阅读说明：本技术 一种激光训练服的激光接收模块结构 (Laser receiving module structure of laser training clothes ) 是由 黄菊 于 2020-10-29 设计创作，主要内容包括：本发明公开了一种激光训练服的激光接收模块结构,包括训练服本体,所述训练服本体的内部固定连接有激光接收模块,所述激光接收模块包括无线芯片,所述无线芯片的输入端电连接有激光探测器,所述无线芯片的输出端和输入端双向电连接有WIFI模块,所述WIFI模块的输出端和输入端双向电连接有后台数据处理计算机。本发明通过激光探测器便于探测激光枪发射的激光,具备独立的供电、激光接收、无线传输功能,自身可通过无线数据交换方式与配套设备互联,可实现离散布置或拼接布置与数据传递方式多元组合配置,有效规避点状激光接收模块只能有线连接,随着布置数量增加导致相互之间电缆长度增加而影响训练服使用的缺点。(The invention discloses a laser receiving module structure of laser training clothes, which comprises a training clothes body, wherein a laser receiving module is fixedly connected inside the training clothes body, the laser receiving module comprises a wireless chip, the input end of the wireless chip is electrically connected with a laser detector, the output end and the input end of the wireless chip are bidirectionally and electrically connected with a WIFI module, and the output end and the input end of the WIFI module are bidirectionally and electrically connected with a background data processing computer. The laser detector is convenient to detect the laser emitted by the laser gun, has independent power supply, laser receiving and wireless transmission functions, can be interconnected with matched equipment in a wireless data exchange mode, can realize the multi-element combined configuration of discrete arrangement or splicing arrangement and a data transmission mode, and effectively overcomes the defect that the use of the training clothes is influenced due to the fact that the lengths of cables among the punctiform laser receiving modules are increased along with the increase of the arrangement number because the punctiform laser receiving modules can only be connected in a wired mode.)

1. The utility model provides a laser receiving module structure of laser training clothes, includes training clothes body (1), its characterized in that: the inside fixedly connected with laser receiving module (2) of training clothes body (1), laser receiving module (2) include wireless chip (3), the input electricity that wireless chip (3) were used is connected with laser detector (4), the two-way electricity of the output and the input of wireless chip (3) is connected with WIFI module (5), the two-way electricity of the output and the input of WIFI module (5) is connected with backstage data processing computer (6).

2. The laser receiving module structure of the laser training suit according to claim 1, wherein: the input end of the wireless chip (3) is electrically connected with a battery (7), the battery (7) is fixedly installed in the laser receiving module (2), and a charging port (8) is formed in the surface of the laser receiving module (2).

3. The laser receiving module structure of the laser training suit according to claim 1, wherein: the number of the laser receiving modules (2) is a plurality of, six laser detectors (4) are installed in each laser receiving module (2), and the six laser detectors (4) are arranged at equal intervals.

4. The laser receiving module structure of the laser training suit according to claim 1, wherein: mounting holes (9) are formed in the surface of the laser receiving module (2), the number of the mounting holes (9) is four, and the mounting holes (9) are formed in four corners of the surface of the laser receiving module (2).

5. The laser receiving module structure of the laser training suit according to claim 1, wherein: the waist belt (10) is sleeved at the bottom of the surface of the training clothes body (1), an insertion block (11) is fixedly connected with one end of the waist belt (10), a buckle (12) is fixedly connected with the other end of the waist belt (10), and one side, far away from the waist belt (10), of the insertion block (11) is inserted into an inner cavity of the buckle (12).

6. A method for data processing by using a background data processing computer (6) in a laser receiving module structure of a laser training suit according to any one of claims 1 to 5, comprising the steps of:

(S1) selecting and sampling data, receiving data information of the laser receiving module (2), the wireless chip (3) or the laser detector (4), and sampling the received data information; analyzing the received data information;

(S2) data calculation, starting a classification algorithm model, classifying the received data information, and classifying the data information received by the laser receiving module (2), the wireless chip (3) or the laser detector (4) according to different classification attributes to output different data categories; the classification algorithm model is a K-Means algorithm, a decision tree or an FCM clustering algorithm; the K-Means algorithm, the decision tree or the FCM clustering algorithm is an improved classification algorithm model, and the output interface of the K-Means algorithm, the decision tree or the FCM clustering algorithm is compatible with at least three different types of data communication interfaces;

(S3) outputting data, and outputting the data output by the classification algorithm model in the step (S2) through a computer output interface.

7. The data processing method of claim 6, wherein the K-Means algorithm model is connected with a strong classifier, and the strong classifier is formed by combining 5 different strong classifiers.

8. The data processing method of claim 7, wherein the K-Means algorithm model is trained by:

(1) selecting data samples, selecting k different data sample objects as initial clustering centers, and collecting data as X ═ X_m1, 2.. times.m., and if there are d different classification attributes in the data set, there is a₁,A₂,...,A_dA different dimension, then different data samples x_i＝(x_i1,x_i2,...,x_id)、x_j＝(x_j1,x_j2,...,x_jd) Is a sample x_i、x_jCorresponding to d different classification attributes A₁,A₂,...,A_dThe specific value of (a);

(2) calculating the distance from each clustering object to the clustering center to divide the classification attribute, x_iAnd x_jThe similarity between them is calculated by a distance formula, x_iAnd x_jThe smaller the distance between, the sample x_iAnd x_jThe more similar, x_iAnd x_jThe greater the distance between, sample x_iAnd x_jThe farther apart the phase difference; the distance formula is:

(3) calculating each clustering center again, taking the sample mean value in each cluster as a new clustering center through repeated calculation, and repeating the step (2);

(4) when the clustering center is not changed any more or the maximum iteration number is reached, stopping the calculation, otherwise, repeating the steps (2) and (3);

the clustering performance evaluation formula of the K-Means algorithm is a square error sum criterion function, and the function is as follows:

where p is the output data set X_iAn arbitrary value of (1), m_iFor different cluster centers, E is a function of the sum of squared errors criterion, where m_i≥5。

9. The data processing method of claim 6, wherein the decision tree algorithm is constructed by:

(1) training data: firstly, selecting a data sample D, and assuming that K categories are selected from the data sample, setting the probability that a sample point belongs to the kth category as p_kThen the kini index of the probability distribution is defined as:

then for data sample D, then there are:

then C is_kIf the data sample is a kth class data sample in the data sample D, the kini index of the data sample D is:

wherein D₁And D₂Is a part divided by a characteristic A in a data set D, then selects the characteristic with the minimum Gini index and the corresponding dividing point as the optimal characteristic and the optimal dividing point,

(3) determining a root node: selecting a root node of the decision tree according to the kini index calculated by the formula (5), and selecting the attribute with the larger kini index as the root node;

(4) determining leaf nodes: selecting leaf nodes of the decision tree according to the calculated kini indexes, and selecting the leaf nodes with smaller kini indexes; then, continuously and repeatedly applying the formula (5) to calculate, and stopping calculating if the number of samples in the node is less than a preset threshold value or the Gini index of the sample set is less than the preset threshold value, then not calculating the classification attribute;

(5) establishing a data model: establishing a data model according to the root node and the leaf node determined by the method;

(6) constructing a decision tree: constructing a decision tree according to the data model; the constructed decision tree is in a tree structure, and the user target value is finally output.

10. The data processing method according to claim 6, wherein the FCM clustering algorithm model is obtained by:

(1) setting the cluster number to be 5, initializing and setting a membership value and a cluster center, and determining an iteration error, wherein the iteration number is more than 4;

(2) for the ith iteration, recalculating the membership function to obtain an updated membership function value; meanwhile, optimizing and updating the clustering center again;

(3) calculating an objective function and storing a result;

(4) if the target function result meets the set condition, stopping the algorithm; otherwise, returning to the step (2).

Technical Field

The invention relates to the technical field of military training equipment, in particular to a laser receiving module structure of a laser training suit.

Background

The traditional individual soldier tactical confrontation training mostly adopts an 'empty aiming' and 'false shooting' training mode, people are easy to fatigue, the actual training effect has a limited effect on improving the actual combat level, most of the existing training methods are abandoned, and instead, the actual shooting mode is adopted for tactical confrontation training, the actual shooting training method has a remarkable effect, but the training cost is high, and safety accidents are easy to cause.

Along with the development of science and technology, particularly the improvement of the emission and receiving level of small-sized safe laser, the laser simulation countermeasure system developed based on the technology can simulate the live-action training effect vividly and avoid the potential safety hazard brought by live-action training, is applied more and more in the individual soldier tactical countermeasure training, and has become a trend to replace live-action training.

Common individual soldier laser simulation is equipped mainly with the laser gun and has arranged laser receiving module's laser training clothes to anti training, and the laser receiving module who arranges on the present laser training clothes is mostly small-size punctiform structure, and built-in single laser detector, and power supply and data signal transmission rely on external cable to provide. The laser receiving module with the structure has the following defects: the laser receiving module with the structure can effectively overcome the defects of the traditional point-like laser receiving module.

Disclosure of Invention

The invention aims to provide a laser receiving module structure of a laser training suit, which has the advantage of wireless connection among laser detectors and solves the problems that the length of interconnection cables among laser receiving modules is increased step by step along with the increase of the number, and the reliability and the maintenance performance of the training suit are greatly influenced by excessive cable connection.

In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a laser receiving module structure of laser training clothes, includes the training clothes body, the inside fixedly connected with laser receiving module of training clothes body, laser receiving module includes wireless chip, wireless chip's input electricity is connected with laser detector, wireless chip's the two-way electricity of output and input is connected with the WIFI module, the two-way electricity of output and the input of WIFI module is connected with backstage data processing computer.

Preferably, the input end of the wireless chip is electrically connected with a battery, the battery is fixedly installed in the laser receiving module, and a charging port is formed in the surface of the laser receiving module.

Preferably, the number of the laser receiving modules is several, six laser detectors are installed in each laser receiving module, and the six laser detectors are arranged at equal intervals.

Preferably, the surface of the laser receiving module is provided with four mounting holes, and the four mounting holes are arranged at four corners of the surface of the laser receiving module.

Preferably, the bottom cover on training clothes body surface is equipped with the waistband, the one end fixedly connected with inserted block of waistband, the other end fixedly connected with buckle of waistband, one side that the inserted block kept away from the waistband is pegged graft to the inner chamber of buckle.

The invention also adopts the following technical scheme:

a method for processing data by using a background data processing computer (6) in a laser receiving module structure of a laser training suit in the technical scheme comprises the following steps:

(S1) selecting and sampling data, receiving data information of the laser receiving module (2), the wireless chip (3) or the laser detector (4), and sampling the received data information; analyzing the received data information;

(S2) data calculation, starting a classification algorithm model, classifying the received data information, and classifying the data information received by the laser receiving module (2), the wireless chip (3) or the laser detector (4) according to different classification attributes to output different data categories; the classification algorithm model is a K-Means algorithm, a decision tree or an FCM clustering algorithm; the K-Means algorithm, the decision tree or the FCM clustering algorithm is an improved classification algorithm model, and the output interface of the K-Means algorithm, the decision tree or the FCM clustering algorithm is compatible with at least three different types of data communication interfaces;

(S3) outputting data, and outputting the data output by the classification algorithm model in the step (S2) through a computer output interface.

Preferably, the K-Means algorithm model is connected with a strong classifier, and the strong classifier is formed by combining 5 different strong classifiers.

Preferably, the training method of the K-Means algorithm model is as follows:

(1) selecting data samples, selecting k different data sample objects as initial clustering centers, and collecting data as X ═ X_m1, 2.. times.m., and if there are d different classification attributes in the data set, there is a₁,A₂,...,A_dA different dimension x_jThen different data samples x_i＝(x_i1,x_i2,...,x_id)、x_j＝(x_j1,x_j2,...,x_jd) Is a sample x_i、x_jCorresponding to d different classification attributes A₁,A₂,...,A_dThe specific value of (a);

(2) calculating the distance from each clustering object to the clustering center to divide the classification attribute, x_iAnd x_jThe similarity between them is calculated by a distance formula, x_iAnd x_jThe smaller the distance between, the sample x_iAnd x_jThe more similar, x_iAnd x_jThe greater the distance between, sample x_iAnd x_jThe farther apart the phase difference; the distance formula is:

(3) calculating each clustering center again, taking the sample mean value in each cluster as a new clustering center through repeated calculation, and repeating the step (2);

(4) when the clustering center is not changed any more or the maximum iteration number is reached, stopping the calculation, otherwise, repeating the steps (2) and (3);

the clustering performance evaluation formula of the K-Means algorithm is a square error sum criterion function, and the function is as follows:

where p is the output data set X_iAn arbitrary value of (1), m_iFor different cluster centers, E is a function of the sum of squared errors criterion, where m_i≥5。

Preferably, the construction method of the decision tree algorithm is as follows:

(1) training data: firstly, selecting a data sample D, and assuming that K categories are selected from the data sample, setting the probability that a sample point belongs to the kth category as p_kThen the kini index of the probability distribution is defined as:

then for data sample D, then there are:

then C is_kIf the data sample is a kth class data sample in the data sample D, the kini index of the data sample D is:

wherein D₁And D₂Is a part divided by a characteristic A in a data set D, then selects the characteristic with the minimum Gini index and the corresponding dividing point as the optimal characteristic and the optimal dividing point,

(3) determining a root node: selecting a root node of the decision tree according to the kini index calculated by the formula (5), and selecting the attribute with the larger kini index as the root node;

(4) determining leaf nodes: selecting leaf nodes of the decision tree according to the calculated kini indexes, and selecting the leaf nodes with smaller kini indexes; then, continuously and repeatedly applying the formula (5) to calculate, and stopping calculating if the number of samples in the node is less than a preset threshold value or the Gini index of the sample set is less than the preset threshold value, then not calculating the classification attribute;

(5) establishing a data model: establishing a data model according to the root node and the leaf node determined by the method;

(6) constructing a decision tree: constructing a decision tree according to the data model; the constructed decision tree is in a tree structure, and the user target value is finally output.

Preferably, the FCM clustering algorithm model is implemented by:

(1) setting the cluster number to be 5, initializing and setting a membership value and a cluster center, and determining an iteration error, wherein the iteration number is more than 4;

(2) for the ith iteration, recalculating the membership function to obtain an updated membership function value; meanwhile, optimizing and updating the clustering center again;

(3) calculating an objective function and storing a result;

(4) if the target function result meets the set condition, stopping the algorithm; otherwise, returning to the step (2).

Compared with the prior art, the invention has the following beneficial effects:

1. the training suit has independent power supply, laser receiving and wireless transmission functions by matching the training suit body, the laser receiving module, the wireless chip, the laser detector, the WIFI module, the background data processing computer, the battery and the charging port, can be interconnected with matched equipment in a wireless data exchange mode, can realize the multi-element combination configuration of discrete arrangement or splicing arrangement and a data transmission mode, and effectively avoids the defects that the use of the training suit is influenced by the increase of the length of cables among the laser receiving modules due to the increase of the arrangement number because the laser receiving modules can be only in wired connection.

2. According to the invention, the laser emitted by the laser gun can be conveniently detected through the laser detector, the WIFI module is arranged, the network connection with an external background data processing computer is conveniently realized, the power can be supplied to the laser receiving module through the battery, the battery can be conveniently charged through the charging port, the laser receiving module can be conveniently installed inside the training clothes body through the installation hole, and the bottom of the training clothes body can be conveniently tensioned through the waistband, the waistband and the buckle, so that the training clothes body is close to the body of a user.

3. According to the invention, the classification of different data such as the training suit body, the laser receiving module, the wireless chip, the laser detector, the WIFI module and the like is realized by adopting a K-Means algorithm, a decision tree or an FCM clustering algorithm, so that a user can quickly classify various data information according to different objects, thus realizing various data processing and greatly improving the data management capability.

Drawings

FIG. 1 is a schematic structural view of the present invention in a discrete arrangement on a laser training garment;

FIG. 2 is a schematic structural diagram of a laser receiving module according to the present invention;

FIG. 3 is a schematic structural view of the laser training suit according to the present invention;

FIG. 4 is a schematic structural diagram of a point-shaped laser receiving module;

FIG. 5 is a schematic diagram of the system of the present invention;

FIG. 6 is a schematic view of the K-Means algorithm of the data processing algorithm of the present invention;

FIG. 7 is a schematic view of a flow structure of a decision tree algorithm in the data processing algorithm of the present invention;

FIG. 8 is a schematic view of the flow structure of the FCM clustering algorithm in the data processing algorithm of the present invention;

in the figure: the training clothes comprises a training clothes body, a laser receiving module 2, a wireless chip 3, a laser detector 4, a WIFI module 5, a background data processing computer 6, a battery 7, a charging port 8, a mounting hole 9, a waistband 10, an insertion block 11 and a buckle 12.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be configured in a specific orientation, and operate, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

Example (1) Structure

The training suit body 1, the laser receiving module 2, the wireless chip 3, the laser detector 4, the WIFI module 5, the background data processing computer 6, the battery 7, the charging port 8, the mounting hole 9, the belt 10 and the buckle 12 are all universal standard parts or parts known by technicians in the field, and the structure and the principle of the training suit are known by the technicians or conventional experimental methods.

Referring to fig. 1-5, a laser receiving module structure of a laser training suit comprises a training suit body 1, a laser receiving module 2 is fixedly connected inside the training suit body 1, the laser receiving module 2 comprises a wireless chip 3, an input end of the wireless chip 3 is electrically connected with a laser detector 4, an output end and an input end of the wireless chip 3 are bidirectionally electrically connected with a WIFI module 5, an output end and an input end of the WIFI module 5 are bidirectionally electrically connected with a background data processing computer 6, an input end of the wireless chip 3 is electrically connected with a battery 7, the battery 7 is fixedly installed inside the laser receiving module 2, a charging port 8 is arranged on the surface of the laser receiving module 2, the number of the laser receiving modules 2 is several, six laser detectors 4 are installed in each laser receiving module 2, the six laser detectors 4 are arranged at equal intervals, mounting holes 9 are formed on the surface of the laser receiving module 2, the number of the mounting holes 9 is four, the mounting holes 9 are arranged at four corners of the surface of the laser receiving module 2, the bottom of the surface of the training clothes body 1 is sleeved with a belt 10, one end of the belt 10 is fixedly connected with an insert block 11, the other end of the belt 10 is fixedly connected with a buckle 12, one side of the insert block 11, which is far away from the belt 10, is inserted into an inner cavity of the buckle 12, laser emitted by a laser gun is conveniently detected through a laser detector 4, network connection with an external background data processing computer 6 is conveniently carried out through arranging a WIFI module 5, the laser receiving module 2 can be powered through arranging a battery 7, the battery 7 is conveniently charged through arranging a charging port 8, the laser receiving module 2 is conveniently arranged inside the training clothes body 1 through arranging the mounting holes 9, the bottom of the training clothes body 1 is conveniently tensioned through arranging the belt 10, the belt 10 and the buckle 12, make training clothes body 1 press close to user's health, through training clothes body 1, laser receiving module 2, wireless chip 3, laser detector 4, WIFI module 5, backstage data processing computer 6, battery 7 and charging mouth 8 cooperate, possess independent power supply, laser receiving, wireless transmission function, self accessible wireless data exchange mode and corollary equipment interconnection, can realize arranging the scattered configuration of mode or concatenation arrangement and the many units combination configuration of data transfer mode, effective punctiform evades laser receiving module 2 and can only wired connection, lead to cable length between each other to increase and influence the shortcoming that training clothes used along with arranging the quantity increase.

During the use, laser gun transmission laser is to training clothes body 1 on, laser detector 4 accepts laser, give wireless chip 3 with information feedback, wireless chip 3 gives backstage data processing computer 6 with information transmission through WIFI module 5, suggestion backstage personnel dress this training clothes person is hit, supply power to laser receiving module 2 through battery 7, be convenient for charge battery 7 through charging mouth 8, through setting up mounting hole 9, be convenient for install laser receiving module 2 in the inside of training clothes body 1, through setting up waistband 10, waistband 10 and buckle 12, be convenient for carry out the tensioning to the bottom of training clothes body 1, make training clothes body 1 press close to user's health.

In summary, the following steps: this laser receiving module structure of laser training clothes, through training clothes body 1, laser receiving module 2, wireless chip 3, laser detector 4, WIFI module 5, backstage data processing computer 6, battery 7 and the mouth 8 that charges cooperate, solved and lead to the laser to accept interconnection cable length also to increase step by step between the module along with quantity increase, excessive cable is connected and is taken care of the reliability to training, and maintenance nature has the problem of great negative effect.

Example (2) data processing method

As shown in fig. 6-8, the present invention also employs the following embodiments:

a method of background data processing computer 6 data processing, comprising the steps of, with reference to fig. 6:

(S1) selecting and sampling data, receiving data information of the laser receiving module 2, the wireless chip 3 or the laser detector 4, and sampling the received data information; analyzing the received data information;

(S2) data calculation, starting a classification algorithm model, classifying the received data information, and classifying the data information received by the laser receiving module 2, the wireless chip 3 or the laser detector 4 according to different classification attributes to output different data categories; the classification algorithm model is a K-Means algorithm, a decision tree or an FCM clustering algorithm; the K-Means algorithm, the decision tree or the FCM clustering algorithm is an improved classification algorithm model, and the output interface of the K-Means algorithm, the decision tree or the FCM clustering algorithm is compatible with at least three different types of data communication interfaces;

(S3) outputting data, and outputting the data output by the classification algorithm model in the step (S2) through a computer output interface.

In the working process, the K-Means algorithm model is connected with a strong classifier, and the strong classifier is formed by combining 5 different strong classifiers.

The training method of the K-Means algorithm model comprises the following steps:

(1) selecting data samples, selecting k different data sample objects as initial clustering centers, and collecting data as X ═ X_m1, 2.. times.m., and if there are d different classification attributes in the data set, there is a₁,A₂,...,A_dA different dimension, then different data samples x_i＝(x_i1,x_i2,...,x_id)、x_j＝(x_j1,x_j2,...,x_jd) Is a sample x_i、x_jCorresponding to d different classification attributes A₁,A₂,...,A_dThe specific value of (a);

(2) calculating the distance from each clustering object to the clustering center to divide the classification attribute, x_iAnd x_jThe similarity between them is calculated by a distance formula, x_iAnd x_jThe smaller the distance between, the sample x_iAnd x_jThe more similar, x_iAnd x_jThe greater the distance between, sample x_iAnd x_jThe farther apart the phase difference; the distance formula is:

(3) calculating each clustering center again, taking the sample mean value in each cluster as a new clustering center through repeated calculation, and repeating the step (2);

(4) when the clustering center is not changed any more or the maximum iteration number is reached, stopping the calculation, otherwise, repeating the steps (2) and (3);

the clustering performance evaluation formula of the K-Means algorithm is a square error sum criterion function, and the function is as follows:

where p is the output data set X_iAn arbitrary value of (1), m_iFor different clusteringCenter, E is a sum of squared errors criterion function, where m_i≥5。

As shown in fig. 7, the construction method of the decision tree algorithm includes:

(1) training data: firstly, selecting a data sample D, and assuming that K categories are selected from the data sample, setting the probability that a sample point belongs to the kth category as p_kThen the kini index of the probability distribution is defined as:

then for data sample D, then there are:

then C is_kIf the data sample is a kth class data sample in the data sample D, the kini index of the data sample D is:

wherein D₁And D₂Is a part divided by a characteristic A in a data set D, then selects the characteristic with the minimum Gini index and the corresponding dividing point as the optimal characteristic and the optimal dividing point,

(2) determining a root node: selecting a root node of the decision tree according to the kini index calculated by the formula (5), and selecting the attribute with the larger kini index as the root node;

(3) determining leaf nodes: selecting leaf nodes of the decision tree according to the calculated kini indexes, and selecting the leaf nodes with smaller kini indexes; then, continuously and repeatedly applying the formula (2) to calculate, and stopping calculating if the number of samples in the node is less than a preset threshold value or the Gini index of the sample set is less than the preset threshold value, then not calculating the classification attribute;

(4) establishing a data model: establishing a data model according to the root node and the leaf node determined by the method;

(5) constructing a decision tree: constructing a decision tree according to the data model; the constructed decision tree is in a tree structure, and the user target value is finally output.

As shown in fig. 8, the FCM clustering algorithm model method is:

(1) setting the cluster number to be 5, initializing and setting a membership value and a cluster center, and determining an iteration error, wherein the iteration number is more than 4;

(2) for the ith iteration, recalculating the membership function to obtain an updated membership function value; meanwhile, optimizing and updating the clustering center again;

(3) calculating an objective function and storing a result;

(4) if the target function result meets the set condition, stopping the algorithm; otherwise, returning to the step (2).

By the method, the training suit body, the laser receiving module, the wireless chip, the laser detector, the WIFI module and other different data can be classified, a user can rapidly classify various data information according to different objects, various data processing is further realized, and the data management capability is greatly improved.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.