CN107944344A - Power supply enterprise's construction mobile security supervision platform - Google Patents

Abstract

The present invention discloses a kind of power supply enterprise's construction mobile security supervision platform, cloud platform including intelligent mobile terminal and with intelligent mobile terminal communication connection, the cloud platform is equipped with the face sample unit of the facial image of storage power supply enterprise on-site personnel and the personnel safety access unit of personnel's access information is sent to intelligent terminal, the intelligent mobile terminal is equipped with face recognition module, the face recognition module is used to identify whether the access facial image sent with personnel safety access unit matches the personnel for entering scene, to determine whether to allow the personnel to enter scene.The present invention further strengthens construction site safety supervision management and control dynamics, standard construction operation, guarantees personal safety using state-of-the-art technologies such as 4G wireless networks, intelligent mobile terminal, cloud computing, recognitions of face.

Description

Construction mobile safety supervision platform for power supply enterprises

technical field

The invention relates to the technical field of electric power construction safety supervision, and is specifically used for face recognition of personnel entering a construction site.

Background technique

In recent years, power supply enterprises have paid more and more attention to the management of the identity of the external cooperation team members, in order to avoid the security risks caused by the frequent replacement of the external cooperation team personnel, mainly adopt the following methods:

1. QR code: Use QR codes and photos to uniquely identify outsourcing team members. During inspections, scan QR codes for identification, which has problems such as low efficiency and easy forgery.

2. Passive RFID technology: Passive RFID cards are used to uniquely identify the personnel of the outsourcing team. During the inspection, the identification is carried out through non-contact scanning of the handheld terminal, which is more efficient, but there may be inconsistencies between the people and cards, and it needs to be held The terminal has rfid reading function.

3. Active RFID technology: Active RFID is used to uniquely mark the personnel of the outsourcing team. During the inspection, the identity can be identified remotely and in batches, which is efficient, but the cost of active RFID cards and scanning terminals is high.

4. Fingerprint identification technology: It is efficient to identify the personnel of the foreign cooperation team based on fingerprint identification, but the handheld terminal needs to be equipped with a fingerprint identification module separately.

At present, face recognition products have been widely used in finance, justice, military, public security, border inspection, government, aerospace, electric power, factories, education, medical care and many enterprises and institutions. Therefore, it is of practical significance to promote the application of face recognition technology to power supply enterprises and manage the identity of foreign cooperation team members.

The face recognition system extracts the face of the input static or dynamic image through the recognition algorithm, so as to determine the identity of the person, and has a wide application prospect. A typical face recognition system (Face Recognition System, FRS) generally consists of the following basic links: preprocessing link, face detection link, feature extraction link and classification recognition link:

1. Preprocess the input face image. The preprocessing methods include image filtering, region segmentation, grayscale and scale normalization, face alignment, histogram equalization, and local binary patterns.

2. Detect whether the preprocessed image includes a human face, if detected, separate the human face from the background and determine its number, position and size. According to the different ways of extracting detection features, existing face detection methods can be roughly divided into three categories: face detection methods based on statistical learning, face detection methods based on knowledge, and face detection methods based on template matching. Its adaptability and stability become a popular face detection method.

3. Extract the features that represent the essence of the face in the face image to be recognized, and require the extracted features to have better robustness under conditions such as expression, occlusion, viewing angle, and illumination. The common methods of face feature extraction mainly include face feature extraction method based on geometric space, face feature extraction method based on subspace, face feature extraction method based on neural network, face feature extraction method based on elastic graph matching and Face feature extraction method based on hidden Markov.

4. Compare the features of the face to be recognized with the features of known faces in the database, and match them to obtain the recognition result. Commonly used classifiers are classifiers based on nearest neighbors, classifiers based on support vector machines, and classifiers based on neural networks.

The current face recognition algorithm has high requirements on the shooting environment and angle, and the recognition efficiency is low. There are great technical difficulties in the application of on-site construction management.

Contents of the invention

The technical problem to be solved by the present invention is to provide a construction mobile safety supervision platform for power supply enterprises to improve the accuracy and efficiency of face recognition in complex environments in view of the current face recognition algorithm that has high requirements on shooting environment and angle and low recognition efficiency .

In order to solve the above-mentioned technical problems, the present invention adopts the following technical solutions: the construction mobile safety supervision platform of the power supply enterprise includes an intelligent mobile terminal and a cloud platform connected to the intelligent mobile terminal, and the cloud platform is provided with a personal computer for storing the on-site operators of the power supply enterprise. The face sample unit of the face image and the personnel security access unit that sends personnel access information to the intelligent terminal, the intelligent mobile terminal is provided with a face recognition module, and the face recognition module is used to identify whether the personnel entering the scene are compatible with personnel The access face image sent by the security access unit is matched to determine whether the person is allowed to enter the scene; wherein, the method for face recognition by the face recognition module includes the following steps,

Step 1: Construct a super-complete dictionary based on face training samples

Step 2, arrange the test images into a column vector x in sequence;

Step 3, design the measurement matrix Φ according to the over-complete dictionary ψ;

Step 4, project x under Φ to obtain the measurement vector y, and obtain

Step five, the obtained Substitution

In this way, the discriminant result of the input test sample is obtained.

Preferably, in step 1, assuming that there are K different types of faces, each training face image is sequentially pulled into an N×1-dimensional column vector ψ, and the _l2 norm normalization process is performed respectively, that is, ψ∈ R ^N×1 and ||ψ|| ₂ = 1, recorded as an atom, select L different training samples from each type of face training samples to form the face sample matrix of this type i=1,2,...,K, get the total number of selected training samples n=KL, and merge these matrices into a super-complete dictionary in order:

Preferably, for any input test face sample, pull it into a column vector x∈R ^N×1 in order, then x is expressed under the dictionary Ψ as:

x=Ψα+z (4.2)

Among them, α∈R ^n×1 is a sparse representation vector, and z∈R ^N×1 is an error representation.

Preferably, based on the CS theory, the test sample x is compressed and projected to obtain a projection vector y∈RM ^×1 (M<N), namely

y=Φx=ΦΨα+Φz=Dα+e (4.3)

where Φ∈RM ^×N is a designed measurement matrix with certain properties, D=ΦΨ∈RM ^×n represents an equivalent dictionary, e=Φz∈RM ^×1 is the error in the projection domain, and the definition For any i, α _i ∈ R ^L×1 , so formula (4.3) can be re-expressed as:

y=Φ(ψ ₁ α ₁ +ψ ₂ α ₂ + . . . +ψ _k α _k )+e (4.4).

Preferably, for a certain i, let D _i =ΦΨ _i ∈ R ^M×L , the cost function of formula (4.5) is transformed into:

Let the singular value decomposition of D _i be as follows:

in Substituting (4.8) into (4.7), we get

make

in and The size is Equation (4.9) expands to:

The second term on the right side of the above equation has nothing to do with α _i , so when

, formula (4.10) takes the minimum value, and at this time, the solution of formula (4.5) is:

where V _i , ∑ _i and are obtained from the measurement matrix, dictionary and input test sample projection values respectively, for any size of vectors.

Preferably, traverse i from 1 to K to find all After that, the test sample category can be obtained by formula (4.6)

Preferably, the input test sample is reconstructed according to the discriminant result Thereby rearranging to obtain the reconstructed image.

Preferably, for personnel who need to temporarily enter the site, the personnel security access unit sends a temporary access permit to the smart mobile terminal, and sets the number of temporary access within a year to no more than 2 times.

Preferably, for a person whose admission qualification needs to be canceled, the personnel security admission unit sends information about canceling admission to the smart mobile terminal.

The present invention utilizes the latest technologies such as 4G wireless network, intelligent mobile terminal, cloud computing, and face recognition to further strengthen the safety supervision and control of construction sites, standardize construction operations, and ensure personal safety.

The face recognition of on-site construction personnel and management personnel is realized through face recognition technology. On the one hand, through the measurement matrix projection, the transmission and calculation data are reduced, the calculation efficiency is improved, and the storage consumption is reduced. On the other hand, it can improve The accuracy and efficiency of face recognition in complex environments.

Detailed ways

The invention solves the problems that the current face recognition algorithm has high requirements on the shooting environment and angle, and the recognition efficiency is low, improves the accuracy and efficiency of face recognition in complex environments, and realizes the face recognition of on-site construction workers and management personnel. Therefore, it prevents outsourced construction personnel from changing at will, prevents outsourced construction personnel with serious violation records from performing on-site operations, and checks the arrival of construction personnel on a functional basis, so as to prevent the occurrence of "work leaders and safety personnel" not arriving on site.

The construction mobile safety supervision platform of the power supply enterprise includes an intelligent mobile terminal and a cloud platform communicating with the intelligent mobile terminal. The personnel security access unit of the access information, the intelligent mobile terminal is provided with a face recognition module, and the face recognition module is used to identify whether the personnel entering the scene match the admission face image sent by the personnel security access unit, To determine whether to allow the person to enter the scene.

Among them, (3) Personnel safety access: After all production employees engaged in electric power production-related professional work have participated in the safety skill level evaluation test and the general examination of safety regulations for personnel in key positions of outsourcing units (work ticket issuers and work leaders), the The project organization unit will enter the information of the qualified personnel into the system and collect the faces.

(4) Temporary personnel access: For outsourcing units that need to temporarily enter the company's production and operation area for construction operations, the engineering organization unit will enter the outsourcing unit's enterprise information and engineering project information into the system, and the engineering organization unit or equipment operation and maintenance management unit will work on it After the personnel pass the safety examination, the personnel information of the key positions will be temporarily admitted into the system, and the temporary construction operation certificate IC card will be made. The number of temporary access for the same person in charge within a year should not exceed 2 times.

(5) Dynamic adjustment of personnel access: adjust the safety skill level of production employees and the person in charge of the outsourcing unit based on their on-site safety conditions and daily violations, or even cancel their access qualifications.

For personnel who need to temporarily enter the site, the personnel security access unit sends a temporary access permit to the smart mobile terminal, and sets the number of temporary access within a year to no more than 2 times. For the personnel whose admission qualification needs to be canceled, the personnel security admission unit sends the information of canceling the admission to the smart mobile terminal.

The face recognition algorithm based on compressed sensing uses the marked face training samples to form an over-complete dictionary. Assuming that there are K different types of faces, each training face image is sequentially pulled into an N×1-dimensional column vector ψ, and the l ₂ norm normalization process is performed respectively, that is, ψ∈R ^N×1 and || ψ|| ₂ =1, recorded as an atom. From each type of face training samples, L different training samples are selected to form the face sample matrix of this type by column i=1,2,...,K. The total number of selected training samples n=KL can be obtained. Merge these matrices sequentially into an overcomplete dictionary:

For any input test face sample, pull it into a column vector x∈R ^N×1 in order, then x can be expressed as:

x=Ψα+z (4.2)

Among them, α∈R ^n×1 is a sparse representation vector, and z∈R ^N×1 is an error representation. Based on the CS theory, the test sample x is compressed and projected to obtain the projection vector y∈RM ^×1 (M<N), namely

y=Φx=ΦΨα+Φz=Dα+e (4.3)

Among them, Φ∈RM ^×N is a designed measurement matrix with certain properties, D=ΦΨ∈RM ^×n represents an equivalent dictionary, and e=Φz∈RM ^×1 is an error in the projection domain. definition For any i, α _i ∈ R ^L×1 , so formula (4.3) can be re-expressed as:

y=Φ(ψ ₁ α ₁ +ψ ₂ α ₂ +…+ψ _k α _k )+e (4.4)

According to the CS theory, ideally, non-zero items exist in a certain α _i in the sparse representation vector α, while other items are all zero. Therefore, solving for α is transformed into:

After obtaining {α _i }, it is used for face recognition classification to form the following problem:

obtained That is, the discriminant result of the input test sample x.

In the case of a given measurement matrix Φ, the difficulty of the above problem lies in how to solve formula (4.5) accurately. For a certain i, let D _i =ΦΨ _i ∈ R ^M×L , the cost function of formula (4.5) is transformed into:

Let the singular value decomposition (Singular Value Decomposition, SVD) of D _i be as follows:

in Substituting (4.8) into (4.7), we get

make

in and The size is Formula (4.9) can be expanded as:

It can be seen that the second term on the right side of the above equation has nothing to do with α _i , so when

Time formula (4.10) takes the minimum value. At this time, the solution of formula (4.5) is:

where V _i , ∑ _i and are obtained from the measurement matrix, dictionary and input test sample projection values respectively, for any size of vectors.

Traverse i from 1 to K to find all After that, the test sample category can be obtained by formula (4.6) According to requirements, the input test samples can also be reconstructed according to the discrimination results Thereby rearranging to obtain the reconstructed image.

In general, the face recognition algorithm based on compressed sensing, on the one hand, reduces the data transmitted and calculated by measuring the matrix projection, improves the calculation efficiency, and reduces the storage consumption; on the other hand, it can improve the accuracy of face recognition. Rate.

Claims (9)

1. power supply enterprise's construction mobile security supervision platform, it is characterised in that including intelligent mobile terminal and and intelligent mobile The cloud platform of terminal called connection, the cloud platform are equipped with the face sample of the facial image of storage power supply enterprise on-site personnel This unit and the personnel safety access unit that personnel's access information is sent to intelligent terminal, the intelligent mobile terminal are equipped with people Face identification module, the face recognition module are used to identify what whether the personnel for entering scene sent with personnel safety access unit Access facial image matches, to determine whether to allow the personnel to enter scene；Wherein, face recognition module carries out recognition of face Method includes the following steps,

Step 1, according to face training sample, constructs super complete dictionary

Step 2, by test image sequentially vector x arranged in columns；

Step 3, according to super complete dictionary ψ design calculation matrix Φ；

Step 4, x projects to obtain measure vectorial y under Φ, and tries to achieve

Step 5, by what is tried to achieveSubstitution formula

So as to try to achieve the differentiation result of input test sample.

2. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that false in step 1 Equipped with the different face of K classes, every width training facial image sequentially pulls into the column vector ψ that N × 1 is tieed up, and carries out l respectively₂Norm is returned One change is handled, i.e. ψ ∈ R^N×1And | | ψ | |₂=1, an atom is denoted as, L different instruction is all selected from every class face training sample Practice sample and form such face sample matrix by rowObtain selection These matrixes are sequentially merged into super complete dictionary by training sample sum n=KL：

3. power supply enterprise's construction mobile security supervision platform according to claim 2, it is characterised in that to what is arbitrarily inputted Face sample is tested, it is sequentially pulled into column vector x ∈ R^N×1, then x be expressed as under dictionary Ψ：

X=Ψ α+z (4.2)

Wherein α ∈ R^n×1For rarefaction representation vector, z ∈ R^N×1It is to represent error.

4. power supply enterprise's construction mobile security supervision platform according to claim 3, it is characterised in that it is theoretical based on CS, Test sample x is compressed projection and obtains projection vector y ∈ R^M×1(M ＜ N), i.e.,

Y=Φ x=Φ Ψ α+Φ z=D α+e (4.3)

Wherein Φ ∈ R^M×NFor the designed calculation matrix with certain property, D=Φ Ψ ∈ R^M×nRepresent equivalent dictionary, e= Φz∈R^M×1For projection domain error, definitionTo any i, α_i∈R^L×1, so that formula (4.3) is heavy Newly it is expressed as：

Y=Φ (ψ₁α₁+ψ₂α₂+…+ψ_kα_k)+e (4.4)。

5. power supply enterprise according to claim 4 construction mobile security supervision platform, it is characterised in that for some i, Make D_i=Φ Ψ_i∈R^M×L, formula (4.5) cost function is converted into：

<mrow> <mo>|</mo> <mo>|</mo> <mi>y</mi> <mo>-</mo> <msub> <mi>D</mi> <mi>i</mi> </msub> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> <mo>=</mo> <mi>&amp;xi;</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4.7</mn> <mo>)</mo> </mrow> </mrow>

If D_iSingular value decomposition be shown below：

<mrow> <msub> <mi>D</mi> <mi>i</mi> </msub> <mo>=</mo> <msub> <mi>U</mi> <mi>I</mi> </msub> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mi>&amp;Sigma;</mi> <mi>i</mi> </msub> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> <msubsup> <mi>V</mi> <mi>i</mi> <mi>T</mi> </msubsup> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4.8</mn> <mo>)</mo> </mrow> </mrow>

WhereinFormula (4.8) is substituted into (4.7), is obtained

<mrow> <mtable> <mtr> <mtd> <mrow> <mi>&amp;xi;</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mrow> <mo>||</mo> <mrow> <mi>y</mi> <mo>-</mo> <msub> <mi>U</mi> <mi>i</mi> </msub> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mo>&amp;Sigma;</mo> <mi>i</mi> </msub> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> <msubsup> <mi>V</mi> <mi>i</mi> <mi>T</mi> </msubsup> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> </mrow> <mo>||</mo> </mrow> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <msubsup> <mrow> <mo>||</mo> <mrow> <msubsup> <mi>U</mi> <mi>i</mi> <mi>T</mi> </msubsup> <mi>y</mi> <mo>-</mo> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mo>&amp;Sigma;</mo> <mi>i</mi> </msub> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> <msubsup> <mi>V</mi> <mi>i</mi> <mi>T</mi> </msubsup> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> </mrow> <mo>||</mo> </mrow> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <msubsup> <mrow> <mo>||</mo> <mrow> <mover> <mi>y</mi> <mo>~</mo> </mover> <mo>-</mo> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mo>&amp;Sigma;</mo> <mi>i</mi> </msub> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> </mrow> <mo>||</mo> </mrow> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mtd> </mtr> </mtable> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4.9</mn> <mo>)</mo> </mrow> </mrow>

Order

<mrow> <mover> <mi>y</mi> <mo>~</mo> </mover> <mo>=</mo> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mn>2</mn> </msub> </mtd> </mtr> </mtable> </mfenced> <mo>,</mo> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> <mo>=</mo> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <msub> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>a</mi> <mo>~</mo> </mover> <mn>2</mn> </msub> </mtd> </mtr> </mtable> </mfenced> </mrow>

WhereinWithSize beFormula (4.9) expands into：

<mrow> <mi>&amp;xi;</mi> <mrow> <mo>(</mo> <msub> <mi>&amp;alpha;</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mo>|</mo> <mo>|</mo> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>&amp;Sigma;</mi> <mi>i</mi> </msub> <msub> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> <mi>i</mi> </msub> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> <mo>+</mo> <mo>|</mo> <mo>|</mo> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mn>2</mn> </msub> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4.10</mn> <mo>)</mo> </mrow> </mrow>

Section 2 and α on the right of above formula equal sign_iIt is unrelated, therefore work as

<mrow> <msub> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> <mo>=</mo> <msubsup> <mi>&amp;Sigma;</mi> <mi>i</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mi>i</mi> </msub> </mrow>

When, formula (4.10) is minimized, and at this time, the solution of formula (4.5) is：

<mrow> <msub> <mover> <mi>&amp;alpha;</mi> <mo>^</mo> </mover> <mi>i</mi> </msub> <mo>=</mo> <msub> <mi>V</mi> <mi>i</mi> </msub> <mfenced open = "|" close = "|"> <mtable> <mtr> <mtd> <mrow> <msubsup> <mo>&amp;Sigma;</mo> <mi>i</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> <msub> <mover> <mi>y</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> </mrow> </mtd> </mtr> <mtr> <mtd> <msub> <mover> <mi>&amp;alpha;</mi> <mo>~</mo> </mover> <mn>2</mn> </msub> </mtd> </mtr> </mtable> </mfenced> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4.11</mn> <mo>)</mo> </mrow> </mrow>

Wherein V_i、∑_iWithTried to achieve respectively by calculation matrix, dictionary and input test sample projection value,For arbitrary dimension for (Vector.

6. power supply enterprise according to claim 5 construction mobile security supervision platform, it is characterised in that by i from 1 traversal to K, is tried to achieve allAfterwards, test sample classification can be tried to achieve by formula (4.6)

7. power supply enterprise's construction mobile security supervision platform according to claim 6, it is characterised in that according to differentiation result Reconstruct the test sample of inputSo as to which reconstructed image is tried to achieve in permutatation.

8. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that interim for needing Into the personnel at scene, the personnel safety access unit sends interim access to intelligent mobile terminal and permits, and sets 1 year Interior interim access number is not to be exceeded 2 times.

9. power supply enterprise's construction mobile security supervision platform according to claim 1, it is characterised in that for needing to cancel The personnel of access qualification, the personnel safety access unit send the information for cancelling access to intelligent mobile terminal.