A site personnel identity recognition management method and system

Abstract

The application discloses a kind of construction site personnel identity recognition management method and system, it includes: the facial expression information of each construction site personnel is collected, and facial expression generation model is constructed based on facial expression information, and facial generation expression is generated according to it;The facial generation expression of construction site personnel is bound with identity information two-dimensional code and is associated with storage;The identity information two-dimensional code of construction site personnel and real-time facial expression are acquired, and the corresponding facial generation expression is acquired based on identity information two-dimensional code;Real-time facial expression and facial generation expression are analyzed, facial expression difference characteristics are determined, and the identity similarity of construction site personnel is evaluated based on it;Based on the evaluation result, whether the identity recognition verification of construction site personnel passes is judged.The facial expression of construction site personnel is generated by modeling in the application, which is compared and evaluated with the captured facial expression to realize the accurate identification and management of the identity of construction site personnel, and the accuracy and efficiency of identity recognition are improved.

Description

Technical Field

[0001] This invention relates to the field of personnel management technology, and in particular to a method and system for identifying and managing personnel on construction sites. Background Technology

[0002] In modern construction site management, accurate identification and management of site personnel is crucial. However, traditional identification methods typically rely on manual verification, which is inefficient and prone to errors. With the development and application of artificial intelligence technology, facial recognition-based methods for identifying and managing construction site personnel are gaining increasing attention.

[0003] The facial recognition-based method for identifying and managing construction site personnel utilizes computer vision and artificial intelligence technologies to accurately identify and manage personnel by capturing and comparing their facial features. This method improves the accuracy and efficiency of identification, reduces human error, and also facilitates the automation and intelligentization of site safety management and attendance management. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method and system for identifying and managing construction site personnel, comprising:

[0005] Collect facial expression information of each construction site worker, and determine the facial expression features of the construction site workers based on the facial expression information;

[0006] A facial expression generation model for construction site personnel is constructed based on facial expression features, and facial expressions for each construction site personnel are generated based on the facial expression generation model.

[0007] The facial expressions generated for each construction site worker are bound to their identity information QR codes, and the bound facial expressions and identity information QR codes are stored together.

[0008] Obtain the QR code of the construction site personnel's identity information and their real-time facial expressions, and generate facial expressions based on the QR code of the identity information of the corresponding construction site personnel;

[0009] Analyze real-time facial expressions and generated facial expressions to determine the differences in facial expression characteristics;

[0010] The identity similarity of construction site personnel is evaluated based on facial expression differences, and an identity similarity evaluation value is obtained.

[0011] The identity verification of construction site personnel is determined based on the identity similarity assessment value.

[0012] Furthermore, the process of collecting facial expression information from each construction site worker and determining the facial expression features of the workers based on this information includes:

[0013] Collect facial expression information of each construction site worker, and extract facial muscle shape, eye shape, mouth shape and nose shape from the facial expression information;

[0014] Facial muscle shape, eye shape, mouth shape, and nose shape were identified as facial expression features of construction site personnel.

[0015] Furthermore, the step of constructing a facial expression generation model for construction site personnel based on facial expression features, and generating facial expressions for each construction site personnel based on the facial expression generation model, includes:

[0016] An image set is constructed based on facial expression features, and the image set is input into a preset image generation model to construct an initial model for generating facial expressions of construction site personnel.

[0017] The image set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial model for generating facial expressions of construction site workers.

[0018] The initial model for generating facial expressions of construction site workers is trained and tested until it meets the preset convergence condition, thus obtaining the facial expression generation model of construction site workers.

[0019] The facial expressions of construction workers are generated based on a facial expression generation model, resulting in several facial expressions of the construction workers.

[0020] Furthermore, the analysis of real-time facial expressions and generated facial expressions to determine facial expression difference features includes:

[0021] The system acquires real-time facial expressions of construction site personnel, identifies these expressions, and determines their state.

[0022] Determine the facial expression corresponding to the facial expression state from several facial expressions generated by construction site personnel;

[0023] The real-time facial expressions and the corresponding generated facial expressions are made transparent and scaled, and the processed real-time facial expressions and the corresponding generated facial expressions are overlapped and merged according to the facial contours to form a composite facial expression.

[0024] Inconsistent facial expression features are identified from synthesized facial expressions, and these inconsistent facial expression features are defined as facial expression difference features.

[0025] Furthermore, the assessment of the identity similarity of construction site personnel based on facial expression difference features to obtain an identity similarity assessment value includes:

[0026] Obtain facial expression difference features and group them according to the same facial expression features to obtain several groups of facial expression difference feature groups;

[0027] Calculate the similarity between facial expression difference features in each group of facial expression difference features, evaluate the similarity, and obtain the similarity evaluation value for each group of facial expression difference features.

[0028] Obtain the facial expression state corresponding to each group of facial expression difference features, and determine the weight of each group of facial expression difference features based on the facial expression state.

[0029] The similarity assessment value of each group of facial expression difference feature groups is weighted and added together with the corresponding weight to obtain the identity similarity assessment value of the construction site personnel.

[0030] Furthermore, determining the weight of each group of facial expression difference feature groups based on facial expression state includes:

[0031] A pre-defined weight value-facial expression state type correspondence is established, with a corresponding weight value associated with each facial expression state type.

[0032] Determine the facial expression state corresponding to each group of facial expression difference features, and based on the mapping relationship between the facial expression state type to which the facial expression state belongs and the correspondence between the weight value and the facial expression state type, select the weight value corresponding to the facial expression state type as the weight of each group of facial expression difference features.

[0033] Furthermore, the step of determining whether the identity verification of construction site personnel passes based on the identity similarity assessment value includes:

[0034] If the identity similarity assessment value exceeds the preset threshold, the identity verification of the construction site personnel is deemed to have passed.

[0035] If the identity similarity assessment value does not exceed the preset threshold, it is determined that the identity verification of the construction site personnel has failed.

[0036] The present invention also provides a construction site personnel identification and management system, comprising:

[0037] The data acquisition module is used to collect facial expression information of each construction site worker and determine the facial expression features of the workers based on the facial expression information.

[0038] The generation module is used to construct a facial expression generation model for construction site personnel based on facial expression features, and to generate facial expressions for each construction site personnel based on the facial expression generation model.

[0039] The association module is used to bind the facial expressions generated by each construction site worker to their identity information QR code, and to store the bound facial expressions and identity information QR code together.

[0040] The acquisition module is used to acquire the QR code of the identity information of the construction site personnel and their real-time facial expressions, and to generate facial expressions based on the QR code of the identity information of the corresponding construction site personnel.

[0041] The analysis module is used to analyze real-time facial expressions and generated facial expressions to determine the differences in facial expression features;

[0042] The evaluation module is used to assess the identity similarity of construction site personnel based on facial expression differences, and obtain an identity similarity evaluation value.

[0043] The identification module is used to determine whether the identity verification of construction site personnel has passed based on the identity similarity assessment value.

[0044] Compared with existing technologies, the construction site personnel identification and management method and system of this invention have the following advantages:

[0045] This invention collects a large amount of facial expression data and builds a facial expression generation model based on this data, which can generate facial expressions of construction site personnel.

[0046] This invention evaluates the similarity of construction site personnel's identities based on facial expression differences, which can help determine the degree of matching between the generated facial expression data and the actual identity, thereby improving the accuracy and efficiency of identity recognition and reducing human error.

[0047] This invention analyzes real-time facial expressions and generated expressions, and verifies them in conjunction with identity information, thereby achieving automated identification and verification of construction site personnel, saving manpower and time costs. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the process structure of the construction site personnel identification and management method in an embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of the composition of the construction site personnel identification management system in an embodiment of the present invention. Detailed Implementation

[0050] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0051] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0052] The terms “second” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the weight of the indicated technical feature. Therefore, a feature defined with “second” or “second” may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, “multiple” means two or more.

[0053] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a cooling connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0054] like Figure 1 As shown in the embodiments of this application, a method for identifying and managing the identity of construction site personnel is provided, including: S100: collecting facial expression information of each construction site personnel and determining the facial expression features of the construction site personnel based on the facial expression information; S200: constructing a facial expression generation model of construction site personnel based on the facial expression features, and generating facial expressions for each construction site personnel based on the facial expression generation model; S300: binding the facial expressions of each construction site personnel with an identity information QR code, and storing the bound facial expressions and identity information QR codes together; S400: obtaining the identity information QR code and real-time facial expressions of construction site personnel, and obtaining the corresponding facial expressions of construction site personnel based on the identity information QR code; S500: analyzing the real-time facial expressions and facial expressions to determine facial expression difference features; S600: evaluating the identity similarity of construction site personnel based on the facial expression difference features to obtain an identity similarity evaluation value; S700: determining whether the identity verification of construction site personnel has passed based on the identity similarity evaluation value.

[0055] Furthermore, this invention collects a large amount of facial expression data and constructs a facial expression generation model based on this data, enabling the generation of facial expressions of construction site personnel. This invention also evaluates the similarity of construction site personnel's identities based on facial expression difference features, helping to determine the degree of matching between the generated facial expression data and the actual identities, thereby improving the accuracy and efficiency of identity recognition and reducing human error. Finally, by analyzing real-time facial expressions and generated expressions, and combining this with identity information for verification, this invention enables automated identification and verification of construction site personnel's identities, saving manpower and time costs.

[0056] In an embodiment of this application, a method for identifying and managing the identity of construction site personnel is provided. The method involves collecting facial expression information of each construction site worker and determining the facial expression features of the workers based on the facial expression information. This includes: collecting facial expression information of each construction site worker and extracting facial muscle shape, eye shape, mouth shape, and nose shape from the facial expression information; and determining the facial muscle shape, eye shape, mouth shape, and nose shape as the facial expression features of the workers.

[0057] Specifically, the facial expressions of construction workers are captured in real time using cameras or other facial recognition devices, which can be static images or video streams; facial expression recognition algorithms are used to analyze and process the collected facial expression data to extract features such as facial muscle shape, eye shape, mouth shape, and nose shape; the extracted facial muscle shape, eye shape, mouth shape, and nose shape are then identified as the facial expression features of the construction workers.

[0058] In an embodiment of this application, a method for identifying and managing construction site personnel is provided. The method involves constructing a facial expression generation model for construction site personnel based on facial expression features, and generating facial expressions for each construction site personnel based on the facial expression generation model. This includes: constructing an image set based on facial expression features and inputting the image set into a preset image generation model to construct an initial facial expression generation model for construction site personnel; dividing the image set into a training set and a test set according to a certain ratio, and inputting the training set and test set into the initial facial expression generation model for construction site personnel; training and testing the initial facial expression generation model for construction site personnel until it meets a preset convergence condition to obtain a facial expression generation model for construction site personnel; and generating several facial expressions for construction site personnel based on the facial expression generation model.

[0059] Specifically, based on the extracted facial expression features, an image dataset containing facial expression features of construction site workers is constructed. Each image should include corresponding facial muscle shape, eye shape, mouth shape, and nose shape, among other features. A suitable preset image generation model for the facial expression generation task is selected, such as a model based on Generative Adversarial Network (GAN) or Variational Autoencoder (VAE). The constructed facial expression feature image set is divided into a training set and a test set according to a certain ratio, typically using 70% of the data as the training set and 30% as the test set. The training set and the test set are input into the selected preset image generation model for training and testing. During training, the model gradually improves its ability to generate realistic facial expression images by learning from the input facial expression feature image set. The testing process is used to evaluate the model's performance and generalization ability. The facial expression generation model for construction site workers is trained and its parameters are tuned in multiple rounds until the preset convergence conditions and performance indicators are met. Once the trained model reaches the expected performance, it can be used to generate facial expressions of construction site workers, resulting in several realistic facial expressions.

[0060] In an embodiment of this application, a method for identifying and managing the identity of construction site personnel is provided. The method involves analyzing real-time facial expressions and generated facial expressions to determine facial expression difference features. This includes: acquiring real-time facial expressions of construction site personnel and identifying these expressions to determine their facial expression states; identifying the generated facial expression corresponding to the given facial expression state from a plurality of generated facial expressions of the construction site personnel; performing transparency and scaling processing on the real-time facial expressions and the corresponding generated facial expressions, and then overlapping and merging the processed real-time facial expressions and the corresponding generated facial expressions according to facial contours to form a composite facial expression; identifying inconsistent facial expression features from the composite facial expression, and defining these inconsistent facial expression features as facial expression difference features.

[0061] Specifically, facial expression recognition algorithms are used to identify real-time facial expressions and determine their states, such as happiness, anger, and surprise. From several previously generated facial expressions, the corresponding generated expressions are selected, finding the one that best matches the real-time expression. The real-time facial expression and its corresponding generated expression are then processed with transparency and scaling for subsequent synthesis. The processed real-time facial expression and its corresponding generated expression are then overlapped and merged according to facial contours to form a synthesized facial expression. Inconsistent facial expression features are identified from the synthesized facial expression, such as differences between the real-time and generated expressions, including inconsistencies in eye expressions, mouth expressions, and facial muscle movements.

[0062] In an embodiment of this application, a method for identifying and managing the identity of construction site personnel is provided. The method involves evaluating the similarity of construction site personnel based on facial expression difference features to obtain an identity similarity assessment value. This includes: acquiring facial expression difference features and grouping these features into several groups based on shared facial expression characteristics; calculating the similarity between facial expression difference features within each group and evaluating the similarity to obtain a similarity assessment value for each group; acquiring the facial expression state corresponding to each group and determining the weight of each group based on the facial expression state; and weighted summing the similarity assessment value of each group with its corresponding weight to obtain the identity similarity assessment value for the construction site personnel.

[0063] Specifically, the process involves obtaining the differences in facial expressions, such as differences in eye expressions, mouth expressions, and facial muscle movements; grouping these differences according to shared facial expression features to obtain several groups, for example, grouping all differences in eye expressions into one group, all differences in mouth expressions into another, and so on; calculating the similarity between the differences in facial expressions within each group using various similarity metrics, such as Euclidean distance or cosine similarity; evaluating the similarity of each group to determine its assessment value; determining the weight of each group based on facial expression states; and finally, weighted summing of the similarity assessment value and the corresponding weights to obtain the identity similarity assessment value for construction site personnel. This value can be used to assess the similarity of facial expression features between different construction site personnel.

[0064] In an embodiment of this application, a method for identifying and managing the identity of construction site personnel is provided. The step of determining the weight of each group of facial expression difference feature groups based on facial expression states includes: pre-setting a weight value-facial expression state type correspondence, wherein the weight value-facial expression state type correspondence is associated with a corresponding weight value for each facial expression state type; determining the facial expression state corresponding to each group of facial expression difference feature groups, and selecting the weight value corresponding to the facial expression state type as the weight of each group of facial expression difference feature groups based on the mapping relationship between the facial expression state type to which the facial expression state belongs and the weight value in the weight value-facial expression state type correspondence.

[0065] Specifically, for each group of facial expression difference features, its corresponding facial expression state type is determined, such as happiness, anger, surprise, etc. Based on the mapping relationship between facial expression state types and their corresponding weights, the weight values ​​corresponding to these facial expression state types are selected as the weights for each group of facial expression difference features. This mapping relationship can be a pre-defined mapping table, where the corresponding weight value is found based on the facial expression state type. Based on this mapping relationship, the corresponding weight value is determined for each group of facial expression difference features.

[0066] In an embodiment of this application, a method for managing the identification of construction site personnel is provided. The step of determining whether the identification verification of construction site personnel is successful based on the identification similarity assessment value includes: if the identification similarity assessment value exceeds a preset threshold, then the identification verification of construction site personnel is deemed successful; if the identification similarity assessment value does not exceed the preset threshold, then the identification verification of construction site personnel is deemed unsuccessful.

[0067] Specifically, if the calculated identity similarity assessment value exceeds a preset threshold, the identity verification of the construction site personnel is considered successful; otherwise, the identity verification is considered unsuccessful. This process, by setting an appropriate threshold, can effectively verify the identity of construction site personnel. A similarity assessment value exceeding the threshold indicates that the facial expression features of the construction site personnel have a high similarity to preset features, thus passing the identity verification.

[0068] like Figure 2 As shown in the embodiments of this application, a construction site personnel identification management system is provided, including: a collection module, used to collect facial expression information of each construction site personnel and determine the facial expression features of the construction site personnel based on the facial expression information; a generation module, used to construct a facial expression generation model of the construction site personnel based on the facial expression features and generate a facial expression for each construction site personnel based on the facial expression generation model; an association module, used to bind the facial expression of each construction site personnel to an identity information QR code and store the bound facial expression and identity information QR code together; an acquisition module, used to acquire the identity information QR code and real-time facial expression of the construction site personnel, and acquire the facial expression of the corresponding construction site personnel based on the identity information QR code; an analysis module, used to analyze the real-time facial expression and the facial expression to determine the facial expression difference features; an evaluation module, used to evaluate the identity similarity of the construction site personnel based on the facial expression difference features and obtain an identity similarity evaluation value; and a recognition module, used to determine whether the identity verification of the construction site personnel is successful based on the identity similarity evaluation value.

[0069] In summary, this invention provides a method and system for identifying and managing construction site personnel, comprising: collecting facial expression information of each construction site worker, constructing a facial expression generation model based on the facial expression information, and generating facial expressions based on the model; binding and storing the generated facial expressions of construction site workers with their identity information QR codes; acquiring the identity information QR codes and real-time facial expressions of construction site workers, and acquiring the corresponding generated facial expressions based on the identity information QR codes; analyzing the real-time facial expressions and the generated facial expressions to determine the facial expression difference features, and evaluating the similarity of the construction site workers' identities based on these features; and determining whether the identity verification of the construction site workers has passed based on the evaluation results. This invention achieves accurate identification and management of construction site workers' identities by modeling and generating their facial expressions, comparing and evaluating them with captured facial expressions, thereby improving the accuracy and efficiency of identity recognition.

[0070] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0071] The above description is merely one embodiment of the present invention, and should not be construed as limiting the scope of the invention. Any structural changes made based on the present invention, as long as they do not depart from the essence of the invention, should be considered as falling within the protection scope of the present invention and subject to its restrictions. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the platform described above can be referred to the corresponding processes in the foregoing platform embodiments, and will not be repeated here.

[0072] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, platform, article, or device / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to those processes, platforms, articles, or devices / platforms.

[0073] The technical solutions of the present invention have been described in conjunction with the accompanying drawings and further embodiments. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

[0074] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A method for identifying and managing personnel at construction sites, characterized in that, include: Collect facial expression information of each construction site worker, and determine the facial expression features of the construction site workers based on the facial expression information; A facial expression generation model for construction site personnel is constructed based on facial expression features, and facial expressions for each construction site personnel are generated based on the facial expression generation model. The facial expressions generated for each construction site worker are bound to their identity information QR codes, and the bound facial expressions and identity information QR codes are stored together. Obtain the QR code of the construction site personnel's identity information and their real-time facial expressions, and generate facial expressions based on the QR code of the identity information of the corresponding construction site personnel; Analyze real-time facial expressions and generated facial expressions to determine the differences in facial expression features; The identity similarity of construction site personnel is evaluated based on facial expression differences, and an identity similarity evaluation value is obtained. The identity verification of construction site personnel is determined based on the identity similarity assessment value. The analysis of real-time facial expressions and generated facial expressions to determine facial expression difference features includes: The system acquires real-time facial expressions of construction site personnel, identifies these expressions, and determines their state. Determine the facial expression corresponding to the facial expression state from several facial expressions generated by construction site personnel; The real-time facial expressions and the corresponding generated facial expressions are made transparent and scaled, and the processed real-time facial expressions and the corresponding generated facial expressions are overlapped and merged according to the facial contours to form a composite facial expression. Inconsistent facial expression features are identified from synthesized facial expressions, and these inconsistent facial expression features are defined as facial expression difference features.

2. A method for identifying and managing construction site personnel as described in claim 1, characterized in that, The process of collecting facial expression information from each construction site worker and determining their facial expression features based on that information includes: Collect facial expression information of each construction site worker, and extract facial muscle shape, eye shape, mouth shape and nose shape from the facial expression information; Facial muscle shape, eye shape, mouth shape, and nose shape were identified as facial expression features of construction site personnel.

3. A method for identifying and managing construction site personnel as described in claim 2, characterized in that, The step of constructing a facial expression generation model for construction site workers based on facial expression features, and generating facial expressions for each construction site worker based on the facial expression generation model, includes: An image set is constructed based on facial expression features, and the image set is input into a preset image generation model to construct an initial model for generating facial expressions of construction site personnel. The image set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial model for generating facial expressions of construction site workers. The initial model for generating facial expressions of construction site workers is trained and tested until it meets the preset convergence condition, thus obtaining the facial expression generation model of construction site workers. The facial expressions of construction workers are generated based on a facial expression generation model, resulting in several facial expressions of the construction workers.

4. A method for identifying and managing construction site personnel as described in claim 1, characterized in that, The assessment of the identity similarity of construction site personnel based on facial expression difference features yields an identity similarity assessment value, including: Obtain facial expression difference features and group them according to the same facial expression features to obtain several groups of facial expression difference feature groups; Calculate the similarity between facial expression difference features in each group of facial expression difference features, evaluate the similarity, and obtain the similarity evaluation value for each group of facial expression difference features. Obtain the facial expression state corresponding to each group of facial expression difference features, and determine the weight of each group of facial expression difference features based on the facial expression state. The similarity assessment value of each group of facial expression difference feature groups is weighted and added together with the corresponding weight to obtain the identity similarity assessment value of the construction site personnel.

5. A method for identifying and managing construction site personnel as described in claim 4, characterized in that, The determination of the weights for each group of facial expression difference features based on facial expression states includes: A pre-defined weight value-facial expression state type correspondence is established, with a corresponding weight value associated with each facial expression state type. Determine the facial expression state corresponding to each group of facial expression difference features, and based on the mapping relationship between the facial expression state type to which the facial expression state belongs and the correspondence between the weight value and the facial expression state type, select the weight value corresponding to the facial expression state type as the weight of each group of facial expression difference features.

6. A method for identifying and managing construction site personnel as described in claim 5, characterized in that, The method of determining whether the identity verification of construction site personnel passes based on identity similarity assessment values ​​includes: If the identity similarity assessment value exceeds the preset threshold, the identity verification of the construction site personnel is deemed to have passed. If the identity similarity assessment value does not exceed the preset threshold, it is determined that the identity verification of the construction site personnel has failed.

7. A construction site personnel identification and management system, characterized in that, include: The data acquisition module is used to collect facial expression information of each construction site worker and determine the facial expression features of the workers based on the facial expression information. The generation module is used to construct a facial expression generation model for construction site personnel based on facial expression features, and to generate facial expressions for each construction site personnel based on the facial expression generation model. The association module is used to bind the facial expressions generated by each construction site worker to their identity information QR code, and to store the bound facial expressions and identity information QR code together. The acquisition module is used to acquire the QR code of the identity information of the construction site personnel and their real-time facial expressions, and to generate facial expressions based on the QR code of the identity information of the corresponding construction site personnel. The analysis module is used to analyze real-time facial expressions and generated facial expressions to determine the differences in facial expression features; The evaluation module is used to assess the identity similarity of construction site personnel based on facial expression differences, and obtain an identity similarity evaluation value. The identification module is used to determine whether the identity verification of construction site personnel has passed based on the identity similarity assessment value; The analysis of real-time facial expressions and generated facial expressions to determine facial expression difference features includes: The system acquires real-time facial expressions of construction site personnel, identifies these expressions, and determines their state. Determine the facial expression corresponding to the facial expression state from several facial expressions generated by construction site personnel; The real-time facial expressions and the corresponding generated facial expressions are made transparent and scaled, and the processed real-time facial expressions and the corresponding generated facial expressions are overlapped and merged according to the facial contours to form a composite facial expression. Inconsistent facial expression features are identified from synthesized facial expressions, and these inconsistent facial expression features are defined as facial expression difference features.

Images