Influenza risk prediction method based on multi-source data

Abstract

The invention relates to an influenza risk prediction method based on multi-source data, and the method comprises the following steps: determining a target influenza type, and determining the type of associated multi-source data according to the target influenza type; determining a weight value corresponding to each data type; calculating a standard value for each data category based on its healthy user sample; obtaining multi-source data of a target user, and further determining a data value corresponding to the multi-source data type of the target user; calculating an offset coefficient between a data value corresponding to each data type of the target user and a standard value of the data value to obtain an offset coefficient of each data type of the target user; calculating an influenza risk value according to the offset coefficient of each data type of the target user and the weight value; and judging whether the flu risk value is greater than a preset risk threshold, if so, judging that the flu risk exists, and if not, judging that the flu risk does not exist. According to the invention, a certain prevention effect on influenza of a user can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field related to influenza risk prediction, and in particular to an influenza risk prediction method based on multi-source data. Background Art

[0002] Influenza, commonly known as flu, is an acute respiratory infectious disease caused by influenza virus.

[0003] Currently, when diagnosing influenza, it is usually necessary for hospital doctors to observe the user's relevant indicators and make corresponding diagnoses based on their experience. The above method has the following problems:

[0004] Hospital doctors see a limited number of patients each day and may not be able to handle users' flu diagnosis needs in a timely manner. Since flu diagnosis requires a large amount of data to observe, it takes doctors a long time to diagnose, affecting their diagnostic efficiency.

[0005] Therefore, there is a need for a method that can intelligently predict influenza risk based on users' multi-source data, and select users who are obviously at risk of influenza. On the one hand, it can facilitate doctors' targeted diagnosis, and on the other hand, it can also play a certain preventive role in users' health. Summary of the Invention

[0006] The purpose of the present invention is to address at least one of the deficiencies of the prior art and to provide an influenza risk prediction method based on multi-source data.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] Specifically, a method for influenza risk prediction based on multi-source data is proposed, including the following:

[0009] Determine the target influenza type, and determine the type of associated multi-source data based on the target influenza type;

[0010] Determine the weight value corresponding to each data type;

[0011] Calculate the standard value for each data type based on its healthy user sample;

[0012] Obtain multi-source data of the target user, and then determine the data value corresponding to the type of the multi-source data of the target user;

[0013] Calculate the deviation coefficient between the data value corresponding to each data type of the target user and its standard value to obtain the deviation coefficient of each data type of the target user;

[0014] Calculating a flu risk value based on the deviation coefficient of each data type of the target user and the weight value;

[0015] Determine whether the influenza risk value is greater than a preset risk threshold. If so, it is determined that there is an influenza risk. If not, it is determined that there is no influenza risk.

[0016] Further, specifically, the weight value corresponding to each data type is determined, including:

[0017] If there are m types of data;

[0018] Standardizing the m types of data to obtain the standardized m types of data;

[0019] Calculate the information entropy of each data type as follows:

[0020]

[0021] Among them, H j represents the information entropy of the jth data type, p ij is the normalized proportion of the i-th data type to the j-th data type, and k is a preset constant;

[0022] The corresponding weight is calculated based on the information entropy of each data type. The calculation formula is as follows:

[0023]

[0024] Among them, w j Represents the weight of the j-th data type.

[0025] Further, specifically, for each data type, its standard value is calculated based on its healthy user sample, including,

[0026] Sampling multiple healthy users to obtain data values of each data type of the sampled healthy users;

[0027] For any type of data, calculate the average value of the data values of all healthy users sampled from it, and finally obtain the average value of the data values of all healthy users of all types of data, and use the average value of the data values of all healthy users as the representation value of the data type;

[0028] The characterization values of all data types are standardized to obtain the standard value of each data type.

[0029] Further, specifically, the deviation coefficient between the data value corresponding to each data type of the target user and its standard value is calculated to obtain the deviation coefficient of each data type of the target user, including:

[0030] For any data type, normalize the data value corresponding to the data type of the target user to obtain a first value;

[0031] Subtract the standard value of the data type from the first value and take the absolute value to obtain the offset coefficient of the data type of the target user;

[0032] The offset coefficient of each data type of the target user is calculated in the above manner.

[0033] Further, specifically, the influenza risk value is calculated based on the deviation coefficient of each data type of the target user and the weight value, including:

[0034] If the offset coefficient of the target user's jth data type is Q j , then the target user's influenza risk value is recorded as FX and is calculated as follows:

[0035]

[0036] Furthermore, the method further comprises:

[0037] When the target user is at risk of influenza, an early warning reminder is issued to the target user. The early warning reminder is sent to the target user in a preset format. A text message informs the user that the user is at risk of influenza and needs to go to the hospital for a checkup in time.

[0038] Furthermore, the method further comprises:

[0039] When the target user is at risk of influenza, the multi-source data obtained for the target user is packaged to obtain a data packet and a query link is generated. The query link is used to provide the data packet for the doctor to review when the target user is reviewed in the hospital and the doctor obtains the target user's authorization.

[0040] Further, specifically, obtaining authorization from the target user includes one or more combinations of face recognition, fingerprint recognition, or key recognition of the target user.

[0041] The beneficial effects of the present invention are:

[0042] This paper proposes a multi-source data-based influenza risk prediction method. This method obtains multi-source data for a target user, calculates the offset coefficient between the target user's multi-source data and the multi-source data of healthy users, and uses a predetermined weight coefficient for each type of multi-source data to ultimately calculate the target user's influenza risk value. This value is then compared with a risk threshold to intelligently determine whether the user is at risk of influenza. This method can identify users at significant risk of influenza, facilitating targeted diagnosis by doctors while also providing a preventative benefit for the user's health. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and other features of the present disclosure will become more apparent through a detailed description of the embodiments shown in conjunction with the accompanying drawings. The same reference numerals in the drawings of the present disclosure represent the same or similar elements. Obviously, the drawings described below are only some embodiments of the present disclosure. It is possible for a person skilled in the art to derive other drawings based on these drawings without inventive effort. In the drawings:

[0044] Figure 1 Shown is a flow chart of the influenza risk prediction method based on multi-source data of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict. The same reference numerals used throughout the drawings indicate the same or similar parts.

[0046] Example 1, with reference to Figure 1 The present invention proposes an influenza risk prediction method based on multi-source data, including the following:

[0047] Step 110: Determine the target influenza type, and determine the type of associated multi-source data based on the target influenza type;

[0048] Step 120: Determine the weight value corresponding to each data type;

[0049] Step 130: Calculate the standard value for each data type based on its healthy user sample;

[0050] Step 140: Acquire multi-source data of the target user, and then determine the data value corresponding to the type of the multi-source data of the target user;

[0051] Step 150: Calculate the deviation coefficient between the data value corresponding to each data type of the target user and its standard value to obtain the deviation coefficient of each data type of the target user;

[0052] Step 160: Calculate the influenza risk value based on the deviation coefficient of each data type of the target user and the weight value;

[0053] Step 170: Determine whether the influenza risk value is greater than a preset risk threshold. If so, determine that there is an influenza risk. If not, determine that there is no influenza risk.

[0054] In this first embodiment, by acquiring multi-source data for a target user, calculating the offset coefficient between the target user's multi-source data and the multi-source data of healthy users, and using a predetermined weight coefficient for each type of multi-source data, the target user's influenza risk value is ultimately calculated. This influenza risk value is then compared with a risk threshold to intelligently determine whether the user is at risk of influenza. This invention can identify users who are clearly at risk of influenza, facilitating targeted diagnosis by doctors while also providing a preventive effect on the user's health.

[0055] As a preferred embodiment of the present invention, specifically, determining the weight value corresponding to each data type includes:

[0056] If there are m types of data;

[0057] Standardizing the m types of data to obtain the standardized m types of data;

[0058] Calculate the information entropy of each data type as follows:

[0059]

[0060] Among them, H j represents the information entropy of the jth data type, p ij is the normalized proportion of the i-th data type to the j-th data type, and k is a preset constant;

[0061] The corresponding weight is calculated based on the information entropy of each data type. The calculation formula is as follows:

[0062]

[0063] Among them, w j Represents the weight of the j-th data type.

[0064] In this preferred embodiment, the above method can accurately determine the weight of any data type, thereby ensuring the accuracy of the subsequent calculation of the influenza risk value.

[0065] As a preferred embodiment of the present invention, specifically, the standard value of each data type is calculated based on its healthy user sample, including:

[0066] Sampling multiple healthy users to obtain data values of each data type of the sampled healthy users;

[0067] For any type of data, calculate the average value of the data values of all healthy users sampled from it, and finally obtain the average value of the data values of all healthy users of all types of data, and use the average value of the data values of all healthy users as the representation value of the data type;

[0068] The characterization values of all data types are standardized to obtain the standard value of each data type.

[0069] In this preferred embodiment, the average value of the data values of any type of data of all sampled healthy users is used to approximately replace the representation value of the data type, which facilitates the subsequent calculation of the offset coefficient. In addition, considering the differences between different data, after calculating the representation values of all data types, standardization is performed to obtain the standard value of each data type.

[0070] As a preferred embodiment of the present invention, specifically, calculating the deviation coefficient between the data value corresponding to each data type of the target user and its standard value to obtain the deviation coefficient of each data type of the target user includes:

[0071] For any data type, normalize the data value corresponding to the data type of the target user to obtain a first value;

[0072] Subtract the standard value of the data type from the first value and take the absolute value to obtain the offset coefficient of the data type of the target user;

[0073] The offset coefficient of each data type of the target user is calculated in the above manner.

[0074] As a preferred embodiment of the present invention, specifically, the influenza risk value is calculated according to the deviation coefficient of each data type of the target user and the weight value, including:

[0075] If the offset coefficient of the target user's jth data type is Q j , then the target user's influenza risk value is recorded as FX and is calculated as follows:

[0076]

[0077] As a preferred embodiment of the present invention, the method further comprises:

[0078] When the target user is at risk of influenza, an early warning reminder is issued to the target user. The early warning reminder is sent to the target user in a preset format. A text message informs the user that the user is at risk of influenza and needs to go to the hospital for a checkup in time.

[0079] In this preferred embodiment, the user is given a flu risk warning by means of preset SIM information, and is informed that the user needs to go to the hospital for a follow-up examination.

[0080] As a preferred embodiment of the present invention, the method further comprises:

[0081] When the target user is at risk of influenza, the multi-source data obtained for the target user is packaged to obtain a data packet and a query link is generated. The query link is used to provide the data packet for the doctor to review when the target user is reviewed in the hospital and the doctor obtains the target user's authorization.

[0082] In this preferred embodiment, in order to facilitate the doctor's review, the multi-source data of the target user is packaged to obtain a data package and a query link is generated. Considering the user's privacy issues, the doctor can only query the data package after obtaining the user's authorization.

[0083] As a preferred embodiment of the present invention, specifically, obtaining authorization from the target user includes one or more combinations of face recognition, fingerprint recognition, or key recognition of the target user.

[0084] Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be construed as providing a broad possible interpretation of these claims in view of the prior art by reference to the appended claims, thereby effectively encompassing the intended scope of the invention. In addition, the invention has been described above in terms of embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the invention that are not currently foreseen may still represent equivalent modifications of the invention.

[0085] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. As long as the technical effects of the present invention are achieved by the same means, they shall fall within the scope of protection of the present invention. Within the scope of protection of the present invention, various modifications and variations of the technical solutions and / or implementation methods may be made.

Claims

1. An influenza risk prediction method based on multi-source data, characterized in that: These include: Determine the target influenza type, and determine the type of associated multi-source data based on the target influenza type; Determine the weight value corresponding to each data type; Calculate the standard value for each data type based on its healthy user sample; Obtain multi-source data of the target user, and then determine the data value corresponding to the type of the multi-source data of the target user; Calculate the deviation coefficient between the data value corresponding to each data type of the target user and its standard value to obtain the deviation coefficient of each data type of the target user; Calculating a flu risk value based on the deviation coefficient of each data type of the target user and the weight value; Determine whether the influenza risk value is greater than a preset risk threshold. If so, it is determined that there is an influenza risk. If not, it is determined that there is no influenza risk.

2. The influenza risk prediction method based on multi-source data according to claim 1, characterized in that: Specifically, determine the weight value corresponding to each data type, including: If there are m types of data; Standardizing the m types of data to obtain the standardized m types of data; Calculate the information entropy of each data type as follows: Among them, H j represents the information entropy of the jth data type, p ij is the normalized proportion of the i-th data type in the j-th data type, and k is a preset constant; The corresponding weight is calculated based on the information entropy of each data type. The calculation formula is as follows: Among them, w j Represents the weight of the j-th data type.

3. The influenza risk prediction method based on multi-source data according to claim 1, characterized in that: Specifically, the standard value of each data type is calculated based on its healthy user sample. include, Sampling multiple healthy users to obtain data values of each data type of the sampled healthy users; For any type of data, calculate the average value of the data values of all healthy users sampled from it, and finally obtain the average value of the data values of all healthy users of all types of data, and use the average value of the data values of all healthy users as the representation value of the data type; The characterization values of all data types are standardized to obtain the standard value of each data type.

4. The influenza risk prediction method based on multi-source data according to claim 3, characterized in that: Specifically, the deviation coefficient between the data value corresponding to each data type of the target user and its standard value is calculated to obtain the deviation coefficient of each data type of the target user, including: For any data type, normalize the data value corresponding to the data type of the target user to obtain a first value; Subtract the standard value of the data type from the first value and take the absolute value to obtain the offset coefficient of the data type of the target user; The offset coefficient of each data type of the target user is calculated in the above manner.

5. The influenza risk prediction method based on multi-source data according to claim 4, characterized in that: Specifically, the influenza risk value is calculated based on the deviation coefficient of each data type of the target user and the weight value, including: If the offset coefficient of the target user's jth data type is Q j , then the target user's influenza risk value is recorded as FX and is calculated as follows:

6. The influenza risk prediction method based on multi-source data according to claim 1, characterized in that: The method further comprises, When the target user is at risk of influenza, an early warning reminder is issued to the target user. The early warning reminder is sent to the target user in a preset format. A text message informs the user that the user is at risk of influenza and needs to go to the hospital for a checkup in time.

7. The influenza risk prediction method based on multi-source data according to claim 6, characterized in that: The method further comprises, When the target user is at risk of influenza, the multi-source data obtained for the target user is packaged to obtain a data packet and a query link is generated. The query link is used to provide the data packet for the doctor to review when the target user is reviewed in the hospital and the doctor obtains the target user's authorization.

8. The influenza risk prediction method based on multi-source data according to claim 7, characterized in that: Specifically, obtaining authorization from the target user includes one or more combinations of face recognition, fingerprint recognition, or key recognition of the target user.

Images