On-site photographing work order verification method in network-free environment

Abstract

The invention discloses an on-site photographing work order verification method in a network-free environment, and relates to the technical field of picture verification, and the method comprises the steps: obtaining an on-site work order picture and a first photographing parameter of the on-site work order picture when a terminal device is in the network-free environment, and adding a watermark to the on-site work order picture based on the first photographing parameter; converting the field work order photo added with the watermark into a compressed file, adding a first shooting parameter to the compressed file to obtain a to-be-uploaded file, and storing the to-be-uploaded file; after monitoring that the terminal equipment recovers the network, extracting a field work order photo and a first shooting parameter in the to-be-uploaded file, and analyzing watermark information in the field work order photo to obtain a second shooting parameter of the field work order photo; and comparing the first shooting parameter with the second shooting parameter, and uploading the site work order picture under the condition that the first shooting parameter is consistent with the second shooting parameter. The effect of ensuring the authenticity of the field work order picture uploaded after the network is recovered is realized.

Description

Technical Field

[0001] The present application relates to the technical field of picture verification, and in particular to a method for verifying on-site photo work orders in a network-free environment. Background Art

[0002] When frontline engineers go to the site for inspection and conduct on-site acceptance work, they often need to take photos of the site or related work orders and upload them. However, since the construction site may be located in a high mountain or remote mountain village, there may be weak or no mobile network signals, which makes it impossible for existing frontline engineers to upload photos of on-site work orders through mobile phones and other terminals. To solve this problem, the current method is mainly to store the photos of on-site work orders in the terminal album first, and then select the photos of on-site work orders from the terminal device album for upload after the network environment is available. However, this method may cause users to tamper with the photos of on-site work orders in the terminal album, making it difficult to ensure the authenticity of the uploaded on-site work order photos.

[0003] Therefore, how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored is a problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of this application is to provide a method for verifying on-site work order by taking photos in a network-free environment, aiming to solve the technical problem of how to ensure the authenticity of on-site work order photos uploaded by the terminal device after the network is restored.

[0005] To achieve the above purpose, the present application proposes a method for verifying a work order by taking photos on site in a network-free environment. The method for verifying a work order by taking photos on site in a network-free environment is applied to a terminal device. The method for verifying a work order by taking photos on site in a network-free environment includes:

[0006] When the terminal device is in a network-free environment, obtaining a site work order photo and a first shooting parameter of the site work order photo, and adding a watermark to the site work order photo based on the first shooting parameter;

[0007] Converting the watermarked on-site work order photo into a compressed file, appending the first shooting parameter to the compressed file to obtain a file to be uploaded, and saving the file to be uploaded;

[0008] After monitoring that the terminal device has restored the network, extracting the on-site work order photo and the first shooting parameter in the file to be uploaded, and parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo;

[0009] The first shooting parameter and the second shooting parameter are compared, and when the first shooting parameter and the second shooting parameter are consistent, the on-site work order photo is uploaded.

[0010] In one embodiment, the step of parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo includes:

[0011] Generate a plurality of feature vectors of preset sizes of the on-site work order photo through a convolutional neural network model, and input each of the feature vectors into a recurrent neural network model;

[0012] In the recurrent neural network model, a feature map is generated based on each of the feature vectors, and the feature map is mapped to an output category;

[0013] A target neuron with the highest activation value among the neurons corresponding to the output category is selected to determine the second shooting parameter corresponding to the watermark information based on the target neuron.

[0014] In one embodiment, the step of generating a plurality of feature vectors of preset sizes of the on-site work order photo by using a convolutional neural network model comprises:

[0015] Extracting initial features of the on-site work order photo through the convolutional neural network model to obtain an initial feature map;

[0016] A plurality of feature vectors of preset sizes are generated by applying a sliding window of preset sizes in the initial feature map based on the watermark position of the on-site work order photo.

[0017] In one embodiment, the second shooting parameters at least include a second shooting position, a second shooting time, second photographer information, and a second work order number, and the step of determining the second shooting parameters corresponding to the watermark information based on the target neuron includes:

[0018] The watermark information recognition result corresponding to the target neuron is obtained, and the watermark information recognition result is divided to obtain the second shooting position, the second shooting time, the second photographer information and the second work order number.

[0019] In one embodiment, the step of adding the first shooting parameter to the compressed file to obtain the file to be uploaded, and saving the file to be uploaded includes:

[0020] Adding the first shooting parameter to the compressed file to obtain a candidate file to be uploaded;

[0021] The candidate file to be uploaded is symmetrically encrypted to obtain the file to be uploaded, and the file to be uploaded is saved.

[0022] In one embodiment, the first shooting parameters at least include a first shooting position, a first shooting time, first photographer information and a first work order number, and after monitoring that the terminal device has restored the network, the step of extracting the on-site work order photo and the first shooting parameters from the file to be uploaded includes:

[0023] After monitoring that the terminal device has restored the network, verifying the hash value of the file to be uploaded based on the original hash value;

[0024] When the original hash value is consistent with the hash value, the file to be uploaded is symmetrically decrypted, and the on-site work order photo, the first shooting location, the first shooting time, the first photographer information and the first work order number are extracted from the symmetrically decrypted file.

[0025] In one embodiment, the on-site photo work order verification method in a non-network environment further includes:

[0026] During the process of taking the on-site work order photo, obtaining device parameters of the terminal device, wherein the device parameters at least include flight mode status, signal power, and signal strength;

[0027] When the device parameters meet the preset shooting conditions, it is determined that the terminal device is in the network-free environment.

[0028] In addition, to achieve the above purpose, the present application also proposes an on-site photo work order verification device, which is applied to a terminal device and includes:

[0029] A watermark adding module, used for obtaining a site work order photo and a first shooting parameter of the site work order photo when the terminal device is in a network-free environment, and adding a watermark to the site work order photo based on the first shooting parameter;

[0030] A compression module, used to convert the watermarked on-site work order photo into a compressed file, append the first shooting parameter to the compressed file to obtain a file to be uploaded, and save the file to be uploaded;

[0031] A parsing module, configured to extract the on-site work order photo and the first shooting parameter from the file to be uploaded after monitoring that the terminal device has restored the network, and parse the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo;

[0032] The uploading module is used to compare the first shooting parameter with the second shooting parameter, and upload the on-site work order photo when the first shooting parameter is consistent with the second shooting parameter.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the on-site photo taking work order verification method in a network-free environment as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the on-site photo-taking work order verification method in a network-free environment as described above are implemented.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the on-site photo-taking work order verification method in a network-free environment as described above.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] The present application first obtains a field work order photo and a first shooting parameter of the field work order photo when the terminal device is in a network-free environment, and adds a watermark to the field work order photo based on the first shooting parameter to ensure that the original shooting information of the field work order photo taken in a network-free environment is recorded, so as to facilitate subsequent verification of the authenticity of the field work order photo; the field work order photo with the watermark added is converted into a compressed file, the first shooting parameter is appended to the compressed file to obtain the file to be uploaded, and the file to be uploaded is saved to provide a data basis for uploading the field work order photo, and the storage efficiency of the field work order photo is improved through compression, and the additional parameters are used for subsequent judgment of the field work order The authenticity of the photo is determined by the following method: after monitoring that the terminal device has restored the network, the on-site work order photo and the first shooting parameter are extracted from the file to be uploaded, and the watermark information in the on-site work order photo is parsed to obtain the second shooting parameter of the on-site work order photo, which provides a basis for judging whether the shooting parameters of the on-site work order photo are consistent when shooting and when uploading; the first shooting parameter and the second shooting parameter are compared, and when the first shooting parameter and the second shooting parameter are consistent, the on-site work order photo is uploaded to ensure that the shooting parameters of the on-site work order photo are consistent when shooting and when uploading, thereby ensuring the authenticity of the uploaded on-site work order photo.

[0038] To summarize, the present application adds a watermark based on shooting parameters to on-site work order photos taken in an off-network environment, and parses the watermark after the network is restored to verify whether the shooting parameters have changed. If the shooting parameters have not changed, the on-site work order photos are uploaded, thereby ensuring the authenticity of the on-site work order photos uploaded after the network is restored. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flowchart diagram of the first embodiment of the on-site photo work order verification method in a network-free environment provided by this application;

[0042] Figure 2 A flowchart diagram of the second embodiment of the on-site photo work order verification method in a network-free environment provided by this application;

[0043] Figure 3 A schematic diagram of a simplified process of a method for verifying an on-site photo work order in a network-free environment provided in the second embodiment of the present application;

[0044] Figure 4 This is a schematic diagram of the module structure of the on-site photo work order verification device of the embodiment of the present application;

[0045] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the on-site photo-taking work order verification method in a non-network environment in an embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] The main solution of the embodiment of the present application is: when the terminal device is in a network-free environment, obtain the on-site work order photo and the first shooting parameter of the on-site work order photo, and add a watermark to the on-site work order photo based on the first shooting parameter; convert the on-site work order photo with the watermark into a compressed file, append the first shooting parameter to the compressed file to obtain the file to be uploaded, and save the file to be uploaded; after monitoring that the terminal device has restored the network, extract the on-site work order photo and the first shooting parameter in the file to be uploaded, and parse the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo; compare the first shooting parameter and the second shooting parameter, and upload the on-site work order photo when the first shooting parameter and the second shooting parameter are consistent.

[0050] The existing technology mainly stores the on-site work order photos in the terminal album first, and then selects the on-site work order photos from the terminal album for uploading after the network environment is available. However, this method may cause the user to tamper with the on-site work order photos in the terminal album, making it difficult to ensure the authenticity of the uploaded on-site work order photos. Therefore, how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored is a problem that needs to be solved urgently.

[0051] The present application provides a solution by adding a watermark based on shooting parameters to on-site work order photos taken in an off-network environment, and parsing the watermark after the network is restored to verify whether the shooting parameters have changed. If the shooting parameters have not changed, the on-site work order photos are uploaded, thereby ensuring the authenticity of the on-site work order photos uploaded after the network is restored.

[0052] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes an electronic device as an example to illustrate this embodiment and the following embodiments.

[0053] Based on this, the embodiment of the present application provides a method for verifying a work order for on-site photography in a non-network environment. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the on-site photo taking work order verification method in a network-free environment of the present application.

[0054] In this embodiment, the on-site photo work order verification method in a non-network environment is applied to a terminal device, and the on-site photo work order verification method in a non-network environment includes steps S10 to S40:

[0055] Step S10, when the terminal device is in a network-free environment, obtaining a site work order photo and a first shooting parameter of the site work order photo, and adding a watermark to the site work order photo based on the first shooting parameter;

[0056] It should be noted that a no-network environment refers to a situation where, when the terminal device takes on-site work order photos, the terminal device is not connected to the Internet or the connection to the Internet is too weak. The first shooting parameter refers to various information related to obtaining on-site work order photos in a no-network environment, which may include shooting location, shooting time and photographer information.

[0057] It is understandable that since the on-site work order photos taken in an off-network environment may have problems such as unreliable source of the on-site work order photos and tampered content of the on-site work order photos, step S10 is performed to add a watermark to the on-site work order photos to implicitly record the shooting parameters in the on-site work order photos, so as to facilitate the subsequent verification of the source and non-tampered status of the on-site work order photos during the upload process.

[0058] Exemplarily, the shooting parameters of the on-site work order photo are obtained, and the shooting parameters are added to the on-site work order photo as a watermark by calling the Canvas API (Application Programming Interface) of HTML5 (Hyper Text Markup Language 5.0).

[0059] Step S20, converting the watermarked on-site work order photo into a compressed file, appending the first shooting parameter to the compressed file to obtain a file to be uploaded, and saving the file to be uploaded;

[0060] It should be noted that a compressed file refers to a data file processed by a specific compression algorithm, which contains the data of the on-site work order photo, but is smaller in size and easier to store and transmit; a file to be uploaded refers to a file that contains the data of the on-site work order photo and the first shooting parameters, and is ready to be uploaded to a server or other storage platform.

[0061] It is understandable that since the photos of on-site work orders taken are often large in file size, resulting in low storage efficiency, step S20 is performed to compress the shot files, reduce the demand for storage space for the shot files, and improve the storage efficiency of the shot files. At the same time, by appending the shooting parameters to the compressed files, it is guaranteed that these key information can be accessed and verified during the subsequent upload process, providing a basis for judging the authenticity of the on-site work order photos.

[0062] Exemplarily, the Canvas API of HTML5 is called to compress the on-site work order photo with a watermark to obtain a compressed file, and the compressed file is converted into a Base64 format encoding, so that the first shooting parameter is added to the Base64 format encoding to obtain a file to be uploaded, and the file to be uploaded is saved in the application file directory of the terminal device, thereby avoiding the problem of easy loss of on-site work order photos when they are saved in the terminal device album, thereby improving the storage security of on-site work order photos.

[0063] In a feasible implementation manner, the step of adding the first shooting parameter to the compressed file to obtain the file to be uploaded and saving the file to be uploaded in step S20 may include steps S21 to S22:

[0064] Step S21, adding the first shooting parameter to the compressed file to obtain a candidate file to be uploaded;

[0065] It should be noted that the candidate file to be uploaded refers to a compressed file containing the on-site work order photo with a watermark and the first shooting parameter.

[0066] It is understandable that in the process of uploading the on-site work order photo, the shooting parameters corresponding to the on-site work order photo may not be accurately obtained because the shooting parameters are separated from the on-site work order photo. Therefore, step S21 is performed to attach the shooting parameters to the compressed file to ensure that the on-site work order photo and the shooting parameters corresponding to the on-site work order photo are saved together, thereby improving the efficiency of accessing and verifying the shooting parameters of the on-site work order photo.

[0067] Exemplarily, the first shooting parameter is added to a compressed file encoded in Base64 format to obtain a candidate file to be uploaded encoded in Base64 format.

[0068] Step S22, symmetrically encrypt the candidate file to be uploaded to obtain the file to be uploaded, and save the file to be uploaded.

[0069] It should be noted that symmetric encryption refers to an encryption method that uses the same key for encryption and decryption. This encryption method ensures that only those who have the correct key can decrypt and access the file contents.

[0070] In addition, it should be noted that the methods used for symmetric encryption may include AES (Advanced Encryption Standard) method, DES (Data Encryption Standard) method, 3DES (Triple Data Encryption Standard) method, etc. The specific implementation method of symmetric encryption is not limited in this embodiment.

[0071] It is understandable that since there may be a risk of information leakage or Trojan attack in the process of saving files containing on-site work order photos and shooting parameters, step S22 is performed to improve the storage security of the files to be uploaded by symmetrically encrypting the candidate files to be uploaded containing on-site work order photos and shooting parameters.

[0072] Exemplarily, the candidate file to be uploaded encoded in Base64 format is encrypted by AES to obtain the file to be uploaded, and the file to be uploaded is saved in the application file directory of the terminal device.

[0073] In this implementation, by appending the shooting parameters to the compressed file and encrypting the file using a symmetric encryption algorithm, the image metadata, i.e., the first shooting parameter, and the content, i.e., the on-site work order photo, are securely encapsulated together, and the file content is protected from unauthorized access.

[0074] Step S30, after monitoring that the terminal device has restored the network, extracting the on-site work order photo and the first shooting parameter from the file to be uploaded, and parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo;

[0075] It should be noted that network recovery refers to a situation where the connection status between the terminal device and the Internet meets preset conditions, which may include that the signal power between the terminal device and the Internet is above the preset power, the signal strength between the terminal device and the Internet is above the preset strength, etc.; watermark information refers to an invisible or semi-visible mark embedded in the captured image, which contains the shooting parameters for taking the on-site work order photo; the second shooting parameters refer to a set of relevant data about the on-site work order photo obtained after parsing the watermark information.

[0076] It is understandable that since it is difficult to identify whether the content of the on-site work order photos taken in a networkless environment has been tampered with after the network is restored, step S30 is performed to avoid the inability to identify the shooting parameters of the files uploaded after the network is restored, thereby providing an effective judgment basis for identifying whether the on-site work order photos have been tampered with.

[0077] In a feasible implementation manner, the first shooting parameters at least include a first shooting position, a first shooting time, first photographer information and a first work order number. The step of extracting the on-site work order photo and the first shooting parameters from the to-be-uploaded file after monitoring that the terminal device has restored the network in step S30 may include steps S301 to S302:

[0078] Step S301, after monitoring that the terminal device has restored the network, verifying the hash value of the file to be uploaded based on the original hash value, wherein the original hash value is calculated when the file to be uploaded is obtained by symmetrical encryption in a networkless environment, and the hash value is calculated when the on-site work order photo is uploaded after the terminal device restores the network;

[0079] It should be noted that the original hash value refers to the unique fixed-length string obtained after the hash function calculation is performed on the file to be uploaded, which is used to verify whether the file to be uploaded has been tampered with; the hash value refers to the unique fixed-length string obtained after the hash function calculation is performed on the file to be uploaded, which is used to reflect whether the content of the file to be uploaded has been changed.

[0080] In addition, it should be noted that the original hash value may include MD5 (Message-Digest Algorithm) code, SHA (Secure Hash Algorithm) code, etc., and the type of the original hash value is not limited in this embodiment; the hash value may include MD5 code, SHA code, etc., and the type of the hash value is not limited in this embodiment.

[0081] It is understandable that since the file to be uploaded may be tampered with during the storage process in an off-network environment, step S301 is performed to verify the hash value of the file to be uploaded to ensure that the content of the file to be uploaded is consistent before and after uploading, thereby further ensuring the authenticity of the data.

[0082] Exemplarily, after monitoring that the terminal device has restored the network, the MD5 code of the file to be uploaded calculated in a network-free environment is compared with the MD5 code of the file to be uploaded calculated when uploading the on-site work order photo after the terminal device restores the network.

[0083] Step S302, when the original hash value is consistent with the hash value, the file to be uploaded is symmetrically decrypted, and the on-site work order photo, the first shooting location, the first shooting time, the first photographer information and the first work order number are extracted from the symmetrically decrypted file.

[0084] It should be noted that symmetric decryption refers to a decryption method that uses the same key for encryption and decryption. This decryption method ensures that only people with the correct key can decrypt and access the file content. The decryption method and the symmetric encryption method correspond to each other; the first shooting location refers to the geographical location information when the on-site work order photo was taken; the first shooting time refers to the exact time point when the on-site work order photo was taken; the first photographer information refers to the relevant information of the photographer who took the on-site work order photo, and the relevant information may include information such as the name or number of the photographer; the first work order number refers to the work order number of the on-site work order obtained by identifying the on-site work order photo through OCR (Optical Character Recognition).

[0085] It is understandable that since the file to be uploaded is an encrypted file, step S302 is performed to symmetrically decrypt the symmetrically encrypted file, thereby avoiding the problem of the file being inaccessible after encryption, and achieving safe decryption of the file to be uploaded, so that the file content of the uploaded file can be accessed and processed. At the same time, the key shooting parameters are extracted, providing an effective basis for judging the authenticity of the on-site work order photos.

[0086] Exemplarily, when the MD5 code of the file to be uploaded is changed, the file to be uploaded encrypted using AES is decrypted by AES, and information such as the shooting location, shooting time, photographer's name, and work order number of the on-site work order are extracted from the decrypted file.

[0087] In this implementation, by using hash value verification and symmetric decryption, it is possible to ensure that the file content has not been tampered with before uploading, and the file content can be securely accessed during uploading, thereby allowing the authenticity and source of the on-site work order photos to be verified.

[0088] In a feasible implementation manner, the step of parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo in step S30 may include steps S31 to S33:

[0089] Step S31, generating feature vectors of multiple preset sizes of the on-site work order photo through a convolutional neural network model, and inputting each of the feature vectors into a recurrent neural network model;

[0090] It should be noted that the Convolutional Neural Networks (CNN) model is a deep learning model specifically used to process data with grid nodes. The CNN can automatically and hierarchically extract features from images by using convolutional layers; a feature vector refers to a set of values ​​extracted from on-site work order photos through a convolutional neural network, which represents the specific features of the image; a Recurrent Neural Network (RNN) model refers to a deep learning model that processes sequence data, namely feature vectors, and the RNN can utilize the temporal dynamic behavior in sequence data.

[0091] In addition, it should be noted that the convolutional neural network model may include standard CNN, deep CNN such as VGGNet (Visual Geometry Group Network), ResNet (Residual Neural Network), etc., and the type of CNN is not limited in this embodiment; the recurrent neural network model may include standard RNN, LSTM (Long Short-Term Memory), etc., and the type of RNN is not limited in this embodiment.

[0092] In a feasible implementation manner, the step of generating a plurality of feature vectors of preset sizes of the on-site work order photo by a convolutional neural network model in step S31 may include steps S311 to S312:

[0093] Step S311, extracting initial features of the on-site work order photo through the convolutional neural network model to obtain an initial feature map;

[0094] It should be noted that the initial feature refers to the image feature obtained through CNN processing, which is usually the basic structural information in the image; the initial feature map refers to the spatial distribution map of the initial feature in the image, and the value at each position of the spatial distribution map represents the feature intensity or existence at that position.

[0095] It is understandable that since the data of on-site work order photos are usually high-dimensional and unstructured, it is often difficult to extract high-level features directly from the on-site work order photos. Therefore, step S311 is performed to extract initial features from the on-site work order photos through CNN, thereby realizing the conversion of the on-site work order photos from raw image data to more abstract and meaningful feature representations, providing a data basis for the subsequent generation of feature vectors.

[0096] Exemplarily, the initial features of the on-site work order photos are extracted through multi-layer convolution and pooling operations of the VGG16 neural network model in VGGNet to obtain an initial feature map.

[0097] Step S312, generating a plurality of feature vectors of preset sizes by applying a sliding window of preset sizes in the initial feature map based on the watermark position of the on-site work order photo.

[0098] It should be noted that the watermark position refers to the specific position of the watermark in the on-site work order photo; the sliding window refers to a fixed-size window that moves on the initial feature map, which is used to extract the features of the local area from the initial feature map. Each time the window slides to a new position, a new feature vector is generated, which contains the feature information of the area covered by the sliding window.

[0099] It is understandable that since the initial feature map contains features of all sizes and positions in the on-site work order photo, but does not clearly indicate the specific position of the watermark in the on-site work order photo, and the initial feature map may also contain a large amount of redundant information and noise, step S312 is performed to generate a feature vector by applying a sliding window based on the watermark position of the on-site work order photo, thereby achieving accurate positioning of the watermark-related features in the initial feature map, avoiding the process of processing redundant information in the initial feature map, and improving the accuracy and efficiency of extracting watermark information from on-site work order photos.

[0100] Exemplarily, in the initial feature map, a 3*3 sliding window is applied based on the watermark position of the on-site work order photo. The sliding window can combine the features of the surrounding 3*3 initial feature map area to generate multiple 3*3*C feature vectors.

[0101] In this embodiment, by adopting the CNN model to extract the initial features of the on-site work order photos and using a sliding window based on the watermark position, it is possible to accurately extract local features related to the watermark from the on-site work order photos and generate representative feature vectors, thereby ensuring the effective parsing of the watermark information in the on-site work order photos, and further ensuring the effective verification of the authenticity of the content of the on-site work order photos.

[0102] Step S32, in the recurrent neural network model, generating a feature map based on each of the feature vectors, and mapping the feature map to an output category;

[0103] It should be noted that the feature map refers to the data structure obtained after processing the feature vector through the RNN model. The data structure is usually a multidimensional array, and each element in the multidimensional array represents a certain feature representation of the input feature vector after being processed by the RNN; the output category refers to the result obtained after the RNN model classifies or identifies the input feature vector. The result is usually a label or category, which represents the model's explanation or prediction of the input data.

[0104] It can be understood that since determining the shooting parameters corresponding to the watermark information needs to be based on an interpretable neural network output, step S32 is performed. By mapping the feature map generated by the RNN model to the output category, automatic recognition and classification of the watermark information is achieved, thereby improving the accuracy and effect of watermark detection.

[0105] Exemplarily, the features of each feature vector are learned through the Bi-LSTM (Bidirectional Long Short-Term Memory) model in the RNN model to convert the initial feature map of N*C*H*W into a feature map of N*9C*H*W, where N is the batch size, C is the number of channels, and H and W are the height and width of the feature map, respectively. The generated feature map is then flattened and passed to the fully connected layer of the Bi-LSTM model to map the features in the feature map to the preset output category through the fully connected layer.

[0106] Step S33: Select a target neuron with the highest activation value among the neurons corresponding to the output category, so as to determine the second shooting parameter corresponding to the watermark information based on the target neuron.

[0107] It should be noted that the activation value refers to the size of the output value of a neuron in the RNN after receiving the input information. The activation value reflects the intensity of the neuron's response to the input information; the target neuron refers to the neuron with the highest activation value in the feature map mapping process, and this neuron is associated with the type of watermark information.

[0108] It is understandable that neurons with lower activation values ​​may not accurately recognize the watermark information of the on-site work order photo, so step S33 is performed to avoid incorrect recognition of the watermark information by selecting the neuron with the highest activation value, thereby improving the recognition accuracy of the watermark information.

[0109] In this embodiment, by combining CNN and RNN, watermark information is accurately extracted from on-site work order photos, and shooting parameters related to the watermark information are determined, thereby improving the system's ability to recognize and parse watermark information, and providing a reliable method for uploading and authenticity verification of on-site work order photos.

[0110] In a feasible implementation manner, the second shooting parameters at least include a second shooting position, a second shooting time, second photographer information, and a second work order number. The step of determining the second shooting parameters corresponding to the watermark information based on the target neuron in step S33 may include step S331:

[0111] Step S331, obtaining the watermark information recognition result corresponding to the target neuron, and dividing the watermark information recognition result to obtain the second shooting position, the second shooting time, the second photographer information and the second work order number.

[0112] It should be noted that the second shooting location refers to the geographical location at which the watermarked on-site work order photo was taken after the watermark information is recognized through the neural network; the second shooting time refers to the exact time point at which the watermarked on-site work order photo was taken after the watermark information is recognized through the neural network; the second photographer information refers to the relevant information of the photographer who took the on-site work order photo with the watermark embedded in it after the watermark information is recognized through the neural network, and the relevant information may include information such as the name or number of the photographer; the second work order number refers to the work order number of the watermarked on-site work order photo obtained after the watermark information is recognized through the neural network.

[0113] Exemplarily, a watermark recognition result corresponding to a target neuron is obtained, and characters of the watermark recognition result are divided to obtain information such as the shooting location, shooting time, photographer's name, and work order number in the characters.

[0114] In this implementation, watermark information is identified through a neural network, and the watermark information identification results are divided into shooting location, shooting time and photographer information, thereby achieving accurate extraction and analysis of the watermark information, providing key information for verifying the authenticity of on-site work order photos, and ensuring that the uploaded on-site work order photos are original and have not been tampered with.

[0115] Step S40: compare the first shooting parameter with the second shooting parameter, and upload the on-site work order photo when the first shooting parameter is consistent with the second shooting parameter.

[0116] It is understandable that since it is currently difficult to ensure that the uploaded on-site work order photos are real on-site work order photos taken in a network-free environment, rather than tampered or forged on-site work order photos, step S40 is performed to verify the authenticity of the on-site work order photos by comparing the original shooting parameters, i.e., the first shooting parameters, and the watermark extraction parameters, i.e., the second shooting parameters, thereby preventing the on-site work order photos from being tampered with during the upload process, and ensuring the authenticity of the content of the on-site work order photos. At the same time, manual verification of the authenticity of the on-site work order photos is avoided, thereby reducing the cost of verifying the authenticity of the on-site work order photos.

[0117] Exemplarily, the first shooting parameters include the first shooting position, the first shooting time and the first photographer information, and the second shooting parameters include the second shooting position, the second shooting time and the second photographer information. The first shooting position and the second shooting position, the first shooting time and the second shooting time, the first photographer name and the second photographer name are compared at the same time. If the above three comparisons are consistent, the first shooting parameters are compared with the preset shooting parameters of the file to be uploaded, wherein the preset shooting parameters include the preset shooting position, the preset shooting time and the preset photographer information. The step of comparing the first shooting parameter with the preset shooting parameter of the file to be uploaded includes: simultaneously comparing the first shooting position with the preset shooting position, the first shooting moment with the preset shooting moment, the first photographer information with the preset photographer information, and uploading the on-site work order photo when the first photographer information and the preset photographer information, the first shooting moment and the preset shooting moment are consistent, and the error between the first shooting position and the preset shooting position is less than the preset position error threshold; and prohibiting uploading the on-site work order photo when the first photographer information and the preset photographer information, the first shooting moment and the preset shooting moment are consistent, and the error between the first shooting position and the preset shooting position is greater than or equal to the preset position error threshold. Since positioning errors are often caused by equipment performance limitations when obtaining the shooting position, the fault tolerance of the determined shooting position is improved by setting the preset position error threshold when the photographer information is consistent, thereby improving the applicability of the method for uploading on-site work order photos in a networkless environment after the network is restored.

[0118] The present embodiment provides a method for verifying work orders by taking photos on-site in a network-free environment. Watermarks based on shooting parameters are added to the photos of on-site work orders taken in a network-free environment, and the watermarks are parsed after the network is restored to verify whether the shooting parameters have changed. If the shooting parameters have not changed, the on-site work order photos are uploaded, thereby ensuring the authenticity of the on-site work order photos uploaded after the network is restored.

[0119] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 This is a flow chart of the first embodiment of the on-site photo work order verification method in a network-free environment of the present application. The on-site photo work order verification method in a network-free environment also includes steps S01 to S02:

[0120] Step S01, during the process of taking the on-site work order photo, obtaining device parameters of the terminal device, wherein the device parameters at least include flight mode status, signal power and signal strength;

[0121] It should be noted that device parameters refer to various technical indicators and status information that the terminal device can collect during the shooting process. The device parameters can help determine whether the terminal device is in a network-free environment and determine whether the preset shooting conditions are met; the flight mode status refers to whether the terminal device is in flight mode; signal power refers to the power of the signal received by the terminal device, usually in dBm (decibel milliwatts), which is used to measure the power of the wireless signal between the terminal device and the base station or other equipment; signal strength refers to the strength of the signal sent or received by the terminal device, reflecting the communication capability of the terminal device and the stability of the signal.

[0122] It is understandable that, since there are often users who abuse the offline mode of terminal devices to create an inaccurate network-free environment, step S01 is performed to obtain the device parameters of the terminal device to provide a basis for judgment to ensure that the on-site work order photos taken in a network-free environment meet the requirements.

[0123] Exemplarily, during the process of taking photos of the on-site work order, the flight mode status of the terminal device is obtained. When the obtained flight mode status is on, a flight mode off prompt signal is output; when the obtained flight mode status is on, the signal power and signal strength of the terminal device are obtained.

[0124] Step S02: when the device parameters meet the preset shooting conditions, it is determined that the terminal device is in the network-free environment.

[0125] It should be noted that the preset shooting conditions refer to the conditions that are pre-set to determine under what circumstances the device is allowed to shoot.

[0126] It is understandable that, since there are often users abusing the offline mode of terminal devices to create an inaccurate network-free environment, step S02 is performed to ensure that the on-site work order photos taken are completed in a network-free environment by judging whether the device parameters meet the preset shooting conditions, thereby improving the reliability of the on-site work order photos.

[0127] Exemplarily, when the terminal device is not in flight mode, the signal power is less than -100dbm and the signal strength is less than 10asu, it is determined that the terminal device is in a network-free environment, so that a photo of the on-site work order can be taken by the terminal device.

[0128] In this embodiment, by judging whether the device parameters meet the preset shooting conditions during the shooting process of the on-site work order photos, it is judged whether the terminal device is actually in a network-free environment, thereby avoiding irregular operations performed by users when shooting on-site work order photos.

[0129] For example, in order to help understand the implementation process of the on-site photo work order verification method in a non-network environment obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flow chart of a method for verifying a work order by taking photos on site in a network-free environment is provided, specifically:

[0130] First, determine whether there is no network based on the shooting parameters of the terminal device, that is, whether it is a network-free environment. If it is determined that there is no network environment, take a photo to obtain a photo of the on-site work order, and obtain the real-time location and time of the photo, that is, the first shooting location and the first shooting moment. Then compress the photo obtained by taking the photo, that is, the on-site work order photo, and add a watermark to obtain a candidate file to be uploaded. Then add the shooting location and time, that is, the first shooting location and the first shooting moment, to the file, encrypt it and record the MD5 code, that is, the original hash value, to obtain the file to be uploaded. Open the work order in a network environment and verify the MD5 code, that is, after the network is restored, verify the hash value of the file to be uploaded based on the original hash value. If they are consistent, decrypt the file, that is, decrypt the file to be uploaded when the original hash value is consistent with the hash value, obtain the shooting location and time, and convert the file into a photo, that is, obtain the first shooting location, the first shooting moment, and the on-site work order photo in the file to be uploaded. Call AI capabilities to obtain the location and time information in the photo watermark and compare it with the photo location and time in the file, that is, determine the second shooting location and second shooting time of the watermark information in the on-site work order photo through convolutional neural network and recurrent neural network, and compare the second shooting location with the first shooting location, and compare the second shooting time with the first shooting time. Compare the photo location and time information in the file with the photo location and time required for the work order, that is, compare the preset shooting location with the first shooting location in the file to be uploaded, the preset shooting time with the first shooting time in the file to be uploaded, and upload the photo when the preset shooting location and the first shooting location, the preset shooting time and the first shooting time are all consistent, that is, upload the on-site work order photo.

[0131] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the on-site photo-taking work order verification method in a network-free environment of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0132] This application also provides a device for verifying on-site photo taking work orders. Please refer to Figure 4 The on-site photo work order verification device is applied to a terminal device, and the on-site photo work order verification device includes:

[0133] A watermark adding module 10, configured to obtain a site work order photo and a first shooting parameter of the site work order photo when the terminal device is in a network-free environment, and add a watermark to the site work order photo based on the first shooting parameter;

[0134] A compression module 20, used to convert the on-site work order photo with the watermark added into a compressed file, add the first shooting parameter to the compressed file, obtain a file to be uploaded, and save the file to be uploaded;

[0135] The parsing module 30 is used to extract the on-site work order photo and the first shooting parameter from the to-be-uploaded file after monitoring that the terminal device has restored the network, and parse the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo;

[0136] The uploading module 40 is used to compare the first shooting parameter with the second shooting parameter, and upload the on-site work order photo when the first shooting parameter is consistent with the second shooting parameter.

[0137] Optionally, the parsing module 30 is further used for:

[0138] Generate a plurality of feature vectors of preset sizes of the on-site work order photo through a convolutional neural network model, and input each of the feature vectors into a recurrent neural network model;

[0139] In the recurrent neural network model, a feature map is generated based on each of the feature vectors, and the feature map is mapped to an output category;

[0140] A target neuron with the highest activation value among the neurons corresponding to the output category is selected to determine the second shooting parameter corresponding to the watermark information based on the target neuron.

[0141] Optionally, the parsing module 30 is further used for:

[0142] Extracting initial features of the on-site work order photo through the convolutional neural network model to obtain an initial feature map;

[0143] A plurality of feature vectors of preset sizes are generated by applying a sliding window of preset sizes in the initial feature map based on the watermark position of the on-site work order photo.

[0144] Optionally, the second shooting parameters at least include a second shooting position, a second shooting time, and second photographer information, and the parsing module 30 is further used for:

[0145] The watermark information recognition result corresponding to the target neuron is obtained, and the watermark information recognition result is divided to obtain the second shooting position, the second shooting time and the second photographer information.

[0146] Optionally, the compression module 20 is further used for:

[0147] Adding the first shooting parameter to the compressed file to obtain a candidate file to be uploaded;

[0148] The candidate file to be uploaded is symmetrically encrypted to obtain the file to be uploaded, and the file to be uploaded is saved.

[0149] Optionally, the first shooting parameter at least includes a first shooting position, a first shooting time, and first photographer information, and the parsing module 30 is further used for:

[0150] After monitoring that the terminal device has restored the network, the hash value of the file to be uploaded is verified based on the original hash value, wherein the original hash value is calculated when the file to be uploaded is obtained by symmetrical encryption in a networkless environment, and the hash value is calculated when the file to be uploaded is uploaded after the terminal device restores the network.

[0151] When the original hash value is consistent with the hash value, the file to be uploaded is symmetrically decrypted, and the on-site work order photo, the first shooting location, the first shooting time and the first photographer information in the symmetrically decrypted file are extracted.

[0152] Optionally, the determination module 50 in the on-site photo work order verification device is used to:

[0153] During the process of taking the on-site work order photo, obtaining device parameters of the terminal device, wherein the device parameters at least include flight mode status, signal power, and signal strength;

[0154] When the device parameters meet the preset shooting conditions, it is determined that the terminal device is in the network-free environment.

[0155] The on-site photo work order verification device provided by the present application adopts the on-site photo work order verification method in a network-free environment in the above-mentioned embodiment, which can solve the technical problem of how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored. Compared with the prior art, the beneficial effects of the on-site photo work order verification device provided by the present application are the same as the beneficial effects of the on-site photo work order verification method in a network-free environment provided by the above-mentioned embodiment, and the other technical features of the on-site photo work order verification device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0156] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the on-site photo taking work order verification method in a network-free environment in the above-mentioned embodiment one.

[0157] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0158] like Figure 5 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0159] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0160] The electronic device provided by the present application adopts the on-site photo work order verification method in a network-free environment in the above-mentioned embodiment, which can solve the technical problem of how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the on-site photo work order verification method in a network-free environment provided by the above-mentioned embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0161] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0162] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0163] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the on-site photo taking work order verification method in a network-free environment in the above-mentioned embodiment.

[0164] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0165] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0166] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: when the terminal device is in a network-free environment, obtains an on-site work order photo and a first shooting parameter of the on-site work order photo, and adds a watermark to the on-site work order photo based on the first shooting parameter; converts the on-site work order photo with the watermark into a compressed file, appends the first shooting parameter to the compressed file to obtain a file to be uploaded, and saves the file to be uploaded; after monitoring that the terminal device has restored the network, extracts the on-site work order photo and the first shooting parameter in the file to be uploaded, and parses the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo; compares the first shooting parameter and the second shooting parameter, and uploads the on-site work order photo when the first shooting parameter and the second shooting parameter are consistent.

[0167] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0168] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0169] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0170] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned on-site photo work order verification method in a network-free environment, and can solve the technical problem of how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the on-site photo work order verification method in a network-free environment provided by the above-mentioned embodiment, and will not be repeated here.

[0171] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned on-site photo-taking work order verification method in a network-free environment.

[0172] The computer program product provided by the present application can solve the technical problem of how to ensure the authenticity of the on-site work order photos uploaded by the terminal device after the network is restored. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the on-site photo work order verification method in a non-network environment provided by the above embodiment, and will not be repeated here.

[0173] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for verifying on-site photo work orders in a non-network environment, characterized in that: Applied to the terminal device, the on-site photo work order verification method in a non-network environment includes: When the terminal device is in a network-free environment, obtaining a site work order photo and a first shooting parameter of the site work order photo, and adding a watermark to the site work order photo based on the first shooting parameter; Converting the watermarked on-site work order photo into a compressed file, appending the first shooting parameter to the compressed file to obtain a file to be uploaded, and saving the file to be uploaded; After monitoring that the terminal device has restored the network, extracting the on-site work order photo and the first shooting parameter in the file to be uploaded, and parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo; The first shooting parameter and the second shooting parameter are compared, and when the first shooting parameter and the second shooting parameter are consistent, the on-site work order photo is uploaded.

2. The on-site photo work order verification method in a non-network environment as claimed in claim 1, characterized in that: The step of parsing the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo includes: Generate a plurality of feature vectors of preset sizes of the on-site work order photo through a convolutional neural network model, and input each of the feature vectors into a recurrent neural network model; In the recurrent neural network model, a feature map is generated based on each of the feature vectors, and the feature map is mapped to an output category; A target neuron with the highest activation value among the neurons corresponding to the output category is selected to determine the second shooting parameter corresponding to the watermark information based on the target neuron.

3. The on-site photo work order verification method in a non-network environment as claimed in claim 2, characterized in that: The step of generating a plurality of feature vectors of preset sizes of the on-site work order photo by using a convolutional neural network model comprises: Extracting initial features of the on-site work order photo through the convolutional neural network model to obtain an initial feature map; A plurality of feature vectors of preset sizes are generated by applying a sliding window of preset sizes in the initial feature map based on the watermark position of the on-site work order photo.

4. The on-site photo work order verification method in a non-network environment as claimed in claim 2, characterized in that: The second shooting parameters at least include a second shooting position, a second shooting time, second photographer information and a second work order number, and the step of determining the second shooting parameters corresponding to the watermark information based on the target neuron includes: The watermark information recognition result corresponding to the target neuron is obtained, and the watermark information recognition result is divided to obtain the second shooting position, the second shooting time, the second photographer information and the second work order number.

5. The on-site photo work order verification method in a non-network environment as claimed in claim 1, characterized in that: The steps of adding the first shooting parameter to the compressed file to obtain the file to be uploaded and saving the file to be uploaded include: Adding the first shooting parameter to the compressed file to obtain a candidate file to be uploaded; The candidate file to be uploaded is symmetrically encrypted to obtain the file to be uploaded, and the file to be uploaded is saved.

6. The on-site photo work order verification method in a non-network environment as claimed in claim 5, characterized in that: The first shooting parameters at least include a first shooting position, a first shooting time, first photographer information and a first work order number. After monitoring that the terminal device has restored the network, the step of extracting the on-site work order photo and the first shooting parameters from the file to be uploaded includes: After monitoring that the terminal device has restored the network, the hash value of the file to be uploaded is verified based on the original hash value, wherein the original hash value is calculated when the file to be uploaded is obtained by symmetrical encryption in a networkless environment, and the hash value is calculated when the file to be uploaded is uploaded after the terminal device restores the network. When the original hash value is consistent with the hash value, the file to be uploaded is symmetrically decrypted, and the on-site work order photo, the first shooting location, the first shooting time, the first photographer information and the first work order number are extracted from the symmetrically decrypted file.

7. The on-site photo work order verification method in a non-network environment as claimed in claim 1, characterized in that: The on-site photo work order verification method in a non-network environment also includes: During the process of taking the on-site work order photo, obtaining device parameters of the terminal device, wherein the device parameters at least include flight mode status, signal power, and signal strength; When the device parameters meet the preset shooting conditions, it is determined that the terminal device is in the network-free environment.

8. An on-site photo work order verification device, characterized in that: Applied to terminal equipment, the on-site photo work order verification device includes: A watermark adding module, used for obtaining a site work order photo and a first shooting parameter of the site work order photo when the terminal device is in a network-free environment, and adding a watermark to the site work order photo based on the first shooting parameter; A compression module, used to convert the watermarked on-site work order photo into a compressed file, append the first shooting parameter to the compressed file to obtain a file to be uploaded, and save the file to be uploaded; A parsing module, configured to extract the on-site work order photo and the first shooting parameter from the file to be uploaded after monitoring that the terminal device has restored the network, and parse the watermark information in the on-site work order photo to obtain the second shooting parameter of the on-site work order photo; The uploading module is used to compare the first shooting parameter with the second shooting parameter, and upload the on-site work order photo when the first shooting parameter is consistent with the second shooting parameter.

9. An electronic device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the on-site photo taking work order verification method in a network-free environment as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the on-site photo taking work order verification method in a network-free environment are implemented as described in any one of claims 1 to 7.

Images