Passive electromagnetic wave biological resonance chip for health field

Abstract

The invention relates to the field of passive electromagnetic wave biological resonance chips, in particular to a passive electromagnetic wave biological resonance chip used in the health field. The system specifically comprises an energy receiving device used for receiving space electromagnetic field energy; the processor is used for generating functional electromagnetic waves; and the radio frequency electromagnetic wave transmitting device is used for transmitting the functional electromagnetic waves to the surrounding space. The passive electromagnetic wave biological resonance chip stores electromagnetic field energy in a short time, adjusts the frequency of the electromagnetic field energy and then oscillates the electromagnetic field energy, the electromagnetic field energy is released and transmitted to a human body through the radio frequency electromagnetic wave transmitting device, oscillated electromagnetic waves and human body biological electromagnetic waves resonate, and the aim of activating human cells is achieved through biological electric signal amplification. Therefore, human microcirculation is improved, and human metabolism is promoted.

Description

Technical Field

[0001] The present application relates to the field of passive electromagnetic wave bioresonance chips, and in particular to a passive electromagnetic wave bioresonance chip for use in the health field. Background Art

[0002] Microcirculation refers to the blood circulation between arterioles and venules. The blood flow of microcirculation is affected by the contraction and relaxation of vascular smooth muscles regulated by nerves and body fluids. At present, in traditional Chinese medicine, acupuncture and moxibustion are usually used to promote blood microcirculation in the human body and change the human magnetic field to improve human functions; however, the existing methods are simply carried out through a simple magnetic field, and an external power supply is generally required during the process, which has poor effects.

[0003] RF energy harvesting technology can power low-power sensors, implantable biomedical chips and other electronic devices by collecting RF electromagnetic wave signals. As a form of energy that is prevalent in the current environment, RF energy has the characteristics of being green, environmentally friendly and having stable power supply. Based on this, the development and application of RF energy harvesting technology provides a new idea for solving the above technical problems. Summary of the invention

[0004] This application is made in view of the above problems. One purpose of this application is to provide a passive electromagnetic wave bioresonance chip for the health field.

[0005] The embodiment of the present application provides a passive electromagnetic wave bioresonance chip for the health field, which includes: an energy receiving device for receiving space electromagnetic field energy; a processor for generating functional electromagnetic waves; a radio frequency electromagnetic wave transmitting device for sending the functional electromagnetic waves to the surrounding space; wherein the processor includes: a vital sign data acquisition module for acquiring a time series of vital sign data of a monitored object collected by a wearable device, wherein the vital sign data includes a heart rate value, a body temperature value, a blood pressure value, a respiratory rate value and a blood oxygen saturation; a vital sign time series correlation feature extraction module for performing vital sign time series correlation feature extraction on the time series of the vital sign data to obtain a vital sign time series correlation feature map; a semantic enhancement module for performing context semantic enhancement on the vital sign time series correlation feature map to obtain a set of enhanced vital sign time series correlation pixel-level feature vectors; a functional electromagnetic wave frequency recommendation module for determining a recommended frequency value of the functional electromagnetic wave based on the set of enhanced vital sign time series correlation pixel-level feature vectors; an output frequency adjustment module for adjusting the output frequency of the functional electromagnetic wave to the recommended frequency value.

[0006] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the vital sign time series correlation feature extraction module includes: a data structuring unit, which is used to arrange the time series of the vital sign data into a vital sign time series correlation matrix according to the time dimension and the parameter sample dimension; a vital sign feature extraction unit, which is used to input the vital sign time series correlation matrix into a vital sign time series correlation pattern feature extractor based on a void convolutional neural network model to obtain the vital sign time series correlation feature graph.

[0007] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the semantic enhancement module includes: a feature dispersion unit, which is used to disperse the feature pixel granularity of the vital sign time series association feature map along the channel dimension to obtain a set of vital sign time series association pixel-level feature vectors; a significance-global dual semantic enhancement unit, which is used to input the set of vital sign time series association pixel-level feature vectors into the contextual semantic enhancement module based on significance-globality to obtain the set of enhanced vital sign time series association pixel-level feature vectors.

[0008] For example, according to the passive electromagnetic wave bioresonance chip for the health field of the embodiment of the present application, the saliency-global dual semantic enhancement unit includes: a saliency information extraction subunit, which is used to extract the vital sign time series associated prominent feature vector of the set of the vital sign time series associated pixel-level feature vectors; a global information extraction subunit, which is used to extract the vital sign time series associated global feature vector of the set of the vital sign time series associated pixel-level feature vectors; a neighborhood encoding and activation subunit, which is used to perform neighborhood encoding and activation on the vital sign time series associated prominent feature vector and the vital sign time series associated global feature vector to obtain the vital sign time series associated prominent feature context associated activation feature vector and the vital sign time series associated global feature context associated activation feature vector; a dual semantic enhancement weight construction subunit, which is used to fuse the vital sign time series associated prominent feature vector and the vital sign time series associated global feature vector. After the feature context-associated activation feature vector and the vital sign timing-associated global feature context-associated activation feature vector are obtained by combining the vital sign timing-associated highlighting-global feature context-associated activation feature vector, the vital sign timing-associated highlighting-global feature context-associated activation feature vector is nonlinearly activated to obtain the vital sign timing-associated highlighting-global feature context-associated weight feature vector; a semantic reinforcement subunit is used to use the vital sign timing-associated highlighting-global feature context-associated weight feature vector as the weight vector, perform positional dot multiplication on each vital sign timing-associated pixel-level feature vector in the set of the vital sign timing-associated pixel-level feature vectors, and perform element-by-element addition of the sequence obtained by the positional dot multiplication and the set of the vital sign timing-associated pixel-level feature vectors to obtain the set of the enhanced vital sign timing-associated pixel-level feature vectors.

[0009] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the saliency information extraction subunit is used to: calculate the maximum value of each vital sign time-series associated pixel-level feature vector in the set of the vital sign time-series associated pixel-level feature vectors to obtain the vital sign time-series associated salient feature vector composed of each of the maximum values.

[0010] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the global information extraction subunit is used to: calculate the average value of each vital sign timing-associated pixel-level feature vector in the set of the vital sign timing-associated pixel-level feature vectors to obtain the vital sign timing-associated global feature vector composed of each of the average values.

[0011] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the neighborhood coding and activation subunit is used to: perform one-dimensional convolution coding, nonlinear activation and linear transformation on the vital sign time series associated salient feature vector to obtain the vital sign time series associated salient feature context associated activation feature vector; perform one-dimensional convolution coding, nonlinear activation and linear transformation on the vital sign time series associated global feature vector to obtain the vital sign time series associated global feature context associated activation feature vector.

[0012] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the dual semantic reinforcement weight construction subunit is used to: respectively pass the vital sign timing association prominence-global feature context association activation feature vector through the tanh activation function and the sigmoid activation function, and then perform dot multiplication on the two vectors obtained to obtain the vital sign timing association prominence-global feature context association weight feature vector.

[0013] For example, according to the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the functional electromagnetic wave frequency recommendation module is used to: input the set of enhanced vital sign timing-related pixel-level feature vectors into a decoder-based frequency recommender to obtain a decoding result, and the decoding result is used to represent the recommended frequency value of the functional electromagnetic wave.

[0014] According to the passive electromagnetic wave bioresonance chip for the health field of the embodiment of the present application, it stores the electromagnetic field energy for a short time, adjusts its frequency and then oscillates it, and releases it to the human body through a radio frequency electromagnetic wave transmitting device. The oscillated electromagnetic waves resonate with the human body's biological electromagnetic waves, and amplify the bioelectric signals to achieve the purpose of activating human cells, thereby improving human microcirculation and promoting human metabolism. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0016] Figure 1 A schematic diagram of the application architecture of a passive electromagnetic wave bioresonance chip used in the health field in an embodiment of the present application is shown.

[0017] Figure 2 A schematic diagram of the structure of a passive electromagnetic wave bioresonance chip used in the health field in an embodiment of the present application is shown.

[0018] Figure 3A schematic diagram of the structure of a processor of a passive electromagnetic wave bioresonance chip used in the health field in an embodiment of the present application is shown;.

[0019] Figure 4 A schematic diagram of the structure of a vital sign time series correlation feature extraction module of a passive electromagnetic wave bioresonance chip used in the health field in an embodiment of the present application is shown.

[0020] Figure 5 A structural schematic diagram of a semantic enhancement module of a passive electromagnetic wave bioresonance chip used in the health field in an embodiment of the present application is shown.

[0021] Figure 6 A flow chart of a processing method of a passive electromagnetic wave bioresonance chip for the health field in an embodiment of the present application is shown.

[0022] Figure 7 A schematic diagram of a storage medium according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0024] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intention of a person of ordinary skill in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0025] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0026] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0027] Figure 1 A schematic diagram of the application architecture of a passive electromagnetic wave bioresonance chip for the health field in an embodiment of the present application is shown, including a server 100 and a terminal device 200.

[0028] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, the data exchanged through the network is represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0029] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0030] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present application, the memory 120 may be used to store the method corresponding to the passive electromagnetic wave bioresonance chip used in the health field in the embodiment of the present application.

[0031] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the processing methods for the passive electromagnetic wave bioresonance chip for the health field in the embodiments of the present application according to the obtained program instructions.

[0032] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0033] The following is a non-limiting description of the passive electromagnetic wave bioresonance chip for the health field provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also belong to the scope of protection of the present application.

[0034] The coupling of electromagnetic waves between the human body depends on the wavelength of the electromagnetic waves. 30KHz-10MHz electromagnetic waves cannot resonate with the human body, 10MHz-2GHz electromagnetic waves can resonate with the human body, and 2GHz-300GHz electromagnetic waves can be absorbed by the skin. Electromagnetic waves have a skin effect (when electromagnetic waves are incident from a medium to a good conductor, they decay quickly in the good conductor and the electromagnetic waves only exist on the surface of the good conductor). The shorter the wavelength, the more obvious the skin effect. This is why people feel their skin is very hot when infrared rays irradiate the human body.

[0035] The electromagnetic wave frequency generated by the passive electromagnetic wave bioresonance chip is concentrated in 500MHz-1000MHz, which is easy to resonate with the human body's biological electromagnetic field. The chip processor transmits the functional electromagnetic wave to the surrounding space through the transmitter, which is absorbed by the human body and resonates with the human body's biological electromagnetic field. The purpose of activating human cells is achieved through the amplification of bioelectric signals.

[0036] The space we live in is full of electromagnetic fields, including the universe, the sun, and the earth. The energy receiving device in the passive electromagnetic wave bioresonance chip can absorb and utilize these space electromagnetic fields. At the same time, the human body is also radiating electromagnetic fields outward all the time, which can also be received and utilized by the chip, providing energy to the chip through inductive coupling.

[0037] The space is full of electromagnetic waves, and the human body itself radiates electromagnetic waves all the time. The chip absorbs these electromagnetic waves radiated from space and generates 500MHz-1000MHz electromagnetic waves. When electromagnetic waves encounter the human body, they can be reflected and transmitted. The transmitted electromagnetic waves are the main component of the biological effect.

[0038] Cells are the smallest unit of life and a system with life characteristics and functions. The cell system model of the electromagnetic environment describes the relationship between the electromagnetic field and the biological system. The electromagnetic field force causes nucleic acids, proteins, ions and other substances to interact with each other, and the electromagnetic energy causes the chemical bonds of molecules and the energy level changes of electrons to produce new chemical substances, such as free radicals. Whether it is an extremely low frequency electromagnetic field with a wavelength far greater than the scale of the organism itself, or a radio frequency electromagnetic field with a wavelength close to the scale of the organism itself, the interaction with the organism is initially initiated by the absorption of electromagnetic energy, which initiates the biological reaction.

[0039] Human cells contain Na+, K+ plasma, which migrate under the electromagnetic field of the chip, forming a potential difference, that is, an electrical signal. The electrical signal is transmitted to the central nervous system through the meridians (nerves). The autonomic nerves in the central nervous system control the smooth muscles to dilate blood vessels, increase blood circulation, and transport nutrients, water, and oxygen to the cells. The cells discharge metabolic waste such as carbon dioxide, urea, and uric acid into the blood, and finally, they are excreted from the body through breathing, sweating, urination, etc.

[0040] The passive electromagnetic wave bioresonance chip can absorb electromagnetic waves in space and emit radio frequency electromagnetic waves, which resonate with the human body's biological electromagnetic field. The human body receives the stimulation signals emitted by the chip and transmits them to the nervous system, through the sensory nerves, central nervous system, motor nerves and autonomic nerves, and then controls the movement of smooth muscles, myocardium and glands. Because smooth muscles are distributed on the walls of human arteries and veins, they can relax and dilate blood vessels under nerve regulation, increase blood flow rate, and reduce blood flow resistance and increase blood flow by dilating blood vessels, thereby accelerating metabolism, providing cells with nutrients, water and oxygen, and excreting metabolic waste.

[0041] Based on the above principles and mechanisms, the present application provides a passive electromagnetic wave bioresonance chip for use in the health field, such as Figure 2 As shown, it specifically includes: an energy receiving device 1, used for receiving space electromagnetic field energy; a processor 2, used for generating functional electromagnetic waves; and a radio frequency electromagnetic wave transmitting device 3, used for sending the functional electromagnetic waves to the surrounding space.

[0042] The electromagnetic wave frequency generated by the passive electromagnetic wave bioresonance chip is concentrated in 500MHz-1000MHz, and the range after detection is 922.52MHz-925.76MHz, which is easy to resonate with the human body's biological electromagnetic field. The chip can act on the acupuncture points of the human body, which can effectively promote the blood circulation of the human body. According to the different locations of the acupuncture points, related products such as glasses, eye masks, belts, knee pads, etc. can be developed. According to the beneficial effects of the passive electromagnetic wave bioresonance chip, users only need to wear its derivative products to the position that needs to be adjusted according to their own needs (head, neck, waist, legs, joints, etc.).

[0043] Specifically, the passive electromagnetic wave bioresonance chip stores the electromagnetic field energy for a short time, adjusts its frequency and then oscillates it, and releases it to the human body through a radio frequency electromagnetic wave transmitting device. The oscillated electromagnetic waves resonate with the human body's biological electromagnetic waves, and amplify the bioelectric signals to achieve the purpose of activating human cells, thereby improving human microcirculation and promoting human metabolism.

[0044] Considering that the traditional output frequency adjustment relies on a preset mathematical model, it cannot be adaptively adjusted according to the characteristics of human bio-electromagnetic waves, and there may be problems such as inconsistency with the human body's resonance frequency. In response to the above technical problems, the technical concept of this application is: using wearable devices to collect human vital signs data, constructing a deep learning model to extract time-series correlation feature patterns from the vital signs data, and forming semantic reinforcement weights based on the significance information and global information of the vital signs time-series correlation feature patterns themselves, and further performing double semantic reinforcement on the vital signs time-series correlation feature patterns. In this way, a frequency recommender is constructed using a decoder to generate a recommended frequency value of a functional electromagnetic wave based on the semantically reinforced vital signs time-series correlation feature representation, so that the output frequency of the functional electromagnetic wave can be adaptively adjusted according to the physical sign characteristics of the human body.

[0045] Based on this, Figure 3 As shown, the processor 2 includes: a vital sign data acquisition module 21, which is used to obtain the time series of vital sign data of the monitored object collected by the wearable device, wherein the vital sign data includes heart rate value, body temperature value, blood pressure value, respiratory rate value and blood oxygen saturation; a vital sign time series association feature extraction module 22, which is used to extract vital sign time series association features from the time series of the vital sign data to obtain a vital sign time series association feature map; a semantic enhancement module 23, which is used to perform contextual semantic enhancement on the vital sign time series association feature map to obtain a set of enhanced vital sign time series association pixel-level feature vectors; a functional electromagnetic wave frequency recommendation module 24, which is used to determine the recommended frequency value of the functional electromagnetic wave based on the set of enhanced vital sign time series association pixel-level feature vectors; an output frequency adjustment module 25, which is used to adjust the output frequency of the functional electromagnetic wave to the recommended frequency value.

[0046] Specifically, in the technical solution of the present application, first, the time series of vital sign data of the monitored object collected by the wearable device is obtained, wherein the vital sign data includes heart rate value, body temperature value, blood pressure value, respiratory rate value and blood oxygen saturation. Here, heart rate data, body temperature data, blood pressure data, respiratory rate data and blood oxygen saturation data are basic parameters reflecting the physiological state of the human body, and they reflect the change of the individual physiological state in real time. Then, the time series of the vital sign data is arranged into a vital sign time series association matrix according to the time dimension and the parameter sample dimension; and the vital sign time series association matrix is ​​input into a vital sign time series association pattern feature extractor based on a hollow convolutional neural network model to obtain a vital sign time series association feature map. That is, after the discretely distributed heart rate data, body temperature data, blood pressure data, respiratory rate data and blood oxygen saturation data are converted into a structured matrix representation, the hollow convolutional neural network model is used to construct a vital sign time series association pattern feature extractor to capture the complex neighborhood association relationship between the vital sign data.

[0047] Accordingly, if Figure 4 As shown, the vital sign time series association feature extraction module 22 includes: a data structuring unit 221, which is used to arrange the time series of the vital sign data into a vital sign time series association matrix according to the time dimension and the parameter sample dimension; a vital sign feature extraction unit 222, which is used to input the vital sign time series association matrix into a vital sign time series association pattern feature extractor based on a void convolutional neural network model to obtain the vital sign time series association feature graph.

[0048] However, considering that although the hole convolution neural network model can make up for the problem of small receptive field of traditional convolution kernel feature extraction to a certain extent, it is still limited by the shape of the convolution kernel itself and cannot capture longer-distance dependencies, thus lacking global contextual semantic association information. Therefore, in the technical solution of the present application, the feature pixel granularity of the vital sign temporal association feature map is first dispersed along the channel dimension to disperse the feature map into a set representation of vectors, thereby obtaining a set of vital sign temporal association pixel-level feature vectors; then, the set of vital sign temporal association pixel-level feature vectors is input into a contextual semantic enhancement module based on significance-globality to obtain a set of enhanced vital sign temporal association pixel-level feature vectors. Among them, the contextual semantic enhancement module based on saliency-globality calculates the maximum value of each vital sign temporal correlation pixel-level feature vector as a saliency feature, and calculates the average value of each vital sign temporal correlation pixel-level feature vector as a global feature. In this way, the saliency feature and the global feature are converted into dual semantic optimization weights as a vital sign temporal correlation feature pattern through convolution coding, nonlinear activation and linear transformation to semantically enhance the vital sign temporal correlation feature pattern, that is, the set of vital sign temporal correlation pixel-level feature vectors, so that the model can capture the long-dependent temporal correlation of vital signs across distance limits. More specifically, by strengthening the saliency semantic information, the model can pay more attention to the information that is most critical for understanding the changes in vital signs, such as a sudden increase in heart rate or a sharp change in blood pressure; and by integrating global semantic information, the model can learn the common patterns and overall trends in the vital sign data set. This is very important for understanding both the long-term trend and short-term fluctuation of vital sign changes.

[0049] Accordingly, if Figure 5 As shown, the semantic enhancement module 23 includes: a feature dispersion unit 231, which is used to disperse the feature pixel granularity of the vital sign time series association feature map along the channel dimension to obtain a set of vital sign time series association pixel-level feature vectors; a significance-global dual semantic enhancement unit 232, which is used to input the set of vital sign time series association pixel-level feature vectors into the contextual semantic enhancement module based on significance-globality to obtain the set of enhanced vital sign time series association pixel-level feature vectors.

[0050] The saliency-global dual semantic enhancement unit 232 includes: a saliency information extraction subunit, which is used to extract the vital sign time series associated prominent feature vector of the set of the vital sign time series associated pixel-level feature vectors; a global information extraction subunit, which is used to extract the vital sign time series associated global feature vector of the set of the vital sign time series associated pixel-level feature vectors; a neighborhood encoding and activation subunit, which is used to perform neighborhood encoding and activation on the vital sign time series associated prominent feature vector and the vital sign time series associated global feature vector to obtain the vital sign time series associated prominent feature context associated activation feature vector and the vital sign time series associated global feature context associated activation feature vector; a dual semantic enhancement weight construction subunit, which is used to fuse the vital sign time series associated prominent feature context associated activation feature vector and the vital sign time series associated global feature context associated activation feature vector. After the vital sign timing-associated global feature context-associated activation feature vector is obtained to obtain the vital sign timing-associated highlight-global feature context-associated activation feature vector, the vital sign timing-associated highlight-global feature context-associated activation feature vector is nonlinearly activated to obtain the vital sign timing-associated highlight-global feature context-associated weight feature vector; a semantic reinforcement subunit is used to use the vital sign timing-associated highlight-global feature context-associated weight feature vector as the weight vector, perform positional dot multiplication on each vital sign timing-associated pixel-level feature vector in the set of the vital sign timing-associated pixel-level feature vectors, and perform element-by-element addition of the sequence obtained by positional dot multiplication and the set of the vital sign timing-associated pixel-level feature vectors to obtain the set of the enhanced vital sign timing-associated pixel-level feature vectors.

[0051] Specifically, the saliency information extraction subunit is used to calculate the maximum value of each vital sign time series associated pixel level feature vector in the set of vital sign time series associated pixel level feature vectors to obtain the vital sign time series associated salient feature vector composed of each of the maximum values.

[0052] Specifically, the global information extraction subunit is used to calculate the average value of each vital sign time series associated pixel level feature vector in the set of vital sign time series associated pixel level feature vectors to obtain the vital sign time series associated global feature vector composed of each of the average values.

[0053] Specifically, the neighborhood coding and activation subunit is used to: perform one-dimensional convolution coding, nonlinear activation and linear transformation on the vital sign time series associated salient feature vector to obtain the vital sign time series associated salient feature context associated activation feature vector; perform one-dimensional convolution coding, nonlinear activation and linear transformation on the vital sign time series associated global feature vector to obtain the vital sign time series associated global feature context associated activation feature vector.

[0054] Specifically, the dual semantic reinforcement weight construction subunit is used to: after respectively passing the vital sign temporal association prominence-global feature context association activation feature vector through the tanh activation function and the sigmoid activation function, the two obtained vectors are point multiplied to obtain the vital sign temporal association prominence-global feature context association weight feature vector.

[0055] In a specific example, the saliency-global dual semantic enhancement unit 232 is used to: input the set of vital sign temporal associated pixel-level feature vectors into the saliency-global contextual semantic enhancement module to process it with the following enhancement formula to obtain the set of enhanced vital sign temporal associated pixel-level feature vectors; wherein the enhancement formula is: ;in, is the set of pixel-level feature vectors associated with the vital signs time series, is the global eigenvector of vital sign temporal association, is the prominent feature vector of vital sign temporal association, It means taking the average value, Indicates taking the maximum value, represents a one-dimensional convolution operation, express Activation function, and are the first weight matrix and the second weight matrix for linear transformation, and They are respectively the vital signs temporal association global feature context association activation feature vector and the vital signs temporal association salient feature context association activation feature vector, express function, express Activation function, represents dot product, It is a set of pixel-level feature vectors associated with the enhanced vital signs time series.

[0056] Furthermore, the set of pixel-level feature vectors associated with the enhanced vital signs in time series is input into a decoder-based frequency recommender to obtain a decoding result, and the decoding result is used to represent the recommended frequency value of the functional electromagnetic wave; then, the output frequency of the functional electromagnetic wave is adjusted to the recommended frequency value. In this way, adaptive adjustment of the output frequency of the functional electromagnetic wave is achieved.

[0057] Correspondingly, the functional electromagnetic wave frequency recommendation module 24 is used to: input the set of enhanced vital sign time-series associated pixel-level feature vectors into a decoder-based frequency recommender to obtain a decoding result, and the decoding result is used to represent the recommended frequency value of the functional electromagnetic wave.

[0058] Here, each vital sign time-series associated pixel-level feature vector in the set of vital sign time-series associated pixel-level feature vectors respectively expresses the channel distribution characteristics of the convolutional neural network model of the local correlation characteristics of the time-sample cross-dimensionality of the vital sign data. Taking into account the channel significance-global context reinforcement weight difference of the cross-dimensional correlation characteristics between each channel, the set of enhanced vital sign time-series associated pixel-level feature vectors as a whole will also have a diversified set expression distribution composed of discretized local feature distributions. Therefore, it is expected to improve the overall expression effect of the set of enhanced vital sign time-series associated pixel-level feature vectors based on the diversified set distribution, thereby improving the accuracy of the decoding results obtained by the decoder-based frequency recommender.

[0059] Specifically, the functional electromagnetic wave frequency recommendation module 24 includes: an optimization unit, used to optimize the set of enhanced vital sign timing-associated pixel-level feature vectors to obtain an optimized enhanced vital sign timing-associated pixel-level cascade feature vector; a decoding unit, used to input the optimized enhanced vital sign timing-associated pixel-level cascade feature vector into the decoder-based frequency recommender to obtain the decoding result.

[0060] Based on this, the present application optimizes the set of enhanced vital sign time-series associated pixel-level feature vectors to obtain an optimized enhanced vital sign time-series associated pixel-level cascade feature vector, including: cascading the set of enhanced vital sign time-series associated pixel-level feature vectors into an enhanced vital sign time-series associated pixel-level cascade feature vector; calculating the sum of the absolute values ​​of each eigenvalue of the enhanced vital sign time-series associated pixel-level cascade feature vector The square root of the sum of squares ,Right now: ;in, The first pixel-level cascade feature vector representing the temporal association of the enhanced vital signs The eigenvalues ​​at the positions, represents the length of the pixel-level cascade feature vector associated with the enhanced vital sign time series, represents the sum of the absolute values ​​of the eigenvalues ​​of the pixel-level cascade eigenvectors associated with the enhanced vital sign temporal sequence, The square root of the sum of squares of the eigenvalues ​​of the pixel-level cascade feature vector associated with the enhanced vital sign time series is represented.

[0061] Subtract each eigenvalue of the pixel-level cascade feature vector associated with the enhanced vital sign time series from Then, take the absolute value and multiply it by the length of the pixel-level cascade feature vector of the enhanced vital sign time series association and The reciprocal of the product is taken to obtain the first enhanced vital sign time series associated pixel-level cascade intermediate feature vector, and each eigenvalue of the enhanced vital sign time series associated pixel-level cascade feature vector is subtracted from Then, take the absolute value and multiply it by the length The square root of The reciprocal of the product is taken to obtain the second enhanced vital sign time series associated pixel-level cascade intermediate feature vector, that is: ;in, The first pixel-level cascade feature vector representing the temporal association of the enhanced vital signs The eigenvalues ​​at the positions, represents the length of the pixel-level cascade feature vector associated with the enhanced vital sign time series, represents the sum of the absolute values ​​of the eigenvalues ​​of the pixel-level cascade eigenvectors associated with the enhanced vital sign temporal sequence, represents the square root of the sum of squares of the eigenvalues ​​of the pixel-level cascade eigenvector associated with the enhanced vital sign temporal sequence, The first intermediate feature vector of the pixel-level cascade of the temporal association of the first enhanced vital sign is represented by The eigenvalues ​​at the positions, The first intermediate feature vector of the pixel-level cascade of the second enhanced vital sign temporal association The feature value at each position.

[0062] Finally, the first enhanced vital sign temporal association pixel-level cascade intermediate feature vector is subtracted from the dot product of the second enhanced vital sign temporal association pixel-level cascade intermediate feature vector and the weighted hyperparameter to obtain an optimized enhanced vital sign temporal association pixel-level cascade feature vector.

[0063] Therefore, the difference of the different and modulation representations of the eigenvalues ​​of the enhanced vital sign temporal associated pixel-level cascade feature vectors relative to the overall feature set of the enhanced vital sign temporal associated pixel-level cascade feature vectors is used as the semantic change intensity information, and a phase-like conversion corresponding to the position-based intensity modulation is performed through different and modulation representations, so that the aggregation enhancement of the semantic change phase perception can improve the axial aggregation receptive field along the feature aggregation direction by performing a spatial translation operation based on alternating stacking under the scale balance of the feature set of the enhanced vital sign temporal associated pixel-level cascade feature vectors, thereby improving the perception effect of the aggregated semantics of the enhanced vital sign temporal associated pixel-level cascade feature vectors on the detailed semantic changes, so as to improve the overall expression effect of the set of the enhanced vital sign temporal associated pixel-level feature vectors, and improve the accuracy of the decoding results obtained by the decoder-based frequency recommender.

[0064] Based on the above embodiments, see Figure 6 FIG. 1 is a flowchart of a method for processing a passive electromagnetic wave bioresonance chip for health in an embodiment of the present application. For example, the method for processing a passive electromagnetic wave bioresonance chip for health can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 6 As shown, according to the processing method of the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application, the method includes the following steps: S510, obtaining a time series of vital sign data of a monitored object collected by a wearable device, wherein the vital sign data includes a heart rate value, a body temperature value, a blood pressure value, a respiratory rate value and a blood oxygen saturation; S520, performing vital sign time series correlation feature extraction on the time series of the vital sign data to obtain a vital sign time series correlation feature graph; S530, performing context semantic enhancement on the vital sign time series correlation feature graph to obtain a set of enhanced vital sign time series correlation pixel-level feature vectors; S540, determining a recommended frequency value of a functional electromagnetic wave based on the set of enhanced vital sign time series correlation pixel-level feature vectors; S550, adjusting the output frequency of the functional electromagnetic wave to the recommended frequency value.

[0065] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned processing method of the passive electromagnetic wave bioresonance chip for the health field have been referred to above. Figures 2 to 5 The passive electromagnetic wave bioresonance chip for the health field has been described in detail, and therefore, its repeated description will be omitted.

[0066] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the processing method of the passive electromagnetic wave bioresonance chip for the health field in the above embodiments when executing the program.

[0067] For example, in the case of electronic equipment Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0068] An embodiment of the present application also provides a computer-readable storage medium. Figure 7 1 shows a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present application. Figure 7 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by the processor, the processing method of the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0069] The embodiment of the present application also provides a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the processing method of the passive electromagnetic wave bioresonance chip for the health field according to the embodiment of the present application.

[0070] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0071] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0072] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0073] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0074] The above is an explanation of the present application and should not be considered as a limitation thereof. Although several exemplary embodiments of the present application have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application. Therefore, all of these modifications are intended to be included within the scope of the present application as defined by the claims. It should be understood that the above is an explanation of the present application and should not be considered to be limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present application is defined by the claims and their equivalents.

Claims

1. A passive electromagnetic wave bioresonance chip for use in the health field, characterized in that: include: An energy receiving device, used for receiving space electromagnetic field energy; A processor, for generating functional electromagnetic waves; Radio Frequency An electromagnetic wave transmitting device is used to send the functional electromagnetic wave to the surrounding space; wherein the processor includes: a vital sign data acquisition module, used to obtain the time series of vital sign data of the monitored object collected by the wearable device, wherein the vital sign data includes heart rate value, body temperature value, blood pressure value, respiratory rate value and blood oxygen saturation; a vital sign time series association feature extraction module, used to extract vital sign time series association features from the time series of the vital sign data to obtain a vital sign time series association feature map; a semantic enhancement module, used to perform contextual semantic enhancement on the vital sign time series association feature map to obtain a set of enhanced vital sign time series association pixel-level feature vectors; a functional electromagnetic wave frequency recommendation module, used to determine the recommended frequency value of the functional electromagnetic wave based on the set of enhanced vital sign time series association pixel-level feature vectors; an output frequency adjustment module, used to adjust the output frequency of the functional electromagnetic wave to the recommended frequency value.

2. The passive electromagnetic wave bioresonance chip for health field according to claim 1, characterized in that: The vital sign time series association feature extraction module includes: a data structuring unit, which is used to arrange the time series of the vital sign data into a vital sign time series association matrix according to the time dimension and the parameter sample dimension; a vital sign feature extraction unit, which is used to input the vital sign time series association matrix into a vital sign time series association pattern feature extractor based on a void convolutional neural network model to obtain the vital sign time series association feature graph.

3. The passive electromagnetic wave bioresonance chip for health field according to claim 2, characterized in that: The semantic enhancement module includes: a feature dispersion unit, which is used to disperse the feature pixel granularity of the vital sign time series association feature map along the channel dimension to obtain a set of vital sign time series association pixel-level feature vectors; a saliency-global dual semantic enhancement unit, which is used to input the set of vital sign time series association pixel-level feature vectors into a saliency-global contextual semantic enhancement module to obtain the set of enhanced vital sign time series association pixel-level feature vectors.

4. The passive electromagnetic wave bioresonance chip for health field according to claim 3, characterized in that: The saliency-global dual semantic reinforcement unit includes: a saliency information extraction subunit, used to extract a vital sign time series associated prominent feature vector of the set of the vital sign time series associated pixel-level feature vectors; a global information extraction subunit, used to extract a vital sign time series associated global feature vector of the set of the vital sign time series associated pixel-level feature vectors; a neighborhood encoding and activation subunit, used to perform neighborhood encoding and activation on the vital sign time series associated prominent feature vector and the vital sign time series associated global feature vector to obtain a vital sign time series associated prominent feature context associated activation feature vector and a vital sign time series associated global feature context associated activation feature vector; a dual semantic reinforcement weight construction subunit, used to fuse the vital sign time series associated prominent feature context associated activation feature vector and the vital sign time series associated global feature context associated activation feature vector. After the vital sign temporal association-global feature context association activation feature vector is obtained, the vital sign temporal association-prominent-global feature context association activation feature vector is nonlinearly activated to obtain the vital sign temporal association-prominent-global feature context association weight feature vector; a semantic reinforcement subunit is used to use the vital sign temporal association-prominent-global feature context association weight feature vector as the weight vector, perform positional dot multiplication on each vital sign temporal association pixel-level feature vector in the set of the vital sign temporal association pixel-level feature vectors, and perform element-by-element addition of the sequence obtained by the positional dot multiplication and the set of the vital sign temporal association pixel-level feature vectors to obtain the set of the reinforced vital sign temporal association pixel-level feature vectors.

5. The passive electromagnetic wave bioresonance chip for health field according to claim 4, characterized in that: The saliency information extraction subunit is used to calculate the maximum value of each vital sign time series associated pixel level feature vector in the set of vital sign time series associated pixel level feature vectors to obtain the vital sign time series associated salient feature vector composed of each of the maximum values.

6. The passive electromagnetic wave bioresonance chip for health field according to claim 5, characterized in that: The global information extraction subunit is used to calculate the average value of each vital sign time series associated pixel level feature vector in the set of vital sign time series associated pixel level feature vectors to obtain the vital sign time series associated global feature vector composed of each of the average values.

7. The passive electromagnetic wave bioresonance chip for health field according to claim 6, characterized in that: The neighborhood coding and activation subunit is used to: perform one-dimensional convolution coding, nonlinear activation and linear transformation on the vital sign time series associated salient feature vector to obtain the vital sign time series associated salient feature context associated activation feature vector; One-dimensional convolution coding, nonlinear activation and linear transformation are performed on the vital sign time series associated global feature vector to obtain the vital sign time series associated global feature context associated activation feature vector.

8. The passive electromagnetic wave bioresonance chip for health field according to claim 7, characterized in that: The dual semantic reinforcement weight construction subunit is used to: after respectively passing the vital sign time series association highlight-global feature context association activation feature vector through the tanh activation function and the sigmoid activation function, the two obtained vectors are point multiplied to obtain the vital sign time series association highlight-global feature context association weight feature vector.

9. The passive electromagnetic wave bioresonance chip for health field according to claim 8, characterized in that: The functional electromagnetic wave frequency recommendation module is used to: input the set of enhanced vital sign time-series associated pixel-level feature vectors into a decoder-based frequency recommender to obtain a decoding result, and the decoding result is used to represent the recommended frequency value of the functional electromagnetic wave.

Images