A cloud platform-based biological scientific research data collaborative analysis system

Abstract

The application discloses a kind of biological scientific research data collaborative analysis system based on cloud platform, it is related to data analysis technical field, including management center, the management center is connected with basic acquisition module, platform processing module, automation analysis module and service support module;To biological scientific research data data transmission change, obtain biological scientific research signal, to biological scientific research signal is dimension conversion, obtains biological wave variation array;Through updating prediction array, biological wave variation array is replaced with number and number chart conversion, obtains the graph of biological science, sets up mobile capture axis and obtains identity characteristic section to the graph of biological science;According to position node interval, identity characteristic section is distinguished by type, obtains biological identity type library, filters combination to biological identity type library, obtains biological type sequence;Efficient data processing is carried out using cloud platform, optimization collaboration experience is ensured Data security.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically a cloud-based collaborative analysis system for biological research data. Background Technology

[0002] A cloud platform, also known as a cloud computing platform, is a service platform based on cloud computing technology. It provides a range of computing resources, storage resources, network resources, applications, and services, which users can access and use on demand via the Internet.

[0003] Collaborative analysis of biological research data refers to the process in which multiple researchers or teams collaborate to integrate, analyze, and mine biological research data in order to discover biological laws, interpret biological phenomena, and advance scientific research. With the development of science and technology, the volume of biological data has surged, the types of data have become diverse, and the analysis process has become complex. Biological research often requires interdisciplinary and cross-regional team collaboration, placing high demands on the real-time nature and accuracy of data sharing and analysis. However, existing biological data analysis tools and platforms have limitations in handling large amounts of data, supporting remote collaboration, and ensuring data security. Therefore, this paper presents a cloud-based collaborative analysis system for biological research data to improve data processing efficiency and enhance research collaboration through collaborative analysis of biological research data. Summary of the Invention

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] A cloud-based collaborative analysis system for biological research data includes a management center, which is connected to a basic data acquisition module, a platform processing module, an automated analysis module, and a service support module.

[0006] The process of acquiring biological research data by the basic acquisition module includes:

[0007] Obtain cloud platform information and build a collaborative scientific research cloud platform based on the cloud platform information;

[0008] Set up a virtual acquisition terminal and build a transmission link between the virtual acquisition terminal and the collaborative scientific research cloud platform;

[0009] Data is collected from multiple sources of technology through a virtual acquisition terminal to obtain biological research data, which is then uploaded to the collaborative research cloud platform.

[0010] The process of constructing the initial prediction element matrix based on the predicted wavelength includes:

[0011] The obtained biological research data is converted into biological research signals, the attributes of the biological research data are extracted to obtain an attribute set, and the wave response coefficient is set according to the attribute set.

[0012] The obtained wave response coefficients are locally adjusted to obtain wave variation parameters. The wave response coefficients are then used to predict the dimension based on the wave variation parameters to obtain the predicted wave distance. An initial prediction element array is then set based on the predicted wave distance.

[0013] The process of obtaining bio-wave array transformation includes:

[0014] Wave-variant sequences are obtained based on the predicted wave distances. Wave response coefficients are then divided into sequences using the wave-variant sequences to obtain the predicted wave-variant segments.

[0015] Based on the sequence division, the obtained predicted wavelet segments are uploaded to the biological research signal, and the biological research signal is captured layer by layer through the predicted wavelet segments to obtain the biological research wavelet segments.

[0016] The obtained biological research wave variant segments are uploaded to the initial prediction element array. The initial prediction element array is supplemented with elements based on the obtained biological research wave variant segments to obtain the biological wave variant array.

[0017] Based on the obtained predicted wavelength, the predicted wavelength segments are assembled to form an updated prediction array.

[0018] The process of obtaining identity feature segments includes:

[0019] The obtained updated prediction matrix is ​​element-averaged to obtain the expected mean. The expected statistics of the updated prediction matrix are then performed based on the expected mean to obtain the expected prediction value.

[0020] The biological wave array is subjected to a digital state change based on the expected mean and expected predicted value to obtain an updated wave array. The updated wave array is then subjected to a digital-graph conversion to obtain a biological wave graph.

[0021] Set a moving capture axis, upload the moving capture axis to the Life Science Wave Map, and capture features of the Life Science Wave Map through the moving capture axis to obtain identity feature segments;

[0022] The biological science fluctuation graph is marked with intervals based on the identity feature segments to obtain the position node intervals.

[0023] The process of performing numerical state transformation on the bio-wave array based on the expected mean and expected predicted value includes:

[0024] The mean of each column of the biological wave array is divided to obtain the mean of the biological column.

[0025] Based on the obtained biological column mean, expected mean, and expected predicted value, the biological wave array is permuted to obtain the permuted waveband value;

[0026] Replace the elements at the original positions of the biowave array with the obtained permutation band values ​​to obtain permutation bands, until all elements in the biowave array are replaced with permutation bands, and mark the biowave array after element replacement as the updated wave array.

[0027] The process of classifying identity feature segments based on location node intervals includes:

[0028] Select any segment of the biomolecular wave pattern as the identification segment, obtain the position node interval corresponding to the identification segment as the identification node interval, and identify the biological wave curve segment corresponding to the identification node interval in the remaining biomolecular wave patterns as the matching wave curve segment.

[0029] The obtained comparison identity segment and the matching waveform segment are similarly matched to obtain the matching waveform segment. A biometric identity type library is constructed, and the comparison identity segment and the matching waveform segment corresponding to the comparison identity segment are uploaded to the biometric identity type library.

[0030] Select any one of the remaining identity feature segments and denote it as the comparison identity segment. Repeat the process of obtaining the biometric identity type library corresponding to the comparison identity segment until all identity feature segments have a corresponding biometric identity type library.

[0031] The process of filtering and combining biometric identity type databases includes:

[0032] Perform time-based filtering on the biometric identity type database to obtain the initial identity segment, and mark the biometric identity type database corresponding to the initial identity segment as the initial type database;

[0033] Based on the initial identity segment, time matching is performed on the remaining biometric identity type library to obtain the continued identity segment. The corresponding biometric identity type library is then obtained and denoted as the continued type library. After removing the initial type library and the continued type library, time matching is performed on the remaining biometric identity type library. The process of obtaining the continued identity segment is repeated until all biometric identity type libraries have been time matched.

[0034] The starting identity segment and the continuing identity segment are combined in the order of time matching to obtain a biological data sequence. The biological data sequence is then replaced with the corresponding biological identity type according to the biological identity type library to obtain a biological type sequence.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] The process involves transforming biological research data into a format to obtain biological research signals, extracting features from these signals, and performing graphical transformation to obtain curve fluctuation graphs. Feature recognition is then performed on these curve fluctuation graphs to obtain the corresponding identity feature segments for the biological research data. Using these identity feature segments to represent the biological research data facilitates efficient processing of large-scale biological research data. Furthermore, transforming the collected biological research data into a format helps ensure data security and protect user data from leakage.

[0037] By analyzing identity feature segments in the cloud platform, we can obtain identity feature segments of the same type and build a biological identity type library. Then, by filtering and analyzing the biological identity type library, we can obtain the order of action and interaction of different types of biological research data. This is conducive to the integration and cross-analysis of biological research data, enabling efficient data processing using the cloud platform and optimizing the collaborative experience. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0040] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] like Figure 1 As shown, a cloud-based collaborative analysis system for biological research data includes a management center, which is connected to a basic data acquisition module, a platform processing module, an automated analysis module, and a service support module.

[0042] The basic data acquisition module is used to collect biological research data, and the specific process includes:

[0043] Obtain cloud platform information and build a collaborative scientific research cloud platform based on the cloud platform information;

[0044] Furthermore, the cloud platform information refers to the construction information composed of the existing cloud platform construction process, which is the cloud platform information. Therefore, a cloud platform for processing and analyzing biological research data is constructed based on the obtained cloud platform information, which is the collaborative research cloud platform.

[0045] Set up a virtual acquisition terminal and construct a transmission link between the virtual acquisition terminal and the collaborative scientific research cloud platform. The transmission link is used to upload the data information generated by the virtual acquisition terminal to the collaborative scientific research cloud platform.

[0046] Data is collected from multiple sources of technology through a virtual acquisition terminal to obtain biological research data, which includes genomic data, proteomic data, metabolomic data, clinical data, experimental data, literature data, and multi-omics data.

[0047] Furthermore, the term "multi-source technology end" refers to the technology companies, researchers, and organizations that generate biological research data.

[0048] The obtained biological research data is uploaded to the collaborative research cloud platform.

[0049] The platform processing module is used to perform data conversion on biological research data to obtain biological research signals, and to perform dimensional transformation on the biological research signals to obtain biological wave arrays. The specific process includes:

[0050] Data exchange is performed on the acquired biological research data to obtain biological research signals;

[0051] Furthermore, the data conversion refers to converting the obtained biological research data into signal form. Based on the genomic data, proteomic data, metabolomic data, clinical data, experimental data, literature data, and multi-omics data included in the biological research data, the biological research signal includes genomic signal, proteomic signal, metabolomic signal, clinical signal, experimental signal, literature signal, and multi-omics signal.

[0052] The obtained biological research signals are subjected to attribute extraction to obtain an attribute set, which includes frequency characteristics, smoothness, and stationarity.

[0053] Wave response coefficients are set based on the obtained attribute set. The wave response coefficients are expressed in functional form and are determined according to wavelet functions, including but not limited to Haar wavelet, Symlet wavelet, and Coiflet wavelet. The characteristics of biological research signals are determined based on the frequency characteristics, smoothness, and stationarity included in the attribute set. The type of wavelet function is determined based on the signal characteristics. For example, for signals requiring high time resolution, the short-support wavelet function Haar wavelet is selected.

[0054] The obtained wave response coefficients are locally adjusted to obtain wave variation parameters;

[0055] The local modulation refers to scaling and translating the wave response coefficients in the time and frequency dimensions, and statistically analyzing the scale of the scaling and translating transformations to obtain wave variation parameters.

[0056] Based on the obtained wave variation parameters, the wave response coefficient is predicted in dimension to obtain the predicted wave distance, and the obtained predicted wave distance is marked as y.

[0057] The dimensional prediction refers to the statistical analysis of the distance between two adjacent wave variables in the wave response coefficient to obtain the predicted wave distance, and the obtained distance is rounded down to the nearest integer, that is, the obtained predicted wave distance is a positive integer. For example, if the distance is 12.6, the predicted wave distance is recorded as 12.

[0058] The initial prediction element matrix is ​​set based on the obtained predicted wavelength. The initial prediction element matrix is ​​in matrix form and is an equal-row, equal-column matrix. The number of diagonal elements of the initial prediction element matrix is ​​equal to the predicted wavelength, that is, the number of rows and columns of the initial prediction element matrix are equal to y. For example, if the predicted wavelength y=12, then there are 12 elements on the diagonal of the initial prediction element matrix, that is, the initial prediction element matrix is ​​a 12-row, 12-column matrix.

[0059] The wave-variant sequence is obtained based on the predicted wave distance and is labeled as b, where b = 3y - 2.

[0060] Based on the obtained wave-variant stratigraphic sequence, the wave response coefficient is divided into sequences to obtain the predicted wave-variant segments;

[0061] Furthermore, the sequence division means that the wave response coefficient is equally divided according to the number of wave-variant sequences to obtain predictive wave-variant segments of equal length, that is, the number of predictive wave-variant segments is equal to the number of wave-variant sequences.

[0062] Based on the sequence division, the obtained predicted wavelet segments are uploaded to the biological research signal. The biological research signal is captured layer by layer through the predicted wavelet segments to obtain the biological research wavelet segments.

[0063] It should be further explained that, in the specific implementation process, the layer-by-layer capture process includes:

[0064] The first predicted wavelet segment obtained according to the hierarchical division order is uploaded to the biological research signal. The biological research signal is then hierarchically extracted through the predicted wavelet segment to obtain hierarchical biological wavelet segments. The hierarchical extraction means convolving the predicted wavelet segment with the corresponding element of the biological research signal.

[0065] Discrete Fourier transform is performed on the obtained hierarchical biological wave bands to obtain the biological research wave bands.

[0066] Based on the order of the stratification, the next predicted wavelet is uploaded to the biological research signal, and the process of obtaining the biological research wavelet is repeated until all the predicted wavelets are extracted hierarchically from the biological research signal, and the obtained biological research wavelets are statistically analyzed according to the order of the stratification.

[0067] Based on the sequence partitioning, the obtained biological research wave variants are uploaded to the initial prediction element array. The initial prediction element array is then supplemented with elements according to the obtained biological research wave variants to obtain the biological wave variant array. Elements within the biological wave variant array are then marked as follows: y = 1, 2, 3, ..., u1, where u1 is a positive integer, and "yy" represents the element in the y-th row and y-th column. For example, if "y" is 55, then... , represents the element at the fifth row and fifth column;

[0068] Furthermore, the element supplementation means first retaining the elements in the first row, first column, and diagonal positions of the initial predicted element array, replacing the elements in the remaining positions with zeros, and then sequentially uploading the biological research wavelet segment to the corresponding positions according to the hierarchical division order, from the first row, second row, third row, ..., y-th row. That is, the first biological research wavelet segment is uploaded to the first row and first column position of the initial predicted element array, the second biological research wavelet segment is uploaded to the first row and second column position of the initial predicted element array, and the third biological research wavelet segment is uploaded to the initial predicted element array. The first row and third column of the array, ..., the (y+1)th biological research wave variable segment is uploaded to the second row and first column of the initial prediction element array, the (y+2)th biological research wave variable segment is uploaded to the second row and second column of the initial prediction element array, the (y+3)th biological research wave variable segment is uploaded to the third row and first column of the initial prediction element array, the (y+4)th biological research wave variable segment is uploaded to the third row and third column of the initial prediction element array, ..., until the elements in the first row, first column and diagonal positions of the initial prediction element array are all completed, thus obtaining the biological wave variable array;

[0069] The predicted wave bands are assembled based on the obtained predicted wave distance to obtain an updated prediction array;

[0070] Furthermore, the set assembly represents constructing an m x m matrix based on the number of predicted wave distances, and sequentially uploading the predicted wave segments to the constructed matrix according to the order of layer division to obtain an updated prediction matrix, where m*m≥y. If there are still empty positions after uploading y predicted wave segments to the updated prediction matrix, the empty position elements are replaced with zeros, where m=1,2,3,...,u2, and u2 is a positive integer.

[0071] Update the internal elements of the prediction matrix and mark them as Where "mm" represents the element in the m-th row and m-th column, for example, "mm" is 15, which is... , represents the element at the position of the first row and fifth column.

[0072] The automated analysis module is used to perform digital state replacement and digital-graph transformation on the biological wave array by updating the prediction array to obtain a biological wave map. It then sets a moving grasping axis to capture features from the biological wave map and obtain identity feature segments. The specific process includes:

[0073] The obtained updated prediction matrix is ​​element-wise equalized to obtain the expected mean, which is denoted as Q. ;

[0074] Based on the obtained expected mean, the expected statistics of the updated prediction matrix are performed to obtain the expected predicted value, which is denoted as W. P represents the total value of the elements in the updated prediction matrix. That is, the determinant operation is performed on the updated prediction matrix, and the value of the determinant is the total value of the elements, which is P.

[0075] The biological wave array is subjected to a numerical state change based on the obtained expected mean and expected predicted value to obtain an updated wave array;

[0076] It should be further explained that, in the specific implementation process, the state-change process includes:

[0077] The mean of each column of the bio-wave array is divided into mean values ​​to obtain the mean of each column, which is denoted as the bio-column mean. The mean division means calculating the mean of each column.

[0078] Based on the obtained biological column mean, expected mean, and expected predicted value, the biological wave array is permuted to obtain the permuted waveband value;

[0079] The column permutation refers to calculating the permutation band value of the corresponding element according to the element arrangement order of the bio-wave array, and marking the obtained permutation band value as... ,in, , This represents the mean of the y-th column of organisms, i.e. The corresponding biological mean of that column, β is the equilibrium factor, when W=P, ,when hour, When W=P and hour, ;

[0080] Replace the elements at the original positions with the obtained permutation band values ​​to obtain permutation wave segments. Replace the corresponding permutation band values ​​with the corresponding values ​​of all elements in the bio-wave array. All the obtained elements are permutation wave segments. Mark the bio-wave array after element replacement as the updated wave array.

[0081] The obtained updated wave arrays are correlated with corresponding biological research data;

[0082] The obtained updated wave array is converted into a digital graph to obtain the biological science wave graph;

[0083] Furthermore, the data-to-image conversion represents the construction of a two-dimensional rectangular coordinate system, with the horizontal axis representing time and the vertical axis representing the elements within the updated wavelet transform matrix. The updated wavelet transform matrix is ​​then converted into a curve, denoted as the bio-wavelet transform curve, and the obtained bio-wavelet transform curve is marked as... , n represents the intersection of the point on the curve with the horizontal axis, i.e. the time node number, i represents the number of the update wave transformation array, which is generated from the update wave transformation array according to the biological wave transformation curve, i also represents the number of the biological wave transformation curve, i=1, 2, 3, ..., u3, u3 is a positive integer; each point on the curve represents an element in the update wave transformation array, and the obtained biological wave transformation curve is uploaded to a two-dimensional rectangular coordinate system to obtain the biological wave diagram;

[0084] A moving grasp axis is set, which consists of two parallel lines parallel to the horizontal axis of the life science fluctuation chart. The moving grasp axis can move freely up and down in the life science fluctuation chart and remains parallel to the horizontal axis during the movement. The moving grasp axis includes a top grasp axis and a bottom grasp axis, and the top grasp axis is located above the bottom grasp axis.

[0085] The obtained motion-grabbing axis is uploaded to the Life Science Wave Map, and the Life Science Wave Map is used to capture features through the motion-grabbing axis to obtain identity feature segments;

[0086] It should be further explained that, in the specific implementation process, the feature capture process includes:

[0087] Move both the top and bottom axes of the obtained grasping axis to the highest point of the bio-wavelength curve within the bio-wavelength curve. Keep the top axis stationary and move the bottom axis downwards until the intersection of the bottom axis and the bio-wavelength curve satisfies the discontinuity interval. Stop moving the bottom axis and mark the bio-wavelength curve corresponding to the discontinuity interval as the identity feature segment. The discontinuity interval represents a pre-defined fixed-length time period, represented on the horizontal axis as a time segment. The movement of the bottom axis stops when the distance between the left and right intersections of the bottom axis and the bio-wavelength curve reaches the discontinuity interval. Mark the left and right intersections of the bottom axis and the bio-wavelength curve as the first node and the second node, respectively. Mark the obtained first node as... Mark the obtained second node as “in” represents the nth time node of the i-th biowave curve, “i-(n+e)” represents the time node after the nth time node of the i-th biowave curve, and e represents the length of the discontinuity interval.

[0088] The biotechnology fluctuation graph is marked with intervals based on the obtained identity feature segments to obtain position node intervals. These position node intervals represent the intersections of discontinuous intervals corresponding to the identity feature segments. to This represents the interval of location nodes, and thus the corresponding position of the identity feature segment in the bio-wave curve.

[0089] The service support module is used to distinguish the types of identity feature segments based on location node intervals, obtain a biometric identity type library, and filter and combine the biometric identity type library to obtain a biometric type sequence. The specific process includes:

[0090] Based on the location node interval, the obtained identity feature segments are distinguished by type to obtain a biometric identity type library;

[0091] Furthermore, the process of distinguishing the types includes:

[0092] Select any segment of the biomolecular wave pattern as the identification segment, obtain the position node interval corresponding to the identification segment as the identification node interval, and identify the biological wave curve segment corresponding to the identification node interval in the remaining biomolecular wave patterns as the matching wave curve segment.

[0093] The obtained identity segments are similarly matched with the matching waveform segments to obtain matching waveform segments. The obtained matching waveform segments and the identity segments are classified into the same type of biological research data, and a biological identity type library is constructed. The identity segments and the matching waveform segments corresponding to the identity segments are uploaded to the biological identity type library. That is, a biological identity type library represents a type of biological research data, including the identity feature segments corresponding to all biological research data of that type.

[0094] Specifically, the similarity matching means comparing the curve overlap of the comparison identity segment with other matching waveform segments within the comparison node interval. If there are other matching waveform segments whose overlap with the comparison identity segment reaches the overlap threshold, they are recorded as matching waveform segments. The overlap threshold represents the threshold of the degree of overlap between two curve segments. In this embodiment, the curve overlap is determined by the smoothness and curvature of the curve.

[0095] Select one of the remaining identity feature segments and record it as the comparison identity segment. Repeat the process of obtaining the biometric identity type library corresponding to the comparison identity segment until all identity feature segments have been classified into types.

[0096] Mark the obtained biometric identity type database as k represents the data type number of biological research data, k=1, 2, 3, ..., u4, where u4 is a positive integer;

[0097] The obtained biometric identity type database is filtered by time to obtain the starting identity segment, and the location node interval corresponding to the starting identity segment is marked as the starting node interval;

[0098] Furthermore, the time filtering means filtering the position node intervals corresponding to the identity feature segments in all obtained biometric identity type databases in chronological order to obtain the position node interval closest to the origin of the biometric fluctuation diagram, that is, the first node is closest to the origin, which is denoted as the starting node interval, and the identity feature segment corresponding to the starting node interval is marked as the starting identity segment.

[0099] The biometric identity type library corresponding to the initial identity segment is marked as the initial type library. Based on the obtained initial identity segment, the remaining biometric identity type library is time-matched to obtain the continued identity segment. Here, the time matching is the matching of the remaining biometric identity type library after removing the initial type library.

[0100] Furthermore, the time matching means obtaining the second node of the starting node interval corresponding to the starting identity segment, performing difference statistics between the obtained second node and the first node of the position node interval of all identity feature segments in the remaining biometric identity type database, and obtaining the comparison difference. The difference statistics means subtracting the value of the second node of the starting node interval on the biometric wave curve from the value of the first node of the position node interval of all identity feature segments in the remaining biometric identity type database on the biometric wave curve, and taking the absolute value of the calculation result to obtain a positive comparison difference.

[0101] The obtained comparison differences are sorted in ascending order, and the identity feature segment corresponding to the first-ranked comparison difference is recorded as the continuation identity segment.

[0102] Obtain the biometric identity type library corresponding to the continued identity segment, denoted as the continued type library;

[0103] After removing the initial type library and the continuation type library, time matching is performed on the remaining biometric identity type library to obtain the second continuation identity segment. The process of time matching on the second continuation identity segment is repeated until all biometric identity type libraries are matched. It is important to note that time matching can only be performed after the biometric identity type library corresponding to the current identity feature segment and the identity feature segment before the first node of the identity segment has been removed.

[0104] The obtained initial identity segments and continuation identity segments are combined according to the time matching order to obtain a biological data sequence. That is, after time matching, a sequence of identity feature segments is obtained according to the order of the first node of the position node interval, which represents the sequential relationship of different types of biological scientific research data.

[0105] By replacing biological data sequences with corresponding biological identity type databases, biological type sequences can be obtained. This involves replacing each identity feature segment in the biological data sequence with the corresponding biological identity type database. This allows us to observe the sequential relationships between different biological research data and obtain the interaction relationships between different types.

[0106] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud-based collaborative analysis system for biological research data, comprising a management center, characterized in that, The management center is connected to a basic data acquisition module, a platform processing module, an automated analysis module, and a service support module. The basic acquisition module is used to collect biological research data; The platform processing module is used to convert biological research data, obtain biological research signals, set wave response coefficients based on biological research signals and perform dimension prediction to obtain predicted wave distances. The wave response coefficients are expressed in the form of functions. The dimensional prediction refers to the rounding and statistical analysis of the distance between two adjacent wave variable parameters in the wave response coefficient to obtain the predicted wave distance. Constructing an initial prediction element matrix based on the predicted wavelength includes the following process: The obtained biological research data is converted into biological research signals, the attributes of the biological research data are extracted to obtain an attribute set, and the wave response coefficient is set according to the attribute set. The obtained wave response coefficients are locally adjusted to obtain wave variation parameters. The wave response coefficients are then used to predict the dimension based on the wave variation parameters to obtain the predicted wave distance. An initial prediction element matrix is ​​then set based on the predicted wave distance. The wave response coefficients are sequence-divided to obtain predicted wave segments and an updated prediction matrix is ​​constructed. The sequence division refers to the equal division of the wave response coefficient according to the number of wave variable sequences to obtain predictive wave variable segments of equal length. Biological research signals are captured layer by layer by predicting wave-variable segments and the initial predictive element array is supplemented to obtain the biological wave-variable array. The process of obtaining bio-wave array transformation includes: Wave-variant sequences are obtained based on the predicted wave distances. Wave response coefficients are then divided into sequences using the wave-variant sequences to obtain the predicted wave-variant segments. Based on the sequence division, the obtained predicted wavelet segments are uploaded to the biological research signal, and the biological research signal is captured layer by layer through the predicted wavelet segments to obtain the biological research wavelet segments. The obtained biological research wave variant segments are uploaded to the initial prediction element array. The initial prediction element array is supplemented with elements based on the obtained biological research wave variant segments to obtain the biological wave variant array. The predicted wave bands are assembled based on the obtained predicted wave distance to obtain an updated prediction array; The automated analysis module is used to perform digital state replacement on the biological wave transformation array by updating the prediction array to obtain the updated wave transformation array, perform digital-graph conversion on the updated wave transformation array to obtain the biological wave graph, and set a moving grasping axis to capture features of the biological wave graph to obtain the identity feature segment. The service support module is used to distinguish the types of identity feature segments according to the location node interval, obtain a biometric identity type library, and filter and combine the biometric identity type library to obtain a biometric type sequence.

2. The cloud-based collaborative analysis system for biological research data according to claim 1, characterized in that, The process of acquiring biological research data by the basic acquisition module includes: Obtain cloud platform information and build a collaborative scientific research cloud platform based on the cloud platform information; Set up a virtual acquisition terminal and build a transmission link between the virtual acquisition terminal and the collaborative scientific research cloud platform; Data is collected from multiple sources of technology through a virtual acquisition terminal to obtain biological research data, which is then uploaded to the collaborative research cloud platform.

3. The cloud-based collaborative analysis system for biological research data according to claim 2, characterized in that, The process of obtaining identity feature segments includes: The obtained updated prediction matrix is ​​element-averaged to obtain the expected mean. The expected statistics of the updated prediction matrix are then performed based on the expected mean to obtain the expected prediction value. The biological wave array is subjected to a digital state change based on the expected mean and expected predicted value to obtain an updated wave array. The updated wave array is then subjected to a digital-graph conversion to obtain a biological wave graph. Set a moving capture axis, upload the moving capture axis to the Life Science Wave Map, and capture features of the Life Science Wave Map through the moving capture axis to obtain identity feature segments; The biological science fluctuation graph is marked with intervals based on the identity feature segments to obtain the position node intervals.

4. The cloud-based collaborative analysis system for biological research data according to claim 3, characterized in that, The process of performing numerical state transformation on the bio-wave array based on the expected mean and expected predicted value includes: The mean of each column of the biological wave array is obtained by dividing the mean of the biological column. Based on the obtained biological column mean, expected mean, and expected predicted value, the biological wave array is permuted to obtain the permuted waveband value; Replace the elements at the original positions of the biowave array with the obtained permutation band values ​​to obtain permutation bands, until all elements in the biowave array are replaced with permutation bands, and mark the biowave array after element replacement as the updated wave array.

5. The cloud-based collaborative analysis system for biological research data according to claim 4, characterized in that, The process of classifying identity feature segments based on location node intervals includes: Select any segment of the biomolecular wave pattern as the identification segment, obtain the position node interval corresponding to the identification segment as the identification node interval, and identify the biological wave curve segment corresponding to the identification node interval in the remaining biomolecular wave patterns as the matching wave curve segment. The obtained comparison identity segment and the matching waveform segment are similarly matched to obtain the matching waveform segment. A biometric identity type library is constructed, and the comparison identity segment and the matching waveform segment corresponding to the comparison identity segment are uploaded to the biometric identity type library. Select any one of the remaining identity feature segments and denote it as the comparison identity segment. Repeat the process of obtaining the biometric identity type library corresponding to the comparison identity segment until all identity feature segments have a corresponding biometric identity type library.

6. The cloud-based collaborative analysis system for biological research data according to claim 5, characterized in that, The process of filtering and combining biometric identity type databases includes: Perform time-based filtering on the biometric identity type database to obtain the initial identity segment, and mark the biometric identity type database corresponding to the initial identity segment as the initial type database; Based on the initial identity segment, time matching is performed on the remaining biometric identity type library to obtain the continued identity segment. The corresponding biometric identity type library is then obtained and denoted as the continued type library. After removing the initial type library and the continued type library, time matching is performed on the remaining biometric identity type library. The process of obtaining the continued identity segment is repeated until all biometric identity type libraries have been time matched. The starting identity segment and the continuing identity segment are combined in the order of time matching to obtain a biological data sequence. The biological data sequence is then replaced with the corresponding biological identity type according to the biological identity type library to obtain a biological type sequence.

Images