CN114240364A - Method and device for automatically auditing industrial injury, computer equipment and storage medium - Google Patents
Method and device for automatically auditing industrial injury, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114240364A CN114240364A CN202111542371.9A CN202111542371A CN114240364A CN 114240364 A CN114240364 A CN 114240364A CN 202111542371 A CN202111542371 A CN 202111542371A CN 114240364 A CN114240364 A CN 114240364A
- Authority
- CN
- China
- Prior art keywords
- human body
- auditing
- user
- accident
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 208000027418 Wounds and injury Diseases 0.000 title claims abstract description 102
- 208000014674 injury Diseases 0.000 title claims abstract description 102
- 230000006378 damage Effects 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000009471 action Effects 0.000 claims abstract description 76
- 239000000463 material Substances 0.000 claims abstract description 46
- 238000012550 audit Methods 0.000 claims abstract description 45
- 239000013598 vector Substances 0.000 claims description 60
- 210000000746 body region Anatomy 0.000 claims description 29
- 238000002372 labelling Methods 0.000 claims description 21
- 206010061225 Limb injury Diseases 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 238000012552 review Methods 0.000 claims description 10
- 238000012417 linear regression Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 7
- 235000002566 Capsicum Nutrition 0.000 claims description 5
- 239000006002 Pepper Substances 0.000 claims description 5
- 235000016761 Piper aduncum Nutrition 0.000 claims description 5
- 235000017804 Piper guineense Nutrition 0.000 claims description 5
- 235000008184 Piper nigrum Nutrition 0.000 claims description 5
- 150000003839 salts Chemical class 0.000 claims description 5
- 244000203593 Piper nigrum Species 0.000 claims 1
- 206010052428 Wound Diseases 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000013473 artificial intelligence Methods 0.000 abstract description 12
- 238000001514 detection method Methods 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 10
- 230000033001 locomotion Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 241000722363 Piper Species 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 208000012260 Accidental injury Diseases 0.000 description 1
- 208000028571 Occupational disease Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for automatically auditing industrial injury, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. According to the method and the device, auditing materials uploaded by a user to be audited are obtained, the auditing materials comprise accident address information, a commuting path and an accident scene picture, whether the accident happens in the range of the commuting path is audited firstly according to the accident address information and the commuting path, then the posture of the user is predicted through the accident scene picture, the limb disability condition of the user is judged according to the posture of the user, and finally the work injury auditing result of the user is judged to pass or not according to the action path auditing result and the limb disability auditing result of the user. In addition, the application also relates to a block chain technology, and audit materials can be stored in the block chain. According to the method and the system, the auditing of the action path and the auditing of the limb disability condition are automatically realized through the auditing materials uploaded by the user, the workload of social security personnel is reduced, and the work injury auditing efficiency is improved.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to a method and a device for automatically auditing industrial injury, computer equipment and a storage medium.
Background
Industrial risk refers to a social insurance system in which workers or their relatives obtain material help from the country and society when workers are in work or in a specific situation, suffer accidental injury or occupational disease, lose labor capacity temporarily or permanently, and die. The claims of the industrial risk are required to satisfy a plurality of conditions, firstly, the identity of the laborer and the industrial risk of purchase. The second is the identification of the injury during working hours or on the way to work. In the process, some accident scene photos, diagnosis books, wounded identity cards, work attendance records and other documents need to be collected to prove that the conditions for indemnification are met.
At present, the work injury investigation of each region is reported by the wounded person/company personnel to the social security bureau, the data is submitted to the social security bureau, and the work injury investigation is verified and calculated manually by the social security staff. In the process, if the data submission fails, the wounded needs to submit for multiple times, which causes time waste. Meanwhile, the social security personnel need to check repeated data for many times, the workload is large, and the efficiency is low.
Disclosure of Invention
The embodiment of the application aims to provide a method and a device for automatically auditing industrial injuries, computer equipment and a storage medium, so as to solve the technical problems of large workload, low efficiency and labor and material consumption of the existing industrial injury auditing scheme in a manual auditing mode.
In order to solve the above technical problem, an embodiment of the present application provides a method for automatically auditing a work injury, which adopts the following technical scheme:
a method for automated review of a work injury, comprising:
receiving a work injury audit instruction, and acquiring audit materials uploaded by a user to be audited, wherein the audit materials comprise accident address information, a commuting path and an accident scene picture;
generating an action path auditing result of the user to be audited based on the accident address information and the commuting path;
marking the human body joint points on the picture of the accident scene to generate a human body joint point image;
importing the human body joint point image into a pre-trained posture prediction model to obtain a posture prediction result of the user to be audited;
comparing the posture prediction result with a preset standard disabled posture result to obtain a disabled limb audit result of the user to be audited;
and generating a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
Further, the step of generating an action path audit result of the user to be audited based on the accident address information and the commute path specifically includes:
judging whether an accident address is within the range of the commute path or not based on the accident address information and the commute path;
and obtaining an action path auditing result of the user to be audited by judging whether the accident address is in the range of the commuting path or not, wherein the action path auditing result comprises a first action path auditing result and a second action path auditing result, the first action path auditing result is that the accident address is in the range of the commuting path, and the second action path auditing result is that the accident address is not in the range of the commuting path.
Further, before the step of labeling the human body joint points on the picture of the accident scene and generating the human body joint point image, the method further comprises the following steps:
identifying the picture of the accident scene based on a preset content identification model to obtain human body contour characteristics;
denoising the accident scene picture, and removing salt and pepper noise points of the accident scene picture to obtain a denoised image;
determining a human body region in the accident scene picture based on the de-noised image and the human body contour characteristics;
the step of labeling the human body joint points of the accident scene picture to generate a human body joint point image specifically comprises the following steps:
and marking the human body joint points of the accident scene picture carrying the human body area to generate a human body joint point image.
Further, the step of labeling the human body joint points on the picture of the accident scene to generate an image of the human body joint points specifically includes:
importing the accident scene picture after the human body region is identified into a joint point confidence coefficient prediction model which is trained in advance;
predicting the confidence of each pixel point in the human body region by using the joint point confidence prediction model;
and marking the human body joint points based on the confidence coefficient of each pixel point in the human body region to generate a human body joint point image.
Further, the step of labeling the human joint points based on the confidence of each pixel point in the human body region to generate an image of the human joint points specifically includes:
calculating affinity values between the human joint points;
judging whether the affinity value is greater than or equal to a preset threshold value;
and when the affinity value is greater than or equal to a preset threshold value, performing matching connection on the human body joint points to obtain a human body joint point image.
Further, before the step of importing the human body joint point image into a pre-trained posture prediction model to obtain the posture prediction result of the user to be audited, the method further includes:
constructing an image coordinate system, and acquiring the coordinates of human body joint points in the human body region based on the image coordinate system;
and identifying the connecting lines of the human body joint points, and calculating the included angle between the connecting lines of the human body joint points to obtain the movable angle of the human body joint.
Further, the step of importing the human body joint point image into a pre-trained posture prediction model to obtain a posture prediction result of the user to be audited specifically includes:
extracting the characteristics of the human body joint point image to obtain a connecting line characteristic and a moving angle characteristic;
respectively coding the connecting line characteristic and the moving angle characteristic to obtain a first characteristic vector and a second characteristic vector;
respectively carrying out linear transformation on the first feature vector and the second feature vector, and fusing the first feature vector and the second feature vector after the linear transformation to obtain a fused feature vector;
performing linear regression on the fusion feature vector to obtain a regression feature vector;
and decoding the regression feature vector to obtain a posture prediction result of the user to be audited.
In order to solve the above technical problem, an embodiment of the present application further provides an apparatus for automatically auditing a work injury, which adopts the following technical scheme:
an apparatus for automatic review of a work injury, comprising:
the system comprises a material acquisition module, a data processing module and a data processing module, wherein the material acquisition module is used for receiving a work injury audit instruction and acquiring audit materials uploaded by a user to be audited, and the audit materials comprise accident address information, a commuting path and an accident scene picture;
the path checking module is used for generating an action path checking result of the user to be checked based on the accident address information and the commuting path;
the joint point marking module is used for marking the human joint points of the accident scene picture to generate a human joint point image;
the posture prediction module is used for importing the human body joint point image into a posture prediction model trained in advance to obtain a posture prediction result of the user to be checked;
and the disability auditing module is used for comparing the posture prediction result with a preset standard disability posture result to obtain a limb disability auditing result of the user to be audited.
And the work injury checking module is used for generating a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of a method for automatic review of a work injury as claimed in any one of the above.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of a method for automated work injury review as claimed in any one of the preceding claims.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
the application discloses a method and a device for automatically auditing industrial injury, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method includes the steps that after a work injury auditing instruction is received, auditing materials uploaded by a user to be audited are obtained, wherein the auditing materials comprise accident address information, a commuting path and an accident site picture, whether the accident happens in the range of the commuting path or not is audited firstly according to the accident address information and the commuting path, if the accident happens in the range of the commuting path, the limb disability condition of the user in the accident continues to be audited, the posture of the user is predicted by the aid of the accident site picture, the limb disability condition of the user is judged according to the posture of the user, and finally, whether the work injury auditing result of the user passes or not is judged by combining a action path auditing result and a limb disability auditing result of the user. In a work injury auditing scene, the application realizes auditing of the action path through the accident address information and the commuting path uploaded by the user, and after the action path is audited, auditing of the limb injury condition of the user is completed through a pre-trained injury detection model and an accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 illustrates a flow diagram of one embodiment of a method for automated review of a work injury according to the present application;
FIG. 3 illustrates a schematic structural diagram of one embodiment of an apparatus for automated review of industrial injuries in accordance with the present application;
FIG. 4 shows a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server that provides various services, for example, a background server that provides support for pages displayed on the terminal devices 101, 102, and 103, and may be an independent server, or a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
It should be noted that, the method for automatically auditing a work injury provided in the embodiment of the present application is generally executed by a server, and accordingly, an apparatus for automatically auditing a work injury is generally disposed in the server.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a method for automated review of a work injury according to the present application is shown. The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like. The automatic checking method for the industrial injury comprises the following steps:
s201, receiving a work injury auditing instruction, and acquiring auditing materials uploaded by a user to be audited, wherein the auditing materials comprise accident address information, a commuting path and an accident scene picture.
Specifically, after a work injury accident occurs, a user to be audited (i.e., a wounded person in the accident) initiates a work injury audit instruction, and after receiving the work injury audit instruction, the server instructs the user to be audited to upload audit materials and receives the audit materials uploaded by the user to be audited, wherein the audit materials include accident address information, commuting paths and accident scene pictures.
In this embodiment, an electronic device (for example, a server shown in fig. 1) on which the method for automatically auditing a work injury operates may receive a work injury audit instruction through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.
It should be noted that the audit material further includes identity information of the user to be audited, such as an identity card picture, the server checks the identity of the user to be audited through an OCR scanning technology and a face recognition technology, specifically, the identity card information is obtained through the OCR scanning technology identity card picture, and the identity card information is compared with the identity information input by the user; and identifying the identity card picture and the accident scene picture by a face identification technology, and comparing the face characteristics of the identity card picture and the accident scene picture. And when the identity verification passes, the action path verification and the limb disability verification are started. The accident scene graph can be shot and uploaded by a camera of a traffic network around the accident site, or shot and uploaded by professional processing personnel arriving at the scene, such as the underwriting personnel of the corresponding insurance company.
And S202, generating an action path checking result of the user to be checked based on the accident address information and the commuting path.
Specifically, the server acquires accident address information, generates a regional map according to the accident address information, positions an accident site on the regional map according to the accident address information, and judges whether an accident site is in the range of the commuting path to obtain an action path auditing result of the user to be audited.
After the action path is checked, the action time is checked, for example, whether the accident occurrence time meets the time of work injury underwriting is determined according to the attendance time of the user to be checked.
And S203, marking the human body joint points on the picture of the accident scene to generate a human body joint point image.
The Human body key point Detection (Human Keypoints Detection) is also called Human body posture estimation 2D Pose, is a relative basic task in computer vision, and is a preposed task of Human body action recognition, behavior analysis, Human-computer interaction and the like. The human body joint point identification model is based on a convolutional neural network and an open source library which is supervised learning and developed by taking Caffe as a framework, can realize the identification of the human body joint points and the generation of human body joint point images, is suitable for single person and multiple persons, and has excellent robustness.
Specifically, the human joint point identification model comprises two submodels, namely a joint point confidence degree prediction model and a joint point affinity value calculation model, wherein the joint point confidence degree prediction model is used for predicting the positions of human joint points, and the joint point affinity value calculation model is used for calculating the affinity values among the human joint points and performing human joint point connection to generate a human joint point image.
In the specific embodiment of the application, an accident scene picture after a human body area is identified is input, features are extracted through a convolutional network to obtain a group of feature Maps, then the group of feature Maps are divided into two branches, a Part consistency Maps and a Part Affinity Fields are respectively extracted through a human body joint point identification model, human body joint point labeling is carried out according to the Part consistency Maps, and human body joint points are connected in a matching mode according to the Part Affinity Fields to obtain a human body joint point image.
And S204, importing the human body joint point image into a pre-trained posture prediction model to obtain a posture prediction result of the user to be audited.
The gesture prediction model is obtained based on Transformer model training, the Transformer network architecture is a neural network architecture based on a U-shaped model, the Transformer network architecture comprises a plurality of coding layers and a plurality of decoding layers, each coding layer corresponds to one decoding layer, characteristic coding vectors output by the coding layers can be sent to the corresponding decoding layers to be decoded, and the characteristics of input vectors in all dimensions can be completely obtained by the user intention recognition model through a U-shaped coding-decoding network structure. In addition, a corresponding self-attention layer is arranged in front of each coding layer and used for improving the weight of key features, and a corresponding full-connection layer is arranged behind the decoding layer and composed of a softmax function and used for realizing the normalization of results.
Specifically, the server leads the human body joint point image into a pre-trained posture prediction model, and predicts the posture of the user by performing feature extraction on the human body joint point image and performing feature coding, feature fusion and feature decoding on the extracted features.
S205, comparing the posture prediction result with a preset standard disabled posture result to obtain a disabled limb examination result of the user to be examined.
Specifically, multiple standard disability posture results are preset in a database of the server, each posture corresponds to one standard disability posture result, after the posture prediction result of the user to be audited is predicted through the posture prediction model, the server compares the posture prediction result with the multiple standard disability posture results one by one, and when the posture prediction result is matched with one of the standard disability posture results, the matched disability posture is output as the limb disability audit result of the user to be audited. For example, in one accident, the left arm of the user to be audited is injured, the posture prediction result predicted by the multiple groups of accident scene pictures is that the left arm joint of the user to be audited is not movable, the posture prediction result of the user to be audited is matched with the standard left arm disabled posture result by comparing the posture prediction result with multiple standard disabled posture results, and the limb disabled auditing result of the user to be audited is determined to be left arm disabled.
And S206, generating a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
Specifically, a work injury audit result of the user to be audited is generated based on the action path audit result and the limb injury audit result. For example, in an accident, when a traffic accident occurs on the working road by a user to be audited, the left arm is disabled, the action path and the limb disability are automatically audited through the server, and the action path audit result and the limb disability audit result both meet the work injury audit requirement, the result of passing the work injury audit is output to the user to be audited. According to the method and the system, the auditing of the action path and the auditing of the limb disability condition are automatically realized through the auditing materials uploaded by the user, the workload of social security personnel is reduced, and the work injury auditing efficiency is improved.
In the above embodiment, in a work injury auditing scene, the application realizes auditing the action path through the accident address information and the commuting path uploaded by the user, and after the action path auditing is passed, auditing the limb injury condition of the user is completed through the pre-trained injury detection model and the accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
Further, the step of generating an action path audit result of the user to be audited based on the accident address information and the commute path specifically includes:
judging whether an accident address is within the range of the commute path or not based on the accident address information and the commute path;
and obtaining an action path auditing result of the user to be audited by judging whether the accident address is in the range of the commuting path or not, wherein the action path auditing result comprises a first action path auditing result and a second action path auditing result, the first action path auditing result is that the accident address is in the range of the commuting path, and the second action path auditing result is that the accident address is not in the range of the commuting path.
Specifically, the server locates the accident location based on the accident address information, judges whether the accident occurs in the range of the commuting path, generates a first action path auditing result if the accident address is in the range of the commuting path, and generates a second action path auditing result if the accident address is not in the range of the commuting path. And the first action path auditing result is that the accident address is in the range of the commuting path, namely the action path auditing is successful, and the second action path auditing result is that the accident address is not in the range of the commuting path, and the action path auditing is failed. It should be noted that, if the action path audit fails, the limb disability audit is not performed any more, and only after the action path audit is successful, the limb disability audit is performed continuously.
In the above embodiment, the action path audit in the work injury audit is completed by determining whether the accident address is within the range of the commute path.
Further, before the step of labeling the human body joint points on the picture of the accident scene and generating the human body joint point image, the method further comprises the following steps:
identifying the picture of the accident scene based on a preset content identification model to obtain human body contour characteristics;
denoising the accident scene picture, and removing salt and pepper noise points of the accident scene picture to obtain a denoised image;
determining a human body region in the accident scene picture based on the de-noised image and the human body contour characteristics;
the step of labeling the human body joint points of the accident scene picture to generate a human body joint point image specifically comprises the following steps:
and marking the human body joint points of the accident scene picture carrying the human body area to generate a human body joint point image.
Specifically, before the human body joint point marking is carried out on the picture of the accident scene to generate the human body joint point image, the picture of the accident scene is preprocessed, wherein the preprocessing comprises the sharpening processing and the human body region identification processing. The method comprises the steps of recognizing an accident scene picture based on a preset content recognition model to obtain a human body contour characteristic and a background contour of the accident scene picture, denoising the accident scene picture to remove salt and pepper noise points of the accident scene picture to obtain a denoised image so as to ensure the definition of the image, and determining a human body region in the accident scene picture based on the denoised image and the human body contour characteristic.
In the implementation, the clear human body region in the picture of the accident scene is obtained by carrying out content identification and denoising treatment on the picture of the accident scene, so that the subsequent human body joint point labeling is facilitated.
Further, the step of labeling the human body joint points on the picture of the accident scene to generate an image of the human body joint points specifically includes:
importing the accident scene picture after the human body region is identified into a joint point confidence coefficient prediction model which is trained in advance;
predicting the confidence of each pixel point in the human body region by using the joint point confidence prediction model;
and marking the human body joint points based on the confidence coefficient of each pixel point in the human body region to generate a human body joint point image.
Specifically, the server imports an accident scene picture after a human body region is identified into a joint point confidence coefficient prediction model which is trained in advance, predicts the confidence coefficient of each pixel point in the human body region by using the joint point confidence coefficient prediction model, and labels the human body joint points of the pixel points with the built-in confidence coefficient of the human body region larger than a preset confidence coefficient threshold value to generate the human body joint points.
Further, the step of labeling the human joint points based on the confidence of each pixel point in the human body region to generate an image of the human joint points specifically includes:
calculating affinity values between the human joint points;
judging whether the affinity value is greater than or equal to a preset threshold value;
and when the affinity value is greater than or equal to a preset threshold value, performing matching connection on the human body joint points to obtain a human body joint point image.
Specifically, the method comprises the steps of calculating an affinity value between human body joint points based on a pre-trained joint point affinity value calculation model, judging whether the affinity value between the two human body joint points is larger than or equal to a preset threshold value, performing matching connection on the two human body joint points when the affinity value between the two human body joint points is larger than or equal to the preset threshold value, executing the operation in a circulating mode, and obtaining a human body joint point image after all the human body joint points are connected in a line.
It should be noted that the preset human joint recognition model includes two sub models, namely, a joint confidence prediction model and a joint affinity value calculation model, where the joint confidence prediction model is used to predict the positions of human joints, and the joint affinity value calculation model is used to calculate the affinity values between human joints, and perform human joint connection.
In the above embodiments, the human joint point recognition model is used to recognize, label and connect human joint points, where the human joint point recognition model includes a joint point confidence prediction model and a joint point affinity value calculation model, the joint point confidence prediction model is used to predict positions of human joint points, and the joint point affinity value calculation model is used to calculate affinity values between human joint points and connect human joint points.
Further, before the step of importing the human body joint point image into a pre-trained posture prediction model to obtain the posture prediction result of the user to be audited, the method further includes:
constructing an image coordinate system, and acquiring the coordinates of human body joint points in the human body region based on the image coordinate system;
and identifying the connecting lines of the human body joint points, and calculating the included angle between the connecting lines of the human body joint points to obtain the movable angle of the human body joint.
Before the human body joint point image is imported into the pre-trained posture prediction model, the coordinates of the human body joint points are required to be obtained in advance, and the activity angles of the human body joints are required to be calculated.
Specifically, the server constructs an image coordinate system on an accident scene picture, acquires coordinates of human body joint points in a human body region based on the image coordinate system, connects the human body joint points based on an affinity field to obtain human body joint point connecting lines, and calculates cosine included angles between the human body joint point connecting lines to obtain human body joint movement angles.
In the above embodiment, in order to predict the posture of the user, an image coordinate system is constructed before the human body joint point image is imported into a posture prediction model trained in advance, the positions of the human body joint point connecting lines and the human body joint movement angles among the human body joint point connecting lines are calculated in the image coordinate system, and the posture of the user is predicted through the connecting line characteristics and the movement angle characteristics of the human body joint points.
Further, the step of importing the human body joint point image into a pre-trained posture prediction model to obtain a posture prediction result of the user to be audited specifically includes:
extracting the characteristics of the human body joint point image to obtain a connecting line characteristic and a moving angle characteristic;
respectively coding the connecting line characteristic and the moving angle characteristic to obtain a first characteristic vector and a second characteristic vector;
respectively carrying out linear transformation on the first feature vector and the second feature vector, and fusing the first feature vector and the second feature vector after the linear transformation to obtain a fused feature vector;
performing linear regression on the fusion feature vector to obtain a regression feature vector;
and decoding the regression feature vector to obtain a posture prediction result of the user to be audited.
Specifically, the server performs feature extraction on a human body joint point image to obtain a connection feature and a motion angle feature, encodes the connection feature and the motion angle feature through an encoding layer of a transform model to obtain a first feature vector and a second feature vector, performs linear transformation on the first feature vector and the second feature vector respectively to ensure that the first feature vector and the second feature vector can be mapped to a same dimensional space, fuses the first feature vector and the second feature vector after the linear transformation in the same dimensional space to obtain a fused feature vector, performs linear regression on the fused feature vector to obtain a regression feature vector, and decodes the regression feature vector through a transform model decoding layer to obtain a posture prediction result of a user to be checked.
It should be noted that, when the feature vector is linearly transformed, the feature vector is compressed, which results in a part of the features being lost, so that after the feature fusion is completed, linear regression needs to be performed to find the lost features, so that the regression feature vector can represent the connection features and the motion angle features of all dimensions.
In the embodiment, the connection characteristic and the activity angle characteristic are coded, the coded connection characteristic vector and the coded activity angle characteristic vector are subjected to linear transformation and fusion, the connection characteristic and the activity angle characteristic are fused, and then the fused characteristic vector is subjected to linear regression and decoding to obtain a user posture prediction result, so that the limb disability condition of the user can be recognized through the user posture prediction result.
The application discloses a method for automatically auditing industrial injuries, and belongs to the technical field of artificial intelligence. The method includes the steps that after a work injury auditing instruction is received, auditing materials uploaded by a user to be audited are obtained, wherein the auditing materials comprise accident address information, a commuting path and an accident site picture, whether the accident happens in the range of the commuting path or not is audited firstly according to the accident address information and the commuting path, if the accident happens in the range of the commuting path, the limb disability condition of the user in the accident continues to be audited, the posture of the user is predicted by the aid of the accident site picture, the limb disability condition of the user is judged according to the posture of the user, and finally, whether the work injury auditing result of the user passes or not is judged by combining a action path auditing result and a limb disability auditing result of the user. In a work injury auditing scene, the application realizes auditing of the action path through the accident address information and the commuting path uploaded by the user, and after the action path is audited, auditing of the limb injury condition of the user is completed through a pre-trained injury detection model and an accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
It is emphasized that, in order to further ensure the privacy and security of the audit material uploaded by the user, the audit material uploaded by the user may also be stored in a node of a block chain.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, can include processes of the embodiments of the methods described above. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an apparatus for automatically auditing a work injury, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 3, the automatic industrial injury auditing device according to this embodiment includes:
the material acquisition module 301 is configured to receive a work injury audit instruction and acquire audit materials uploaded by a user to be audited, where the audit materials include accident address information, commute routes, and accident scene pictures;
a path auditing module 302, configured to generate an action path auditing result of the user to be audited based on the accident address information and the commute path;
a joint point labeling module 303, configured to perform human joint point labeling on the accident scene picture to generate a human joint point image;
the posture prediction module 304 is configured to import the human body joint point image into a posture prediction model trained in advance, so as to obtain a posture prediction result of the user to be audited;
and the disability auditing module 305 is configured to compare the posture prediction result with a preset standard disability posture result to obtain a limb disability auditing result of the user to be audited.
And a work injury checking module 306, configured to generate a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
Further, the path checking module 302 specifically includes:
an address judging unit, configured to judge whether an accident address is within a range of the commute path based on the accident address information and the commute path;
and the address auditing result unit is used for obtaining an action path auditing result of the user to be audited by judging whether the accident address is in the range of the commuting path or not, wherein the action path auditing result comprises a first action path auditing result and a second action path auditing result, the first action path auditing result is that the accident address is in the range of the commuting path, and the second action path auditing result is that the accident address is not in the range of the commuting path.
Further, the device for automatically auditing the industrial injury further comprises:
the content identification module is used for identifying the accident scene picture based on a preset content identification model to obtain human body contour characteristics;
the denoising module is used for denoising the accident scene picture, removing salt and pepper noise points of the accident scene picture and obtaining a denoised image;
the contour identification module is used for determining a human body region in the accident scene picture based on the de-noised image and the human body contour characteristics;
the step of labeling the human body joint points of the accident scene picture to generate a human body joint point image specifically comprises the following steps:
and marking the human body joint points of the accident scene picture carrying the human body area to generate a human body joint point image.
Further, the joint point labeling module 303 specifically includes:
the image importing unit is used for importing the accident scene image after the human body region is identified into a joint point confidence coefficient prediction model which is trained in advance;
the confidence coefficient calculation unit is used for predicting the confidence coefficient of each pixel point in the human body region by using the joint point confidence coefficient prediction model;
and the joint point labeling unit is used for labeling the human joint points based on the confidence coefficient of each pixel point in the human body region to generate a human joint point image.
Further, the joint point labeling unit specifically includes:
an affinity value calculating subunit for calculating an affinity value between the human body joint points;
an affinity value judging subunit, configured to judge whether the affinity value is greater than or equal to a preset threshold;
and the affinity value judgment result subunit is used for performing matching connection on the human body joint points to obtain a human body joint point image when the affinity value is greater than or equal to a preset threshold value.
Further, the device for automatically auditing the industrial injury further comprises:
the coordinate system construction module is used for constructing an image coordinate system and acquiring the coordinates of human body joint points in the human body area based on the image coordinate system;
and the joint movement angle calculation module is used for identifying the connecting lines of the human body joint points and calculating the included angle between the connecting lines of the human body joint points to obtain the movement angle of the human body joint.
Further, the posture prediction module 304 specifically includes:
the characteristic extraction unit is used for extracting the characteristics of the human body joint point image to obtain a connecting line characteristic and a moving angle characteristic;
the characteristic coding unit is used for coding the connecting line characteristic and the activity angle characteristic respectively to obtain a first characteristic vector and a second characteristic vector;
the linear transformation unit is used for respectively carrying out linear transformation on the first feature vector and the second feature vector and fusing the first feature vector and the second feature vector after the linear transformation to obtain a fused feature vector;
the linear regression unit is used for performing linear regression on the fusion characteristic vector to obtain a regression characteristic vector;
and the feature decoding unit is used for decoding the regression feature vector to obtain the attitude prediction result of the user to be audited.
The application discloses automatic device that audits of industrial injury belongs to artificial intelligence technical field. The method includes the steps that after a work injury auditing instruction is received, auditing materials uploaded by a user to be audited are obtained, wherein the auditing materials comprise accident address information, a commuting path and an accident site picture, whether the accident happens in the range of the commuting path or not is audited firstly according to the accident address information and the commuting path, if the accident happens in the range of the commuting path, the limb disability condition of the user in the accident continues to be audited, the posture of the user is predicted by the aid of the accident site picture, the limb disability condition of the user is judged according to the posture of the user, and finally, whether the work injury auditing result of the user passes or not is judged by combining a action path auditing result and a limb disability auditing result of the user. In a work injury auditing scene, the application realizes auditing of the action path through the accident address information and the commuting path uploaded by the user, and after the action path is audited, auditing of the limb injury condition of the user is completed through a pre-trained injury detection model and an accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4, fig. 4 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only computer device 4 having components 41-43 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Of course, the memory 41 may also include both internal and external storage devices of the computer device 4. In this embodiment, the memory 41 is generally used for storing an operating system installed on the computer device 4 and various application software, such as computer readable instructions of a method for automatically auditing a work injury. Further, the memory 41 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions stored in the memory 41 or process data, such as computer readable instructions for executing the method for automatically auditing the industrial injury.
The network interface 43 may comprise a wireless network interface or a wired network interface, and the network interface 43 is generally used for establishing communication connection between the computer device 4 and other electronic devices.
The application discloses computer equipment belongs to artificial intelligence technical field. The method includes the steps that after a work injury auditing instruction is received, auditing materials uploaded by a user to be audited are obtained, wherein the auditing materials comprise accident address information, a commuting path and an accident site picture, whether the accident happens in the range of the commuting path or not is audited firstly according to the accident address information and the commuting path, if the accident happens in the range of the commuting path, the limb disability condition of the user in the accident continues to be audited, the posture of the user is predicted by the aid of the accident site picture, the limb disability condition of the user is judged according to the posture of the user, and finally, whether the work injury auditing result of the user passes or not is judged by combining a action path auditing result and a limb disability auditing result of the user. In a work injury auditing scene, the application realizes auditing of the action path through the accident address information and the commuting path uploaded by the user, and after the action path is audited, auditing of the limb injury condition of the user is completed through a pre-trained injury detection model and an accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
The present application provides yet another embodiment, which provides a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the method for automatic review of a work injury as described above.
The application discloses a storage medium belongs to artificial intelligence technical field. The method includes the steps that after a work injury auditing instruction is received, auditing materials uploaded by a user to be audited are obtained, wherein the auditing materials comprise accident address information, a commuting path and an accident site picture, whether the accident happens in the range of the commuting path or not is audited firstly according to the accident address information and the commuting path, if the accident happens in the range of the commuting path, the limb disability condition of the user in the accident continues to be audited, the posture of the user is predicted by the aid of the accident site picture, the limb disability condition of the user is judged according to the posture of the user, and finally, whether the work injury auditing result of the user passes or not is judged by combining a action path auditing result and a limb disability auditing result of the user. In a work injury auditing scene, the application realizes auditing of the action path through the accident address information and the commuting path uploaded by the user, and after the action path is audited, auditing of the limb injury condition of the user is completed through a pre-trained injury detection model and an accident scene picture uploaded by the user, so that the injury detection precision and the work injury auditing efficiency are improved, and the consumption of manpower and material resources is reduced.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A method for automatically auditing industrial injuries is characterized by comprising the following steps:
receiving a work injury audit instruction, and acquiring audit materials uploaded by a user to be audited, wherein the audit materials comprise accident address information, a commuting path and an accident scene picture;
generating an action path auditing result of the user to be audited based on the accident address information and the commuting path;
marking the human body joint points on the picture of the accident scene to generate a human body joint point image;
importing the human body joint point image into a pre-trained posture prediction model to obtain a posture prediction result of the user to be audited;
comparing the posture prediction result with a preset standard disabled posture result to obtain a disabled limb audit result of the user to be audited;
and generating a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
2. The method for automatically auditing industrial injuries according to claim 1, where the step of generating an action path audit result for the user to be audited based on the accident address information and the commute path specifically includes:
judging whether an accident address is within the range of the commute path or not based on the accident address information and the commute path;
and obtaining an action path auditing result of the user to be audited by judging whether the accident address is in the range of the commuting path or not, wherein the action path auditing result comprises a first action path auditing result and a second action path auditing result, the first action path auditing result is that the accident address is in the range of the commuting path, and the second action path auditing result is that the accident address is not in the range of the commuting path.
3. The method for automatically auditing a work injury according to claim 1, further comprising, prior to the step of generating a human joint image by performing human joint labeling on the picture of the accident scene:
identifying the picture of the accident scene based on a preset content identification model to obtain human body contour characteristics;
denoising the accident scene picture, and removing salt and pepper noise points of the accident scene picture to obtain a denoised image;
determining a human body region in the accident scene picture based on the de-noised image and the human body contour characteristics;
the step of labeling the human body joint points of the accident scene picture to generate a human body joint point image specifically comprises the following steps:
and marking the human body joint points of the accident scene picture carrying the human body area to generate a human body joint point image.
4. The method for automatically auditing a industrial injury according to claim 3, where the step of labeling the human joint points to the picture of the accident scene to generate an image of the human joint points specifically comprises:
importing the accident scene picture carrying the human body region into a joint point confidence coefficient prediction model which is trained in advance;
predicting the confidence of each pixel point in the human body region by using the joint point confidence prediction model;
and marking the human body joint points based on the confidence coefficient of each pixel point in the human body region to generate a human body joint point image.
5. The method for automatically auditing industrial injury according to claim 4, wherein the step of labeling human joint points based on the confidence of each pixel point in the human body region to generate a human joint point image specifically comprises:
calculating affinity values between the human joint points;
judging whether the affinity value is greater than or equal to a preset threshold value;
and when the affinity value is greater than or equal to a preset threshold value, performing matching connection on the human body joint points to obtain a human body joint point image.
6. The method for automatically auditing a work injury according to claim 5, wherein prior to the step of importing the human joint image into a pre-trained pose prediction model to obtain a pose prediction result for the user to be audited, the method further comprises:
constructing an image coordinate system, and acquiring the coordinates of human body joint points in the human body region based on the image coordinate system;
and identifying the connecting lines of the human body joint points, and calculating the included angle between the connecting lines of the human body joint points to obtain the movable angle of the human body joint.
7. The method of claim 6, wherein the step of importing the human joint image into a pre-trained pose prediction model to obtain a pose prediction result of the user to be reviewed specifically comprises:
extracting the characteristics of the human body joint point image to obtain a connecting line characteristic and a moving angle characteristic;
respectively coding the connecting line characteristic and the moving angle characteristic to obtain a first characteristic vector and a second characteristic vector;
respectively carrying out linear transformation on the first feature vector and the second feature vector, and fusing the first feature vector and the second feature vector after the linear transformation to obtain a fused feature vector;
performing linear regression on the fusion feature vector to obtain a regression feature vector;
and decoding the regression feature vector to obtain a posture prediction result of the user to be audited.
8. An apparatus for automatically auditing a work injury, comprising:
the system comprises a material acquisition module, a data processing module and a data processing module, wherein the material acquisition module is used for receiving a work injury audit instruction and acquiring audit materials uploaded by a user to be audited, and the audit materials comprise accident address information, a commuting path and an accident scene picture;
the path checking module is used for generating an action path checking result of the user to be checked based on the accident address information and the commuting path;
the joint point marking module is used for marking the human joint points of the accident scene picture to generate a human joint point image;
the posture prediction module is used for importing the human body joint point image into a posture prediction model trained in advance to obtain a posture prediction result of the user to be checked;
and the disability auditing module is used for comparing the posture prediction result with a preset standard disability posture result to obtain a limb disability auditing result of the user to be audited.
And the work injury checking module is used for generating a work injury checking result of the user to be checked based on the action path checking result and the limb injury checking result.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed performs the steps of a method for automatic review of work wounds as claimed in any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, carry out the steps of a method for automated work injury review as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111542371.9A CN114240364A (en) | 2021-12-13 | 2021-12-13 | Method and device for automatically auditing industrial injury, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111542371.9A CN114240364A (en) | 2021-12-13 | 2021-12-13 | Method and device for automatically auditing industrial injury, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114240364A true CN114240364A (en) | 2022-03-25 |
Family
ID=80757068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111542371.9A Pending CN114240364A (en) | 2021-12-13 | 2021-12-13 | Method and device for automatically auditing industrial injury, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114240364A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345396A (en) * | 2018-09-13 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of intelligence people wound Claims Resolution management system |
| CN109345394A (en) * | 2018-08-30 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of medical supervision and examination system of people's wound Claims Resolution |
| CN109636632A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning |
| US20190197414A1 (en) * | 2017-12-22 | 2019-06-27 | At&T Intellectual Property I, L.P. | System and method for estimating potential injuries from a vehicular incident |
| CN112037235A (en) * | 2020-08-27 | 2020-12-04 | 平安科技（深圳）有限公司 | Injury picture automatic auditing method and device, electronic equipment and storage medium |
| CN112085466A (en) * | 2020-08-31 | 2020-12-15 | 阳光财产保险股份有限公司 | Device and method for generating damage assessment result of human injury claim |
| CN113657343A (en) * | 2021-08-30 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Method and device for generating claim resource data based on machine learning |
| CN113781462A (en) * | 2021-09-17 | 2021-12-10 | 平安医疗健康管理股份有限公司 | Human body disability detection method, device, equipment and storage medium |
-
2021
- 2021-12-13 CN CN202111542371.9A patent/CN114240364A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190197414A1 (en) * | 2017-12-22 | 2019-06-27 | At&T Intellectual Property I, L.P. | System and method for estimating potential injuries from a vehicular incident |
| CN109345394A (en) * | 2018-08-30 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of medical supervision and examination system of people's wound Claims Resolution |
| CN109345396A (en) * | 2018-09-13 | 2019-02-15 | 医倍思特（北京）医疗信息技术有限公司 | A kind of intelligence people wound Claims Resolution management system |
| CN109636632A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning |
| CN112037235A (en) * | 2020-08-27 | 2020-12-04 | 平安科技（深圳）有限公司 | Injury picture automatic auditing method and device, electronic equipment and storage medium |
| CN112085466A (en) * | 2020-08-31 | 2020-12-15 | 阳光财产保险股份有限公司 | Device and method for generating damage assessment result of human injury claim |
| CN113657343A (en) * | 2021-08-30 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Method and device for generating claim resource data based on machine learning |
| CN113781462A (en) * | 2021-09-17 | 2021-12-10 | 平安医疗健康管理股份有限公司 | Human body disability detection method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 山东人社: ""青岛首创‘五位一体’工伤保险智能服务平台 推动工伤保险服务水平再上新台阶"", pages 1 - 6, Retrieved from the Internet <URL:https://sdxw.iqilu.com/share/YS0yMS03OTI4Mzg1.html> * |
| 张蕊: "《社会保障学概论》", 30 September 2021, 西安交通大学出版社, pages: 117 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112863683B (en) | Medical record quality control method and device based on artificial intelligence, computer equipment and storage medium | |
| CN112561684A (en) | Financial fraud risk identification method and device, computer equipment and storage medium | |
| CN112699297A (en) | Service recommendation method, device and equipment based on user portrait and storage medium | |
| CN113127633B (en) | Intelligent conference management method and device, computer equipment and storage medium | |
| CN114241459B (en) | Driver identity verification method and device, computer equipment and storage medium | |
| CN112650875A (en) | House image verification method and device, computer equipment and storage medium | |
| CN113705534A (en) | Behavior prediction method, behavior prediction device, behavior prediction equipment and storage medium based on deep vision | |
| CN113761577A (en) | Big data desensitization method and device, computer equipment and storage medium | |
| CN114550051A (en) | Vehicle loss detection method and device, computer equipment and storage medium | |
| CN110909578A (en) | Low-resolution image recognition method and device and storage medium | |
| CN113781462A (en) | Human body disability detection method, device, equipment and storage medium | |
| CN114550951A (en) | Rapid medical treatment method and device, computer equipment and storage medium | |
| CN114861241A (en) | Anti-peeping screen method based on intelligent detection and related equipment thereof | |
| CN113343898B (en) | Mask shielding face recognition method, device and equipment based on knowledge distillation network | |
| CN113963446A (en) | Behavior recognition method and system based on human skeleton | |
| CN116681045A (en) | Report generation method, report generation device, computer equipment and storage medium | |
| CN114240364A (en) | Method and device for automatically auditing industrial injury, computer equipment and storage medium | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN115967549A (en) | Anti-leakage method based on internal and external network information transmission and related equipment thereof | |
| CN115618859A (en) | Research efficiency management method, device, equipment and storage medium based on big data | |
| CN114549221A (en) | Vehicle accident loss processing method and device, computer equipment and storage medium | |
| CN114647733B (en) | Question and answer corpus evaluation method and device, computer equipment and storage medium | |
| CN113723093B (en) | Personnel management policy recommendation method and device, computer equipment and storage medium | |
| CN114359582B (en) | Small sample feature extraction method based on neural network and related equipment | |
| CN117422523A (en) | Product online method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |