Pension service supervision data processing method and system based on multi-source data and machine learning

By using the SFIC model and real-time monitoring feature compliance index method in the processing of elderly care service supervision data, the problem of low real-time quality assessment in the existing technology is solved, and the real-time and accuracy of elderly care service supervision data processing is improved.

CN119026964AInactive Publication Date: 2024-11-26GUANGZHOU TIANCHEN INFORMATION TECH CO LTD
View PDF 0 Cites 6 Cited by

Patent Information

Application Number
CN202411515716.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-29
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, there is a problem of low real-time quality assessment in the processing of elderly care service supervision data, especially in the case of complex or unstable network environment, data transmission delay affects the timeliness of data evaluation results.

Method used

By obtaining data from the elderly care service data source and integrating it, inputting data into the SFIC model with preset time intervals to obtain service efficiency evaluation values, and comparing it with the reference evaluation threshold range to determine abnormal behavior patterns, real-time monitoring of the characteristics conformity index To determine whether intervention measures are implemented, the real-time and accuracy of data processing are improved.

Benefits of technology

It has achieved real-time improvement in the quality assessment of elderly care services during the processing of elderly care service supervision data, ensured the accurate judgment of abnormal behavior patterns and the effectiveness of intervention measures, and improved the accuracy and efficiency of regulatory data processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026964A_ABST
    Figure CN119026964A_ABST
Patent Text Reader

Abstract

The invention discloses a pension service supervision data processing method and system based on multi-source data and machine learning, and relates to the technical field of pension service supervision data processing. The pension service supervision data processing method based on multi-source data and machine learning comprises the steps of obtaining a service efficiency evaluation value; judging an abnormal behavior mode; and obtaining a feature coincidence index. According to the method, the old-age service data are acquired and integrated, then the integrated old-age service data are input into the SFIC model to obtain the service efficiency evaluation value, and the service efficiency evaluation value is compared with the reference evaluation threshold range to judge whether to switch the abnormal behavior mode or not. And finally, obtaining a feature coincidence index and comparing the feature coincidence index with a preset threshold range to judge whether to execute an intervention measure, so as to improve the real-time performance of the pension service quality evaluation in the pension service supervision data processing process. The problem that in the prior art, in the old-age service supervision data processing process, old-age service quality evaluation is low in real-time performance is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of elderly care service supervision data processing, and in particular to an elderly care service supervision data processing method and system based on multi-source data and machine learning. Background Art

[0002] With the increasingly serious problem of population aging and the continuous improvement of the quality of elderly care services in society, the supervision of elderly care services has become particularly important. In the process of elderly care services, a large amount of multi-source heterogeneous data will be generated, including basic information, health status, living habits, service records, etc. of the elderly. The explosive growth of these data volumes provides rich data resources for the supervision of elderly care services, but it also brings challenges to data processing and analysis. For example, data security and privacy protection issues, technology popularization and regulatory standardization issues, cross-domain data fusion and sharing issues, etc. Therefore, the data processing method and system for elderly care service supervision based on multi-source data and machine learning is an important means to cope with the challenges of an aging society and improve the quality and efficiency of elderly care services.

[0003] Existing technology builds a smart elderly care data cloud storage service platform, and applies machine learning algorithms to process and analyze elderly care service data to extract related information in the elderly care service data. By inputting the related information into the trained learning algorithm model, the prediction and query of elderly care service data can be realized.

[0004] For example, the service data processing method, system and storage medium based on home-based elderly care announced by the invention patent with announcement number: CN111861636B include: receiving age data uploaded by a first terminal; after determining that the age data belongs to a preset range of age data, receiving a product request uploaded by the first terminal; matching multiple product information to be selected according to the product request; obtaining target product information uploaded by the first terminal, the target product information is one of multiple product information to be selected; generating order information according to the target product information; and judging the completion status of the order information according to the video data.

[0005] For example, the blockchain-based home-based elderly care data processing method and device disclosed in the patent application with publication number: CN115330570A includes: receiving elderly customer information in a specified area; uploading elderly customer information that meets preset conditions to the blockchain network for storage; obtaining life data corresponding to the elderly customer information that meets preset conditions, and uploading the obtained life data to the blockchain network for storage, so that the bank server performs life payment settlement based on the life data.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: In the existing technology, the data transmission process may be affected by network delays and stability. In particular, when the network environment is complex or unstable, the real-time transmission of data may be affected, resulting in delayed data evaluation results. There is a problem of low real-time performance of elderly care service quality evaluation in the process of elderly care service supervision data processing. Summary of the invention

[0007] The embodiments of the present application solve the problem of low real-time evaluation of elderly care service quality in the process of elderly care service supervision data processing in the prior art by providing a method and system for processing elderly care service supervision data based on multi-source data and machine learning, and achieve improved real-time evaluation of elderly care service quality in the process of elderly care service supervision data processing.

[0008] The embodiment of the present application provides a method for processing elderly care service supervision data based on multi-source data and machine learning, comprising the following steps: step one, obtaining elderly care service data from an elderly care service data source and performing data integration, and at the same time, inputting the integrated elderly care service data into the SFIC model in combination with a preset time interval to obtain a service efficiency evaluation value, wherein the elderly care service data includes behavioral data, video surveillance data, and physical examination frequency data, and the service efficiency evaluation value is used to evaluate the efficiency level of elderly care services within a preset time interval; step two, comparing the obtained service efficiency evaluation value with a reference evaluation threshold range to determine whether to switch to an abnormal behavior mode, and if the abnormal behavior mode is switched, performing abnormal behavior mode processing and feeding back the processing result to medical staff for processing before performing step three; step three, real-time monitoring of the comparison process to obtain a feature compliance index, and at the same time, comparing the obtained feature compliance index with a preset threshold range to determine whether to perform intervention measures, and the feature compliance index is used to reflect the matching between the elderly care service data and the reference feature data in a preset elderly care service supervision feature library.

[0009] Furthermore, the service efficiency evaluation value is obtained by the following method: A1, collecting service request records of service objects from a preset database to obtain service response time, wherein the service response time represents the time difference from the issuance of a service request to the start of response of the elderly care service network within a preset time interval, and the service request record includes the service object type and the service object request time; A2, judging whether the obtained service response time is less than the reference service response time, if so, obtaining the service efficiency evaluation value according to the service coverage rate and a preset service coverage rate weight factor, otherwise executing A3, wherein the service coverage rate is represented by the result of a ratio operation between the actual number of service objects in the preset service area and the reference number of service objects; A3, obtaining the service efficiency evaluation value according to the obtained service response time and the service coverage rate in combination with the preset service response time weight factor and the service coverage rate weight factor.

[0010] Furthermore, the specific limiting expression of the service efficiency evaluation value is: ; Where y is the number of the preset service area, , Y is the total number of preset service areas, t is the number of preset time intervals, , T is the total number of preset time intervals, e is a natural constant, represents the service efficiency evaluation value of the elderly care service data in the y-th preset service area, Represents the service response time weight factor, represents the service response time of the yth preset service area in the tth preset time interval, Indicates the reference service response time. represents the service coverage weight factor, It represents the service coverage of the y-th preset service area in the t-th preset time interval.

[0011] Furthermore, the specific steps of comparing the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch the abnormal behavior mode are as follows: E1, if the obtained service efficiency evaluation value is within the reference evaluation threshold range, it indicates that the behavior data of the service object is normal; if the obtained service efficiency evaluation value is not within the reference evaluation threshold range, the abnormal behavior mode is switched and E2 is executed; E2, an abnormal behavior interference value is obtained according to the degree to which the service efficiency evaluation value exceeds the reference evaluation threshold range, and the abnormal behavior interference value is used to reflect the degree of abnormality of the behavior data in the elderly care service data within a preset time interval.

[0012] Furthermore, the process of obtaining the abnormal behavior interference value is as follows: according to the comparison between the service efficiency evaluation value and the reference evaluation threshold range, the abnormal service efficiency evaluation value is obtained and counted, so as to obtain the number of abnormal service efficiency evaluation values ​​in the preset service area within the preset time interval, and at the same time, the number of abnormal service efficiency evaluation values ​​is compared with the total number of service efficiency evaluation values ​​to obtain the abnormal data volume index, and the number of abnormal service efficiency evaluation values ​​is the number of service efficiency evaluation values ​​exceeding the reference evaluation threshold range; real-time monitoring of the response process of the elderly care service network in the preset service area to the abnormal service efficiency evaluation value is carried out to obtain the data transmission delay rate, and the data transmission delay rate is the ratio of the difference between the network response time and the reference network response time to the reference network response time, and the network response time is the value of the elderly care service. the time interval between the moment when the service network sends the abnormal service efficiency evaluation value and the moment when the abnormal service efficiency evaluation value is received; judging whether the acquired network response time is less than the reference network response time, if the acquired network response time is less than the reference network response time, adding the abnormal time index and the acquired abnormal data volume index to obtain the abnormal behavior interference value, otherwise adding the abnormal time index, the acquired data transmission delay rate and the abnormal data volume index to obtain the abnormal behavior interference value, the abnormal time index being the ratio of the abnormal duration to the total duration of the preset time interval, the total duration of the preset time interval being the product of the preset time interval duration and the total number of preset time intervals, and the abnormal duration being the duration period during which the abnormal service efficiency evaluation value exceeds the reference evaluation threshold range.

[0013] Furthermore, the specific process of comparing the obtained feature compliance index with the preset threshold range to determine whether to implement intervention measures is as follows: determine whether the obtained feature compliance index is within the preset threshold range: if the feature compliance index is within the preset threshold range, continue to monitor the changes in the elderly care service data within the preset time interval; if the feature compliance index is not within the preset threshold range, implement intervention measures and evaluate the effectiveness of the intervention measures.

[0014] The embodiment of the present application provides a system for applying the elderly care service supervision data processing method based on multi-source data and machine learning, including: a service efficiency evaluation value acquisition module, an abnormal behavior pattern judgment module and a feature compliance index acquisition module; wherein the service efficiency evaluation value acquisition module is used to acquire elderly care service data from an elderly care service data source and perform data integration, and at the same time, input the elderly care service data after data integration into the SFIC model in combination with a preset time interval to obtain a service efficiency evaluation value, the elderly care service data includes behavior data, video surveillance data and physical examination frequency data, and the service efficiency evaluation value is used to evaluate the efficiency level of elderly care services within a preset time interval; the abnormal behavior pattern judgment module is used to compare the acquired service efficiency evaluation value with a reference evaluation threshold range to determine whether to switch the abnormal behavior mode, and if the abnormal behavior mode is switched, the abnormal behavior mode processing is performed and the processing result is fed back to the medical staff for processing and then the function of executing the feature compliance index acquisition module is executed; the feature compliance index acquisition module is used to monitor the comparison process in real time to obtain a feature compliance index, and at the same time, the acquired feature compliance index is compared with a preset threshold range to determine whether to perform intervention measures, and the feature compliance index is used to reflect the matching between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library.

[0015] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The service efficiency evaluation value is obtained by inputting the integrated elderly care service data into the SFIC model, and compared with the reference evaluation threshold range to determine whether to switch to the abnormal behavior mode. The feature compliance index is obtained through real-time monitoring of the comparison process and compared with the preset threshold range to determine whether to implement intervention measures, thereby achieving a more accurate judgment of abnormal behavior patterns, and then achieving the improvement of the real-time performance of elderly care service quality evaluation in the process of elderly care service supervision data processing, effectively solving the problem of low real-time performance of elderly care service quality evaluation in the process of elderly care service supervision data processing in the prior art.

[0016] 2. By judging whether the abnormal behavior interference value is equal to 0, if so, the elderly care service data and the reference feature data in the preset elderly care service supervision feature library are normalized to obtain the real-time feature value and the reference feature value, otherwise the corresponding feature conformity index is equal to 0, and the real-time feature value and the reference feature value are respectively calculated by distance measurement and addition and summation to obtain the feature conformity index, thereby achieving a more accurate judgment of the abnormal behavior interference value, and then achieving the improvement of the accuracy and reliability of the feature conformity index.

[0017] 3. By judging whether the characteristic compliance index after the intervention measures is within the preset threshold range, if so, the elderly care service process, elderly care supervision area and preset service area are optimized; otherwise, early warning feedback is given and the elderly care service process, elderly care supervision area and preset service area are adjusted and optimized, thereby achieving a more accurate evaluation of the efficiency of the intervention measures, and then achieving the improvement of the accuracy and real-time nature of elderly care service supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application; Figure 2 A two-dimensional analysis diagram of the service response time coefficient provided in an embodiment of the present application; Figure 3 A two-dimensional analysis diagram of the service coverage coefficient provided in the embodiment of the present application; Figure 4 A schematic diagram of the structure of a system for applying a method for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application; Figure 5 A flowchart of the elderly care service supervision process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiments of the present application solve the problem of low real-time performance of elderly care service quality assessment in the process of elderly care service supervision data processing in the prior art by providing a method and system for processing elderly care service supervision data based on multi-source data and machine learning. The method obtains elderly care service data from the elderly care service data source and integrates the data. At the same time, the integrated elderly care service data is input into the SFIC model at a preset time interval to obtain a service efficiency assessment value. The obtained service efficiency assessment value is then compared with a reference assessment threshold range to determine whether to switch the abnormal behavior mode. If the abnormal behavior mode is switched, the abnormal behavior mode processing is performed and the processing result is fed back to the medical staff for processing. Finally, the comparison process is monitored in real time to obtain a feature compliance index. At the same time, the obtained feature compliance index is compared with the preset threshold range to determine whether to perform intervention measures. This improves the real-time performance of elderly care service quality assessment in the process of elderly care service supervision data processing.

[0020] The technical solution in the embodiment of the present application is to solve the problem of low real-time performance of elderly care service quality assessment in the above-mentioned elderly care service supervision data processing process. The overall idea is as follows: By inputting the integrated elderly care service data into the SFIC model to obtain the service efficiency evaluation value and comparing it with the reference evaluation threshold range to determine whether to switch to the abnormal behavior mode, the real-time monitoring and comparison process is used to obtain the feature compliance index and compare it with the preset threshold range to determine whether to implement intervention measures, thereby achieving the effect of improving the real-time performance of elderly care service quality assessment in the process of elderly care service supervision data processing.

[0021] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0022] like Figure 1 As shown, it is a flow chart of a method for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application. The method for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application includes the following steps: Step 1, obtaining elderly care service data from an elderly care service data source and integrating the data, and inputting the elderly care service data after data integration into the SFIC model in combination with a preset time interval to obtain a service efficiency evaluation value, the elderly care service data includes behavioral data, video surveillance data and physical examination frequency data, and the service efficiency evaluation value is used to evaluate the efficiency level of elderly care services within a preset time interval; Step 2, comparing the obtained service efficiency evaluation value with a reference evaluation threshold range to determine whether to switch to an abnormal behavior mode, if the abnormal behavior mode is switched, performing abnormal behavior mode processing and feeding back the processing result to the medical staff for processing and then performing step 3, the abnormal behavior mode processing includes generating an abnormal report and sending an emergency notification; Step 3, real-time monitoring of the comparison process to obtain a feature compliance index, and comparing the obtained feature compliance index with a preset threshold range to determine whether to perform intervention measures, the feature compliance index is used to reflect the matching between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library.

[0023] Among them, behavioral data include the number of steps, sleep duration and activity area of ​​the service object; video surveillance data is used to record real-time image information within the preset service area within the preset time interval (within the preset time interval, automatically record and save the video images within the preset service area for real-time monitoring and subsequent playback); physical examination frequency data is used to record the physical examination frequency of the service object within the preset time interval; data integration means data cleaning (for removing duplicate data and filling missing data) and data conversion (for unifying the format and unit of elderly care service data from different elderly care service data sources) of elderly care service data from different elderly care service data sources.

[0024] Specifically, the SFIC (Starting Conditions, Facilitative Leadership, Institutional Design, Collaborative Process) model is a collaborative governance framework model in a machine learning algorithm commonly used in the elderly care service supervision process. In this embodiment, the input of the collaborative quality framework model is the elderly care service data after data integration, and the output is the service efficiency evaluation value; when the abnormal behavior mode is switched, the system generates an abnormal report by the time and cause of the abnormal behavior, and sends it to medical staff and system managers in the form of emails and text messages, thereby improving the real-time performance of elderly care service quality evaluation in the process of elderly care service supervision data processing.

[0025] In a modern smart elderly care community, in order to improve the quality of life of the elderly and ensure their safety and health, the community uses multi-source data to process elderly care service data. These data sources include but are not limited to behavioral data, video surveillance data, and physical examination frequency data. By collecting, processing, and analyzing these data in real time, the community can achieve comprehensive monitoring of the living conditions of the elderly.

[0026] Among them, behavioral data: every elderly person wears a smart bracelet or wearable device, which can automatically record and upload the elderly’s activity steps, sleep duration and activity areas to the community’s elderly care service data center. For example, an elderly person walked 5,000 steps in a day, slept for 7 hours, and his main activity areas were the living room and bedroom in his home.

[0027] Video surveillance data: High-definition cameras are installed in key areas of the community (such as public corridors, entrances and exits to residential areas, and fitness areas). These cameras automatically record and save real-time image information in the area at preset time intervals (such as every 15 minutes). This data is not only used for real-time monitoring, but can also be replayed later when necessary to conduct incident investigations or confirm the safety of the elderly.

[0028] Physical examination frequency data: The community organizes health examinations for the elderly on a regular basis (such as monthly) and records the date and results of each physical examination. The system calculates the physical examination frequency of each elderly person based on this information and monitors the changing trend of their health status. For example, an elderly person has participated in a physical examination every month in the past three months, and the results of the physical examinations have been stable.

[0029] Furthermore, the service efficiency evaluation value is obtained by the following method: A1, collecting the service request records of the service objects from the preset database to obtain the service response time, the service response time indicates the time difference from the issuance of the service request to the start of the response of the elderly care service network within a preset time interval, and the service request record includes the service object type and the service object request time; A2, judging whether the obtained service response time is less than the reference service response time, if so, obtaining the service efficiency evaluation value according to the service coverage rate and the preset service coverage rate weight factor, otherwise executing A3, the service coverage rate is represented by the result of the ratio operation of the actual number of service objects in the preset service area and the reference number of service objects, and the service coverage rate weight factor is used to reflect the proportion of the service coverage rate relative to the service efficiency evaluation value; A3, obtaining the service efficiency evaluation value according to the obtained service response time and the service coverage rate in combination with the preset service response time weight factor and the service coverage weight factor, and the service response time weight factor is used to reflect the proportion of the service response time relative to the service efficiency evaluation value.

[0030] The specific restricted expression of the service efficiency evaluation value is: ; Where y is the number of the preset service area, , Y is the total number of preset service areas, t is the number of preset time intervals, , T is the total number of preset time intervals, e is a natural constant, represents the service efficiency evaluation value of the elderly care service data in the y-th preset service area, Represents the service response time weight factor, represents the service response time of the yth preset service area in the tth preset time interval, Indicates the reference service response time. represents the service coverage weight factor, It represents the service coverage of the y-th preset service area in the t-th preset time interval.

[0031] In this embodiment, the service object types generally include the elderly, the elderly's family members and medical staff. The service object request time is the time point corresponding to the service object's request for elderly care services, and the service object reference number is the total number of service objects in the preset service area; it should be noted that the sum of the service response time weight factor and the service coverage weight factor in the embodiment of the present application is equal to 1.

[0032] Among them, the service response time weight factor is the weight factor corresponding to the service response time in the preset database during the process of obtaining the service efficiency evaluation value, which represents the numerical value of the influence of the service response time on the service efficiency evaluation value. When in use, the service response time weight factor corresponding to the service response time can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the service response time corresponding to the service response time in the process of obtaining the service efficiency evaluation value and the weight factor corresponding to the service response time in the preset database form a mapping set, and the real-time service response time is input into the mapping set to obtain the corresponding service response time weight factor, and the mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0033] The reference service response time is the sum of the minimum historical service response time in each historical time interval in the preset database. When , that is, the service response time has no effect on the efficiency level of elderly care services within the preset time interval, so it does not need to be substituted as an independent variable into the service efficiency evaluation value for calculation. At this time, the service efficiency evaluation value increases with the increase of service coverage; when When , the service efficiency evaluation value decreases with the increase of service response time and increases with the increase of service coverage. and When , the efficiency level of elderly care services in the corresponding preset time interval is the highest.

[0034] Specifically, when To simplify the analysis, we define , , the simplified calculation formula of service efficiency evaluation value is: , where represents the service response time coefficient of the yth preset service area within the preset time interval, represents the service coverage coefficient of the yth preset service area within the preset time interval; Figure 2 As shown, it is a two-dimensional analysis diagram of the service response time coefficient provided in the embodiment of the present application (constraint: the service coverage coefficient is a fixed value of 0.5), and the service efficiency evaluation value decreases as the service response time coefficient increases; Figure 3 As shown in FIG. 1 , a two-dimensional analysis diagram of the service coverage coefficient provided in the embodiment of the present application (constraint: the service response time coefficient is a fixed value of 0.5), the service efficiency evaluation value increases with the increase of the service coverage coefficient. It should be understood that when When the service coverage rate coefficient is increased, it also indirectly affects the value of the service response time coefficient. For example, if the service coverage rate of the preset service area increases, the elderly care service institutions in the preset service area may be equipped with more staff or more advanced equipment, so they can respond to service needs in a shorter time. Therefore, when service needs occur, resources can be mobilized more quickly to respond, thereby reducing the service response time. This indirect impact mechanism helps to improve the efficiency of elderly care services in the preset service area, thereby achieving the improvement of the real-time quality assessment of elderly care services in the process of processing elderly care service supervision data, and effectively solves the problem of low real-time quality assessment of elderly care services in the process of processing elderly care service supervision data in the prior art.

[0035] Furthermore, the specific steps of comparing the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch the abnormal behavior mode are as follows: E1, if the obtained service efficiency evaluation value is within the reference evaluation threshold range, it indicates that the behavior data of the service object is normal; if the obtained service efficiency evaluation value is not within the reference evaluation threshold range, the abnormal behavior mode is switched and E2 is executed; E2, the abnormal behavior interference value is obtained according to the degree of excess of the service efficiency evaluation value relative to the reference evaluation threshold range, and the abnormal behavior interference value is used to reflect the degree of abnormality of the behavior data in the elderly care service data within a preset time interval.

[0036] In this embodiment, the reference evaluation threshold range is represented by the range corresponding to the maximum and minimum values ​​of the historical service efficiency evaluation values ​​within a preset time interval in a preset database. By comparing the service efficiency evaluation value with the reference evaluation threshold range in real time, abnormal situations in the service process can be quickly identified to ensure that the problems receive timely attention and processing, thereby improving the accuracy and reliability of abnormal behavior identification.

[0037] Furthermore, the process of obtaining the abnormal behavior interference value is as follows: according to the comparison between the service efficiency evaluation value and the reference evaluation threshold range, the abnormal service efficiency evaluation value is obtained and counted, and the number of abnormal service efficiency evaluation values ​​in the preset service area within the preset time interval is obtained; at the same time, the number of abnormal service efficiency evaluation values ​​is compared with the total number of service efficiency evaluation values ​​to obtain the abnormal data volume index, and the number of abnormal service efficiency evaluation values ​​is the number of service efficiency evaluation values ​​that exceed the reference evaluation threshold range; real-time monitoring of the response process of the elderly care service network in the preset service area to the abnormal service efficiency evaluation value is obtained to obtain the data transmission delay rate, and the data transmission delay rate is the ratio of the difference between the network response time and the reference network response time to the reference network response time, and the network response time is the abnormal service efficiency evaluation value sent by the elderly care service network. The time interval between the moment of the evaluation value and the moment of receiving the abnormal service efficiency evaluation value; determine whether the obtained network response time is less than the reference network response time. If the obtained network response time is less than the reference network response time, add the abnormal time index and the obtained abnormal data volume index to obtain the abnormal behavior interference value; otherwise, add the abnormal time index, the obtained data transmission delay rate and the abnormal data volume index to obtain the abnormal behavior interference value. The abnormal time index is the ratio of the abnormal duration to the total duration of the preset time interval. The total duration of the preset time interval is the product of the preset time interval duration and the total number of preset time intervals. The preset time interval contains only one service efficiency evaluation value. The abnormal duration is the duration period during which the abnormal service efficiency evaluation value exceeds the reference evaluation threshold range.

[0038] Specifically, the specific limiting expression of the abnormal behavior interference value is: ; Where t is the number of the preset time interval, , T is the total number of preset time intervals, y is the number of the preset service area, , Y is the total number of preset service areas, e is a natural constant, represents the abnormal behavior interference value of the y-th preset service area, Indicates the network response time of the yth preset service area, Indicates the reference network response time. Indicates the duration of the abnormality in the yth preset service area within the preset time interval, Indicates the duration of each preset time interval. Represents the number of abnormal service efficiency evaluation values ​​in the y-th preset service area.

[0039] In this embodiment, the abnormal data volume index is the ratio of the number of abnormal service efficiency evaluation values ​​to the total number of service efficiency evaluation values. The reference network response time is represented by the sum and average of the minimum values ​​of the historical elderly care service network response times within the historical preset time interval in the preset database. When the acquired network response time is less than the reference network response time, it indicates that the network response time meets the actual response requirements of the elderly care service network. At this time, the network response time has no effect on the abnormality of the behavior data in the elderly care service data within the preset time interval, that is, it does not affect the value of the abnormal behavior interference value (so it does not need to be substituted into the calculation formula of the abnormal behavior interference value).

[0040] It should be noted that, since the preset time interval only includes one service efficiency evaluation value, the total number of service efficiency evaluation values ​​is the same as the total number of the preset time intervals.

[0041] Specifically, when When , the abnormal behavior interference value increases with the increase of abnormal duration and the number of abnormal service efficiency evaluation values. and , the abnormality of the behavior data in the corresponding elderly care service data is the smallest within the preset time interval; when When , the abnormal behavior interference value increases with the increase of network response time, abnormal duration and abnormal service efficiency evaluation value data. , and When , the abnormality of the behavior data in the corresponding elderly care service data is the smallest within the preset time interval.

[0042] It should be understood that the abnormal quantity index also indirectly affects the value of the abnormal duration index. For example, within a preset time interval (such as ten minutes), the network response rate increases, but the number of abnormal service efficiency evaluation values ​​increases, that is, the abnormal quantity index increases, resulting in a longer duration of abnormality. By considering the abnormal quantity index (indirectly through the number of abnormal service efficiency evaluation values ​​and the duration of abnormality) and the network response time, the abnormal behavior interference value provides a multi-dimensional evaluation tool to help service providers and regulators better understand abnormal behaviors in elderly care services and make more reasonable decisions and intervention measures accordingly. This evaluation method helps to improve the quality and efficiency of elderly care services.

[0043] Furthermore, the steps for obtaining the feature conformity index include: L1, determining whether the abnormal behavior interference value is equal to 0, if so, executing L2, otherwise it indicates that the elderly care service data does not match the reference feature data in the preset elderly care service supervision feature library, and the corresponding feature conformity index is equal to 0; L2, normalizing the elderly care service data and the reference feature data in the preset elderly care service supervision feature library to obtain real-time feature values ​​and reference feature values, the real-time feature values ​​include behavior feature values, video surveillance feature values ​​and physical examination feature values, and the reference feature values ​​include reference behavior feature values, reference video surveillance feature values ​​and reference physical examination feature values; L3, performing distance measurement calculation and addition and summation operations on the real-time feature values ​​and the reference feature values ​​respectively to obtain the feature conformity index, and the distance measurement calculation indicates that the real-time feature value is subtracted from the reference feature value and then squared.

[0044] In this embodiment, the real-time characteristic value and the reference characteristic value are usually acquired in real time through the elderly care service monitoring equipment in the preset service area. The reference characteristic data in the preset elderly care service supervision characteristic library refers to the historical numerical values ​​in the preset database used to reflect the activity ability and living status of the elderly. In the calculation formula of the characteristic compliance index, the behavior characteristic value is the ratio of the behavior characteristic parameter to the reference behavior characteristic parameter, the video monitoring characteristic value is the ratio of the video monitoring parameter to the reference video monitoring parameter, and the physical examination characteristic value is the ratio of the physical examination parameter to the reference physical examination parameter, wherein the behavior characteristic parameter can be expressed in the form of the activity frequency of the service object within a preset time interval, the video monitoring parameter can be expressed in the form of the elderly care service monitoring frequency of the service object within a preset time interval, the physical examination parameter can be expressed in the form of the physical examination frequency of the service object within a preset time interval, and the behavior characteristic parameter , video surveillance characteristic values ​​and physical examination characteristic values ​​are obtained in real time through elderly care service supervision sensors, reference behavior characteristic parameters are represented by the sum and average of historical behavior characteristic parameters within historical time intervals in a preset database, reference video surveillance parameters are represented by the sum and average of historical video surveillance parameters within historical time intervals in a preset database, reference physical examination parameters are represented by the sum and average of historical physical examination parameters within historical time intervals in the preset database. It should be noted that the reference behavior characteristic parameters, reference video surveillance parameters and reference physical examination parameters are stored in a preset elderly care service database, behavior characteristic values ​​are used to reflect the daily activity frequency of service objects in the preset service area, video surveillance characteristic values ​​are used to reflect the daily activity trajectory of service objects in the preset service area, and physical examination characteristic values ​​are used to reflect the physical examination frequency of service objects in the preset service area.

[0045] Specifically, in the application scenario of elderly care services, behavioral feature values ​​include the daily activity frequency and activity time of the elderly, which are used to evaluate the activity ability of the elderly. For example, by recording the number of activities (such as walking, participating in social activities) performed by the elderly every day and comparing them with the preset reference frequency, when the daily activity frequency is less than the reference frequency, it is necessary to increase the service frequency for the elderly, otherwise it is normal; video surveillance feature values ​​are collected in real time through video surveillance equipment, such as the activity trajectory and abnormal behavior of the elderly, and are used to monitor the safety of the elderly. For example, the elderly care service personnel monitor the elderly in the preset service area within a preset time period. The number of times is ten times (for example, the elderly care service staff checks the monitor every three minutes within half an hour). If the elderly person is found to have fallen to the ground during the fifth monitoring, it means that ten monitoring times within half an hour cannot ensure the safety of the elderly person. At this time, it is necessary to increase the number of service monitoring of the elderly by the elderly care service staff (that is, the monitoring frequency of elderly care services); the physical examination characteristic value monitors the elderly person's physical examination data (such as the elderly person's blood pressure and blood sugar) in real time through medical testing equipment. For example, by measuring the blood sugar value twice a day (morning and evening), if the elderly person's sugar intake increases, the number of blood sugar value measurements needs to be increased (from twice a day to four times a day).

[0046] Specifically, the specific restriction expression of the characteristic compliance index is: ; Where y is the number of the preset service area, , Y is the total number of preset service areas, t is the number of preset time intervals, , T is the total number of preset time intervals, e is a natural constant, It indicates that the characteristic conformity index of the elderly care service data in the preset service area within the tth preset time interval, represents the reference behavior characteristic value, represents the behavior characteristic value of the behavior data in the yth preset service area within the tth preset time interval, represents the reference video surveillance feature value, represents the video surveillance feature value of the video surveillance data in the yth preset service area within the tth preset time interval, represents the reference physical examination characteristic value, represents the physical examination characteristic value of the physical examination frequency data in the yth preset service area within the tth preset time interval, It represents the abnormal behavior interference value of the y-th preset service area within the preset time interval.

[0047] Specifically, when This table only considers the elderly care service data of a preset service area, and the statistical table of changes in the characteristic compliance index is shown in Table 1: Table 1 Statistics of changes in characteristic compliance index

[0048] It should be understood that the feature conformity index decreases as the behavior feature value, video surveillance feature value, and physical examination feature value increase. , and , the matching degree between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library is the highest; it should be noted that the behavior feature value also indirectly affects the value of the physical examination feature value. For example, in a community, the average daily number of steps of the elderly in the preset time interval reaches the recommended health level (such as 8,000 steps), which indicates that the activity level of the elderly in the community has increased, that is, the metabolism of the elderly in the community has accelerated. Therefore, in the next physical examination, the abnormal rate of blood pressure and blood sugar may decrease. Due to the influence of the above-mentioned behavior feature value, the physical examination feature value (that is, the proportion or degree of abnormal physical examination results) of the elderly in the community within the preset time interval is relatively reduced. By considering the indirect influence of the behavior feature value on the physical examination feature value, and acting together with the video surveillance feature value on the calculation of the feature compliance index, a comprehensive evaluation of the quality of elderly care services is achieved.

[0049] Furthermore, the specific process of comparing the obtained feature compliance index with the preset threshold range to determine whether to implement intervention measures is as follows: determine whether the obtained feature compliance index is within the preset threshold range: if the feature compliance index is within the preset threshold range, it indicates that the service object is in a normal state and continue to monitor the changes in the elderly care service data within the preset time interval; if the feature compliance index is not within the preset threshold range, implement intervention measures and evaluate the effectiveness of the intervention measures.

[0050] Furthermore, the specific process for evaluating the effectiveness of intervention measures is as follows: if the characteristic conformity index after the implementation of the intervention measures is within the preset threshold range, the elderly care service process, elderly care supervision area and preset service area are optimized; if the characteristic conformity index after the implementation of the intervention measures is still not within the preset threshold range, an early warning feedback is performed and the elderly care service process, elderly care supervision area and preset service area are adjusted and optimized, and the early warning feedback is used to automatically send the location information of the early warning feedback to the preset personnel.

[0051] In this embodiment, the preset threshold range is represented by the range corresponding to the maximum and minimum values ​​of the historical feature compliance index in each historical time interval in the preset database. When the feature compliance index after the intervention measures are implemented is within the preset threshold range, the elderly care service process (such as daily exercise guidance program, social activity information, rescue service introduction), elderly care supervision area (such as service object living area, service object food area) and elderly care service satisfaction questionnaire survey in the preset service area are added to meet the personalized needs of the elderly; when the feature compliance index after the intervention measures are implemented is not within the preset threshold range, the corresponding warning information (such as the location and impact range in the preset service area) is displayed in the form of a sound alarm on the video monitoring interface. At this time, the system administrator needs to increase the number of supervisions in high-risk areas (such as boiler areas) and increase the service content and number of preset service areas. Through the above adjustment and optimization, it helps to ensure the effectiveness and reliability of the elderly care service supervision system and improve the accuracy and efficiency of elderly care service quality assessment.

[0052] like Figure 4 As shown, it is a structural schematic diagram of a system for applying a method for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application. The system for processing elderly care service supervision data based on multi-source data and machine learning provided in an embodiment of the present application includes: a service efficiency evaluation value acquisition module, an abnormal behavior pattern judgment module and a feature compliance index acquisition module; wherein the service efficiency evaluation value acquisition module is used to obtain elderly care service data from an elderly care service data source and perform data integration, and at the same time, input the integrated elderly care service data into the SFIC model in combination with a preset time interval to obtain a service efficiency evaluation value, the elderly care service data includes behavior data, video surveillance data and physical examination frequency data, and the service efficiency evaluation value is used to evaluate the preset time. The efficiency level of elderly care services within the interval; the abnormal behavior pattern judgment module is used to compare the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch the abnormal behavior mode. If the abnormal behavior mode is switched, the abnormal behavior pattern processing is executed and the processing result is fed back to the medical staff for processing, and then the function of the feature compliance index acquisition module is executed. The abnormal behavior pattern processing includes generating abnormal reports and sending emergency notifications; the feature compliance index acquisition module is used to monitor the comparison process in real time to obtain the feature compliance index, and at the same time compare the obtained feature compliance index with the preset threshold range to determine whether to implement intervention measures. The feature compliance index is used to reflect the matching situation between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library.

[0053] like Figure 5As shown, it is a flow chart of the elderly care service supervision process provided in the embodiment of the present application. The synergistic effect of the service efficiency evaluation value acquisition module, the abnormal behavior pattern judgment module and the feature compliance index acquisition module helps to dynamically evaluate the efficiency level of elderly care services within a preset time interval, improves the accuracy and efficiency of data processing and evaluation, and realizes the improvement of the efficiency and real-time performance of elderly care service supervision.

[0054] To summarize, the embodiment of the present application obtains a service efficiency evaluation value by inputting the integrated elderly care service data into the SFIC model, and compares it with the reference evaluation threshold range to determine whether to switch to the abnormal behavior mode. The feature compliance index is obtained by real-time monitoring of the comparison process and compared with the preset threshold range to determine whether to perform intervention measures, thereby achieving a more accurate judgment of abnormal behavior patterns, and further achieving the improvement of the real-time performance of the elderly care service quality evaluation in the process of elderly care service supervision data processing, effectively solving the problem of low real-time performance of the elderly care service quality evaluation in the process of elderly care service supervision data processing in the prior art.

[0055] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0059] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0060] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for processing elderly care service supervision data based on multi-source data and machine learning, characterized in that: The following steps are involved: Step 1: Obtain elderly care service data from the elderly care service data source and integrate the data. At the same time, input the integrated elderly care service data into the SFIC model to obtain a service efficiency evaluation value in combination with a preset time interval. The elderly care service data includes behavioral data, video surveillance data, and physical examination frequency data. The service efficiency evaluation value is used to evaluate the efficiency level of elderly care services within a preset time interval; Step 2: compare the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch to the abnormal behavior mode. If the abnormal behavior mode is switched, perform abnormal behavior mode processing and feed back the processing result to the medical staff for processing before executing step 3; Step three, monitor the comparison process in real time to obtain the feature compliance index, and compare the obtained feature compliance index with the preset threshold range to determine whether to implement intervention measures. The feature compliance index is used to reflect the matching between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library.

2. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 1, characterized in that: The behavioral data includes the number of steps, sleep duration and activity area of ​​the service object; The video surveillance data is used to record real-time image information within a preset service area within a preset time interval; The physical examination frequency data is used to record the physical examination frequency of the service object within a preset time interval; The data integration refers to data cleaning and data conversion of elderly care service data from different elderly care service data sources.

3. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 1, characterized in that: The service efficiency evaluation value is obtained by the following method: A1, collecting service request records of service objects from a preset database to obtain service response duration, wherein the service response duration indicates the time difference from the issuance of a service request to the start of response by the elderly care service network within a preset time interval, and the service request record includes the service object type and the service object request time; A2, judging whether the obtained service response time is less than the reference service response time, if so, obtaining the service efficiency evaluation value according to the service coverage rate and the preset service coverage rate weight factor, otherwise executing A3, the service coverage rate is represented by the result of the ratio operation of the actual number of service objects in the preset service area and the reference number of service objects; A3, obtaining a service efficiency evaluation value according to the obtained service response time and service coverage ratio in combination with a preset service response time weight factor and a preset service coverage ratio weight factor.

4. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 3, characterized in that: The specific limiting expression of the service efficiency evaluation value is: ; Where y is the number of the preset service area, , Y is the total number of preset service areas, t is the number of preset time intervals, , T is the total number of preset time intervals, e is a natural constant, represents the service efficiency evaluation value of the elderly care service data in the y-th preset service area, Represents the service response time weight factor, represents the service response time of the yth preset service area in the tth preset time interval, Indicates the reference service response time. represents the service coverage weight factor, It represents the service coverage of the y-th preset service area in the t-th preset time interval.

5. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 1, characterized in that: The specific steps of comparing the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch to the abnormal behavior mode are: E1: If the service efficiency evaluation value obtained is within the reference evaluation threshold range, it indicates that the behavior data of the service object is normal. If the service efficiency evaluation value obtained is not within the reference evaluation threshold range, the abnormal behavior mode is switched and E2 is executed; E2, obtaining an abnormal behavior interference value according to the degree to which the service efficiency evaluation value exceeds the reference evaluation threshold range, wherein the abnormal behavior interference value is used to reflect the abnormal degree of the behavior data in the elderly care service data within a preset time interval.

6. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 5, characterized in that: The process of obtaining the abnormal behavior interference value is as follows: According to the comparison between the service efficiency evaluation value and the reference evaluation threshold range, the abnormal service efficiency evaluation value is obtained and counted, and the number of abnormal service efficiency evaluation values ​​in the preset service area within the preset time interval is obtained. At the same time, the number of abnormal service efficiency evaluation values ​​is compared with the total number of service efficiency evaluation values ​​to obtain the abnormal data volume index, and the number of abnormal service efficiency evaluation values ​​is the number of service efficiency evaluation values ​​that exceed the reference evaluation threshold range; Real-time monitoring of the response process of the elderly care service network in the preset service area to the abnormal service efficiency evaluation value to obtain a data transmission delay rate, wherein the data transmission delay rate is the ratio of the difference between the network response time and the reference network response time to the reference network response time, wherein the network response time is the time interval between the time when the elderly care service network sends the abnormal service efficiency evaluation value and the time when the abnormal service efficiency evaluation value is received; Determine whether the acquired network response time is less than the reference network response time. If the acquired network response time is less than the reference network response time, add the abnormal time index and the acquired abnormal data volume index to obtain the abnormal behavior interference value. Otherwise, add the abnormal time index, the acquired data transmission delay rate and the abnormal data volume index to obtain the abnormal behavior interference value. The abnormal time index is the ratio of the abnormal duration to the total duration of the preset time interval. The total duration of the preset time interval is the product of the preset time interval duration and the total number of preset time intervals. The abnormal duration is the duration period during which the abnormal service efficiency evaluation value exceeds the reference evaluation threshold range.

7. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 1, characterized in that: The step of obtaining the characteristic compliance index comprises: L1, determines whether the abnormal behavior interference value is equal to 0. If so, execute L2, otherwise the corresponding feature compliance index is equal to 0; L2, normalizing the elderly care service data and the reference feature data in the preset elderly care service supervision feature library to obtain real-time feature values ​​and reference feature values, wherein the real-time feature values ​​include behavior feature values, video surveillance feature values ​​and physical examination feature values, and the reference feature values ​​include reference behavior feature values, reference video surveillance feature values ​​and reference physical examination feature values; L3, respectively performing distance measurement calculation and addition and summation operations on the real-time eigenvalue and the reference eigenvalue to obtain a feature conformity index, wherein the distance measurement calculation indicates that the real-time eigenvalue and the reference eigenvalue are subtracted and then squared.

8. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 1, characterized in that: The specific process of comparing the acquired feature compliance index with the preset threshold range to determine whether to perform intervention measures is as follows: Determine whether the acquired feature conformity index is within the preset threshold range: If the characteristic compliance index is within the preset threshold range, continue to monitor the changes in the elderly care service data within the preset time interval; If the characteristic compliance index is not within the preset threshold range, the intervention measures are implemented and the effectiveness of the intervention measures is evaluated.

9. The method for processing elderly care service supervision data based on multi-source data and machine learning as claimed in claim 8, characterized in that: The specific process for evaluating the effectiveness of intervention measures is as follows: If the characteristic compliance index after the implementation of the intervention measures is within the preset threshold range, the elderly care service process, elderly care supervision area and preset service area will be optimized; If the characteristic compliance index after the intervention measures are implemented is still not within the preset threshold range, an early warning feedback is given and the elderly care service process, elderly care supervision area and preset service area are adjusted and optimized. The early warning feedback is used to automatically send the location information of the early warning feedback to the preset personnel.

10. A system using the method for processing elderly care service supervision data based on multi-source data and machine learning as described in any one of claims 1 to 9, characterized in that: include: Service efficiency evaluation value acquisition module, abnormal behavior pattern judgment module and feature compliance index acquisition module; The service efficiency evaluation value acquisition module is used to obtain elderly care service data from the elderly care service data source and perform data integration, and at the same time, input the integrated elderly care service data into the SFIC model to obtain a service efficiency evaluation value in combination with a preset time interval. The elderly care service data includes behavioral data, video surveillance data, and physical examination frequency data. The service efficiency evaluation value is used to evaluate the efficiency level of elderly care services within a preset time interval; The abnormal behavior mode judgment module is used to compare the obtained service efficiency evaluation value with the reference evaluation threshold range to determine whether to switch the abnormal behavior mode. If the abnormal behavior mode is switched, the abnormal behavior mode processing is performed and the processing result is fed back to the medical staff for processing and then the feature conformity index acquisition module is executed; The feature compliance index acquisition module is used to monitor the comparison process in real time to obtain the feature compliance index, and at the same time compare the obtained feature compliance index with the preset threshold range to determine whether to implement intervention measures. The feature compliance index is used to reflect the matching status between the elderly care service data and the reference feature data in the preset elderly care service supervision feature library.

Citation Information

Cited By

  • Intelligent product risk identification and control method and system based on big data

    CN119293703A

  • Quick construction method for weapon platform-oriented electronic system digital model

    CN119475816A

  • Virtual power plant load prediction system based on big data

    CN119787320A

  • A virtual power plant load forecasting system based on big data

    CN119787320B

  • Service quality evaluation method and system based on multi-source data fusion

    CN120806756A