Human body pressure data null value analysis method and device, medium and equipment

Abstract

The invention provides a human body pressure data null value analysis method and device, a medium and equipment. The method comprises the steps of obtaining initial human body pressure data; wherein the initial human body pressure data comprises a plurality of data columns; identifying and marking null value data columns in the zero data columns; wherein the null value data column indicates that the sensor at the corresponding position does not collect the human body pressure data; inputting the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain an analysis value of the null value data column; obtaining target human body pressure data based on the analysis values of the non-zero data column, the unmarked zero data column and the null value data column; according to the method, the null value data column in the human body pressure data is automatically identified and marked, and the analysis value of the null value data column is automatically calculated by using the neural network model to supplement the missing value of the null value data column, so that the accuracy and reliability of the human body pressure test are improved.

Description

Technical Field

[0001] The present application relates to the technical field of pressure data experiments on a human body acting on a seat, and in particular to a method, device, medium and equipment for analyzing null values ​​of human body pressure data. Background Art

[0002] Physiological data analysis is an important basis for testing the comprehensive performance indicators of automotive seats. In terms of physiological data analysis, pressure sensors are widely used to monitor the pressure distribution of the human body when sitting or lying down. Pressure sensors can capture the shape and natural distribution of pressure between the human body and the contact objects, and provide important information about comfort, posture and health status. However, due to pressure sensor materials or environmental factors, some sensors may have a column of missing data (i.e. all zeros) during use, which causes an obvious null value column in the pressure matrix. The appearance of this all-zero column will appear randomly, interfering with subsequent data analysis, resulting in incorrect health assessment or posture recognition.

[0003] Existing fault detection methods usually rely on empirical rules and lack intelligent processing methods. It is difficult to effectively distinguish between all-zero columns caused by sensor failure and empty columns caused by natural pressure-free areas (such as clothing wrinkles) under normal circumstances. In addition, the empty columns with missing data can only be estimated based on experience, which makes it difficult to ensure the accuracy of the test. Therefore, a method that can accurately and objectively supplement missing data is needed. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, device, medium and equipment for analyzing null values ​​of human body pressure data.

[0005] According to one aspect of the present application, a method for analyzing null values ​​of human body pressure data is provided, comprising: obtaining initial human body pressure data; wherein the initial human body pressure data comprises a plurality of data columns, and the initial human body pressure data comprises a non-zero data column and a zero data column, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; identifying and marking null value data columns in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; inputting the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain analysis values ​​of the null value data column; and obtaining target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column.

[0006] In one embodiment, the identifying and marking of the null value data column in the zero data column includes: for each of the data columns, calculating the data sum of all its elements; if the data sum of the current data column is equal to zero, calculating the preceding data sum of the preceding data column of the current data column and the succeeding data sum of the succeeding data column; if the preceding data sum and the succeeding data sum are greater than zero, determining that the current data column is the null value data column and marking the current data column.

[0007] In one embodiment, the inputting the non-zero data column, the unlabeled zero data column and the null value data column into a neural network model to obtain the analysis value of the null value data column includes: inputting the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model in the original arrangement order to obtain the analysis value of the null value data column.

[0008] In one embodiment, the inputting the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model according to the original arrangement order to obtain the analysis value of the null value data column comprises: based on the first j data value, and analyze to obtain the first j analysis values; among them, j is a positive integer that is less than or equal to the number of rows in the null value data column.

[0009] In one embodiment, the step of inputting the non-zero data column, the unlabeled zero data column and the null value data column into a neural network model in the original arrangement order to obtain the analysis value of the null value data column also includes: correcting multiple analysis values ​​of the null value data column based on the relative relationship between each data value in the non-zero data column and the unlabeled zero data column.

[0010] In one embodiment, the initial human body pressure data includes multiple frames of pressure data; wherein, the analysis method of null values ​​of the human body pressure data also includes: for the null value data column in the current frame pressure data, obtaining multiple frames of pressure data adjacent to the current frame; if there is a non-zero data column in the data column corresponding to the null value data column of the current frame pressure data in the multiple frames of pressure data adjacent to the current frame, then verifying the analysis value of the null value data column of the current frame pressure data based on the non-zero data column.

[0011] In one embodiment, the verification of the analysis value of the null-value data column of the current frame pressure data based on the non-zero data column includes: calculating the estimated value of the null-value data column of the current frame pressure data based on the pressure data where the non-zero data column is located and the current frame pressure data; calculating the variance between the estimated value and the analysis value of the null-value data column of the current frame pressure data; if the variance is less than a preset value, determining that the analysis value of the null-value data column of the current frame pressure data has been verified to be qualified.

[0012] According to another aspect of the present application, a device for analyzing null values ​​of human body pressure data is provided, comprising: a data acquisition module, used to acquire initial human body pressure data; wherein the initial human body pressure data comprises a plurality of data columns, and the initial human body pressure data comprises a non-zero data column and a zero data column, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are all zero; a null value recognition module, used to identify and mark the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; a null value analysis module, used to input the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain analysis values ​​of the null value data column; and a result determination module, used to obtain target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above methods.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the above-described methods.

[0015] The present application provides a method, device, medium and equipment for analyzing null values ​​of human body pressure data, which obtains initial human body pressure data; wherein the initial human body pressure data includes multiple data columns, and the initial human body pressure data includes non-zero data columns and zero data columns, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; identifies and marks the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; inputs the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain the analysis value of the null value data column; based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column, obtains the target human body pressure data; the present application automatically identifies and marks the null value data column in the human body pressure data, and uses the neural network model to automatically calculate the analysis value of the null value data column to supplement the missing value of the null value data column, thereby improving the accuracy and reliability of human body pressure testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flowchart of a method for analyzing null values ​​of human body pressure data provided by an exemplary embodiment of the present application.

[0018] Figure 2 It is a logical diagram of analyzing value calculation of a null value data column provided by an exemplary embodiment of the present application.

[0019] Figure 3 It is a structural schematic diagram of a device for analyzing null values ​​of human body pressure data provided by an exemplary embodiment of the present application.

[0020] Figure 4 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0022] Figure 1 FIG. 1 is a flow chart of a method for analyzing null values ​​of human body pressure data provided by an exemplary embodiment of the present application. Figure 1As shown, the analysis method of the null value of human body pressure data includes the following steps: Step 110: Acquire initial human body pressure data.

[0023] The initial human body pressure data includes multiple data columns, and the initial human body pressure data includes non-zero data columns and zero data columns, and the zero data column indicates that the human body pressure data collected at all corresponding collection points are zero. The present application arranges multiple pressure sensors on the seat to collect the pressure distribution of the human body in a sitting or lying position in real time, wherein the pressure sensors are distributed on the seat in a matrix, and the collected pressure data is also matrix data, that is, it contains multiple rows and columns of data values, wherein the pressure data corresponding to the point where the pressure value is collected is greater than zero, and the pressure data corresponding to the point where the pressure value is not collected is zero.

[0024] Step 120: Identify and mark the null value data columns in the zero data columns.

[0025] Among them, the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data. The present application identifies the null value data column in the zero data column to distinguish the data column in the zero data column due to abnormal pressure sensor collection, that is, to obtain the null value data column with missing data, thereby excluding the zero data column with real data of zero, thereby improving the accuracy of data testing.

[0026] Step 130: Input the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model to obtain the analysis value of the null value data column.

[0027] The present application obtains a neural network model through training, and based on the relevant associations between various data columns, non-zero data columns, unlabeled zero data columns and null value data columns are input into the neural network model, and the analysis values ​​of the null value data columns are obtained by self-analysis. The missing data of the null value data columns are obtained by accurately analyzing the associations between various data columns, which can reduce the uncertainty of human estimation to improve the accuracy of data testing.

[0028] Step 140: Obtain target human body pressure data based on the analysis values ​​of the non-zero data column, the unlabeled zero data column, and the null value data column.

[0029] After analyzing and obtaining the analysis value of the null value data column, the present application combines the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column to obtain the target human body pressure data, thereby realizing the test of the pressure data of the human body on the seat.

[0030] The present application provides a method for analyzing null values ​​of human body pressure data, which comprises obtaining initial human body pressure data; wherein the initial human body pressure data comprises a plurality of data columns, and the initial human body pressure data comprises a non-zero data column and a zero data column, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are all zero; identifying and marking the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; inputting the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain the analysis value of the null value data column; obtaining the target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column; the present application improves the accuracy and reliability of human body pressure testing by automatically identifying and marking the null value data column in the human body pressure data, and using the neural network model to automatically calculate the analysis value of the null value data column to supplement the missing value of the null value data column.

[0031] In one embodiment, the specific implementation method of the above step 120 may be: for each data column, calculate the data sum of all its elements; if the data sum of the current data column is equal to zero, calculate the preceding data sum of the preceding data column of the current data column and the succeeding data sum of the succeeding data column; if the preceding data sum and the succeeding data sum are greater than zero, determine that the current data column is a null value data column and mark the current data column.

[0032] The present application calculates the data sum of all elements in each data column and determines whether the data sum is equal to zero. If it is equal to zero, it means that the data column is a zero data column. If it is not equal to zero, it means that the data column is not a zero data column. It should be understood that the present application can set a smaller threshold and record the data sum less than the threshold as equal to zero to improve the generalization ability of data. After determining that a zero data column is obtained, the data sum of the preceding data column and the subsequent data column of the zero data column is calculated. If the preceding data sum of the preceding data column and the subsequent data sum of the subsequent data column are both greater than zero (i.e., a non-zero data column), it means that both sides of the zero data column (current data column) are non-zero data columns. Based on the continuity of human body pressure, the current data column is a null value data column. Furthermore, if one side of the current data column is a non-zero data column and the other side is a zero data column, the zero data column on the other side is further judged. If there is a non-zero data column on the side of the zero data column on the other side away from the current data column, it is determined that the current data column and the zero data column on the other side are both null value data columns. If there is no non-zero data column on the side of the zero data column on the other side away from the current data column, it is determined that the data of the current data column and the zero data column on the other side are both zero (i.e., not a null value data column).

[0033] In one embodiment, the specific implementation of the above step 130 may be: inputting the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model according to the original arrangement order to obtain the analysis value of the null value data column.

[0034] This application uses a large number of normal pressure value matrices (including multiple continuous pressure data columns, and all pressure data columns are not null value data columns) as training samples to train the neural network model to learn the pressure change rules and characteristics between each pressure data column. After the training is completed, the non-zero data columns, unlabeled zero data columns and null value data columns are input into the neural network model in the original arrangement order to automatically analyze and interpolate the null value data columns to obtain the analysis value of the null value data columns. Specifically, Figure 2 As shown, this application converts the human body pressure data [x1,x2,x3,x4,x i ,x5,x6], where x1, x2, x3, x4, x5, and x6 are accurate data columns (including non-zero data columns and zero data columns with non-null values), and x i For null value data columns, the neural network model identifies the correlation between each accurate data column and uses interpolation to estimate the analysis value x of the null value data column. fi Replace x i , the neural network model outputs the result [x f1 ,x f2 ,x f3 ,x f4 ,x fi ,x f5 ,x f6 ], where x f1 、x f2 、x f3 、x f4 、x f5 、x f6 Corresponding to x1, x2, x3, x4, x5, and x6 respectively.

[0035] In one embodiment, the specific implementation of step 130 may be: based on the non-zero data column and the unmarked zero data column, j data values, and analyze to get the first j analysis values; among them, j A positive integer that is less than or equal to the number of rows in the column that contain null data.

[0036] The present application can split a data column into multiple independent data values, and use the corresponding data values ​​(data values ​​on the same row) to analyze and obtain the analysis value corresponding to the null value data column. Specifically, the present application can analyze the null value data column according to the first j The data values ​​are interpolated to estimate the firstj An analysis value is obtained by utilizing row-wise correlation to obtain each data value of the null value data column to improve the accuracy of data analysis.

[0037] In one embodiment, the specific implementation of step 130 may be: based on the relative relationship between each data value in the non-zero data column and the unmarked zero data column, correct the multiple analysis values ​​of the null value data column.

[0038] After obtaining the analysis value corresponding to the null value data column by analyzing the data values ​​on the same row, the present application further corrects multiple analysis values ​​of the null value data column based on the relative relationship between each data value in the non-zero data column and the unmarked zero data column to improve the accuracy of the analysis value of the null value data column. For example, after obtaining the analysis value, based on the relative size relationship between each data value in the non-zero data column, verify whether each analysis value of the null value data column satisfies the size relationship, and correct the analysis value based on the verification result to ensure its data accuracy.

[0039] In one embodiment, the initial human body pressure data includes multiple frames of pressure data; wherein, the above-mentioned analysis method of null values ​​of human body pressure data may also include: for the null value data column in the current frame pressure data, obtaining multiple frames of pressure data adjacent to the current frame; if there is a non-zero data column in the data column corresponding to the null value data column of the current frame pressure data in the multiple frames of pressure data adjacent to the current frame, then verifying the analysis value of the null value data column of the current frame pressure data based on the non-zero data column.

[0040] The present application obtains multiple frames of pressure data and utilizes the correlation between adjacent multiple frames of pressure data to verify the empty value data column of the current frame data. Specifically, the empty value data column in the current frame data is verified using the data column in the adjacent frame data (only non-zero data columns are used) to improve the accuracy of the analysis value of the empty value data column in the current frame data.

[0041] In one embodiment, the specific implementation method of the above-mentioned verification of the analysis value of the empty value data column of the current frame pressure data may be: based on the pressure data where the non-zero data column is located and the current frame pressure data, calculate the estimated value of the empty value data column of the current frame pressure data; calculate the variance between the estimated value and the analysis value of the empty value data column of the current frame pressure data; if the variance is less than a preset value, determine that the analysis value of the empty value data column of the current frame pressure data is verified to be qualified.

[0042] The present application calculates the estimated value of the null-value data column of the current frame pressure data through the pressure data of the frame where the non-zero data column corresponding to the null-value data column of the current frame in adjacent frames is located and the pressure data of the current frame, and calculates the variance between the estimated value and the analyzed value of the null-value data column of the current frame pressure data (that is, the square root of the sum of the squares of the differences of all corresponding elements). If the variance is small, it means that the analyzed value of the null-value data column of the current frame pressure data has been verified to be qualified, that is, the analyzed value of the null-value data column in the current frame pressure data obtained by analysis is relatively accurate.

[0043] Figure 3 Schematic diagram of the structure of a device for analyzing null values ​​of human body pressure data provided by an exemplary embodiment of the present application. Figure 3 As shown, the analysis device 30 for null values ​​of human body pressure data includes: a data acquisition module 31, used to acquire initial human body pressure data; wherein the initial human body pressure data includes multiple data columns, and the initial human body pressure data includes non-zero data columns and zero data columns, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; a null value recognition module 32, used to identify and mark the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; a null value analysis module 33, used to input the non-zero data column, the unmarked zero data column and the null value data column into the neural network model to obtain the analysis value of the null value data column; a result determination module 34, used to obtain the target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column.

[0044] The present application provides an analysis device for null values ​​of human body pressure data, which acquires initial human body pressure data through a data acquisition module 31; wherein the initial human body pressure data includes multiple data columns, and the initial human body pressure data includes non-zero data columns and zero data columns, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; the null value recognition module 32 identifies and marks the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; the null value analysis module 33 inputs the non-zero data column, the unmarked zero data column and the null value data column into a neural network model to obtain the analysis value of the null value data column; the result determination module 34 obtains the target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column; the present application automatically identifies and marks the null value data column in the human body pressure data, and uses the neural network model to automatically calculate the analysis value of the null value data column to supplement the missing value of the null value data column, thereby improving the accuracy and reliability of the human body pressure test.

[0045] In one embodiment, the above-mentioned null value identification module 32 can be further configured as: for each data column, calculate the data sum of all its elements; if the data sum of the current data column is equal to zero, calculate the preceding data sum of the preceding data column of the current data column and the succeeding data sum of the succeeding data column; if the preceding data sum and the succeeding data sum are greater than zero, determine that the current data column is a null value data column and mark the current data column.

[0046] In one embodiment, the above-mentioned null value analysis module 33 can be further configured to: input the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model according to the original arrangement order to obtain the analysis value of the null value data column.

[0047] In one embodiment, the above-mentioned null value analysis module 33 can be further configured to: based on the non-zero data column and the unmarked zero data column j data values, and analyze to get the first j analysis values; among them, j A positive integer that is less than or equal to the number of rows in the column that contain null data.

[0048] In one embodiment, the null value analysis module 33 may be further configured to correct multiple analysis values ​​of the null value data column based on the relative relationship between each data value in the non-zero data column and the unmarked zero data column.

[0049] In one embodiment, the initial human body pressure data includes multiple frames of pressure data; wherein, the above-mentioned human body pressure data null value analysis device 30 can be further configured as: for the null value data column in the current frame pressure data, obtaining multiple frames of pressure data adjacent to the current frame; if there is a non-zero data column in the data column corresponding to the null value data column of the current frame pressure data in the multiple frames of pressure data adjacent to the current frame, then verifying the analysis value of the null value data column of the current frame pressure data based on the non-zero data column.

[0050] In one embodiment, the above-mentioned analysis device 30 for null values ​​of human body pressure data can be further configured as: based on the pressure data where the non-zero data column is located and the current frame pressure data, calculating the estimated value of the null value data column of the current frame pressure data; calculating the variance between the estimated value and the analyzed value of the null value data column of the current frame pressure data; if the variance is less than a preset value, determining that the analyzed value of the null value data column of the current frame pressure data is verified to be qualified.

[0051] Below, reference Figure 4 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0052] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0053] like Figure 4 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0054] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0055] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0056] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0057] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0058] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0059] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0060] Of course, to simplify, Figure 4 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0061] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0062] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0063] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0064] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0065] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0066] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0067] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0068] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0069] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for analyzing null values ​​of human body pressure data, characterized in that: include: Acquire initial human body pressure data; wherein the initial human body pressure data includes a plurality of data columns, and the initial human body pressure data includes a non-zero data column and a zero data column, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; Identify and mark the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; Inputting the non-zero data column, the unlabeled zero data column and the null value data column into a neural network model to obtain an analysis value of the null value data column; Target human body pressure data is obtained based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column.

2. The method for analyzing null values ​​of human body pressure data according to claim 1, characterized in that: The identifying and marking of the null value data column in the zero data column comprises: For each of the data columns, calculate the data sum of all elements thereof; If the data sum of the current data column is equal to zero, then the preceding data sum of the preceding data column of the current data column and the following data sum of the following data column are calculated; If the sum of the preceding data and the sum of the succeeding data is greater than zero, the current data column is determined to be the null value data column and the current data column is marked.

3. The method for analyzing null values ​​of human body pressure data according to claim 1, characterized in that: The step of inputting the non-zero data column, the unlabeled zero data column and the null value data column into a neural network model to obtain an analysis value of the null value data column comprises: The non-zero data column, the unlabeled zero data column and the null value data column are input into the neural network model according to the original arrangement order to obtain the analysis value of the null value data column.

4. The method for analyzing null values ​​of human body pressure data according to claim 3, characterized in that: The step of inputting the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model in the original arrangement order to obtain the analysis value of the null value data column comprises: Based on the non-zero data column and the unmarked zero data column j data value, and analyze to obtain the first j analysis values; among them, j is a positive integer that is less than or equal to the number of rows in the null value data column.

5. The method for analyzing null values ​​of human body pressure data according to claim 4, characterized in that: The step of inputting the non-zero data column, the unlabeled zero data column and the null value data column into the neural network model in the original arrangement order to obtain the analysis value of the null value data column further comprises: Based on the relative relationship between the non-zero data column and the data values ​​in the unmarked zero data column, the plurality of analysis values ​​of the null value data column are corrected.

6. The method for analyzing null values ​​of human body pressure data according to claim 1, characterized in that: The initial human body pressure data includes multiple frames of pressure data; wherein the method for analyzing null values ​​of the human body pressure data further includes: For a null value data column in the current frame pressure data, obtaining a plurality of frames of pressure data adjacent to the current frame; If there is a non-zero data column in the data columns corresponding to the null value data column of the pressure data of the current frame in the multiple frames of pressure data adjacent to the current frame, the analysis value of the null value data column of the pressure data of the current frame is verified based on the non-zero data column.

7. The method for analyzing null values ​​of human body pressure data according to claim 6, characterized in that: The analyzing value of the null value data column of the current frame pressure data is verified based on the non-zero data column, including: Based on the pressure data where the non-zero data column is located and the current frame pressure data, calculating an estimated value of the null value data column of the current frame pressure data; Calculating the variance between the estimated value and the analyzed value of the null value data column of the current frame pressure data; If the variance is less than a preset value, it is determined that the analysis value of the null value data column of the current frame pressure data is qualified.

8. A device for analyzing null values ​​of human body pressure data, characterized in that: include: A data acquisition module, used to acquire initial human body pressure data; wherein the initial human body pressure data includes a plurality of data columns, and the initial human body pressure data includes a non-zero data column and a zero data column, and the zero data column indicates that the human body pressure data collected by all corresponding collection points are zero; A null value identification module, used to identify and mark the null value data column in the zero data column; wherein the null value data column indicates that the sensor at the corresponding position has not collected human body pressure data; A null value analysis module, used for inputting the non-zero data column, the unlabeled zero data column and the null value data column into a neural network model to obtain an analysis value of the null value data column; The result determination module is used to obtain the target human body pressure data based on the analysis values ​​of the non-zero data column, the unmarked zero data column and the null value data column.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the method described in any one of claims 1 to 7.

Images