Intelligent health-care service guiding method and system and related equipment

Abstract

The invention provides an intelligent health service guiding method and system and related equipment, and the guiding method comprises the steps: obtaining a to-be-processed health service data set containing multiple pieces of target health management information, screening key health guiding information, and generating first health guiding information; converting the multi-dimensional vector data into multi-dimensional vector data as second health guidance information; performing correlation analysis by using a multi-source analysis method to generate a first analysis result containing multi-dimensional features; on the basis of the similarity between the result and sub-health directory multi-dimensional features in a preset health directory, sub-health directories to which the target health management information belongs are determined, and each sub-health directory at least corresponds to one group of health information guiding strategies; and based on the first analysis result corresponding to each piece of target health management information in the same sub-health directory, extracting individual feature difference parameters, and generating a final personalized health service guide result. According to the guiding method, personalized guiding services are provided for the health of the user, and the user requirements can be effectively met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health care service guidance methods, and in particular to a smart health care service guidance method, system and related equipment. BACKGROUND

[0002] Health care service guidance is a service that guides the elderly to conduct health checkups and daily health care. Existing health care guidance services often use general templates, resulting in a disconnection between services and actual needs. The health status and living habits of the elderly population vary greatly, and existing health care guidance services cannot develop precise health checkup and health care plans according to the specific circumstances of each elderly person, such as underlying diseases, exercise capacity, and dietary preferences, thereby failing to effectively prevent and respond to health problems. SUMMARY

[0003] In view of the above, the purpose of the present application is to provide a smart health care service guidance method, system and related equipment to solve the problem that existing health care services cannot effectively guide each elderly person.

[0004] To achieve the above purpose, the present application provides a smart health care service guidance method, which comprises:

[0005] Obtaining a set of to-be-processed health care service data containing a plurality of target health management information, screening key health guidance information from the target health management information, and generating first health guidance information;

[0006] Converting the first health guidance information into multi-dimensional vector data, and taking the multi-dimensional vector data as second health guidance information;

[0007] Using a multi-source analysis method to analyze the correlation of the second health guidance information to generate a first analysis result containing multi-dimensional features;

[0008] Based on the similarity of the first analysis result and the multi-dimensional features of a sub-health directory in a preset health directory, determining the sub-health directory to which each target health management information belongs, and each sub-health directory corresponding to at least one group of health information guidance strategies;

[0009] Based on the first analysis result corresponding to each target health management information in the same sub-health directory, extracting individual feature difference parameters, and generating a final personalized health care service guidance result based on the individual feature difference parameters.

[0010] Optionally, the multi-source analysis method comprises at least two different analysis techniques to generate a first analysis result containing multi-dimensional features, and the multi-dimensional features include disease type features, service type features, psychological state features, disease development features and living habit features.

[0011] Optionally, the sub-health directory to which each target health management information belongs is determined based on similarity of the first analysis result and multi-dimensional features of the sub-health directory in the preset health directory, and the method comprises the following steps.

[0012] The feature similarity of the first analysis result and the sub-health directory in different dimensions is calculated.

[0013] When the feature similarity meets a preset threshold, the corresponding target health management information belongs to the sub-health directory.

[0014] Optionally, the similarity is calculated in the following manner.

[0015] Similarity = second quantity / first quantity.

[0016] The first quantity is the number of feature dimensions that are included in both the first analysis result and the sub-health directory, and the second quantity is the number of dimensions in the common feature dimensions in which the analysis result is completely consistent.

[0017] Optionally, the preset threshold is dynamically adjusted according to the number of categories of the sub-health directory, and the adjusting step comprises the following steps: when the number of categories is less than 5, the preset threshold is set to 0.8; when the number of categories is between 5 and 10, the preset threshold is set to 0.7; and when the number of categories is greater than 10, the preset threshold is set to 0.6.

[0018] Optionally, the target health management information is screened for key health guidance information, which comprises screening the target health management information for key health guidance information according to a preset screening rule, wherein the preset screening rule comprises a keyword matching rule and a semantic analysis rule, the keyword matching rule is used to extract specific key health guidance information, and the semantic analysis rule is used to identify semantic content with potential health guidance value.

[0019] Optionally, the set of to-be-processed health service data containing a plurality of target health management information is obtained by performing deduplication, error correction and format unification on an original set of intelligent health service data to generate the set of to-be-processed health service data.

[0020] Based on the same inventive concept, the present disclosure also provides an intelligent health service guidance system, which comprises:

[0021] A data acquisition module is configured to acquire a set of to-be-processed health service data.

[0022] A feature extraction module is configured to screen key health guidance information from the set of to-be-processed health service data to generate first health guidance information.

[0023] a vector conversion module configured to convert the first health guidance information into multi-dimensional vector data to generate second health guidance information;

[0024] a multi-source analysis module configured to perform relevance analysis on the second health guidance information by rule engine analysis and machine learning analysis to generate a first analysis result containing multi-dimensional features;

[0025] a catalog matching module configured to calculate the similarity of multi-dimensional features between the first analysis result and the sub-health catalog in the preset health catalog, and when the feature similarity meets a preset threshold, to classify the corresponding target health management information into the sub-health catalog;

[0026] a personalized recommendation module configured to extract individual feature difference parameters of the first analysis result based on the first analysis result corresponding to each target health management information in the same sub-health catalog, and to generate a final personalized health and rehabilitation service guidance result based on the individual feature difference parameters.

[0027] Based on the same inventive concept, the disclosure also provides an electronic device including a memory, a processor, and a computer program stored on the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0028] Based on the same inventive concept, the disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described above.

[0029] As described above, the smart health and wellness service guidance method provided in this application precisely extracts complex health data into multidimensional features by screening key information, transforming multidimensional vectors, and performing correlation analysis on the target health management information. These features are then matched with the sub-health directories of a preset health directory based on similarity, with each sub-health directory corresponding to at least one set of health information guidance strategies. Based on this, the system can first provide a unified basic health guidance strategy for target health management information within the same sub-health directory, and then provide further differentiated health guidance strategies based on individual characteristic difference parameters, ultimately generating personalized health and wellness service guidance results. This approach closely aligns with users' actual health conditions, effectively meets user needs, significantly improves user satisfaction and compliance with health and wellness services, and truly enhances the actual effectiveness of health and wellness services. Furthermore, this method has significant advantages in algorithmic resource utilization. The process of classifying target health management information into sub-health directories is essentially a preliminary screening and division of massive amounts of raw data. Compared to traditional methods that perform comprehensive analysis of all data, this method only requires differential analysis of data with similar characteristics within each sub-health category. This significantly reduces the amount of data processing, substantially lowers the computational resources and time costs required for algorithm operation, and achieves efficient data processing and accurate service output. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a flowchart illustrating a method for guiding elderly care services, as shown in an embodiment of this application.

[0032] Figure 2 This is a schematic diagram of the hardware structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0034] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the embodiments of the present application shall have the common meaning understood by one of ordinary skill in the art to which the embodiments of the present application belong. The terms "first", "second" and similar terms used in the embodiments of the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms encompass the elements or objects listed after the terms and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships can also change accordingly.

[0035] Based on the background, in recent years, the degree of global population aging continues to deepen, and currently, most health care guidance services still rely on standardized and universal templates, which unify health examination items and daily health care programs for planning and pushing. This "one-size-fits-all" service mode is rooted in the fact that the traditional service system is difficult to efficiently handle the complex individual differences of the elderly population - the health status of the elderly includes multiple chronic diseases such as hypertension, diabetes, and cardiovascular and cerebrovascular diseases, and the disease stages and complication risk of different individuals differ significantly; in terms of living habits, from exercise ability (such as some old people who are unable to move, cannot complete regular exercise) to dietary preferences, all show highly decentralized characteristics.

[0036] Taking health examination as an example, the universal template often recommends "full physical examination package" as a unified recommendation, but ignores the special examination needs of some old people due to age and disease history, such as Parkinson's disease patients who need to monitor neurological function indicators, but the template recommendation fails to timely detect potential risks. In the field of daily health care, standardized exercise recommendations (such as 5000 steps per day) lack practical guidance for people with limited mobility, and dietary recommendations are also difficult to adapt to the individualized dietary needs of old people with special diseases such as kidney disease and gout.

[0037] The disconnection between services and actual needs directly leads to a significant reduction in the effectiveness of health problem prevention and response. On the one hand, due to the lack of accurate health examination guidance, chronic disease early symptoms are easily ignored, delaying the best treatment opportunity; on the other hand, the inappropriately adapted daily health care programs cannot effectively improve the health status of the elderly, and may even exacerbate the physical burden and increase medical expenses and care costs due to incorrect guidance (such as recommending high-intensity exercise for joint degeneration old people). This imbalance between supply and demand not only restricts the high-quality development of health care services industry, but also poses a serious challenge to the health and well-being of the elderly population.

[0038] The following will be described in conjunction with the accompanying drawings Figures 1-2To illustrate embodiments of the present application in detail.

[0039] As shown in the figure, a smart health care service guidance method includes the following steps: Figure 1

[0040] S100: Obtain a set of to-be-processed health care service data containing a plurality of target health management information, perform key health guidance information screening on the target health management information, and generate first health guidance information;

[0041] Specifically, the set of to-be-processed health care service data refers to the original data set of health information collected through various channels before the start of the smart health care service guidance process, which has not been screened and analyzed. The set of to-be-processed health care service data is widely sourced, including but not limited to the electronic health records of the elderly (such as physical examination reports, disease diagnosis records), real-time health data collected by wearable devices (such as heart rate, sleep quality), daily behavior monitoring data (such as exercise steps, diet records), and health appeal reports submitted by users. Target health management information is the health information of each elderly person in the set of to-be-processed health care service data. By screening the key health guidance information from the target health management information, the information with low correlation with the key health information is removed, the target data for subsequent screening and analysis is established, the direction is avoided in the massive data, and the data processing work is more targeted and efficient.

[0042] S200: Convert the first health guidance information into multi-dimensional vector data, and use the multi-dimensional vector data as second health guidance information;

[0043] Specifically, in order to facilitate computer processing and analysis, it is necessary to convert the first health guidance information from text, numerical value and other original forms into multi-dimensional vector data understandable by computers. In this step, word embedding technology in the field of natural language processing (NLP) can be used, such as Word2Vec, GloVe or BERT model word vector representation, to map text information to a high-dimensional vector space. For example, "exercise rehabilitation service suitable for hypertension patients, recommended 3 times a week, each time for 45 minutes" is converted into a vector: disease type = hypertension, service type = exercise rehabilitation, frequency = 3 times / week, duration = 45 minutes.

[0044] S300: Perform correlation analysis on the second health guidance information using a multi-source analysis method to generate a first analysis result containing multi-dimensional features;

[0045] ​In this step, the exemplary multi-source analysis method uses a rule engine to analyze and work with a machine learning model. The former builds a rule base based on medical diagnosis guidelines, etc., to make logical reasoning, such as determining the user's psychological risk based on the characteristics of hypertension and unhealthy lifestyle habits; the latter uses algorithms to deeply mine feature associations and predict disease development trends. The results of the two technologies are fused to generate a first analysis result containing multiple features such as disease, service, psychology, disease prediction, and lifestyle habits, providing a key data basis for information classification and personalized service recommendation for smart health and wellness.

[0046] S400: Based on the similarity of the multi-dimensional features of the first analysis result and the sub-health directory in the preset health directory, determine the sub-health directory to which each target health management information belongs, and each sub-health directory corresponds to at least one group of health information guidance strategy;

[0047] Specifically, the preset health directory is a highly refined classification system, which is composed of sub-health directories directly constructed by multi-dimensional health elements. These sub-health directories are not simply disease or behavior classification, but a multi-element combination covering health status, lifestyle, psychological status, etc. For example, "diabetes-movement preference-meat preference-psychological stability", "no disease-movement avoidance-vegetarian habit-psychological anxiety", etc. are all independent sub-health directories.

[0048] The system classifies the target health management information by accurately calculating the similarity of the first analysis result and the multi-dimensional features of each sub-health directory. Taking the "diabetes-movement preference-meat preference-psychological stability" sub-health directory as an example, if the first analysis result shows that a patient has diabetes, regular exercise habits, prefers meat, and has a stable psychological state, and the matching degree with the characteristics of the directory reaches the threshold, the health guidance information will be classified into this sub-health directory.

[0049] S500: Based on the first analysis result corresponding to each target health management information in the same sub-health directory, extract the individual feature difference parameters, and generate the final personalized health and wellness service guidance result based on the individual feature difference parameters.

[0050] Specifically, after determining the sub-health directory to which the target health management information belongs, although these information have similar health topics, there are still significant differences in individual characteristics of different old people. For example, two old people who both belong to the hypertension management sub-health directory may have different ages, complications, and living habits. Therefore, individual characteristic difference parameters such as age, gender, physical function indicators, medication history, and exercise preferences need to be extracted from the first analysis result. Based on these individual characteristic difference parameters, combined with the health information guidance strategy corresponding to the sub-health directory, the guidance strategy is personalized adjusted through machine learning algorithms such as decision tree, random forest or reinforcement learning model. For example, for the old people who have difficulty in moving, the walking suggestion in the exercise health strategy is adjusted to low-intensity exercise suitable for indoor; for the old people who have heavy taste, more targeted low-salt diet recipes are provided in the dietary nutrition strategy. The finally generated personalized health and rehabilitation service guidance result can accurately match the actual needs of each old person, and realize efficient and scientific health and rehabilitation service guidance.

[0051] In the present embodiment, the intelligent health and rehabilitation service guidance method accurately refines complex health data into multi-dimensional features through key information screening, multi-dimensional vector conversion and correlation analysis on target health management information. These multi-dimensional features are matched with the similarity of the sub-health directories of the preset health directory, and each sub-health directory corresponds to at least one set of health information guidance strategy. Based on this, the system can first give a unified basic health guidance strategy for the target health management information in the same sub-health directory, and then provide further differentiated health guidance strategies according to individual characteristic difference parameters, and finally generate personalized health and rehabilitation service guidance results. This processing method closely matches the actual health status of the user, effectively meets the needs of the user, significantly improves the satisfaction and compliance of the user to the health and rehabilitation service, and effectively enhances the actual effect of the health and rehabilitation service.

[0052] In addition, the method has great advantages in algorithm resource utilization. The process of classifying the target health management information into the sub-health directory is essentially a preliminary screening and division of massive raw data. Compared with the comprehensive analysis of all data by traditional methods, this method only needs to conduct differential analysis on the data with similar characteristics under each sub-health directory, greatly reducing the data processing amount, significantly reducing the computing resources and time cost required for algorithm running, and realizing efficient data processing and accurate service output.

[0053] In some embodiments, the multi-source analysis method includes at least two different analysis techniques to generate a first analysis result containing multi-dimensional features including disease type features, service type features, psychological state features, disease development features, and living habit features.

[0054] Exemplarily, the multi-source analysis method includes rule engine analysis and machine learning model analysis. The rule engine analysis builds a rule library based on medical treatment guidelines and industry standards, and processes the basic dimension information in a logical reasoning manner, such as inferring the user's psychological characteristics by the disease type characteristics and the living habit characteristics. Exemplarily, according to the disease type characteristics such as hypertension, in combination with the living habit characteristics such as lack of exercise and high-salt diet, it is preliminarily determined that the user has psychological risks of anxiety or excessive stress; the machine learning model analysis uses algorithms to associate the basic dimension information and predict the disease development trend, such as predicting the disease development characteristics by the disease type characteristics, the living habit characteristics and the user's psychological characteristics. Exemplarily, a hypertension patient maintains the living habit of smoking a pack of cigarettes every day, exercising less than once a week, and high-salt diet, and is in an anxious state for a long time due to high work pressure. Through machine learning model analysis and prediction, it is predicted that the systolic pressure of the patient may increase by 8-10 mmHg within 6 months, and the risk of cardiovascular complications within 1 year is 2.5 times higher than that of ordinary patients. The output results of the above two analysis techniques are subjected to confidence evaluation and weighted fusion, and finally a multi-dimensional characteristic first analysis result covering disease type, service type, psychological state, disease prediction and living habit is generated, which lays a data foundation for subsequent health management information classification and personalized service recommendation.

[0055] In the embodiment, the multi-source analysis method can mine data value from different angles, reduce the limitations of single technology, more accurately and comprehensively extract multi-dimensional characteristics in health data, and improve the accuracy and comprehensiveness of the analysis result.

[0056] In some embodiments, the similarity between the first analysis result and the multi-dimensional characteristics of the sub-health directory in the preset health directory is determined, and each target health management information belongs to a sub-health directory, including:

[0057] The feature similarity between the first analysis result and the sub-health directory in different dimensions is calculated.

[0058] When the feature similarity meets a preset threshold, the corresponding target health management information belongs to the sub-health directory.

[0059] In addition, the similarity is calculated by the following method:

[0060] Similarity = Second Number / First Number

[0061] Wherein, the first number is the number of feature dimensions commonly included in the first analysis result and the sub-health directory; and the second number is the number of dimensions in the common feature dimensions that are completely consistent.

[0062] For example, the first analysis result shows that a certain user has the disease type of "hypertension", the service requirement of "regular physical examination", the psychological state of "anxiety", the life habit of "lack of exercise and high-salt diet", and the disease development characteristic of "unstable blood pressure control". Compared with the "hypertension-multiple intervention management" sub-health directory, both of them contain five characteristic dimensions of disease type, service type, psychological state, life habit and disease development (first number = 5), and the analysis results of four dimensions of disease type, psychological state, life habit and disease development are completely consistent (second number = 4). The similarity of the characteristics of the first analysis result and the sub-health directory in different dimensions is 4 / 5 = 0.8. Assuming that the preset threshold is 0.85, the user information is classified into the "hypertension-multiple intervention management" sub-health directory.

[0063] In the embodiment, the standardized similarity calculation method and the preset threshold determination rule are adopted, so that the system can quickly process and classify the target health management information. The system can process a large amount of health data in a short time, improves the efficiency of health information classification, and meets the real-time requirement of intelligent health care service.

[0064] In some embodiments, the preset threshold is dynamically adjusted according to the number of categories of the sub-health directory. The adjustment step includes: when the number of categories is less than 5, the preset threshold is set to 0.8; when the number of categories is between 5 and 10, the preset threshold is set to 0.7; and when the number of categories is greater than 10, the preset threshold is set to 0.6.

[0065] Specifically, the embodiment is based on the logic that "the number of categories is negatively related to the classification accuracy". When the number of categories of the sub-health directory is less than 5, it means that the classification system is relatively rough, and each category covers a wide range. Therefore, a higher threshold of 0.8 is set to ensure that the health management information classified into the same category has high similarity. When the number of categories is between 5 and 10, the classification accuracy is moderate, and the threshold of 0.7 balances the information aggregation and differentiation requirements. If the number of categories is greater than 10, it means that the classification system is extremely detailed, and the threshold is reduced to 0.6 to allow more information with certain differences to be classified into the corresponding category, avoiding the difficulty of information classification due to the high threshold. For the critical case where the number of categories is exactly 5 or 10, the system adopts the principle of "not low but high", such as when the number of categories reaches 5, the threshold of 0.8 is automatically applied to avoid the sudden change of classification standard due to the sudden reduction of threshold, and to ensure the stability and continuity of the classification result.

[0066] In the embodiment, the dynamic threshold adjustment avoids the "one-size-fits-all" threshold setting. When the number of categories is small, a high threshold accelerates information screening and reduces unnecessary matching calculations. When the number of categories is large, a low threshold reduces the difficulty of information classification, so that the system can quickly process a large amount of health management information and significantly improve the overall classification efficiency.

[0067] In some embodiments, the key health guidance information screening on the target health management information comprises: screening the target health management information according to a preset screening rule, wherein the preset screening rule comprises a keyword matching rule and a semantic analysis rule, the keyword matching rule is used to extract specific key health guidance information, and the semantic analysis rule is used to identify semantic content with potential health guidance value.

[0068] For example, the information containing disease keywords such as "hypertension" and "diabetes" can be quickly locked by keyword matching, and synonyms and near synonyms such as "hypertension" can be matched, such as "high blood pressure", "hypertension" and "essential hypertension", thereby expanding the coverage of keywords. The semantic analysis technology is used to identify content with potential health guidance value. When a user expresses "breathes heavily when climbing stairs and recovers after a long rest", the semantic analysis technology analyzes the text semantics, combines medical knowledge and user physical examination information, and identifies that the user may have a heart and lung function problem. Even if the specific disease is not mentioned, the potential health risk can be captured, and a clue is provided for subsequent health assessment. The first health guidance information obtained by the above-mentioned preset screening rule has high accuracy and relevance, and is the core data for subsequent analysis.

[0069] In the embodiment, the keyword matching rule can quickly capture medical terms and health service keywords by means of a dynamically updated professional word library, and reduce information errors and omissions. The semantic analysis rule can understand the health risks implied behind the text by means of a deep learning model and a knowledge graph, and the combination of the two can greatly improve the accuracy of key information extraction and avoid screening deviation caused by non-standard expression.

[0070] In some embodiments, the obtaining of the to-be-processed health service data set containing a plurality of target health management information comprises: de-duplicating, correcting errors and unifying formats of an original intelligent health service data set to generate the to-be-processed health service data set.

[0071] Specifically, a combination of fast screening based on hash values and deep comparison based on data fingerprints can be used for deduplication operation on the original smart health and wellness service data set. Further, the hash value of each data is calculated first to quickly filter out data with the same hash value. Then, for data with hash value conflicts, key features such as user ID, record time, and core health indicators are extracted to generate data fingerprints, and through cosine similarity calculation comparison, repeated data is accurately identified. By constructing a medical data verification rule library, error correction operation is performed on the original smart health and wellness service data set. For example, the blood pressure value should be within the normal physiological range (systolic pressure 90-140 mmHg, diastolic pressure 60-90 mmHg), but the user shows a systolic pressure of 900 mmHg, which does not conform to normal physiological common sense, indicating an input error. The systolic pressure is modified to 90 mmHg. Through the standardized data model, the original smart health and wellness service data set is processed for format unification, including fields such as basic information (name, age, gender), health indicators (blood pressure, blood sugar, heart rate), service records (consultation time, service type), and the data type and format requirements of each field are clearly defined.

[0072] In this embodiment, by deduplicating the original smart health and wellness service data set, the interference of redundant information on subsequent analysis is avoided; by correcting the original smart health and wellness service data set, the data accuracy is improved; by unifying the format of the original smart health and wellness service data set, the data consistency is guaranteed, laying a solid foundation for accurate health information analysis. The above operations reduce the amount of processed data and improve the quality, reducing the computational complexity and data processing amount of subsequent key information screening, multi-source analysis, and other algorithms.

[0073] In some embodiments, the final personalized health and wellness service guidance result is pushed to the corresponding user.

[0074] Specifically, in the smart health and wellness service, the process of accurately pushing the final personalized health and wellness service guidance result to the user can be deeply expanded through multi-scene fusion and technological innovation. For example, for elderly people with different health statuses, the system can automatically match differentiated push channels: for elderly people who are used to using smart devices, real-time push of motion rehabilitation videos with pictures and text through the health and wellness APP; for elderly people living alone, rely on smart speakers to remind them by voice at a fixed time every day, such as "Grandpa Zhang, remember to take your blood pressure medication at 9 am today, and take a 15-minute walk outside after taking the medication", and send a medication confirmation notification to the user's children's mobile phones at the same time.

[0075] The push effect can be visualized and evaluated through multi-dimensional data. The system background tracks the opening rate and completion rate of the old people in real time, and combines physiological indicators (such as blood pressure fluctuation and sleep quality) collected by wearable devices to form an effect analysis report. For example, after receiving personalized exercise push for 3 months, the diastolic pressure of a certain old person with hypertension decreased from 100 mmHg to 85 mmHg, and the system automatically marked this scheme as “high-efficiency scheme” and included it in the recommended template for people with similar health characteristics. At the same time, the platform supports family members to remotely view the push history and health trends, promoting family participation in health management, such as children can understand the listening frequency of parents to psychological counseling audio through the applet, and timely intervene in communication to alleviate anxiety.

[0076] It should be noted that the method of the embodiments of the present application can be executed by a single device, such as a computer or a server. The method of the embodiments can also be applied to a distributed scenario, and completed by multiple devices cooperating with each other. In this distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiments of the present application, and the multiple devices can interact with each other to complete the method.

[0077] It should be noted that some embodiments of the present application have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than that described above and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or necessary.

[0078] Based on the same inventive concept, the present application also provides a smart health and wellness service guidance system corresponding to the method of any of the above embodiments, comprising:

[0079] A data acquisition module is configured to acquire a set of health and wellness service data to be processed;

[0080] A feature extraction module is configured to filter key health guidance information from the set of health and wellness service data to be processed, and generate first health guidance information;

[0081] A vector conversion module is configured to convert the first health guidance information into multi-dimensional vector data, and generate second health guidance information;

[0082] A multi-source analysis module is configured to perform correlation analysis on the second health guidance information through rule engine analysis and machine learning analysis to generate a first analysis result containing multi-dimensional features;

[0083] a catalog matching module, configured to calculate the similarity of the first analysis result and the multi-dimensional features of the sub-health catalog in the preset health catalog, and when the feature similarity meets a preset threshold, to classify the corresponding target health management information into the sub-health catalog;

[0084] a personalized recommendation module, configured to extract individual feature difference parameters of the first analysis result based on the first analysis result corresponding to each target health management information in the same sub-health catalog, and to generate a final personalized health and wellness service guidance result based on the individual feature difference parameters.

[0085] Specifically, the data acquisition module acquires the health data of the elderly through various sensors, communication chips and edge computing devices. The data acquired by the data acquisition module is sourced from a wide range, including but not limited to the electronic health records of the elderly (such as physical examination reports, disease diagnosis records), real-time health data collected by wearable devices (such as heart rate, sleep quality), daily behavior monitoring data (such as exercise steps, diet records) and health appeals actively submitted by users, etc.

[0086] The feature extraction module performs key health guidance information screening on the target health management information according to a preset screening rule. The preset screening rule includes a keyword matching rule and a semantic analysis rule. The keyword matching rule is used to extract specific key health guidance information, and the semantic analysis rule is used to identify semantic content with potential health guidance value.

[0087] The vector conversion module can use word embedding technology in the field of natural language processing (NLP), such as Word2Vec, GloVe or BERT model word vector representation, to convert the first health guidance information into multi-dimensional vector data that is easy for computers to process.

[0088] The multi-source analysis module uses a rule engine and a machine learning model to collaboratively analyze the second health guidance information, generating a first analysis result containing multi-dimensional features such as disease, service, psychology, prediction and lifestyle, providing a key data basis for information classification and personalized service recommendation of smart health and wellness.

[0089] The catalog matching module compares the first analysis result with the preset health catalog. The preset health catalog is jointly formulated by medical experts and industry practitioners, with sub-health catalogs constructed in multi-dimensional combinations such as "disease-lifestyle-psychological state". The system calculates the feature matching degree of the analysis result and each sub catalog through the cosine similarity algorithm, and when the similarity exceeds the preset threshold (such as 0.8), the target health management information is classified into the corresponding sub catalog.

[0090] The personalized recommendation module, as the "service outlet" of the system, further mines individual characteristic differences after determining the sub-health catalog. Individual parameters such as age, gender, medication history, and exercise ability are extracted from the first analysis result, combined with the corresponding basic health guidance strategy of the sub catalog, and the reinforcement learning model is used for personalized adjustment.

[0091] In the embodiment, the intelligent health and rehabilitation service guidance system realizes intelligent management of the whole process from data acquisition to personalized service through the cooperation of multiple modules. The data acquisition module ensures accurate and comprehensive information, the feature extraction and vector conversion module deeply mines the value of data, the multi-source analysis and catalog matching module improves the accuracy of health assessment, and the personalized recommendation module provides customized services. Finally, the system can efficiently identify health risks and accurately match service strategies, significantly improving the pertinence and effectiveness of health and rehabilitation services, while reducing the burden of manual management, enhancing the initiative of health management of the elderly and the sense of security of family members, and helping to build an efficient and scientific intelligent health and rehabilitation ecosystem.

[0092] Based on the same inventive concept, the present application also provides an electronic device corresponding to the method of any of the above embodiments, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to realize the guidance method of any one of the embodiments.

[0093] Figure 2 A more specific hardware structure schematic diagram of an electronic device provided in the embodiment is shown, which can include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040 and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030 and the communication interface 1040 are connected to each other through the bus 1050 for communication within the device.

[0094] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to realize the technical solutions provided by the embodiments of the present application.

[0095] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0096] The input / output interface 1030 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0097] The communication interface 1040 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or through a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0098] The bus 1050 includes a channel for transmitting information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0099] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only include the components necessary to implement the solutions of the embodiments of the present specification, and does not have to include all the components shown in the figure.

[0100] The electronic device of the above embodiments is used to implement the corresponding boot method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here again.

[0101] Based on the same inventive concept, the present application also provides a non-transitory computer readable storage medium, which stores computer instructions for causing the computer to execute the boot method according to any of the above embodiments.

[0102] The computer readable medium of the embodiments can include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0103] The storage medium of the above embodiments stores computer instructions for causing the computer to perform the booting method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0104] It can be understood that before using the technical solutions of various embodiments in the present disclosure, the type, use range, use scenario, etc. of the personal information involved will be informed to the user in an appropriate manner, and the authorization of the user will be obtained.

[0105] For example, in response to receiving the active request of the user, prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the software or hardware such as electronic devices, application programs, servers or storage media that perform the operation of the technical solutions of the present disclosure according to the prompt information.

[0106] As an optional but not limited implementation manner, in response to accepting the active request of the user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0107] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation of the present disclosure, and other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0108] Those of ordinary skill in the art will realize that the foregoing discussion of any of the embodiments has been presented for the purpose of illustration and description and is not intended to be exhaustive or to limit the application to the precise forms described. Many modifications and variations will be apparent to those of ordinary skill in the art. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0109] In addition, to simplify the description and discussion, and so as not to make the embodiments of the application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components can or can not be shown in the provided drawings. Further, devices can be shown in block diagram form so as not to make the embodiments of the application difficult to understand, and this also takes into account the fact that details regarding implementation of these block diagram devices are highly dependent on the platform to which the embodiments of the application are to be implemented (i.e., these details should be well within the understanding of one of ordinary skill in the art). Where specific details (e.g., circuitry) are set forth in order to describe an illustrative embodiment of the application, it should be apparent to one of ordinary skill in the art that the embodiments of the application can be practiced without or with variations of these specific details. Thus, the description should not be viewed as limiting the application, but rather as merely describing illustrative embodiments.

[0110] While the application has been described in connection with specific embodiments thereof, it will be understood that many modifications, variations and alternatives will be apparent to those skilled in the art as a result of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0111] It is therefore intended that the embodiments of the application embrace all such alternatives, modifications and variations as falling within the broad scope of the appended claims. Accordingly, any and all departures from the above described methods, apparatus and techniques are intended to be included within the scope of the application.

Claims

1. A method for guiding smart elderly care services, characterized in that, include: Obtain a set of health and wellness service data to be processed that contains multiple target health management information, filter the target health management information for key health guidance information, and generate first health guidance information; The first health guidance information is converted into multi-dimensional vector data, and the multi-dimensional vector data is used as the second health guidance information; The second health guidance information is analyzed using a multi-source analysis method to generate a first analysis result containing multi-dimensional features; Based on the similarity between the first analysis result and the multidimensional features of the sub-health directories in the preset health directory, the sub-health directory to which each target health management information belongs is determined, and each sub-health directory corresponds to at least one set of health information guidance strategies. Based on the first analysis results corresponding to each target health management information in the same sub-health catalog, individual characteristic difference parameters are extracted, and a final personalized health and wellness service guidance result is generated based on the individual characteristic difference parameters.

2. The intelligent elderly care service guidance method according to claim 1, characterized in that, The multi-source analysis method includes at least two different analysis techniques to generate a first analysis result containing multidimensional features, including disease type features, service type features, psychological state features, disease development features, and lifestyle feature.

3. The intelligent elderly care service guidance method according to claim 1, characterized in that, The step of determining the sub-health directory to which each target health management information belongs based on the similarity between the first analysis result and the multidimensional features of the sub-health directories in the preset health directory includes: Calculate the feature similarity between the first analysis result and the sub-health catalog in different dimensions; When the feature similarity meets a preset threshold, the corresponding target health management information belongs to the sub-health directory.

4. The intelligent elderly care service guidance method according to claim 3, characterized in that, The similarity is calculated in the following way: Similarity = Second quantity / First quantity; Wherein, the first quantity is the number of feature dimensions that are commonly included in the first analysis result and the sub-health catalog; the second quantity is the number of dimensions among the common feature dimensions whose analysis results are completely consistent.

5. The intelligent elderly care service guidance method according to claim 4, characterized in that, The preset threshold is dynamically adjusted based on the number of categories in the sub-health directory. The adjustment steps include: when the number of categories is less than 5, the preset threshold is set to 0.8; when the number of categories is between 5 and 10, the preset threshold is set to 0.7; and when the number of categories is greater than 10, the preset threshold is set to 0.

6.

6. The method for guiding smart elderly care services according to claim 1, characterized in that, The step of filtering key health guidance information for the target health management information includes: filtering key health guidance information for the target health management information according to preset filtering rules, wherein the preset filtering rules include keyword matching rules and semantic analysis rules, the keyword matching rules are used to extract information containing specific key health guidance information, and the semantic analysis rules are used to identify semantic content with potential health guidance value.

7. The intelligent elderly care service guidance method according to claim 1, characterized in that, The process of obtaining a set of health and wellness service data to be processed, which contains multiple target health management information, includes: deduplicating, correcting errors, and unifying the format of the original smart health and wellness service data set to generate the set of health and wellness service data to be processed.

8. A smart elderly care service guidance system, characterized in that, include: The data acquisition module is used to acquire the set of health and wellness service data to be processed; The feature extraction module is used to filter key health guidance information from the dataset of health and wellness services to be processed, and generate first health guidance information. The vector conversion module is used to convert the first health guidance information into multi-dimensional vector data to generate the second health guidance information; The multi-source analysis module performs correlation analysis on the second health guidance information through rule engine analysis and machine learning analysis to generate a first analysis result containing multi-dimensional features; The directory matching module calculates the similarity between the first analysis result and the multidimensional features of the sub-health directories in the preset health directory. When the feature similarity meets the preset threshold, the corresponding target health management information is assigned to the sub-health directory. The personalized recommendation module extracts individual characteristic difference parameters from the first analysis results corresponding to each target health management information in the same sub-health directory, and generates a final personalized health and wellness service guidance result based on the individual characteristic difference parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

Images