CN115564350A

CN115564350A - Equipment checking method and device

Info

Publication number: CN115564350A
Application number: CN202211253323.2A
Authority: CN
Inventors: 陈亮; 肖钢; 潘建东; 丁瑞; 李祥煌; 程曦
Original assignee: China Securities Co Ltd
Current assignee: China Securities Co Ltd
Priority date: 2022-10-13
Filing date: 2022-10-13
Publication date: 2023-01-03

Abstract

The embodiment of the invention provides a method and a device for equipment checking, relates to the technical field of data processing, and is applied to electronic equipment, wherein the method comprises the following steps: acquiring a target video acquired by image acquisition equipment aiming at target equipment; identifying a first device identification from the video frame of the target video and identifying a device information code; analyzing the equipment information code to obtain first equipment information of the target equipment; obtaining a second device identification of the target device stored locally based on the first device information; if the first equipment identifier is the same as the second equipment identifier, second equipment information corresponding to the second equipment identifier stored locally is obtained; and determining that the target device is successfully checked under the condition that the first device information is the same as the second device information. By applying the scheme provided by the embodiment of the invention, the inventory efficiency of the equipment can be improved.

Description

Equipment checking method and device

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to an apparatus checking method and an apparatus.

Background

At present, all industries are in the way of digital transformation, and more electronic devices are applied to daily office. In order to ensure the normal working of the office, the electronic equipment is required to be checked regularly to ensure that the actual use condition of the electronic equipment is consistent with the expectation.

Currently, equipment checking is generally performed manually, when the equipment checking is performed, a checking person needs to compare whether the actual use condition of each electronic equipment is consistent with reference information of the electronic equipment stored in a database in advance, and if so, the electronic equipment is considered to pass through the checking.

Therefore, the above-mentioned checking process needs the checking personnel to compare each electronic device, which is time-consuming and labor-consuming, and the number of electronic devices in the actual scene is often large, resulting in low efficiency of checking the devices.

Disclosure of Invention

The embodiment of the invention aims to provide an equipment inventory method and an equipment inventory device, so as to improve the inventory efficiency of equipment. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides an apparatus inventory method, which is applied to an electronic apparatus, and the method includes:

obtaining a target video acquired by image acquisition equipment aiming at target equipment;

identifying a first device identification from the video frame of the target video and identifying a device information code;

analyzing the equipment information code to obtain first equipment information of the target equipment;

obtaining a second device identification of the target device stored locally based on the first device information;

if the first equipment identifier is the same as the second equipment identifier, second equipment information corresponding to the second equipment identifier stored locally is obtained;

and determining that the target device is successfully checked under the condition that the first device information is the same as the second device information.

In a second aspect, an embodiment of the present invention provides an apparatus checking device, which is applied to an electronic apparatus, and the apparatus includes:

the target video acquisition module is used for acquiring a target video acquired by the image acquisition equipment aiming at the target equipment;

the information identification module is used for identifying a first equipment identifier from a video frame of the target video and identifying an equipment information code;

the first equipment information obtaining module is used for analyzing the equipment information code to obtain first equipment information of the target equipment;

a device identifier obtaining module, configured to obtain a second device identifier of the target device, where the second device identifier is locally stored, based on the first device information;

a second device information obtaining module, configured to obtain, if the first device identifier is the same as the second device identifier, second device information corresponding to the second device identifier that is locally stored;

and the equipment checking module is used for determining that the target equipment is checked successfully under the condition that the first equipment information is the same as the second equipment information.

In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;

a memory for storing a computer program;

a processor, configured to implement the method steps of the first aspect when executing the program stored in the memory.

In a fourth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps described in the first aspect.

In a fifth aspect, embodiments of the present invention provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method steps of the first aspect described above.

As can be seen from the above, when the scheme provided by the embodiment of the present invention is applied to perform device inventory, a first device identifier and a device information code are identified from a target video acquired for a target device, first device information is analyzed from the device information code, then a second device identifier of the target device stored locally is obtained based on the first device information, and if the first device identifier is the same as the second device identifier, second device information corresponding to the second device identifier stored locally is further obtained, so that it is determined that the target device inventory is successful under the condition that the first device information is the same as the second device information. Therefore, the equipment does not need to be checked by the checking personnel one by one, the electronic equipment is used for checking the equipment, the workload required by the equipment checking is reduced, and the checking efficiency of the equipment is improved.

In addition, the first device identifier is a device identifier extracted from a target video acquired from the target device, and represents an actual device identifier of the target device; the second device identifier is a device identifier obtained based on the device information code posted on the target device, and represents a device identifier when the target device initially registers, and if the first device identifier is different from the second device identifier, the second device identifier represents that the actual device identifier of the target device is inconsistent with the device identifier when the target device initially registers, that is, the device identifier of the target device is tampered, the content of the device information code is tampered or the device information code is mistakenly posted, and it is meaningless to perform subsequent device information comparison at this time. Therefore, the first device identifier and the second device identifier are judged firstly, and the first device information and the second device information are compared when the identifiers are the same, so that the consistency between the actual device identifier of the target device and the device identifier when the target device is initially registered can be ensured, the waste of time and computing resources caused by the comparison of subsequent device information when the identifiers are inconsistent is prevented, and the equipment counting efficiency and the practicability of the equipment counting scheme are further improved.

Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by referring to these drawings.

Fig. 1 is a schematic diagram of an equipment inventory system according to an embodiment of the present invention;

fig. 2 is a schematic diagram of an apparatus identification image according to an embodiment of the present invention;

fig. 3 is a schematic diagram of an apparatus information code according to an embodiment of the present invention;

fig. 4 is a schematic flowchart of a first device inventory method according to an embodiment of the present invention;

fig. 5 is a schematic flowchart of a second device inventory method according to an embodiment of the present invention;

fig. 6 is a schematic flowchart of a third method for checking a device according to an embodiment of the present invention;

fig. 7 is a schematic diagram of an apparatus inventory procedure according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an apparatus inventory device according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

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 from the embodiments of the present invention by those skilled in the art based on the description, are within the scope of the present invention.

First, the main implementation of the solution provided by the embodiment of the present invention will be described.

In terms of hardware, the main execution body of the scheme provided by the embodiment of the invention is as follows: any electronic device with data processing, data communication, data storage and other functions is provided, and an equipment inventory system is deployed in the electronic device.

From the software level, the execution subject of the scheme provided by the embodiment of the present invention can also be understood as: an equipment inventory system deployed in the electronic equipment.

The various subsystems that comprise the above-described equipment inventory system are briefly described below.

Referring to fig. 1, fig. 1 is a schematic diagram of an equipment inventory system according to an embodiment of the present application.

As shown in fig. 1, the device inventory system is divided into a device registration subsystem, a device video capture subsystem, and a device inventory subsystem, wherein the main functions of each subsystem are as follows:

the device registration subsystem is primarily responsible for: the method comprises the steps of equipment information acquisition, equipment image hash value generation, hash value distribution storage, equipment information storage and equipment information code generation.

The equipment video acquisition subsystem is mainly responsible for: acquiring a video of the equipment and generating a video watermark.

The equipment inventory subsystem is mainly responsible for: extracting a serial number, extracting an equipment information code, comparing information, reading collected equipment information, reading account equipment information and checking equipment.

The three subsystems cooperate with each other to jointly realize the inventory of the equipment.

In addition, it should be noted that the device registration subsystem and the device video capture subsystem are executed before the device inventory subsystem executes, and the execution steps in the device registration subsystem and the device video capture subsystem are the pre-step of the execution steps in the device inventory subsystem.

Since the device inventory scheme provided in the embodiment of the present invention mainly introduces the execution steps of the device inventory subsystem, in order to facilitate understanding of the device inventory scheme provided in the embodiment of the present invention, the following description will first describe the pre-steps executed by the device registration subsystem and the device video capture subsystem.

Device registration subsystem

The following describes the functions mainly responsible for the device registration subsystem, respectively:

1. device information collection

For the equipment to be checked without equipment information registered, the equipment registration subsystem can collect information of equipment type, equipment brand, equipment quantity, factory serial number, affiliated service type, equipment user, equipment use department, tax amount, purchase date, supplier, operator, warehousing date, signature number and the like of the equipment.

The device to be checked, for which the device information is not registered, may be a newly purchased device, or a device that has been purchased in the past but first participates in device checking, and the like.

2. Device image acquisition

For the device to be checked without the device information registered, the device registration subsystem further needs to acquire a device image of the device, where the device image includes a device identifier clearly visible to the device.

For example, the device identifier may be a factory serial number, a factory part number, a fixed asset number, or the like.

The device image may be an image obtained by shooting a device identification area in the device by using an image capturing device such as a camera by a worker.

The device identification image will be more intuitively described below by way of example.

Referring to fig. 2, a schematic diagram of an apparatus identification image according to an embodiment of the present invention is provided.

As can be seen from the figure, the figure includes S/N (Serial Number) and P/N (Part Number) of the device, and both the factory Serial Number and the factory Part Number may be used as the device identifier.

3. Device image hash value generation

The device registration subsystem starts a hash value generation program, reads a device image of a device to be checked, for which device information is not registered, and encrypts the device image by using a hash algorithm to generate a hash value of the device image.

The Hash Algorithm may be an Algorithm such as MD5 (Message-Digest Algorithm 5, information-Digest Algorithm 5), SHA-1 (Secure Hash Algorithm 1 ), or the like.

4. Hash value distributed storage

The device registration subsystem transmits the generated hash value to other nodes in the distributed system, so that the other nodes store the hash value.

The distributed system is a distributed system where electronic devices deployed by the device registration system are located.

The other nodes are nodes in the distributed system except the electronic device, for example, for a security company, the other nodes may be a financial system node, an office system node, a data warehouse system node, and the like in the company network.

5. Device information storage and device information code generation

The device registration subsystem correspondingly stores the acquired device information of the device and the device image for each device, completes initial information registration for the device, and generates a device information code of the device, wherein the device information code uniquely identifies and binds with the device, and the device information code stores the device information of the device or stores a hash value of the device image of the device.

An example of an equipment information code used in the equipment inventory scheme provided in the embodiment of the present invention is described below.

Fig. 3 is a schematic diagram of an apparatus information code according to an embodiment of the present invention.

The two-dimensional code on the right side in fig. 3 is the device information code, wherein the hash value of the device information and the device image is stored, and the left side of the two-dimensional code can be additionally added with the text record of the device information, so that the staff can identify the device.

After the device registration subsystem generates the device information code, the device information code may be printed out, and then the worker may post the device information code on the surface of its corresponding device.

(II) equipment video acquisition subsystem

The following describes the functions mainly responsible for the video acquisition subsystem of the device:

1. and acquiring the video of the equipment.

The device video acquisition subsystem acquires a device video in response to the device inventory instruction.

The device video may be a video obtained by recording each device to be checked by a worker holding the video recording device, and the device video includes a clearly visible device information code and a device identifier of the device.

2. And generating a video watermark.

The device video acquisition subsystem can read file attribute information of the device video and add the device shooting time contained in the file attribute information to the device video as a watermark.

Of course, when the worker holds the video recording device by hand to record the video to the equipment to be checked, the video watermark generation function can be started at the same time, so that the generated equipment video can directly carry the shooting time watermark, the place watermark and the like of the video.

The equipment inventory method provided by the embodiment of the invention is further described in detail below.

Referring to fig. 4, a flowchart of a first method for device inventory according to an embodiment of the present invention is shown, where the method is applied to an electronic device, and includes the following steps S401 to S408.

Step S401: and obtaining a target video acquired by the image acquisition equipment aiming at the target equipment.

The image acquisition device may be any device capable of acquiring a video, and the target device is a device to be checked.

Step S402: from the video frames of the target video, a first device identification is identified, and a device information code is identified.

As can be seen from the foregoing description of the device video capture subsystem, the target video captured by the image capture device for the target device includes the first device identifier and the device information code.

The first device identifier may be any information that can uniquely identify the target device, and may be, for example, the aforementioned factory serial number, factory part number, fixed asset number, or the like.

The device information code may be any information code capable of carrying information, and for example, may be a two-dimensional code such as a DM (Data Matrix) code or a QR (Quick Response) code, or may be a barcode or an ARUCO code, or may be a pattern which is generated based on other encoding rules and carries information.

It should be noted that, when the first device identifier and the identification device information code are identified from the video frames of the target video in this step, identification is not necessarily performed for each video frame of the target video, but may be performed for each video frame one by one, and the identification may be stopped after the above contents are identified.

The manner in which the first device identification is identified from the video frame is first explained by the following steps a-C.

Step A: a first device identification area is located.

Specifically, the first device identification area may be located in the following manner.

In one embodiment, edge image features of a video frame may be extracted, and then a factory serial number region in the video frame may be determined according to the edge image features. For example, after extracting edge image features of a video frame, a region surrounded by character edge feature points is selected as a factory serial number region from a region surrounded by continuous edge feature points.

In another embodiment, the first target image feature of the first device identification area may be preset, in which case, the image feature of the video frame may be extracted, and the image area corresponding to the feature matching the first target image feature in the image feature may be determined as the first device identification area in the video frame.

And B: the first device identification is segmented into individual characters.

Specifically, the characters, numbers, letters, and the like in the first device identifier may be divided into individual characters according to preset parameters of the first device identifier, such as character color, character interval, character structure, and font.

And C: the individual characters that are segmented are identified.

In this step, the individual characters that are segmented can be identified in a variety of ways, and several examples are given below.

In a first embodiment, each individual character that is segmented may be identified based on template matching.

For example, similarity comparison is performed between each individual character and a template in a preset dictionary, and the template with the highest similarity is the recognition result of the character.

In the second embodiment, the features of the characters may be extracted, and the individual characters may be recognized based on the extracted features.

The features may be geometric moment features, feature point features, gridding features, etc. of the character.

In a third embodiment, the individual characters may be recognized based on a Support Vector Machine (Support Vector Machine).

In a fourth embodiment, the individual characters obtained by segmentation can be identified by a pre-trained convolutional neural network model. The training method of the convolutional neural network model is described in detail in the following examples, and will not be described in detail here.

A description will be given of a manner of identifying the device information code from the video frame of the target video.

In one embodiment, a target color parameter of the device information code may be set in advance, and the device information code may be determined from the video frame based on the target color parameter. Specifically, an area in the video frame where the color parameter is the target color parameter is identified, and the identified area is determined as an area where the device information code in the video frame is located. In this case, the target color of the device information code may be set in advance to a color distinguished from the target device.

In another embodiment, a second target image feature of the device information code may be preset, and the device information code may be determined from the video frame based on the second target image feature. In this case, the image feature of the video frame may be extracted, and an image area corresponding to a feature matching the second target image feature in the image feature may be determined as an area where the device information code in the video frame is located. Taking the device information code as a two-dimensional code as an example, since the image features of the two-dimensional code are obvious, the device information code can be better identified from the video frame by adopting the feature matching mode.

In another embodiment, the video frame may be binarized to obtain an intermediate image, and the device information code may be identified based on the corner points and the tilt angles of the device information code in the intermediate image. The detailed description is given in the following examples, and the detailed description is omitted here.

Step S403: and analyzing the equipment information code to obtain first equipment information of the target equipment.

As can be seen from the foregoing description of the device registration subsystem, the first device information recorded in the device information code may include the following device information: fixed asset number, equipment brand, equipment quantity, factory serial number, equipment user, tax amount, equipment purchase date, equipment identification image hash value, warehousing date and other information.

The embodiment of the present invention does not limit the way of parsing the device information code to obtain the first device information, and a way of parsing the device information code is exemplified through steps D to G.

Step D: the device information code is corrected.

Specifically, the tilt angle determined when the device information code is recognized from the video frame may be obtained, and then the device information code may be corrected according to the tilt angle. The manner of determining the tilt angle is described in detail in the following embodiments of identifying the device information code from the video frame, and will not be described in detail here.

Step E: and establishing a sampling grid aiming at the corrected equipment information code, and sampling the intersection points of the sampling grid.

Specifically, binarization processing may be performed on the corrected device information code, a sampling grid may be established for the device information code, and intersections of the sampling grid may be sampled to obtain pixel values of sampling points.

Step F: and obtaining a code word sequence recorded in the equipment information code according to the pixel values of the sampling points.

Specifically, a sampling point with a pixel value of 0 may be denoted as 0, and a sampling point with a pixel value of 255 may be denoted as 1, so as to obtain a codeword sequence of the two-dimensional code.

Step G: and decoding the code word sequence to obtain first device information of the target device represented by the code word sequence.

In this step, the codeword sequence may be decoded according to the type of the device information code and the coding rule corresponding to the device information code, so as to obtain the first device information represented by the codeword sequence.

Therefore, the code word sequence recorded in the equipment information code can be accurately obtained by correcting and sampling the equipment information code, and then the code word sequence can be decoded to accurately obtain the first equipment information of the target equipment represented by the code word sequence.

Step S404: and obtaining a second device identification of the target device stored locally based on the first device information.

As can be seen from the foregoing description of the device registration subsystem, device information of the target device is stored locally.

Specifically, the second device identification of the target device stored locally may be obtained in the following manner.

In one embodiment, information that can uniquely identify the target device in the first device information may be obtained, and a device identifier corresponding to the target device whose information matches the information may be locally searched as the second device identifier.

For example, the information that can uniquely identify the target device in the first device information may be a factory serial number, a factory part number, a fixed asset number, or the like.

In another embodiment, multiple types of information of the target device in the first device information may be obtained, and a device identifier corresponding to the target device whose information is matched with the multiple types of information is locally searched as the second device identifier.

For example, the plurality of types of information may be partial information such as a factory serial number, a device brand, a purchase date, and a warehousing date, or may be all information included in the first device information.

In another embodiment, a device identification image of the target device stored locally may be obtained based on the first device information, and a device identification in the device identification image may be identified as the second device identification.

The method for obtaining the device identification image based on the first device information can be obtained on the basis of the two methods for obtaining the second device identification based on the first device information, and the difference is only that the second device identification is replaced by the device identification image; and the way of identifying the device identifier in the device identifier image is the same as the way of identifying the first device identifier from the video frame, which is not described herein again.

It can be seen that this does not directly obtain the second device identification locally, but rather identifies the second device identification in the locally stored device identification image. From the perspective of data security, the image is less prone to being tampered than the identifier, and therefore the second device identifier is indirectly obtained based on the device identifier image which is less prone to being tampered, and accuracy of the obtained second device identifier is improved.

Step S405: and judging whether the first device identifier is the same as the second device identifier, if so, executing the step S406.

The first equipment identification is extracted from a target video collected by the target equipment and represents the actual equipment identification of the target equipment; the second device identifier is a device identifier obtained based on the device information code posted on the target device, and represents the device identifier at the time of initial registration of the target device.

Then, if the first device identifier is the same as the second device identifier, it indicates that the actual device identifier of the target device is consistent with the device identifier of the target device at the time of initial registration, and it may be considered that the device identifier of the target device has not been tampered or the content of the device information code has not been tampered.

Therefore, at this time, the subsequent step 406 may be executed to obtain the second device information corresponding to the locally stored second device identifier, so as to perform further comparison of the subsequent device information.

Step S406: and obtaining second device information corresponding to the second device identification stored locally.

And searching the device information of the target device with the device identification matched with the second device identification from the local as the second device information.

Step S407: and judging whether the first device information is the same as the second device information, if so, executing step S408.

The first device information is the device information of the target device extracted from the device identification code, the second device information is the device information of the target device stored locally, and as can be seen from the foregoing description of the device registration subsystem, the device identification code is generated based on the device information stored locally, and in the case where the device identification code is not tampered, the recorded device information thereof should be the same as the device information stored locally.

Therefore, if the recorded first device information is the same as the second device information stored locally, which indicates that the device information code has not been tampered with, the following step 408 may be executed to determine that the target device has successfully checked.

Step S408: and determining that the inventory of the target equipment is successful.

As can be seen from the above, when the device inventory is performed by applying the scheme provided in the embodiment of the present invention, the first device identifier and the device information code are identified from the target video collected for the target device, the first device information is analyzed from the device information code, the second device identifier of the target device stored locally is obtained based on the first device information, and if the first device identifier is the same as the second device identifier, the second device information corresponding to the second device identifier stored locally is further obtained, so that the target device inventory is determined to be successful under the condition that the first device information is the same as the second device information. Therefore, the equipment does not need to be checked by the checking personnel one by one, the electronic equipment completes the equipment checking, the workload required by the equipment checking is reduced, the checking efficiency of the equipment is improved, and the technical problems that manual checking is time-consuming, labor-consuming, high in cost and low in efficiency are solved.

In addition, the first device identifier is a device identifier extracted from a target video acquired from the target device, and represents an actual device identifier of the target device; the second device identifier is a device identifier obtained based on the device information code posted on the target device, and represents a device identifier when the target device initially registers, and if the first device identifier is different from the second device identifier, the second device identifier represents that the actual device identifier of the target device is inconsistent with the device identifier when the target device initially registers, that is, the device identifier of the target device is tampered, the content of the device information code is tampered or the device information code is mistakenly posted, and it is meaningless to perform subsequent device information comparison at this time. Therefore, the first device identifier and the second device identifier are judged firstly, and the first device information and the second device information are compared when the identifiers are the same, so that the consistency between the actual device identifier of the target device and the device identifier of the target device during initial registration can be ensured, the waste of time and computing resources caused by the comparison of subsequent device information when the identifiers are inconsistent can be prevented, and the inventory efficiency of the device and the practicability of an equipment inventory scheme are further improved.

In an embodiment of the present invention, the target video is: in this case, after the image capturing device receives the device inventory instruction, the image capturing device may further obtain the shooting time of the target video, determine whether the shooting time is earlier than the trigger time of the device inventory instruction, and if not, execute the subsequent step S402.

Specifically, the shooting time of the target video can be obtained in the following manner.

In one embodiment, the shooting time of the video may be read from file attribute information of the target video.

In another embodiment, the target video includes a shooting time watermark, in which case, the shooting time watermark may be identified from the target video to obtain the shooting time of the target video.

If the shooting time of the target video is earlier than the triggering time of the equipment inventory instruction, the target video is shot before the triggering of the equipment inventory instruction, and at the moment, the target video can be judged to be not in accordance with the equipment inventory requirement, so that the target video participating in the equipment inventory process is prevented from being the video shot in the past, the target video participating in the equipment inventory process is favorably ensured to be the latest video of the target equipment, the timeliness value of the target video is improved, and the accuracy of the equipment inventory result is favorably ensured.

In an embodiment of the present invention, the target video may further include a shooting location watermark, in this case, after the step S401, the shooting location watermark may be further identified from the target video to obtain a shooting location of the target video, and whether the shooting location belongs to a preset area where the device is located is determined, if so, the subsequent step S402 is executed.

Still another way of identifying the device information code from the video frame of the target video, which is mentioned in the foregoing step S402, is explained below through steps H to J.

Step H: and carrying out binarization processing on the target video frame to obtain an intermediate image.

Wherein, the target video frame is: one frame of video frame in the target video.

In order to facilitate the identification of the device information code from the target video frame, the target video frame may be first subjected to binarization processing to obtain an intermediate image, and then the device information code may be identified based on the intermediate image.

In this step, before performing binarization processing on the target video frame, preprocessing may be performed on the target video frame, where the preprocessing may include image compression, image graying processing, grayscale stretching, image denoising, image difference, and the like. A specific manner of performing graying processing on the target video frame is described in detail in the following examples, and will not be described in detail here.

Specifically, binarization processing may be performed on the target video frame based on a binarization threshold value to obtain an intermediate image. For example, the pixel value of the pixel point whose pixel value is smaller than the binarization threshold is set to 0, and the pixel value of the pixel point whose pixel value is larger than the binarization threshold is set to 255.

The binarization threshold may be preset, may be determined based on a pixel average value of the target video frame, or may be determined based on a histogram of the target video frame.

Step I: and determining the corner points and the inclination angles of the equipment information codes in the intermediate image.

Specifically, the corner points of the device information code may be identified from the intermediate image, and the tilt angle of the device information code in the intermediate image may be determined based on the relative position relationship of the corner points in the intermediate image.

For example, if the device information code is a rectangular two-dimensional code, four corner points of the device information code may be identified from the intermediate image, pixel coordinates of the four corner points in the intermediate image are obtained, and an inclination angle of a horizontal side of the device information code relative to the Y axis or an inclination angle of a vertical side of the device information code relative to the X axis is determined as the inclination angle by calculating a positional relationship between the obtained pixel coordinates.

Step J: and determining the area where the equipment information code is located from the intermediate image based on the angular point and the inclination angle, and identifying the equipment information code according to the determined area.

After the angular points and the inclination angles are obtained, the positions of all sides of the equipment information code in the intermediate image can be determined, so that the area surrounded by all sides can be determined as the area where the equipment information code is located, and the equipment information code can be identified according to the determined area.

Therefore, by carrying out binarization processing on the target video frame, the contrast of the obtained intermediate image is improved, the angular point and the inclination angle of the equipment information code are easier to determine from the intermediate image, and the accuracy of identifying the equipment information code from the image based on the angular point and the inclination angle is improved.

One way of graying the target video frame mentioned in the foregoing step H is described below.

In an embodiment of the present invention, a target video frame may be grayed by using an adaptive luminance balancing algorithm, so that an influence of uneven illumination on graying can be removed, and the specific manner is described in the following steps H1 to H4.

Step H1: aiming at each line of pixel points of the target video frame, equally dividing the pixel points of the line into a first number of pixel blocks to obtain the gray scale of each pixel block.

If the first number is N and each pixel block contains C pixels, the total number K = N × C of pixels in the line.

For a pixel block, if the gray value of each pixel point in the pixel block is respectively recorded as p _N1 、p _N2 、p _N3 ...p _NC Then its gray scale SL _N Can be calculated according to the following formula:

wherein the content of the first and second substances,

m is a predetermined parameter, H _pi The gray value of the largest M pixel points in the pixel block.

It can be seen that the gray scale SL of the pixel block obtained by the above formula _N The average value of the gray values of the maximum M pixel points in the pixel block is represented, so that the noise point interference can be reducedAnd (4) disturbing.

Step H2: determining the gray level difference between adjacent pixel blocks based on the obtained gray levels, then splitting the pixel blocks equally, and repeating the step of obtaining the gray level of each pixel block until the obtained gray level difference is less than a first threshold or the size of the pixel block is not more than a second threshold.

The first threshold value and the second threshold value may be preset by a worker.

In this step, after obtaining the gray scale difference and splitting the pixel blocks equally, it is determined whether the gray scale difference is smaller than a first threshold or whether the size of the pixel block is smaller than a second threshold, if not, the step H1 is returned to be executed, and if yes, the subsequent step H3 is executed.

Specifically, the gray scale difference Diff between the adjacent pixel blocks may be calculated by the following formula:

Diff＝|SL _N -SL _N+1 |

wherein SL _N And SL _N+1 Respectively representing the gray levels of two adjacent pixel blocks.

Step H3: and aiming at the adjacent pixel blocks, linear interpolation operation is used to obtain the gray value of each pixel point in the pixel blocks.

Specifically, the gray value S of each pixel point in the pixel block _Ni The following formula can be used for calculation:

wherein S is _Ni And expressing the gray value of the ith pixel point in the Nth pixel block.

Step H4: determining a brightness gain parameter of each pixel point based on the gray value of each pixel point, adjusting the gray value of each pixel point based on the determined brightness gain parameter, and obtaining a grayed image based on the adjusted gray value.

After the processing of step H3, the gray value of each pixel point represents the light distribution in the target video frame.

Specifically, the brightness gain parameter AGC of the pixel point _Ni The following formula can be used for calculation:

where BC denotes a coefficient value for controlling the image brightness, and is set by an operator based on experience.

After obtaining the brightness gain parameter, the following formula may be used to adjust the gray level of the pixel point:

wherein, P _Ni Representing the gray value of the pixel point before being processed,

and the gray values of the pixel points after adjustment.

After the gray value of each pixel point is adjusted, a gray image subjected to adaptive brightness equalization processing is obtained.

The aforementioned training method of the convolutional neural network model for recognizing individual characters is illustrated below.

Specifically, the convolutional layers and the fully-connected layers can be defined firstly, then folders of models and weight parameters are created, the image folders are traversed, sample pictures and labels are generated, a neural network model comprising two convolutional layers and a fully-connected layer is constructed, the model is subjected to iterative training by adopting an Adam gradient descent optimization algorithm, the trained models, the weight parameters and the like are stored through an API (application programming interface) provided by tensoflow, and the trained models are tested by using the segmented characters, numbers and letter images until the condition that the model training is finished is reached.

The sample picture is a picture containing characters, and the training end condition can be that the recognition accuracy reaches a preset index and the like.

As can be seen from the foregoing embodiment shown in fig. 4, the second device identifier may be obtained from a locally stored device identifier image, and in this case, it may be verified whether the device identifier image is tampered when the second device information is obtained. In view of the above, the embodiment of the present invention provides a second device inventory method.

Referring to fig. 5, a flowchart of a second method for checking an equipment according to an embodiment of the present invention is shown, and is applied to an electronic device, where the electronic device includes: the method comprises the following steps S501-S510.

Step S501: and obtaining a target video acquired by the image acquisition equipment aiming at the target equipment.

Step S502: from the video frames of the target video, a first device identification is identified, and a device information code is identified.

Step S503: and analyzing the equipment information code to obtain first equipment information of the target equipment.

The steps S501 to S503 are the same as the steps S401 to S403 in the embodiment shown in fig. 4, and are not described again here.

Step S504: and obtaining a second device identification of the target device stored locally based on the first device information.

In this step, a device identification image of the target device stored locally is obtained based on the first device information, and then a device identification in the device identification image is recognized as a second device identification. The specific implementation has already been described in step S404 in the foregoing embodiment shown in fig. 4, and is not described here again.

Step S505: and judging whether the first device identifier is the same as the second device identifier, if so, executing the step S506.

Step S506: image representation values of the device identification image are obtained.

Specifically, the image representation value of the device identification image may be obtained in the following manner.

In one embodiment, image representation values of the device identification image are stored locally. In this case, after the device identification image stored locally is obtained, the image characterization value stored in correspondence with the device identification image may be obtained.

In another embodiment, after obtaining the locally stored device identification image, an image characterization value of the resulting image may be calculated.

For example, the image representation value may be a hash value of the device identification image, such that after obtaining the device identification image, the hash value of the obtained image may be calculated as the image representation value of the device identification image. The manner of calculating the hash value of the device identification image has been described in the foregoing embodiment, and is not described herein again.

Step S507: and detecting whether other nodes in the distributed system store image representation values, and if so, executing step S508.

As can be seen from the foregoing embodiment, the image representation values stored in the other nodes are the image representation values of the device identification image, and therefore, if all the other nodes in the distributed system store the image representation values, it indicates that the device identification image locally stored in the electronic device has not been changed, that is, has not been tampered with.

Step S508: and obtaining second device information corresponding to the second device identification stored locally.

Step S509: determining whether the first device information is the same as the second device information, if so, executing step S510.

Step S510: and determining that the inventory of the target equipment is successful.

The foregoing steps S508 to S510 are the same as the steps S406 to S408 in the embodiment shown in fig. 4, and are not repeated herein.

As can be seen from the above, before the second device information corresponding to the locally stored second device identifier is obtained, it is first verified whether the locally stored device identifier image is not tampered by detecting whether the image representation value of the device identifier image is stored in another node in the distributed system, and the second device information is obtained for subsequent comparison when the locally stored device identifier image passes the detection, so that the reliability and authenticity of the second device information obtained based on the second device identifier, and the efficiency of the device inventory scheme are further improved.

On the basis of the foregoing embodiment shown in fig. 4, it is verified whether the first device information is the same as the second device information, and it can also be determined whether the second device information stored locally is tampered. In view of the above, the embodiment of the present invention provides a third device inventory method.

Referring to fig. 6, a flowchart of a third method for checking an equipment according to an embodiment of the present invention is schematically shown, and is applied to an electronic device, where the electronic device is: the method comprises the following steps S601-S610.

Step S601: and obtaining a target video acquired by the image acquisition equipment aiming at the target equipment.

Step S602: from the video frames of the target video, a first device identification is identified, and a device information code is identified.

Step S603: and analyzing the equipment information code to obtain first equipment information of the target equipment.

Step S604: and obtaining a second device identification of the target device stored locally based on the first device information.

Step S605: and judging whether the first device identifier is the same as the second device identifier, if so, executing the step S606.

Step S606: and obtaining second device information corresponding to the second device identification stored locally.

The steps S601 to S606 are the same as the steps S401 to S406 in the embodiment shown in fig. 4, and are not repeated here.

Step S607: and obtaining an information representation value of the second device information.

Specifically, the information characterizing value of the second device information may be obtained in the following manner.

In one embodiment, the information characterizing value of the second device information is stored locally. In this case, after the second device information stored locally is obtained, the information characterizing value stored in correspondence with the second device information may be obtained.

In another embodiment, after the second device information stored locally is obtained, an information characterizing value of the obtained second device information may be calculated.

For example, the information characterizing value may be a hash value of the second device information, such that after obtaining the second device information, the obtained hash value of the second device information may be calculated as the information characterizing value of the second device information. The calculation method of the hash value of the second device information may be obtained based on the calculation method of the hash value of the device identification image described above, and is not described here again.

Step S608: and detecting whether other nodes in the distributed system store information representation values, and if so, executing the step S609.

The information characteristic value stored in the other node is the information characteristic value of the second device information, and therefore, if the other nodes in the distributed system all store the information characteristic value, it indicates that the second device information locally stored in the electronic device is not changed, that is, has not been tampered.

Step S609: whether the first device information is the same as the second device information is judged, and if yes, step S610 is executed.

Step S610: and determining that the inventory of the target equipment is successful.

The foregoing steps S609 to S610 are the same as the steps S407 to S408 in the embodiment shown in fig. 4, and are not described again here.

As can be seen from the above, before determining whether the first device information is the same as the second device information, it is first verified whether the locally stored second device information is not tampered by detecting whether the information characterizing value of the second device information is stored in other nodes in the distributed system, and the first device information is compared with the second device information when the locally stored second device information passes the detection, so that the reliability and the authenticity of the obtained second device information are further improved, and the efficiency of the device inventory scheme is improved.

Of course, in an embodiment of the present invention, the equipment inventory schemes shown in fig. 5 and fig. 6 may also be combined, since the related embodiments are described in fig. 5 and fig. 6, respectively, and will not be described in detail here, the following is briefly described as follows:

after the second device identification is obtained, whether the locally stored device identification image is not tampered or not is verified based on other nodes in the distributed system, the device identification image is detected and then second device information is obtained based on the second device identification, whether the locally stored second device information is not tampered or is verified based on other nodes in the distributed system, and the first device information and the second device information are compared when the second device information is detected.

The following describes an overall device inventory process provided by an embodiment of the present invention.

Fig. 7 is a schematic diagram of an equipment inventory process according to an embodiment of the present invention.

The device inventory flow shown in fig. 7 will be described below from two perspectives of device registration and device inventory.

1. Device registration

Acquiring equipment information and acquiring an equipment identification image, on one hand, storing the acquired equipment information and the equipment identification image, and generating an equipment information code based on the stored information so that a worker prints the equipment information code and posts the equipment information code on equipment; on the other hand, a device identification image hash value is generated, and distributed storage is performed on the hash value, that is, the hash value is stored in other nodes in the distributed system.

2. Receiving an equipment inventory instruction to perform equipment inventory

(1) After receiving the device inventory instruction, the image acquisition device records the device video and starts the watermark function, so that the device video automatically generates the watermark.

(2) Splitting the video of the equipment into images, and then extracting the serial number of the equipment in the images on one hand; on the other hand, information in the device information code in the image is extracted, and a device serial number in the device identification image stored locally is obtained according to the extracted information.

Specifically, the video data may be split frame by frame, so as to obtain a split image.

(3) And comparing the serial numbers of the devices, obtaining device acquisition information after comparison, obtaining device account information, and checking the devices based on the device acquisition information and the device account information.

The device acquisition information is first device information stored in the device identification code, and the device account information is second device information stored locally.

Specifically, whether the device acquisition information is completely consistent with the device account information or not can be judged, if yes, it indicates that the device is checked without profit or loss, and if not, it indicates that the information of the physical device and the account device is different, and the subsequent processing can be further performed according to the difference information.

Corresponding to the above equipment checking method, the embodiment of the invention also provides an equipment checking device.

Referring to fig. 8, a schematic structural diagram of an equipment inventory apparatus according to an embodiment of the present invention is provided, where the apparatus includes the following modules 801 to 806.

A target video obtaining module 801, configured to obtain a target video, which is collected by an image collection device for a target device;

an information identification module 802, configured to identify a first device identifier from a video frame of the target video, and identify a device information code;

a first device information obtaining module 803, configured to analyze the device information code to obtain first device information of the target device;

a device identifier obtaining module 804, configured to obtain a second device identifier of the target device, which is locally stored, based on the first device information;

a second device information obtaining module 805, configured to obtain second device information corresponding to the second device identifier that is locally stored, if the first device identifier is the same as the second device identifier;

a device inventory module 806, configured to determine that the target device is successfully inventoried when the first device information is the same as the second device information.

As can be seen from the above, when the scheme provided by the embodiment of the present invention is applied to perform device inventory, a first device identifier and a device information code are identified from a target video acquired for a target device, first device information is analyzed from the device information code, then a second device identifier of the target device stored locally is obtained based on the first device information, and if the first device identifier is the same as the second device identifier, second device information corresponding to the second device identifier stored locally is further obtained, so that it is determined that the target device inventory is successful under the condition that the first device information is the same as the second device information. Therefore, the equipment does not need to be checked by the checking personnel one by one, the electronic equipment completes the equipment checking, the workload required by the equipment checking is reduced, the checking efficiency of the equipment is improved, and the technical problems that manual checking is time-consuming, labor-consuming, high in cost and low in efficiency are solved.

In an embodiment of the present invention, the device identifier obtaining module 804 is specifically configured to obtain, based on the first device information, a device identifier image of the target device stored locally; and identifying the equipment identifier in the equipment identifier image as a second equipment identifier.

It can be seen that this identifies the second device identification in the locally stored device identification image, rather than directly obtaining it locally. From the perspective of data security, the image is less prone to being tampered than the identifier, and therefore the second device identifier is indirectly obtained based on the device identifier image which is less prone to being tampered, and accuracy of the obtained second device identifier is improved.

In an embodiment of the present invention, the electronic device is: a node in a distributed system;

the second device information obtaining module 805 is specifically configured to obtain an image representation value of the device identifier image if the first device identifier is the same as the second device identifier; detecting whether other nodes in the distributed system store the image representation values or not; and if so, obtaining second equipment information corresponding to the second equipment identifier stored locally.

As can be seen from the above, before obtaining the second device information corresponding to the locally stored second device identifier, it is first verified whether the locally stored device identifier image is not tampered by detecting whether the image representation value of the device identifier image is stored in another node in the distributed system, and the second device information is obtained for subsequent comparison when the locally stored device identifier image passes the detection, so that the reliability and the authenticity of the second device information obtained based on the second device identifier, and the efficiency of the device inventory scheme are further improved.

the device inventory module 806 is specifically configured to obtain an information representation value of the second device information; detecting whether other nodes in the distributed system store the information representation values or not; if so, and the first device information is the same as the second device information, and the target device is determined to be successfully checked.

In an embodiment of the present invention, the target video is: the image acquisition equipment receives a video acquired by the target equipment after receiving an equipment inventory instruction;

after the target video obtaining module 801, the method further includes:

the shooting time obtaining module is used for obtaining the shooting time of the target video;

a time judgment module, configured to judge whether the shooting time is earlier than the trigger time of the device inventory instruction, and if not, trigger the information identification module 802.

If the shooting time of the target video is earlier than the triggering time of the equipment inventory instruction, the target video is shot before the triggering of the equipment inventory instruction, and then the target video can be judged to be not in accordance with the equipment inventory requirement, so that the target video participating in the equipment inventory process is prevented from being a video shot in the past, the target video participating in the equipment inventory process is favorably ensured to be the latest video of the target equipment, the timeliness value of the target video is improved, and the accuracy of the equipment inventory result is favorably ensured.

In one embodiment of the present invention, the device information code is identified by:

an intermediate image obtaining module, configured to perform binarization processing on a target video frame to obtain an intermediate image, where the target video frame is: a frame of video frames in the target video;

the information code position determining module is used for determining the angular point and the inclination angle of the equipment information code in the intermediate image;

and the information code identification module is used for determining the area where the equipment information code is located from the intermediate image based on the angular point and the inclination angle, and identifying the equipment information code according to the determined area.

Thus, by carrying out binarization processing on the target video frame, the contrast of the obtained intermediate image is improved, the angular point and the inclination angle of the equipment information code are easier to determine from the intermediate image, and the accuracy of identifying the equipment information code from the image based on the angular point and the inclination angle is improved.

In an embodiment of the present invention, the first device information obtaining module 803 is specifically configured to correct the device information code; establishing a sampling grid aiming at the corrected equipment information code; sampling the intersection points of the sampling grid; obtaining a code word sequence recorded in the equipment information code according to the pixel value of the sampling point; and decoding the code word sequence to obtain first device information of the target device represented by the code word sequence.

An embodiment of the present invention further provides an electronic device, as shown in fig. 9, which includes a processor 901, a communication interface 902, a memory 903, and a communication bus 904, where the processor 901, the communication interface 902, and the memory 903 complete mutual communication through the communication bus 904,

a memory 903 for storing computer programs;

the processor 901 is configured to implement the device inventory method provided in the embodiment of the present invention when executing the program stored in the memory 903.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In still another embodiment provided by the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the device inventory method provided by the embodiment of the present invention.

In yet another embodiment provided by the present invention, a computer program product containing instructions is also provided, which when run on a computer, causes the computer to execute the device inventory method provided by the embodiment of the present invention.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, the electronic device, and the storage medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. An apparatus inventory method, applied to an electronic apparatus, the method comprising:

acquiring a target video acquired by image acquisition equipment aiming at target equipment;

2. The method of claim 1, wherein obtaining the locally stored second device identification of the target device based on the first device information comprises:

obtaining a locally stored device identification image of the target device based on the first device information;

and identifying the equipment identifier in the equipment identifier image as a second equipment identifier.

3. The method of claim 2, wherein the electronic device is: a node in a distributed system;

the obtaining second device information corresponding to the locally stored second device identifier includes:

obtaining an image representation value of the device identification image;

detecting whether other nodes in the distributed system store the image representation values or not;

and if so, obtaining second equipment information corresponding to the second equipment identifier stored locally.

4. The method of claim 1, wherein the electronic device is: a node in a distributed system;

the determining that the target device has successfully checked the device information under the condition that the first device information is the same as the second device information includes:

obtaining an information representation value of the second device information;

detecting whether other nodes in the distributed system store the information representation values or not;

if so, and the first device information is the same as the second device information, determining that the target device is successfully checked.

5. The method according to any one of claims 1 to 4,

the target video is as follows: the image acquisition equipment receives a video acquired by the target equipment after receiving an equipment inventory instruction;

after the obtaining of the target video captured by the image capturing device for the target device, the method further includes:

acquiring shooting time of the target video;

judging whether the shooting time is earlier than the trigger time of the equipment inventory instruction or not;

and if the video frame is not earlier than the target video frame, identifying a first device identifier from the video frame of the target video and identifying a device information code.

6. The method according to any one of claims 1 to 4, wherein the device information code is identified by:

carrying out binarization processing on a target video frame to obtain an intermediate image, wherein the target video frame is as follows: a frame of video frames in the target video;

determining the angular point and the inclination angle of the equipment information code in the intermediate image;

and determining the area where the equipment information code is located from the intermediate image based on the angular point and the inclination angle, and identifying the equipment information code according to the determined area.

7. The method according to any one of claims 1 to 4, wherein the parsing the device information code to obtain the first device information of the target device includes:

correcting the equipment information code;

establishing a sampling grid aiming at the corrected equipment information code;

sampling the intersection points of the sampling grid;

obtaining a code word sequence recorded in the equipment information code according to the pixel value of the sampling point;

and decoding the code word sequence to obtain first device information of the target device represented by the code word sequence.

8. An equipment inventory device, applied to electronic equipment, the device comprising:

a second device information obtaining module, configured to obtain second device information corresponding to the second device identifier that is locally stored, if the first device identifier is the same as the second device identifier;

9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1 to 7 when executing a program stored in the memory.

10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.