Data processing method and related device, storage medium and computer program product

Abstract

The embodiment of the invention discloses a data processing method, a related device, a storage medium and a computer program product, and the data processing method applied to a cloud server comprises the steps: carrying out the gait data region segmentation of an original gait data set at a set segmentation scale based on the static physical sign of a human body; the original gait data set comprises gait data of healthy people; performing representative value replacement processing on each gait data area in the original gait data set to generate a replacement gait data set corresponding to the original gait data set; performing crowd gait portrait clustering on the original gait data set and the replacement gait data set, and determining a clustering effect index of a clustering result; and pushing the segmentation scale and clustering effect indexes of respective clustering results of the original gait data set and the replacement gait data set to a body area network node so as to select a clustering result for evaluating the fusion gait information of the monitored object by the donor area network node.

Description

Technical Field

[0001] This application relates to the field of data service technology, and in particular to a data processing method and related apparatus, storage medium, and computer program product. Background Technology

[0002] With the development of standby time, accuracy and computing power based on wearable systems, it is gradually becoming possible to realize real-time digital twins of human vital signs in all scenarios such as home and office, which requires the establishment of standard templates for dynamic user profiles of healthy people.

[0003] Currently, while massive amounts of real-time data bring accuracy to digital twins of people, they also pose challenges to the user profiling needs of follow-up systems for hospitals. If data processing is too coarse, it is not suitable for the characteristics of the health indicators industry; if it is comprehensive, cautious, and detailed, it is too difficult, consumes too many resources, and does not conform to the actual application environment. Summary of the Invention

[0004] This application provides a data processing method and related apparatus, storage medium, and computer program product. Considering the different requirements for clustering accuracy, it not only adopts a coarse-grained representation method for clustering healthy people to achieve rapid convergence and save resources, but also makes the clustering effect indicators achieved by clustering open, so as to realize on-demand selection and application.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a data processing method applied to a cloud server, the method comprising:

[0007] Based on static human physical characteristics, the original gait dataset is segmented into gait data regions using a set segmentation scale; the original gait dataset contains gait data of healthy individuals.

[0008] The representative value is replaced for each gait data region in the original gait dataset to generate a replaced gait dataset corresponding to the original gait dataset;

[0009] The original gait dataset and the replacement gait dataset are respectively subjected to gait profile clustering, and the clustering effect index of the clustering results is determined.

[0010] The segmentation scale, as well as the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset, are pushed to the body area network node so that the body area network node can select the clustering result for evaluating the fused gait information of the monitored object.

[0011] In the above method, the step of performing representative value replacement processing on each gait data region in the original gait dataset to obtain the replaced gait dataset corresponding to the original gait dataset includes:

[0012] For each gait data region in the original gait dataset, determine the representative value corresponding to the included gait data;

[0013] The gait data contained in each gait data region of the original gait dataset is replaced with the corresponding representative value to generate the replaced gait dataset.

[0014] In the above method, the step of performing crowd gait profile clustering on the original gait dataset and the replaced gait dataset respectively, and determining the clustering effect index of the clustering results, includes:

[0015] The original gait dataset and the replaced gait dataset are respectively input into the crowd gait profile clustering model for clustering to obtain their respective clustering results;

[0016] For the clustering results of the original gait dataset and the replacement gait dataset, the corresponding intra-cluster compactness index and inter-cluster separation index are determined respectively, and the clustering effect index is determined based on the corresponding intra-cluster compactness index and inter-cluster separation index.

[0017] The above method also includes:

[0018] The system receives the fused gait information and indication information sent by the body area network node; the indication information is used to indicate the clustering results used to evaluate the fused gait information.

[0019] The clustering results indicated by the aforementioned indication information are invoked to evaluate whether the fused gait information is abnormal.

[0020] This application provides a data processing method applied to a body area network node, the method comprising:

[0021] Based on the segmentation scale sent by the cloud server, and the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset, the clustering result used to evaluate the fused gait information of the monitored object is selected.

[0022] The replacement gait dataset is generated by segmenting the original gait dataset into gait data regions based on the static physical characteristics of the human body using the segmentation scale, and then replacing the representative value of each gait data region.

[0023] The above method also includes:

[0024] The fused gait information and indication information are sent to the cloud server; the indication information is used to indicate the clustering results used to evaluate the fused gait information.

[0025] The above method also includes:

[0026] The monitoring object acquires various dynamic feature parameters and various gait feature parameters; wherein, each dynamic feature parameter contains dynamic data of the monitoring object under a dynamic index, and each gait feature parameter contains gait data of the monitoring object under a gait index.

[0027] Based on the correlation between each dynamic feature parameter and different gait feature parameters, N key gait feature parameters of the monitored object are selected; N is a natural number greater than or equal to 1.

[0028] The fused gait information is generated based on the N gait feature parameters.

[0029] In the above method, the selection of N key gait characteristic parameters of the monitored object based on the correlation between each dynamic characteristic parameter and different gait characteristic parameters includes:

[0030] For each dynamic feature parameter, the correlation coefficient between it and different time-state feature parameters is calculated, and the mean of the calculated correlation coefficients is determined as the corresponding correlation index.

[0031] The dynamic characteristic parameter with the largest corresponding relevant indicator is determined as the most relevant parameter;

[0032] Each gait feature parameter whose correlation coefficient with the most relevant parameter is greater than a threshold is selected to obtain the N gait feature parameters.

[0033] In the above method, generating the fused gait information based on the N gait feature parameters includes:

[0034] After converting the N gait feature parameters into fusion weight coefficients, normalization is performed to obtain N fusion weight coefficients corresponding to the N gait feature parameters.

[0035] The sum of the N fusion weight coefficients is determined as the fusion gait information.

[0036] This application provides a cloud server, including: a first processor, a first memory, and a first communication bus;

[0037] The first communication bus is used to establish a communication connection between the first processor and the first memory;

[0038] The first processor is configured to execute one or more computer programs stored in the first memory to implement a data processing method applied to a cloud server.

[0039] This application provides a body area network node, including: a second processor, a second memory, and a second communication bus;

[0040] The second communication bus is used to establish a communication connection between the second processor and the second memory;

[0041] The second processor is configured to execute one or more computer programs stored in the second memory to implement a data processing method applied to a body area network node.

[0042] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements steps in a data processing method applied to a cloud server, or steps in a data processing method applied to a body area network node.

[0043] This application provides a computer program product, including a computer program that, when executed by a processor, implements steps in a data processing method applied to a cloud server, or steps in a data processing method applied to a body area network node.

[0044] This application provides a data processing method and related apparatus, storage medium, and computer program product. The method, applied to a cloud server, includes: segmenting an original gait dataset into gait data regions based on static human physical characteristics using a set segmentation scale; the original gait dataset contains gait data of healthy individuals; performing representative value replacement processing on each gait data region in the original gait dataset to generate a replacement gait dataset corresponding to the original gait dataset; performing gait profile clustering on the original gait dataset and the replacement gait dataset respectively, and determining the clustering effect index of the clustering results; pushing the segmentation scale and the clustering effect index of the original gait dataset and the replacement gait dataset to body area network nodes, allowing the body area network nodes to select the clustering result for evaluating the fused gait information of the monitored object. The technical solution provided in this application, considering different clustering accuracy requirements, not only adopts a coarse-grained representative replacement method for clustering healthy individuals to achieve rapid convergence and save resources, but also makes the clustering effect index available, enabling on-demand selection and application. Attached Figure Description

[0045] Figure 1 A schematic diagram illustrating an exemplary stage of hospital-oriented clustering capabilities provided in this application embodiment;

[0046] Figure 2 A schematic diagram of an exemplary body area network architecture provided for embodiments of this application;

[0047] Figure 3 A schematic diagram illustrating an exemplary gait index provided in an embodiment of this application;

[0048] Figure 4 A flowchart illustrating a data processing method provided in this application embodiment. Figure 1 ;

[0049] Figure 5 A flowchart illustrating a data processing method provided in this application embodiment. Figure 2 ;

[0050] Figure 6 A schematic diagram of the structure of a cloud server provided in this application embodiment. Figure 1 ;

[0051] Figure 7 A schematic diagram of the structure of a cloud server provided in this application embodiment. Figure 2 ;

[0052] Figure 8 A schematic diagram of the structure of a body area network node provided in this application embodiment. Figure 1 ;

[0053] Figure 9 A schematic diagram of the structure of a body area network node provided in this application embodiment. Figure 2 . Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below through embodiments and in conjunction with the accompanying drawings. The embodiments below can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0056] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0057] This application provides a data processing method applied to a cloud server and a body area network node. In this application's embodiments, the cloud server can support clustering implementation in a hospital setting, such as... Figure 1 As shown, there is a need for gait profiling and clustering in hospital settings. Body area network nodes are responsible for aggregating various types of data, such as... Figure 2 As shown, a large amount of data is involved. Taking gait as an example, through processes such as sensor calibration, preprocessing, feature extraction, coordinate system transformation, and posture calculation, gait data for 164 gait indices can be calculated, such as... Figure 3 As shown below, the data processing method provided in the embodiments of this application will be described in detail from the perspectives of cloud servers and other aspects.

[0058] This application provides a data processing method implemented through a cloud server. Figure 4 A flowchart illustrating a data processing method provided in this application embodiment. Figure 1 .like Figure 4 As shown in the embodiments of this application, the data processing method applied to the cloud server mainly includes the following steps:

[0059] S101. Based on static human physical characteristics, segment the gait data region of the original gait dataset using a set segmentation scale; the original gait dataset contains gait data of healthy individuals.

[0060] In the embodiments of this application, the cloud server performs gait data region segmentation on the original gait dataset based on static human physical characteristics and a set segmentation scale.

[0061] It should be noted that, in the embodiments of this application, the data in the original gait dataset is the gait data of healthy people. Healthy people may include people who are physically healthy in terms of static physical characteristics such as gender, age, and height. This embodiment of the application does not limit this.

[0062] It should be noted that, in the embodiments of this application, the cloud server can first divide the dataset into two parts according to gender, and then divide the value range of static physical characteristics such as age, height and weight into K equal parts according to the set segmentation scale K, thereby segmenting the data in the original gait dataset, segmenting the gait data region, and the values ​​of human static features corresponding to the data in the same gait data region are in the same range.

[0063] It should be noted that, in the embodiments of this application, the segmentation scale can be set by the user, and there can be multiple scales. That is, the cloud server can segment the original gait dataset with different segmentation scales and perform subsequent steps respectively.

[0064] S102. Perform representative value replacement processing on each gait data region in the original gait dataset to generate a replacement gait dataset corresponding to the original gait dataset.

[0065] In the embodiments of this application, after the cloud server performs gait data region segmentation on the original gait dataset, it can perform representative value replacement processing on each gait data region in the original gait dataset to generate a replacement gait dataset corresponding to the original gait dataset.

[0066] In the embodiments of this application, the cloud server performs representative value replacement processing on each gait data region in the original gait dataset to obtain a replacement gait dataset corresponding to the original gait dataset, including: determining the representative value corresponding to the gait data contained in each gait data region in the original gait dataset; replacing the gait data contained in each gait data region in the original gait dataset with the corresponding representative value to generate a replacement gait dataset.

[0067] It should be noted that, in the embodiments of this application, for each gait data region, the mean value of the gait data contained therein can be determined as the corresponding representative value. Of course, other methods can also be used to determine it, and this embodiment of the application does not limit it.

[0068] It is understood that, in the embodiments of this application, for each gait data region in the original gait dataset, the cloud server can replace the representative value of the gait data contained therein, and the replaced gait data regions constitute the replaced gait dataset.

[0069] It should be noted that, in the embodiments of this application, the representative value replacement process can avoid the impact of individual differences and abnormal data on data processing, thereby improving robustness.

[0070] S103. Perform population gait profile clustering on the original gait dataset and the replacement gait dataset respectively, and determine the clustering effect index of the clustering results.

[0071] In the embodiments of this application, after the cloud server performs the representative value replacement process, it further performs crowd gait profile clustering on the original gait dataset and the replaced gait dataset respectively, and determines the clustering effect index of the clustering results.

[0072] In the embodiments of this application, the cloud server performs crowd gait profile clustering on the original gait dataset and the alternative gait dataset respectively and determines the clustering effect index of the clustering results, including: inputting the original gait dataset and the alternative gait dataset into the crowd gait profile clustering model respectively for clustering to obtain their respective clustering results; determining the corresponding intra-cluster compactness index and inter-cluster separation index for the respective clustering results of the original gait dataset and the alternative gait dataset, and determining the clustering effect index based on the corresponding intra-cluster compactness index and inter-cluster separation index.

[0073] It should be noted that, in the embodiments of this application, the clustering algorithm used in the crowd gait profile clustering model can specifically be the K-means (K-Means) clustering algorithm. The specific crowd profile clustering model is not limited in the embodiments of this application.

[0074] In the embodiments of this application, intra-cluster compactness can be evaluated for the clustering results of the original gait dataset and the replacement gait dataset. For the clustering results of the original gait dataset and the replacement gait dataset, the corresponding intra-cluster compactness index can include the average distance from the data contained in each cluster to the cluster center of that cluster. Specifically, σ i σ is the average distance from the data in the i-th cluster to the cluster center of that cluster. i The calculation method is shown in formula (1):

[0075]

[0076] Among them, C i d(x, c) represents the data points contained in the i-th cluster. i ) is the cluster center c from data point x in the i-th cluster to the i-th cluster. i The distance.

[0077] In the embodiments of this application, the inter-class separation degree can be evaluated on the clustering results of the original gait dataset and the replacement gait dataset. The inter-class separation degree index can include the distance between cluster centers within different clusters in the clustering results, d(c i c j ) represents the distance between the cluster centers of the i-th cluster and the j-th cluster in the clustering results, d(c i c j The calculation method is shown in the following formula (2):

[0078] d(c i c j )=||c i -c j || (2)

[0079] Among them, c i Let c be the cluster center of the i-th cluster. j Let be the cluster center of the j-th cluster.

[0080] In the embodiments of this application, for the clustering results of the original gait dataset and the replacement gait dataset, the clustering effect index can be determined based on the corresponding intra-cluster compactness index and inter-cluster separation index. Specifically, the Davies-Bouldin index (DBI) can be calculated as the clustering effect index, and the calculation method is shown in the following formula (3):

[0081]

[0082] The lower the DBI value, the better the clustering effect.

[0083] It should be noted that, in the embodiments of this application, for the clustering results of the original gait dataset and the replacement gait dataset, the cloud server can use the above formulas (1)-(3) to perform calculations to determine the clustering effect index.

[0084] S104. Push the segmentation scale, as well as the clustering effect index of the original gait dataset and the replacement gait dataset, to the body area network node so that the body area network node can select the clustering result for evaluating the fused gait information of the monitored object.

[0085] In the embodiments of this application, the cloud server can push the segmentation scale, as well as the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset, to the body area network node.

[0086] It should be noted that in the embodiments of this application, there can be multiple segmentation scales. The cloud server can segment the gait data region using different segmentation scales and sequentially implement representative value replacement, clustering, and clustering effect evaluation according to the above steps. Based on this, there can be multiple replacement gait datasets, each of which can have its own clustering effect index and push it to the body area network results. This application embodiment does not limit this.

[0087] It should be noted that, in the embodiments of this application, the various information pushed can be presented in the form of visual lines or directly in the form of data, and this embodiment of the application does not limit the specific presentation.

[0088] It should be noted that, in the embodiments of this application, the cloud server pushes the segmentation scale and the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset to the body area network node. This information represents the clustering effect of clustering the gait profile of the population under different segmentation scales. Using this as reference information, the clustering result of actual needs can be selected as the evaluation basis for the fusion of gait information of the monitoring object. In addition, it can also be used as a reference for tiered pricing.

[0089] In embodiments of this application, the cloud server may further perform the following steps: receiving fused gait information and indication information sent by a body area network node; the indication information is used to indicate the clustering results used to evaluate the fused gait information; and the clustering results indicated by the indication information are invoked to evaluate whether the fused gait information is abnormal.

[0090] It should be noted that, in the embodiments of this application, the indication information may be the clustering effect index of the clustering results, and the corresponding segmentation scale used.

[0091] It is understood that, in the embodiments of this application, the body area network node can indicate to the cloud server the selected clustering result for evaluating the fused gait information, as well as the specific fused gait information. Since the data used for clustering is the gait data of healthy people, the clustering achieved is a gait profile clustering of the population. In fact, it clusters the gait data of healthy people with similar human static characteristics into one category. Based on this, the cloud server uses the gait data of healthy people with similar human static characteristics to the monitored object in the indicated clustering result to determine the normal value range of the corresponding fused gait information, which is used to evaluate the fused gait information of a specific monitored object and determine whether the monitored object is healthy.

[0092] It should be noted that, in the embodiments of this application, the cloud server can be divided into a cloud application server and a cloud analysis server. Steps S101, S102 and S104 can be executed on the cloud application server, and step S103 can be executed on the cloud analysis server.

[0093] This application provides a data processing method applied to a body area network node. Figure 5 A flowchart illustrating a data processing method provided in this application embodiment. Figure 2 .like Figure 5 As shown in the embodiments of this application, the data processing method applied to a body area network node mainly includes the following steps:

[0094] S201. Based on the segmentation scale sent by the cloud server and the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset, select the clustering result used to evaluate the fused gait information of the monitored object.

[0095] The replacement gait dataset is generated by segmenting the original gait dataset into gait data regions based on static human physical characteristics and replacing the representative value of each gait data region.

[0096] In the embodiments of this application, corresponding to the method applied to the cloud server described above, the body area network node can select the clustering result for evaluating the fused gait information of the monitored object based on the information sent by the cloud server.

[0097] In the embodiments of this application, users can view the segmentation scale and clustering effect index through body area network nodes according to actual needs. Through human-computer interaction, the body area network nodes can select the clustering result for evaluating the fused gait information of the monitored object, send the fused gait information and indication information to the cloud server, and enable the cloud server to call the clustering result indicated by the indication information to evaluate whether the fused gait information is abnormal. The indication information is used to indicate the clustering result for evaluating the fused gait information. The indication information can be the clustering effect index of the clustering result and the corresponding segmentation scale used.

[0098] In the embodiments of this application, the body area network node needs to determine the fused gait information of the monitored object and send it to the cloud server for evaluation. The implementation method of the body area network node determining the fused gait information is described in detail below.

[0099] In the embodiments of this application, a body area network node can perform the following steps to determine the fused gait information of the monitored object: acquiring various dynamic feature parameters and various gait feature parameters of the monitored object; wherein, each dynamic feature parameter contains dynamic data of the monitored object under a dynamic index, and each gait feature parameter contains gait data of the monitored object under a gait index; selecting N key gait feature parameters of the monitored object based on the correlation between each dynamic feature parameter and different gait feature parameters; N is a natural number greater than or equal to 1; and generating fused gait information based on the N gait feature parameters.

[0100] In the embodiments of this application, the body area network node selects N key gait feature parameters of the monitored object based on the correlation between each dynamic feature parameter and different gait feature parameters. This includes: calculating the correlation coefficient between each dynamic feature parameter and different gait feature parameters, and determining the mean of the calculated correlation coefficients as the corresponding correlation index; determining the dynamic feature parameter with the largest corresponding correlation index as the most relevant parameter; and selecting each gait feature parameter whose correlation coefficient with the most relevant parameter is greater than a threshold, thus obtaining N gait feature parameters.

[0101] In the embodiments of this application, the body area network node can calculate the correlation coefficient between the dynamic feature parameters and the gait feature parameters according to the following formula (4):

[0102]

[0103] Among them, X i,k Y is the k-th dynamic data of the i-th dynamic feature parameter. j,k For the k-th gait data of the j-th gait feature parameter, Let be the average value of the i-th dynamic feature parameter. Let r be the average value of the j-th gait feature parameter, N be the number of data points, and r be the average value of the j-th gait feature parameter.i,j Let be the correlation coefficient between the i-th dynamic feature parameter and the j-th gait feature parameter.

[0104] In the embodiments of this application, the body area network node calculates the average correlation coefficient between each dynamic feature parameter and each gait feature parameter, as shown in the following formula (5), thereby selecting the dynamic feature parameter with the largest correlation coefficient as the most relevant parameter:

[0105]

[0106] Where L is the number of gait feature parameters. Let be the average of the correlation coefficients between the i-th dynamic feature parameter and each of the gait feature parameters.

[0107] In the embodiments of this application, the most relevant parameter is a dynamic feature parameter. In the process of determining the most relevant parameter, the body area network node has calculated the correlation coefficient between each dynamic feature parameter and different gait feature parameters. Based on this, the body area network node can select gait feature parameters whose correlation coefficient with the most relevant parameter is greater than a threshold for subsequent data processing. The threshold for selecting gait feature parameters can be 0.5. Of course, it can also be set to other values ​​according to actual needs and application scenarios. This application embodiment does not limit this.

[0108] In the embodiments of this application, generating fused gait information based on N gait feature parameters includes: converting the N gait feature parameters into fusion weight coefficients and then performing normalization processing to obtain N fusion weight coefficients corresponding to the N gait feature parameters; and determining the sum of the N fusion weight coefficients as the fused gait information.

[0109] In the embodiments of this application, the body area network node normalizes the converted fusion weight coefficients, standardizing their numerical range to the [0,1] interval, as shown in the following formula (6):

[0110]

[0111] Where 2logM is The maximum value, is the normalized fusion weight coefficient for the m-th gait feature parameter.

[0112] In the embodiments of this application, the body area network node adds up the N fusion weight coefficients corresponding to the N gait feature parameters to obtain the fused gait information Score, as shown in the following formula (7):

[0113]

[0114] In the embodiments of this application, the body area network node can also set an update trigger mechanism for the crowd gait profile clustering model for the cloud server.

[0115] In the embodiments of this application, the body area network node can continuously store the gait data, dynamic and static data, etc. of the monitored object, and set a model update trigger mechanism to save the newly added data to the database and perform statistics on the newly added data. When the number threshold is reached, the model update mechanism is triggered to send the newly added data to the cloud server for real-time optimization of the crowd gait profile clustering model, thereby continuously reducing the prediction error and the actual error.

[0116] It is understood that in the embodiments of this application, when the amount of newly added data reaches a certain amount, the cloud model update mechanism is activated, and the crowd gait profile clustering model and the deep learning-based error correction algorithm are retrained using all existing datasets to optimize the algorithm. As the amount of data increases, the crowd gait profile is made more refined through iteration, and the model prediction error is continuously reduced.

[0117] Based on the data processing methods applied to cloud servers and body area network nodes described above, the technical solution provided in this application, compared to traditional statistical methods, eliminates the influence of factors that lack statistical concentration, more comprehensively reflects the impact of diseases, and also saves computing resources. Combined with the data capabilities of future mobile network operators, it assists medical researchers in determining dynamic vital sign health boundaries, taking into account the large number and dynamic nature of dynamic profile parameters. On the one hand, the model uses a coarse-grained approach to represent healthy population profiles from the cloud, achieving faster module convergence and avoiding excessive consumption of computing resources. On the other hand, the fine-grained, on-demand fusion method used in body area network nodes balances accuracy while avoiding excessive consumption of computing resources.

[0118] This application provides a cloud server. Figure 6 A schematic diagram of the structure of a cloud server provided in this application embodiment. Figure 1 .like Figure 6 As shown in the embodiments of this application, the cloud server includes:

[0119] The first processing module 301 is used to segment the original gait dataset into gait data regions based on static human physical characteristics and a set segmentation scale; the original gait dataset contains gait data of healthy people; representative value replacement processing is performed on each gait data region in the original gait dataset to generate a replacement gait dataset corresponding to the original gait dataset; population gait profile clustering is performed on the original gait dataset and the replacement gait dataset respectively, and the clustering effect index of the clustering results is determined;

[0120] The first communication module 302 is used to push the segmentation scale, as well as the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset, to the body area network node, so that the body area network node can select the clustering result for evaluating the fused gait information of the monitored object.

[0121] In one embodiment of this application, the first processing module 301 is configured to determine the representative value corresponding to the gait data contained in each gait data region in the original gait dataset; and replace the gait data contained in each gait data region in the original gait dataset with the corresponding representative value to generate the replaced gait dataset.

[0122] In one embodiment of this application, the first processing module 301 is used to input the original gait dataset and the alternative gait dataset into a crowd gait profile clustering model for clustering to obtain their respective clustering results; for the respective clustering results of the original gait dataset and the alternative gait dataset, the corresponding intra-class compactness index and inter-class separation index are determined respectively, and the clustering effect index is determined based on the corresponding intra-class compactness index and inter-class separation index.

[0123] In one embodiment of this application, the first communication module 302 is further configured to receive the fused gait information and indication information sent by the body area network node; the indication information is used to indicate the clustering result for evaluating the fused gait information; the first processing module 301 is further configured to call the clustering result indicated by the indication information to evaluate whether the fused gait information is abnormal.

[0124] Figure 7 A schematic diagram of the structure of a cloud server provided in this application embodiment. Figure 2 .like Figure 7 As shown, it includes: a first processor 401, a first memory 402, and a first communication bus 403;

[0125] The first communication bus 403 is used to realize the communication connection between the first processor 401 and the first memory 402;

[0126] The first processor 401 is configured to execute one or more computer programs stored in the first memory 402 to implement a data processing method applied to a cloud server.

[0127] This application provides a body area network node. Figure 8 A schematic diagram of the structure of a body area network node provided in this application embodiment. Figure 1 .like Figure 8 As shown in the embodiments of this application, the body area network node includes:

[0128] The second processing module 501 is used to select a clustering result for evaluating the fused gait information of the monitored object based on the segmentation scale sent by the cloud server and the clustering effect index of the clustering results of the original gait dataset and the replacement gait dataset.

[0129] The replacement gait dataset is generated by segmenting the original gait dataset into gait data regions based on the static physical characteristics of the human body using the segmentation scale, and then replacing the representative value of each gait data region.

[0130] In one embodiment of this application, the body area network node further includes a second communication module 502, used to send the fused gait information and indication information to the cloud server; the indication information is used to indicate the clustering results used to evaluate the fused gait information.

[0131] In one embodiment of this application, the second processing module 501 is further configured to acquire various dynamic feature parameters and various gait feature parameters of the monitored object; wherein, each dynamic feature parameter contains dynamic data of the monitored object under a dynamic index, and each gait feature parameter contains gait data of the monitored object under a gait index; based on the correlation between each dynamic feature parameter and different gait feature parameters, N key gait feature parameters of the monitored object are selected; N is a natural number greater than or equal to 1; and the fused gait information is generated based on the N gait feature parameters.

[0132] In one embodiment of this application, the second processing module 501 is further configured to calculate the correlation coefficient between each dynamic feature parameter and different gait feature parameters, and determine the mean of the calculated correlation coefficients as the corresponding correlation index; determine the dynamic feature parameter with the largest corresponding correlation index as the most relevant parameter; select each gait feature parameter whose correlation coefficient with the most relevant parameter is greater than a threshold, and obtain the N gait feature parameters.

[0133] In one embodiment of this application, the second processing module 501 is further configured to convert the N gait feature parameters into fusion weight coefficients and then perform normalization processing to obtain N fusion weight coefficients corresponding to the N gait feature parameters; and to determine the sum of the N fusion weight coefficients as the fused gait information.

[0134] Figure 9 A schematic diagram of the structure of a body area network node provided in this application embodiment. Figure 2 .like Figure 9 As shown in the embodiments of this application, the body area network node includes: a second processor 601, a second memory 602, and a second communication bus 603;

[0135] The second communication bus 603 is used to realize the communication connection between the second processor 601 and the second memory 602;

[0136] The second processor 601 is used to execute one or more computer programs stored in the second memory 602 to implement a data processing method applied to a body area network node.

[0137] This application provides a computer program product, including a computer program that, when executed by a processor, implements steps in a data processing method applied to a cloud server, or steps in a data processing method applied to a body area network node.

[0138] This application provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements steps in a data processing method applied to a cloud server, or steps in a data processing method applied to a body area network node. The computer-readable storage medium can be volatile memory, such as random-access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or it can be a device including one or any combination of the above-mentioned memories, such as a mobile phone, computer, tablet device, personal digital assistant, etc.

[0139] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0140] This application is described with reference to schematic and / or block diagrams of implementations of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the schematic and / or block diagrams can be implemented by computer program instructions, and combinations of blocks in the schematic and / or block diagrams can be implemented. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the schematic and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0141] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in the implementation flow diagram. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0142] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0143] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A data processing method, characterized by, Applied to a cloud server, the method comprises: Based on the static signs of the human body, the original gait data set is segmented into gait data regions at a set segmentation scale; the original gait data set contains gait data of healthy people; The representative value replacement processing is performed on each gait data region in the original gait data set to generate a replacement gait data set corresponding to the original gait data set; The original gait data set and the replacement gait data set are respectively clustered to determine the clustering effect indicators of the clustering results. The segmentation scale, and the clustering effect indicators of the clustering results of the original gait data set and the replacement gait data set are pushed to a body area network node, so that the body area network node selects the clustering result used for evaluating the fusion gait information of the monitoring object.

2. The method of claim 1, wherein, The representative value replacement processing is performed on each gait data region in the original gait data set to generate a replacement gait data set corresponding to the original gait data set, comprising: For each gait data region in the original gait data set, determine the representative value corresponding to the gait data contained therein; The gait data contained in each gait data region in the original gait data set is replaced by the corresponding representative value to generate the replacement gait data set.

3. The method of claim 1, wherein, The original gait data set and the replacement gait data set are respectively clustered to determine the clustering effect indicators of the clustering results, comprising: The original gait data set and the replacement gait data set are respectively input into a population gait portrait clustering model for clustering to obtain respective clustering results; For the clustering results of the original gait data set and the replacement gait data set, the respective intra-class compactness indicators and inter-class separation indicators are determined, and the clustering effect indicators are determined based on the respective intra-class compactness indicators and inter-class separation indicators.

4. The method of claim 1, wherein, The method further comprises: Receiving the fusion gait information and indication information sent by the body area network node; the indication information is used to indicate the clustering result used for evaluating the fusion gait information; Calling the clustering result indicated by the indication information to evaluate whether the fusion gait information is abnormal.

5. A data processing method, characterized by, Applied to a body area network node, the method comprises: Based on the segmentation scale sent by the cloud server, and the clustering effect indicators of the clustering results of the original gait data set and the replacement gait data set, select the clustering result used for evaluating the fusion gait information of the monitoring object; The replacement gait data set is generated by performing representative value replacement processing on each gait data region after segmenting the original gait data set into gait data regions at the segmentation scale based on the static signs of the human body.

6. The method of claim 5, wherein, The method further comprises: Sending the fusion gait information and indication information to the cloud server; the indication information is used to indicate the clustering result used for evaluating the fusion gait information.

7. The method according to claim 5 or 6, characterized in that, The method further comprises: Obtaining each dynamic feature parameter and each gait feature parameter of the monitoring object; each dynamic feature parameter contains dynamic data of the monitoring object under a dynamic indicator, and each gait feature parameter contains gait data of the monitoring object under a gait indicator; Selecting N gait feature parameters which are key to the monitoring object based on the correlation degree between each dynamic feature parameter and different gait feature parameters; N is a natural number greater than or equal to 1; Generating the fusion gait information based on the N gait feature parameters.

8. The method of claim 7, wherein, The selecting of the N gait feature parameters which are key to the monitoring object based on the correlation degree between each dynamic feature parameter and different gait feature parameters comprises: For each dynamic feature parameter, the correlation coefficient between the dynamic feature parameter and different gait feature parameters is calculated respectively, and the mean of the calculated correlation coefficients is determined as the corresponding correlation index; The dynamic feature parameter with the largest corresponding correlation index is determined as the most relevant parameter; Each gait feature parameter with a correlation coefficient greater than a threshold value with respect to the most relevant parameter is selected to obtain the N gait feature parameters.

9. The method of claim 7, wherein, The generating of the fusion gait information based on the N gait feature parameters comprises: After the N gait feature parameters are converted into fusion weight coefficients and normalized, N fusion weight coefficients corresponding to the N gait feature parameters are obtained; The sum of the N fusion weight coefficients is determined as the fusion gait information.

10. A cloud server, characterized by, It comprises: a first processor, a first memory and a first communication bus; The first communication bus is used to realize the communication connection between the first processor and the first memory; The first processor is used to execute one or more computer programs stored in the first memory to realize the data processing method in any one of claims 1-4.

11. A body area network node, characterized by It comprises: a second processor, a second memory and a second communication bus; The second communication bus is used to realize the communication connection between the second processor and the second memory; The second processor is used to execute one or more computer programs stored in the second memory to realize the data processing method in any one of claims 5-9.

12. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the data processing method in any one of claims 1-9.

13. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the data processing method in any one of claims 1-9.

Images