An intelligent monitoring system and method for nursing services based on artificial intelligence

Abstract

The present invention relates to an intelligent monitoring system and method for nursing services based on artificial intelligence, and belongs to the field of artificial intelligence technology. The method specifically includes: obtaining the vital sign parameter information of the ward, processing the vital sign parameter information to obtain the de-alienated vital sign parameter information, obtaining the real-time health status of the ward according to the de-alienated vital sign parameter information, generating abnormal warning information according to the real-time health status, obtaining the abnormal fluctuation probability according to the real-time health status, generating abnormal warning information according to the abnormal fluctuation probability, obtaining the reference tag information and the signal strength of the tag to be tested of the ward, obtaining the position coordinates of the ward according to the reference tag information and the signal strength of the tag to be tested, uploading the abnormal warning information, abnormal warning information and the position coordinates of the ward to the nursing service terminal, realizing the real-time health status monitoring, abnormal health status warning and position positioning of the ward, ensuring the health of the ward, and improving the quality of nursing services.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence, and in particular relates to an intelligent monitoring system and method for nursing services based on artificial intelligence. Background Art

[0002] As people's demand for medical care services continues to increase, the traditional medical care model centered on hospitals, diagnosis and treatment as the core, and face-to-face diagnosis and treatment faces huge challenges. On the one hand, these challenges are caused by the shortage of medical resources. On the other hand, for nursing services, limited space resources and high flow of patients make it difficult for medical service personnel to monitor each patient in a meticulous and thoughtful manner. These will affect the patient's nursing experience and physical and mental health. In the traditional nursing service process, the collection of the patient's physiological parameters usually requires medical staff to collect and evaluate them face to face. If the patient's physiological parameters fluctuate abnormally, the medical staff are often notified afterwards, which will affect the patient's optimal diagnosis and treatment time. Summary of the invention

[0003] In order to solve the above-mentioned problems existing in the prior art, the present invention provides an intelligent monitoring system and method for nursing services based on artificial intelligence, which obtains the vital sign parameter information of the ward, performs de-identification processing on the vital sign parameter data according to the data label, and obtains the de-identified vital sign parameter information, obtains the real-time health status of the ward through data fusion evaluation based on the de-identified vital sign parameter information, generates abnormal warning information according to the real-time health status, analyzes the real-time health status to obtain the abnormal fluctuation probability, generates abnormal early warning information according to the abnormal fluctuation probability, obtains reference tag information and the signal strength of the ward's tag to be measured based on the abnormal warning information and the abnormal early warning information, obtains the position coordinates of the ward according to the reference tag information and the signal strength of the tag to be measured, and uploads the abnormal warning information, the abnormal early warning information and the position coordinates of the ward to the nursing service terminal, thereby realizing the real-time health status monitoring of the ward, and realizing the abnormal early warning of the health status and the position positioning of the ward by processing the vital sign parameter information, thereby improving the quality of nursing services and facilitating the rehabilitation of the ward.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] An artificial intelligence-based nursing service intelligent monitoring method comprises the following steps:

[0006] S1: After authorization, obtain the guardian's vital sign parameter information, the vital sign parameter information including data label and vital sign parameter data;

[0007] S2: performing de-noising processing on the physical sign parameter data according to the data label to obtain de-noised physical sign parameter information;

[0008] S3: Based on the abnormal sign parameter information, evaluate the real-time health status of the ward by data fusion, generate an abnormal warning message according to the real-time health status, analyze the real-time health status to obtain the abnormal fluctuation probability, and generate an abnormal early warning message according to the abnormal fluctuation probability;

[0009] S4: Based on the abnormal warning message and the abnormal early warning message, obtain the reference tag information and the signal strength of the tag to be measured of the ward, and obtain the position coordinates of the ward according to the reference tag information and the signal strength of the tag to be measured;

[0010] S5: Upload the abnormal warning message, the abnormal early warning message and the position coordinates of the ward to the nursing service terminal.

[0011] Preferably, the step S2 specifically includes the following steps:

[0012] S201: Arrange the sign parameter data of the same data tag in ascending order to obtain a data sequence as follows: , where k represents the number of the data tag, n represents the number of sign parameter data, represents the sign parameter data of the nth data tag being k. Among them, one data tag corresponds to one tag type, and one tag type corresponds to one sign parameter type. According to the data sequence, calculate the first abnormal statistic and the second abnormal statistic through the formula , where A1 represents the first abnormal statistic and A2 represents the second abnormal statistic;

[0013] S202: Obtain the test critical value A3. When A1 > A2 and A1 > A3, then judge as an outlier, and delete . When A1 < A2 and A1 < A3, then judge as an outlier, and delete . After deleting the outliers, obtain the abnormal sign parameter information. When the above two situations are not met, it means that there are no outliers in the data sequence, and the sign parameter information is used as the abnormal sign parameter information.

[0014] Preferably, the step S3 includes the following steps:

[0015] S301: Based on the abnormal sign parameter information, process through a data fusion model to obtain a health degree value. The data fusion model is expressed as: , where HS represents the health degree value, m represents the number of abnormal sign parameter information, m ≤ n, represents the ith abnormal sign parameter information, represents the weight of the ith abnormal sign parameter information;

[0016] S302: When the health level value is less than a preset threshold, the real-time health status is unhealthy and an abnormal warning message is generated; when the health level value is greater than or equal to the preset threshold, the real-time health status is healthy and a real-time status no abnormality message is generated.

[0017] Preferably, the specific calculation method of the abnormal fluctuation probability is as follows:

[0018] Acquire historical health status data, wherein the historical health status data includes the number of healthy→healthy transitions, the number of healthy→unhealthy transitions, the number of unhealthy→healthy transitions, and the number of unhealthy→unhealthy transitions;

[0019] According to the real-time health status combined with historical health status data, the formula The abnormal fluctuation probability is calculated, wherein YN represents the number of transitions from unhealthy to unhealthy, YH represents the number of transitions from unhealthy to healthy, TN represents the number of transitions from healthy to unhealthy, and TH represents the number of transitions from healthy to healthy. and Indicates the abnormal fluctuation probability of real-time health status → unhealthy status, NH means unhealthy, and H means healthy;

[0020] When the abnormal fluctuation probability is greater than a preset threshold, the abnormal warning information is generated, and when the abnormal fluctuation probability is less than or equal to the preset threshold, no abnormality information is generated.

[0021] Preferably, the step S4 specifically includes the following steps:

[0022] S401: When the abnormal warning information and the abnormal early warning information are generated, a tag reader is triggered to read the signal strength of the tag to be tested and the reference tag information in the scene, wherein the reference tag information includes a reference tag number and a reference tag signal strength;

[0023] S402: According to the reference tag signal strength and the tag signal strength to be tested, the formula The label difference is calculated, where i represents the reference label number. Indicates the label difference between the reference label i and the label to be measured. represents the signal strength of the tag to be tested, represents the reference tag signal strength of reference tag i;

[0024] S403: Sort the label differences in ascending order, select the first p reference label information corresponding to the label differences, and calculate the label differences according to the formula The reference label weight is calculated, where h represents the reference label number, represents the reference label weight of the reference label h, represents the label difference between the reference label h and the label coordinates to be measured, and p represents the number of reference labels;

[0025] S404: Obtain reference tag coordinates according to the reference tag number, and calculate the reference tag weight according to the reference tag coordinates and the reference tag weight by the formula The position coordinates of the guardian are calculated, where: represents the position coordinates of the guardian, represents the reference label coordinates of the reference label h, represents the reference tag weight of the reference tag h, and p represents the number of reference tags.

[0026] Furthermore, the present application also provides an artificial intelligence-based nursing service intelligent monitoring system, comprising the following modules:

[0027] A data acquisition module is used to obtain the vital sign parameter information of the guardian after authorization, wherein the vital sign parameter information includes a data label and vital sign parameter data;

[0028] A data processing module, used for performing a de-noising process on the vital sign parameter data according to the data label to obtain de-noised vital sign parameter information;

[0029] An intelligent monitoring module, for obtaining the real-time health status of the ward through data fusion evaluation according to the devitalization parameter information, generating abnormal warning information according to the real-time health status, analyzing the real-time health status to obtain abnormal fluctuation probability, and generating abnormal warning information according to the abnormal fluctuation probability;

[0030] A location positioning module, used to obtain reference tag information and the signal strength of the tag to be tested of the guardian based on the abnormal warning information and the abnormal early warning information, and obtain the location coordinates of the guardian according to the reference tag information and the signal strength of the tag to be tested;

[0031] The nursing warning module is used to upload the abnormal warning information, the abnormal warning information and the position coordinates of the guardian to the nursing service terminal.

[0032] The beneficial effects of the present invention are:

[0033] By setting up an intelligent monitoring module, the real-time health status of the ward is obtained through data fusion evaluation based on the information of the foreign body sign parameter, abnormal warning information is generated based on the real-time health status, and the abnormal fluctuation probability is obtained based on the real-time health status analysis. Abnormal warning information is generated based on the abnormal fluctuation probability, thereby realizing the real-time health status monitoring and abnormal health status warning of the ward, ensuring the health of the ward, improving the quality of nursing services, and facilitating medical staff to track the real-time nursing of the ward;

[0034] By providing a position positioning module, the reference tag information and the signal strength of the tag to be tested of the ward are obtained based on the abnormal warning information and the abnormal early warning information, and the position coordinates of the ward are obtained according to the reference tag information and the signal strength of the tag to be tested. When the health condition of the ward is abnormal, the position of the ward can be positioned in real time, which improves the quality of nursing services, helps medical staff to track the real-time care of the ward, and enables medical staff to diagnose and treat the ward in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0036] Figure 1 The figure is a flow chart of the intelligent monitoring method for nursing services based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0037] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0038] See also Figure 1 , an intelligent monitoring method for nursing services based on artificial intelligence, comprising the following steps:

[0039] S1: After authorization, obtain the guardian's vital sign parameter information, the vital sign parameter information including data label and vital sign parameter data;

[0040] S2: performing de-noising processing on the physical sign parameter data according to the data label to obtain de-noised physical sign parameter information;

[0041] S3: obtaining the real-time health status of the ward through data fusion evaluation according to the devitalization parameter information, generating abnormal warning information according to the real-time health status, analyzing the real-time health status to obtain abnormal fluctuation probability, and generating abnormal warning information according to the abnormal fluctuation probability;

[0042] S4: Based on the abnormal warning information and the abnormal early warning information, obtain the reference tag information and the signal strength of the tag to be measured of the ward, and obtain the location coordinates of the ward according to the reference tag information and the signal strength of the tag to be measured;

[0043] S5: Upload the abnormal warning information, the abnormal early warning information and the location coordinates of the ward to the nursing service terminal.

[0044] It should be further noted that, in this embodiment, the physical sign parameter information of the ward includes physical sign parameter data of multiple parameter types. The physical sign parameter data includes, but is not limited to, body temperature data, heart rate data, blood oxygen data and blood pressure data. The data tag represents the physical sign parameter type. Among them, the above reference tag information refers to the reference tag information composed of electronic tags set by the staff as references within the activity scene of the ward.

[0045] Specifically, the step S2 specifically includes the following steps:

[0046] S201: Arrange the physical sign parameter data of the same data tag in ascending order to obtain a data sequence: , where k represents the number of the data tag, n represents the number of physical sign parameter data, represents the physical sign parameter data with the nth data tag being k. Among them, one data tag corresponds to one tag type, and one tag type corresponds to one physical sign parameter type. According to the data sequence, the first abnormal statistic and the second abnormal statistic are calculated through the formula , where A1 represents the first abnormal statistic and A2 represents the second abnormal statistic;

[0047] S202: Obtain the test critical value A3. When A1 > A2 and A1 > A3, then judge as an outlier, and delete . When A1 < A2 and A1 < A3, then judge as an outlier, and delete . After deleting the outliers, the outlier-removed physical sign parameter information is obtained. When the above two situations are not met, it means that there are no outliers in the data sequence, and the physical sign parameter information is used as the outlier-removed physical sign parameter information.

[0048] It should be further explained that when measuring the vital sign parameter information of the guardian, due to the existence of instrument measurement errors, abnormal data will exist in the measurement process. Therefore, the vital sign parameter information needs to be processed to improve the data accuracy. Since the errors generated in the instrument measurement process usually exist as extreme values, in this embodiment, the collected vital sign parameter data are sorted in order from small to large, and the abnormal values ​​are eliminated by comparing the differences between the extreme values ​​in the vital sign parameter data and other data.

[0049] Specifically, step S3 includes the following steps:

[0050] S301: According to the devitalization parameter information, a health level value is obtained through data fusion model processing. The data fusion model is expressed as: , where HS represents the health level value, m represents the number of allopathic sign parameter information, m≤n, Indicates the parameter information of the i-th de-alienation sign, represents the weight of the parameter information of the ith de-alienation sign;

[0051] S302: When the health level value is less than a preset threshold, the real-time health status is unhealthy and an abnormal warning message is generated; when the health level value is greater than or equal to the preset threshold, the real-time health status is healthy and a real-time status no abnormality message is generated.

[0052] It should be further explained that, in this embodiment, the weight of the physical sign parameter information is obtained by experts in the medical field scoring the importance of the physical sign parameters based on their professional experience and knowledge, and converting the scores of the physical sign parameters into weights. ;

[0053] In addition, in order to avoid the problem of calculation difficulties caused by inconsistent units in this embodiment, the parameter information of the body temperature removal is the AD value transmitted by the sensor. The body temperature removal parameters include: , heart rate data , blood oxygen data and blood pressure data , substitute the allotropy parameters into the data fusion model The health level value is obtained. In this embodiment, the preset threshold is set to 1, and the health level value 1.33>1, then the real-time health status is obtained as healthy, and the status no abnormality information is generated.

[0054] Specifically, the specific calculation method of the abnormal fluctuation probability is as follows:

[0055] Acquire historical health status data, wherein the historical health status data includes the number of healthy→healthy transitions, the number of healthy→unhealthy transitions, the number of unhealthy→healthy transitions, and the number of unhealthy→unhealthy transitions;

[0056] According to the real-time health status combined with historical health status data, the formula The abnormal fluctuation probability is calculated, wherein YN represents the number of transitions from unhealthy to unhealthy, YH represents the number of transitions from unhealthy to healthy, TN represents the number of transitions from healthy to unhealthy, and TH represents the number of transitions from healthy to healthy. and Indicates the abnormal fluctuation probability of real-time health status → unhealthy status, NH means unhealthy, and H means healthy;

[0057] When the abnormal fluctuation probability is greater than a preset threshold, the abnormal warning information is generated, and when the abnormal fluctuation probability is less than or equal to the preset threshold, no abnormality information is generated.

[0058] In this embodiment, the historical health status data includes: healthy → healthy transition times: TH=100; healthy → unhealthy transition times: TN=30; unhealthy → healthy transition times: YH=28; unhealthy → unhealthy transition times: YN=15; Based on the historical health status data combined with the real-time health status, the formula Calculating and obtaining the abnormal fluctuation probability;

[0059] It should be noted that the abnormal fluctuation probability here is based on the current real-time health status combined with the historical health status data to calculate the probability of the next health status being unhealthy. When the real-time health status is healthy, the formula The abnormal fluctuation probability of the health status from healthy to unhealthy is calculated. When the real-time health status is unhealthy, the formula Calculate the probability of abnormal fluctuation of health status from unhealthy to unhealthy;

[0060] The preset threshold is set to 0.6. When the real-time health status is healthy, the probability of abnormal fluctuation from healthy to unhealthy is 0.23<0.6, so no abnormal information is generated. When the real-time health status is unhealthy, the probability of abnormal fluctuation from unhealthy to unhealthy is 0.70>0.6, so abnormal warning information is generated.

[0061] Specifically, the step S4 comprises the following steps:

[0062] S401: When the abnormal warning information and the abnormal early warning information are generated, a tag reader is triggered to read the signal strength of the tag to be tested and the reference tag information in the scene, wherein the reference tag information includes a reference tag number and a reference tag signal strength;

[0063] S402: According to the reference tag signal strength and the tag signal strength to be tested, the formula The label difference is calculated, where i represents the reference label number. Indicates the label difference between the reference label i and the label to be measured. represents the signal strength of the tag to be tested, represents the reference tag signal strength of reference tag i;

[0064] S403: Sort the label differences in ascending order, select the first p reference label information corresponding to the label differences, and calculate the label differences according to the formula The reference label weight is calculated, where h represents the reference label number, represents the reference label weight of the reference label h, represents the label difference between the reference label h and the label coordinates to be measured, and p represents the number of reference labels;

[0065] S404: Obtain reference tag coordinates according to the reference tag number, and calculate the reference tag weight according to the reference tag coordinates and the reference tag weight by the formula The position coordinates of the guardian are calculated, where: represents the position coordinates of the guardian, represents the reference label coordinates of the reference label h, represents the reference tag weight of the reference tag h, and p represents the number of reference tags.

[0066] In this embodiment, according to the abnormal warning information and the abnormal early warning information, the tag reader is triggered to read the reference tag signal strength and the signal strength of the tag to be tested. , the signal strength of the tag to be tested is , substitute the reference tag signal strength and the tag signal strength to be tested into the formula Calculate the label differences and sort them in ascending order, then we have ;

[0067] Select the first 3 label differences and substitute the label differences into the formula In the calculation, the reference label weight is obtained. The reference label weight is , according to the selected reference tag number, the reference tag coordinates are obtained, where the reference tag coordinates are , substitute the reference label coordinates into the formula The position coordinates of the guardian are obtained by calculation .

[0068] It should be further explained that, by setting a reference electronic tag in the activity scene of the ward, the indoor positioning of the ward is performed according to the reference tag information of the reference electronic tag and the electronic tag carried by the ward. Currently commonly used indoor positioning technologies include infrared positioning and Bluetooth positioning. However, infrared transmission is easily blocked, thus affecting the positioning effect, and Bluetooth positioning consumes a lot of power and is not suitable for long-term wearing by the ward. In this embodiment, abnormal warning information and abnormal early warning information are obtained according to the real-time health status of the ward. The tag reader is triggered by the abnormal warning information and the abnormal early warning information to read the reference tag information and the electronic tag of the ward to determine the position coordinates of the ward, which is convenient for medical care personnel to quickly locate the ward when he is in an abnormal state, so that medical care personnel can provide faster care and treatment to the ward.

[0069] Furthermore, the present application also provides an artificial intelligence-based nursing service intelligent monitoring system, comprising the following modules:

[0070] A data acquisition module is used to obtain the vital sign parameter information of the guardian after authorization, wherein the vital sign parameter information includes a data label and vital sign parameter data;

[0071] A data processing module, used for performing a de-noising process on the vital sign parameter data according to the data label to obtain de-noised vital sign parameter information;

[0072] An intelligent monitoring module, for obtaining the real-time health status of the ward through data fusion evaluation according to the devitalization parameter information, generating abnormal warning information according to the real-time health status, analyzing the real-time health status to obtain abnormal fluctuation probability, and generating abnormal warning information according to the abnormal fluctuation probability;

[0073] A location positioning module, used to obtain reference tag information and the signal strength of the tag to be tested of the guardian based on the abnormal warning information and the abnormal early warning information, and obtain the location coordinates of the guardian according to the reference tag information and the signal strength of the tag to be tested;

[0074] The nursing warning module is used to upload the abnormal warning information, the abnormal warning information and the position coordinates of the guardian to the nursing service terminal.

[0075] The working principle and use process of the present invention:

[0076] After being authorized, the data acquisition module obtains the vital sign parameter information of the ward, and performs de-identification processing on the vital sign parameter data according to the data label to obtain the de-identified vital sign parameter information. Based on the de-identified vital sign parameter information, the real-time health status of the ward is obtained through data fusion evaluation, and abnormal warning information is generated according to the real-time health status. The real-time health status is analyzed to obtain the probability of abnormal fluctuation, and abnormal early warning information is generated according to the probability of abnormal fluctuation. Based on the abnormal warning information and the abnormal early warning information, the reference tag information and the signal strength of the tag to be tested of the ward are obtained, and the position coordinates of the ward are obtained according to the reference tag information and the signal strength of the tag to be tested, and the abnormal warning information, the abnormal early warning information and the position coordinates of the ward are uploaded to the nursing service terminal.

[0077] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0078] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0079] The program code included in the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wire, optical cable, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0080] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An intelligent monitoring method for nursing services based on artificial intelligence, characterized in that: The following steps are involved: S1: After authorization, obtain the guardian's vital sign parameter information, the vital sign parameter information including data label and vital sign parameter data; S2: performing de-noising processing on the physical sign parameter data according to the data label to obtain de-noised physical sign parameter information; S3: obtaining the real-time health status of the ward through data fusion evaluation according to the devitalization parameter information, generating abnormal warning information according to the real-time health status, analyzing the real-time health status to obtain abnormal fluctuation probability, and generating abnormal warning information according to the abnormal fluctuation probability; S4: based on the abnormal warning information and the abnormal early warning information, obtaining the reference tag information and the signal strength of the tag to be tested of the guardian, and obtaining the position coordinates of the guardian according to the reference tag information and the signal strength of the tag to be tested; S5: Uploading the abnormal warning information, the abnormal early warning information and the position coordinates of the ward to the nursing service terminal; The step S2 specifically includes the following steps: S201: Arrange the vital sign parameter data of the same data label in ascending order to obtain the data sequence: Wherein, k represents the number of the data label, n represents the number of vital sign parameter data, It represents the vital sign parameter data with the nth data label k, wherein one data label corresponds to one label type, one label type corresponds to one vital sign parameter type, and according to the data sequence, the formula Calculate and obtain a first abnormality statistic and a second abnormality statistic, wherein A1 represents the first abnormality statistic and A2 represents the second abnormality statistic; S202: Obtain the inspection critical value A3. When A1 > A2 and A1 > A3, then judge as an outlier, and delete it. When A1 < A2 and A1 < A3, then judge as an outlier, and delete it. After deleting the outliers, the outlier-removed physical sign parameter information is obtained. When the above two situations are not met, it means that there are no outliers in the data sequence, and the physical sign parameter information is used as the outlier-removed physical sign parameter information.

2. The method for intelligent monitoring of nursing services based on artificial intelligence according to claim 1, characterized in that: The step S3 comprises the following steps: S301: According to the devitalization parameter information, a health level value is obtained through data fusion model processing. The data fusion model is expressed as: Wherein, HS represents the health level value, m represents the number of allopathic sign parameter information, m≤n, x i represents the parameter information of the i-th de-alienation sign, θ i represents the weight of the parameter information of the ith de-alienation sign; S302: When the health level value is less than a preset threshold, the real-time health status is unhealthy and an abnormal warning message is generated; when the health level value is greater than or equal to the preset threshold, the real-time health status is healthy and a real-time status no abnormality message is generated.

3. The method for intelligent monitoring of nursing services based on artificial intelligence according to claim 2, characterized in that: The specific calculation method of the abnormal fluctuation probability is as follows: Acquire historical health status data, wherein the historical health status data includes the number of healthy→healthy transitions, the number of healthy→unhealthy transitions, the number of unhealthy→healthy transitions, and the number of unhealthy→unhealthy transitions; According to the real-time health status combined with historical health status data, the formula The abnormal fluctuation probability is calculated, where YN represents the number of transitions from unhealthy to unhealthy, YH represents the number of transitions from unhealthy to healthy, TN represents the number of transitions from healthy to unhealthy, TH represents the number of transitions from healthy to healthy, and P NH→NH represents the probability of abnormal fluctuation of health status from unhealthy to unhealthy, P H→NH It represents the probability of abnormal fluctuation of health status from healthy to unhealthy, NH represents unhealthy and H represents healthy; When the abnormal fluctuation probability is greater than a preset threshold, the abnormal warning information is generated, and when the abnormal fluctuation probability is less than or equal to the preset threshold, no abnormality information is generated.

4. The method for intelligent monitoring of nursing services based on artificial intelligence according to claim 1, characterized in that: The step S4 specifically comprises the following steps: S401: When the abnormal warning information and the abnormal early warning information are generated, a tag reader is triggered to read the signal strength of the tag to be tested and the reference tag information in the scene, wherein the reference tag information includes a reference tag number and a reference tag signal strength; S402: According to the reference tag signal strength and the tag signal strength to be tested, the formula The label difference is calculated, where h represents the reference label number and D h represents the label difference between the reference label h and the label to be tested, w0 represents the signal strength of the label to be tested, and w h represents the reference tag signal strength of the reference tag h; S403: Sort the label differences in ascending order, select the first p reference label information corresponding to the label differences, and calculate the label differences according to the formula The reference label weight is calculated, where h represents the reference label number, R h represents the reference label weight of the reference label h, D h represents the label difference between the reference label h and the label coordinates to be measured, and p represents the number of reference labels; S404: Obtain reference tag coordinates according to the reference tag number, and calculate the reference tag weight according to the reference tag coordinates and the reference tag weight by the formula The position coordinates of the guardian are calculated, where G(x, y) represents the position coordinates of the guardian, and B(x h ,y h ) represents the reference label coordinates of the reference label h, R h represents the reference tag weight of the reference tag h, and p represents the number of reference tags.

5. An artificial intelligence-based nursing service intelligent monitoring system, the system adopts the artificial intelligence-based nursing service intelligent monitoring method according to claim 1, characterized in that: Includes the following modules: A data acquisition module is used to obtain the vital sign parameter information of the guardian after authorization, wherein the vital sign parameter information includes a data label and vital sign parameter data; A data processing module, used for performing a de-noising process on the vital sign parameter data according to the data label to obtain de-noised vital sign parameter information; An intelligent monitoring module, for obtaining the real-time health status of the ward through data fusion evaluation according to the devitalization parameter information, generating abnormal warning information according to the real-time health status, analyzing the real-time health status to obtain abnormal fluctuation probability, and generating abnormal warning information according to the abnormal fluctuation probability; A location positioning module, used to obtain reference tag information and the signal strength of the tag to be tested of the guardian based on the abnormal warning information and the abnormal early warning information, and obtain the location coordinates of the guardian according to the reference tag information and the signal strength of the tag to be tested; The nursing warning module is used to upload the abnormal warning information, the abnormal warning information and the position coordinates of the guardian to the nursing service terminal.

Images