WO2021143337A1 - Data processing method, apparatus, and device, and computer readable storage medium - Google Patents

Abstract

A data processing method, a data processing apparatus, a device, and a computer readable storage medium, the method comprising: acquiring multi-dimensional monitoring data corresponding to each person at regular intervals of a first preset duration (S110); respectively performing normalisation processing on each dimension of monitoring data corresponding to each person to acquire normalised monitoring data (S120); determining the similarity between each two of the people and, on the basis of the similarity, determining a similarity matrix corresponding to each person (S130); and, on the basis of the similarity matrix, determining an outlying person amongst the people (S140). The present method can monitor in real time the occurrence of abnormal people among the people and, by digging out possible abnormal points from mass data, facilitates medical staff understanding and continuously tracking the state of people in real time in order to analyse and dig out the potential causes of abnormalities, to thereby reduce abnormal incidents occurring to people in the sporting scenarios of sports events.

Description

Data processing method, device, equipment and computer readable storage medium

This application claims the priority of the Chinese patent application filed on January 17, 2020 with the application number 202010057407.3 and the title "data processing method, device, equipment and computer readable storage medium", the entire content of which is incorporated by reference in In this application.

Technical field

This application relates to the field of data processing technology, and in particular to a data processing method, device, device, and computer-readable storage medium.

Background technique

In the sports scene of sports events, due to weather or road reasons, it is inevitable that some athletes will suffer injuries, such as falls, sudden death, cardiac arrest, physical discomfort, and so on.

At present, most of the athletes collect physiological indicators and sports data after abnormal events of athletes, and then make preliminary judgments. These methods basically use traditional medical equipment for analysis, and cannot analyze and dig out the potential causes of athletes' abnormalities in real time. As a result, the abnormal personnel incidents that occur in the sports scenes of sports events have not been reduced.

The above content is only used to assist the understanding of the technical solution of the application, and does not mean that the above content is recognized as prior art.

Technical solutions

The main purpose of this application is to provide a data processing method, device, equipment, and computer-readable storage medium, aiming to solve the current technical problem that it is difficult to detect abnormal personnel among athletes.

In order to achieve the above objective, this application provides a data processing method, which includes the following steps:

Obtain multiple dimensions of monitoring data corresponding to each person at regular intervals at the first preset duration;

Normalize the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data;

Based on the normalized monitoring data of each dimension in each person, determine the similarity between each person, and determine the similarity matrix corresponding to each person based on the similarity;

Based on the similarity matrix, outliers among the individuals are determined.

Further, the step of determining the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel includes:

Obtain the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person;

Based on the mean value of each dimension corresponding to each person, the similarity between each person is determined.

Further, the step of determining the outliers among the individuals based on the similarity matrix includes:

Performing dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

Based on the two-dimensional matrix, outliers among the individuals are determined.

Further, the step of determining the outliers among the individuals based on the two-dimensional matrix includes:

Processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

Determine the outlier among the individuals based on the local outlier factor.

Further, after the step of determining the outliers among the individuals based on the similarity matrix, the data processing method further includes:

Based on the local outlier factor, the status graph of each person is displayed in a two-dimensional plan view, wherein the area of the state graph corresponds to the local outlier factor one-to-one, and all the persons except for outliers The color of the status graphic of the person is different from the color of the status graphic of the outlier.

Further, after the step of displaying the status graph of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further includes:

When the first display instruction triggered based on the target state graphic in each of the state graphics is detected, acquiring target monitoring data of each dimension corresponding to the target state graphic within the first preset time period;

Based on the target monitoring data of each dimension and the time sequence of each target monitoring data, the monitoring data curve of each dimension is displayed in a two-dimensional plan.

Further, after the step of displaying the status graph of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further includes:

Based on the outliers, update the number of abnormalities corresponding to each individual;

In the first preset area of the two-dimensional plan view, the identification information of the person who currently has an abnormality and the corresponding number of abnormalities are displayed.

Further, after the step of normalizing the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data, the data processing method further includes:

Split the normalized monitoring data based on the second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person, wherein the first preset duration is an integer multiple of the second preset duration , The sub-monitoring data includes data of multiple dimensions;

Add the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain the comprehensive score corresponding to each person;

In the second preset area of the two-dimensional plan, according to the time sequence of the comprehensive score, the comprehensive score corresponding to each person is displayed through a line graph.

Further, after the step of displaying the comprehensive score corresponding to each person through a line graph in the second preset area of the two-dimensional plan in the time sequence of the comprehensive score, the data processing method further includes:

Based on the third preset duration, multiple box and whisker diagrams are displayed in the second preset area, where the third preset duration is an integer multiple of the second preset duration, and the first preset Set the duration to be an integer multiple of the third preset duration;

When the second display instruction triggered by the target box and whisker diagram in multiple box and whisker diagrams is detected, the maximum score, minimum score, and score of each person’s comprehensive score are obtained before the time corresponding to the target box and whisker diagram. Mean value

Display the obtained maximum score, minimum score, and average score.

Further, after the step of displaying the comprehensive score corresponding to each person through a line graph in the second preset area of the two-dimensional plan in the time sequence of the comprehensive score, the data processing method further includes:

Determine whether there is target normalized data whose normalized data of each dimension is within the corresponding preset range in the normalized monitoring data corresponding to each person;

If it exists, obtain the collection time corresponding to the target normalized data and the target person;

Based on the collection time, a preset graph is displayed in a line chart corresponding to the target person.

In addition, in order to achieve the above objective, this application also provides a data processing device, the data processing device including:

The first acquisition module is configured to periodically acquire monitoring data of multiple dimensions corresponding to each person at intervals of a first preset duration;

The second acquisition module is used to perform normalization processing on the monitoring data of each dimension corresponding to each person, so as to obtain normalized monitoring data;

The first determination module is used to determine the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel, and determine the similarity matrix corresponding to each personnel based on the similarity;

The second determining module is used to determine the outliers among the personnel based on the similarity matrix.

In addition, in order to achieve the above object, the present application also provides a data processing device, the data processing device includes: a memory, a processor, and a data processing program stored on the memory and running on the processor, so When the data processing program is executed by the processor, the steps of the aforementioned data processing method are realized.

In addition, in order to achieve the above-mentioned object, the present application also provides a computer-readable storage medium having a data processing program stored on the computer-readable storage medium, and when the data processing program is executed by a processor, the aforementioned data processing method is implemented. step.

This application regularly obtains the monitoring data of multiple dimensions corresponding to each person by the first preset time interval, and then normalizes the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data. Then, based on the normalized monitoring data of each dimension in each person, determine the similarity between each person, and determine the similarity matrix corresponding to each person based on the similarity, and finally based on the similarity matrix Identify the outliers among the personnel and monitor the abnormal ones among the personnel in real time. By digging out the possible abnormal points (outliers) from the massive data, it is convenient for medical personnel to understand and keep track of the status of the personnel in real time. To analyze and dig out the potential causes of personnel abnormalities, so as to reduce the occurrence of abnormal personnel incidents in the sports scenes of sports events.

Description of the drawings

FIG. 1 is a schematic structural diagram of a data processing device in a hardware operating environment involved in a solution of an embodiment of the present application;

2 is a schematic flowchart of the first embodiment of the data processing method of this application;

3 is a schematic diagram of a display scene in an embodiment of the data processing method of this application;

4 is a schematic diagram of a display scene in another embodiment of the data processing method of this application;

5 is a schematic diagram of a display scene in another embodiment of the data processing method of this application;

Fig. 6 is a schematic diagram of functional modules of an embodiment of a data processing device according to the present application.

Embodiments of the present invention

It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

As shown in FIG. 1, FIG. 1 is a schematic structural diagram of a data processing device in a hardware operating environment involved in a solution of an embodiment of the present application.

The data processing equipment in the embodiment of this application may be a PC, or a smart phone, a tablet computer, an e-book reader, MP3 (Moving Picture Experts Group Audio Layer) III. Moving Picture Experts Group Audio Layer IV (Moving Picture Experts Group Audio Layer IV) player, portable computer and other portable terminal equipment with display function.

As shown in FIG. 1, the data processing device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a magnetic disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

In an embodiment, the data processing device may also include a camera, RF (Radio Frequency (radio frequency) circuits, sensors, audio circuits, WiFi modules, etc.

Those skilled in the art can understand that the structure of the data processing device shown in FIG. 1 does not constitute a limitation on the data processing device, and may include more or less components than shown in the figure, or a combination of certain components, or different components Layout.

As shown in FIG. 1, a memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a data processing program.

In the data processing device shown in FIG. 1, the network interface 1004 is mainly used to connect to a back-end server and perform data communication with the back-end server; the user interface 1003 is mainly used to connect to a client (user side) and perform data communication with the client; and The processor 1001 may be used to call a data processing program stored in the memory 1005.

In this embodiment, the data processing device includes a memory 1005, a processor 1001, and a data processing program stored on the memory 1005 and running on the processor 1001. The processor 1001 calls the memory 1005 to store Data processing program, and perform the operations in the following data processing method.

This application also provides a data processing method. Refer to FIG. 2, which is a schematic flowchart of the first embodiment of the data processing method of this application.

In this embodiment, the data processing method can be applied to scenes of large-scale sports events, and can also be applied to similar scenes in other fields, such as marathon scenes.

The data processing method includes:

Step S110: Obtain monitoring data of multiple dimensions corresponding to each person at regular intervals of a first preset duration;

In this embodiment, each athlete (person) wears a wearable device such as a bracelet. The wearable device can collect data from multiple dimensions of the athlete, and upload the collected data in real time or at regular intervals (at the first preset time interval) To the data processing device or data processing equipment, multiple dimensions of monitoring data include at least 3 of the latitude and longitude information of the athlete’s current location, current time, current heart rate, current speed, current pace, current distance, current cadence, etc. kind.

The monitoring data of multiple dimensions corresponding to each individual refers to the data of each dimension of each individual within the first preset period of time.

Step S120, normalize the monitoring data of each dimension corresponding to each person to obtain normalized monitoring data;

In this embodiment, when the multiple dimensions of monitoring data corresponding to each person are obtained, the monitoring data of each dimension of each person is respectively normalized to obtain the normalized monitoring data, that is, each person is obtained. The data after the normalization of each dimension of a person, specifically, the min-max normalization algorithm can be used to normalize the data of different dimensions to the range of (0, 1).

Step S130, based on the normalized monitoring data of each dimension in each person, determine the similarity between two of each person, and determine the similarity matrix corresponding to each person based on the similarity;

In this embodiment, after the normalized monitoring data is obtained, the normalized data of each dimension of each person is used to determine the similarity between each person, that is, any two persons in each person Based on the obtained similarity, a similarity matrix corresponding to each person is generated, where the element in the similarity matrix corresponding to each person is the similarity between the person and any other person.

Step S140: Determine outliers among the personnel based on the similarity matrix.

In this embodiment, when the similarity matrix corresponding to each person is obtained, the outliers in each person are determined based on the similarity matrix. Specifically, the outlier detection algorithm is used to process the similarity matrix to obtain the similarity matrix The corresponding outlier matrix (outlier), the person corresponding to the outlier matrix is the outlier.

The technical solution of this embodiment can automatically dig out possible abnormal points (outliers) from massive data, which is convenient for medical personnel to understand and keep track of the status of personnel in real time, and can find information that is ignored in the monitoring data or Symptoms and form new knowledge and experience in order to prevent similar incidents from happening again.

In the data processing method proposed in this embodiment, the monitoring data of multiple dimensions corresponding to each person is periodically obtained by an interval of a first preset time, and then the monitoring data of each dimension corresponding to each person is normalized to obtain a return. After the unified monitoring data, and then based on the normalized monitoring data of each dimension in each person, determine the similarity between the two of each person, and determine the similarity matrix corresponding to each person based on the similarity, Finally, based on the similarity matrix, the outliers among the personnel are determined, which can monitor the abnormal personnel among the personnel in real time. By digging out the possible abnormal points (outliers) from the massive data, it is convenient for medical personnel to understand and understand in real time. Continuously track the status of personnel to facilitate analysis and dig out potential causes of personnel abnormalities, so as to reduce the occurrence of abnormal personnel incidents in sports scenes.

Based on the first embodiment, a second embodiment of the data processing method of the present application is proposed. In this embodiment, step S120 includes:

Step S121: Obtain the mean value corresponding to the normalized monitoring data of each dimension in each person, so as to obtain the mean value of each dimension corresponding to each person;

Step S122, based on the average value of each dimension corresponding to each person, determine the similarity between each person.

In this embodiment, after the normalized monitoring data is obtained, the average value corresponding to the normalized monitoring data of each dimension of each person is calculated according to the normalized data of each dimension of each person, that is, the average value of the normalized monitoring data of each dimension of each person is calculated. The average value of the normalized monitoring data of each dimension corresponding to a person is obtained, and the average value of each dimension corresponding to each person is obtained, so as to obtain the summary data characteristics of each dimension corresponding to each person.

Then, based on the average value of each dimension corresponding to each person, determine the similarity between each pair of personnel. Specifically, the Canberra Distance formula is used to calculate the similarity between each two personnel in all dimensions, that is, each person The similarity between any two persons in the group, for example, according to the preset order based on the mean value of each dimension corresponding to each person, the mean vector is generated, and the Canberra Distance distance formula is used to calculate the distance between each two persons according to the mean vector of each person Similarity in all dimensions.

The data processing method proposed in this embodiment obtains the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person; then, based on the average value of each dimension corresponding to each person, Determine the similarity between the two in each person, and accurately get the similarity between the two in each person according to the mean value of each dimension corresponding to each person, which improves the accuracy of the similarity matrix and the efficiency of data processing, thereby improving The accuracy of outlier detection.

Based on the first embodiment, a third embodiment of the data processing method of the present application is proposed. In this embodiment, step S140 includes:

Step S141: Perform dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

Step S142: Determine outliers among the personnel based on the two-dimensional matrix.

In this embodiment, due to the large number of personnel, the dimensionality of the similarity matrix is also large. In order to facilitate processing, the dimensionality reduction process is performed on the similarity matrix first to obtain a two-dimensional matrix corresponding to each person. Specifically, The T-SNE algorithm is used to reduce the dimensionality of the similarity matrix. Among them, the T-SNE algorithm is a machine learning method for dimensionality reduction, which can recognize the associated patterns. The main advantage of the t-SNE algorithm is to keep the local The ability of structure, that is to say, the projection of similar points in the high-dimensional data space to the low-dimensional is still similar.

The data processing method proposed in this embodiment obtains a two-dimensional matrix corresponding to each person by performing dimensionality reduction processing on the similarity matrix; The degree matrix performs dimensionality reduction processing to improve the efficiency of data processing, thereby improving the efficiency of outlier detection.

Based on the third embodiment, a fourth embodiment of the data processing method of the present application is proposed. In this embodiment, step S142 includes:

Step S1421, processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

In step S1422, the outliers among the individuals are determined based on the local outlier factor.

In this embodiment, after obtaining the two-dimensional matrix corresponding to each person, the outlier detection algorithm is used to process each two-dimensional matrix to obtain the local outlier factor corresponding to each person. Specifically, the LOF outlier detection algorithm can be used to process each two-dimensional matrix. The LOF outlier detection algorithm is a density-based algorithm. The core part is the characterization of the data point density, and the samples around a sample point The average density of the location of the point is higher than the density of the location of the sample point. The larger the local outlier factor is, the less the density of the location of the point is than the density of the location of the surrounding samples, and the more likely this point is an abnormal point. Therefore, the person corresponding to the local outlier factor greater than 1 in the local outlier factor corresponding to each person is an outlier.

Further, in an embodiment, after step S140, the data processing method further includes:

Step S150, based on the local outlier factor, display the status graph of each person in a two-dimensional plan view, wherein the area of the state graph corresponds to the local outlier factor one-to-one, and each person except for outliers The color of the status graphic of the other personnel is different from the color of the status graphic of the outlier.

In this embodiment, the two dimensions of the two-dimensional matrix are used as the coordinate axes of the two-dimensional plan. According to the two-dimensional matrix of each person, the state graph of each person is displayed in the two-dimensional plan view. The area of the state graph is related to the partial distance. There is a one-to-one correspondence between the group factors. For example, referring to Figure 3, the status graph is dots. The larger the local outlier factor, the larger the radius of the dot. And, the black dots are all personnel except outliers. The status graphics of the personnel (normal personnel). The gray dots are the status graphics of the outliers. Of course, a more prominent color such as red can also be used as the color of the status graphics of the outliers. Among them, ppi in Figure 3 is the current heart rate, pace is the current pace, distance is the current distance, and speed is the current speed.

The data processing method proposed in this embodiment processes the two-dimensional matrix based on an outlier detection algorithm to obtain the local outlier factor corresponding to each person; and then determines the outlier in each person based on the local outlier factor. Group personnel can accurately determine outliers based on the local outlier factor, thereby improving the accuracy of outlier detection.

Based on the fourth embodiment, a fifth embodiment of the data processing method of the present application is proposed. In this embodiment, after step S150, the data processing method further includes:

Step S160, when the first display instruction triggered based on the target state graph in each of the state graphs is detected, obtain target monitoring data of each dimension corresponding to the target state graph within the first preset time period;

Step S170, based on the target monitoring data of each dimension and the time sequence of each target monitoring data, display the monitoring data curve of each dimension in a two-dimensional plan view.

In this embodiment, the first display instruction can be triggered by operations such as double-clicking, clicking, or when the cursor is hovering over a certain state graph. When the first display instruction triggered based on the target state graph in each of the state graphs is detected , Obtain the target monitoring data of each dimension corresponding to the target status graph within the first preset time period, and then display the monitoring data of each dimension in a two-dimensional plan based on the target monitoring data of each dimension and the time sequence of each target monitoring data Curve, so that medical staff can view the monitoring data of outliers in real time. Referring to Fig. 3, the curve near the status graph in Fig. 3 is the monitoring data curve of a certain person.

The data processing method proposed in this embodiment acquires the targets of each dimension corresponding to the target state graphics within the first preset time period when the first display instruction triggered based on the target state graphics in each of the state graphics is detected. Monitoring data; Then, based on the target monitoring data of each dimension and the time sequence of each target monitoring data, the monitoring data curve of each dimension is displayed in a two-dimensional plan, so that medical personnel can view the monitoring data of outliers in real time.

Based on the fourth embodiment, a sixth embodiment of the data processing method of the present application is proposed. In this embodiment, after step S150, the data processing method further includes:

Step S180, based on the outliers, update the number of abnormalities corresponding to each individual;

In step S190, in the first preset area of the two-dimensional plan view, the identification information of the person who has currently been abnormal and the corresponding number of abnormalities are displayed.

In this embodiment, after each outlier is determined, the number of abnormalities of each individual is accumulated, that is, the number of times that each individual is detected as an outlier, and the first preset area of the two-dimensional plan shows that the current has appeared Refer to Figure 4 for the identification information of abnormal persons and the number of abnormalities of persons who have occurred. In Figure 4, the first preset area is below the status graph. The identifications of persons who have been abnormal are displayed in the first preset area one by one. Information, if a person has repeated abnormalities in multiple time periods, the corresponding abnormal number is greater than 1, and the number in the upper right corner of the identification information can be used to identify the number of abnormalities of the person, and the number can be displayed in red.

The data processing method proposed in this embodiment updates the number of abnormalities corresponding to each individual based on the outlier; then, in the first preset area of the two-dimensional plan view, the identification information of the currently abnormal person is displayed and Corresponding abnormal times, so that medical staff can continue to monitor and diagnose the person, and reduce the probability of injury.

Based on the foregoing embodiments, a sixth embodiment of the data processing method of the present application is proposed. In this embodiment, after step S120, the data processing method further includes:

Step S200: Split the normalized monitoring data based on the second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person, where the first preset duration is the second preset duration An integer multiple of, the sub-monitoring data includes data of multiple dimensions;

Step S210: Add the data of each dimension in the sub-monitoring data corresponding to each person to obtain a comprehensive score corresponding to each person;

Step S220: In the second preset area of the two-dimensional plan view, according to the time sequence of the comprehensive score, the comprehensive score corresponding to each person is respectively displayed through a line graph.

In this embodiment, when the normalized monitoring data is obtained, the normalized monitoring data is split according to the second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person. The sub-monitoring data is Including data of multiple dimensions within the second preset duration, that is, segmenting the normalized monitoring data of each person to obtain multiple pieces of data with the same duration, that is, sub-monitoring data. The second preset duration can be set reasonably according to the first preset duration. For example, when the first preset duration is 2 minutes, the second preset duration can be set to 5S.

Then, in the sub-monitoring data corresponding to each personnel, the data of each dimension is added to obtain multiple comprehensive scores corresponding to each personnel. For each sub-monitoring data of each personnel, each sub-monitoring data The data of the dimensions are added together to obtain a comprehensive score. The number of comprehensive scores is the same as the number of sub-monitoring data for each individual.

When the comprehensive score corresponding to each person is obtained, in the second preset area of the two-dimensional plan, according to the time sequence of the comprehensive score, the comprehensive score corresponding to each person is displayed through a line graph, specifically, in the second preview Set the area to display the comprehensive score corresponding to each person in chronological order, and connect the comprehensive score corresponding to each person to form a line chart. Refer to Figure 3 and Figure 5, where the upper area of Figure 3 is the second The preset area, Figure 5 is the second preset area.

Further, in an embodiment, after step S220, the data processing method further includes:

Step a: Based on a third preset duration, display a plurality of box and whisker diagrams in the second preset area, wherein the third preset duration is an integer multiple of the second preset duration, and the The first preset duration is an integer multiple of the third preset duration;

Step b: When the second display instruction triggered by the target box and whisker diagram in multiple box and whisker diagrams is detected, obtain the maximum score and minimum score of the comprehensive score of each person before the time corresponding to the target box and whisker diagram. Value and mean value of score;

Step c, displaying the obtained maximum score, minimum score, and average score.

Among them, the box-and-whisker chart is a statistical chart used to display a set of data dispersion information. Named because of its shape like a box, the maximum, minimum, median, and upper and lower quartiles of a set of data can be displayed through an energy box and whisker diagram. The third preset duration can be set reasonably. For example, when the first preset duration is 2 minutes and the second preset duration is 5S, the third preset duration can be set to 20S.

In this embodiment, based on the third preset duration, multiple box and whisker diagrams are displayed in the second preset area. Specifically, referring to FIG. 3 and FIG. 5, drawing in the second preset area every 20 seconds For a box and whisker diagram, the medical staff can trigger the second display instruction by clicking, double-clicking, etc., when the second display instruction is detected, the target box and whisker diagram in multiple box and whiskers diagrams is determined according to the second display instruction first, namely Trigger the box and whisker diagram of the second display instruction, and obtain the maximum score, minimum score, and average score of each person's comprehensive score before the time corresponding to the target box and whisker diagram, and then display the maximum score obtained Value, minimum score, and average score, so that you can view the distribution of the maximum score, minimum score, and average score of all personnel, and perform horizontal comparison of data at multiple time points.

Further, in another embodiment, after step S220, the data processing method further includes:

Step d: Determine whether there is target normalized data whose normalized data of each dimension is within a corresponding preset range in the normalized monitoring data corresponding to each person;

Step e, if it exists, obtain the collection time corresponding to the target normalized data and the target person;

Step f, based on the collection time, display a preset graph in a line graph corresponding to the target person.

In this embodiment, the preset range of each dimension can be set in advance, and the data within the preset range is abnormal data. When the normalized monitoring data corresponding to each person is obtained, the normalized corresponding to each person is determined In the subsequent monitoring data, whether there is target normalized data in which the normalized data of each dimension is within the corresponding preset range, and each dimension data in the target normalized data is within the preset range of the corresponding dimension, If it exists, obtain the collection time corresponding to the target normalized data and the target person, and display the preset graph in the line chart corresponding to the target person according to the collection time, for example, display dots in the line chart for easy viewing Person data with abnormal data at a single moment.

The data processing method proposed in this embodiment splits the normalized monitoring data based on the second preset time length to obtain multiple sets of sub-monitoring data corresponding to each person, and then separately divides the sub-monitoring data corresponding to each person , The data of each dimension is added to obtain the comprehensive score corresponding to each person; then in the second preset area of the two-dimensional plan, in accordance with the time sequence of the comprehensive score, the comprehensive score corresponding to each person is displayed through a line chart. Value, it is convenient for medical personnel to view the status of the personnel through the line chart, so that the medical personnel can continue to monitor and diagnose the personnel, and reduce the probability of injury events of the personnel.

An embodiment of the present application also provides a data processing device. Referring to FIG. 6, the data processing device includes:

The first acquiring module 110 is configured to acquire multiple dimensions of monitoring data corresponding to each person at regular intervals of a first preset time period;

The second acquisition module 120 is configured to perform normalization processing on the monitoring data of each dimension corresponding to each person, so as to obtain normalized monitoring data;

The first determining module 130 is configured to determine the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel, and determine the similarity matrix corresponding to each personnel based on the similarity;

The second determining module 140 is configured to determine the outliers among the personnel based on the similarity matrix.

Further, the first determining module 130 is also used for:

Obtain the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person;

Based on the mean value of each dimension corresponding to each person, the similarity between each person is determined.

Further, the second determining module 140 is also used for:

Performing dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

Based on the two-dimensional matrix, outliers among the individuals are determined.

Further, the second determining module 140 is also used for:

Processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

Determine the outlier among the individuals based on the local outlier factor.

Further, the data processing device further includes:

Based on the local outlier factor, the status graph of each person is displayed in a two-dimensional plan view, wherein the area of the state graph corresponds to the local outlier factor one-to-one, and all the persons except for outliers The color of the status graphic of the person is different from the color of the status graphic of the outlier.

Further, the data processing device further includes:

When the first display instruction triggered based on the target state graphic in each of the state graphics is detected, acquiring target monitoring data of each dimension corresponding to the target state graphic within the first preset time period;

Based on the target monitoring data of each dimension and the time sequence of each target monitoring data, the monitoring data curve of each dimension is displayed in a two-dimensional plan.

Further, the data processing device further includes:

Based on the outliers, update the number of abnormalities corresponding to each individual;

In the first preset area of the two-dimensional plan view, the identification information of the person who currently has an abnormality and the corresponding number of abnormalities are displayed.

Further, the data processing device further includes:

Split the normalized monitoring data based on the second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person, wherein the first preset duration is an integer multiple of the second preset duration , The sub-monitoring data includes data of multiple dimensions;

Add the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain the comprehensive score corresponding to each person;

In the second preset area of the two-dimensional plan, according to the time sequence of the comprehensive score, the comprehensive score corresponding to each person is displayed through a line graph.

Further, the data processing device further includes:

Based on the third preset duration, multiple box and whisker diagrams are displayed in the second preset area, where the third preset duration is an integer multiple of the second preset duration, and the first preset Set the duration to be an integer multiple of the third preset duration;

When the second display instruction triggered by the target box and whisker diagram in multiple box and whisker diagrams is detected, the maximum score, minimum score, and score of each person’s comprehensive score are obtained before the time corresponding to the target box and whisker diagram. Mean value

Display the obtained maximum score, minimum score, and average score.

Further, the data processing device further includes:

Determine whether there is target normalized data whose normalized data of each dimension is within the corresponding preset range in the normalized monitoring data corresponding to each person;

If it exists, obtain the collection time corresponding to the target normalized data and the target person;

Based on the collection time, a preset graph is displayed in a line chart corresponding to the target person.

For the methods executed by the above-mentioned program modules, please refer to the various embodiments of the data processing method of this application, which will not be repeated here.

In addition, the embodiment of the present application also proposes a computer-readable storage medium.

A data processing program is stored on the computer-readable storage medium, and the data processing program implements the steps of the data processing method as described above when the data processing program is executed by a processor.

For the method implemented when the data processing program running on the processor is executed, please refer to the various embodiments of the data processing method of the present application, which will not be repeated here.

It should be noted that in this article, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, It also includes other elements that are not explicitly listed, or elements inherent to the process, method, article, or system. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or system that includes the element.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority of the embodiments.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disks, optical disks), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims (20)

1. A data processing method, wherein the data processing method includes the following steps:

   Obtain multiple dimensions of monitoring data corresponding to each person at regular intervals at the first preset duration;

   Normalize the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data;

   Based on the normalized monitoring data of each dimension in each person, determine the similarity between each person, and determine the similarity matrix corresponding to each person based on the similarity;

   Based on the similarity matrix, outliers among the individuals are determined.
2. 5. The data processing method according to claim 1, wherein the step of determining the similarity between two of each person based on the normalized monitoring data of each dimension in each person comprises:

   Obtain the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person;

   Based on the mean value of each dimension corresponding to each person, the similarity between each person is determined.
3. The data processing method according to claim 1, wherein the step of determining the outliers among the individuals based on the similarity matrix comprises:

   Performing dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

   Based on the two-dimensional matrix, outliers among the individuals are determined.
4. The data processing method according to claim 3, wherein the step of determining the outliers among the individuals based on the two-dimensional matrix comprises:

   Processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

   Determine the outlier among the individuals based on the local outlier factor.
5. 5. The data processing method according to claim 4, wherein after the step of determining outliers among the individuals based on the similarity matrix, the data processing method further comprises:

   Based on the local outlier factor, the status graph of each person is displayed in a two-dimensional plan view, wherein the area of the state graph corresponds to the local outlier factor one-to-one, and all the persons except for outliers The color of the status graphic of the person is different from the color of the status graphic of the outlier.
6. 5. The data processing method according to claim 5, wherein, after the step of displaying the status graph of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further comprises:

   When the first display instruction triggered based on the target state graphic in each of the state graphics is detected, acquiring target monitoring data of each dimension corresponding to the target state graphic within the first preset time period;

   Based on the target monitoring data of each dimension and the time sequence of each target monitoring data, the monitoring data curve of each dimension is displayed in a two-dimensional plan.
7. 5. The data processing method according to claim 5, wherein, after the step of displaying the status graph of each person in a two-dimensional plan view based on the local outlier factor, the data processing method further comprises:

   Based on the outliers, update the number of abnormalities corresponding to each individual;

   In the first preset area of the two-dimensional plan view, the identification information of the person who currently has an abnormality and the corresponding number of abnormalities are displayed.
8. The data processing method according to any one of claims 1 to 7, wherein after the step of normalizing the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data, The data processing method further includes:

   Split the normalized monitoring data based on the second preset duration to obtain multiple sets of sub-monitoring data corresponding to each person, wherein the first preset duration is an integer multiple of the second preset duration , The sub-monitoring data includes data of multiple dimensions;

   Add the data of each dimension in the sub-monitoring data corresponding to each person respectively to obtain the comprehensive score corresponding to each person;

   In the second preset area of the two-dimensional plan, according to the time sequence of the comprehensive score, the comprehensive score corresponding to each person is displayed through a line graph.
9. 8. The data processing method according to claim 8, wherein after the step of displaying the corresponding comprehensive scores of each person through a line graph in the second preset area of the two-dimensional plan view in the time sequence of the comprehensive scores, The data processing method further includes:

   Based on the third preset duration, multiple box and whisker diagrams are displayed in the second preset area, where the third preset duration is an integer multiple of the second preset duration, and the first preset Set the duration to be an integer multiple of the third preset duration;

   When the second display instruction triggered by the target box and whisker diagram in multiple box and whisker diagrams is detected, the maximum score, minimum score, and score of each person’s comprehensive score are obtained before the time corresponding to the target box and whisker diagram. Mean value

   Display the obtained maximum score, minimum score, and average score.
10. 8. The data processing method according to claim 8, wherein after the step of displaying the corresponding comprehensive scores of each person through a line graph in the second preset area of the two-dimensional plan view in the time sequence of the comprehensive scores, The data processing method further includes:

    Determine whether there is target normalized data whose normalized data of each dimension is within the corresponding preset range in the normalized monitoring data corresponding to each person;

    If it exists, obtain the collection time corresponding to the target normalized data and the target person;

    Based on the collection time, a preset graph is displayed in a line chart corresponding to the target person.
11. A data processing device, wherein the data processing device includes:

    The first acquisition module is configured to periodically acquire monitoring data of multiple dimensions corresponding to each person at intervals of a first preset duration;

    The second acquisition module is used to perform normalization processing on the monitoring data of each dimension corresponding to each person, so as to obtain normalized monitoring data;

    The first determination module is used to determine the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel, and determine the similarity matrix corresponding to each personnel based on the similarity;

    The second determining module is used to determine the outliers among the personnel based on the similarity matrix.
12. A data processing device, wherein the data processing device includes a memory, a processor, and a data processing program stored in the memory and running on the processor, and the data processing program is executed by the processor. The following steps are implemented during execution:

    Obtain multiple dimensions of monitoring data corresponding to each person at regular intervals at the first preset duration;

    Normalize the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data;

    Based on the normalized monitoring data of each dimension in each person, determine the similarity between each person, and determine the similarity matrix corresponding to each person based on the similarity;

    Based on the similarity matrix, outliers among the individuals are determined.
13. The data processing device according to claim 12, wherein the step of determining the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel comprises:

    Obtain the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person;

    Based on the mean value of each dimension corresponding to each person, the similarity between each person is determined.
14. The data processing device according to claim 12, wherein the step of determining the outliers among the individuals based on the similarity matrix comprises:

    Performing dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

    Based on the two-dimensional matrix, outliers among the individuals are determined.
15. The data processing device according to claim 14, wherein the step of determining the outliers among the individuals based on the two-dimensional matrix comprises:

    Processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

    Determine the outlier among the individuals based on the local outlier factor.
16. A computer-readable storage medium, wherein a data processing program is stored on the computer-readable storage medium, and when the data processing program is executed by a processor, the following steps are implemented:

    Obtain multiple dimensions of monitoring data corresponding to each person at regular intervals at the first preset duration;

    Normalize the monitoring data of each dimension corresponding to each person to obtain the normalized monitoring data;

    Based on the normalized monitoring data of each dimension in each person, determine the similarity between each person, and determine the similarity matrix corresponding to each person based on the similarity;

    Based on the similarity matrix, outliers among the individuals are determined.
17. 16. The computer-readable storage medium according to claim 16, wherein the step of determining the similarity between two of the personnel based on the normalized monitoring data of each dimension in each personnel comprises:

    Obtain the average value corresponding to the normalized monitoring data of each dimension in each person to obtain the average value of each dimension corresponding to each person;

    Based on the mean value of each dimension corresponding to each person, the similarity between each person is determined.
18. 15. The computer-readable storage medium of claim 16, wherein the step of determining the outliers among the individuals based on the similarity matrix comprises:

    Performing dimensionality reduction processing on the similarity matrix to obtain a two-dimensional matrix corresponding to each person;

    Based on the two-dimensional matrix, outliers among the individuals are determined.
19. 18. The computer-readable storage medium according to claim 18, wherein the step of determining outliers among the individuals based on the two-dimensional matrix comprises:

    Processing the two-dimensional matrix based on an outlier detection algorithm to obtain a local outlier factor corresponding to each person;

    Determine the outlier among the individuals based on the local outlier factor.
20. 18. The computer-readable storage medium of claim 18, wherein each two-dimensional matrix is processed using an LOF outlier detection algorithm.