Home-based elderly care service matching processing method based on machine learning and related equipment

Abstract

The application belongs to the field of medical health, and provides a home-based care service matching processing method and device based on machine learning and related equipment, in order to solve the problem of low matching efficiency of home-based care services in traditional technologies, by data fusion of health status information data, self-care ability information data, living state information data and mental health information data in different dimensions, determining the user portrait and customer category corresponding to the home-based care customer according to the fused data, then based on the preset prediction model of machine learning, and according to the user portrait and customer category, predicting the home-based care service demand corresponding to the home-based care customer, finally determining the target home-based care service project corresponding to the home-based care service demand, and matching the target home-based care service project to the home-based care customer, realizing the improvement of the accuracy of home-based care service matching according to the multi-dimensional information of the home-based care customer and based on the prediction of machine learning.

Description

Technical Field

[0001] This application relates to the field of healthcare, and in particular to a method, apparatus, computer equipment, and computer-readable storage medium for matching and processing home-based elderly care services based on machine learning. Background Technology

[0002] More and more elderly people are aging at home, and the most prominent issue is how to match the supply of elderly care services with the diverse needs of the elderly population.

[0003] For the elderly, home-based aging requires more than just basic daily care; they crave personalized care and respect. However, the reality is that a significant gap exists between service supply and demand. The needs of elderly people in different situations vary greatly. For example, some require professional medical care, some crave emotional support, and others wish to continue participating in social activities. This diversity presents a considerable challenge to the provision of elderly care services.

[0004] Traditional techniques typically involve manually following up with elderly individuals to understand their individual needs. However, this method is extremely labor-intensive and resource-intensive, and inefficient. Furthermore, there is a lack of effective technological means to automatically and accurately match the individual needs of the elderly with the available services. This not only affects the quality of life of the elderly but also hinders the effective development of the elderly care service industry.

[0005] Therefore, how to use technological means to accurately predict the personalized needs of the elderly and automatically provide precise matching of elderly care services has become an urgent technical problem to be solved in the elderly care service industry. Summary of the Invention

[0006] This application provides a method, apparatus, computer equipment, and computer-readable storage medium for matching home-based elderly care services based on machine learning, which can solve the technical problem of low matching efficiency of home-based elderly care services in traditional technologies.

[0007] Firstly, this application provides a machine learning-based method for matching home-based elderly care services, comprising: acquiring physical and mental health information data of home-based elderly care clients from different dimensions, the physical and mental health information data including health status information data, self-care ability information data, living status information data, and mental health information data; fusing the health status information data, the self-care ability information data, the living status information data, and the mental health information data to obtain fused data; determining a user profile corresponding to the home-based elderly care client based on the fused data; determining a client category corresponding to the home-based elderly care client based on the user profile; predicting the home-based elderly care service needs corresponding to the home-based elderly care client based on a preset prediction model of machine learning and the user profile and the client category; matching target home-based elderly care service projects corresponding to the home-based elderly care service needs based on a preset home-based elderly care service project database, and matching the target home-based elderly care service projects to the home-based elderly care client.

[0008] Secondly, this application provides a machine learning-based home care service matching and processing device, comprising: a first acquisition unit, used to acquire physical and mental health information data of home care customers in different dimensions, the physical and mental health information data including health status information data, self-care ability information data, living status information data, and mental health information data; a data fusion unit, used to fuse the health status information data, the self-care ability information data, the living status information data, and the mental health information data to obtain fused data; a first determination unit, used to determine the user profile corresponding to the home care customer based on the fused data; a second determination unit, used to determine the customer category corresponding to the home care customer based on the user profile; a first prediction unit, used to predict the home care service needs corresponding to the home care customer based on a preset prediction model of machine learning and the user profile and the customer category; and a first matching unit, used to match the target home care service project corresponding to the home care service needs based on a preset home care service project database, and match the target home care service project to the home care customer.

[0009] Thirdly, this application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the machine learning-based home care service matching processing method.

[0010] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the machine learning-based home care service matching processing method.

[0011] This application provides a method, apparatus, computer device, and computer-readable storage medium for matching home-based elderly care services based on machine learning. The method acquires physical and mental health information data from different dimensions of home-based elderly care clients, fuses this data, determines the user profile and client category based on the fused data, then predicts the corresponding home-based elderly care service needs based on a pre-set prediction model using machine learning, and finally determines the target home-based elderly care service projects corresponding to these needs. This matching of target home-based elderly care service projects to home-based elderly care clients improves the accuracy of home-based elderly care service matching, thereby enhancing the quality and efficiency of home-based elderly care services. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating the machine learning-based home care service matching method provided in this application embodiment;

[0014] Figure 2 A schematic diagram of the first sub-process of the home-based elderly care service matching and processing method based on machine learning provided in the embodiments of this application;

[0015] Figure 3 A schematic diagram of the second sub-process of the home-based elderly care service matching and processing method based on machine learning provided in the embodiments of this application;

[0016] Figure 4 A schematic block diagram of a home-based elderly care service matching and processing device based on machine learning provided in an embodiment of this application;

[0017] Figure 5 A schematic block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0020] This application provides a machine learning-based method for matching home-based elderly care services. The method can be applied to computer devices including but not limited to smartphones, tablets, laptops, desktop computers, and servers, and can be used in elderly care service matching for the elderly in fields including but not limited to the medical and health field.

[0021] To address the technical problem of low matching efficiency in traditional home-based elderly care services, the inventors propose a machine learning-based home-based elderly care service matching method according to embodiments of this application. The core idea of ​​this application is to utilize data fusion technology to comprehensively consider five dimensions of elderly people living at home: age, health status, self-care ability, living conditions, and psychological and emotional state, forming a comprehensive user profile and classifying customers. Then, based on a machine learning prediction model, the service needs of elderly people living at home are predicted according to customer categories, and these service needs are pushed to them through various media. This method can group elderly people based on their corresponding customer tags, enabling personalized service recommendations and improving the accuracy of home-based elderly care service matching, thereby improving the quality and efficiency of home-based elderly care services.

[0022] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0023] Please see Figure 1 , Figure 1 This is a flowchart illustrating the machine learning-based home-based elderly care service matching method provided in an embodiment of this application. Figure 1 As shown, the method includes, but is not limited to, the following steps S11-S16:

[0024] S11. Obtain physical and mental health information data of home-based elderly care customers from different dimensions, including health status information data, self-care ability information data, living status information data, and mental health information data.

[0025] Interpretatively, home-based elderly care clients have needs in both physical care and psychological and emotional support. Therefore, it is necessary to assess the physical and mental health status of these clients and quantify this status into specific information. This involves obtaining physical and mental health data from different dimensions, including health status, self-care ability, living situation, and mental health. Specifically, health status data indicates whether the client has any physical or pathological illnesses; self-care ability data indicates whether the client is able to live independently; living situation data indicates whether the client lives alone or with family members; and mental health data indicates the client's psychological, mental, and emotional state.

[0026] S12. The health status information data, the self-care ability information data, the living status information data, and the mental health information data are fused to obtain fused data.

[0027] Explained, data fusion refers to transforming data from different sources, formats, structures, and types into a unified format, structure, and type, merging multiple data sets and mapping them to a unified dataset. Data fusion includes, but is not limited to, data preprocessing and data cleaning. Its purpose is to improve the uniformity, completeness, accuracy, and usability of data by integrating diverse data. Data fusion methods include, but are not limited to, ETL (Extract, Transform, Load) processes, data integration and federation, data mining, and machine learning. ETL involves extracting data from different data sources, transforming the data into a unified format or structure, and finally loading it into the target system. Data integration and federation integrates data from multiple data sources into a unified data model, enabling the data to be queried and analyzed together. Data mining and machine learning techniques use data mining and machine learning algorithms to perform data fusion, identify patterns and relationships, and generate higher-quality fused data.

[0028] Based on the above concept and description, health status information, self-care ability information, living status information, and mental health information from different sources, formats, structures, and dimensions are fused to obtain fused data. This facilitates comprehensive processing and analysis of the fused data, resulting in the most accurate possible information on the physical and mental health of home-based elderly care clients across different dimensions, thereby improving the accuracy of matching home-based elderly care services.

[0029] S13. Based on the fused data, determine the user profile corresponding to the home-based elderly care customer.

[0030] Explained, user personas, also known as user roles or customer profiles, are the process of collecting and analyzing users' personal information and behavioral data from different dimensions to divide users into different groups and to describe and analyze each group in detail.

[0031] Based on the above concept and description, and by integrating data and information from different dimensions, we determine the user profiles of home-based elderly care customers. The content of the user profiles includes, but is not limited to, specific information on health status, self-care ability, living conditions, and mental health.

[0032] S14. Based on the user profile, determine the customer category corresponding to the home-based elderly care customer.

[0033] Explained, based on user profiles, unsupervised aggregation algorithms including but not limited to K-Means, Mini-Batch K-Means, Affinity Propagation, and Mean Shift are used to determine the customer categories corresponding to home-based elderly care customers. Customer categories include but are not limited to health categories, disability categories, and dementia categories. Here, user profiles are multi-dimensional tag representations of users, and customer categories are category representations of comprehensive customer content.

[0034] For example, when using an unsupervised aggregation algorithm to determine the customer category corresponding to home-based elderly care customers, the user profile data is mapped to a high-dimensional coordinate system scatter plot based on the user profile. Groups of people that are close to each other are aggregated into one group. The density of core points within the group needs to reach the threshold set by the algorithm, and the radius is iterated using Euclidean distance as the calculation method to determine the customer category corresponding to home-based elderly care customers.

[0035] S15. Based on a preset prediction model using machine learning, and according to the user profile and the customer category, predict the home-based elderly care service needs corresponding to the home-based elderly care customer.

[0036] Explained, a pre-set prediction model, also known as a preset prediction model, is a model that predicts the home-based elderly care service needs of home-based elderly care customers based on user profiles and customer categories. Pre-set prediction models include, but are not limited to, neural network models, such as BP (back propagation) neural networks.

[0037] Based on the above concept and setup, a pre-set prediction model based on machine learning is used to predict the home-based elderly care service needs of home-based elderly care customers according to user profiles and customer categories. The home-based elderly care service needs include, but are not limited to, medical care, food, housing, transportation, rehabilitation, elderly care, entertainment, and nursing care.

[0038] S16. Based on a preset home-based elderly care service project database, match the target home-based elderly care service project corresponding to the home-based elderly care service demand, and match the target home-based elderly care service project to the home-based elderly care customer.

[0039] Explained, based on a pre-set database of home-based elderly care service projects, and according to the home-based elderly care service needs of the clients, the system automatically matches target home-based elderly care service projects corresponding to the needs. The target home-based elderly care service projects can be project plans, which represent a collection of services including but not limited to medical care, food, housing, transportation, rehabilitation, elderly care, entertainment, and nursing. This allows for the customization of elderly care services for home-based elderly care clients, and the matching of target home-based elderly care service projects to these clients, thus achieving personalized service recommendations.

[0040] This application embodiment acquires physical and mental health information data from home-based elderly care clients across different dimensions, and integrates this data, including health status, self-care ability, living conditions, and mental health information. Based on the integrated data, it determines the user profile and client category corresponding to each home-based elderly care client. Then, based on a pre-set prediction model using machine learning, it predicts the corresponding home-based elderly care service needs of each client according to their user profile and client category. Finally, it identifies the target home-based elderly care service projects corresponding to these needs and matches them to the clients. This approach categorizes home-based elderly care clients based on their multi-dimensional information, and then, based on their user profiles and client categories, and using a pre-set prediction model using machine learning, provides personalized service recommendations, improving the accuracy of home-based elderly care service matching and thus enhancing the quality and efficiency of home-based elderly care services.

[0041] In one embodiment, acquiring physical and mental health information data of home-based elderly care customers from different dimensions includes:

[0042] Determine the medical information of home-based elderly care clients;

[0043] Based on a pre-set wearable smart device, obtain the health information of the home-based elderly care customer;

[0044] Based on the medical information and the health information, the health status of the home-based elderly care customers is classified to obtain the health status information data of the home-based elderly care customers.

[0045] Explained, with permission from relevant institutions or personnel, medical information of home-based elderly care clients is obtained. This medical information includes, but is not limited to, physical examination reports, test reports, prescriptions, medications, and medical records. Based on pre-set wearable smart devices, including but not limited to smartwatches, smart gloves, and smart bracelets, health information of home-based elderly care clients is collected and obtained. This health information includes, but is not limited to, health indicators such as heart rate, blood pressure, blood sugar, uric acid, blood oxygen saturation, body temperature, stress, mood, sleep, exercise, and diet. Then, based on the medical and health information, and using machine learning, the health status of home-based elderly care clients is automatically determined, thereby classifying their health status and obtaining health status information data, including but not limited to healthy, mild illness, serious illness, and disability.

[0046] This application embodiment determines the medical and health information of home-based elderly care clients and classifies their health status based on this information. It can assess the health status of home-based elderly care clients based on information from multiple dimensions, thereby obtaining more accurate health status data. Furthermore, based on the multi-dimensional information of home-based elderly care clients, it can improve the accuracy of matching home-based elderly care services, thereby improving the quality and efficiency of home-based elderly care services.

[0047] In one embodiment, determining the medical information of home-based elderly care clients includes:

[0048] Obtain medical image data of home-based elderly care clients;

[0049] Based on a preset OCR recognition method, the medical image data is recognized to obtain the medical text data of the home-based elderly care customer;

[0050] The medical text data is structured and the preset target medical content is extracted to obtain the medical information of the home-based elderly care customer.

[0051] Explained, medical information refers to information related to medical treatment and testing for home-based elderly care clients, such as physical examinations, medical visits, and other medical procedures. In many cases, this information is in image format. Therefore, the medical image data of home-based elderly care clients is acquired, and based on a preset OCR recognition method, the medical image data is recognized and converted into text to obtain the medical text data of home-based elderly care clients. Then, various medical text data with inconsistent formats are subjected to unified structural processing, and preset target medical content is extracted accordingly, such as extracting relevant attributes such as disease, medication, abnormal indicators, surgery, onset time, and current control status, to obtain the medical information of home-based elderly care clients.

[0052] This application embodiment identifies medical image data based on a preset OCR recognition method and performs structured processing on medical text data. This allows for the acquisition of medical information of home-based elderly care clients based on a standardized data format. It can combine multiple medical data to obtain multi-dimensional medical information of home-based elderly care clients, resulting in a more accurate medical status. Furthermore, it assesses the health status of home-based elderly care clients based on multi-dimensional information, improving the accuracy of home-based elderly care service matching and thus enhancing the quality and efficiency of home-based elderly care services.

[0053] Please see Figure 2 , Figure 2 This is a schematic diagram of the first sub-process of the machine learning-based home-based elderly care service matching method provided in an embodiment of this application. Figure 2 As shown, in this embodiment, acquiring physical and mental health information data of home-based elderly care customers from different dimensions includes:

[0054] S21. Collect behavioral images of home-based elderly care customers based on preset home cameras;

[0055] S22. Based on IoT communication, acquire the behavior image, and based on a preset cross-modal learning model, identify the behavior image to obtain behavior information text;

[0056] S23. Based on a preset smart client terminal, obtain the voice recording of the call with the home-based elderly care customer;

[0057] S24. Based on a preset automatic speech recognition model, identify the text corresponding to the speech in the call;

[0058] S25. Based on the medical text data, the behavioral information text, and the call text, determine the self-care ability information data of the home-based elderly care customer.

[0059] Explained, a pre-set cross-modal learning model, i.e. a preset cross-modal learning model, represents a model that learns from data in one modality and applies its knowledge to data in another modality. Cross-modal learning includes, but is not limited to, learning from image data for text generation. Pre-set cross-modal learning models include, but are not limited to, Transformer models, combinations of convolutional neural networks (CNN) and recurrent neural networks (RNN), and cross-modal contrastive learning.

[0060] Pre-setting an automatic speech recognition model, also known as a preset automatic speech recognition model, is a technology that converts human speech into text.

[0061] Based on the above concept and setup, with the popularization and development of the Internet of Things and video surveillance, it is relatively convenient to collect and obtain relevant information about home-based elderly care customers through video surveillance, with the permission of relevant institutions or personnel. This information can then be used to analyze the status of home-based elderly care customers and provide them with targeted services. Therefore, based on preset home cameras, behavioral images of home-based elderly care customers are collected. These images are then acquired through IoT communication, and cross-modal learning is used to recognize the behavioral images, resulting in behavioral information text. This behavioral information text represents textual information describing the behavior of home-based elderly care customers based on the behavioral images. Simultaneously, based on preset smart client terminals (including but not limited to video surveillance, smartphones, smart bracelets, smartwatches, smart speakers, and smart home devices), the voice messages corresponding to conversations with home-based elderly care customers are acquired. Furthermore, based on a preset automatic speech recognition model, the corresponding text messages are recognized. Then, based on the aforementioned medical text data, behavioral information text, and conversation text, information including but not limited to daily living activities, social participation, basic motor skills, and cognitive abilities of home-based elderly care customers is extracted to obtain self-care ability data.

[0062] This application embodiment collects behavioral images and voice recordings of home-based elderly care clients. Based on IoT communication, it obtains behavioral information text and voice recordings, and then uses these to obtain self-care ability information data of the home-based elderly care clients. Combining this self-care ability information data with IoT devices and IoT technology, and based on ASR technology, it can monitor the behavior of home-based elderly care clients in real time. This enables real-time assessment of the health status of home-based elderly care clients based on multi-dimensional information, and adjustments to the matching of home-based elderly care services, further improving the accuracy of home-based elderly care service matching, thereby improving the quality and efficiency of home-based elderly care services.

[0063] Please see Figure 3 , Figure 3 This is a schematic diagram of the second sub-process of the machine learning-based home-based elderly care service matching method provided in the embodiments of this application. Figure 3 As shown, in this embodiment, acquiring physical and mental health information data of home-based elderly care customers from different dimensions includes:

[0064] S31. Based on a preset home camera, collect facial expression images of elderly people living at home;

[0065] S32. Acquire the facial expression image based on Internet of Things (IoT) communication;

[0066] S33. Based on a preset artificial intelligence recognition model, the facial expression image is recognized to obtain the mental health information data of the home-based elderly care customer.

[0067] Explained, a pre-set artificial intelligence recognition model, also known as a preset artificial intelligence recognition model or AI intelligent recognition, refers to an artificial intelligence model that identifies the relationship between facial expressions and mental health status. Pre-set artificial intelligence recognition models include, but are not limited to, DeepFace, VGGFace, OpenFace, and other models.

[0068] Based on the aforementioned preset home cameras, in addition to obtaining behavioral information text, it is also possible to collect facial expression images of home-based elderly care customers based on the preset home cameras, and obtain facial expression images based on Internet of Things communication. Since facial expressions are related to a person's psychology, spirit, and emotions, based on the preset artificial intelligence recognition model, the facial expression images are recognized to obtain mental health information data of home-based elderly care customers. Mental health information data includes, but is not limited to, information data such as mental health status, mental health status, and emotional status.

[0069] This application embodiment collects facial expression images of home-based elderly care clients based on a preset home camera, acquires these images via IoT communication, and then identifies them using a preset artificial intelligence recognition model to obtain mental health information data of the home-based elderly care clients. This combination of IoT and AI enables real-time monitoring of the mental health status of home-based elderly care clients, allowing for real-time assessment of their health status based on multi-dimensional information and adjustment of home-based elderly care service matching. This further improves the accuracy of home-based elderly care service matching, thereby enhancing the quality and efficiency of home-based elderly care services.

[0070] In one embodiment, the user profile includes several customer physical and mental health information features; based on the user profile, the customer category corresponding to the home-based elderly care customer is determined, including:

[0071] Based on the preset Multiple Hot encoding method, all customer physical and mental health information features are encoded into the same feature to obtain a unified encoded feature;

[0072] Based on a preset feature embedding method, the unified coded features are mapped from high-dimensional data to low-dimensional space to obtain an embedding vector;

[0073] Based on the preset Wide&Deep model and according to the embedding vector, the customer category corresponding to the home-based elderly care customer is determined.

[0074] Explained, the pre-set Multiple Hot encoding method, also known as Multi-hot encoding, is a method that encodes multiple attributes into a single feature simultaneously.

[0075] Pre-setting feature embedding, also known as embedding, is a technique that maps high-dimensional data to a low-dimensional space. Its purpose is to transform discrete, sparse data into continuous, dense vector representations, enabling these data to be better processed and understood by machine learning or deep learning models. Embedding is commonly used to represent elements in fields such as text, images, and graph nodes. Essentially, embedding is a way to represent complex objects (such as words, phrases, users, products, etc.) using a real-valued vector. Each dimension of the vector corresponds to a certain latent feature of the object, and this representation can capture the similarity or correlation between objects.

[0076] The Wide&Deep model is a pre-configured model used by TensorFlow for classification and regression. It combines the memorization capability of a linear model with the generalization capability of a DNN model, optimizing the parameters of both models simultaneously during training to achieve optimal overall predictive performance.

[0077] Based on the above concept and setup, when a user profile contains several customer physical and mental health information features of different dimensions, to determine the customer category corresponding to a home-based elderly care customer based on the user profile, firstly, based on a preset Multiple Hot encoding method, all customer physical and mental health information features are encoded into the same feature, resulting in a unified encoded feature. The unified encoded feature is a sequence representation containing several information granularities, thus simultaneously encoding the multi-dimensional attributes of home-based elderly care customers into one feature, facilitating comprehensive analysis of information from different dimensions to improve the accuracy of home-based elderly care customer analysis. Then, based on a preset feature embedding method, the unified encoded feature is mapped from high-dimensional data to a low-dimensional space to obtain an embedding vector, thereby transforming the discrete and sparse unified encoded feature into a continuous and dense vector representation, and capturing the similarity or correlation between objects of different granularities of the aforementioned unified encoded feature. Finally, based on the preset Wide&Deep model, the memory capacity of the linear model combined with the generalization capacity of the DNN model is fully utilized. Based on the embedding vector, the multi-dimensional information of the home-based elderly care customer represented by the embedding vector is comprehensively analyzed to determine the customer category corresponding to the home-based elderly care customer, so as to achieve the most accurate prediction of the customer category corresponding to the home-based elderly care customer.

[0078] In this embodiment, multiple hot encoding is performed, and the encoding embedding is vectorized. Then, based on the Wide & Deep model, the customer category corresponding to the home-based elderly care customer is determined. This enables unified embedding and processing of multi-dimensional information of home-based elderly care customers, and realizes the determination of customer category based on multi-dimensional information. This improves the classification accuracy of home-based elderly care customers. Based on the accurate classification of home-based elderly care customers, precise personalized service recommendations can be realized, improving the accuracy of home-based elderly care service matching, thereby improving the quality and efficiency of home-based elderly care services.

[0079] In one embodiment, after matching the target home-based elderly care service to the home-based elderly care customer, the method further includes:

[0080] Based on a preset IoT communication method, the target home-based elderly care service project is pushed to the preset IoT terminal corresponding to the home-based elderly care customer.

[0081] Explaining this, after matching target home-based elderly care service projects to home-based elderly care customers, based on preset IoT communication methods and recommendation system technology, the target home-based elderly care service projects are pushed to the corresponding preset IoT terminals of the home-based elderly care customers. For example, personalized home-based elderly care service packages are recommended to home-based elderly care customers through smart home devices such as front-end speakers, WeChat service accounts, and related apps. At the same time, behavioral data such as home-based elderly care customers' clicks, browsing, collection, purchase, and satisfaction with home-based elderly care service packages are collected to optimize the machine learning-based home-based elderly care service matching model, thereby updating the machine learning-based home-based elderly care service matching model and further improving the accuracy and quality of home-based elderly care service matching.

[0082] In this embodiment of the application, target home-based elderly care service projects are recommended to home-based elderly care customers through Internet of Things (IoT) communication. This enables IoT-based smart home-based elderly care services, which not only allows for personalized service recommendations to improve the accuracy and quality of matching home-based elderly care services, but also improves the efficiency and intelligence level of home-based elderly care services, thereby enhancing the intelligence level of IoT-based home-based elderly care.

[0083] It should be noted that the machine learning-based home care service matching and processing methods described in the above embodiments can be recombined with the technical features included in different embodiments as needed to obtain a combined implementation scheme, but all of them are within the scope of protection claimed in this application.

[0084] Please see Figure 4 , Figure 4 This is a schematic block diagram of a machine learning-based home-based elderly care service matching and processing device provided in an embodiment of this application. Corresponding to the above-described machine learning-based home-based elderly care service matching and processing method, this application also provides a machine learning-based home-based elderly care service matching and processing device. Figure 4 As shown, the machine learning-based home care service matching and processing device includes a unit for executing the aforementioned machine learning-based home care service matching and processing method. This machine learning-based home care service matching and processing device can be configured in a computer device. Specifically, please refer to... Figure 4 The machine learning-based home care service matching and processing device 40 includes a first acquisition unit 41, a data fusion unit 42, a first determination unit 43, a second determination unit 44, a first prediction unit 45, and a first matching unit 46.

[0085] The first acquisition unit 41 is used to acquire physical and mental health information data of home-based elderly care customers in different dimensions, including health status information data, self-care ability information data, living status information data, and mental health information data.

[0086] Data fusion unit 42 is used to fuse the health status information data, the self-care ability information data, the living status information data, and the mental health information data to obtain fused data;

[0087] The first determining unit 43 is used to determine the user profile corresponding to the home-based elderly care customer based on the fused data;

[0088] The second determining unit 44 is used to determine the customer category corresponding to the home-based elderly care customer based on the user profile.

[0089] The first prediction unit 45 is used to predict the home-based elderly care service needs of the home-based elderly care customer based on a preset prediction model based on machine learning and according to the user profile and the customer category.

[0090] The first matching unit 46 is used to match the target home-based elderly care service project corresponding to the home-based elderly care service demand based on a preset home-based elderly care service project database, and match the target home-based elderly care service project to the home-based elderly care customer.

[0091] In one embodiment, the first acquisition unit 41 includes:

[0092] The first determining subunit is used to determine the medical information of home-based elderly care customers;

[0093] The first acquisition subunit is used to acquire the health information of the home-based elderly care customer based on a preset wearable smart device;

[0094] The first classification subunit is used to classify the health status of the home-based elderly care customers based on the medical information and the health information, and obtain the health status information data of the home-based elderly care customers.

[0095] In one embodiment, the first determining subunit includes:

[0096] The second acquisition subunit is used to acquire medical image data of home-based elderly care customers;

[0097] The first recognition subunit is used to recognize the medical image data based on a preset OCR recognition method to obtain the medical text data of the home-based elderly care customer.

[0098] The first processing subunit is used to perform structured processing on the medical text data and extract preset target medical content to obtain the medical information of the home-based elderly care customer.

[0099] In one embodiment, the first acquisition unit 41 includes:

[0100] The first acquisition subunit is used to acquire behavioral images of home-based elderly care customers based on preset home cameras;

[0101] The second identification subunit is used to acquire the behavior image based on IoT communication, and to identify the behavior image based on a preset cross-modal learning model to obtain behavior information text.

[0102] The third acquisition subunit is used to acquire the voice call corresponding to the call with the home-based elderly care customer based on a preset smart client terminal.

[0103] The third recognition subunit is used to recognize the call text corresponding to the call voice based on a preset automatic speech recognition model;

[0104] The second determining subunit is used to determine the self-care ability information data of the home-based elderly care customer based on the medical text data, the behavioral information text, and the call text.

[0105] In one embodiment, the first acquisition unit 41 includes:

[0106] The second acquisition subunit is used to acquire facial expression images of home-based elderly care customers based on a preset home camera;

[0107] The fourth acquisition subunit is used to acquire the facial expression image based on Internet of Things communication;

[0108] The fourth identification subunit is used to identify the facial expression image based on a preset artificial intelligence identification model to obtain the mental health information data of the home-based elderly care customer.

[0109] In one embodiment, the user profile includes several customer physical and mental health information features; the second determining unit 44 includes:

[0110] The encoding subunit is used to encode all the customer's physical and mental health information features into the same feature based on a preset Multiple Hot encoding method, so as to obtain a unified encoded feature;

[0111] The mapping subunit is used to map the unified encoded features from high-dimensional data to low-dimensional space based on a preset feature embedding method to obtain an embedding vector;

[0112] The third determining subunit is used to determine the customer category corresponding to the home-based elderly care customer based on the preset Wide&Deep model and the embedding vector.

[0113] In one embodiment, the machine learning-based home care service matching and processing device 40 further includes:

[0114] The push unit is used to push the target home-based elderly care service project to the preset IoT terminal corresponding to the home-based elderly care customer based on a preset IoT communication method.

[0115] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned machine learning-based home care service matching and processing device and its various units can be referred to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity, these details will not be repeated here.

[0116] Meanwhile, the division and connection methods of the various units in the above-mentioned machine learning-based home care service matching and processing device are only for illustrative purposes. In other embodiments, the machine learning-based home care service matching and processing device can be divided into different units as needed, and the various units in the machine learning-based home care service matching and processing device can be connected in different sequences and methods to complete all or part of the functions of the above-mentioned machine learning-based home care service matching and processing device.

[0117] The aforementioned machine learning-based home care service matching and processing device can be implemented as a computer program, which can, for example... Figure 5 It runs on the computer device shown.

[0118] Please see Figure 5 , Figure 5 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a desktop computer or a server, or it can be a component or part of other devices.

[0119] See Figure 5 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504, or it may be a volatile storage medium.

[0120] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to perform the aforementioned machine learning-based home care service matching processing method.

[0121] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0122] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the above-mentioned home-based elderly care service matching processing method based on machine learning.

[0123] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 5 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only a memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown in the figures. Figure 5 The embodiments shown are consistent and will not be described again here.

[0124] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps: acquiring physical and mental health information data of home-based elderly care customers from different dimensions, including health status information data, self-care ability information data, living status information data, and mental health information data; fusing the health status information data, self-care ability information data, living status information data, and mental health information data to obtain fused data; determining the user profile corresponding to the home-based elderly care customer based on the fused data; determining the customer category corresponding to the home-based elderly care customer based on the user profile; predicting the home-based elderly care service needs corresponding to the home-based elderly care customer based on a preset prediction model using machine learning, and based on the user profile and the customer category; matching the target home-based elderly care service project corresponding to the home-based elderly care service needs based on a preset home-based elderly care service project database, and matching the target home-based elderly care service project to the home-based elderly care customer.

[0125] In one embodiment, when the processor 502 acquires physical and mental health information data of home-based elderly care customers from different dimensions, it specifically implements the following steps:

[0126] Determine the medical information of home-based elderly care clients;

[0127] Based on a pre-set wearable smart device, obtain the health information of the home-based elderly care customer;

[0128] Based on the medical information and the health information, the health status of the home-based elderly care customers is classified to obtain the health status information data of the home-based elderly care customers.

[0129] In one embodiment, when determining the medical information of a home-based elderly care customer, the processor 502 specifically implements the following steps:

[0130] Obtain medical image data of home-based elderly care clients;

[0131] Based on a preset OCR recognition method, the medical image data is recognized to obtain the medical text data of the home-based elderly care customer;

[0132] The medical text data is structured and the preset target medical content is extracted to obtain the medical information of the home-based elderly care customer.

[0133] In one embodiment, when the processor 502 acquires physical and mental health information data of home-based elderly care customers from different dimensions, it specifically implements the following steps:

[0134] Based on preset home cameras, collect behavioral images of home-based elderly care customers;

[0135] Based on IoT communication, the behavioral images are acquired, and based on a preset cross-modal learning model, the behavioral images are identified to obtain behavioral information text.

[0136] Based on a preset smart client terminal, obtain the voice recordings corresponding to the calls with the home-based elderly care clients.

[0137] Based on a preset automatic speech recognition model, the text corresponding to the speech in the call is identified;

[0138] Based on the medical text data, the behavioral information text, and the call text, the self-care ability information data of the home-based elderly care customer is determined.

[0139] In one embodiment, when the processor 502 acquires physical and mental health information data of home-based elderly care customers from different dimensions, it specifically implements the following steps:

[0140] Based on pre-set home cameras, capture facial expression images of elderly people living at home;

[0141] The facial expression image is acquired based on Internet of Things (IoT) communication.

[0142] Based on a preset artificial intelligence recognition model, the facial expression images are identified to obtain the mental health information data of the home-based elderly care customers.

[0143] In one embodiment, the user profile includes several customer physical and mental health information features; when the processor 502 determines the customer category corresponding to the home-based elderly care customer based on the user profile, it specifically implements the following steps:

[0144] Based on the preset Multiple Hot encoding method, all customer physical and mental health information features are encoded into the same feature to obtain a unified encoded feature;

[0145] Based on a preset feature embedding method, the unified coded features are mapped from high-dimensional data to low-dimensional space to obtain an embedding vector;

[0146] Based on the preset Wide&Deep model and according to the embedding vector, the customer category corresponding to the home-based elderly care customer is determined.

[0147] In one embodiment, after matching the target home-based elderly care service to the home-based elderly care customer, the processor 502 further performs the following steps:

[0148] Based on a preset IoT communication method, the target home-based elderly care service project is pushed to the preset IoT terminal corresponding to the home-based elderly care customer.

[0149] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0150] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program, which can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0151] Therefore, this application also provides a computer-readable storage medium. This computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0152] A computer program product, when run on a computer, causes the computer to perform the steps of the machine learning-based home care service matching processing method described in the above embodiments.

[0153] The computer-readable storage medium can be an internal storage unit of the aforementioned device, such as the device's hard drive or memory. The computer-readable storage medium can also be an external storage device of the device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the device.

[0154] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0155] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing computer programs.

[0156] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0158] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0160] The software tools or components not belonging to our company that appear in the embodiments of this application are merely examples and do not represent actual use.

[0161] The data collection in this application embodiment complies with the requirements of relevant laws and regulations, such as GDPR (General Data Protection Regulation) or other national and regional information security standards.

[0162] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for matching and processing home-based elderly care services based on machine learning, characterized in that, include: Acquire physical and mental health information data of home-based elderly care customers from different dimensions, including health status information data, self-care ability information data, living status information data, and mental health information data; The health status information data, the self-care ability information data, the living status information data, and the mental health information data are fused to obtain fused data; Based on the fused data, a user profile corresponding to the home-based elderly care customer is determined; Based on the user profile, the customer category corresponding to the home-based elderly care customer is determined; Based on a pre-defined prediction model using machine learning, and according to the user profile and the customer category, the home-based elderly care service needs corresponding to the home-based elderly care customers are predicted. Based on a pre-set database of home-based elderly care service projects, the target home-based elderly care service projects corresponding to the home-based elderly care service needs are matched, and the target home-based elderly care service projects are matched to the home-based elderly care customers. The user profile includes several characteristics of the customer's physical and mental health; based on the user profile, the customer category corresponding to the home-based elderly care customer is determined, including: Based on the preset Multiple Hot encoding method, all customer physical and mental health information features are encoded into the same feature to obtain a unified encoded feature; Based on a preset feature embedding method, the unified coded features are mapped from high-dimensional data to low-dimensional space to obtain an embedding vector; Based on the preset Wide&Deep model and according to the embedding vector, the customer category corresponding to the home-based elderly care customer is determined.

2. The home-based elderly care service matching and processing method based on machine learning according to claim 1, characterized in that, Obtain physical and mental health information data from different dimensions of home-based elderly care clients, including: Determine the medical information of home-based elderly care clients; Based on a pre-set wearable smart device, obtain the health information of the home-based elderly care customer; Based on the medical information and the health information, the health status of the home-based elderly care customers is classified to obtain the health status information data of the home-based elderly care customers.

3. The home-based elderly care service matching and processing method based on machine learning according to claim 2, characterized in that, Determine the medical information of home-based elderly care clients, including: Obtain medical image data of home-based elderly care clients; Based on a preset OCR recognition method, the medical image data is recognized to obtain the medical text data of the home-based elderly care customer; The medical text data is structured and the preset target medical content is extracted to obtain the medical information of the home-based elderly care customer.

4. The home-based elderly care service matching and processing method based on machine learning according to claim 3, characterized in that, Obtain physical and mental health information data from different dimensions of home-based elderly care clients, including: Based on preset home cameras, collect behavioral images of home-based elderly care customers; Based on IoT communication, the behavioral images are acquired, and based on a preset cross-modal learning model, the behavioral images are identified to obtain behavioral information text. Based on a preset smart client terminal, obtain the voice recordings corresponding to the calls with the home-based elderly care clients. Based on a preset automatic speech recognition model, the text corresponding to the speech in the call is identified; Based on the medical text data, the behavioral information text, and the call text, the self-care ability information data of the home-based elderly care customer is determined.

5. The home-based elderly care service matching and processing method based on machine learning according to claim 1, characterized in that, Obtain physical and mental health information data from different dimensions of home-based elderly care clients, including: Based on pre-set home cameras, capture facial expression images of elderly people living at home; The facial expression image is acquired based on Internet of Things (IoT) communication. Based on a preset artificial intelligence recognition model, the facial expression images are identified to obtain the mental health information data of the home-based elderly care customers.

6. The home-based elderly care service matching and processing method based on machine learning according to claim 1, characterized in that, After matching the target home-based elderly care service project to the home-based elderly care customer, the process also includes: Based on a preset IoT communication method, the target home-based elderly care service project is pushed to the preset IoT terminal corresponding to the home-based elderly care customer.

7. A home-based elderly care service matching and processing device based on machine learning, characterized in that, include: The first acquisition unit is used to acquire physical and mental health information data of home-based elderly care customers in different dimensions, including health status information data, self-care ability information data, living status information data, and mental health information data. The data fusion unit is used to fuse the health status information data, the self-care ability information data, the living status information data, and the mental health information data to obtain fused data; The first determining unit is used to determine the user profile corresponding to the home-based elderly care customer based on the fused data. The second determining unit is used to determine the customer category corresponding to the home-based elderly care customer based on the user profile. The first prediction unit is used to predict the home-based elderly care service needs of the home-based elderly care customers based on a preset prediction model based on machine learning and the user profile and the customer category. The first matching unit is used to match the target home-based elderly care service project corresponding to the home-based elderly care service demand based on a preset home-based elderly care service project database, and match the target home-based elderly care service project to the home-based elderly care customer. The user profile includes several customer physical and mental health information features; the second determining unit includes: The encoding subunit is used to encode all the customer's physical and mental health information features into the same feature based on a preset Multiple Hot encoding method, so as to obtain a unified encoded feature; The mapping subunit is used to map the unified encoded features from high-dimensional data to low-dimensional space based on a preset feature embedding method to obtain an embedding vector; The third determining subunit is used to determine the customer category corresponding to the home-based elderly care customer based on the preset Wide&Deep model and the embedding vector.

8. A computer device, characterized in that, The computer device includes a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program to perform the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the steps of the method as described in any one of claims 1-6.

Images