Multi-physical field data fusion system and method of biological probe, product and medium

Abstract

The invention provides a multi-physical field data fusion system and method of a biological probe, a product and a medium, belongs to the field of biosensing and tissue characteristic analysis, and solves the problem of how to accurately and effectively adapt to different biological tissues to fuse multi-physical field data acquired by the biological probe and extract key information. And thus, the biological tissue state can be quickly and accurately determined. According to the method, multi-physical field data fusion, parameter optimization and self-adaptive model construction are combined, so that the overall performance of a biological probe measurement system can be remarkably improved, internal association among physical field data is fully mined for state detection of biological tissues, information loss and deviation caused by single physical field data are avoided, and the detection accuracy is improved. And multi-dimensional support is provided for subsequent biological characteristic analysis.

Description

Technical Field

[0001] The present invention relates to the field of biosensing and tissue feature analysis in medical engineering, and in particular to a multi-physical field data fusion system and method for a biological probe, a computer program product, and a computer-readable storage medium. Background Art

[0002] With the development of biomedical technology, bioprobes, as an important detection tool, have been widely used in biological tissue status monitoring, disease diagnosis, and medical research. The perception and data collection of characteristic tissues by bioprobes provide doctors and researchers with key information about the status of biological tissues.

[0003] However, there are complex interactive relationships between different biological tissues and the detection results of biological probes on different biological tissues. How to accurately and effectively adapt to multi-source data of different biological tissues, that is, to fuse and extract key information from multi-physical field data collected by biological probes, and then quickly and accurately determine the state of biological tissues, has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] One purpose of the present invention is to solve the technical problem of how to accurately and effectively adapt to different biological tissues to fuse the multi-physical field data (including impedance data, pressure data, temperature data, angle data) collected by biological probes and extract key information, so as to quickly and accurately determine the state of biological tissues.

[0005] According to one aspect of an embodiment of the present invention, a multi-physical field data fusion system for a biological probe is disclosed, the system comprising: A biological probe, used for collecting data of the currently measured biological tissue to obtain multi-physical field data of the biological tissue, wherein the multi-physical field data includes environmental parameters and intrinsic characteristic parameters of the biological tissue; A memory, a processor, and a computer program stored in the memory, wherein the computer program is executed by the processor to implement the following steps: Determine the key parameters of the currently measured biological tissue by the multi-physical field data through the biological probe measurement model, and find a set of optimal parameter values ​​for the key parameters, as well as a weighted coefficient combination of the optimal parameter value mapping; Adapting to the contact between the biological probe and the biological tissue, the characteristic parameters of the biological tissue are obtained by combining and calibrating the optimal parameter values ​​through the mapped weighted coefficients; A biological tissue feature analysis model of the feature parameter mapping is adaptively constructed for the measured biological tissue, and a state evaluation result of the biological tissue is output.

[0006] According to one aspect of an embodiment of the present application, the biological probe senses different types of physical signals to sense and collect multi-physical field data corresponding to multiple physical fields of biological tissue in real time.

[0007] According to one aspect of an embodiment of the present application, the method of determining the key parameters of the currently measured biological tissue by the multi-physical field data through the biological probe measurement model, and finding a set of optimal parameter values ​​for the key parameters, as well as a weighted coefficient combination of the optimal parameter value mapping, includes: For the biological tissue currently contacted and measured by the biological probe, based on the discretization processing of the multi-physical field data by the biological probe measurement model and the random sampling on the discretization processing, sensitivity calculation is performed to determine the key parameters in the multi-physical field data; Parameter identification is performed on key parameters in the multi-physical field data to obtain a set of optimal parameter values ​​corresponding to the key parameters, and a weighted coefficient combination of the optimal parameter value mapping.

[0008] According to one aspect of an embodiment of the present application, for the biological tissue currently contacted and measured by the biological probe, based on the discretization processing of the multi-physical field data by the biological probe measurement model and the random sampling on the discretization processing, sensitivity calculation is performed to determine the key parameters in the multi-physical field data, including: Initializing the configuration of the parameter range of each parameter mapping in the multi-physical field data and the number of sampling points of the parameter in the parameter range for the biological tissue; Adapting the number of sampling points to generate a series of discrete sampling values ​​within the parameter range, and using the sampling values ​​as possible values ​​of the corresponding parameters to form a vector representation of the parameters; In the parameter-oriented vector representation, the sensitivity of each parameter is evaluated by successively changing the parameter, and the parameter with the largest sensitivity is taken as the key parameter in the multi-physical field data.

[0009] According to one aspect of an embodiment of the present application, the parameter range of each parameter mapping is different for different biological tissues.

[0010] According to one aspect of an embodiment of the present application, the parameter-oriented vector representation evaluates the sensitivity of each parameter by successively changing the parameter, and takes the parameter with the largest sensitivity as the key parameter in the multi-physical field data, including: Calculate the local sensitivity and global sensitivity of the sampled trajectory to obtain the local sensitivity and global sensitivity of each parameter; According to the local sensitivity and the global sensitivity, the parameters that have a significant impact on the state change of the biological tissue under its own physiological activities are identified as the key parameters of the multi-physical field data in the biological tissue.

[0011] According to one aspect of an embodiment of the present application, the step of performing parameter identification on key parameters in the multi-physical field data to obtain a set of optimal parameter values ​​corresponding to the key parameters, and a weighted coefficient combination of the optimal parameter value mapping, includes: The genetic algorithm is used to iteratively optimize the biological probe measurement model using multi-physical field data corresponding to each parameter to obtain a set of optimal parameter values ​​corresponding to key parameters and a weighted coefficient combination of the optimal parameter value mapping.

[0012] According to one aspect of an embodiment of the present invention, a multi-physical field data fusion method for a biological probe is disclosed, characterized in that the method executes the steps implemented in the system as described above.

[0013] According to one aspect of an embodiment of the present invention, a computer program product is disclosed, including a computer program, wherein the computer program implements the above-mentioned system when executed by a processor.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is disclosed, on which a computer program is stored. When the program is executed by a processor, the system as described above is implemented.

[0015] The embodiments of the present invention can significantly improve the overall performance of the biological probe measurement system by combining multi-physics field data fusion, parameter optimization and adaptive model construction.

[0016] Specifically, the system implemented in the embodiment of the present invention comprehensively considers the impact of different physical fields on biological tissues and implements the fusion of multiple physical field data (including impedance data, pressure data, temperature data, and angle data) obtained by the biological probe, so as to obtain more comprehensive and accurate measurement results adapted to the currently measured biological tissue. In addition, the search for optimal values ​​of key parameters and the optimization of weighted coefficient combinations effectively improve the ability of the biological probe measurement model to recognize the characteristics of complex biological tissues, greatly reduce errors and improve measurement stability.

[0017] The biological probe measurement model is adapted to the optimization achieved by biological tissues and can be dynamically adjusted according to different environmental conditions and biological tissue characteristics, so that it can maintain excellent performance for various biological tissues and various changes in biological tissues, and ultimately adaptively and accurately respond to changes in physical tissues and the environment, thereby enhancing the system's adaptability and robustness.

[0018] As a result, efficient fusion of multiple physical field data (including impedance data, pressure data, temperature data, and angle data) can be achieved, fully exploring the intrinsic correlation between various physical field data for the state detection of biological tissues, avoiding information loss and deviation caused by single physical field data, and providing multi-dimensional support for subsequent biometric analysis.

[0019] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0022] Figure 1 It is a schematic diagram of an implementation of a multi-physics field data fusion system of a biological probe according to an exemplary embodiment.

[0023] Figure 2 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of determining the key parameters of the currently measured biological tissue from multi-physical field data through a biological probe measurement model, finding a set of optimal parameter values ​​for the key parameters, and combining weighted coefficients for mapping the optimal parameter values.

[0024] Figure 3 is based on Figure 2 The corresponding embodiment shows a flow chart of a method for describing the discretization processing of multi-physical field data and random sampling on the discretization processing based on the biological probe measurement model, and implementing sensitivity calculation to determine key parameters in the multi-physical field data.

[0025] Figure 4 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of generating a series of discrete sampling values ​​within a parameter range for adapting the number of sampling points, and forming a vector representation of the parameters using the sampling values ​​as possible values ​​of the corresponding parameters.

[0026] Figure 5 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of evaluating the sensitivity of each parameter by successively changing the parameter for the vector representation of the parameter, and taking the parameter with the largest sensitivity as the key parameter in the multi-physical field data.

[0027] Figure 6 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of evaluating the sensitivity of each parameter by successively changing the parameter for the vector representation of the parameter, and taking the parameter with the largest sensitivity as the key parameter in the multi-physical field data.

[0028] Figure 7A mapping diagram of the weighted fusion value (biological tissue health status assessment result) corresponding to each skin tissue sample and the health status is shown. DETAILED DESCRIPTION

[0029] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present invention will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0030] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present invention.

[0031] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0032] See also Figure 1 , Figure 1 It is a schematic diagram of an implementation of a multi-physics field data fusion system of a biological probe according to an exemplary embodiment.

[0033] The multi-physics field data fusion system of the biological probe provided in the embodiment of the present invention includes a biological probe and a control terminal, wherein the control terminal includes a memory, a processor, and a computer program stored in the memory. It should be understood that the control terminal interacts with the biological probe to control the biological probe, and processes the data collected by the biological probe to output the corresponding biological tissue state evaluation result.

[0034] The control end can be a variety of terminal devices, such as Figure 1 Any terminal device among the control terminals 1, 2 and 3 shown in the figure that can be connected to the biological probe and run the computer program can be used as the control terminal of the system implemented by the present invention.

[0035] The biological probe is used to collect data of the currently measured biological tissue and obtain multi-physical field data of the biological tissue, wherein the multi-physical field data includes environmental parameters of the biological tissue and its intrinsic characteristic parameters; The computer program is executed by the processor to implement the following steps: Step S410, determining the key parameters of the currently measured biological tissue by the multi-physical field data through the biological probe measurement model, and finding a set of optimal parameter values ​​for the key parameters, and a weighted coefficient combination of the optimal parameter value mapping; Step S420, adapting to the contact between the biological probe and the biological tissue, obtaining characteristic parameters of the biological tissue by combining and calibrating the optimal parameter values ​​through the mapped weighted coefficients; Step S430, adaptively constructing a biological tissue feature analysis model for feature parameter mapping for the measured biological tissue, and outputting a state assessment result of the biological tissue.

[0036] The following is a detailed description of the system and the steps implemented by the system.

[0037] The biological probe can be configured with sensors, sensor arrays, etc., and the biological probe can be configured to adapt to the full dimensions of parameter detection required, so that the biological probe can sense and collect biological tissues in multiple physical fields.

[0038] For characteristic tissues that need to be measured, such as skin, liver, spine, etc., the biological probe can sense and collect multi-physical field data. The biological probe is used to collect relevant parameters in the environment and / or biological tissues in real time, that is, environmental parameters and their intrinsic characteristic parameters.

[0039] That is to say, the multi-physical field data obtained by the biological probe through data collection on the currently measured biological tissue includes parameters corresponding to physical quantities such as impedance, pressure, temperature and angle, and the parameter values ​​corresponding to various parameters constitute a physical field data.

[0040] The biological probe senses different types of physical signals in biological tissues and performs real-time perception of multi-physical signals in biological tissues, so as to sense and collect multi-physical field data corresponding to multiple physical fields in real time.

[0041] For any biological tissue that needs to be measured, the biological probe implements data collection for multiple physical fields, that is, through built-in sensors, sensor arrays, etc., it implements parameter collection of physical quantities such as impedance, pressure, temperature and angle, and obtains physical field data corresponding to various parameters. The physical field data corresponding to all types of parameters form the multi-physical field data output by the biological probe.

[0042] Biological probes collect different types of multi-physics field data through the interaction with biological tissues through physical principles (such as impedance, temperature, pressure, heat conduction, electromagnetic wave reflection, conductivity, etc.). Multi-physics field data reflects the physical, chemical and physiological characteristics of biological tissues.

[0043] The biological probe that implements data acquisition in the system transmits the collected multi-physical field data to the computer program run by the processor, and the computer program then implements multi-physical field data fusion adapted to the currently measured biological tissue. Ultimately, on this basis, it is able to efficiently and accurately analyze the characteristics of the biological tissue and output the status evaluation results of the currently measured biological tissue.

[0044] With the help of the embodiments of the present invention, it is possible to implement status detection on different biological tissues without replacing or adjusting biological probes, thereby achieving adaptive and high-precision data fusion and status evaluation for different biological tissues.

[0045] The multi-physical field data obtained by the biological probe are streamed to the computer program through the interaction between the biological probe and the computer program run by the system. The biological probe measurement model is optimized through the execution of steps S410 to S430 in the computer program, so as to adaptively and accurately fuse the multi-physical field data and output the state evaluation results for the measured biological tissue.

[0046] In step S410, the biological probe measurement model is used to identify key parameters of the multi-physical field data belonging to the currently measured biological tissue and determine the corresponding parameter values, and to optimize the weighted coefficient combination for each type of identified key parameter.

[0047] Specifically, the biological probe collects multi-physical field data of biological tissue by contacting the biological tissue. The collected multi-physical field data include but are not limited to environmental parameters such as temperature and pressure, and parameters describing the intrinsic characteristics of biological tissue such as impedance, mechanical stress, and electrical layer ratio.

[0048] The collected multi-physics field data are mostly high-dimensional and noisy, and there may be complex interactions between the physical fields. Therefore, it is necessary to use the biological probe measurement model to accurately obtain the optimal parameter values ​​of key parameters.

[0049] Key parameters refer to the parameters that have the greatest impact on the final results during the state assessment of biological tissues. The key parameters of different biological tissues are often different.

[0050] The bioprobe measurement model is a mathematical or computational model used to describe and analyze the interaction between the bioprobe and biological tissue. The bioprobe measurement model obtains the optimal parameter values ​​and weighted coefficient combinations of the adapted key parameters based on the multi-physical field data (such as temperature, conductivity, pressure, optical properties, etc.) sensed by the bioprobe.

[0051] The bioprobe measurement model extracts useful information from multi-physics field data to identify key parameters that have a significant impact on the state of the currently measured biological tissue. The bioprobe measurement model has adaptive capabilities for different biological tissues and can dynamically adjust according to different biological tissues and their environmental conditions to ensure high-precision evaluation of biological tissues.

[0052] Through the biological probe measurement model and even the discrete processing of each parameter and random sampling based on the discrete processing, the vector representation corresponding to each parameter is finally obtained. The vector representation of each parameter changes the parameter successively in each sampling, and then the sensitivity of each parameter is calculated, and the key parameters are identified based on the sensitivity.

[0053] For the identified key parameters, an optimization algorithm, such as a genetic algorithm, is used in the biological probe measurement model to iterate to find a set of optimal parameter values ​​corresponding to the key parameters and a weighted coefficient combination of the optimal parameter value mapping.

[0054] The optimal set of parameter values ​​found best matches the actual state of the biological tissue, and the corresponding weighted coefficient combination is obtained by trying different weighted coefficient combinations in the iterative optimization process, which can minimize the error in the biological tissue state assessment.

[0055] By combining the obtained weighted coefficients, the multi-physics field data is weightedly fused, and the characteristics of each physical field data are combined to improve the accuracy of the fusion results. For example, some parameters (such as impedance) may play a dominant role in a specific biological tissue state, while other parameters (such as humidity and angle) participate in the fusion as auxiliary information.

[0056] See also Figure 2 , Figure 2 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of determining the key parameters of the currently measured biological tissue from multi-physical field data through a biological probe measurement model, finding a set of optimal parameter values ​​for the key parameters, and combining weighted coefficients for mapping the optimal parameter values.

[0057] The embodiment of the present invention provides a step S410 of determining the key parameters of the currently measured biological tissue by using the biological probe measurement model for multi-physical field data, and finding a set of optimal parameter values ​​for the key parameters, as well as a weighted coefficient combination step for mapping the optimal parameter values, including: Step S411, for the biological tissue currently contacted and measured by the biological probe, based on the discretization processing of the multi-physical field data and the random sampling on the discretization processing by the biological probe measurement model, sensitivity calculation is performed to determine the key parameters in the multi-physical field data; Step S412, performing parameter identification on key parameters in the multi-physical field data to obtain a set of optimal parameter values ​​corresponding to the key parameters, and a weighted coefficient combination of the optimal parameter value mapping.

[0058] These two steps are described in detail below.

[0059] Based on the biological probe measurement model, the multi-physics field data are discretized and randomly sampled, and sensitivity calculations are implemented to determine the key parameters in the multi-physics field data to ensure the accuracy, stability and efficiency of biological tissue measurements.

[0060] As mentioned above, biological probes can sense and collect multi-physical field data of biological tissues by contacting with them. These data cover the environmental parameters (such as temperature, humidity, pressure, etc.) and intrinsic characteristic parameters (such as conductivity, optical properties, mechanical properties, etc.) of biological tissues. These multi-physical field data are often continuous, complex, and usually noisy.

[0061] Therefore, in practical applications, the collected continuous data must first be discretized in order to facilitate simple data processing and analysis.

[0062] Exemplarily, the discretization process is to convert the continuous physical quantity into a finite number of discrete values ​​or intervals to obtain the discrete representation of various parameters in the currently measured biological tissue, that is, the sampling value at each sampling point.

[0063] Random sampling is performed on the basis of discretization processing. For example, the random sampling performed can be a Monte Carlo simulation. Random sampling is performed within the parameter range defined by each parameter through the Monte Carlo simulation to cover various possibilities, so that the sampling is more accurate and balanced.

[0064] Specifically, the execution process of the Monte Carlo simulation includes: randomly sampling discrete sampling values ​​of various parameters, performing a simulation after obtaining a set of parameter sampling values, that is, obtaining the sensitivity calculation of the set of sampling values, and improving and optimizing the biological probe measurement model based on the obtained calculation results, and so on, iterating the Monte Carlo simulation to obtain a vector representation that can characterize significant effects and characterize the state of biological tissues, so as to implement sensitivity.

[0065] See also Figure 3 , Figure 3 is based on Figure 2The corresponding embodiment shows a flow chart of a method for describing the discretization processing of multi-physical field data and random sampling on the discretization processing based on the biological probe measurement model, and implementing sensitivity calculation to determine key parameters in the multi-physical field data.

[0066] The embodiment of the present invention shows a step S411 of performing sensitivity calculation to determine key parameters in the multi-physical field data based on the discretization processing of the multi-physical field data and the random sampling on the discretization processing by the biological probe measurement model for the biological tissue currently contacted and measured by the biological probe, including: Step S4111, initializing the configuration of the parameter range of each parameter mapping in the multi-physics field data for the biological tissue and the number of sampling points of the parameters within the parameter range; Step S4112, adapting the number of sampling points to generate a series of discrete sampling values ​​within the parameter range, and using the sampling values ​​as possible values ​​of the corresponding parameters to form a vector representation of the parameters; Step S4113, for the vector representation of parameters, the sensitivity of each parameter is evaluated by successively changing the parameters, and the parameter with the largest sensitivity is taken as the key parameter in the multi-physical field data.

[0067] These steps are described in detail below.

[0068] Parameters have different parameter ranges for different biological tissues. Therefore, for the biological tissue currently being measured, it is necessary to initialize and configure the parameter ranges of various parameter mappings in the multi-physics field data to control the reliability of the implemented discretization processing and random sampling.

[0069] In addition, a reasonable number of sampling points will be selected based on the parameter range and correlation of various parameters to ensure that the parameter range can be covered in subsequent model operations, thereby obtaining the most comprehensive results.

[0070] For example, the larger the parameter range, the more sampling points are required, and the stronger the correlation between various parameters, the number of sampling points can be appropriately reduced. Therefore, the number of sampling points configured can be dynamically configured for different biological tissues and different types of parameters.

[0071] The number of sampling points is dynamically configured to ensure the accuracy of the biological probe measurement model while avoiding excessive increase in computational complexity, that is, the accuracy and computational efficiency are balanced through the dynamically configured number of sampling points.

[0072] For example, assume that the parameter range of each parameter is [ L i , U i], on the one hand, when the parameter range is small and the change trend is relatively linear, the parameter range can be divided into equal intervals. p points as sampling points. The number of sampling points is p On the other hand, sampling points can be added to the sensitive intervals within the parameter range of certain parameters. Therefore, the number of sampling points can be dynamically configured to adapt to various situations.

[0073] After implementing dynamic configuration of parameter range and number of sampling points for biological tissues and various parameters, the continuous data of various parameters in the mapped parameter range are discretized into finite sampling points to obtain the corresponding sampling values ​​as vector representation of the parameters.

[0074] The sampled values, as possible values ​​of the parameters, represent the possible discrete states of the parameters within their parameter range. The obtained sampled values ​​are combined into a parameter vector, ie, the vector representation of the parameters.

[0075] For example, k Class parameters, each class parameter i Within its parameter range, p i discrete sampling points, the vector of the obtained parameters is expressed as: X i =[ X i,0 , X i,1 , X i,2 ,……, X i, p i-1 ,]; X i is a parameter i The vector representation of X i,j Representation parameters i The sample value at the jth sampling point.

[0076] By analogy, vector representations are obtained for all types of parameters, and then based on this, the parameters are sampled one after another. In the vector representations of all parameters finally obtained, only the sampling value corresponding to one parameter changes.

[0077] For further information, see Figure 4 , Figure 4 is based on Figure 3The corresponding embodiment shows a method flow chart describing the steps of generating a series of discrete sampling values ​​within a parameter range for adapting the number of sampling points, and forming a vector representation of the parameters using the sampling values ​​as possible values ​​of the corresponding parameters.

[0078] The step S4112 of adapting the number of sampling points provided in the embodiment of the present invention to generate a series of discrete sampling values ​​within the parameter range, and using the sampling values ​​as possible values ​​of the corresponding parameters to form a vector representation of the parameters includes: Step S501, generating a normalized sequence with equal intervals according to the number of sampling points; Step S502, scaling up the normalized sequence to the parameter range of the corresponding type of parameter, so as to generate sampling values ​​corresponding to the number of sampling points for each type of parameter within the respective parameter range, and the sampling values ​​are used to generate a vector representation of the parameter.

[0079] This is the process of generating a discrete sampling set within the parameter range mapped by the parameter. The vector representation of the obtained parameter is the discrete sampling set within the parameter range. By executing this process, the parameter range can be divided into a series of discrete points, and then these discrete points can be used to estimate the influence of the parameters and determine the degree of influence of each parameter.

[0080] The sampling points of the parameters are defined by evenly discretizing the parameter value range into a number of equally spaced points. The specific sampling points are obtained by multiplying the normalized discrete value by the parameter range mapped by the parameter and adding the lower limit.

[0081] For example, the number of sampling points is p , the sampling value of each type of parameter is .

[0082] right k The parameters are p The sampling points are sampled once and the parameters are obtained. i The vector representations are X i =[ X i,0 , X i,1 , X i,2 ,……, X i, p i-1 ], X i is a parameter i The vector representation of X i,j Representation parameters i In the j The sample value of each sampling point.

[0083] As the vector representations of each parameter are obtained, the parameters are gradually changed through the execution of step S4113, and the sensitivity of each parameter is evaluated based on this, and the key parameters are determined based on the sensitivity.

[0084] Successive changes refer to the execution process of changing the sampling value of each parameter one by one, keeping the sampling values ​​of other parameters unchanged to obtain a number of sampling vectors, each sampling vector is composed of the sampling values ​​of each parameter.

[0085] A sampling can obtain the sampling values ​​corresponding to a set of parameters in one sampling. This set of parameters is all the parameters corresponding to the multi-physical field data. The sampling values ​​obtained in one sampling form a sampling vector. Only one sampling value corresponding to one parameter changes between adjacent sampling vectors.

[0086] Therefore, for the parameter i , the set of its sampled values ​​is the aforementioned parameter i The vector representation of is: X i =[ X i,0 , X i,1 , X i,2 ,……, X i, p i-1 ,]; vector X It is represented by a vector of parameters, specifically: X =[ X 1 , X 2 , X 3 ,……, X n ]; in, n is the number of parameters, illustratively, for k parameters, n = k . X i is the value of parameter i at a specific sampling point.

[0087] So far, we will use the vector representation of each parameter, that is, in the vector X Implementation kThe sampling is changed successively to obtain the corresponding sampling vectors successively, and for the sampling vector obtained by one change, the sampling vector obtained by the next change and the sampling vector obtained by the previous change are all adjacent vectors, so that only the sampling value corresponding to one parameter has a numerical change between them.

[0088] The change applied to each change is related to the parameter range and the number of sampling points corresponding to the changed sample value. The sample value, as an element in the sampling vector, corresponds to a parameter, which also initializes its parameter range and the number of sampling points, so that the change required to be applied to the sample value can be calculated.

[0089] Exemplarily, the applied change Δ is calculated by the following formula, namely: ; The vector representation of parameters comes from the discretization of the parameter space. Each vector represents a specific parameter value of a parameter, and the sampling vector is obtained by successively sampling the vectors of all parameters. Each element (sampling value) in the sampling vector represents the value of a parameter. In other words, a sampling vector represents a set of specific parameter values.

[0090] In the execution of the successive sampling process, the vector representation of the parameter is firstly independently sampled to obtain a sampling vector, and then the data of one element is successively changed based on this, that is, a change is applied to a sampling value to form a new sampling vector.

[0091] Specifically, in the successive sampling strategy, for a vector containing n parameters X =[ X 1 , X 2 , X 3 ,……, X n ], independent sampling is implemented to select a specific sampling vector, such as (X 1,0 , X 2,0 , X 3,0 ,……, X n,0 ); Then, using this as the initial value, the value of one parameter is changed in succession each time, that is, a change is applied to the value of a parameter in the previous vector to obtain a new sampling vector, and so on, each parameter is changed in turn to obtain a series of sampling vectors.

[0092] A series of sampling vectors are obtained by successive sampling. Since the adjacent sampling vectors only have one element changed and the other elements remain unchanged, only one independent sampling is required to obtain the initial sampling vector, and then the elements in the sampling vector are gradually adjusted to generate multiple adjacent sampling vectors, without the need for completely independent re-sampling.

[0093] Therefore, the number of sampling times is greatly reduced by performing successive sampling changes, and a clear parameter change trend is constructed, so that the influence of a single parameter can be clearly presented. There is no need to worry about the interference of multiple parameters' interactions on the results, which helps to identify key parameters through sensitivity.

[0094] It should be understood that if multiple parameters are randomly sampled at the same time each time, the dimension of the search space may increase, making the optimization more difficult. The sampling method of successive changes can "decompose" the optimization space into a one-dimensional problem, making it easier to find the optimal solution when performing step-by-step optimization.

[0095] After obtaining a series of sampling vectors, the sensitivity of each parameter can be calculated, and then the parameters with high sensitivity can be taken as the key parameters in the multi-physics field data.

[0096] See also Figure 5 , Figure 5 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of evaluating the sensitivity of each parameter by successively changing the parameter for the vector representation of the parameter, and taking the parameter with the largest sensitivity as the key parameter in the multi-physical field data.

[0097] The parameter-oriented vector representation of the embodiment of the present invention evaluates the sensitivity of each parameter by successively changing the parameters, and takes the parameter with the largest sensitivity as the key parameter in the multi-physical field data, step S4113, includes: Step S601, for each type of parameter, the corresponding vector is represented as an initial vector to perform sampling at the initial sampling point to obtain all parameter values ​​at the beginning of sampling to form an initial vector; Step S602, after obtaining the initial vector, sampling is performed a specified number of times by successive changes in the sampling values ​​between the parameters, and a number of adjacent vectors obtained by sampling form a trajectory, and the specified number of times is the number of the parameters.

[0098] That is to say, a series of sampling vectors obtained by successive sampling form a trajectory, which is then used to implement sensitivity calculation.

[0099] By executing step S601 and step S602, only the value of one parameter is changed while other parameters are kept unchanged, thereby avoiding repeated sampling and obtaining enough representative samples with a smaller number of sampling times, thereby improving calculation efficiency.

[0100] Compared with completely random or independent multiple sampling methods, the difference between the vectors generated by each sampling is smaller by changing the sampling successively, which can reduce unnecessary calculation repetition, while ensuring the diversity and breadth of sampling, saving computing and storage resources.

[0101] Under the effect of successive change sampling, since only the sampling value of one parameter is changed each time and the others remain consistent, the controllability of the sampling vector is ensured, and the interactive complexity caused by the simultaneous changes of multiple parameters is avoided. The effect of each parameter change can be clearly controlled, reducing the interference of interactions on the results.

[0102] This enables the influence of different physical field parameters on multi-physical field data to be captured in detail, and the role and relationship of different parameters in actual biological tissue measurements to be accurately evaluated, thereby enhancing the accuracy and reliability of biological tissue measurements.

[0103] In another embodiment, for the implemented sensitivity analysis, local sensitivity and global sensitivity are calculated, and finally key parameters are identified based on this.

[0104] See also Figure 6 , Figure 6 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of evaluating the sensitivity of each parameter by successively changing the parameter for the vector representation of the parameter, and taking the parameter with the largest sensitivity as the key parameter in the multi-physical field data.

[0105] The parameter-oriented vector representation of the embodiment of the present invention evaluates the sensitivity of each parameter by successively changing the parameters, and takes the parameter with the largest sensitivity as the key parameter step S4113 in the multi-physical field data, and further includes: Step S701, calculating the local sensitivity and global sensitivity of the trajectory to obtain the local sensitivity and global sensitivity of each parameter; Step S702: identifying, based on the local sensitivity and the global sensitivity, parameters that have a significant impact on the state change of the biological tissue under its own physiological activity as key parameters of the multi-physical field data in the biological tissue.

[0106] For the trajectory formed by the obtained series of sampling vectors, the sensitivity index of each parameter is calculated, and the sensitivity index includes local sensitivity and global sensitivity.

[0107] Exemplarily, the elementary effect (EE) is the result of evaluating the change of each parameter one by one and calculating the output. The importance of each parameter is estimated by evaluating the local change of each parameter within its parameter range. Therefore, the elementary effect (EE) is the local sensitivity of the parameter.

[0108] After calculating the basic effects of each parameter, the global sensitivity of each parameter will be obtained through the global sensitivity calculation. Exemplarily, the global sensitivity may include the EE mean and the EE variance. For example, the EE mean is used to measure the overall impact of the corresponding parameter, and the EE variance is used to evaluate the uncertainty and volatility of the impact of the corresponding parameter. The combination of the EE mean and variance can more accurately improve the accuracy and reliability of key parameter identification, and ensure the biological tissue measurement with high reliability.

[0109] Therefore, after determining the key parameters in the multi-physical field data through the execution of step S411, the optimal parameter values ​​and the applicable weighting coefficient combination can be obtained for the identified key parameters through the execution of step S412.

[0110] In an exemplary embodiment, the solution of the optimal parameter value and the acquisition of the applicable weighting coefficient combination are achieved through iterative optimization implemented by a genetic algorithm.

[0111] Specifically, the execution of step S412 includes: executing a genetic algorithm to iteratively optimize the biological probe measurement model with multi-physical field data corresponding to each parameter to obtain a set of optimal parameter values ​​corresponding to key parameters and a weighted coefficient combination of the optimal parameter value mapping.

[0112] The iterative optimization of the model through the genetic algorithm enables the implemented parameter identification to output a set of optimal parameter values, which is closer to the actual biological tissue measurement.

[0113] A set of optimal parameter values ​​of the currently applicable key parameters and a combination of weighted coefficients for mapping the optimal parameter values ​​are obtained adapted to the contact between the biological probe and the biological tissue, that is, after executing step S410, calibration fusion is implemented adapted to the contact between the biological probe and the biological tissue, as shown in step S420.

[0114] In the execution of step S420, the multi-physical field data collected by the biological probe is used to calibrate the optimal parameter value. It should be understood that the multi-physical field data describes the characteristics of the biological tissue itself, as well as the environmental parameters such as temperature, angle, etc. The angle referred to is the contact angle of the biological probe. For example, when the biological probe contacts the body horizontally (0 degrees), the contact area is the largest, and the multi-physical field data collected at this time is the most accurate, but as the angle increases, the multi-physical field data obtained will deviate. Therefore, it is necessary to calibrate the optimal parameter value output of the multi-physical field data for key parameters.

[0115] The implemented calibration is accompanied by numerical fusion. For a set of optimal parameter values ​​obtained, an angle-based calibration can be performed first and then the calibrated values ​​can be fused according to a combination of weighted coefficients to obtain the characteristic parameters of the biological tissue.

[0116] In addition, the optimal values ​​may be fused according to a combination of weighted coefficients to obtain a fused value, and then the fused value may be calibrated based on the angle.

[0117] Exemplarily, the angle angle in the multi-physics field data is used as an aid, and the cosine value cos(angle) corresponding to the angle angle is used as an adjustment factor to describe the influence of the angle on the measurement.

[0118] For example, for the optimal parameter value corresponding to each key parameter, the corresponding angle is obtained, and then the calibration values ​​of the three key parameters of impedance, pressure and temperature are obtained, as shown in the following formula: impedance_adj= impedance×cos(angle); pressure_adj=pressure×cos(angle); temperature_adj=temperature×cos(angle); Among them, impedance is the optimal parameter value corresponding to the key parameter impedance, and impedance_adj is the calibration value of impedance; pressure is the optimal parameter value corresponding to the key parameter pressure, and pressure_adj is the calibration value of pressure; temperature is the optimal parameter value corresponding to the key parameter temperature, and temperature_adj is the calibration value of temperature.

[0119] After the calibration is completed with the help of the angle, the calibration values ​​are combined and fused based on the applicable weighting coefficients to obtain the characteristic parameters of the currently measured characteristic tissue.

[0120] In summary, exemplarily, the execution process of step S420 includes: obtaining auxiliary physical quantities adapted to the contact between the biological probe and the biological tissue, the auxiliary physical quantities being used to describe the contact state of the biological probe with the biological tissue; calibrating and fusing the optimal parameter values ​​according to the auxiliary physical quantities and the weighting coefficient combination to obtain the characteristic parameters of the biological tissue.

[0121] Therefore, describing the contact state between the biological probe and the characteristic tissue currently being measured through auxiliary physical quantities, such as angle, helps to accurately reflect the response characteristics of the biological tissue under different contact conditions, thereby significantly improving the accuracy of biological tissue measurement and avoiding errors caused by poor contact or environmental interference.

[0122] Combining auxiliary physical quantities with weighted coefficients, calibrating and integrating optimal parameter values ​​can effectively eliminate unnecessary interference factors and improve the accuracy of biological tissue characteristic parameters. Different data sources are given different weights by weighting to ensure that the final output characteristic parameters are optimal and can more realistically reflect the state of biological tissues.

[0123] Under the action of step S420, the adaptability of the biological probe to the contact with the biological tissue is enhanced, and it can dynamically adapt to different contact conditions and adapt to a variety of biological tissue types. It is further explained that the contact state between the biological probe and the biological tissue is dynamically changing. Under the action of the auxiliary physical quantity, it can help the system to understand the change of the contact in real time, and then adjust itself to obtain consistent and high-quality result output. In addition, different biological tissues have different physical properties, such as hardness, conductivity and temperature, which often vary with different biological tissue types. Therefore, with the help of auxiliary physical quantities, the calibration fusion is adapted to the currently measured biological tissue, so that the system can adapt to multiple types of biological tissues to provide high-precision measurements.

[0124] With the realization of calibration fusion, external interference is eliminated. Even if the contact of the biological probe is affected by the environment, the interference will be effectively shielded under the action of the combination of auxiliary physical quantities and applicable weighting coefficients, ensuring the reliability of the measurement and the stable operation of the system, providing support for precision medicine and personalized health assessment.

[0125] For the characteristic parameters obtained by calibration and fusion, a biological tissue characteristic analysis model mapped by the characteristic parameters is constructed by executing step S430, so as to obtain the state evaluation result of the currently measured biological tissue.

[0126] In step S430, for each characteristic parameter obtained, a biological tissue characteristic analysis model mapped thereto is adaptively constructed. Exemplarily, the biological tissue characteristic analysis model may be in the form of a mapping function.

[0127] Each characteristic parameter can be fitted to obtain its corresponding mapping function, which is used to describe the relationship between the characteristic parameter and the state of the biological tissue. For example, some characteristic parameters can be linearly associated with the health state of the biological tissue, while some characteristic parameters may be nonlinear. Therefore, a set of mapping functions will be generated for the obtained characteristic parameters to provide a multi-dimensional state evaluation for the currently measured biological tissue.

[0128] For example, through calibration fusion, key parameters such as impedance change rate, pressure response coefficient and temperature regulation ability of biological tissues are obtained. These key parameters are closely related to the health status and functional status of the currently measured biological tissues.

[0129] Based on these key parameters, corresponding characteristic parameters are obtained, and the corresponding weights and mapping functions are configured. Then, the weights and mapping functions are used to evaluate the state of the biological tissue to obtain the current health state and / or functional state of the biological tissue.

[0130] The stronger the correlation of a characteristic parameter with the health status of biological tissue, the higher the accuracy of judging the pathological changes of biological tissue, and the greater the corresponding weight. For example, the weights of the characteristic parameters α and β of the key parameters are calculated as follows: ; in, w α is the characteristic parameter α The weight of w β is the characteristic parameter β The weight of , n is the number of sampling points, and e is a constant.

[0131] Finally, the current measured state of biological tissue can be calculated, namely: ; Among them, f(α) and f(β) are mapping functions constructed based on the relationship between characteristic parameters and biological tissue properties, thereby providing strong support for biomedical research.

[0132] The following uses the measurement of the biological tissue of skin as an example to illustrate the system implementation of the present invention.

[0133] Skin tissue is affected by the external environment, such as pressure and temperature, and internal characteristics, such as impedance. The multi-physical field data y output by the bioprobe exists in the form of skin bioelectric signal intensity. At this time, the bioprobe measurement model is used to identify key parameters, such as impedance, pressure and temperature. Figure 7 As shown, Figure 7 1 is a graph of multi-physical field data output by the biological probe 10 in an example. In the multi-physical field data output by the biological probe 10, the data curves corresponding to the three parameters of impedance, temperature and pressure are shown as follows: Figure 7 shown.

[0134] The parameter ranges involved in the three types of parameters, impedance, pressure and temperature, are as follows: Impedance x 1 , parameter range [10,1000]Ω; Pressure x 2 , parameter range [0,5]N; Temperature x 3 , parameter range [20,40]℃.

[0135] Configure the number of sampling points to p=5; after discretization and random sampling, the vector of each parameter is expressed as: x 1 ={10,257.5,505,752.5,1000}Ω; x 2 ={0,1.25,2.5,3.75,5}N; x 3 ={20,25,30,35,40}℃.

[0136] Then, the initial value of this independent sampling method is selected by Monte Carlo simulation to obtain a specific sampling vector (initial vector) obtained by independent sampling: X=(x 1 ,x 2 ,x 3 )=(505Ω,2.5N,30℃).

[0137] For this specific sampling vector X=(x 1 ,x 2 ,x 3 )=(505Ω,2.5N,30℃) implements successive changes, i.e., successive disturbances. Starting from the initial point, a single parameter is disturbed in turn (increase or decrease a step size (i.e., the imposed change)), and the other parameters remain unchanged.

[0138] The perturbation step size is Δ: x 1 : Δ=(1000-10) / (5-1)=247.5Ω.

[0139] x 2 :Δ=(5-0) / (5-1)=1.25N.

[0140] x 3 :Δ=(40-20) / (5-1)=5℃.

[0141] Thus, the first perturbation, the second perturbation and the third perturbation are performed to obtain a series of sampling vectors, which are as follows: The first perturbation x 1 :X=(752.5Ω,2.5N,30℃); The second perturbation x 2 :X=(505Ω,3.75N,30℃); The third disturbance x 3 :X=(505Ω,2.5N,35℃).

[0142] The series of sampling vectors obtained by three perturbations constitute the sampling trajectory, and the basic effect (EE) is performed on the sampling trajectory. After repeated sampling, the following average sensitivity effect EE is obtained: Impedance x 1 :EEx 1 =-0.15μV / Ω (negative value means that the increase of parameter will lead to the decrease of output); Pressure x 2 :EEx 2 =22.5μV / N; Temperature x 3 :EEx 3 =3.8μV / ℃.

[0143] It can be seen that the pressure x 2 As the key parameter, pressure x 2 The optimal parameter values ​​are searched for the key parameters, and the skin tissue status assessment results are outputted through the subsequent calibration fusion under the action of the mapped characteristic tissue feature analysis model.

[0144] To further illustrate, a set of optimal parameter values ​​corresponding to the key parameters are calibrated and fused. In the calibration fusion performed, angles are added as described above to assist calibration data, that is, the fusion of the set of optimal parameter values ​​is first performed and then calibration is performed.

[0145] In addition, it is also possible to add angle assistance to implement calibration re-fusion with respect to the optimal parameter value corresponding to each key parameter.

[0146] By analogy, the fused feature parameters are finally used to output the skin tissue status assessment result under the action of the mapped feature tissue feature analysis model, that is, Figure 7 shown.

[0147] Figure 7 The weighted fusion value (bio-tissue health status assessment result) corresponding to each skin tissue sample is mapped to the health status, that is, the formula The calculated biological tissue health status assessment result determines whether the skin tissue sample is in a healthy state, a sub-healthy state, or even an unhealthy state.

[0148] In an exemplary embodiment, the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned method.

[0149] In an exemplary embodiment, the present invention further provides a computer program product, comprising a computer program, wherein the computer program implements the steps of the above method when executed by a processor.

[0150] In an exemplary embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method when executed by a processor.

[0151] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0152] In an exemplary embodiment of the present invention, a computer program medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the method described in the above method embodiment.

[0153] According to one embodiment of the present invention, a program product for implementing the method in the above method embodiment is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0154] The program product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0155] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0156] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0157] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0158] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0159] In addition, although the steps of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0160] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation method of the present invention.

[0161] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the appended claims.

Claims

1. A multi-physics field data fusion system for biological probes, characterized in that: The system comprises: A biological probe, used for collecting data of the currently measured biological tissue to obtain multi-physical field data of the biological tissue, wherein the multi-physical field data includes environmental parameters and intrinsic characteristic parameters of the biological tissue; A memory, a processor, and a computer program stored in the memory, wherein the computer program is executed by the processor to implement the following steps: Determine the key parameters of the currently measured biological tissue by the multi-physical field data through the biological probe measurement model, and find a set of optimal parameter values ​​for the key parameters, as well as a weighted coefficient combination of the optimal parameter value mapping; Adapting to the contact between the biological probe and the biological tissue, the characteristic parameters of the biological tissue are obtained by combining and calibrating the optimal parameter values ​​through the mapped weighted coefficients; A biological tissue feature analysis model of the feature parameter mapping is adaptively constructed for the measured biological tissue, and a state evaluation result of the biological tissue is output.

2. The system according to claim 1, characterized in that The biological probe senses different types of physical signals to sense and collect multi-physical field data corresponding to multiple physical fields in real time on biological tissues.

3. The system according to claim 1, characterized in that The method of determining the key parameters of the currently measured biological tissue by the multi-physical field data through the biological probe measurement model, and finding a set of optimal parameter values ​​for the key parameters, and a weighted coefficient combination of the optimal parameter value mapping, includes: For the biological tissue currently contacted and measured by the biological probe, based on the discretization processing of the multi-physical field data by the biological probe measurement model and the random sampling on the discretization processing, sensitivity calculation is performed to determine the key parameters in the multi-physical field data; Parameter identification is performed on key parameters in the multi-physical field data to obtain a set of optimal parameter values ​​corresponding to the key parameters, and a weighted coefficient combination of the optimal parameter value mapping.

4. The system according to claim 3, characterized in that The method of performing sensitivity calculation on the biological tissue currently contacted and measured by the biological probe based on the discretization processing of the multi-physical field data by the biological probe measurement model and random sampling on the discretization processing to determine the key parameters in the multi-physical field data includes: Initializing the configuration of the parameter range of each parameter mapping in the multi-physical field data and the number of sampling points of the parameter within the parameter range for the biological tissue; Adapting the number of sampling points to generate a series of discrete sampling values ​​within the parameter range, and using the sampling values ​​as possible values ​​of the corresponding parameters to form a vector representation of the parameters; The parameter-oriented vector representation evaluates the sensitivity of each parameter by successively changing the parameters, and the parameter with the largest sensitivity is taken as the key parameter in the multi-physical field data.

5. The system according to claim 4, characterized in that The parameter range of each parameter mapping is different for different biological tissues.

6. The system according to claim 4, characterized in that The parameter-oriented vector representation evaluates the sensitivity of each parameter by successively changing the parameters, and takes the parameter with the largest sensitivity as the key parameter in the multi-physics field data, including: Calculate the local sensitivity and global sensitivity of the sampled trajectory to obtain the local sensitivity and global sensitivity of each parameter; According to the local sensitivity and the global sensitivity, the parameters that have a significant impact on the state change of the biological tissue under its own physiological activities are identified as the key parameters of the multi-physical field data in the biological tissue.

7. The system according to claim 3, characterized in that The step of performing parameter identification on the key parameters in the multi-physics field data to obtain a set of optimal parameter values ​​corresponding to the key parameters, and a weighted coefficient combination of the optimal parameter value mapping, includes: The genetic algorithm is used to iteratively optimize the biological probe measurement model using multi-physical field data corresponding to each parameter to obtain a set of optimal parameter values ​​corresponding to key parameters and a weighted coefficient combination of the optimal parameter value mapping.

8. A multi-physics field data fusion method for a biological probe, characterized in that: The method executes the steps implemented in the system of any one of claims 1-7.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the system according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the system according to any one of claims 1 to 7.

Images