A vital signs data acquisition system based on artificial intelligence

Abstract

The present invention belongs to the field of intelligent medical data collection and discloses a vital sign data collection system based on artificial intelligence. The present invention collects human bioelectric signals, user information feature data, user medical diagnosis lesion sites and user preferred vital signs to construct a vital sign collection and positioning model. The constructed vital sign collection and positioning model generates real-time user preferred vital signs based on the real-time human bioelectric signals, real-time user information feature data and real-time user medical diagnosis lesion sites received by the bioinformation detector. According to the pathological tissue corresponding to the real-time user preferred vital signs, the pathological tissue is repaired by bioelectromagnetic therapy using bioinformation. The present invention accurately identifies the user's abnormal vital sign data and obtains the pathological location, realizes the optimized collection of vital sign data based on artificial intelligence, reduces the workload of medical personnel, and provides a basis for subsequent bioelectromagnetic therapy to select the pathological site of the vital body for targeted bioelectromagnetic feedback treatment.

Description

Technical Field

[0001] This invention belongs to the field of intelligent medical data acquisition technology, and in particular relates to an artificial intelligence-based vital sign data acquisition system. Background Technology

[0002] With home-based elderly care becoming the norm, the vital signs and condition of the elderly cannot be monitored in real time. Most monitoring and alarm devices on the market only issue alarms after a problem occurs, and patients cannot interact with medical staff promptly after leaving the hospital. Therefore, how to conduct real-time bio-information monitoring of the monitored population, assist doctors in locating pathological tissues, and utilize bioelectromagnetic technology for subsequent electromagnetic therapy targeting these pathological points has become an urgent problem to be solved.

[0003] Furthermore, how to accurately identify abnormal vital signs data of users and obtain pathological locations, realize AI-based optimized collection of vital signs data, reduce the workload of medical personnel, and provide a foundation for subsequent bioelectromagnetic therapy to select pathological sites for targeted bioelectromagnetic feedback treatment has become an important issue for rapidly identifying the real-time health status of patients.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art.

[0005] Therefore, there is an urgent need for an artificial intelligence-based vital sign data acquisition system to solve the above problems. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention proposes a vital signs data acquisition system based on artificial intelligence.

[0007] In a first aspect of the present invention, a method for collecting vital sign data based on artificial intelligence is provided, characterized in that the method includes the following steps:

[0008] S1. Acquire the first bioelectric signal of the human body and the first user information feature data, the first user medical diagnosis lesion site and the first user preferred vital signs collected and transmitted from the user's hospital end.

[0009] S2. A first acquisition vector feature constructed based on the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site;

[0010] S3. Construct a vital sign acquisition and positioning model by utilizing the features of the first acquisition vector and the first user-preferred vital signs.

[0011] S4. The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital sign localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

[0012] Furthermore, the first bioelectric signal or the second bioelectric signal uses the bioinformation sensing sensor built into the bioinformation detector to acquire muscle electrical signals from the arm area, and uses a wireless EEG acquisition device to acquire EEG signals and transmit them to the bioinformation detector. The EEG signals and the muscle electrical signals are combined to form the first bioelectric signal or the second bioelectric signal.

[0013] Furthermore, the first user information feature data or the first user information feature data includes user gender, user age, user height, and user weight;

[0014] The location of the lesion diagnosed by the first user or the second user is determined by collecting and transmitting the user's previous first or second medical record data from the hospital.

[0015] Furthermore, the wireless EEG acquisition device includes the NeuroHUB series wireless EEG acquisition system, which can acquire brain signals from 64 brain EEG channels; the specific brain acquisition areas for the EEG signals are F7, F3, Fz, F4, F8, Cz, C3, C4, O1, and O2.

[0016] Furthermore, the muscle electrical signal M t It is obtained by processing the reciprocal of the distance between the location of the muscle electromyography signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user.

[0017] Furthermore, the first acquisition vector feature is composed of the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site, and the second acquisition vector feature is composed of the second bioelectric signal, the second user information feature data, and the second user's medical diagnosis lesion site, specifically composed of vector feature splicing.

[0018] Furthermore, the vital signs acquisition and localization model employs an improved neural network model.

[0019] A vital signs data acquisition system based on artificial intelligence is also provided. The system includes a bioinformatics monitoring module, a user information registration module, a user information storage module, a medical diagnostic information collection module, a vital signs acquisition and positioning model construction module, and a vital signs data acquisition module. Its features are:

[0020] The bio-information monitoring module is used to collect and acquire the first bioelectrical signal of the human body, and also to collect and acquire the second bioelectrical signal of the human body.

[0021] The user information registration module is used for uploading first user information feature data during user registration, and also for uploading second user information feature data.

[0022] The medical diagnostic information collection module is connected to the hospital client and receives the first user medical diagnostic lesion site collected and transmitted from the user hospital and the second user medical diagnostic lesion site collected and transmitted from the user hospital.

[0023] The user information storage module is used to receive the first user information feature data transmitted from the user information registration module, and also to receive the second user information feature data. It stores the preferred vital signs of the first user and is connected to the medical diagnosis information collection module to receive the lesion sites of the first user and the second user.

[0024] The vital signs acquisition and positioning model construction module receives the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site, processes them to obtain the first acquisition vector feature, and uses the first acquisition vector feature and the first user's preferred vital signs to construct a vital signs acquisition and positioning model.

[0025] The vital signs data acquisition module: The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital signs localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

[0026] Furthermore, the first bioelectric signal or the second bioelectric signal uses the bioinformation sensing sensor built into the bioinformation detector to acquire muscle electrical signals from the arm area, and uses a wireless EEG acquisition device to acquire EEG signals and transmit them to the bioinformation detector. The EEG signals and the muscle electrical signals are combined to form the first bioelectric signal or the second bioelectric signal.

[0027] The muscle electrical signal M t It is obtained by processing the reciprocal of the distance between the location of the electromyographic signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user;

[0028] The first acquisition vector feature is composed of the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site. The second acquisition vector feature is composed of the second bioelectric signal, the second user information feature data, and the second user's medical diagnosis lesion site. The specific composition method is vector feature splicing.

[0029] Furthermore, the vital signs acquisition and localization model employs an improved neural network model.

[0030] This invention discloses an artificial intelligence-based vital sign data acquisition system. By collecting muscle electrical signals and electroencephalographic signals from key parts of the body and combining them with vital sign data related to individual height, age, and other factors, the system improves the neural network model suitable for optimal vital sign data acquisition. This allows for the accurate identification of abnormal vital sign data and the acquisition of pathological locations, achieving AI-driven optimized acquisition of vital sign data. This reduces the workload of medical personnel and provides a foundation for subsequent targeted bioelectromagnetic feedback therapy to select pathological sites in the body. Attached Figure Description

[0031] Figure 1 This is a flowchart of a vital sign data acquisition method based on artificial intelligence according to the present invention;

[0032] Figure 2 This is a schematic diagram of the structure of a vital signs data acquisition system based on artificial intelligence according to the present invention;

[0033] Figure 3 This is a schematic diagram of the bioinformatics detector in this invention;

[0034] Figure 4 This is a schematic diagram of the human body point coordinates after two-dimensional coordinate conversion in this method;

[0035] Figure 5 This is an EEG lead diagram in an embodiment of the present invention. Detailed Implementation

[0036] The invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0037] First embodiment of the present invention:

[0038] In a first aspect of the present invention, in order to solve the above-mentioned technical problems, an artificial intelligence-based vital sign data acquisition system is provided.

[0039] In a first aspect of the present invention, a method for collecting vital sign data based on artificial intelligence is provided, characterized in that the method includes the following steps:

[0040] S1. Acquire the first bioelectric signal of the human body and the first user information feature data, the first user medical diagnosis lesion site and the first user preferred vital signs collected and transmitted from the user's hospital end.

[0041] S2. A first acquisition vector feature constructed based on the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site;

[0042] S3. Construct a vital sign acquisition and positioning model by utilizing the features of the first acquisition vector and the first user-preferred vital signs.

[0043] S4. The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital sign localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

[0044] In this embodiment, the first or second preferred vital signs of the user are vector features composed of four feature vector values: the coordinates of the human body points after being converted into two-dimensional coordinates from front to back, the coordinates of the points, body temperature, and electromyographic signal parameters. Electromagnetic feedback therapy can be performed on the corresponding points based on the preferred vital signs of the user.

[0045] Furthermore, the first bioelectric signal or the second bioelectric signal uses the bioinformation sensing sensor built into the bioinformation detector to acquire muscle electrical signals from the arm area, and uses a wireless EEG acquisition device to acquire EEG signals and transmit them to the bioinformation detector. The EEG signals and the muscle electrical signals are combined to form the first bioelectric signal or the second bioelectric signal.

[0046] Furthermore, the first user information feature data or the first user information feature data includes user gender, user age, user height, and user weight;

[0047] The location of the lesion diagnosed by the first user or the second user is determined by collecting and transmitting the user's previous first or second medical record data from the hospital.

[0048] Furthermore, the wireless EEG acquisition device includes the NeuroHUB series wireless EEG acquisition system, which can acquire brain signals from 64 brain EEG channels; the specific brain acquisition areas for the EEG signals are F7, F3, Fz, F4, F8, Cz, C3, C4, O1, and O2.

[0049] The formula for calculating the EEG signal is as follows:

[0050]

[0051] In the formula, R f The EEG signal is represented by k, which is the gender adjustment coefficient, n, the number of selected EEG channels, S, and the number of uncollected EEG channels. R1, R2, ..., R 10 The amplitude of the EEG signal collected corresponding to F7, F3, Fz, F4, F8, Cz, C3, C4, O1, and O2 is expressed in μV.

[0052] Furthermore, the muscle electrical signal M t The calculation formula is as follows:

[0053] M t =k1M h +k2M l +k3M d

[0054] In the formula, k1, k2, and k3 are the reciprocals of the distances between the location of the electromyographic signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user, and M... h For the electrical signals of the arm muscles, M l M represents the electrical signals of the leg muscles. d This represents the electrical signal of the abdominal muscles, measured in mV.

[0055] Furthermore, the first acquisition vector feature is composed of the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site, and the second acquisition vector feature is composed of the second bioelectric signal, the second user information feature data, and the second user's medical diagnosis lesion site, specifically composed of vector feature splicing.

[0056] Furthermore, the vital sign acquisition and localization model employs an improved neural network model, and its improved activation function calculation formula is shown below:

[0057]

[0058] e(X) is the activation function value, X is the input acquisition vector feature, k1, k2, k3 are the reciprocals of the distances between the source location of the electromyography signal and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user, n is the number of EEG channels selected for acquisition, and S is the number of EEG channels not acquired.

[0059] A vital signs data acquisition system based on artificial intelligence is also provided. The system includes a bioinformatics monitoring module, a user information registration module, a user information storage module, a medical diagnostic information collection module, a vital signs acquisition and positioning model construction module, and a vital signs data acquisition module. Its features are:

[0060] The bio-information monitoring module is used to collect and acquire the first bioelectrical signal of the human body, and also to collect and acquire the second bioelectrical signal of the human body.

[0061] The user information registration module is used for uploading first user information feature data during user registration, and also for uploading second user information feature data.

[0062] The medical diagnostic information collection module is connected to the hospital client and receives the first user medical diagnostic lesion site collected and transmitted from the user hospital and the second user medical diagnostic lesion site collected and transmitted from the user hospital.

[0063] The user information storage module is used to receive the first user information feature data transmitted from the user information registration module, and also to receive the second user information feature data. It stores the preferred vital signs of the first user and is connected to the medical diagnosis information collection module to receive the lesion sites of the first user and the second user.

[0064] The vital signs acquisition and positioning model construction module receives the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site, processes them to obtain the first acquisition vector feature, and uses the first acquisition vector feature and the first user's preferred vital signs to construct a vital signs acquisition and positioning model.

[0065] The vital signs data acquisition module: The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital signs localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

[0066] Furthermore, the first bioelectric signal or the second bioelectric signal uses the bioinformation sensing sensor built into the bioinformation detector to acquire muscle electrical signals from the arm, thigh, and abdomen, and uses a wireless EEG acquisition device to acquire EEG signals and transmit them to the bioinformation detector. The EEG signals and the muscle electrical signals are combined to form the first bioelectric signal or the second bioelectric signal.

[0067] The formula for calculating the EEG signal is as follows:

[0068]

[0069] In the formula, R f The EEG signal is represented by k, which is the gender adjustment coefficient, n, the number of selected EEG channels, S, and the number of uncollected EEG channels. R1, R2, ..., R 10 The amplitude of the EEG signal collected corresponding to F7, F3, Fz, F4, F8, Cz, C3, C4, O1 and O2 is expressed in μV.

[0070] The muscle electrical signal M t The calculation formula is as follows:

[0071] M t =k1M h +k2M l +k3M d

[0072] In the formula, k1, k2, and k3 are the reciprocals of the distances between the location of the electromyographic signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user, and M... hFor the electrical signals of the arm muscles, M l M represents the electrical signals of the leg muscles. d This represents the electrical signal of the abdominal muscles, measured in mV.

[0073] The first acquisition vector feature is composed of the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site. The second acquisition vector feature is composed of the second bioelectric signal, the second user information feature data, and the second user's medical diagnosis lesion site. The specific composition method is vector feature splicing.

[0074] Furthermore, the vital sign acquisition and localization model employs an improved neural network model, and its improved activation function calculation formula is shown below:

[0075]

[0076] e(X) is the activation function value, X is the input acquisition vector feature, k1, k2, k3 are the reciprocals of the distances between the source location of the electromyography signal and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user, n is the number of EEG channels selected for acquisition, and S is the number of EEG channels not acquired.

[0077] This invention discloses an artificial intelligence-based vital sign data acquisition system. By collecting muscle electrical signals and electroencephalographic signals from key parts of the body and combining them with vital sign data related to individual height, age, and other factors, the system improves the neural network model suitable for optimal vital sign data acquisition. This allows for the accurate identification of abnormal vital sign data and the acquisition of pathological locations, achieving AI-driven optimized acquisition of vital sign data. This reduces the workload of medical personnel and provides a foundation for subsequent targeted bioelectromagnetic feedback therapy to select pathological sites in the body.

[0078] The combination of multiple embodiments of the present invention can achieve all the above effects, but it is not required that each embodiment of the present invention achieve all the above advantages and effects, because each embodiment of the present invention can constitute a separate technical solution and make one or more contributions to the prior art.

[0079] For any module structures not specifically defined in this invention, the existing technical specifications shall prevail. The existing technical specifications mentioned in the foregoing background and specific embodiments sections are considered part of this invention and are used to understand the meaning of certain technical features or parameters. The scope of protection of this invention is determined by the actual contents of the claims.

Claims

1. A vital sign data acquisition system based on artificial intelligence, characterized in that, The system implements the following method steps: S1. Acquire the first bioelectric signal of the human body and the first user information feature data, the first user medical diagnosis lesion site and the first user preferred vital signs collected and transmitted from the user's hospital end. S2. A first acquisition vector feature constructed based on the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site; S3. A vital sign acquisition and positioning model is constructed using the features of the first acquisition vector and the first user-preferred vital signs. The vital sign acquisition and positioning model adopts an improved neural network model, and its improved activation function calculation formula is shown below: ； Let X be the activation function value, and X be the input sampled vector features. , , The distance between the location of the electromyography signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user is the reciprocal of the distance. n is the number of EEG channels selected for acquisition, and S is the number of EEG channels not acquired. The first or second bioelectrical signal is acquired using a bioinformation sensor built into the bioinformation detector, which obtains muscle electrical signals from the arm area. The brain signals are then acquired using a wireless EEG acquisition device and transmitted to the bioinformation detector. The brain signals are then compared with... The combination forms the first bioelectric signal or the second bioelectric signal; The It is obtained by processing the reciprocal of the distance between the source location of the electromyographic signal and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user. Further, the... The calculation formula is as follows: ； In the formula, , , It is the reciprocal of the distance between the location of the electromyography signal source and the lesion site diagnosed by the first user or the lesion site diagnosed by the second user. Electrical signals from arm muscles. This represents the electrical signals from the leg muscles. This represents the electrical signal of the abdominal muscles, measured in mV. S4. The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital sign localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

2. The vital sign data acquisition system based on artificial intelligence as described in claim 1, characterized in that: The first user information feature data or the second user information feature data includes user gender, user age, user height, and user weight; The location of the lesion diagnosed by the first user or the second user is determined by collecting and transmitting the user's previous first or second medical record data from the hospital.

3. The artificial intelligence-based vital sign data acquisition system as described in claim 2, characterized in that: The wireless EEG acquisition device includes the NeuroHUB series wireless EEG acquisition system from Boruikang. This device can acquire brain signals from 64 brain EEG channels. The specific brain regions for acquiring these signals are F7, F3, Fz, F4, F8, Cz, C3, C4, O1, and O2. The calculation formula for these EEG signals is as follows: ； In the formula, The EEG signal is represented by k, which is the gender adjustment coefficient, n is the number of selected EEG channels, and S is the number of uncollected EEG channels. , ... The amplitude values ​​of the EEG signals collected for F7, F3, Fz, F4, F8, Cz, C3, C4, O1, and O2 are given, with units of [missing information]. .

4. The vital sign data acquisition system based on artificial intelligence as described in claim 3, characterized in that: The first acquisition vector feature is composed of the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site. The second acquisition vector feature is composed of the second bioelectric signal, the second user information feature data, and the second user's medical diagnosis lesion site. The specific composition method is vector feature splicing.

5. A vital sign data acquisition system based on artificial intelligence as described in claim 1, the system comprising a bioinformatics monitoring module, a user information registration module, a user information storage module, a medical diagnostic information collection module, a vital sign acquisition and positioning model construction module, and a vital sign data acquisition module, characterized in that: The bio-information monitoring module is used to collect and acquire the first bioelectrical signal of the human body, and also to collect and acquire the second bioelectrical signal of the human body. The user information registration module is used for uploading first user information feature data during user registration, and also for uploading second user information feature data. The medical diagnostic information collection module is connected to the hospital client and receives the first user medical diagnostic lesion site collected and transmitted from the user hospital and the second user medical diagnostic lesion site collected and transmitted from the user hospital. The user information storage module is used to receive the first user information feature data transmitted from the user information registration module, and also to receive the second user information feature data. It stores the preferred vital signs of the first user and is connected to the medical diagnosis information collection module to receive the lesion sites of the first user and the second user. The vital signs acquisition and positioning model construction module receives the first bioelectric signal, the first user information feature data, and the first user's medical diagnosis lesion site, processes them to obtain the first acquisition vector feature, and uses the first acquisition vector feature and the first user's preferred vital signs to construct a vital signs acquisition and positioning model. The vital signs data acquisition module: The bioinformatics detector receives the second bioelectric signal and second user information feature data of the human body, as well as the second user medical diagnosis lesion site collected and transmitted from the user's hospital. Based on the second bioelectric signal, the second user information feature data, and the second user medical diagnosis lesion site, a second acquisition vector feature is constructed. The vital signs localization model processes the second acquisition vector feature to generate the second user preferred vital signs. Based on the second user preferred vital signs, the corresponding pathological tissue site of the human body is obtained, and bioelectromagnetic feedback therapy is selectively performed on the pathological tissue site.

Images