Patient monitoring method and device based on Internet of Things

Abstract

The invention provides a patient monitoring method and device based on the Internet of Things, and relates to the technical field of Internet of Things monitoring. The method comprises the following steps: determining a target disease type in a monitoring range, and obtaining Internet of Things big data of diseases of the same type according to the target disease type; performing nursing analysis based on behavior information and physiological information on the internet-of-things big data to form internet-of-things monitoring basic big data; and updating the target disease type, collecting new Internet of Things big data according to the updated target disease type, and updating the Internet of Things monitoring basic big data according to the updated Internet of Things big data. According to the method, the acquired internet-of-things nursing monitoring data is further analyzed and processed, so that reference data which can be directly applied by nursing personnel or can assist the nursing personnel in quickly performing high-quality nursing service is formed, and the working pressure of the nursing personnel is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things monitoring technology, and in particular to a patient monitoring method and device based on the Internet of Things. Background Art

[0002] As an important part of the medical field, nursing is faced with the situation of insufficient manpower for many nursing objects, and due to the diversity of needs and the individual needs and requirements of different objects, nursing work is complex, difficult and has high work intensity. With the progress and development of science, improving nursing work, effectively reducing the complexity and difficulty of nursing content, providing personalized nursing services, and reducing the work pressure of nursing staff have become an important issue that needs to be urgently addressed.

[0003] At present, with the development of Internet of Things technology, it has become possible to adjust the form of nursing work through the Internet of Things. There have also been many attempts to deeply integrate Internet of Things technology into nursing work to improve the quality of nursing services and reduce the work pressure of nursing staff. However, most of them are just summarizing the original Internet of Things collected data to nursing staff, which does not really reduce the work pressure of nursing staff and improve the quality of nursing services.

[0004] Therefore, designing patient monitoring methods and devices based on the Internet of Things, and further analyzing and processing the collected IoT nursing monitoring data to form reference data that nursing staff can directly use or assist nursing staff in quickly providing high-quality nursing services, greatly reducing the work pressure of nursing staff, is an urgent problem to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a patient monitoring method based on the Internet of Things. By collecting the Internet of Things big data of the same type of disease according to the disease type of the patient within the monitoring range, sufficient basic analysis data can be obtained in a targeted manner, avoiding the increase in the volume of basic data caused by non-targeted data collection, resulting in a waste of resources. At the same time, nursing data analysis based on behavior and physiology is performed according to the collected Internet of Things big data. On the one hand, full attention is paid to the characteristic information that can be extracted from the monitoring data to form characteristic information that can be used and referenced for subsequent real-time monitoring, thereby helping nursing staff to accurately judge the needs and condition of the patient, and then efficiently and quickly perform nursing treatment, greatly improving the quality of nursing services. On the other hand, sufficient data collection and analysis result data can be obtained through the Internet of Things, which can ensure that the monitoring range of the Internet of Things system can achieve the same level of nursing service quality to a certain extent, and improve the level of nursing services as a whole. In addition, the disease types within the monitoring range are different due to the changes of patients, so the monitoring analysis of new disease types is completed by regularly or based on demand to update the basic Internet of Things data, which can ensure that the nursing services within the monitoring range fully meet the needs of real-time nursing, while making full use of data resources, further improving the quality of nursing services, and reducing the work pressure of nursing staff.

[0006] The purpose of the present invention is also to provide a patient monitoring device based on the Internet of Things, which is beneficial to ensure the efficient and stable implementation of the patient monitoring method based on the Internet of Things by configuring a system device that fully realizes the entire process of the monitoring method. On the one hand, it can continuously and stably collect the Internet of Things data efficiently, and on the other hand, it can also realize in-depth and effective feature extraction and analysis of the Internet of Things data, providing a practical and reliable material basis for patient monitoring, greatly improving the quality of nursing services and reducing the work pressure of nursing staff.

[0007] In a first aspect, the present invention provides a patient monitoring method based on the Internet of Things, including determining the target disease type within the monitoring range, and obtaining Internet of Things big data of the same type of diseases based on the target disease type; performing nursing analysis on the Internet of Things big data based on behavioral information and physiological information to form basic Internet of Things monitoring big data; updating the target disease type, collecting new Internet of Things big data based on the updated target disease type, and updating the basic Internet of Things monitoring big data based on the updated Internet of Things big data.

[0008] In the present invention, the method collects IoT big data of the same type of disease according to the disease type of the patient within the monitoring range, and can obtain sufficient basic analysis data in a targeted manner, avoiding the waste of resources caused by the increase in the volume of basic data due to the non-targeted data collection. At the same time, nursing data analysis based on behavior and physiology is performed according to the collected IoT big data. On the one hand, full attention is paid to the characteristic information that can be extracted from the monitoring data to form characteristic information that can be used and referenced for subsequent real-time monitoring, thereby helping nursing staff to accurately judge the needs and condition of the sick object, and then efficiently and quickly perform nursing treatment, greatly improving the quality of nursing services. On the other hand, sufficient data collection and analysis result data can be obtained through the Internet of Things, which can ensure that the monitoring range of the IoT system can achieve the same level of nursing service quality to a certain extent, and improve the level of nursing services as a whole. In addition, the disease types within the monitoring range are different due to the changes of patients, so the monitoring analysis of new disease types is completed by regularly or based on demand to update the IoT basic data, which can ensure that the nursing services within the monitoring range fully meet the needs of real-time nursing, while making full use of data resources, further improving the quality of nursing services, and reducing the work pressure of nursing staff.

[0009] As a possible implementation method, nursing analysis based on behavioral information and physiological information is performed on IoT big data to form IoT monitoring basic big data, including: extracting demand behavior monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on demand behavior, and forming demand behavior IoT monitoring and nursing basic data; extracting pain behavior monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on pain behavior, and forming pain behavior IoT monitoring and nursing basic data; extracting physiological monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on physiological information, and forming physiological information IoT monitoring and nursing basic data; and combining demand behavior IoT monitoring and nursing basic data, pain behavior IoT monitoring and nursing basic data, and physiological information IoT monitoring and nursing basic information to form IoT monitoring basic big data.

[0010] In the present invention, for nursing operations, the data that can be intuitively collected through monitoring are mainly the patient's behavioral data and the physiological detection data formed by the patient through instruments or detection input devices. Therefore, the in-depth analysis of the Internet of Things big data at the monitoring level is mainly carried out using the important feature data that can be collected by monitoring. As for behavioral monitoring information, the nursing content corresponding to different types of behavioral data is different. Here, demand behavior and pain behavior are strictly distinguished. The nursing work performed by these two behaviors by nursing staff has an important degree of distinction and an absolute distinction between nursing content and nursing concepts. In addition, physiological monitoring data is an important basic data for accurately analyzing and judging the patient's physical condition. Monitoring and analysis based on the Internet of Things must include this type of monitoring data. Therefore, the nursing analysis of the Internet of Things big data includes nursing analysis for demand behavior, nursing analysis for pain behavior, and analysis for physiological monitoring data. Of course, the three types of data have certain interactions when considering different nursing contents for analysis, and can form more reasonable nursing monitoring data, providing accurate data reference for subsequent real-time monitoring.

[0011] As a possible implementation method, the demand behavior monitoring data and the corresponding nursing treatment content in the IoT big data are extracted, and IoT monitoring nursing analysis based on the demand behavior is performed to form basic nursing data for demand behavior IoT monitoring, including: clustering the demand behavior monitoring data according to different nursing treatment items to form different nursing treatment demand behavior monitoring data sets; performing feature extraction on the nursing treatment demand behavior monitoring data sets based on different behavior type information to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment items; and aggregating different nursing treatment demand behavior feature data sets to form basic nursing data for demand behavior IoT monitoring.

[0012] In the present invention, the nursing monitoring and analysis based on demand behavior mainly extracts the characteristic information of the patient's demand behavior. Of course, since different demands will target different nursing treatment items, the characteristic information needs to be clustered on the characteristic information extracted based on the patient object, so as to form sufficient characteristic information. After all, in many cases, the behavioral information contains a certain degree of personalization, so the characteristic data formed by clustering can effectively reduce the impact of personalization on monitoring and analysis.

[0013] As a possible implementation method, feature extraction based on different behavior type information is performed on the nursing treatment demand behavior monitoring data set to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment item, including: extracting language demand monitoring information, performing semantic-based feature analysis, and forming demand behavior language feature information; collecting all demand behavior language feature information in the nursing treatment demand behavior monitoring data set to form a demand behavior language feature information set; extracting action demand monitoring information, and based on a single demand action of a single patient object, decomposing and describing the demand action to form an action description chain corresponding to the single demand action; performing the following intersection operation judgment on all action description chains: if different actions on the same body part If there are no less than 2 adjacent and continuous identical action descriptions in a description chain, any action description chain will be determined as an intersection operation target description chain, and the same action description, the previous action description adjacent to the same action description, and the next action description adjacent to the same action description in the intersection operation target description chain will be extracted to form a characteristic action description chain; if there are less than 2 adjacent and continuous identical action descriptions in different action description chains with the same body part, no extraction will be performed, and different action description chains will be used as characteristic action description chains respectively; all characteristic action description chains are collected to form a demand behavior action feature information set; the demand behavior language feature information set and the demand behavior action feature information set are combined to form a nursing treatment demand behavior feature data set.

[0014] In the present invention, the demand behavior of people is multifaceted. Considering that the nursing object is a patient, most of the patients mainly express their needs in two types of behaviors, one is language behavior and the other is action behavior. For language behavior, basically, the language expression of the needs in the sick state is very straightforward, so the demand feature information can be extracted through simple semantic analysis. For action behavior, basically, the demand of each object each time is the coordination and change of a string of actions, so the feature extraction of action behavior first needs to split the action, and then convert the split action into action description information and form a description chain according to the order of the actions, so that the feature information of the action behavior can be obtained by converting it into an action description chain. On the one hand, the logic of action changes under specific needs can be determined intuitively and clearly, and on the other hand, a unified data type is formed by converting it into text description and language feature information, which is convenient for unified data processing. Of course, in order to further reduce the impact of personalization, after obtaining the action description chain of a single object's single demand, it is helpful to merge and extract the description chain features again to accurately identify the needs more reasonably and efficiently. Of course, the object of feature extraction of the description chain should be the same action part, such as all actions on the hands, all actions on the legs, all actions on the head, etc. The division of action parts can be carried out according to the needs to obtain the most reasonable and effective feature data. In addition, it should be noted that for the needs of patients, basically different action types can transmit demand information separately, so the extracted language feature information and action feature information of different parts can be used separately as comparative reference data for subsequent real-time demand behavior monitoring. As long as one of them matches, it can be considered that the patient has the corresponding demand.

[0015] As a possible implementation method, the pain behavior monitoring data and the corresponding nursing treatment content in the IoT big data are extracted, and IoT monitoring and nursing analysis based on pain behavior is performed to form basic IoT monitoring and nursing data for pain behavior, including: extracting pain movement monitoring information and pain physiological monitoring information based on a single treatment of a single subject, and performing feature extraction and matching analysis based on the time dimension to form pain unit matching nursing data; based on the pain unit matching nursing data, clustering analysis is performed on the pain unit matching data based on the same nursing content to form similar nursing pain matching data; based on different similar nursing pain matching data, a combined analysis of nursing content for pain behavior is performed to form pain behavior nursing treatment data.

[0016] In the present invention, the monitoring and nursing analysis of pain behavior takes into account the important influence of the two factors of disease type and disease duration on pain behavior. Therefore, when performing the analysis, the data basis for the analysis is the pain behavior data involved in a single treatment of a single subject. Of course, the patient's pain behavior is often not only manifested in the pain action behavior, but also in the physiological monitoring data, so the analysis requires the simultaneous analysis and processing of the pain action behavior data and the physiological monitoring data to form sufficient and reasonable feature information to ensure the accuracy of subsequent real-time monitoring and analysis.

[0017] As a possible implementation method, pain action monitoring information and pain physiological monitoring information are extracted based on a single treatment of a single object, and feature extraction and matching analysis based on the time dimension is performed to form pain unit matching nursing data, including: extracting the pain action monitoring information corresponding to a single treatment of a single object, and decomposing and describing the action behavior to form a pain action description chain; extracting the pain physiological monitoring information corresponding to a single treatment of a single object, and determining the parameter change values ​​of all pain physiological monitoring parameters in the pain period defined by the corresponding pain action description chain to form pain physiological monitoring feature information; matching the pain physiological monitoring feature information with the corresponding pain action description chain in the time dimension to form pain unit matching data; matching the pain unit matching data with the nursing treatment content corresponding to the single treatment of the single object to form pain unit matching nursing data.

[0018] In the present invention, the feature extraction of the pain action monitoring information and the pain physiological monitoring information of a single subject in a single treatment unit can be performed by first extracting the features of the pain action monitoring information and the pain physiological monitoring information respectively and then performing matching processing. Of course, since the type and form of the data will change after feature extraction, it is necessary to determine a reference basis for accurately matching the two feature information. Here, considering that the actions have sequence and the physiological monitoring data also have variability, the accurate coordination of the two feature information can be ensured by establishing a matching connection through time parameters.

[0019] As a possible implementation method, according to the pain unit matching nursing data, the pain unit matching data is clustered based on the same nursing content to form the same nursing pain matching data, including: clustering all pain unit matching nursing data corresponding to the same disease to form the same disease pain nursing data set; clustering and merging analysis of the pain unit matching data with the same nursing content in the same disease pain nursing data set in the following manner: if there are different pain unit matching data, the pain action description chain corresponds to each other, and all parameters in the pain physiological monitoring feature information form a merging range with endpoint values, and all parameters of other pain physiological monitoring feature information belong to the merging range of the corresponding parameters, then the different pain unit matching data are merged; otherwise, no merging is performed; all pain unit matching data sets after the clustering and merging analysis are completed are collected to form the same nursing pain matching data.

[0020] In the present invention, it can be understood that for a single subject, the range defined by the physiological monitoring characteristic data obtained by a single treatment is relatively narrow, and sometimes the value of the parameter on the physiological monitoring characteristic information corresponding to a single treatment of a single subject is a fixed value. For the physiological monitoring characteristic data using the same nursing content, there will inevitably be differences, especially in the parameter values. Therefore, it is necessary to conduct a reasonable cluster analysis to determine the reasonable value range corresponding to the parameters in the physiological monitoring characteristic data under each nursing content. Here, when performing cluster merging analysis, the matching consistency of the description of the pain action is mainly aimed at the consistency of the pain action in the same part. Of course, this consistency does not necessarily mean that all descriptions in the description chain must be consistent. It can also be judged by setting a consistency percentage and can be designed and determined according to the actual situation. In addition, when performing clustering and merging analysis, the parameters must form a reasonable range, and it is necessary to judge whether the merged range is correct. Here, the judgment is made based on whether the parameters of other physiological monitoring data belong to the corresponding range. On the one hand, the other physiological monitoring data here are mainly physiological monitoring data with different nursing contents corresponding to the clustered and merged physiological monitoring data. On the other hand, whether they belong to the corresponding range should be judged for all parameters, that is, for other physiological monitoring data, only when the values ​​of all parameters belong to the corresponding merged range will the merge be considered not allowed. Otherwise, clustering and merging processing can be performed.

[0021] As a possible implementation method, based on different similar nursing pain matching data, a combined analysis of nursing content for pain behavior is conducted to form pain behavior nursing treatment data, including: for the similar nursing pain matching data corresponding to different nursing contents, taking the pain unit matching data as the leading factor, establishing the corresponding relationship between each pain unit matching data and the nursing content, and forming pain unit matching-nursing content data; setting similar parameter judgment factors, and conducting the following combined analysis on the similar nursing pain matching data corresponding to different nursing contents in the pain unit matching-nursing content data: if two different nursing contents are matched, the corresponding relationship between each pain unit matching data and the nursing content is established, and ... If, in the corresponding similar nursing pain matching data, there are pain unit matching data with the same pain action description chain, and the ratio of the non-intersection segment to the intersection segment of the value range corresponding to each parameter in the pain physiological monitoring feature information is not greater than the corresponding similar parameter judgment factor, then the two pain unit matching data are merged, and the two nursing contents corresponding to the pain unit matching data are determined as the corresponding nursing content set after the merger; otherwise, no merger is performed; the merged nursing content set and the corresponding pain unit matching data as well as the nursing contents that are not merged and the corresponding pain unit matching data are combined to form pain behavior nursing treatment data.

[0022] In the present invention, different nursing contents can also correspond to the same pain behavior monitoring data. Therefore, after completing the clustering and merging analysis of the pain behavior monitoring data under the same nursing content, it is also necessary to perform a merging analysis of the pain behavior monitoring data under different nursing contents, so as to provide the most perfect different nursing content selection for pain nursing, which is conducive to improving the quality of nursing services. When performing the merging analysis, the dynamic description chain needs to be analyzed for consistency judgment. For the physiological monitoring data, the ratio of the intersection width and the non-intersection width of the two ranges of the parameters is used for analysis and judgment. Of course, since the parameters of the physiological monitoring data have a certain connection, only when all parameters meet the requirements can they be considered to be merged.

[0023] As a possible implementation method, physiological monitoring data and corresponding nursing processing contents in IoT big data are extracted, and IoT monitoring and nursing analysis based on physiological information is performed to form basic data of physiological information IoT monitoring and nursing, including: taking a single object single nursing as a unit, extracting physiological monitoring information and corresponding auxiliary nursing processing contents to form physiological monitoring auxiliary nursing processing content data; performing a combined analysis on different physiological monitoring auxiliary nursing processing contents in the following manner: if all parameters of physiological monitoring information under different physiological monitoring auxiliary nursing processing contents have an intersection, then performing a AND operation on the corresponding parameters to form a combined range, and forming a combined corresponding auxiliary nursing processing content set by combining the auxiliary nursing processing content sets corresponding to the two physiological monitoring information respectively; if different physiological monitoring auxiliary nursing processing If all parameters of the physiological monitoring information under the physiological monitoring content do not have an intersection, but the merged range formed after the merger does not have parameters of other physiological monitoring information that belong to the corresponding merged range, the corresponding parameters are taken and operated to form a merged range, and the auxiliary nursing processing content sets corresponding to the two physiological monitoring information are respectively formed into the corresponding auxiliary nursing processing content set after the merger; if all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents do not have an intersection, and the merged range formed after the merger has parameters of other physiological monitoring information that belong to the corresponding merged range, no merger is performed; all merged physiological monitoring information and corresponding auxiliary nursing processing content sets as well as unmerged physiological monitoring information and corresponding auxiliary nursing processing contents are collected to form physiological information IoT monitoring and nursing basic data.

[0024] In the present invention, it should be noted that the monitoring and nursing analysis of pain behavior is mainly aimed at extracting the monitoring data feature information of the nursing content mainly for treatment, and the auxiliary nursing for non-treatment such as low blood sugar and dehydration that occurs during the usual nursing process is also determined based on the physiological monitoring data, so the feature information extraction of the physiological monitoring data corresponding to this type of nursing treatment is also necessary. The nursing content is merged and processed based on the comparison of physiological monitoring information with a single nursing treatment of a single object as the data unit to form reasonable and accurate nursing treatment data corresponding to the physiological monitoring information.

[0025] In a second aspect, the present invention provides a patient monitoring device based on the Internet of Things, which is configured to determine the target disease type within the monitoring range, and obtain Internet of Things big data of the same type of diseases based on the target disease type; perform nursing analysis on the Internet of Things big data based on behavioral information and physiological information to form basic Internet of Things monitoring big data; update the target disease type, collect new Internet of Things big data based on the updated target disease type, and update and process the basic Internet of Things monitoring big data based on the updated Internet of Things big data.

[0026] In the present invention, the system equipment that fully realizes the whole process of the monitoring method is configured to ensure the efficient and stable implementation of the patient monitoring method based on the Internet of Things. On the one hand, the Internet of Things data can be continuously and stably collected efficiently, and on the other hand, in-depth and effective feature extraction and analysis of the Internet of Things data can be achieved, providing a practical and reliable material basis for patient monitoring, greatly improving the quality of nursing services and reducing the work pressure of nursing staff.

[0027] The beneficial effects of the patient monitoring method and device based on the Internet of Things provided by the present invention are:

[0028] This method collects IoT big data of the same type of diseases according to the disease type of the patients within the monitoring range, and can obtain sufficient basic analysis data in a targeted manner, avoiding the waste of resources caused by the increase in the volume of basic data due to non-targeted data collection. At the same time, nursing data analysis based on behavior and physiology is carried out according to the collected IoT big data. On the one hand, full attention is paid to the characteristic information that can be extracted from the monitoring data to form characteristic information that can be used and referenced for subsequent real-time monitoring, thereby helping nursing staff to accurately judge the needs and conditions of the sick objects, and then efficiently and quickly perform nursing treatment, greatly improving the quality of nursing services. On the other hand, sufficient data collection and analysis result data can be obtained through the Internet of Things, which can ensure that the monitoring range of the establishment of the IoT system can achieve the same level of nursing service quality to a certain extent, and improve the level of nursing services as a whole. In addition, the disease types within the monitoring range are different due to the changes of patients. Therefore, the IoT basic data is updated regularly or based on demand to complete the monitoring and analysis of new disease types, which can ensure that the nursing services within the monitoring range fully meet the needs of real-time nursing, while making full use of data resources, further improving the quality of nursing services, and reducing the work pressure of nursing staff.

[0029] The device is configured with system equipment that fully realizes the whole process of the monitoring method to ensure the efficient and stable implementation of the patient monitoring method based on the Internet of Things. On the one hand, it can continuously and stably collect IoT data efficiently, and on the other hand, it can also realize in-depth and effective feature extraction and analysis of IoT data, providing a practical and reliable material basis for patient monitoring, greatly improving the quality of nursing services and reducing the work pressure of nursing staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 A step diagram of a patient monitoring method based on the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0033] As an important part of the medical field, nursing is faced with the situation of insufficient manpower for many nursing objects, and due to the diversity of needs and the individual needs and requirements of different objects, nursing work is complex, difficult and has high work intensity. With the progress and development of science, improving nursing work, effectively reducing the complexity and difficulty of nursing content, providing personalized nursing services, and reducing the work pressure of nursing staff have become an important issue that needs to be urgently addressed.

[0034] At present, with the development of Internet of Things technology, it has become possible to adjust the form of nursing work through the Internet of Things. There have also been many attempts to deeply integrate Internet of Things technology into nursing work to improve the quality of nursing services and reduce the work pressure of nursing staff. However, most of them are just summarizing the original Internet of Things collected data to nursing staff, which does not really reduce the work pressure of nursing staff and improve the quality of nursing services.

[0035] refer to Figure 1 , the embodiment of the present invention provides a patient monitoring method based on the Internet of Things. The method can obtain sufficient basic analysis data in a targeted manner by collecting Internet of Things big data of the same type of disease according to the disease type of the patient within the monitoring range, avoiding the waste of resources caused by the increase in the volume of basic data due to non-targeted data collection. At the same time, nursing data analysis based on behavior and physiology is performed based on the collected Internet of Things big data. On the one hand, full attention is paid to the characteristic information that can be extracted from the monitoring data to form characteristic information that can be used and referenced for subsequent real-time monitoring, thereby helping nursing staff to accurately judge the needs and condition of the patient, and then efficiently and quickly perform nursing treatment, greatly improving the quality of nursing services. On the other hand, sufficient data collection and analysis result data can be obtained through the Internet of Things, which can ensure that the monitoring range of the establishment of the Internet of Things system can achieve the same level of nursing service quality to a certain extent, and improve the level of nursing services as a whole. In addition, the disease types within the monitoring range are different due to the changes of patients. Therefore, the monitoring analysis of new disease types is completed by updating the basic Internet of Things data regularly or based on demand, which can ensure that the nursing services within the monitoring range fully meet the needs of real-time nursing, while making full use of data resources, further improving the quality of nursing services, and reducing the work pressure of nursing staff.

[0036] The IoT-based patient monitoring method specifically includes the following steps:

[0037] S1: Determine the target disease types within the monitoring scope, and obtain IoT big data of the same type of diseases based on the target disease types.

[0038] First, determine the types of diseases within the monitoring scope, and then obtain the IoT big data of these diseases in a targeted manner. On the one hand, it avoids the waste of resources caused by aimless data collection, and on the other hand, it greatly improves the efficiency of data collection and processing.

[0039] S2: Conduct nursing analysis on IoT big data based on behavioral information and physiological information to form basic IoT monitoring big data.

[0040] Nursing analysis based on behavioral information and physiological information is performed on IoT big data to form IoT monitoring basic big data, including: extracting demand behavior monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on demand behavior, and forming demand behavior IoT monitoring and nursing basic data; extracting pain behavior monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on pain behavior, and forming pain behavior IoT monitoring and nursing basic data; extracting physiological monitoring data and corresponding nursing processing content from IoT big data, performing IoT monitoring and nursing analysis based on physiological information, and forming physiological information IoT monitoring and nursing basic data; gathering demand behavior IoT monitoring and nursing basic data, pain behavior IoT monitoring and nursing basic data, and physiological information IoT monitoring and nursing basic information to form IoT monitoring basic big data.

[0041] For nursing work, the data that can be directly collected through monitoring are mainly the patient's behavior data and the physiological detection data formed by the patient through instruments or detection input devices. Therefore, the in-depth analysis of IoT big data at the monitoring level is mainly carried out using the important feature data that can be collected by monitoring. As for behavioral monitoring information, different types of behavioral data correspond to different nursing contents. Here, demand behavior and pain behavior are strictly distinguished. The nursing work performed by nursing staff for these two behaviors has an important degree of distinction and an absolute distinction between nursing content and nursing concepts. In addition, physiological monitoring data is an important basic data for accurately analyzing and judging the patient's physical condition. Monitoring and analysis based on the Internet of Things must include this type of monitoring data. Therefore, the nursing analysis of IoT big data includes nursing analysis for demand behavior, nursing analysis for pain behavior, and analysis for physiological monitoring data. Of course, the three types of data have certain interactions when considering different nursing contents for analysis, which can form more reasonable nursing monitoring data and provide accurate data reference for subsequent real-time monitoring.

[0042] Among them, the demand behavior monitoring data and the corresponding nursing treatment content in the IoT big data are extracted, and IoT monitoring nursing analysis based on the demand behavior is performed to form basic data of demand behavior IoT monitoring nursing, including: clustering the demand behavior monitoring data according to different nursing treatment items to form different nursing treatment demand behavior monitoring data sets; performing feature extraction based on different behavior type information on the nursing treatment demand behavior monitoring data sets to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment items; and aggregating different nursing treatment demand behavior feature data sets to form basic data of demand behavior IoT monitoring nursing.

[0043] Nursing monitoring and analysis based on demand behavior mainly involves extracting characteristic information of patients' demand behavior. Of course, since different demands will target different nursing treatment items, the characteristic information needs to be clustered on the characteristic information extracted based on the patient object, so as to form sufficient characteristic information. After all, behavioral information often contains a certain degree of personalization, so the characteristic data formed by clustering can effectively reduce the impact of personalization on monitoring and analysis.

[0044] The feature extraction based on different behavior type information is performed on the nursing treatment demand behavior monitoring data set to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment item, including: extracting language demand monitoring information, performing semantic-based feature analysis, and forming demand behavior language feature information; collecting all demand behavior language feature information in the nursing treatment demand behavior monitoring data set to form a demand behavior language feature information set; extracting action demand monitoring information, and based on a single demand action of a single patient object, performing decomposition and action description of the demand action to form an action description chain corresponding to the single demand action; performing the following intersection operation judgment on all action description chains: if there are multiple different action description chains with the same body part, If the number of adjacent and continuous action descriptions that are not less than 2 are the same, any action description chain will be determined as the intersection operation target description chain, and the same action description, the previous action description adjacent to the same action description, and the next action description adjacent to the same action description in the intersection operation target description chain will be extracted to form a characteristic action description chain; if different action description chains with the same body part have less than 2 adjacent and continuous action descriptions that are the same, no extraction will be performed, and different action description chains will be used as characteristic action description chains respectively; all characteristic action description chains are collected to form a demand behavior action feature information set; the demand behavior language feature information set and the demand behavior action feature information set are combined to form a nursing treatment demand behavior feature data set.

[0045] People's demand behaviors are multifaceted. Considering that the nursing object is a patient, most patients' main demand expressions are in two types of behaviors, one is language behavior and the other is action behavior. For language behavior, basically, the language expression of demand in the sick state is very straightforward, so the demand feature information can be extracted through simple semantic analysis. For action behavior, basically, each object's demand each time is a series of action coordination and changes. Therefore, the feature extraction of action behavior first requires the action to be split, and then the split action is converted into action description information and a description chain is formed according to the order of the action. In this way, by converting to an action description chain to obtain the feature information of the action behavior, on the one hand, the logic of action changes under specific needs can be determined intuitively and clearly, and on the other hand, a unified data type is formed by converting to text description and language feature information, which facilitates the unified processing of data. Of course, in order to further reduce the impact of personalization, after obtaining the action description chain of a single object's single demand, it is helpful to merge and extract the description chain features again to accurately identify the needs more reasonably and efficiently. Of course, the object of feature extraction of the description chain should be the same action part, such as all actions on the hands, all actions on the legs, all actions on the head, etc. The division of action parts can be carried out according to the needs to obtain the most reasonable and effective feature data. In addition, it should be noted that for the needs of patients, basically different action types can transmit demand information separately, so the extracted language feature information and action feature information of different parts can be used separately as comparative reference data for subsequent real-time demand behavior monitoring. As long as one of them matches, it can be considered that the patient has the corresponding demand.

[0046] Extract the pain behavior monitoring data and the corresponding nursing treatment content from the IoT big data, conduct IoT monitoring and nursing analysis based on pain behavior, and form basic IoT monitoring and nursing data for pain behavior, including: extract pain movement monitoring information and pain physiology monitoring information based on a single treatment of a single subject, and conduct feature extraction and matching analysis based on the time dimension to form pain unit matching nursing data; based on the pain unit matching nursing data, perform cluster analysis on the pain unit matching data based on the same nursing content to form similar nursing pain matching data; based on different similar nursing pain matching data, conduct a combined analysis of nursing content for pain behavior to form pain behavior nursing treatment data.

[0047] The monitoring and nursing analysis of pain behavior takes into account the important influence of the type of illness and the duration of illness. Therefore, when conducting the analysis, the data basis for the analysis is the pain behavior data involved in a single treatment of a single subject. Of course, the patient's pain behavior is often not only manifested in the pain movement behavior, but also in the physiological monitoring data. Therefore, the analysis requires the simultaneous analysis and processing of the pain movement behavior data and the physiological monitoring data to form sufficient and reasonable feature information to ensure the accuracy of subsequent real-time monitoring and analysis.

[0048] Taking a single treatment of a single object as a unit, pain action monitoring information and pain physiological monitoring information are extracted, and feature extraction matching analysis based on the time dimension is performed to form pain unit matching nursing data, including: extracting the pain action monitoring information corresponding to a single treatment of a single object, and decomposing and describing the action behavior to form a pain action description chain; extracting the pain physiological monitoring information corresponding to a single treatment of a single object, and determining the parameter change values ​​of all pain physiological monitoring parameters in the pain period defined by the corresponding pain action description chain to form pain physiological monitoring feature information; matching the pain physiological monitoring feature information with the corresponding pain action description chain in the time dimension to form pain unit matching data; matching the pain unit matching data with the nursing treatment content corresponding to the single treatment of a single object to form pain unit matching nursing data.

[0049] The feature extraction of pain action monitoring information and pain physiological monitoring information for a single subject in a single treatment can be done by first extracting features from the pain action monitoring information and the pain physiological monitoring information respectively and then matching them. Of course, since the type and form of the data will change after feature extraction, it is necessary to determine a reference basis for accurately matching the two feature information. Here, considering that the actions are sequential and the physiological monitoring data are also variable, the matching connection established through the time parameter can ensure the accurate coordination of the two feature information.

[0050] According to the pain unit matching nursing data, cluster analysis is performed on the pain unit matching data based on the same nursing content to form the same type of nursing pain matching data, including: clustering all pain unit matching nursing data corresponding to the same disease to form the same disease pain nursing data set; clustering and merging analysis is performed on the pain unit matching data with the same nursing content in the same disease pain nursing data set in the following manner: if there are different pain unit matching data, the pain action description chain corresponds to each other, and all parameters in the pain physiological monitoring feature information form a merging range with endpoint values, and all parameters of other pain physiological monitoring feature information belong to the merging range of the corresponding parameters, then the different pain unit matching data are merged; otherwise, no merging is performed; all pain unit matching data sets after the cluster merging analysis are completed are collected to form the same type of nursing pain matching data.

[0051] It is understandable that for a single subject, the range defined by the physiological monitoring characteristic data obtained by a single treatment is relatively narrow, and sometimes the parameter value of the physiological monitoring characteristic information corresponding to a single treatment of a single subject is a fixed value. For the physiological monitoring characteristic data using the same nursing content, there will inevitably be differences, especially in the parameter values. Therefore, a reasonable cluster analysis is required to determine the reasonable value range corresponding to the parameters in the physiological monitoring characteristic data under each nursing content. Here, when performing cluster merging analysis, the matching consistency of the description of the pain action is mainly aimed at the consistency of the pain action in the same part. Of course, this consistency does not necessarily mean that all descriptions in the description chain must be consistent. It can also be judged by setting a consistency percentage and can be designed and determined according to the actual situation. In addition, when performing clustering and merging analysis, the parameters must form a reasonable range, and it is necessary to judge whether the merged range is correct. Here, the judgment is made based on whether the parameters of other physiological monitoring data belong to the corresponding range. On the one hand, the other physiological monitoring data here are mainly physiological monitoring data with different nursing contents corresponding to the clustered and merged physiological monitoring data. On the other hand, whether they belong to the corresponding range should be judged for all parameters, that is, for other physiological monitoring data, only when the values ​​of all parameters belong to the corresponding merged range will the merge be considered not allowed. Otherwise, clustering and merging processing can be performed.

[0052] According to different similar nursing pain matching data, a nursing content merger analysis for pain behavior is performed to form pain behavior nursing treatment data, including: for similar nursing pain matching data corresponding to different nursing contents, taking pain unit matching data as the main factor, a corresponding relationship between each pain unit matching data and the nursing content is established to form pain unit matching-nursing content data; setting similar parameter judgment factors, and performing the following merger analysis on similar nursing pain matching data corresponding to different nursing contents in the pain unit matching-nursing content data: if in similar nursing pain matching data corresponding to two different nursing contents, there are pain unit matching data with the same pain action description chain, and the ratio of the non-intersection segment to the intersection segment of the value range corresponding to each parameter in the pain physiological monitoring feature information is not greater than the corresponding similar parameter judgment factor, then the two pain unit matching data are merged, and the two nursing contents corresponding to the pain unit matching data are determined as the corresponding nursing content set after the merger; otherwise, no merger is performed; the merged nursing content set and the corresponding pain unit matching data as well as the nursing contents and the corresponding pain unit matching data that are not merged are combined to form pain behavior nursing treatment data.

[0053] Different nursing contents can also correspond to the same pain behavior monitoring data. Therefore, after completing the clustering and merging analysis of pain behavior monitoring data under the same nursing content, it is also necessary to conduct a merging analysis of pain behavior monitoring data under different nursing contents, so as to provide pain nursing with the best possible selection of different nursing contents, which is conducive to improving the quality of nursing services. When conducting a merging analysis, the dynamic description chain needs to be analyzed for consistency judgment. For physiological monitoring data, the ratio of the intersection width of the two ranges of the parameters to the non-intersection width is used for analysis and judgment. Of course, since there is a certain connection between the parameters of the physiological monitoring data, only when all parameters meet the requirements can they be considered to be merged.

[0054] Extract the physiological monitoring data and the corresponding nursing processing content in the IoT big data, conduct IoT monitoring and nursing analysis based on physiological information, and form basic data of physiological information IoT monitoring and nursing, including: extracting physiological monitoring information and corresponding auxiliary nursing processing content based on a single nursing of a single object to form physiological monitoring auxiliary nursing processing content data; performing a combined analysis on different physiological monitoring auxiliary nursing processing contents in the following manner: if all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents have an intersection, then perform a AND operation on the corresponding parameters to form a combined range, and form a combined corresponding auxiliary nursing processing content set corresponding to the two physiological monitoring information respectively; if the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents have an intersection, then perform a AND operation on the corresponding parameters to form a combined range, and form a combined corresponding auxiliary nursing processing content set; if the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents have an intersection, then perform a AND operation on the corresponding parameters to form a combined corresponding auxiliary nursing processing content set. If all parameters of the physiological monitoring information do not have an intersection, but the merged range formed after the merger does not have parameters of other physiological monitoring information that belong to the corresponding merged range, the corresponding parameters are taken and operated to form a merged range, and the auxiliary nursing processing content sets corresponding to the two physiological monitoring information are respectively formed into the corresponding auxiliary nursing processing content set after the merger; if all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents do not have an intersection, and the merged range formed after the merger has parameters of other physiological monitoring information that belong to the corresponding merged range, no merger is performed; all merged physiological monitoring information and corresponding auxiliary nursing processing content sets as well as unmerged physiological monitoring information and corresponding auxiliary nursing processing contents are collected to form physiological information IoT monitoring and nursing basic data.

[0055] It should be noted that the monitoring and nursing analysis of pain behavior is mainly aimed at extracting the characteristic information of monitoring data of nursing content mainly for treatment, while auxiliary nursing for non-therapeutic purposes such as low blood sugar and dehydration that occur during normal nursing is also determined based on physiological monitoring data, so it is also necessary to extract characteristic information of physiological monitoring data corresponding to this type of nursing treatment. Taking a single nursing treatment of a single object as the data unit, the nursing content is merged and processed based on the comparison of physiological monitoring information to form reasonable and accurate nursing treatment data corresponding to the physiological monitoring information.

[0056] S3: Update the target disease types, collect new IoT big data based on the updated target disease types, and update the IoT monitoring basic big data based on the updated IoT big data.

[0057] According to the steps of S2, reasonable data analysis is performed on the IoT big data collected due to new diseases caused by changes in patients within the monitoring range, and then the basic IoT monitoring big data is updated to ensure the validity and real-time nature of the data.

[0058] The present invention also provides a patient monitoring device based on the Internet of Things. The device adopts the patient monitoring method based on the Internet of Things provided by the present invention. The device is configured to determine the type of target disease within the monitoring range, and obtain Internet of Things big data of the same type of diseases based on the type of target disease; perform nursing analysis on the Internet of Things big data based on behavioral information and physiological information to form basic Internet of Things monitoring big data; update the type of target disease, collect new Internet of Things big data based on the updated type of target disease, and update the basic Internet of Things monitoring big data based on the updated Internet of Things big data.

[0059] The device is configured with system equipment that fully realizes the whole process of the monitoring method to ensure the efficient and stable implementation of the patient monitoring method based on the Internet of Things. On the one hand, it can continuously and stably collect IoT data efficiently, and on the other hand, it can also realize in-depth and effective feature extraction and analysis of IoT data, providing a practical and reliable material basis for patient monitoring, greatly improving the quality of nursing services and reducing the work pressure of nursing staff.

[0060] In summary, the beneficial effects of the patient monitoring method and device based on the Internet of Things provided by the embodiments of the present invention are:

[0061] This method collects IoT big data of the same type of diseases according to the disease type of the patients within the monitoring range, and can obtain sufficient basic analysis data in a targeted manner, avoiding the waste of resources caused by the increase in the volume of basic data due to non-targeted data collection. At the same time, nursing data analysis based on behavior and physiology is carried out according to the collected IoT big data. On the one hand, full attention is paid to the characteristic information that can be extracted from the monitoring data to form characteristic information that can be used and referenced for subsequent real-time monitoring, thereby helping nursing staff to accurately judge the needs and conditions of the sick objects, and then efficiently and quickly perform nursing treatment, greatly improving the quality of nursing services. On the other hand, sufficient data collection and analysis result data can be obtained through the Internet of Things, which can ensure that the monitoring range of the establishment of the IoT system can achieve the same level of nursing service quality to a certain extent, and improve the level of nursing services as a whole. In addition, the disease types within the monitoring range are different due to the changes of patients. Therefore, the IoT basic data is updated regularly or based on demand to complete the monitoring and analysis of new disease types, which can ensure that the nursing services within the monitoring range fully meet the needs of real-time nursing, while making full use of data resources, further improving the quality of nursing services, and reducing the work pressure of nursing staff.

[0062] The device is configured with system equipment that fully realizes the whole process of the monitoring method to ensure the efficient and stable implementation of the patient monitoring method based on the Internet of Things. On the one hand, it can continuously and stably collect IoT data efficiently, and on the other hand, it can also realize in-depth and effective feature extraction and analysis of IoT data, providing a practical and reliable material basis for patient monitoring, greatly improving the quality of nursing services and reducing the work pressure of nursing staff.

[0063] In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved by means of the arrangement order of each piece of information agreed in advance (for example, specified by the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can also be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0064] In addition, the specific indication method may also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can refer to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, different indication methods may be used for different information. In the specific implementation process, the desired indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0065] It should be understood that the information to be indicated can be sent as a whole, or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiment of the present application. Among them, the sending period and / or sending time of these sub-information can be pre-defined, for example, pre-defined according to a protocol, or can be configured by the sending end device by sending configuration information to the receiving end device.

[0066] "Pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiments of the present application do not limit the specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, which is not limited by the embodiments of the present application.

[0067] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems, and the embodiments of the present application do not make specific limitations on this.

[0068] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will make corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to have a judgment action when implementing it, nor does it mean that there are other limitations.

[0069] In the description of the embodiments of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or its similar expression refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solution of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish the same or similar items with basically the same functions and effects. Those skilled in the art will appreciate that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0070] It should be understood that the processor in the embodiment of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0071] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0072] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0073] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0074] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0075] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0076] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0078] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0081] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0082] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A patient monitoring method based on the Internet of Things, characterized in that: include: Determine the target disease types within the monitoring scope, and obtain IoT big data of the same type of diseases based on the target disease types; Performing nursing analysis on the IoT big data based on behavioral information and physiological information to form IoT monitoring basic big data; The target disease categories are updated, new IoT big data are collected according to the updated target disease categories, and the IoT monitoring basic big data are updated according to the updated IoT big data.

2. The patient monitoring method based on the Internet of Things according to claim 1, characterized in that: The nursing analysis of the IoT big data based on behavioral information and physiological information to form IoT monitoring basic big data includes: Extracting demand behavior monitoring data and corresponding nursing processing content from the IoT big data, performing IoT monitoring and nursing analysis based on demand behavior, and forming basic data of demand behavior IoT monitoring and nursing; Extracting the pain behavior monitoring data and the corresponding nursing treatment content in the IoT big data, performing IoT monitoring and nursing analysis based on pain behavior, and forming basic IoT monitoring and nursing data for pain behavior; Extracting physiological monitoring data and corresponding nursing processing content from the IoT big data, performing IoT monitoring and nursing analysis based on physiological information, and forming basic data of physiological information IoT monitoring and nursing; The demand behavior IoT monitoring and nursing basic data, the pain behavior IoT monitoring and nursing basic data, and the physiological information IoT monitoring and nursing basic information are collected to form the IoT monitoring basic big data.

3. The patient monitoring method based on the Internet of Things according to claim 2, characterized in that: The extracting of demand behavior monitoring data and corresponding nursing processing content in the IoT big data, performing IoT monitoring and nursing analysis based on demand behavior, and forming demand behavior IoT monitoring and nursing basic data includes: Clustering the demand behavior monitoring data according to different nursing treatment items to form different nursing treatment demand behavior monitoring data sets; Extracting features of the nursing treatment demand behavior monitoring data set based on information of different behavior types to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment item; The different nursing processing demand behavior characteristic data sets are collected to form the demand behavior IoT monitoring nursing basic data.

4. The method for monitoring patients based on the Internet of Things according to claim 3, characterized in that: The step of extracting features of the nursing treatment demand behavior monitoring data set based on information of different behavior types to form a nursing treatment demand behavior feature data set corresponding to the nursing treatment item includes: Extract language demand monitoring information, conduct semantic-based feature analysis, and form demand behavior language feature information; Gathering all the demand behavior language feature information in the nursing treatment demand behavior monitoring data set to form a demand behavior language feature information set; Extract action-type demand monitoring information, and based on a single demand action of a single patient object, decompose and describe the demand action to form an action description chain corresponding to the single demand action; The following intersection operation is performed on all the action description chains: If there are no less than 2 adjacent and continuous identical action descriptions in different action description chains with the same body part, any one of the action description chains will be determined as an intersection operation target description chain, and the identical action description, the previous action description adjacent to the identical action description, and the next action description adjacent to the identical action description in the intersection operation target description chain will be extracted to form a feature action description chain; If the number of adjacent and continuous identical action descriptions in different action description chains with the same body part is less than 2, no extraction is performed, and the different action description chains are respectively used as feature action description chains; Gather all the characteristic action description chains to form a demand behavior action characteristic information set; The nursing treatment demand behavior characteristic data set is formed by combining the demand behavior language characteristic information set and the demand behavior action characteristic information set.

5. The method for monitoring patients based on the Internet of Things according to claim 4, characterized in that: The step of extracting the pain behavior monitoring data and the corresponding nursing processing content from the IoT big data, performing IoT monitoring and nursing analysis based on pain behavior, and forming basic pain behavior IoT monitoring and nursing data includes: Extract pain motion monitoring information and pain physiological monitoring information based on a single treatment of a single subject, and perform feature extraction and matching analysis based on the time dimension to form pain unit matching nursing data; According to the pain unit matching nursing data, cluster analysis is performed on the pain unit matching data based on the same nursing content to form the same type of nursing pain matching data; Based on the different similar nursing pain matching data, a combined analysis of the nursing content for pain behaviors is performed to form pain behavior nursing treatment data.

6. The method for monitoring patients based on the Internet of Things according to claim 5, characterized in that: The method of extracting pain motion monitoring information and pain physiological monitoring information based on a single treatment of a single subject, and performing feature extraction matching analysis based on the time dimension to form pain unit matching nursing data includes: Extract the pain action monitoring information corresponding to a single treatment of a single subject, decompose and describe the action behavior, and form a pain action description chain; Extracting pain physiological monitoring information corresponding to a single treatment of a single subject, and determining parameter change values ​​of all pain physiological monitoring parameters in the pain period defined by the corresponding pain action description chain, to form pain physiological monitoring characteristic information; Matching the pain physiological monitoring characteristic information with the corresponding pain action description chain in the time dimension to form pain unit matching data; The pain unit matching data is matched with the nursing treatment content corresponding to a single treatment of a single subject to form the pain unit matching nursing data.

7. The method for monitoring patients based on the Internet of Things according to claim 6, characterized in that: According to the pain unit matching nursing data, cluster analysis is performed on the pain unit matching data based on the same nursing content to form the same type of nursing pain matching data, including: Clustering all the pain unit matching nursing data corresponding to the same disease to form a pain nursing data set for the same disease; The matching data of the pain units with the same nursing content in the same disease pain nursing data set are subjected to clustering and merging analysis in the following manner: If there are different matching data of the pain unit, the corresponding pain action description chains are consistent, and after all parameters in the pain physiological monitoring characteristic information are taken as endpoint values ​​to form a merging range, no other parameters of the pain physiological monitoring characteristic information belong to the merging range of the corresponding parameters, then the different matching data of the pain unit are merged; Otherwise, no merging will be performed; All the disease unit matching data sets after clustering and merging analysis are completed to form the same type of nursing disease matching data.

8. The method for monitoring patients based on the Internet of Things according to claim 7, characterized in that: According to the matching data of different similar nursing pains, a combined analysis of nursing contents for pain behaviors is performed to form pain behavior nursing treatment data, including: For the same type of nursing pain matching data corresponding to different nursing contents, taking the pain unit matching data as the leading factor, a corresponding relationship between each pain unit matching data and nursing content is established to form pain unit matching-nursing content data; The same type of parameter judgment factor is set, and the same type of nursing pain matching data corresponding to different nursing contents in the pain unit matching-nursing content data are combined and analyzed in the following manner: If, in the same type of nursing pain matching data corresponding to two different nursing contents, there are the same pain action description chains of the pain unit matching data, and the ratio of the non-intersection segment to the intersection segment of the value range corresponding to each parameter in the pain physiological monitoring feature information is not greater than the corresponding same type parameter judgment factor, then merge the two pain unit matching data, and determine the two nursing contents corresponding to the pain unit matching data as the corresponding nursing content set after the merger; Otherwise, no merging will be performed; The merged nursing content set and the corresponding pain unit matching data as well as the unmerged nursing content and the corresponding pain unit matching data are collected to form the pain behavior nursing treatment data.

9. The method for monitoring patients based on the Internet of Things according to claim 8, characterized in that: The extracting of physiological monitoring data and corresponding nursing processing content in the IoT big data, performing IoT monitoring and nursing analysis based on physiological information, and forming basic data of physiological information IoT monitoring and nursing, includes: Taking a single nursing session of a single subject as a unit, extract physiological monitoring information and corresponding auxiliary nursing processing content to form physiological monitoring auxiliary nursing processing content data; The different physiological monitoring auxiliary nursing treatment contents are combined and analyzed in the following manner: If all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents have an intersection, the corresponding parameters are taken and operated to form a merged range, and the auxiliary nursing processing content sets corresponding to the two physiological monitoring information are respectively formed into a merged corresponding auxiliary nursing processing content set; If all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents do not have an intersection, but the merged range formed after merging does not have parameters of other physiological monitoring information that belong to the corresponding merged range, then the corresponding parameters are taken and operated to form the merged range, and the auxiliary nursing processing content sets corresponding to the two physiological monitoring information are respectively formed into the auxiliary nursing processing content set corresponding to the merged; If all parameters of the physiological monitoring information under different physiological monitoring auxiliary nursing processing contents do not have an intersection, and the merged range formed after the merge has other parameters of the physiological monitoring information belonging to the corresponding merged range, no merging is performed; All merged physiological monitoring information and the corresponding auxiliary nursing processing content set as well as unmerged physiological monitoring information and the corresponding auxiliary nursing processing content are collected to form the physiological information IoT monitoring and nursing basic data.

10. A patient monitoring device based on the Internet of Things, using the patient monitoring method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The IoT-based patient monitoring device is configured to: Determine the target disease types within the monitoring scope, and obtain IoT big data of the same type of diseases based on the target disease types; Performing nursing analysis on the IoT big data based on behavioral information and physiological information to form IoT monitoring basic big data; The target disease categories are updated, new IoT big data are collected according to the updated target disease categories, and the IoT monitoring basic big data are updated according to the updated IoT big data.

Images