Community service ergonomics evaluation method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of data processing, in particular to a community service ergonomics evaluation method and device, equipment, a medium and a program product, and the method comprises the steps: obtaining user file data, community service facility data, service process data and environment perception data of a target community, and carrying out the data preprocessing of various data; inputting the plurality of preprocessed data into a pre-trained big language model, calling a pre-established service ergonomics evaluation system by the big language model, mapping the plurality of preprocessed data to a pre-established service index under the service evaluation system, calculating the score of the corresponding service index according to the mapping data corresponding to each service index; and calculating the score of the target community according to the score and the weight of each service index in a weighted manner, and determining a service evaluation result of the target community according to the score of the target community. Therefore, the problems of long evaluation period, low efficiency, relatively low accuracy and the like in related technologies are solved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment, medium and program product for evaluating the ergonomics of community services. Background Technology

[0002] As the primary space for daily life and social interaction for the elderly, the development of community service systems directly impacts their quality of life, health and safety, and social integration. Therefore, it is necessary to evaluate community services to help improve their quality and level.

[0003] The evaluation of community services in related technologies mainly relies on manual methods such as questionnaires, interviews, and expert scoring. The evaluation cycle is long and the efficiency is low. In addition, due to the subjective differences in human evaluation, the evaluation error is relatively large to a certain extent, making it difficult to accurately reflect the true level of community services. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, medium, and program product for evaluating the ergonomics of community services, in order to solve the problems of long evaluation cycles, low efficiency, and low accuracy in related technologies.

[0005] The first aspect of this application provides a method for evaluating the ergonomics of community services, comprising the following steps: acquiring user profile data, community service facility data, service process data, and environmental perception data of a target community; performing data preprocessing on the user profile data, community service facility data, service process data, and environmental perception data; inputting the preprocessed user profile data, community service facility data, service process data, and environmental perception data into a pre-trained large language model; the large language model calling a pre-established service ergonomics evaluation system; mapping the preprocessed user profile data, community service facility data, service process data, and environmental perception data to pre-established service indicators under the service evaluation system; calculating the score of the corresponding service indicator based on the mapping data corresponding to each service indicator; obtaining the weight of each service indicator; calculating the score of the target community by weighting the score of each service indicator and the weight; and determining the service evaluation result of the target community based on the score of the target community.

[0006] Optionally, the service ergonomics evaluation system includes first to fourth criterion layers, with each criterion layer containing multiple service indicators. The first criterion layer is the service safety layer, the second criterion layer is the service efficiency layer, the third criterion layer is the service user-friendliness layer, and the fourth criterion layer is the service ecology layer.

[0007] Optionally, the service indicators under the first criterion layer include the first, second, third, fourth, and fifth indicators, where the first indicator is service reliability, the second is service availability, the third is service risk predictability, the fourth is service emergency responsiveness, and the fifth is service traceability. The service indicators under the second criterion layer include the sixth, seventh, eighth, and ninth indicators, where the sixth is service adaptability, the seventh is service stability, the eighth is service simplicity, and the ninth is service economy. The service indicators under the third criterion layer include the tenth, eleventh, twelfth, and thirteenth indicators, where the tenth is service empathy, the eleventh is service inclusiveness, the twelfth is service personalization, and the thirteenth is service co-creation. The service indicators under the fourth criterion layer include the fourteenth, fifteenth, sixteenth, and seventeenth indicators, where the fourteenth is service interactivity, the fifteenth is service longevity, the sixteenth is service sustainability, and the seventeenth is service scalability.

[0008] Optionally, obtaining the weight of each service indicator includes: obtaining the importance score between every two criterion layers, determining the weight of each criterion layer based on the importance score between every two criterion layers, performing a consistency check, and readjusting the weight of the criterion layer if the check fails, until the consistency check passes; obtaining the importance score between every two service indicators under the same criterion layer, determining the initial weight of the service indicator based on the importance score between every two service indicators, performing a consistency check, and readjusting the initial weight of the service indicator if the check fails, until the consistency check passes; and determining the final weight of the service indicator based on the initial weight of the service indicator and the weight of the criterion layer to which it belongs.

[0009] Optionally, the initial weights of service indicators are determined based on the importance scores between each pair of service indicators, including: generating a judgment matrix for the corresponding level based on the importance scores between each pair of service indicators; calculating the largest eigenvalue of the judgment matrix and normalizing the eigenvector corresponding to the largest eigenvalue to obtain the initial weights of the corresponding service indicators.

[0010] Optionally, the processing steps of the large language model include: performing semantic analysis and / or semantic mapping on preprocessed user profile data, community service facility data, service process data, and environmental perception data to obtain multiple semantic information; extracting features from the semantic information to obtain multiple service features; determining the scores corresponding to the multiple service features based on preset quantification rules, converting the scores of the multiple service features into numerical features, and generating feature vectors corresponding to the multiple service features; calculating the semantic similarity between the multiple feature vectors, dividing the multiple service features based on the semantic similarity to obtain multiple feature clusters; mapping the multiple feature clusters to corresponding service indicators using a target clustering algorithm, wherein the cluster centers of the target clustering algorithm are the multiple service indicators; and calculating the score of the service indicator based on the scores of the service features in the feature clusters corresponding to the service indicators.

[0011] A second aspect of this application provides a community service ergonomics evaluation device, comprising: an acquisition module for acquiring user profile data, community service facility data, service process data, and environmental perception data of a target community, and performing data preprocessing on the user profile data, community service facility data, service process data, and environmental perception data; an input module for inputting the preprocessed user profile data, community service facility data, service process data, and environmental perception data into a pre-trained large language model, wherein the large language model calls a pre-established service ergonomics evaluation system to map the preprocessed user profile data, community service facility data, service process data, and environmental perception data onto pre-established service indicators under the service evaluation system, and calculates the score of the corresponding service indicator based on the mapping data corresponding to each service indicator; and an evaluation module for acquiring the weight of each service indicator, calculating the score of the target community by weighting the score of each service indicator and the weight, and determining the service evaluation result of the target community based on the score of the target community.

[0012] Optionally, the service ergonomics evaluation system includes first to fourth criterion layers, with each criterion layer containing multiple service indicators. The first criterion layer is the service safety layer, the second criterion layer is the service efficiency layer, the third criterion layer is the service user-friendliness layer, and the fourth criterion layer is the service ecology layer.

[0013] Optionally, the service indicators under the first criterion layer include the first, second, third, fourth, and fifth indicators, where the first indicator is service reliability, the second is service availability, the third is service risk predictability, the fourth is service emergency responsiveness, and the fifth is service traceability. The service indicators under the second criterion layer include the sixth, seventh, eighth, and ninth indicators, where the sixth is service adaptability, the seventh is service stability, the eighth is service simplicity, and the ninth is service economy. The service indicators under the third criterion layer include the tenth, eleventh, twelfth, and thirteenth indicators, where the tenth is service empathy, the eleventh is service inclusiveness, the twelfth is service personalization, and the thirteenth is service co-creation. The service indicators under the fourth criterion layer include the fourteenth, fifteenth, sixteenth, and seventeenth indicators, where the fourteenth is service interactivity, the fifteenth is service longevity, the sixteenth is service sustainability, and the seventeenth is service scalability.

[0014] Optionally, the evaluation module is further configured to: obtain the importance score between every two criterion layers, determine the weight of each criterion layer based on the importance score between every two criterion layers, perform consistency verification, and readjust the weight of the criterion layer if the verification fails, until the consistency verification passes; obtain the importance score between every two service indicators under the same criterion layer, determine the initial weight of the service indicator based on the importance score between every two service indicators, perform consistency verification, and readjust the initial weight of the service indicator if the verification fails, until the consistency verification passes; and determine the final weight of the service indicator based on the initial weight of the service indicator and the weight of the criterion layer to which it belongs.

[0015] Optionally, the evaluation module is further used to: generate a judgment matrix for the corresponding level based on the importance scores between every two service indicators; calculate the maximum eigenvalue of the judgment matrix and normalize the eigenvector corresponding to the maximum eigenvalue to obtain the initial weight of the corresponding service indicator.

[0016] Optionally, the processing steps of the large language model include: performing semantic analysis and / or semantic mapping on preprocessed user profile data, community service facility data, service process data, and environmental perception data to obtain multiple semantic information; extracting features from the semantic information to obtain multiple service features; determining the scores corresponding to the multiple service features based on preset quantification rules, converting the scores of the multiple service features into numerical features, and generating feature vectors corresponding to the multiple service features; calculating the semantic similarity between the multiple feature vectors, dividing the multiple features based on the semantic similarity to obtain multiple feature clusters; mapping the multiple feature clusters to corresponding service indicators using a target clustering algorithm, wherein the cluster centers of the target clustering algorithm are the multiple service indicators; and calculating the score of the service indicator based on the scores of the service features in the feature clusters corresponding to the service indicators.

[0017] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to perform the community service ergonomics evaluation method as described in the above embodiments.

[0018] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which is executed by a processor to perform the community service ergonomics evaluation method as described above.

[0019] The fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the community service ergonomics evaluation method as described in the above embodiments.

[0020] Therefore, this application has at least the following beneficial effects: This application embodiment can preprocess user profile data, community service facility data, service process data, and environmental perception data of the target community. The preprocessed data is then input into a pre-trained large language model. The large language model invokes a pre-established service ergonomics evaluation system, mapping the preprocessed data to pre-established service indicators within the evaluation system. Based on the mapped data for each service indicator, a score is calculated. This achieves the transformation from data to indicator scores using a large language model, improving service evaluation efficiency, avoiding inconsistencies in scoring due to differences in individual standards during manual scoring, and enhancing the objectivity and repeatability of the scores. Furthermore, based on the scores and weights of each service indicator, the target community's score is calculated, and the service evaluation result is determined based on the target community's score. This achieves automated evaluation of community services and improves the accuracy of the evaluation to a certain extent. Therefore, it solves the technical problems of long evaluation cycles, low efficiency, and low accuracy in related technologies.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a community service ergonomics evaluation method provided according to an embodiment of this application; Figure 2 A flowchart illustrating the ergonomic design of community services according to embodiments of this application; Figure 3 This is an example diagram of a community service ergonomics evaluation device provided according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] Before describing the solution of this application, let's first introduce the relevant terms and technologies involved in this application to help in understanding the solution of this application.

[0025] Ergonomics, also known as product ergonomics, is the study of the interaction between humans and products (including tools, equipment, and work environments). Its core purpose is to design and optimize work environments, tools, tasks, and systems to achieve optimal adaptation to human physiological, psychological, and cognitive abilities, thereby improving work efficiency, safety, and comfort, and reducing errors and accidents. Ergonomics' indicator system covers multiple dimensions, including safety, efficiency, and user comfort, aiming to optimize work systems and tools to better suit human needs, reduce fatigue, errors, and injuries, and improve work efficiency, user satisfaction, and quality of life. Through systematic design evaluation and optimization, ergonomics can help achieve the best match between humans and machines, enhancing the comfort and safety of human work and life.

[0026] In the context of industrial manufacturing, traditional ergonomics is widely used in fields such as industrial engineering, architecture and environment, product design, and information interaction. Current international and domestic ergonomics research generally employs a method based on the "human-machine-environment" system relationship, constructing a multi-level indicator system with "safety-efficiency-comfort" as the core principle, and conducting ergonomic quality evaluation accordingly. Traditional ergonomics is applicable and effective for tangible objects.

[0027] The rise of the service economy has shifted the mode of human labor from "material production" to "value co-creation," significantly increasing the frequency and complexity of interactions between people and service systems. This leads to a greater emphasis on emotional connections with users, interactive experiences during service processes, and the optimization of service workflows. For example, in traditional product design, ergonomics research typically focuses on improving the ease of use and safety of individual products (such as home appliances) through user interface design optimization. However, in community service design, ergonomics emphasizes the system optimization of the entire service process, encompassing multiple stages such as appointment scheduling, service delivery, and after-sales support, to enhance user experience and satisfaction throughout the entire process.

[0028] The following problems exist in the evaluation methods for community services in related technologies: (1) Low data processing efficiency.

[0029] The community service evaluation methods for related technologies mainly rely on manual methods such as questionnaires, interviews, and expert scoring. Faced with a large amount of service data from multiple dimensions and touchpoints (such as user health records, facility usage frequency, service response records, etc.), manual processing requires a lot of time and human resources, cannot achieve rapid calculation and real-time feedback, and has a long evaluation cycle and delayed updates.

[0030] (2) The evaluation results are not accurate enough and have large errors.

[0031] The related technologies lack unified quantitative algorithms and weighting mechanisms, and the subjective judgments of different evaluators vary greatly, resulting in discrete scoring results, poor repeatability, and the inability to form comparable historical data sequences. Manual statistics and experience-based judgments are also susceptible to cognitive biases, leading to high evaluation errors and making it difficult to accurately reflect the true level of service.

[0032] To this end, this application provides a community service evaluation method that uses an artificial intelligence large language model to evaluate community services, transforming the evaluation from a subjective, human-driven model to a data-driven, automated calculation model, thereby significantly improving the efficiency and accuracy of community service evaluation.

[0033] Specifically, Figure 1 This is a flowchart illustrating a community service ergonomics evaluation method provided in an embodiment of this application.

[0034] like Figure 1 As shown, the community service ergonomics evaluation method includes the following steps: In step S101, user profile data, community service facility data, service process data, and environmental perception data of the target community are acquired, and data preprocessing is performed on the user profile data, community service facility data, service process data, and environmental perception data.

[0035] The user profile data includes age, health status, activity level, perception level, and social participation; the community service facility data includes service facility type, usage frequency, equipment integrity rate, and spatial layout; the service process data includes service response time, task completion rate, interaction frequency, and user satisfaction; and the environmental perception data is collected through deployed sensors, including environmental noise, light, temperature, humidity, and air quality parameters.

[0036] The preprocessing steps in this application include cleaning, denoising, missing value completion, normalization, and timestamp standardization.

[0037] It should be noted that the community services in this application mainly refer to community services for the elderly.

[0038] In step S102, the preprocessed user profile data, community service facility data, service process data, and environmental perception data are input into the pre-trained large language model. The large language model calls the pre-established service ergonomics evaluation system and maps the preprocessed user profile data, community service facility data, service process data, and environmental perception data to the pre-established service indicators under the service evaluation system. The score of the corresponding service indicator is calculated based on the mapping data corresponding to each service indicator.

[0039] Among them, LLM (Large Language Model) is a large language model that is finely tuned based on community elderly care service corpus and human factors ergonomics knowledge; the preprocessed data includes structured data and unstructured data.

[0040] It is understood that, in the embodiments of this application, preprocessed user profile data, community service facility data, service process data, and environmental perception data can be input into a pre-trained large language model. The large language model calls a pre-established service ergonomics evaluation system to map the preprocessed user profile data, community service facility data, service process data, and environmental perception data onto pre-established service indicators under the service evaluation system, and calculates the score of the corresponding service indicator based on the mapping data corresponding to each service indicator.

[0041] In this embodiment, the processing steps of the large language model include: performing semantic analysis and / or semantic mapping on preprocessed user profile data, community service facility data, service process data, and environmental perception data to obtain multiple semantic information; extracting features from the semantic information to obtain multiple service features; determining the scores corresponding to the multiple service features based on preset quantization rules, converting the scores of the multiple service features into numerical features, and generating feature vectors corresponding to the multiple service features; calculating the semantic similarity between the multiple feature vectors, dividing the multiple service features based on the semantic similarity to obtain multiple feature clusters; mapping the multiple feature clusters to corresponding service indicators using a target clustering algorithm, wherein the cluster centers of the target clustering algorithm are the multiple service indicators; and calculating the score of the service indicator based on the scores of the service features in the feature clusters corresponding to the service indicators.

[0042] Among them, the target clustering algorithm can be semantic similarity clustering or K-means clustering, etc.

[0043] It is understood that the large language model in this application embodiment can perform semantic analysis on the preprocessed data, identify sentiment tendencies and key information, associate service indicators through semantic features, extract service features, convert service features into numerical features according to preset quantification rules, generate feature vectors, realize the structuring and quantification of unstructured data, further calculate the semantic similarity between feature vectors, use semantic similarity clustering or K-means clustering algorithms to divide feature vectors with high similarity into feature clusters, use service indicators as cluster centers, match feature clusters with the most similar cluster centers (service indicators), complete the mapping from feature clusters to service indicators, clarify the evaluation indicators corresponding to each feature cluster, and count the numerical features of all service features in the feature clusters corresponding to each service indicator. The final score of the indicator can be calculated using methods such as average value, weighted average value, etc. For example, the empathy indicator corresponds to 3 feature clusters with numerical features of 6, 7, and 5 respectively, and the average value is 6, that is, the indicator gets 6 points, realizing the transformation from service features to indicator scores.

[0044] This application embodiment eliminates the need for manual scoring of each service step. Through semantic processing, cluster analysis, and mapping of a large language model, it automatically completes the transformation from data to indicator scores, improving the efficiency of service evaluation. Furthermore, based on preset quantitative rules and clustering algorithms, it avoids inconsistencies in scoring caused by differences in personal standards during manual scoring, thereby enhancing the objectivity and repeatability of the scoring.

[0045] Specifically, the large language model processing procedure in this embodiment includes: LLM analyzes contextual information in service data through a self-attention mechanism to identify key behavioral patterns, service quality information, and potential risk signals (such as user emotional changes, device malfunctions, etc.). From the input multidimensional data, LLM extracts features related to various service indicators to form high-dimensional feature vectors. These features represent every detail of the service process (such as the interaction between service personnel and the elderly, the usage status of equipment, and the perceived comfort of the elderly). After feature extraction, LLM uses clustering algorithms (such as semantic similarity clustering, K-means clustering, etc.) to group the extracted features according to similarity and maps each feature cluster to 17 preset ergonomic indicators. Simultaneously, according to the Likert seven-point scoring system, the score of each indicator is quantified from 1 to 7.

[0046] For example, in this embodiment, the pre-processed voice recording of the bathing assistance service, such as "The bathing assistant says, 'Please get up slowly, I'll help you. If the water temperature isn't suitable, please let me know,'" and the elderly person responds, "That's fine, thank you," is input into a large language model. The model analyzes key information such as the bathing assistant proactively offering assistance, inquiring about water temperature, and using a gentle tone, as well as the elderly person's positive emotional response. Through semantic mapping, it correlates with empathy indicators, extracting four service features from the semantic information: proactive assistance, proactive inquiry about needs, gentle tone, and positive user feedback. According to quantification rules, proactive assistance with no negative feedback scores 7 points, proactive inquiry about needs scores 6 points, gentle tone scores 6 points, and positive user feedback scores 7 points. These service features are converted into numerical features of [7,6,6,7], generating a feature vector. The semantic similarity of this feature vector with other feature vectors is calculated. For example, the cosine similarity of the feature vector [6,7,6,6] with the feature vector showing the bathing assistant patiently helping the elderly person put on and take off clothes and the elderly person expressing satisfaction is 0.97, indicating high semantic similarity. These two are then grouped into a high-quality empathy service feature cluster.

[0047] Using service indicators such as empathy and inclusiveness as cluster centers, the similarity between the high-quality empathy service feature cluster and each cluster center was calculated. It was found that the similarity with the empathy indicator was the highest (0.95). This feature cluster was mapped to the empathy indicator. The average value of all numerical features in this feature cluster was calculated. (7+6+6+7+6+7+6+6) / 8=6.25. Based on rounding, we can take 6 points. Therefore, the final score of the empathy indicator is 6 points.

[0048] In this embodiment of the application, before inputting the pre-processed user profile data, community service facility data, service process data, and environmental perception data into the pre-trained large language model, the method further includes: acquiring service design data and human factors ergonomics data; and constructing a service ergonomics evaluation system based on the service design data and human factors ergonomics data.

[0049] The service ergonomics evaluation system includes four criterion layers, each containing multiple service indicators. The first criterion layer is the service safety layer, the second criterion layer is the service efficiency layer, the third criterion layer is the service user-friendliness layer, and the fourth criterion layer is the service ecology layer.

[0050] The service indicators under the first criterion layer include the first, second, third, fourth, and fifth indicators. The first indicator is service reliability, the second is service availability, the third is service risk predictability, the fourth is service emergency response capability, and the fifth is service traceability. The service indicators under the second criterion layer include the sixth, seventh, eighth, and ninth indicators. The sixth indicator is service adaptability, the seventh is service stability, the eighth is service simplicity, and the ninth is service economy. The service indicators under the third criterion layer include the tenth, eleventh, twelfth, and thirteenth indicators. The tenth indicator is service empathy, the eleventh is service inclusiveness, the twelfth is service personalization, and the thirteenth is service co-creation. The service indicators under the fourth criterion layer include the fourteenth, fifteenth, sixteenth, and seventeenth indicators. The fourteenth indicator is service interactivity, the fifteenth is service longevity, the sixteenth is service sustainability, and the seventeenth is service scalability.

[0051] Specifically, the construction process of the service ergonomics evaluation system for the community in this application embodiment is as follows: This study analyzes community-based aging-friendly services in detail from the perspective of the entire service process, and then constructs a community service ergonomics evaluation system. The process of providing community-based aging-friendly services is broken down into five interrelated observation and measurement points, such as... Figure 2 As shown.

[0052] (1) Service objectives. User needs directly affect the determination of design principles and service content. When designing community-based age-friendly services, we should first consider the characteristics of target users, such as their self-care ability, basic motor skills, mental state, perception ability and social participation ability, as well as the resulting physiological and psychological needs. At the same time, we should also consider the commonalities and differences in user characteristics. Therefore, we should determine targeted and precise service objectives for different elderly users in terms of daily care, medical care, spiritual life and emergency safety.

[0053] (2) Service touchpoints. The service touchpoints for age-friendly communities include service products / facilities, age-friendly service spaces / environments, and age-friendly service information. Among them, service products / facilities include transportation facilities, information interaction facilities, basic service equipment, etc.; service spaces / environments include residences, public areas, and service rooms, etc.; service information includes signage, interfaces, text, images, sound, video, etc.

[0054] (3) Service journey. The service journey is constructed based on the goals and service scenarios of community-based age-friendly services. The community-based age-friendly service journey includes service journey forms such as in-store services, door-to-door services, and online services.

[0055] (4) Service Scenarios. Community-based age-friendly service scenarios refer to the direct physical and social environments in which age-friendly services are provided. Community-based age-friendly service scenarios include community daily care service scenarios, community medical security service scenarios, community spiritual life service scenarios, community safety assistance service scenarios, and resident-commissioned consultation service scenarios, etc.

[0056] (5) Service delivery. The provision of service value is not manifested in tangible objects as the final form of delivery, but rather in the entire service process. Service design needs to focus on the tangibility, evidentiary nature, and traceability of service value delivery, and the value delivery design of community-based age-friendly services is particularly important.

[0057] Combining the community service design process and the principles of human factors engineering, a four-tiered indicator system for service ergonomics is constructed: the service safety layer, including indicators for service reliability, availability, risk prevention, emergency response, and traceability; the service efficiency layer, including indicators for service adaptability, stability, simplicity, and economy; the service human-centeredness layer, including indicators for service empathy, inclusiveness, personalization, and co-creation; and the service ecology layer, including indicators for service interactivity, longevity, greenness, and growth. The specific service evaluation system is shown in Table 1.

[0058]

[0059] In step S103, the weight of each service indicator is obtained, and the score of the target community is calculated by weighting the score of each service indicator with its weight. The service evaluation result of the target community is determined based on the score of the target community.

[0060] It is understood that the embodiments of this application can obtain the weight of each service indicator, calculate the score of the target community based on the score and weight of each service indicator, and determine the service evaluation result of the target community based on the score of the target community, so as to realize the automated evaluation of community services.

[0061] In this embodiment of the application, obtaining the weight of each service indicator includes: obtaining the importance score between every two criterion layers, determining the weight of each criterion layer based on the importance score between every two criterion layers, performing a consistency check, and readjusting the weight of the criterion layer if the check fails, until the consistency check passes; obtaining the importance score between every two service indicators under the same criterion layer, determining the initial weight of the service indicator based on the importance score between every two service indicators, performing a consistency check, and readjusting the initial weight of the service indicator if the check fails, until the consistency check passes; and determining the final weight of the service indicator based on the initial weight of the service indicator and the weight of the criterion layer to which it belongs.

[0062] The importance score can be obtained by collecting expert opinions using the Delphi method. Experts from relevant fields such as service design, ergonomics, and elderly care are selected to form an evaluation expert group. The group investigates the experts’ views on the importance of different service indicators in community-based aging services, establishes the importance of each indicator or criterion layer (pairwise comparison), and assigns a score (using a 1-9 scale to represent the relative importance between indicators). The hierarchical structure can include a target layer (1), a criterion layer (4), and an indicator layer (17).

[0063] It is understood that, in the embodiments of this application, the weight of each criterion layer can be determined based on the importance score between every two criterion layers, and the weight is checked for consistency. If the check fails, the weight is adjusted. After the weight of the criterion layer is determined, the importance score between every two service indicators at the same level is obtained. The initial weight of each service indicator is determined based on the importance score between every two service indicators, and the weight is checked for consistency. If the check fails, the initial weight is adjusted. After the initial weight is determined, the final weight of the service indicator is finally determined based on the initial weight of the service indicator and the weight of the criterion layer to which it belongs.

[0064] This application uses objective weighting to avoid biases caused by subjective human determination of weights, thereby improving the reliability of weights and thus enhancing the accuracy of community service assessment.

[0065] The consistency verification in this application embodiment can be performed using the consistency index (CR value). If the CR value is greater than a preset threshold, such as 0.1, the importance score is adjusted and re-evaluated to adjust the weight of the service indicator.

[0066] In this embodiment of the application, the initial weight of a service indicator is determined based on the importance score between every two service indicators, including: generating a judgment matrix for the corresponding level based on the importance score between every two service indicators; calculating the maximum eigenvalue of the judgment matrix and normalizing the eigenvector corresponding to the maximum eigenvalue to obtain the initial weight of the corresponding service indicator.

[0067] It is understood that, in the embodiments of this application, a judgment matrix corresponding to the level can be generated based on the importance score between each pair of service indicators, the maximum eigenvalue of the judgment matrix can be calculated, and the eigenvector corresponding to the maximum eigenvalue can be normalized to obtain the initial weight of the service indicator.

[0068] Similarly, the weights of the criterion layer in this application embodiment are also determined based on the same method.

[0069] Specifically, in this embodiment, the initial index weights can be determined using the analytic hierarchy process (AHP) and the Delphi method. Subsequently, the weight matrix is ​​calculated using YAAHP software, and a consistency ratio (CR) check is performed: when the CR value is greater than 0.1, inconsistent weights are corrected until the consistency requirements are met. The specific process includes: 1. Collect expert opinions using the Delphi method. Select experts from service design, ergonomics, and elderly care fields to form an evaluation expert group. Survey experts on the importance of different service ergonomic indicators in community-based age-friendly services, establish the importance of each indicator (compare pairs) and assign scores (using a 1-9 scale to represent the relative importance between indicators).

[0070] 2. Construct an AHP (Analytic Hierarchy Process) model. Determine the hierarchical structure design, including: Goal layer: Determine the ultimate goal (the overall ergonomic level of community-based age-friendly services); Criterion layer: Define the main criteria affecting the ergonomics of community-based age-friendly services (service safety, efficiency, human-centeredness, and ecological sustainability); Indicator layer: Each criterion can be further subdivided into specific indicators (17 specific indicators).

[0071] 3. Calculate the weights of each indicator using YAAHP software. Input the constructed hierarchical structure into YAAHP, including the target layer, criterion layer, and indicator layer, forming a complete evaluation indicator system. Input the importance evaluation scores of each indicator (pairwise comparison) from the expert group into YAAHP. YAAHP will automatically calculate the consistency index (CR value) using its built-in linear algebra calculation method to check the consistency of the pairwise comparison results. If the CR value is greater than 0.1, the comparison values ​​need to be adjusted and re-evaluated until consistency is achieved. After 10 rounds of comparison, YAAHP calculates the weights of each indicator based on the importance evaluation scores given by experts in each round, using its built-in linear algebra calculation method, and finally obtains the average weight value of each indicator.

[0072] For example, taking the three service metrics of the service security criteria layer as an example, including A. Reliability, B. Availability, and C. Risk Predictability, the importance scores for each pair of service metrics are as follows: Comparing A and B, you get 3 points; comparing A and C, you get 5 points; comparing B and C, you get 3 points.

[0073] 1. Construct a judgment matrix by comparing scores pairwise.

[0074] The judgment matrix is ​​a square matrix that compares the scores of all indicators pairwise within the same level. Rows and columns correspond to indicators, and matrix element a... ij Let represent the importance score of the i-th indicator compared to the j-th indicator. Then, the judgment matrix for the above three indicators is: The rows of the matrix from left to right correspond to A, B, and C, and the columns of the matrix from top to bottom correspond to A, B, and C.

[0075] 2. Calculate the initial weight for each service metric.

[0076] (1) Calculate the largest eigenvalue (λ) of the judgment matrix. max ) and the corresponding feature vector.

[0077] The largest eigenvalue λ of the above matrix can be calculated using mathematical algorithms (such as the sum-product method or the square root method). max ≈3.038, corresponding to an eigenvector of approximately [0.634, 0.286, 0.080] (this vector reflects the original values ​​of the relative importance of the three indicators). (2) Normalization is to make the sum of the weights of all indicators equal to 1. The sum of the elements of the above eigenvector is close to 1 (0.634+0.286+0.080=1.0). Therefore, the normalized indicator weights are: A weight = 0.634 (accounting for 63.4%); B weight = 0.286 (accounting for 28.6%); C weight = 0.080 (accounting for 8.0%).

[0078] 3. Consistency check.

[0079] Verification using CR value (CR=CI / RI, CI=(λ)). max -n) / (n-1), where n is the number of indicators, and RI is a built-in constant (RI=0.58 when n=3). CI = (3.038-3) / (3-1) = 0.019, CR = 0.019 / 0.58 ≈ 0.033 (< 0.1), thus passing the consistency check.

[0080] 4. Calculate the final weights.

[0081] If the weight of the security criteria layer for identification services is, for example, 0.6157, then the final weight of A is 0.6157×0.6157≈0.389, the final weight of B is 0.286×0.6157≈0.176, and the final weight of C is 0.080×0.6157≈0.049.

[0082] Furthermore, it should be noted that the score of the target community in this application embodiment includes the score of each criterion layer and the overall score, and is output to the community information management platform through a visual interface to realize trend analysis and historical tracking of the results.

[0083] The community assessment method of this application is described below through a specific embodiment, taking the assessment of age-friendly bathing services in the community as an example.

[0084] 1. Construction of an ergonomic indicator system for community-based age-friendly services.

[0085] This paper analyzes community-based age-friendly services from the perspective of the entire service process, and then constructs a community service ergonomics evaluation system. The process of providing community-based age-friendly services is broken down into five interrelated observation and measurement points. Combining the community service design process and ergonomics principles, a four-tiered indicator system for service ergonomics is constructed: Service Safety Layer, including indicators for service reliability, availability, risk prevention, emergency response, and traceability; Service Efficiency Layer, including indicators for service adaptability, stability, simplicity, and economy; Service Humanity Layer, including indicators for service empathy, inclusiveness, personalization, and co-creation; and Service Ecology Layer, including indicators for service interactivity, longevity, greenness, and growth. The evaluation system for the bathing service in this embodiment is shown in Table 2.

[0086]

[0087] 2. Data collection.

[0088] To support the calculation and analysis of the ergonomic index system for elderly bathing services, this embodiment establishes a multi-source heterogeneous data acquisition system, covering four dimensions: users, equipment, environment, and service process.

[0089] (1) User profile data collection. Supports indicators such as "personalization" and "adaptability". The collected content includes: age, gender, type of residence, mobility, chronic disease status, skin sensitivity, cognitive level, communication ability, service preferences, water temperature preferences, etc. Collection method: collected through the community elderly care management system and user terminal APP, and entered on-site by bathing assistants when necessary.

[0090] (2) Data collection on service facilities and equipment to support indicators such as "reliability", "availability", "risk preventability", "green sustainability" and "growth". The data collected includes: the integrity rate and usage frequency of shower chairs, hot water systems, anti-slip mats, and handrails, as well as energy consumption information and safety monitoring parameters. Data collection method: real-time data collection is conducted through IoT sensors installed in the bathroom, and the data is transmitted to the community cloud platform via the MQTT protocol.

[0091] (3) Service process data collection, supporting indicators such as "adaptability," "stability," "simplicity," "economy," "empathy," "inclusivity," "personalization," "co-creativity," "interactivity," "humanity," "long-term effectiveness," and "traceability." The collected content includes: appointment time, arrival time, start / end time of bathing assistance, task completion rate, caregiver operation log, interaction process between the bathing assistant and the elderly, abnormal event records, fee standards, and user satisfaction feedback. Collection methods: Automatically uploaded to the cloud platform via the bathing assistant's mobile terminal; user feedback is collected via tablet or voice assistant.

[0092] (4) Environmental perception data collection. Collection purpose: to support indicators such as "emergency responsiveness", "long-term effectiveness" and "growth". Collection content includes: temperature and humidity, air quality, noise, illuminance, slippery risk, fall risk score, etc. Collection method: deploy environmental sensor nodes for automatic collection, and transmit data back via Wi-Fi protocol. Key parameters are updated every 10 seconds.

[0093] 3. Data preprocessing.

[0094] To ensure the data quality of the input large model and AHP weight calculation, this embodiment performs the following preprocessing steps on the collected data: Data cleaning and denoising: Duplicate records and invalid values ​​are deleted; outliers are identified and marked using the IQR method; text noise from speech recognition is corrected semantically using the large model. Normalization: All indicator data are uniformly scaled to the [0,1] range. Timestamp standardization: UTC+8 timestamps are uniformly adopted, and Session_IDs are generated to aggregate data from the same service. Data structuring and labeling: Preprocessed data is stored in CSV+JSON format, and label fields for the criterion and indicator layers are added.

[0095] The standardized dataset is input into the LLM (Lifecycle Management Model), which has been fine-tuned using elderly care service corpus and ergonomics knowledge. The LLM processes this data and maps it to corresponding service ergonomics indicators through semantic understanding, feature extraction, and pattern clustering algorithms (each indicator uses a Likert seven-point scale scoring method, as shown in Table 3). For example, when "increased slipperiness index + increased abnormal event records" is identified, the "risk preventability" indicator score is automatically determined to have decreased; when voice interaction records show that the caregiver's tone is stable and user satisfaction is increased, the "empathy" indicator score is automatically increased. This step achieves automatic identification from raw data to indicator elements, significantly reducing statistical errors.

[0096]

[0097] 4. Steps for calculating indicator weights and verifying consistency.

[0098] The initial index weights were determined using the AHP and Delphi methods. The specific process included: First, the Delphi method was used to collect expert opinions. Experts from relevant fields such as service design, ergonomics, and elderly care were selected to form an evaluation expert group. The experts' views on the importance of different service ergonomic indicators in community-based aging-friendly services were investigated. The importance of each indicator (pairwise comparison) was established and scored (using a 1-9 scale to represent the relative importance between indicators), as shown in Tables 4-8. Table 4 shows the importance scores for pairwise comparisons at each criterion level; Table 5 shows the importance scores for each service indicator under the service safety criterion level; Table 6 shows the importance scores for each service indicator under the service efficiency criterion level; Table 7 shows the importance scores for each service indicator under the service pleasantness criterion level; and Table 8 shows the importance scores for each service indicator under the service ecology criterion level. A hierarchical analytic hierarchy process (AHP) model was constructed, and the hierarchical structure design was determined, including: the objective layer: determining the ultimate goal (the overall ergonomic level of community-based age-friendly services); the criteria layer: defining the main criteria affecting the ergonomics of community-based age-friendly services (service safety, efficiency, human-centeredness, and ecological sustainability); and the indicator layer: each criterion can be further subdivided into specific indicators (17 specific indicators). The weights of each indicator are calculated using the YAAHP software. The hierarchical structure, including the target layer, criterion layer, and indicator layer, is entered into YAAHP to form a complete evaluation indicator system. The importance evaluation scores of each indicator (pairwise comparisons) by the expert group are entered into YAAHP. YAAHP automatically calculates the consistency index (CR value) using its built-in linear algebra method to check the consistency of the pairwise comparison results. If the CR value is greater than 0.1, the comparison values ​​need to be adjusted and re-evaluated until consistency is achieved. After 10 rounds of comparison, YAAHP automatically calculates the weights of each indicator based on the importance evaluation scores given by the experts in each round, using its built-in linear algebra method, and finally obtains the average weight value of each indicator, as shown in Table 9.

[0099]

[0100]

[0101]

[0102]

[0103]

[0104]

[0105] 5. Comprehensive evaluation and result output.

[0106] By combining the Likert seven-point scale scores of each indicator, a comprehensive evaluation value is calculated using weighted summation, and a service ergonomics evaluation report is generated. The evaluation results include the scores of each criterion level and the overall score, enabling trend analysis and historical tracking of the results.

[0107] In summary, this application combines artificial intelligence large-scale model analysis, AHP (Analytic Hierarchy Process), and Delphi method to achieve rapid, accurate, dynamic, and traceable assessment of community service levels, significantly reducing manual statistical errors and improving assessment efficiency and consistency.

[0108] Specifically, at the data level, this application achieves automatic collection and standardized processing of multi-source heterogeneous data such as user profiles, community service facilities, and service processes, minimizing manual input and statistical errors; at the algorithm level, it utilizes the semantic analysis and pattern recognition capabilities of large language models to automatically identify key factors affecting ergonomics during the service process, thereby optimizing the structure of the indicator system; at the evaluation level, it improves the stability and consistency of indicator weight calculation through a weight determination mechanism combining AHP and the Delphi method.

[0109] According to the community service ergonomics evaluation method proposed in this application, user profile data, community service facility data, service process data, and environmental perception data of the target community can be preprocessed. The preprocessed data is then input into a pre-trained large language model. The large language model calls a pre-established service ergonomics evaluation system, mapping the preprocessed data to pre-established service indicators under the service evaluation system. Based on the mapping data corresponding to each service indicator, a score for that service indicator is calculated. This achieves the transformation from data to indicator scores using a large language model, improving service evaluation efficiency, avoiding inconsistencies in scoring due to differences in individual standards during manual scoring, and enhancing the objectivity and repeatability of the scoring. Furthermore, based on the score and weight of each service indicator, the score of the target community is calculated, and the service evaluation result of the target community is determined based on the target community's score. This achieves automated evaluation of community services and, to a certain extent, improves the accuracy of the evaluation.

[0110] Next, the community service ergonomics evaluation device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0111] Figure 3 This is a block diagram of a community service ergonomics evaluation device according to an embodiment of this application.

[0112] like Figure 3 As shown, the community service ergonomics assessment device 10 includes: an acquisition module 100, an input module 200, and an assessment module 300.

[0113] The acquisition module 100 is used to acquire user profile data, community service facility data, service process data, and environmental perception data of the target community, and to preprocess the user profile data, community service facility data, service process data, and environmental perception data. The input module 200 is used to input the preprocessed user profile data, community service facility data, service process data, and environmental perception data into a pre-trained large language model. The large language model calls a pre-established service ergonomics evaluation system to map the preprocessed user profile data, community service facility data, service process data, and environmental perception data to pre-established service indicators under the service evaluation system, and calculates the score of the corresponding service indicator based on the mapping data corresponding to each service indicator. The evaluation module 300 is used to acquire the weight of each service indicator, calculate the score of the target community based on the score and weight of each service indicator, and determine the server evaluation result of the target community based on the score of the target community.

[0114] In this embodiment of the application, the service ergonomics evaluation system includes a first to a fourth criterion layer, with each criterion layer including multiple service indicators. The first criterion layer is the service security layer, the second criterion layer is the service efficiency layer, the third criterion layer is the service user-friendliness layer, and the fourth criterion layer is the service ecology layer.

[0115] In this embodiment, the service indicators under the first quasi-testing layer include a first indicator, a second indicator, a third indicator, a fourth indicator, and a fifth indicator. The first indicator is service reliability, the second indicator is service availability, the third indicator is service risk predictability, the fourth indicator is service emergency responsiveness, and the fifth indicator is service traceability. The service indicators under the second quasi-testing layer include a sixth indicator, a seventh indicator, an eighth indicator, and a ninth indicator. The sixth indicator is service adaptability, the seventh indicator is service stability, the eighth indicator is service simplicity, and the ninth indicator is service economy. The service indicators under the third criterion layer include a tenth indicator, an eleventh indicator, a twelfth indicator, and a thirteenth indicator. The tenth indicator is service empathy, the eleventh indicator is service inclusiveness, the twelfth indicator is service personalization, and the thirteenth indicator is service co-creation. The service indicators under the fourth criterion layer include a fourteenth indicator, a fifteenth indicator, a sixteenth indicator, and a seventeenth indicator. The fourteenth indicator is service interactivity, the fifteenth indicator is service longevity, the sixteenth indicator is service greenness, and the seventeenth indicator is service scalability.

[0116] In this embodiment of the application, the evaluation module 300 is further configured to: obtain the importance score between every two criterion layers, determine the weight of each criterion layer based on the importance score between every two criterion layers, perform a consistency check, and if the check fails, readjust the weight of the criterion layer until the consistency check passes; obtain the importance score between every two service indicators under the same criterion layer, determine the initial weight of the service indicator based on the importance score between every two service indicators, perform a consistency check, and if the check fails, readjust the initial weight of the service indicator until the consistency check passes; and determine the final weight of the service indicator based on the initial weight of the service indicator and the weight of the criterion layer to which it belongs.

[0117] In this embodiment of the application, the evaluation module 300 is further configured to: generate a judgment matrix of the corresponding level based on the importance score between each pair of service indicators; calculate the maximum eigenvalue of the judgment matrix and normalize the eigenvector corresponding to the maximum eigenvalue to obtain the initial weight of the corresponding service indicator.

[0118] In this embodiment, the processing steps of the large language model include: performing semantic analysis and / or semantic mapping on preprocessed user profile data, community service facility data, service process data, and environmental perception data to obtain multiple semantic information; extracting features from the semantic information to obtain multiple service features; determining the scores corresponding to the multiple service features based on preset quantization rules, converting the scores of the multiple service features into numerical features, and generating feature vectors corresponding to the multiple service features; calculating the semantic similarity between the multiple feature vectors, dividing the multiple service features based on the semantic similarity to obtain multiple feature clusters; mapping the multiple feature clusters to corresponding service indicators using a target clustering algorithm, wherein the cluster centers of the target clustering algorithm are the multiple service indicators; and calculating the score of the service indicator based on the scores of the service features in the feature clusters corresponding to the service indicators.

[0119] It should be noted that the foregoing explanation of the community service ergonomics evaluation method embodiment also applies to the community service ergonomics evaluation device of this embodiment, and will not be repeated here.

[0120] The community service ergonomics evaluation device proposed in this application can preprocess user profile data, community service facility data, service process data, and environmental perception data of the target community. The preprocessed data is then input into a pre-trained large language model. The large language model invokes a pre-established service ergonomics evaluation system, mapping the preprocessed data to pre-established service indicators within the evaluation system. Based on the mapping data for each service indicator, a score is calculated for that indicator. This utilizes the large language model to transform data into indicator scores, improving service evaluation efficiency, avoiding inconsistencies in scoring due to differences in individual standards during manual scoring, and enhancing the objectivity and repeatability of the scores. Furthermore, the target community's score is calculated based on the score and weight of each service indicator, and the service evaluation result is determined based on the target community's score. This achieves automated evaluation of community services and improves the accuracy of the evaluation to a certain extent.

[0121] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0122] When the processor 402 executes the program, it implements the community service ergonomics evaluation method provided in the above embodiments.

[0123] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0124] The memory 401 is used to store computer programs that can run on the processor 402.

[0125] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0126] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0127] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0128] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0129] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the above-described community service ergonomics evaluation method.

[0130] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the above-mentioned community service ergonomics evaluation method.

[0131] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0132] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0133] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0134] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0135] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

Claims

1. A method for evaluating the ergonomics of community services, characterized in that, Includes the following steps: Acquire user profile data, community service facility data, service process data, and environmental perception data of the target community, and perform data preprocessing on the user profile data, community service facility data, service process data, and environmental perception data; The preprocessed user profile data, community service facility data, service process data, and environmental perception data are input into a pre-trained large language model. The large language model calls a pre-established service ergonomics evaluation system to map the preprocessed user profile data, community service facility data, service process data, and environmental perception data onto pre-established service indicators under the service evaluation system. The score of the corresponding service indicator is calculated based on the mapping data corresponding to each service indicator. Obtain the weight of each service indicator, calculate the score of the target community based on the score of each service indicator and its weight, and determine the service evaluation result of the target community based on the score of the target community.

2. The community service ergonomics evaluation method according to claim 1, characterized in that, The service ergonomics evaluation system includes first to fourth criterion layers, with multiple service indicators under each criterion layer. The first criterion layer is the service safety layer, the second criterion layer is the service efficiency layer, the third criterion layer is the service user-friendliness layer, and the fourth criterion layer is the service ecology layer.

3. The community service ergonomics evaluation method according to claim 2, characterized in that, The service metrics under the first quasi-testing layer include a first metric, a second metric, a third metric, a fourth metric, and a fifth metric. The first metric is service reliability, the second metric is service availability, the third metric is service risk predictability, the fourth metric is service emergency response capability, and the fifth metric is service traceability. The service metrics under the second quasi-testing layer include the sixth, seventh, eighth, and ninth metrics. The sixth metric is service adaptability, the seventh metric is service stability, the eighth metric is service simplicity, and the ninth metric is service economy. The service indicators under the third criterion layer include the tenth, eleventh, twelfth and thirteenth indicators. The tenth indicator is service empathy, the eleventh indicator is service inclusiveness, the twelfth indicator is service personalization, and the thirteenth indicator is service co-creation. The service indicators under the fourth criterion layer include the fourteenth, fifteenth, sixteenth, and seventeenth indicators. The fourteenth indicator is service interactivity, the fifteenth indicator is service longevity, the sixteenth indicator is service greenness, and the seventeenth indicator is service scalability.

4. The community service ergonomics evaluation method according to claim 3, characterized in that, The process of obtaining the weight of each service metric includes: Obtain the importance score between every two criterion layers, determine the weight of each criterion layer based on the importance score between every two criterion layers, perform a consistency check, and if the check fails, readjust the weight of the criterion layer until the consistency check passes; Obtain the importance score of every two service indicators under the same criterion layer, determine the initial weight of the service indicator based on the importance score between every two service indicators, perform a consistency check, and if the check fails, readjust the initial weight of the service indicator until the consistency check passes. The final weight of the service indicator is determined based on its initial weight and the weight of the criterion layer to which it belongs.

5. The community service ergonomics evaluation method according to claim 4, characterized in that, The determination of the initial weight of the service indicator based on the importance score between every two service indicators includes: A judgment matrix for the corresponding level is generated based on the importance score between each pair of service indicators; Calculate the largest eigenvalue of the judgment matrix, and normalize the eigenvector corresponding to the largest eigenvalue to obtain the initial weight of the corresponding service indicator.

6. The community service ergonomics evaluation method according to claim 1, characterized in that, The processing steps of the large language model include: Semantic analysis and / or semantic mapping are performed on the preprocessed user profile data, community service facility data, service process data, and environmental perception data to obtain multiple semantic information. Feature extraction is performed on the semantic information to obtain multiple service features; The scores corresponding to the multiple service features are determined based on preset quantization rules, the scores of the multiple service features are converted into numerical features, and feature vectors corresponding to the multiple service features are generated. Calculate the semantic similarity between the multiple feature vectors, and divide the multiple service features based on the semantic similarity to obtain multiple feature clusters; The multiple feature clusters are mapped to corresponding service metrics using a target clustering algorithm, wherein the cluster centers of the target clustering algorithm are the multiple service metrics; The score of the service indicator is calculated based on the scores of the service features in the feature cluster corresponding to the service indicator.

7. A community service ergonomics evaluation device, characterized in that, include: The acquisition module is used to acquire user profile data, community service facility data, service process data, and environmental perception data of the target community, and to perform data preprocessing on the user profile data, community service facility data, service process data, and environmental perception data. The input module is used to input the pre-processed user profile data, community service facility data, service process data, and environmental perception data into a pre-trained large language model. The large language model calls a pre-established service ergonomics evaluation system to map the pre-processed user profile data, community service facility data, service process data, and environmental perception data to pre-established service indicators under the service evaluation system, and calculates the score of the corresponding service indicator based on the mapping data corresponding to each service indicator. The evaluation module is used to obtain the weight of each service indicator, calculate the score of the target community based on the score of each service indicator and the weight, and determine the service evaluation result of the target community based on the score of the target community.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the community service ergonomics evaluation method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, The computer program or instructions are executed by a processor to implement the community service ergonomics evaluation method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed, they implement the community service ergonomics evaluation method as described in any one of claims 1-6.

Images