can be predicted, if the service record data shows an abnormal trend, it is judged that the current property service is in a risk state, the property service enterprise needs to improve the processing method of the current service, and after the processing method of the current service is improved, the machine learning model learns and trains the current processing method to obtain a higher quality service processing method, so that the property service enterprise can adopt a more high-quality service processing method when similar service risks occur again.

[0097] In addition, with reference to Figure 6 , further, in one of the embodiments, step S30 is refined into the following sub-steps:

[0098] S300, using statistical methods or anomaly detection algorithms, identifying outliers in the service record data in several service files of different enterprises, if outliers appear, it is considered that the service file has service abnormal problems.

[0099] In the embodiment, outliers represent abnormal problems in the service record data, which may be caused by errors, abnormal operations or special circumstances, in the service record, outliers may indicate potential risks or problems, such as decline in service quality or service failure, real-time monitoring of service data can help to issue early warning and improve service response speed by identifying these outliers in time.

[0100] In addition, with reference to Figure 7 , further, in one of the embodiments, step S1 is refined into the following sub-steps:

[0101] S10, uploading the evidence record according to the evidence storage standard, converting the evidence record into a consistent data format, and denoising the evidence record to establish the service file data of the enterprise.

[0102] In the embodiment, the evidence record is converted into a unified standardized data format, ensuring consistency of all evidence record data. By implementing text denoising on the evidence record, irrelevant or redundant information is removed, improving the accuracy of data analysis, establishing service archive data of the enterprise, and realizing systematic management of enterprise service information, facilitating real-time monitoring and analysis of service data by the property service enterprise.

[0103] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0104] The embodiment of the present application also provides a property service risk prediction system, which corresponds one-to-one to the property service risk prediction method in the embodiment.

[0105] Reference Figure 8 A property service risk prediction system includes a data processing module 1, an anomaly identification module 2, an anomaly prediction module 3, a report generation module 4, and a model training module 5. The detailed description of each functional module is as follows:

[0106] Data processing module 1: The data processing module 1 is used to obtain the evidence record uploaded by the enterprise, to pre-process and standardize, and to establish the service archive of the enterprise according to the evidence record.

[0107] Anomaly identification module 2: The anomaly identification module 2 is used to define service risk and quality indicators based on industry standards and service specifications to identify whether the service archive has service anomaly problems.

[0108] Anomaly prediction module 3: The anomaly prediction module 3 is used to predict the occurrence of service risk and substandard quality indicators of the service archive according to the risk assessment model.

[0109] Report generation module 4: The report generation module 4 is used to generate a risk report according to the service risk and substandard quality of the service archive, and to perform visual display.

[0110] Model training module 5: The model training module 5 is used to start an internal improvement process according to the risk report, collect feedback information in the improvement process and import it into the risk assessment model for continuous training and optimization.

[0111] The data processing module 1 is responsible for obtaining the record storage uploaded by the enterprise, pre-processing and standardizing, and establishing a dedicated service file for the enterprise according to the records; the abnormality identification module 2 defines service risk and quality indicators based on industry standards and service specifications, checks whether there is a service abnormality problem in the service file, so as to realize the abnormal detection of property services; the abnormality prediction module 3 uses a preset risk assessment model to timely predict the service risks and quality indicators that may occur in the service file; the report generation module 4 generates a risk report according to the prediction result, and displays it in a visual manner, so that the management personnel can more accurately analyze the risk problems existing in the property services; the model training module 5 starts the internal improvement process according to the risk report, collects feedback information in the improvement process, imports it into the risk assessment model, and continuously trains and optimizes it, so as to improve the prediction accuracy of the model and the improvement effect of the service. Through the joint action of each module, it is helpful for real-time monitoring of service data, prediction and response of risks, and continuous improvement of property service quality.

[0112] The specific limitations of the property service risk prediction system can be referred to the limitations of the property service risk prediction method in the context, which will not be repeated here. Each module in the above property service risk prediction system can be realized by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to the above modules. In one embodiment, an electronic device is provided, which is a user terminal. Referring to Figure 9 , the electronic device includes a processor, a memory, a network interface and a database connected by a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a detection data table. The network interface of the electronic device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a property service risk prediction method.

[0113] In one embodiment, an electronic device is provided, including a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the following steps:

[0114] S1, obtaining the record storage uploaded by the enterprise, pre-processing and standardizing, and establishing the service file of the enterprise according to the record storage.

[0115] S2, define service risk and quality indicators based on industry standards and service specifications to identify whether the service profile has service abnormal problems.

[0116] S3, predict the situation of service risk and quality indicators not meeting the standards of the service profile according to the risk assessment model.

[0117] S4, generate a risk report according to the service risk and quality not meeting the standards of the service profile, and visually display it.

[0118] S5, start the internal improvement process according to the risk report, collect feedback information in the improvement process and import it into the risk assessment model for continuous training and optimization.

[0119] In one embodiment, the industry standards and service specifications include a number of historical service profiles of the enterprise, and the step S2 includes the following sub-steps:

[0120] S20, obtain service record data with service abnormal problems from a number of historical service profiles of the enterprise, and define the service record data with service abnormal problems as service risk and quality indicators.

[0121] S21, integrate a number of historical service profiles of the enterprise in chronological order to generate time series data.

[0122] S22, cross-match analysis is performed based on a number of historical service profiles of the enterprise and time series data, and whether the service profile has service abnormal problems is determined based on service risk and quality indicators.

[0123] In one embodiment, the step S22 includes the following sub-steps:

[0124] S220, determine whether service record data with service abnormal problems exists in service record data of a number of service profiles of different enterprises based on service request processing in the preset service request data set. If service record data with service abnormal problems exists in the service profile, the service profile has service unfairness or resource allocation problems.

[0125] S221, determine whether there is a service standard decline or a persistent unresolved problem based on the time series data and the number of service record data with service abnormal problems in the service profile of the same enterprise.

[0126] In one embodiment, the step S220 includes the following sub-steps:

[0127] S2200, obtain the average value of each type of service record data in the preset service request data set.

[0128] S2201, compare the service record data in the service archives of different enterprises with the average value of the corresponding service record data, if the service record data is higher than the average value, the service archives have problems of service unfairness or resource allocation unevenness.

[0129] In one of the embodiments, the step S3 is refined into the following sub-steps:

[0130] S30, using a machine learning model, analyzing the service archives to predict the trend of service record data of the service archives with service abnormal problems.

[0131] In one of the embodiments, the step S30 is refined into the following sub-steps:

[0132] S300, using a statistical method or an anomaly detection algorithm, identifying outliers in the service record data in the service archives of different enterprises, if outliers exist, regarding the service archives as having service abnormal problems.

[0133] In one of the embodiments, the step S1 is refined into the following sub-steps:

[0134] S10, uploading the evidence storage records according to the evidence storage standards, converting the evidence storage records into consistent data formats, and performing text denoising on the evidence storage records to organize and establish the service archive data of the enterprise.

[0135] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In the embodiments provided by the present application, any reference to the memory, storage, database or other medium can include non-volatile and / or volatile memory. The non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. The volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM) and the like.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above described functions.

Claims

1. A method for predicting property service risks, characterized in that, include: Obtain the evidence storage records uploaded by the enterprise, perform preprocessing and standardization, and organize and establish the enterprise's service file based on the evidence storage records; Based on industry standards and service specifications, service risk and quality indicators are defined to identify whether there are service anomalies in the service files. These industry standards and service specifications include several historical service files of the enterprise, specifically including A1: A1: Based on several historical service files of the enterprise, obtain service record data showing service anomalies, and define the service record data showing service anomalies as service risk and quality indicators; integrate several historical service files of the enterprise in chronological order to generate time series data; perform cross-matching analysis on the enterprise's several historical service files and time series data, and based on the service risk and quality indicators, determine whether there are service anomalies in the service files, specifically including A2: A2: Based on the centralized processing of service requests using a preset service request dataset, determine whether there are service record data with service anomalies in several service files from different enterprises. If a service file has service record data with service anomalies, then the service file has a problem of service unfairness or uneven resource allocation, specifically including A3: A3: Obtain the average value of various service record data in the preset service request dataset; compare the service record data in several service files of different enterprises with the average value of the corresponding service record data. If the service record data is higher than the average value, then the service file has problems of service unfairness or uneven resource allocation. Based on the risk assessment model, the occurrence of service risks and substandard quality indicators in the service files is predicted. Based on the service risks and quality deficiencies identified in the service records, a risk report is generated and visualized. An internal improvement process is initiated based on the risk report, and feedback information from the improvement process is collected and imported into the risk assessment model for continuous training and optimization.

2. The method according to claim 1, characterized in that, The step of performing cross-matching analysis based on several historical service records and time-series data of the enterprise, and determining whether there are service anomalies in the service records based on the service risk and quality indicators, includes: Based on the time series data and the number of service records showing service anomalies in the service archives of the same enterprise, it can be determined whether there are any issues of declining service standards or persistent unresolved problems.

3. The method according to claim 1, characterized in that, The step of identifying situations where service risks and quality indicators fail to meet standards in the service file based on the risk assessment model includes: Using machine learning models, the service archives are analyzed to predict trends in service record data where service anomalies occur.

4. The method according to claim 3, characterized in that, The step of using a machine learning model to analyze the service archive and predict the trend of service record data showing service anomalies includes: Using statistical methods or anomaly detection algorithms, outliers in the service record data of several service files from different enterprises are identified. If an outlier is found, the service file is considered to have a service anomaly.

5. The method according to claim 1, characterized in that, The steps of obtaining the evidence storage records uploaded by the enterprise, preprocessing and standardizing them, and organizing and establishing the enterprise's service file based on the evidence storage records include: Upload evidence records according to the evidence preservation standards, convert the evidence records into a consistent data format, perform text denoising on the evidence records, and organize and establish the enterprise's service file data.

6. A property service risk prediction system, characterized in that, include: Data processing module (1): The data processing module (1) is used to obtain the evidence storage records uploaded by the enterprise, perform preprocessing and standardization, and organize and establish the enterprise's service files based on the evidence storage records; Anomaly Identification Module (2): The anomaly identification module (2) is used to define service risk and quality indicators based on industry standards and service specifications to identify whether there are service anomaly issues in the service file. The industry standards and service specifications include several historical service files of the enterprise, specifically including A1: A1: Based on several historical service files of the enterprise, obtain service record data showing service anomalies, and define the service record data showing service anomalies as service risk and quality indicators; integrate several historical service files of the enterprise in chronological order to generate time series data; perform cross-matching analysis on the enterprise's several historical service files and time series data, and based on the service risk and quality indicators, determine whether there are service anomalies in the service files, specifically including A2: A2: Based on the centralized processing of service requests using a preset service request dataset, determine whether there are service record data with service anomalies in several service files from different enterprises. If a service file has service record data with service anomalies, then the service file has a problem of service unfairness or uneven resource allocation, specifically including A3: A3: Obtain the average value of various service record data in the preset service request dataset; compare the service record data in several service files of different enterprises with the average value of the corresponding service record data. If the service record data is higher than the average value, then the service file has problems of service unfairness or uneven resource allocation. Anomaly prediction module (3): The anomaly prediction module (3) is used to predict, based on the risk assessment model, the occurrence of service risks and quality indicators that fail to meet the standards in the service file; Report generation module (4): The report generation module (4) is used to generate a risk report based on the service risks and quality deficiencies of the service file, and to display the report visually. Model training module (5): The model training module (5) is used to initiate an internal improvement process based on the risk report, collect feedback information in the improvement process and import it into the risk assessment model for continuous training and optimization.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as any one of the property service risk prediction methods as claimed in claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as any one of the property service risk prediction methods as claimed in claims 1 to 5.

Images