CN-122000020-A - Multi-source information processing method and system based on Internet of things

CN122000020ACN 122000020 ACN122000020 ACN 122000020ACN-122000020-A

Abstract

The invention discloses a multisource information processing method and system based on the Internet of things, which belong to the technical field of information management, the invention carries out edge calculation on multidimensional sign data through a primary screening link and then uploads the multidimensional sign data to a cloud end, evaluates sample transportation risk values on a transportation link and dynamically adjusts a transportation route by combining with transportation data, reduces the transportation risk and the time length of samples, ensures the effectiveness of the samples to improve the detection accuracy, and in the detection link, an effective detection result is obtained by evaluating from sample detection results according to the operation data of the detection equipment, the disease risk level of a corresponding detected person is evaluated by combining multidimensional sign data, and finally, the statistics and distribution link pushes hospital advice according to the geographic position and the disease risk level, so that the detection accuracy is improved and the whole-flow data processing of disease control screening is completed.

Inventors

Zhuo Lanyun
HUANG YAJUN
Shen Jinmiao
Wen Hainan

Assignees

广州兰卫医学检验实验室有限公司

Dates

Publication Date: 20260508
Application Date: 20251225

Claims (10)

1. The multi-source information processing method based on the Internet of things is characterized by comprising the following steps of: A primary screening step, namely collecting biological samples, and uploading the obtained multidimensional sign data of the detected person to a central cloud after edge calculation; a transportation link, namely evaluating a sample transportation risk value according to transportation environment data through a dynamic threshold model, and dynamically adjusting a transportation route through a path optimization algorithm by combining the sample transportation risk value and the transportation data; The detection link comprises the steps of carrying out edge calculation on detection equipment operation data and sample detection results, and uploading the detection equipment operation data and the sample detection results to a central cloud end, wherein the central cloud end evaluates the sample detection results according to the detection equipment operation data to obtain effective detection results, and evaluates the disease risk level of a corresponding person to be detected by combining multidimensional sign data; and counting the number of people in each disease risk level of each screening area, and pushing the advice of the hospital to visit according to the geographic position of the screening area where the checked person is and the disease risk level.
2. The multi-source information processing method based on the internet of things, which is characterized in that the edge calculation is specifically performed through deployed edge calculation nodes, the data is cleaned in real time through a filtering algorithm, noise and abnormal values are removed, and the missing value filling is completed through a Newton interpolation algorithm.
3. The internet of things-based multi-source information processing method of claim 1, wherein the transportation environment data is collected by a cluster of sensors deployed on a transportation carrier and a sample storage device, the transportation environment data including transportation environment temperature, transportation environment humidity, and transportation vibration data.
4. The internet of things-based multi-source information processing method according to claim 1, wherein the evaluating the sample transportation risk value according to the transportation environment data through the dynamic threshold model is specifically: dynamic safety threshold for analyzing each transport environment data: ; Wherein, the As a safety threshold for the current ith transport environment data, Is the basic safety threshold of the ith transport environment data, A threshold decay factor for the ith transport environment data, t is the length of time that has been transported, In order to preset the maximum length of the transportation, For the rate of change sensitivity coefficient of the ith transport environment data, The change rate of the ith transportation environment data in the preset unit time is set; analyzing interaction factors of the transport environment data: ; Wherein n is the number of the transportation environment data, For the current value of the ith transport environment data, As a historical average of the ith transport environment data, For the preset temperature change sensitivity coefficient, For the rate of temperature change within a preset unit time, The historical standard deviation of the ith transportation environment data is given, and k is a preset experience coefficient; evaluating the sample transportation risk value based on the dynamic threshold and the interaction factor: ; wherein FX is the current sample transportation risk value.
5. The internet of things-based multi-source information processing method according to claim 1, wherein the method is characterized in that the transportation route is dynamically adjusted by combining the sample transportation risk value and the transportation data through a path optimization algorithm, specifically: evaluating the remaining maximum transportation duration according to the sample transportation risk value: ; Wherein, the In order to leave a maximum length of transportation, In order to preset the maximum length of the transportation, For the length of time that it has been transported, And A preset duration reduction coefficient and a preset risk threshold sensitivity coefficient respectively, FX0 is a preset risk threshold value for sample transportation risk value; Acquiring a first transportation route with a transportation duration not longer than the remaining maximum transportation duration from a navigation system; Acquiring the comprehensive cost of the traffic data analysis path of each first transportation route: ; Wherein, the For the path comprehensive cost of the ith first transportation route, k1, k2 and k3 are respectively a first preset weight, a second preset weight and a third preset weight, For the estimated transportation time length of the ith first transportation route, For the congestion index of the ith first haul route, A road flatness index for the ith first transportation route; And selecting the first transportation route with the minimum path comprehensive cost as the adjusted transportation route.
6. The internet of things-based multi-source information processing method according to claim 1, wherein the effective detection result is obtained by evaluating from sample detection results according to the detection device operation data, specifically: Acquiring preset control parameters of the detection equipment, and acquiring various reference operation data of the detection equipment according to the preset control parameters through a preset deep learning model; calculating error values corresponding to various operation data according to the operation data of various detection devices and various reference operation data, and calculating a comprehensive error index WCZ: ; Wherein N is the number of kinds of the operation data of the detection equipment, The preset weight of the operation data of the ith detection equipment, An error value of the operation data of the ith detection equipment; If the comprehensive error index is smaller than the preset comprehensive error threshold value and the error value of the operation data of each detection device is smaller than the corresponding preset error threshold value, the detection result of the corresponding detected sample is an effective detection result.
7. The internet of things-based multi-source information processing method according to claim 1, wherein the evaluating the disease risk level of the corresponding subject in combination with the multi-dimensional sign data specifically comprises: Outputting a preliminary risk level of the detected person according to an effective detection result through a preset risk assessment model, wherein the assessment model completes model training through a historical detection result and a corresponding historical disease risk level as a training sample; Screening a first detection result and a first risk level of a first historical detected person with preset quantity from a database according to the multi-dimensional sign data of the detected person, wherein the similarity between the multi-dimensional sign data of the first historical detected person and the multi-dimensional sign data of the detected person is larger than a first preset similarity threshold value, and the similarity between the first detection result and the effective detection result of the detected person is larger than a second preset similarity threshold value; obtaining a disease risk level L of the corresponding detected person through the preliminary risk level and the first risk level: ; Wherein, the And A2 is a first preset level weight and a second preset level weight, respectively, L0 is a preliminary risk level, M is the number of first historical subjects, And L is an integer for the first risk level of the ith first historical subject.
8. The internet of things-based multi-source information processing method according to claim 1, wherein the pushing of the hospital advice for treatment according to the geographical location and the disease risk level of the screening area where the subject is located specifically comprises: acquiring relevant medical resources of each hospital on the current disease to be screened in each screening area, and evaluating the processing capacity grade of each hospital on the current disease to be screened according to the relevant medical resources, wherein the processing capacity grade corresponds to the disease risk grade; And acquiring hospitals with the same processing capacity level as the disease risk level of the checked person in the screening area, if not, selecting the hospitals with the same processing capacity level as the disease risk level from other screening areas according to the nearby principle to push, if not, selecting the hospitals with the processing capacity level higher than the disease risk level by one step from the screening area to push, if not, selecting the hospitals from other screening areas, and the like.
9. The multi-source information processing system based on the internet of things, which applies the multi-source information processing method based on the internet of things according to any one of claims 1 to 8, is characterized by comprising the following steps: the physical sign data acquisition module is used for carrying out edge calculation on the acquired multidimensional physical sign data of the checked person and uploading the multidimensional physical sign data to the central cloud; The route optimization module is used for evaluating the sample transportation risk value according to the transportation environment data through the dynamic threshold model and dynamically adjusting the transportation route through a route optimization algorithm by combining the sample transportation risk value and the transportation data; The grade evaluation module is used for carrying out edge calculation on the detection equipment operation data and the sample detection result and then uploading the detection equipment operation data and the sample detection result to the central cloud, the central cloud evaluates the sample detection result according to the detection equipment operation data to obtain an effective detection result, and evaluates the disease risk grade of the corresponding person to be detected by combining the multidimensional sign data; The statistics and distribution module is used for counting the number of people of each disease risk level of each screening area and pushing the advice of the hospital to visit according to the geographic position of the screening area where the checked person is located and the disease risk level.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the internet of things-based multi-source information processing method according to any one of claims 1 to 8.

Description

Multi-source information processing method and system based on Internet of things Technical Field The invention relates to the technical field of information management, in particular to a multisource information processing method and system based on the Internet of things. Background The disease control screening is a key measure for maintaining health, preventing and managing diseases, and in the disease control screening, the data information to be noted is not only the detection data of biological samples, because a complete screening detection flow comprises various links, and each link generates different data information which influences the accuracy of screening detection results, in the prior art, most of the data information is focused on the management of detection information data, therefore, the invention provides a multi-source information processing method and system based on the Internet of things. Disclosure of Invention The invention aims to solve the technical problems existing in the prior art and provides The multi-source information processing method based on the Internet of things is characterized by comprising the following steps of: A primary screening step, namely collecting biological samples, and uploading the obtained multidimensional sign data of the detected person to a central cloud after edge calculation; a transportation link, namely evaluating a sample transportation risk value according to transportation environment data through a dynamic threshold model, and dynamically adjusting a transportation route through a path optimization algorithm by combining the sample transportation risk value and the transportation data; The detection link comprises the steps of carrying out edge calculation on detection equipment operation data and sample detection results, and uploading the detection equipment operation data and the sample detection results to a central cloud end, wherein the central cloud end evaluates the sample detection results according to the detection equipment operation data to obtain effective detection results, and evaluates the disease risk level of a corresponding person to be detected by combining multidimensional sign data; and counting the number of people in each disease risk level of each screening area, and pushing the advice of the hospital to visit according to the geographic position of the screening area where the checked person is and the disease risk level. The edge calculation method comprises the steps of carrying out data cleaning and missing value filling through deployed edge calculation nodes, carrying out real-time cleaning through a filtering algorithm, removing noise and abnormal values, and carrying out the missing value filling through a Newton interpolation algorithm. Further, the transport environment data is collected by a cluster of sensors deployed on the transport carrier and the sample storage device, the transport environment data including transport environment temperature, transport environment humidity, and transport vibration data. Further, the sample transportation risk value is evaluated according to the transportation environment data through the dynamic threshold model, specifically: dynamic safety threshold for analyzing each transport environment data: ; Wherein, the As a safety threshold for the current ith transport environment data,Is the basic safety threshold of the ith transport environment data,A threshold decay factor for the ith transport environment data, t is the length of time that has been transported,In order to preset the maximum length of the transportation,For the rate of change sensitivity coefficient of the ith transport environment data,The change rate of the ith transportation environment data in the preset unit time is set; analyzing interaction factors of the transport environment data: Wherein n is the number of the transportation environment data, For the current value of the ith transport environment data,As a historical average of the ith transport environment data,For the preset temperature change sensitivity coefficient,For the rate of temperature change within a preset unit time,The historical standard deviation of the ith transportation environment data is given, and k is a preset experience coefficient; evaluating the sample transportation risk value based on the dynamic threshold and the interaction factor: ; wherein FX is the current sample transportation risk value. Further, the transportation route is dynamically adjusted by combining the sample transportation risk value and the traffic data through a path optimization algorithm, specifically: evaluating the remaining maximum transportation duration according to the sample transportation risk value: ; Wherein, the In order to leave a maximum length of transportation,In order to preset the maximum length of the transportation,For the length of time that it has been transported,AndA preset duration reduction coefficient and a preset ri