Return visit evaluation method for community old-age care service
Through screening and deep learning algorithms, analyzing the weight of key service quality characteristics, combined with real-time feedback data, the problems of low data utilization and inaccurate evaluation in community elderly care service evaluation are solved, and more refined and accurate service quality evaluation is achieved, improving Overall service quality and user satisfaction.
Patent Information
- Application Number
- CN202411435004.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-10-15
AI Technical Summary
The existing community elderly care service return evaluation technology has problems such as low data utilization and inaccurate evaluation, especially when processing complex data and extracting key service quality factors, there is a lack of effective mechanisms to combine historical service data with real-time user feedback. This results in incomplete and accurate evaluation results.
By screening out the key service quality impact feature weights, using deep learning algorithms to analyze these features, and matching the analysis results with the user feedback data collected in real time, hierarchical storage of evaluation scores is performed based on the calculation results to ensure the evaluation results Accuracy and timeliness. The specific steps include: collecting historical service records, cleaning and formatting, identifying key features using principal component analysis and regression analysis algorithms, and optimizing feature weights through deep learning algorithms, and finally combining real-time feedback data to weight sum to calculate evaluation scores.
The dynamic adaptability and long-term effectiveness of the service evaluation model are improved, so that the evaluation results can continuously reflect the true level of service quality, provide more accurate service quality assessment and improvement basis, and significantly improve the overall quality and efficiency of community elderly care services.
Smart Images

Figure CN118941341A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart community management and big data processing, and in particular to a return visit evaluation method for community elderly care services. Background Art
[0002] Community elderly care service is one of the key measures to meet the challenges of population aging. With the development of social economy and changes in population structure, the requirements for the quality of elderly care services are getting higher and higher. Traditional community elderly care services mainly rely on manual experience to evaluate service quality. This method has disadvantages such as low efficiency, strong subjectivity and difficulty in standardization.
[0003] In recent years, with the rapid development of information technology, especially the application of data mining and machine learning technology, the evaluation methods of elderly care service quality have gradually developed towards intelligence and precision. For example, some studies have used user feedback data and service records to construct evaluation models. These models can better reflect the actual effect of the service and user satisfaction.
[0004] However, existing technologies still have shortcomings in processing complex data and extracting key service quality influencing factors. The current evaluation system often ignores the weight distribution of service quality influencing features, resulting in evaluation results that cannot fully and accurately reflect the actual situation of the service.
[0005] In addition, the existing technology lacks an effective mechanism to combine historical service data with real-time user feedback, which limits the effectiveness and practicality of the evaluation system in actual applications; therefore, there is an urgent need for a new elderly care service evaluation method that can integrate historical and real-time data and improve evaluation accuracy and efficiency through intelligent methods. Summary of the invention
[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0007] In view of the above existing problems, the present invention is proposed.
[0008] Therefore, the technical problem solved by the present invention is that the existing community elderly care service return visit evaluation technology has the problems of low data utilization and inaccurate evaluation.
[0009] In order to solve the above technical problems, the present invention provides the following technical solutions: based on the historical service records of elderly care service users, the weights of key service quality influencing features are screened out; Analyzing the weights of the key service quality influencing features using a deep learning algorithm; The analysis results are matched and calculated with the real-time collected feedback data from elderly care service users, and stored in a graded manner according to the evaluation scores corresponding to the calculation results.
[0010] As a preferred solution of the method for evaluating the return visit of community elderly care services according to the present invention, the weights of key service quality influencing features are screened out, including: Collecting historical service records of the elderly care service users, wherein the historical service records at least include service logs, user feedback, and complaint records; Cleaning and formatting the historical service records; Using a principal component analysis algorithm, identifying key features that affect service quality from the historical service records; According to the influence of each feature on user satisfaction, weights are assigned based on a regression analysis algorithm to obtain the weights of the key service quality influencing features.
[0011] As a preferred solution of the method for return visit evaluation of community elderly care services according to the present invention, finding the key features includes: Calculate the mean and standard deviation of X to obtain the standardized data matrix Z; Calculate the covariance matrix C and solve the eigenvalues and corresponding eigenvectors of C; According to the order of the eigenvalues from large to small, the first m eigenvectors are selected as the key features; Wherein, X is an n*p data matrix, representing the cleaned and formatted historical service records, n is the number of records, and p is the number of feature elements.
[0012] As a preferred solution of the return visit evaluation method for community elderly care services described in the present invention, the key features at least include service attitude, professional ability, response speed, service continuity, and personalized service.
[0013] As a preferred solution of the method for return visit evaluation of community elderly care services described in the present invention, weights are allocated based on a regression analysis algorithm, which can be expressed by the following formula:
[0014]
[0015] Among them, Z ij is the standardized value, t ik is the score of the i-th record on the k-th principal component, u jk is the score of the jth feature element on the kth principal component, w k is the weight of the kth principal component, yi For user satisfaction, is the error term.
[0016] As a preferred embodiment of the method for evaluating the return visit of community elderly care services according to the present invention, the analysis can be expressed by the following mathematical formula:
[0017]
[0018] Among them, h i is the output of the i-th layer, W i is the weight matrix of the i-th layer, b i is the bias vector of the i-th layer, is the activation function, and F is the output vector, which represents the estimate of each feature weight.
[0019] As a preferred solution of the method for evaluating the return visit of community elderly care services according to the present invention, the value range of the output vector F is [0,1], where: The closer the value is to 1, the greater the impact of the feature on service quality; The closer the value is to 0, the smaller the impact of the feature on service quality.
[0020] As a preferred solution of the method for evaluating the return visit of community elderly care services according to the present invention, hierarchical storage is performed according to the evaluation scores corresponding to the calculation results, including: Normalize the real-time feedback data collected from elderly care service users to make the data at the same level; The normalized feedback data is combined with the feature weights using a weighted summation algorithm to obtain the evaluation score for each element; The evaluation scores are stored in a hierarchical manner.
[0021] Beneficial effects of the present invention: The present invention uses a deep learning algorithm to learn subtle patterns and correlations from complex data sets, thereby providing a more refined and accurate weight for each service quality feature, greatly improving the dynamic adaptability and long-term effectiveness of the service evaluation model, so that the evaluation results can continuously reflect the true level of service quality; it can not only more accurately evaluate service quality, but also provide a basis for service providers to improve services, thereby significantly improving the overall quality and efficiency of community elderly care services. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 It is a flow chart of the method for return visit evaluation of community elderly care services shown in the present invention. DETAILED DESCRIPTION
[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.
[0024] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.
[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0026] According to an embodiment of the present invention, Figure 1 The flowchart shown is a method for evaluating the return visit of community elderly care services, which specifically includes the following steps: S1. Filter out the weights of key service quality influencing features based on the historical service records of elderly care service users. It should be noted that the weights of key service quality influencing features are filtered out, including: Collect historical service records of elderly care service users, which at least include service logs, user feedback, and complaint records; Clean and format historical service records; Using principal component analysis algorithm, key features that affect service quality are identified from historical service records; According to the influence of each feature on user satisfaction, weights are assigned based on the regression analysis algorithm to obtain the weights of key service quality influencing features.
[0027] Further, key features were found, including: Calculate the mean and standard deviation of X to obtain the standardized data matrix Z; Calculate the covariance matrix C and solve the eigenvalues and corresponding eigenvectors of C; Sort by eigenvalue from large to small and select the first m eigenvectors as key features; Where X is an n*p data matrix, representing the cleaned and formatted historical service records, n is the number of records, and p is the number of feature elements.
[0028] As an example, the weights are assigned based on the regression analysis algorithm, which can be expressed by the following formula:
[0029]
[0030] Among them, Z ij is the standardized value, t ik is the score of the i-th record on the k-th principal component, u jk is the score of the jth feature element on the kth principal component, w k is the weight of the kth principal component, y i For user satisfaction, is the error term.
[0031] In an optional embodiment, the key features include at least service attitude, professional ability, response speed, service continuity, and personalized service.
[0032] In an optional embodiment, the historical service records include at least service logs, user feedback, complaint records, service effect tracking, and service personnel change records.
[0033] As an example, the service log is used to record the date, time, service personnel, and service content of each service.
[0034] As an example, user feedback is used to provide users with feedback on their satisfaction with each service and suggestions for improvement.
[0035] As an example, complaint records are used to record user dissatisfaction with a service or detailed records of complaint events.
[0036] As an example, service effect tracking is used to track and record users’ health status, quality of life, etc. over a long period of time, and to evaluate the long-term effects of the service.
[0037] As an example, service personnel change records are used to record the replacement of service personnel in order to assess the impact of personnel changes on service quality.
[0038] Preferably, this step can accurately identify and screen out key features that affect service quality, such as response time, service attitude, and professional ability, and assign corresponding weights to these features to ensure that the evaluation calculation process is more in line with the actual service situation, thereby improving the accuracy and effectiveness of the evaluation.
[0039] S2. Analyze the weights of key service quality influencing features using a deep learning algorithm. It should be noted that the analysis can be expressed by the following mathematical formula:
[0040]
[0041] Among them, h i is the output of the i-th layer, W i is the weight matrix of the i-th layer, b i is the bias vector of the i-th layer, is the activation function, and F is the output vector, which represents the estimate of each feature weight.
[0042] As an example, the output vector F has a value range of [0,1], where: The closer the value is to 1, the greater the impact of the feature on service quality; The closer the value is to 0, the smaller the impact of the feature on service quality.
[0043] Preferably, this step applies a deep learning algorithm to further analyze the weights of key service quality influencing features, which not only enhances the prediction and evaluation accuracy of the model, but also automatically adjusts and optimizes the weight distribution, greatly improving the dynamic adaptability and long-term effectiveness of the service evaluation model, so that the evaluation results can continuously reflect the true level of service quality.
[0044] S3. Match and calculate the analysis results with the real-time collected elderly care service user feedback data, and store them in different levels according to the evaluation scores corresponding to the calculation results. It should be noted that the step of storing the evaluation scores in different levels according to the calculation results includes: Normalize the real-time feedback data collected from elderly care service users to make the data at the same level; The normalized feedback data is combined with the feature weights using a weighted summation algorithm to obtain the evaluation score for each element; The evaluation scores are stored in a hierarchical manner.
[0045] As an example, the evaluation score can be expressed as follows:
[0046] By adding an exponential function to adjust the sensitivity of the evaluation score, the evaluation score calculation result is more in line with the actual situation, which can be expressed by the following mathematical formula:
[0047] Based on the adjusted V iAs a result, the evaluation scores are stored in a hierarchical manner, and the mathematical expression formula is as follows:
[0048] Among them, S i is the original evaluation score of the ith sample, k and c are the adjustment parameters of the exponential function, which are used to control the shape and position of the function, and F j is the output vector of the jth feature, R is the normalized user feedback data matrix, R ij is the original feedback of the i-th sample to the j-th feature, V i is the adjusted evaluation score, is the classification threshold of the evaluation score.
[0049] As an example, V i The value range is [0,1], where a value close to 0 indicates poor service quality, and a value close to 1 indicates excellent service quality.
[0050] Preferably, this embodiment combines the analysis results with user feedback data collected in real time, obtains the final service quality evaluation score through matching calculation, and stores them in a graded manner according to these scores, so that the evaluation results can immediately reflect the user's current satisfaction and service experience, increasing the timeliness and practicality of the evaluation.
[0051] Preferably, the hierarchical storage method facilitates the rapid identification of different levels of service quality, and makes it easier for managers to make targeted service improvements or formulate differentiated service strategies based on specific evaluation results, thereby improving the overall service level and enhancing user satisfaction.
[0052] It is also necessary to explain in the embodiments of the present invention that traditional methods usually rely on a single type of service data (such as user feedback or service logs only), lack multi-dimensional comprehensive analysis, and the weights of service quality characteristics are often fixed and cannot be dynamically adjusted according to actual service changes, thereby ignoring the importance assessment of user personalized needs.
[0053] In order to better verify and illustrate the technical effects used in the method of the present invention, this embodiment chooses to conduct comparative tests using the traditional method and the method of the present invention, and compares the test results by means of scientific demonstration to verify the real effect of the method.
[0054] (1) Experimental conditions Collect 1,000 historical service records, each of which includes service logs, user feedback, complaint records, service effect tracking, and service personnel change records; Five key characteristics: service attitude, professional ability, response speed, service continuity and personalized service; High-performance computers using NVIDIA Tesla V100 GPUs, powered by Python 3.8 and TensorFlow 2.4, were used to implement deep learning algorithms. The principal component analysis uses the SciPy library, and the deep learning model construction and training uses the TensorFlow framework.
[0055] (2) Experimental process Clean the data, including removing invalid records and formatting date and time; Standardize the data so that different types of data can be compared quantitatively; Principal component analysis (PCA) was used to extract key features from historical service records; Calculate the covariance matrix of the feature, analyze its eigenvalues and eigenvectors, and select the eigenvector with the highest contribution; Use regression analysis algorithms to assign weights to each feature based on its impact on user satisfaction; Apply deep learning algorithms to further optimize feature weights; Combined with user feedback data collected in real time, a weighted sum algorithm is used to calculate the evaluation score of service quality; Adjust the sensitivity of the evaluation score through the exponential adjustment function to ensure that the evaluation results are consistent with the actual situation; Evaluation results are stored hierarchically to facilitate rapid identification and response to changes in service quality.
[0056] (3) Experimental results Table 1. Comparison statistics of scoring results Experimental subjects Service attitude Professional capabilities Response speed Service Continuity Personalized service Customer satisfaction Final Rating Traditional methods 0.80 0.82 0.78 0.85 0.79 0.84 0.82 Method of the present invention 0.92 0.91 0.89 0.94 0.90 0.93 0.92 Referring to Table 1, it can be seen intuitively that the scores of the method of the present invention in various key features are higher than those of the traditional method, especially the significant improvement in personalized service and response speed, which shows that the method of the present invention can more accurately identify and respond to the actual needs of users, and effectively improve the overall quality of elderly care services and user satisfaction.
[0057] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for evaluating the return visit of community elderly care services, characterized in that: include: According to the historical service records of elderly care service users, the weights of key service quality influencing features are screened out; Analyzing the weights of the key service quality influencing features using a deep learning algorithm; The analysis results are matched and calculated with the real-time collected feedback data from elderly care service users, and stored in a graded manner according to the evaluation scores corresponding to the calculation results.
2. The method for evaluating the return visit of community elderly care services according to claim 1 is characterized in that: The screening out of the key service quality influencing feature weights includes: Collecting historical service records of the elderly care service users, wherein the historical service records at least include service logs, user feedback, and complaint records; Cleaning and formatting the historical service records; Using a principal component analysis algorithm, identifying key features that affect service quality from the historical service records; According to the influence of each feature on user satisfaction, weights are assigned based on a regression analysis algorithm to obtain the weights of the key service quality influencing features.
3. The method for evaluating the return visit of community elderly care services according to claim 2 is characterized in that: The key features found include: Calculate the mean and standard deviation of X to obtain the standardized data matrix Z; Calculate the covariance matrix C and solve the eigenvalues and corresponding eigenvectors of C; According to the order of the eigenvalues from large to small, the first m eigenvectors are selected as the key features; Wherein, X is an n*p data matrix, representing the cleaned and formatted historical service records, n is the number of records, and p is the number of feature elements.
4. The method for evaluating the return visit of community elderly care services according to claim 3 is characterized in that: The key features include at least service attitude, professional ability, response speed, service continuity, and personalized service.
5. The method for evaluating the return visit of community elderly care services according to claim 2 is characterized in that: The weights are assigned based on the regression analysis algorithm and can be expressed as follows: ; ; Among them, Z ij is the standardized value, t ik is the score of the i-th record on the k-th principal component, u jk is the score of the jth feature element on the kth principal component, w k is the weight of the kth principal component, y i For user satisfaction, is the error term.
6. The method for evaluating the return visit of community elderly care services according to claim 1 is characterized in that: The analysis can be expressed by the following mathematical formula: ; ; Among them, h i is the output of the i-th layer, W i is the weight matrix of the i-th layer, b i is the bias vector of the i-th layer, is the activation function, and F is the output vector, which represents the estimate of each feature weight.
7. The method for evaluating the return visit of community elderly care services according to claim 6 is characterized in that: The value range of the output vector F is [0,1], where: The closer the value is to 1, the greater the impact of the feature on service quality; The closer the value is to 0, the smaller the impact of the feature on service quality.
8. The method for evaluating the return visit of community elderly care services according to claim 1 is characterized in that: The calculation results are stored in different levels according to the evaluation scores, including: Normalize the real-time feedback data collected from elderly care service users to make the data at the same level; The normalized feedback data is combined with the feature weights using a weighted summation algorithm to obtain the evaluation score for each element; The evaluation scores are stored in a hierarchical manner.
Citation Information
Patent Citations
Power supply enterprise customer satisfaction evaluation method based on partial least square method
CN108446850A
Intelligent spoken English retelling question scoring method and system
CN109658918A
Community service management method and device, equipment and storage medium
CN117035565A
Behavior analysis method and system based on customer group portrait
CN117151870A
Remote monitoring system and method for old-age care facilities
CN117854730A
Cited By
Pension service quality intelligent evaluation method and system based on multi-dimensional data fusion
CN120163500A
