Regional personnel intelligent management method, related equipment and dynamic coding label

Abstract

The application discloses a regional personnel intelligent management method, related equipment and a dynamic coding label, which is realized based on a dynamic coding label configured for regional personnel, a radio frequency positioning network and a multi-modal visual recognition device. A rough position is obtained through radio frequency positioning and a visual device is dispatched. The personnel attribute and accurate position are identified in combination with the dynamic coding label. After the overall and attribute sub-density are calculated, the dynamic threshold is compared. The density abnormal situation is judged and the corresponding management operation is performed. The dynamic coding label contains a periodically updated visible light and fluorescent hidden part, which can prevent counterfeiting and help accurate positioning and attribute matching. The multi-modal visual device reduces invalid collection through radio frequency scheduling and improves the accuracy and efficiency in complex environments in combination with label feature recognition. The scheme realizes abnormal fast disposal through the dual statistics of overall and attribute sub-density, avoids misjudgment through the dynamic threshold rule base, and realizes real-time data processing and preplan library linkage, thereby providing strong support for regional safety and efficient operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management, more particularly, to a regional personnel intelligent management method, related equipment and a dynamic coding label. BACKGROUND

[0002] With the acceleration of urbanization, personnel-intensive areas such as industrial parks, commercial complexes, and transportation hubs are increasing, and accurate and efficient management of personnel in the region has become a core requirement for ensuring public safety and improving operational efficiency. Especially in the context of public emergencies and important event security, quickly grasping the distribution, attributes, and density of personnel is the key to scientific scheduling and risk warning, so developing an efficient regional personnel intelligent management method has strong practical necessity.

[0003] In the prior art, regional personnel management usually uses visual recognition technology to detect personnel by collecting images with surveillance cameras, but this method is easily affected by factors such as light, obstruction, and complex background, with large fluctuations in recognition accuracy, and cannot efficiently associate personnel attribute information, making it difficult to achieve classification management. In addition, the method combines manual statistics with traditional monitoring, relying on on-site patrols or reviewing monitoring data by management personnel, but this method not only has poor real-time performance, but also cannot complete large-scale personnel density statistics and attribute classification statistics, making it difficult to adapt to dynamic management needs. These defects result in deficiencies in personnel positioning accuracy, recognition security, statistical comprehensiveness, and management response timeliness in the prior art, and when faced with sudden increases in personnel flow and the gathering of personnel with specific attributes, problems such as delayed warning and improper handling may occur, making it difficult to meet the high-precision and intelligent needs of modern regional management.

[0004] Therefore, there is an urgent need for a new regional personnel intelligent management method to address the deficiencies of existing technology and achieve the goal of intelligent management of accurate positioning, efficient recognition, comprehensive statistics, and timely response to abnormalities. SUMMARY

[0005] The present application provides a regional personnel intelligent management method, related equipment and a dynamic coding label, which realizes personnel accurate positioning, attribute efficient recognition, density abnormal situation rapid judgment and automatic disposal through the cooperation of dynamic coding label, radio frequency positioning network and multi-modal visual recognition equipment, providing support for regional safety operation.

[0006] A regional personnel intelligent management method is realized based on a dynamic coding label configured for each personnel in the region, a radio frequency positioning network deployed in the region, and multi-modal visual recognition equipment, and the method comprises:

[0007] Acquiring rough regional position information of the personnel by the radio frequency positioning network, and scheduling corresponding visual recognition devices based on the rough regional position information to determine attribute category and position information of the personnel in the region by recognizing the dynamic coding label, wherein the coding information of the dynamic coding label comprises a periodically dynamically updated visible light part and / or a fluorescent hidden part, and is associated with personnel attribute category information in a background database;

[0008] Based on the recognized attribute category and position information of the personnel, calculating the overall personnel density of the target region in real time, and simultaneously calculating at least one attribute sub-density based on the attribute category of the personnel, the attribute sub-density being a density obtained by counting personnel with the same attribute category in the target region;

[0009] Comparing the overall personnel density and the attribute sub-density calculated in real time with a preset dynamic threshold rule library to determine whether there is a density abnormal situation, the dynamic threshold rule library comprising attribute sub-density thresholds set based on different attribute category combinations and / or different time and space scenarios;

[0010] If it is determined that there is a density abnormal situation, generating and executing corresponding management operation instructions according to the abnormal type and a preset management plan library.

[0011] Optionally, acquiring rough regional position information of the personnel by the radio frequency positioning network, and scheduling corresponding visual recognition devices based on the rough regional position information to determine attribute category and position information of the personnel in the region by recognizing the dynamic coding label, comprising:

[0012] Acquiring rough regional position information of each personnel in the region by periodic detection signals of the radio frequency positioning network;

[0013] Scheduling visual recognition devices deployed above the corresponding region to perform image acquisition on the target region according to the rough regional position information;

[0014] During the image acquisition process, analyzing the image to detect whether there is an area where personnel are shielded or dynamic coding labels overlap;

[0015] If so, scheduling visual recognition devices of at least two different spectral characteristics to perform cooperative image acquisition and multi-modal image fusion processing on the target region to resolve the shielded dynamic coding labels;

[0016] From the acquired images and the images after fusion processing, positioning and recognizing the current coding information of the dynamic coding label worn by each personnel;

[0017] The identified current encoding information is matched with a background database, a corresponding attribute category of a person is associated, and position information of the person is determined in combination with image and radio frequency signal analysis.

[0018] Optionally, before scheduling the visual recognition device, the method further comprises extracting and analyzing multi-dimensional radio frequency characteristics of the radio frequency positioning network signal to optimize the visual recognition strategy.

[0019] The multi-dimensional radio frequency characteristics at least include a multipath time delay difference characteristic, a signal strength gradient characteristic, and a signal dynamic change rate characteristic, wherein the multipath time delay difference characteristic is used to represent the richness of the signal propagation path, the signal strength gradient characteristic is used to represent the spatial variation of the signal strength received by different positioning anchors, and the signal dynamic change rate characteristic is used to represent the frequency and amplitude of the change of the signal strength over time.

[0020] The process of optimizing the visual recognition strategy comprises:

[0021] Based on the multipath time delay difference characteristic, it is determined whether there is a personnel dense gathering sub-region in the rough regional position, and if so, the visual recognition device is scheduled to preferentially start multi-modal collaborative collection and fusion recognition in the region.

[0022] Based on the signal strength gradient characteristic, the relative distance distribution between different persons in the rough regional position is calculated to determine the focusing and field of view segmentation parameters of the visual recognition device during collection.

[0023] Based on the signal dynamic change rate characteristic, the frame rate of visual collection is dynamically adjusted, high frame rate collection is used for moving persons, and low frame rate collection is used for stationary persons.

[0024] Optionally, the attribute sub-density includes at least one of a function sub-density, a behavior state sub-density, and a space-time compliance sub-density.

[0025] The function sub-density is obtained by classifying and counting the post functions of the persons.

[0026] The behavior state sub-density is obtained by classifying and counting the behavior states of the persons identified through visual posture analysis or radio frequency signal characteristics.

[0027] The space-time compliance sub-density is obtained by classifying and counting the matching results of the scheduling information, access permission history, and real-time position information of the persons.

[0028] Optionally, the overall personnel density and the attribute sub-density calculated in real time are compared with a preset dynamic threshold rule library to determine whether there is an abnormal density situation, including:

[0029] The overall personnel density is compared with a maximum carrying density threshold value calculated based on regional three-dimensional terrain structure, channel traffic capacity and real-time event state, and when the overall personnel density exceeds the threshold value and the duration exceeds a preset length of time, it is determined that the regional gathering density is abnormal;

[0030] Based on the functional sub-density and the spatio-temporal compliance sub-density, through double compliance detection including post absence detection and unauthorized trajectory analysis, it is determined whether there is a functional compliance density anomaly;

[0031] The instantaneous change rate and spatial distribution entropy value of a specific functional sub-density are monitored, and when the instantaneous change rate generated by the concentration of specific functional personnel exceeds the dynamic risk threshold value in a short time and the spatial distribution entropy value suddenly changes from uniform distribution to highly concentrated distribution, it is determined that the functional gathering density is abnormal, and cross verification based on the behavior state sub-density in the region is triggered;

[0032] A specific behavior state sub-density is compared with a state alarm threshold value preset based on scene safety rules in real time, while the spatial propagation speed and personnel flow direction of the behavior state are monitored, and when the state alarm threshold value is exceeded and a diffusion trend towards a key area is presented, it is determined that the state gathering density is abnormal.

[0033] Optionally, the regional gathering density anomaly triggers evacuation guidance based on multi-dimensional attribute cooperation, and the generation process of the corresponding management operation instruction includes:

[0034] The movement state of personnel in the region is classified based on the identified behavior state sub-density, and personnel are functionally grouped based on the identified functional sub-density;

[0035] The optimal path load of personnel in the region to each safety exit is calculated, and combined with the abnormal stay area identified by the spatio-temporal compliance sub-density, a differentiated evacuation path planning is generated;

[0036] According to the differentiated evacuation path planning, evacuation instructions with priority differences and path guidance differences are sent to intelligent terminals held by different functional groups.

[0037] Optionally, the execution process of the double compliance detection includes:

[0038] The functional sub-density of each key area is compared with an expected functional density distribution map dynamically generated based on scheduling information and work flow dependency relationship, and the post absence detection result is determined by detecting whether the functional sub-density corresponding to the necessary function is lower than the minimum configuration threshold value and whether the duration exceeds the business process tolerance window;

[0039] The spatio-temporal compliance sub-density is matched with a predefined three-dimensional permission matrix, when it is detected that a real-time location information of a person exists an unauthorized target that does not conform to an authorized spatio-temporal range, a history track and a current activity mode of the unauthorized target are analyzed in a backtracking manner, an abnormal behavior sequence is constructed, and an unauthorized track analysis result is determined.

[0040] Optionally, the process of cross verification based on the behavior state sub-density in the region comprises:

[0041] When it is determined that the function aggregation density is abnormal, the behavior state sub-density in the same period and the same spatial range as the abnormal function aggregation is acquired, a time sequence change curve of the function sub-density is aligned with a same period change curve of the behavior state sub-density, and a correlation degree is calculated;

[0042] If the calculation result shows that a time point of occurrence of the function aggregation is highly correlated with a time point of outbreak of the abnormal behavior state, and a spatial range is highly overlapped, a confidence degree of the function aggregation density abnormality is enhanced, and it is determined as a high-probability emergency disposal type event, otherwise, the confidence degree of the function aggregation density abnormality is reduced.

[0043] Optionally, when the density abnormality situation is judged, the process further comprises:

[0044] A change trend of the attribute sub-density of the same attribute category in different regions is monitored and compared in real time;

[0045] When it is detected that a specific attribute sub-density of a first region significantly decreases in a time period, a same attribute sub-density of a second region adjacent to the first region significantly increases in a similar time period, and a change amount has a correlation, it is determined that a cross-region personnel transfer event occurs, and a root cause is inferred in combination with other sub-density situations of the first region and the second region.

[0046] Optionally, after the attribute category and the location information of the person in the region are determined by recognizing the dynamic coding label, the process further comprises:

[0047] A causal knowledge graph containing scene prior business rules is acquired;

[0048] The attribute category and the location information of the person in the region determined by recognizing the dynamic coding label, and the causal knowledge graph are input into a causal inference engine for logical consistency verification;

[0049] If the logical consistency verification finds a conflict, an identity correction process is triggered, and the identity correction process comprises:

[0050] A dynamic coding label of a related person is re-identified and reviewed based on multi-modal image fusion;

[0051] When the review is correct, the attribute category matching result conforming to the scene priori business logic is output by combining the historical behavior data and the scheduling information of the personnel with the causal knowledge graph to probabilistically correct the attribute categories in conflict.

[0052] A regional personnel intelligent management device, comprising a memory and a processor;

[0053] The memory is configured to store a program.

[0054] The processor is configured to execute the program to implement the steps of the regional personnel intelligent management method according to any one of the preceding embodiments.

[0055] A readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the regional personnel intelligent management method according to any one of the preceding embodiments.

[0056] A computer program product comprising a computer program, the computer program being executed by a processor to implement the steps of the regional personnel intelligent management method according to any one of the preceding embodiments.

[0057] A dynamic coding label for the regional personnel intelligent management method according to any one of the preceding embodiments, comprising:

[0058] A label substrate;

[0059] A visible light coding area provided on the label substrate, the visible light coding area comprising periodically dynamically updated digital and letter combinations;

[0060] A fluorescent material layer provided on or in the label substrate, the fluorescent material layer presenting a hidden coding pattern under excitation light of a specific wavelength;

[0061] A microcontroller for controlling the coding of the visible light coding area to be synchronously updated in association with the personnel attribute category information in the background database.

[0062] As can be seen from the above technical solutions, the regional personnel intelligent management method, related device and dynamic coding label provided by the embodiments of the present application are realized based on a dynamic coding label configured for regional personnel, a radio frequency positioning network and a multi-modal visual recognition device, a rough position is obtained by radio frequency positioning and a visual device is dispatched, personnel attributes and accurate positions are recognized in combination with the dynamic coding label, overall and attribute sub-density are calculated and compared with a dynamic threshold, an abnormal situation of the density is judged and a corresponding management operation is performed.

[0063] The present application achieves multiple beneficial effects in view of the defects of the prior art:

[0064] Firstly, the existing radio frequency technology positioning is coarse and the coding is not safe. The dynamic coding label contains a periodically updated visible light and a fluorescent hidden part, which avoids the risk of fixed coding forgery and coordinates with radio frequency and vision to schedule, so as to improve the position recognition from a rough area to precise positioning. Through the association of the label and the background database, the personnel attribute matching is realized quickly.

[0065] Secondly, the single visual recognition has poor environmental adaptability and weak attribute association. The multi-modal visual recognition device is based on the precise scheduling of radio frequency positioning, reduces invalid image acquisition, combines the feature recognition of dynamic coding label, greatly improves the recognition accuracy in complex environment, and directly obtains attribute information through the label without relying on complex image feature extraction, thereby improving the attribute recognition efficiency.

[0066] Thirdly, the existing technology has the problems of one-sided density statistics and rigid threshold. The application calculates the overall personnel density and the sub-density based on attribute classification, and cooperates with the dynamic threshold rule database containing different attribute combinations and space-time scenes, so that the density anomaly judgment is more in line with the actual management needs, and the false judgment and missed judgment of the fixed threshold in different scenes are avoided.

[0067] Fourthly, through real-time data collection, analysis and linkage with the preplan library, the rapid identification and automatic disposal of abnormal situation are realized, the management response speed is greatly improved, and reliable support is provided for regional safety guarantee and efficient operation. BRIEF DESCRIPTION OF DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0069] Figure 1 The flow chart of a regional personnel intelligent management method disclosed by the embodiments of the present application;

[0070] Figure 2 The architecture flow chart applied by a regional personnel intelligent management method disclosed by the embodiments of the present application;

[0071] Figure 3 The hardware structure block diagram of a regional personnel intelligent management device disclosed by the embodiments of the present application. DETAILED DESCRIPTION

[0072] With reference to the drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0073] Next, the technical solutions of the present application are introduced. The present application proposes the following technical solutions, which are specifically described below.

[0074] Figure 1 A flowchart of a regional personnel intelligent management method disclosed in an embodiment of the present application.

[0075] Figure 2 An architecture flowchart to which a regional personnel intelligent management method disclosed in an embodiment of the present application is applied.

[0076] The regional personnel intelligent management method is realized based on a dynamic coding label configured for each personnel in a region, a radio frequency positioning network deployed in the region, and a multi-modal visual recognition device.

[0077] The dynamic coding label specifically includes the following components:

[0078] A label base;

[0079] A visible light coding area arranged on the label base, the visible light coding area containing periodically dynamically updated digital and letter combinations;

[0080] A fluorescent material layer arranged on or in the label base, the fluorescent material layer presenting a hidden coding pattern under excitation light of a specific wavelength;

[0081] A microcontroller for controlling the coding of the visible light coding area to be synchronously updated according to the personnel attribute category information in the background database.

[0082] Specifically, the regional personnel intelligent management method disclosed in the present application relies on three key components, namely, a dynamic coding label uniformly configured for each personnel in a region, a radio frequency positioning network deployed in a global grid, and a multi-modal visual recognition device arranged in multiple dimensions. The three components interact with each other through data and instructions, and jointly support the whole-process management of personnel attribute recognition, location positioning, density monitoring, and abnormality disposal. The dynamic coding label serves as the core carrier of personnel identity and attribute information, and its structural design and functional implementation directly determine the accuracy and safety of the whole management method. The specific components and working logic are as follows.

[0083] The dynamic coding label carries a structure based on a label base, and the base is made of flexible materials resistant to wear and interference, which can adapt to the physical needs of different wearing scenarios and provide a stable installation and protection base for each functional area and component of the label. On the surface of the label base, a visible light coding area is integrated, which uses high-contrast numbers and letters as the basic coding form. The core feature is that the coding information has the ability to update periodically, and the automatic switching of the coding content can be completed according to the preset time period or background instructions. It can be quickly captured in a regular visual recognition scenario, and the dynamic change of the coding can also avoid the security risk that fixed coding is easily imitated. On the surface or inside of the label base, a fluorescent material layer is also embedded. The material layer has no obvious visual features in natural light environment, and only under the irradiation of excitation light of a specific wavelength, it will present a preset hidden coding pattern. The content of the hidden coding and the visible light coding area form a complementary check relationship, which can provide secondary information support for personnel identity verification in special scenarios such as visible light coding being blocked or tampered with.

[0084] In order to realize accurate control and synchronization of coding information, a microcontroller is also built into the dynamic coding label. The controller serves as the core control unit of the label. On the one hand, it maintains real-time data communication with the background database and can automatically receive personnel attribute category information update instructions issued by the background. On the other hand, it can drive the visible light coding area to update the coding content periodically, while ensuring that the update logic of the hidden coding pattern of the fluorescent material layer and the visible light coding area is consistent, realizing the accurate association and binding of the coding information and the personnel attribute category information in the background database. When the personnel enter the management area, the dynamic coding label can be recognized by the radio frequency positioning network for its signal range and captured by the multi-modal visual recognition device for its coding features, providing reliable information sources for subsequent location positioning and attribute recognition.

[0085] In actual management processes, the dynamic coding label will first be captured by the radio frequency positioning network to obtain the rough regional location information of the personnel. The background system will dispatch the multi-modal visual recognition device of the corresponding region to start the collection work based on the rough location. The visual recognition device will recognize the real-time coding of the visible light coding area and the hidden coding of the fluorescent material layer at the same time, match the recognized coding information with the background database, accurately associate the attribute category information of the personnel, and finally determine the accurate location of the personnel by combining image analysis and radio frequency signal calibration, laying a data foundation for subsequent density calculation and abnormal judgment.

[0086] As shown in Figure 1 and Figure 2 The regional personnel intelligent management method disclosed by the application relies on the cooperation of the dynamic coding label, the radio frequency positioning network and the multi-modal visual recognition device to realize accurate perception and intelligent management of regional personnel. The method can include:

[0087] Step S1, obtaining rough regional position information of the personnel by the radio frequency positioning network, and scheduling corresponding visual recognition equipment based on the rough regional position information, determining the attribute category and position information of the personnel in the region by recognizing the dynamic coding label, wherein the coding information of the dynamic coding label includes periodically dynamically updated visible light part and / or fluorescent hidden part, and is associated with the personnel attribute category information in the background database.

[0088] Specifically, the radio frequency positioning network periodically transmits a detection signal to the management region, and preliminarily locks the rough regional position of the personnel by receiving the radio frequency signal feedback from the dynamic coding label worn by the personnel and combining multi-anchor signal intersection analysis. While obtaining the rough position information, the system synchronously extracts multi-dimensional features of the radio frequency signal, including multi-path time delay difference features representing the richness of signal propagation path, signal strength gradient features reflecting the spatial variation of signal strength of different anchors, and signal dynamic change rate features embodying the time variation law of signal strength, so as to optimize the visual recognition strategy.

[0089] Specifically, the system will dispatch and deploy multi-modal visual recognition equipment in the corresponding region according to the rough regional position of the personnel to start image acquisition work; for the personnel dense sub-region determined by the multi-path time delay difference feature, multi-spectral characteristic visual equipment is preferentially dispatched for collaborative acquisition; based on the relative distance distribution of the personnel calculated by the signal strength gradient feature, the focusing parameters and field of view segmentation range of the visual equipment are set; according to the signal dynamic change rate feature, the acquisition frame rate is adjusted, high frame rate acquisition is used for moving personnel and low frame rate acquisition is used for stationary personnel. In the image acquisition stage, if the personnel occlusion or label overlap is detected, multi-modal image fusion processing will be started to analyze the occluded dynamic coding label; then the real-time digital letter combination of the visible light coding area is identified from the acquired image, and the fluorescent hidden coding pattern is awakened by the specific wavelength excitation light and identified, the two types of coding information are matched with the background database, and the attribute category of the personnel is associated, then combined with the image space positioning and radio frequency signal calibration, the precise position of the personnel is finally determined. In addition, the system also inputs the personnel attribute and position information into the causal knowledge graph loaded with scene prior business rules, and completes logical consistency verification by the causal inference engine. If information conflict is found, identity correction process is triggered, and matching results conforming to business logic are output through label re-identification and historical data review.

[0090] It can be considered that after the attribute category and position information of the personnel in the region are determined by recognizing the dynamic coding label, in order to further ensure the accuracy of the personnel identity and attribute information and conform to the scene business logic, the present application also adds a logical verification and identity correction process based on the causal knowledge graph, as follows:

[0091] ①obtain a causal knowledge graph containing scenario prior business rules;

[0092] ②input the attribute category and location information of the personnel in the region determined by recognizing the dynamic coding label and the causal knowledge graph into a causal inference engine for logical consistency verification;

[0093] ③if the logical consistency verification finds a conflict, trigger an identity correction process, the identity correction process comprising:

[0094] ④re-identify and review the dynamic coding label of the relevant personnel based on multi-modal image fusion;

[0095] ⑤when the review is correct, according to the historical behavior data and scheduling information of the personnel, in combination with the causal knowledge graph, probabilistically correct the attribute category in conflict until an attribute category matching result that conforms to the scenario prior business logic is output.

[0096] Specifically, first, a causal knowledge graph containing scenario prior business rules is obtained. The causal knowledge graph is constructed based on historical business data of regional management, preset job specifications, personnel access permission rules, and emergency response processes, etc. prior information, the nodes of which cover personnel attribute categories, job functions, authorized access areas, scheduling time periods, business process dependency relationships, etc. core elements, and the associated edges between nodes represent the causal logic of each element, for example, "a specific function personnel needs to be stationed in a designated area during the scheduling period", "visitors can only enter non-core areas during the authorized period", etc. Business rules are embedded in the knowledge graph in the form of causal association, providing a unified business judgment benchmark for subsequent logical verification.

[0097] Subsequently, the attribute category and location information of the personnel in the region determined by recognizing the dynamic coding label and the causal knowledge graph are input into a causal inference engine for logical consistency verification. The causal inference engine will first structure and disassemble the real-time attributes and location information of the personnel, then match them with the corresponding nodes in the knowledge graph, and verify whether the real-time information conforms to the scenario prior business rules by traversing the causal association edges between nodes. For example, if the knowledge graph limits "security personnel need to be stationed at the entrance area from 8am to 6pm on weekdays", and real-time recognition shows that the attribute category of a security personnel is security, but the real-time location is an unauthorized core office area and the time period is a working time period, then the engine will determine that the attribute and location information of the personnel is logically inconsistent; if the personnel attribute is visitor, but the real-time location is an unauthorized equipment room, then a logical conflict warning will also be triggered, otherwise the information is determined to be consistent with the business logic, and the subsequent correction process is not needed.

[0098] If a conflict is detected during logical consistency verification, the identity correction process is automatically triggered. Based on multimodal image fusion, the dynamic coded tags of relevant personnel are re-identified and verified. The system prioritizes visual recognition devices with multispectral acquisition capabilities to perform secondary image acquisition on the areas where conflicting personnel are located. Addressing potential issues such as tag occlusion and angular deviations, the system enhances the feature extraction effect of dynamic coded tags through the fusion processing of visible light, infrared, and fluorescence multimodal images. Subsequently, the visible light coded area and the fluorescence hidden coded area of ​​the tag are re-identified. After obtaining the coded information, it is again accurately matched with the backend database to confirm whether there are any recognition deviations in the personnel identity and attribute information corresponding to the tag code. If the verification finds that the tag recognition is incorrect, the personnel attribute information is directly corrected, and the verification loop is completed.

[0099] If the verification is correct, meaning there is no deviation between the tag code and the personnel attribute, the system will use the personnel's historical behavior data and shift information, combined with the causal knowledge graph, to probabilistically correct conflicting attribute categories until an attribute category matching result that conforms to the scenario's prior business logic is output. The system will retrieve the personnel's past job performance trajectory, shift attendance records, frequency of permission usage, and other historical behavior data over a period of time. Combining this with the business rules in the causal knowledge graph, a probabilistic correction model will be constructed. For example, if the personnel's historical data shows that they have a high frequency of behavior such as "temporarily dispatched to support the core area," and there is a corresponding dispatch approval record in the current time period, then the system will determine that their current attribute category is "temporary support position" rather than the originally identified regular position with a high probability, thereby correcting the attribute category. If the historical data shows that they have no record of unauthorized access to areas and no temporary dispatch instructions, the system will combine the knowledge graph rules to check whether the permission information has not been updated synchronously, and complete the adaptation and correction of permissions and attributes. After multiple rounds of probabilistic iteration and logical verification, the final attribute category matching result that conforms to the scenario's prior business logic will be output, ensuring the accuracy of personnel information and the consistency of business logic.

[0100] Step S2: Based on the identified attribute categories and location information of the personnel, calculate the overall personnel density of the target area in real time, and simultaneously calculate at least one attribute sub-density based on the personnel attribute classification. The attribute sub-density is the density obtained by statistically analyzing the personnel with the same attribute category in the target area.

[0101] Specifically, the system will take the preset target area geographical boundary as the statistical range, aggregate the position information of all personnel in the area, and combine the area space area to complete the real-time calculation of the overall personnel density, so as to reflect the overall aggregation degree of personnel in the area. For the calculation of attribute sub-density, the system will carry out targeted statistics according to the preset attribute classification dimension, mainly covering three types of core sub-density: first, the function sub-density, which is classified according to the post function label of the personnel, and the distribution density of the same function group in the target area is calculated; second, the behavior state sub-density, which combines visual posture analysis and radio frequency signal dynamic characteristics to identify the behavior state of personnel and complete classification, and calculates the density of a specific behavior state group; and third, the time and space compliance sub-density, which matches the real-time position of personnel with the preset scheduling information and access permission range, and calculates the distribution density of compliant and non-compliant personnel. The three types of sub-density can be calculated alone or in combination to provide multi-dimensional data support for subsequent anomaly judgment.

[0102] Step S3, compare the overall personnel density and the attribute sub-density calculated in real time with the preset dynamic threshold rule library to determine whether there is a density abnormal situation, the dynamic threshold rule library includes attribute sub-density thresholds set based on different attribute category combinations and / or different time and space scenes.

[0103] Specifically, the dynamic threshold rule library pre-stores density determination standards adapted to different scenes, which will complete data comparison and anomaly recognition by dimension. For the overall personnel density, it is compared with the maximum carrying threshold generated by combining the regional terrain structure, channel traffic capacity and real-time event state. If the overall density exceeds the threshold and the duration reaches the preset window, it is determined that the regional aggregation density is abnormal. For the function sub-density and the time and space compliance sub-density, through the dual compliance detection of post absence detection and unauthorized trajectory analysis, the actual function density is matched with the expected function density distribution diagram, and the consistency of personnel position and authorized time and space range is verified, so as to determine whether there is a function compliance density anomaly. For the specific function sub-density, the instantaneous change rate and spatial distribution entropy value are monitored. If the instantaneous change rate suddenly increases and the distribution state changes from uniform to high aggregation, the cross verification of the behavior state sub-density is triggered to confirm whether it is a function aggregation density anomaly; for the behavior state sub-density, it is compared with the scene safety alarm threshold, and the state propagation speed and personnel flow direction are monitored. If it exceeds the threshold and spreads to the key area, it is determined that the state aggregation density is abnormal. In addition, the system will also monitor the linkage change of cross-regional attribute sub-density. If the same attribute sub-density of adjacent areas presents reverse correlation fluctuation, it is determined that there is a cross-regional personnel transfer event and the root cause is inferred.

[0104] In addition, considering that the flow of personnel within the management area often presents a cross-regional linkage feature, density monitoring in a single area tends to overlook the potential risk of local dispersal triggering aggregation in another area, and relying solely on single-area density data to determine abnormalities may lead to delayed warnings or misjudgments, therefore, when judging the abnormal situation of density, a cross-regional personnel transfer monitoring link should be added, and a more comprehensive situation awareness should be achieved through multi-regional data linkage analysis, which specifically includes:

[0105] ① Real-time monitoring and comparison of the change trend of the same attribute sub-density between different regions;

[0106] ② When the sub-density of a specific attribute in the first region is detected to decrease significantly within a certain period, the sub-density of the same attribute in the second region adjacent to the first region increases significantly within a similar period, and the change amount is correlated, it is determined that a cross-regional personnel transfer event occurs, and the root cause is inferred in combination with the other sub-density situations of the first region and the second region.

[0107] Specifically, all attribute sub-density data of each sub-region within the management range is synchronously collected in units of preset time slices, and for each type of attribute (such as "security personnel", "visitor", "technical staff", etc.), the attribute sub-density time series change curve of each sub-region is drawn respectively. To ensure the effectiveness of the comparison, the system will standardize the curve to eliminate the density value deviation caused by the area difference of different regions, and focus on the change amplitude and the change rate as two core indicators. The former is measured by the density difference ratio of the current period to the previous period, and the latter is represented by the number of density changes per unit time, and the flow correlation characteristics of the same attribute in different regions are presented intuitively through curve superposition comparison. At the same time, the system will preferentially mark the regions whose attribute sub-density fluctuation amplitude exceeds the preset reference value, and include them in the key monitoring range, which will reduce the data dimension for subsequent correlation analysis.

[0108] The determination of significant decrease or significant increase needs to meet two conditions: first, the density change amplitude exceeds the cross-regional flow trigger threshold value in the dynamic threshold value rule library (this threshold value will be dynamically adjusted in combination with the functional attributes of the region, such as the trigger threshold value of the office area and the rest area being higher than that of two independent office areas), and second, the change duration reaches at least two consecutive time slices, excluding transient fluctuation interference. The correlation of the change amount is achieved by calculating the matching degree of the density decrease amount of the first region and the density increase amount of the second region. If the difference between the two is within the preset error range, and there is a time sequence correlation that "the decrease in the first region precedes the increase in the second region by 0-1 time slice", it can be determined that the attribute personnel transfer from the first region to the second region.

[0109] After determining the transfer event, root cause inference is carried out in combination with multidimensional sub-density data and scene information of the two areas: if the employee sub-density in the first area decreases during the off-work period, the employee sub-density in the second area increases in the canteen, and there is no fluctuation of the abnormal behavior state sub-density in the two areas, it is inferred that it is a regular meal flow; if the technical post sub-density in the first area of the equipment room suddenly decreases, the technical post sub-density in the adjacent second area of the emergency assembly point suddenly increases, and the "emergency behavior state" sub-density increases in the two areas, in combination with the "equipment failure emergency response rule" in the causal knowledge graph, it is inferred that it is a technical personnel emergency transfer caused by equipment failure. Through this linkage analysis, the system can distinguish between the regularity and emergency of the transfer event, provide accurate basis for whether to start abnormal disposal, avoid over-response to regular flow, and at the same time ensure that the emergency transfer is paid attention to in time.

[0110] Step S4, if it is judged that there is a density abnormal situation, corresponding management operation instructions are generated and executed according to the abnormal type and the preset management plan library.

[0111] Specifically, the management plan library pre-stores disposal strategies corresponding to various density abnormalities, and the system generates differentiated management operation instructions according to the type, level and influence range of the abnormality. For regional aggregation density abnormalities, the system will complete grouping based on personnel behavior state and function classification, formulate differentiated evacuation path planning in combination with the load of each safety exit path and the distribution of abnormal stay areas, and send evacuation guidance instructions with priority to the intelligent terminals of different functional groups. For function compliance density abnormalities, if it is a post vacancy, a post filling warning is pushed to the management terminal, and the information of the deployable personnel in the surrounding area is synchronously called; if it is an unauthorized trajectory, the trajectory monitoring of the unauthorized target is triggered, and an abnormal positioning and disposal prompt is sent to the security terminal. For function aggregation or behavior state aggregation density abnormalities, if it is confirmed as a high-probability emergency event through cross verification, the system will start the emergency broadcasting equipment to issue prompt information, and at the same time, schedule multi-modal visual equipment to intensify real-time monitoring of the target area; for cross-regional personnel transfer events, the system will send a flow warning to the management terminal of the target area of the transfer, and start the dynamic adjustment of the regional carrying capacity in advance. After all the instructions are issued, the system will continuously track the execution state, dynamically adjust the instruction content in combination with the real-time changes of the personnel position and attributes to ensure the disposal effect.

[0112] As can be seen from the above technical solutions, the regional personnel intelligent management method, related equipment and dynamic coding tag provided by the embodiments of the present application are realized based on the dynamic coding tag configured for the regional personnel, the radio frequency positioning network and the multi-modal visual recognition equipment, the rough position is obtained through radio frequency positioning and the visual equipment is dispatched, the personnel attributes and accurate position are recognized in combination with the dynamic coding tag, the overall and attribute sub-density are calculated, and then compared with the dynamic threshold to judge the density abnormal situation and execute the corresponding management operation.

[0113] The present application realizes multiple beneficial effects in view of the defects of the prior art:

[0114] Firstly, the problem of coarse positioning and unsafe coding in the existing radio frequency technology is solved. The dynamic coding tag contains a periodically updated visible light and a fluorescent hidden part, which avoids the risk of forgery of fixed coding, and cooperates with the coordinated scheduling of radio frequency and vision to improve the position recognition from a rough area to accurate positioning. At the same time, through the association of the tag and the background database, the rapid matching of personnel attributes is realized.

[0115] Secondly, the defects of poor environmental adaptability and weak attribute association of single visual recognition are made up. The multi-modal visual recognition device is based on the accurate scheduling of radio frequency positioning, reduces invalid image collection, and combines the feature recognition of dynamic coding tags to greatly improve the recognition accuracy in complex environments. Moreover, attribute information is directly obtained through the tag without relying on complex image feature extraction, which improves the attribute recognition efficiency.

[0116] Thirdly, the problem of one-sided density statistics and rigid threshold in the prior art is overcome. The present application calculates the overall personnel density and the sub-density based on attribute classification, and cooperates with the dynamic threshold rule library containing different attribute combinations and space-time scenes to make the density anomaly judgment more in line with the actual management needs, avoiding the misjudgment and omission of fixed threshold in different scenes.

[0117] Fourthly, through real-time data collection, analysis and linkage with the preplan library, the rapid identification and automatic disposal of abnormal situation are realized, which greatly improves the management response speed and provides reliable support for regional security and efficient operation.

[0118] In some embodiments of the present application, the process of step S1, acquiring the rough area position information of the personnel by using the radio frequency positioning network, and scheduling the corresponding visual recognition device based on the rough area position information, and determining the attribute category and position information of the personnel in the area by recognizing the dynamic coding tag, can specifically include:

[0119] ① Obtain the rough regional position information of each person in the region through the periodic probe signal of the radio frequency positioning network. The radio frequency positioning network adopts a global grid deployment mode, and a plurality of radio frequency positioning anchors are arranged at a predetermined interval in the management region. Each anchor synchronously and periodically emits a probe signal of a specific frequency. The detection period can be dynamically adjusted according to the intensity of the regional personnel flow. When the dynamic coding tag worn by the personnel enters the signal coverage range, it will passively reflect the probe signal. After each anchor receives the reflected signal, it extracts the key parameters such as signal arrival time difference and received signal strength indication, and calculates the spatial coordinate range of the tag through a multi-anchor signal intersection algorithm. Considering that the radio frequency signal is easily affected by obstacles such as walls and metal equipment, the system will compensate for the calculation results. Finally, the rough regional position information represented by the combination of positioning anchors plus the regional grid number is output, such as "anchor A3-A4-grid B2", which ensures that the position information can cover the range where the personnel are located, and provides a clear direction for subsequent visual device scheduling.

[0120] ② According to the rough regional position information, the visual recognition device deployed on the corresponding region is dispatched to collect images of the target region. The system has an associated mapping table of regions and devices, which records the installation position, monitoring coverage range and working state of each visual recognition device. When the rough regional position information of the personnel is obtained, the background scheduling module quickly matches the visual device in the corresponding coverage range, and issues a collection instruction containing parameters such as collection frame rate, focusing range and image resolution to it. For example, if the rough position of the personnel is "grid B2", three panoramic visual cameras installed on the ceiling of the B2 region will be immediately dispatched to start working, and the focusing range will be locked on the ground area of the grid, while the visual devices in the temporarily involved areas will be turned off to reduce system energy consumption. If the main visual device of the corresponding region is in a fault state, the system will automatically switch to the standby device, and push a device fault alarm to the management terminal to ensure uninterrupted collection work.

[0121] ③In the image acquisition process, the image is analyzed to detect whether there is inter-personal occlusion or overlapping area of dynamic coding label. After the visual recognition device collects the image, it is transmitted to the image preprocessing module in real time. The target detection algorithm is used to extract the contour and locate the personnel target in the image, and the approximate area of the head, torso and dynamic coding label of each personnel is marked. Then the system calculates the overlapping area ratio of each personnel target, for example, if the contour area of a personnel overlaps with another personnel more than 30% of its own area, it is determined that there is inter-personal occlusion. At the same time, for the label area, the feature point matching technology is used to identify the rectangular boundary of the label, for example, if the intersection area of the boundaries of two labels exceeds 20% of the area of a single label, it is determined that the labels overlap. In order to improve the detection accuracy, the system combines the change trend of continuous multiple images to exclude false occlusion determination caused by temporary overlap of personnel, and only when the occlusion or overlap state remains for more than a tolerable frame, it is confirmed that there is a problem area that needs to be processed.

[0122] ④If so, dispatch at least two visual recognition devices with different spectral characteristics to cooperatively collect images and perform multi-modal image fusion processing on the target area to resolve the occluded dynamic coding label. The system presets a multi-spectral device combination scheme, and common combinations are visible light camera and near-infrared camera, visible light camera and ultraviolet excitation camera. The near-infrared camera can penetrate some clothing materials, and the ultraviolet excitation camera can awaken the fluorescent hidden part of the dynamic coding label. When the problem area is detected, the dispatch module will immediately issue a cooperative collection instruction to the standby multi-spectral device in the corresponding area to ensure that each device starts collection at the same timestamp to avoid image misalignment caused by time difference. After collection is complete, the multi-modal image fusion module will use a pixel-level fusion algorithm to fuse the feature information of different spectral images. For example, the personnel contour features in the visible light image and the label contour features in the near-infrared image are superimposed, and the fluorescent coding features in the ultraviolet image and the visible light coding features in the visible light image are complementary. Through feature enhancement, the visual interference of the occluded area is eliminated, and the coding area of the occluded label is completely restored.

[0123] V. From the collected images and the fused images, the current encoding information of each dynamic coding label worn by the personnel is located and identified. The system first accurately extracts the independent area of each dynamic coding label from the fused image through image segmentation technology, and eliminates interference elements such as personnel clothing, background environment, etc. For the visible light coding area of the label, an optical character recognition algorithm is used to identify the combination of numbers and letters therein, and combined with the periodic updating rule of the coding, the false recognition results caused by image blur are filtered out; for the fluorescent hidden coding area, the contour features of the fluorescent pattern are extracted through image threshold segmentation technology, and template matching is performed with the preset coding pattern library to determine the hidden coding content. In order to ensure the accuracy of identification, the system will cross-verify the identification results of the two kinds of coding, if the coding sequences associated with each other are consistent, the final coding information is output; if there is a difference, a secondary acquisition and identification process is started until consistent results are obtained.

[0124] VI. The identified current encoding information is matched with the background database to obtain the attribute category of the corresponding personnel, and the position information of the personnel is determined in combination with the image and the radio frequency signal analysis. The one-to-one correspondence relationship between the dynamic coding label and the personnel attribute category data is pre-stored in the background database. The system takes the identified coding information as the retrieval keyword to quickly match the corresponding record in the database, and generates a data package containing the complete attribute category of the personnel. In terms of position information determination, a fusion calibration strategy is adopted, in which visual positioning is the main method and radio frequency positioning is the auxiliary method: the accurate coordinates of the personnel are obtained by converting the pixel distance between the label and the preset reference point (such as ground marking line, equipment base) in the visual image; at the same time, the rough position information output by the radio frequency positioning network is combined to eliminate the errors of the two positioning methods through Kalman filtering algorithm, and finally the high-precision position coordinates of the personnel are output. The accurate position information and attribute category information will be stored in the real-time database at the same time, providing data support for the density calculation of step S2, the monitoring of the attribute sub-density change trend in the subsequent cross-regional transfer judgment, etc. For example, the data source of the specific attribute sub-density required for the subsequent cross-regional transfer judgment comes from the personnel attribute and position information associated in this step.

[0125] It is worth noting that the accurate attribute and position data obtained in step S1 are the basis for significant decrease or significant increase analysis and root cause inference in the subsequent cross-regional personnel transfer judgment. For example, when a sudden drop in the "technical post sub-density in the equipment room" is monitored, data statistics need to be completed relying on the "technical post" attribute category and "equipment room" position information identified in this step; when "equipment failure emergency response" is inferred, the personnel attribute associated in this step also needs to be matched with the business rules of "technical post corresponding to equipment failure disposal" in the causal knowledge graph to ensure the data flow closed loop of the entire management process.

[0126] On this basis, before scheduling the visual recognition device, further comprising extracting and analyzing the multi-dimensional radio frequency characteristics of the radio frequency positioning network signal to optimize the visual recognition strategy;

[0127] The multi-dimensional radio frequency characteristics at least include a multipath time delay difference characteristic, a signal strength gradient characteristic, and a signal dynamic change rate characteristic, wherein the multipath time delay difference characteristic is used to represent the richness of the signal propagation path, the signal strength gradient characteristic is used to represent the spatial variation of the signal strength received by different positioning anchors, and the signal dynamic change rate characteristic is used to represent the frequency and amplitude of the change of the signal strength over time;

[0128] The process of optimizing the visual recognition strategy includes:

[0129] ① Based on the multipath time delay difference characteristic, it is judged whether there is a personnel dense gathering sub-region in the rough area position, and if there is, the visual recognition device is scheduled to preferentially start multi-modal collaborative collection and fusion recognition in the region;

[0130] ② Based on the signal strength gradient characteristic, the relative distance distribution between different personnel in the rough area position is calculated to determine the focusing and field of view segmentation parameters when the visual recognition device collects;

[0131] ③ Based on the signal dynamic change rate characteristic, the frame rate of visual collection is dynamically adjusted, and high frame rate collection is used for moving personnel and low frame rate collection is used for stationary personnel.

[0132] Specifically, the multipath time delay difference characteristic is reflected by the time difference of the same dynamic coding label signal received by different positioning anchors, and the richness of the signal propagation path is directly related to the number of personnel and the distribution of obstacles in the region. When this characteristic presents significant fluctuations, it indicates that the signal reaches the anchor through multiple reflection paths during propagation, which indirectly reflects the dense distribution of personnel in the region, and it is easy to have shielding or label overlapping problems. The present application interprets the multipath time delay difference characteristic through a pre-set characteristic analysis model, and if it is determined that there is a personnel dense gathering sub-region in the rough area, the system will adjust the device scheduling order and preferentially call the visual recognition device with multi-spectral collection capability in the region and its surrounding area. These devices will be started synchronously according to the collaborative collection protocol, and will capture the target area image from different spectral dimensions such as visible light and specific wavelength excitation light, and then through multi-modal image fusion technology, the characteristic information of each spectral image will be complementary superimposed, effectively penetrating the shielding area between personnel, and completely analyzing the covered dynamic coding label, avoiding the recognition blind area caused by single spectral collection.

[0133] The signal strength gradient feature can intuitively reflect the spatial variation rule of the signal strength received by different positioning anchors. When the personnel distribution in the region is dense, the signal strength difference between adjacent anchors is small, and the gradient value is low. When the personnel distribution is sparse, the signal strength changes more obviously with the spatial position, and the gradient value is high. The application utilizes the correlation between the feature and the relative distance of the personnel, and calculates the relative position distribution of each personnel in the rough region through a feature mapping model, that is, to determine which regions have close personnel spacing and which regions have relatively sparse personnel. For the personnel-intensive sub-region, the system configures the collection parameters of small field of view and high focusing accuracy for the visual recognition device to ensure that the label image is clear and identifiable. For the personnel sparse region, large field of view and dynamic focusing parameters are used to expand the coverage range of a single device. At the same time, according to the relative distance distribution, the target region is divided into multiple independent collection sub-views, and each sub-view is allocated exclusive image processing resources to improve the efficiency of label positioning and recognition.

[0134] The signal dynamic change rate feature is quantified by the change frequency and amplitude of the radio frequency signal strength in the continuous period, which is directly related to the movement state of the personnel. When the personnel are in a moving state, the relative position of the dynamic coding label and the positioning anchor changes continuously, the signal strength fluctuates frequently and with a large amplitude, and the feature value is high. When the personnel are stationary, the signal strength tends to be stable, and the feature value is low. The application monitors the change trend of the feature in real time, and establishes a linkage adjustment mechanism of the collection frame rate and the feature value: when the signal dynamic change rate feature value is high, it is determined that the personnel are in a moving state, and the collection frame rate of the corresponding visual device is immediately increased to ensure the complete capture of the coding information of the label in the moving process, and to avoid coding ambiguity or missing caused by insufficient frame rate; when the feature value is low, it is determined that the personnel are in a stationary state, and the collection frame rate is reduced to maintain only periodic image collection to confirm the label state. This dynamic adjustment method not only ensures the integrity of the label recognition of the moving personnel, but also avoids the invalid high-frequency collection of the stationary personnel, significantly reducing the computing power consumption and data transmission pressure of the visual device.

[0135] In some embodiments of the application, as shown in Figure 2 The attribute sub-density includes at least one of a function sub-density, a behavior state sub-density, and a space-time compliance sub-density;

[0136] The functional sub-density is obtained by classifying and counting based on the post functions of the personnel. The personnel attribute information identified and associated through dynamic coding labels contains explicit post function labels such as “security”, “technical operation and maintenance”, “visitor”, “management” and the like, which are synchronized with the personnel archives in the background database in real time. When counting, the system extracts the function labels of all personnel in the target area and groups them based on the geographical boundary of the target area, and then calculates the distribution density of personnel with different functions by combining the number of personnel in each group with the spatial parameters of the area. For example, in the production workshop area, the statistical result of the “operator” functional sub-density directly reflects the personnel allocation of the core post in the area, providing basic data for subsequent functional compliance judgment.

[0137] The behavior state sub-density is obtained by classifying and counting based on the behavior state of the personnel identified through visual posture analysis or radio frequency signal feature recognition. Behavior state recognition relies on optimized visual recognition strategy and radio frequency feature analysis: the visual device analyzes the body posture and movement trajectory of the personnel through image analysis to distinguish between “stillness”, “slow movement”, “gathering” and “emergency running” and the like; the dynamic change rate feature of the radio frequency signal is used for auxiliary verification. Frequent fluctuations in the signal correspond to the moving state, and stable signal corresponds to the still state. When counting, the system groups the personnel in the target area according to the behavior state and calculates the distribution density of each type of state. This sub-density can directly reflect the activity characteristics of the personnel in the area, such as a sudden increase in the emergency running sub-density indicating potential risks.

[0138] The space-time compliance sub-density is obtained by classifying and counting based on the matching results of the scheduling information, access permission history and real-time location information of the personnel. The background database pre-stores the scheduling time period and authorized access area information of each personnel, and the real-time location information obtained through the cooperation of vision and radio frequency provides the core basis for compliance verification. The system matches the real-time location of the personnel with the authorized space-time range, and the result is classified into “space-time compliance”, “time period violation”, “area overreach” and “double violation” and the like. The number of personnel in the target area is counted and the density is calculated according to the classification. For example, in the core machine room area, if the area overreach sub-density is greater than zero, it means that there is an unauthorized personnel entering, which provides a direct clue for abnormal judgment.

[0139] The process of comparing the overall personnel density and the attribute sub-density calculated in real time in step S3 with the preset dynamic threshold rule library to determine whether there is a density abnormal situation is introduced. The density abnormal situation can include but is not limited to the following four kinds:

[0140] The first kind is the regional gathering density anomaly.

[0141] The overall personnel density is compared with a maximum carrying density threshold value calculated based on regional three-dimensional terrain structure, channel traffic capacity and real-time event state, and when the overall personnel density exceeds the threshold value and the duration exceeds a preset length of time, it is determined that the regional gathering density is abnormal.

[0142] The regional gathering density anomaly triggers evacuation guidance based on multi-dimensional attribute coordination, and the generation process of the corresponding management operation instruction further includes:

[0143] ①Classify the movement state of personnel in the region based on the identified behavior state sub-density, and group personnel by function based on the identified function sub-density;

[0144] ②Generate a differentiated evacuation path plan by calculating the optimal path load of personnel in the region to each safety exit, combined with the abnormal stay area identified by the space-time compliance sub-density;

[0145] ③According to the differentiated evacuation path plan, send evacuation instructions with priority differences and path guidance differences to intelligent terminals held by different functional groups.

[0146] Specifically, the core criterion of regional gathering density anomaly is the imbalance between the actual personnel carrying capacity and the maximum safe carrying capacity, and its judgment process needs to consider the regional physical characteristics and real-time scene dynamics. Specifically, the system first compares the overall personnel density calculated in real time with the maximum carrying density threshold value generated based on the regional three-dimensional terrain structure, channel traffic capacity and real-time event state, where the three-dimensional terrain structure determines the upper limit of the physical space that can accommodate personnel, the channel traffic capacity limits the efficiency boundary of personnel evacuation, and the real-time event state such as exhibition, meeting, shift change dynamically adjusts the carrying threshold to adapt to the temporary personnel flow demand. When the overall personnel density exceeds the dynamic threshold value, and the duration of this threshold value exceeds the preset length of time, the system determines that the regional gathering density is abnormal, which can effectively exclude false abnormal alarms caused by instantaneous personnel traffic, and ensure the reliability of the judgment.

[0147] The evacuation guidance mechanism triggered by the abnormal regional gathering density is not the traditional unified instruction issuance, but the collaborative decision based on the multi-dimensional attribute sub-density. The corresponding management operation instruction generation process embodies the characteristics of refinement and differentiation: first, relying on the behavior state sub-density, the personnel in the region are divided into categories such as "static stay", "slow movement", "fast movement", etc. Meanwhile, combining the function sub-density, the personnel are divided into function groups such as "emergency guide personnel", "ordinary personnel", "special groups such as the old, the sick and the disabled", "regional management personnel", etc. to realize subsequent differentiated guidance. Through the path planning algorithm, the optimal path load of each personnel in the region to each safety exit is calculated to avoid congestion at a single exit. At the same time, in combination with the abnormal stay area identified by the space-time compliance sub-density, such as the personnel gathering area that violates the rules and blocks the passage, the path planning actively avoids such obstacles, and finally generates differentiated evacuation paths for different groups. According to the path planning results, individualized evacuation instructions are sent to the intelligent terminals (such as mobile phones, work bracelets, intercoms, etc.) held by personnel in different function groups, such as priority instructions for emergency guide personnel to guide at specified locations, optimal paths and real-time congestion prompts for ordinary personnel, and exclusive instructions for special groups to provide personal assistance and barrier-free passages. Through the dual differences of priority and path, efficient and orderly evacuation is realized.

[0148] The second, function compliance density anomaly:

[0149] Based on the function sub-density and the space-time compliance sub-density, through the dual compliance detection including post absence detection and unauthorized trajectory analysis, it is determined whether there is a function compliance density anomaly.

[0150] The execution process of the dual compliance detection further comprises:

[0151] Post absence detection: comparing the function sub-density of each key area with the expected function density distribution map dynamically generated based on scheduling information and work flow dependency relationship, determining the post absence detection result by detecting whether the function sub-density corresponding to the necessary function is lower than the minimum configuration threshold and whether the duration exceeds the business process tolerance window;

[0152] Unauthorized trajectory analysis: matching the space-time compliance sub-density with a pre-defined three-dimensional permission matrix, when detecting an unauthorized target whose real-time location information does not match the authorized space-time range, backtracking the history trajectory and current activity pattern of the unauthorized target to construct an abnormal behavior sequence to determine the unauthorized trajectory analysis result.

[0153] Specifically, the function compliance density anomaly is used to evaluate the matching degree of regional function demand and personnel configuration and the adaptability of personnel authority and time and space range. Through the dual compliance detection of function sub-density and time and space compliance sub-density, accurate judgment is realized to ensure the function integrity and authority security of regional operation. The dual compliance detection is not independent, but is complementary through data association. The specific execution process is as follows:

[0154] The post loss detection takes the function configuration to meet the business demand as the target, and realizes it by relying on the comparison of function sub-density and dynamically generated expected function density distribution diagram. The expected function density distribution diagram is not a fixed template, but is dynamically generated by the system based on personnel scheduling information and the dependency relationship of each post work process. For example, the production line needs operators, quality inspectors, and material coordination. The necessary functions and corresponding personnel configuration density of each key area at different time periods are clear. The system compares the actual function sub-density of each key area with the expected distribution diagram, and focuses on detecting whether the sub-density corresponding to the necessary function is lower than the minimum configuration threshold, such as nurses in the operating room and operation and maintenance personnel in the substation. Whether the duration of this insufficient state exceeds the tolerance window of the business process. If the sub-density of a key function is chronically insufficient and affects business development, the post loss detection result is abnormal.

[0155] The over-authorization trajectory analysis takes the personnel activity conforming to the authorized range as the target, and completes it by matching the time and space compliance sub-density with the pre-defined three-dimensional authority matrix. The three-dimensional authority matrix integrates the authorization information of personnel, time, and region, and clearly defines the region range that a certain type of personnel can enter at a specific time period. The system compares the personnel position corresponding to the time and space compliance sub-density with the authority matching result with the matrix. When it detects that there is an over-authorization target that does not match the authorized time and space range, it is not directly determined as abnormal, but it is analyzed back to analyze the history trajectory of the over-authorization target (such as whether there have been multiple over-authorization attempts recently, whether the over-authorization path deliberately avoids monitoring) and the current activity mode (such as the residence time in the over-authorization area, whether sensitive equipment is touched). A complete sequence of abnormal behavior is constructed. If the sequence shows that the over-authorization behavior is initiative and purposeful, the over-authorization trajectory analysis result is abnormal, combined with the post loss detection result, to finally determine whether it constitutes a function compliance density anomaly. For example, the function sub-density of a quality inspector in a production workshop is insufficient (post loss), or there is an unauthorized visitor in the quality inspection area (over-authorization trajectory), which is comprehensively determined as a function compliance density anomaly.

[0156] The third, function aggregation density anomaly:

[0157] The instantaneous change rate and the spatial distribution entropy value of the specific function sub-density are monitored, when the instantaneous change rate of the specific function personnel concentration is detected to exceed the dynamic risk threshold in a short time, and the spatial distribution entropy value is mutated from uniform distribution to high concentration distribution, it is determined that the function concentration density is abnormal, and the cross verification based on the behavior state sub-density in the region is triggered.

[0158] The cross verification based on the behavior state sub-density in the region further includes:

[0159] ① When it is determined that the function concentration density is abnormal, the behavior state sub-density in the same period and the same spatial range as the abnormal function concentration is obtained, and the time series change curve of the function sub-density is aligned with the same period change curve of the behavior state sub-density and the correlation degree is calculated.

[0160] ② If the calculation result shows that the occurrence time point of the function concentration and the outbreak time point of the abnormal behavior state are highly correlated, and the spatial range is highly overlapped, the confidence of the function concentration density abnormality is enhanced, and it is determined as a high-probability emergency disposal event, otherwise the confidence of the function concentration density abnormality is reduced.

[0161] Specifically, the function concentration density abnormality is aimed at the potential risk of unplanned concentration of specific function personnel, and the judgment logic considers both the number change and the spatial distribution dimensions, and introduces the behavior state sub-density for cross verification to exclude the interference of regular work concentration. Specifically, the system monitors the instantaneous change rate and the spatial distribution entropy value of the specific function sub-density in real time, that is, the instantaneous change rate reflects the number fluctuation of the function personnel in a short time, and the spatial distribution entropy value represents the dispersion and concentration degree of the personnel in the region. When the instantaneous change rate of the specific function personnel is detected to exceed the dynamic risk threshold in a short time, and the spatial distribution entropy value is mutated from uniform distribution (personnel is dispersed in each working area) to high concentration distribution (personnel is concentrated in a certain area), the system preliminarily determines that the function concentration density is abnormal, and then triggers the cross verification process.

[0162] Cross-validation based on behavior state sub-density is the key to improve the accuracy of abnormal judgment, that is, to exclude false judgments through the analysis of the relevance of function aggregation and behavior abnormality. The specific process is as follows: when the function aggregation density is preliminarily determined to be abnormal, the system immediately extracts the behavior state sub-density data in the same time period and the same spatial range as the abnormal aggregation, aligns the time series change curve of the function sub-density with the same period change curve of the behavior state sub-density, and calculates the correlation degree of the two. If the correlation degree analysis shows that the occurrence time point of the function aggregation and the outbreak time point of the abnormal behavior state (such as "fast running", "emotional agitation", "encircling equipment", etc.) are highly consistent, and the spatial coverage range of the two is completely consistent, it is indicated that the function aggregation is not a regular work cooperation, but is caused by an emergency event. At this time, the system enhances the confidence of the function aggregation density abnormality, determines it as a high-probability emergency disposal event, and immediately triggers the corresponding plan; otherwise, if the function aggregation is associated with "quiet conversation", "cooperative work" and other regular behavior states, the abnormal confidence is reduced, and it is determined as a regular work aggregation, and the emergency disposal does not need to be started.

[0163] The fourth, state aggregation density abnormality:

[0164] The specific behavior state sub-density is compared with the state alarm threshold preset based on the scene safety rules in real time, and the spatial propagation speed and personnel flow direction of the behavior state are monitored. When the state alarm threshold is exceeded and the diffusion trend to the key area is shown, it is determined as a state aggregation density abnormality.

[0165] Specifically, the state aggregation density abnormality takes the behavior state with risk propagation as the monitoring target, and its judgment not only focuses on the density threshold of the behavior state, but also pays more attention to its propagation trend and potential harm, so as to avoid the local risk spreading to regional crisis. Specifically, the system compares the specific behavior state sub-density (such as "crowded pushing and shoving", "emergency call", "disordered running" and other behaviors with safety risks) with the state alarm threshold preset based on the scene safety rules in real time, which is the basic condition of judgment. At the same time, the system synchronously monitors the spatial propagation speed (such as the rate of diffusion from the edge to the center of the region) and the personnel flow direction of the behavior state, which is the key supplement to judge the risk level. If the sub-density of a certain risk behavior only slightly exceeds the threshold, but the propagation speed is extremely fast and the personnel flow direction is directly to the key area, such as the safety exit of the shopping mall, the emergency access of the hospital, and the flammable and explosive goods warehouse of the factory, the potential harm is much greater than the high-density aggregation in the fixed area.

[0166] When the specific behavior state sub-density exceeds the state alarm threshold, and it is monitored that the behavior state presents a clear trend of spreading to the key area, the system determines that the state aggregation density is abnormal. For example, in a station waiting hall, if the behavior state sub-density of "running crowded" exceeds the threshold, and the personnel flow direction points to the only ticket gate, the system will immediately determine the abnormality and trigger multi-level response: on the one hand, the alarm information is sent to the terminal of the regional manager, and the abnormal position and the spreading direction are marked; on the other hand, the guidance instructions are published through the broadcast and electronic screen in the region, prompting the orderly flow of personnel; if the spreading trend intensifies, the security equipment will also be linked to focus on the abnormal area, providing real-time image support for subsequent disposal. The judgment mechanism breaks through the limitation of only using density to judge the abnormality, and realizes the forward-looking early warning and disposal of the risk by combining the propagation characteristics.

[0167] The regional personnel intelligent management method provided by the embodiments of the present application can be applied to a regional personnel intelligent management device. Figure 3 A hardware structure block diagram of the regional personnel intelligent management device is shown, referring to Figure 3 The hardware structure of the regional personnel intelligent management device can include at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4.

[0168] In the embodiments of the present application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete the communication among each other through the communication bus 4.

[0169] The processor 1 can be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application, etc.

[0170] The memory 3 can include a high-speed RAM memory, and can also include a non-volatile memory, etc., such as at least one disk memory.

[0171] The memory stores a program, and the processor can call the program stored in the memory, and the program is used to:

[0172] The rough regional position information of the personnel is obtained by using the radio frequency positioning network, and the corresponding visual recognition device is scheduled based on the rough regional position information, and the attribute category and position information of the personnel in the region are determined by recognizing the dynamic coding label, wherein the coding information of the dynamic coding label includes a periodically dynamically updated visible light part and / or a fluorescent hidden part, and is associated with the personnel attribute category information in the background database.

[0173] based on the identified attribute category and location information of the personnel, calculate the overall personnel density of the target area in real time, and simultaneously calculate at least one attribute sub-density based on the attribute classification of the personnel, the attribute sub-density being a density obtained by counting the personnel with the same attribute category in the target area;

[0174] compare the overall personnel density and the attribute sub-density calculated in real time with a preset dynamic threshold rule library to determine whether there is a density abnormal situation, the dynamic threshold rule library including attribute sub-density thresholds set based on different attribute category combinations and / or different space-time scenarios;

[0175] If it is determined that there is a density abnormal situation, generate and execute corresponding management operation instructions according to the abnormal type and a preset management plan library.

[0176] Optionally, the refinement function and the extension function of the program can refer to the description above.

[0177] The embodiments of the present application also provide a readable storage medium, which can store a program suitable for execution by a processor, and the program is used for:

[0178] acquire rough regional location information of personnel by using the radio frequency positioning network, and schedule corresponding visual recognition devices based on the rough regional location information, determine attribute category and location information of the personnel in the region by recognizing the dynamic coding label, wherein the coding information of the dynamic coding label includes a periodically dynamically updated visible light part and / or a fluorescent hidden part, and is associated with personnel attribute category information in a background database;

[0179] based on the identified attribute category and location information of the personnel, calculate the overall personnel density of the target area in real time, and simultaneously calculate at least one attribute sub-density based on the attribute classification of the personnel, the attribute sub-density being a density obtained by counting the personnel with the same attribute category in the target area;

[0180] compare the overall personnel density and the attribute sub-density calculated in real time with a preset dynamic threshold rule library to determine whether there is a density abnormal situation, the dynamic threshold rule library including attribute sub-density thresholds set based on different attribute category combinations and / or different space-time scenarios;

[0181] If it is determined that there is a density abnormal situation, generate and execute corresponding management operation instructions according to the abnormal type and a preset management plan library.

[0182] Optionally, the refinement function and the extension function of the program can refer to the description above.

[0183] The embodiment of the present application also provides a computer program product comprising a computer program, which, when executed by a processor, performs the method.

[0184] The rough regional position information of the personnel is acquired by using the radio frequency positioning network, and the corresponding visual recognition device is dispatched based on the rough regional position information, the attribute category and the position information of the personnel in the region are determined by recognizing the dynamic coding label, wherein the coding information of the dynamic coding label comprises a periodically dynamically updated visible light part and / or a fluorescent hidden part, and is associated with the attribute category information of the personnel in the background database;

[0185] Based on the attribute category and the position information of the personnel recognized, the overall personnel density of the target region is calculated in real time, and at least one attribute sub-density based on the attribute category of the personnel is calculated, the attribute sub-density being the density obtained by counting the personnel with the same attribute category in the target region;

[0186] The overall personnel density and the attribute sub-density calculated in real time are compared with a preset dynamic threshold rule library to determine whether there is a density abnormal situation, the dynamic threshold rule library comprising attribute sub-density thresholds set based on different attribute category combinations and / or different time and space scenes;

[0187] If it is determined that there is a density abnormal situation, corresponding management operation instructions are generated and executed according to the abnormal type and a preset management plan library.

[0188] Optionally, the refinement function and the extension function of the program can refer to the description above.

[0189] Finally, it should be noted that, in this document, the relationship terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0190] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts between various embodiments can be referred to each other.

[0191] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent management of regional personnel, characterized in that, This is achieved based on dynamically coded tags configured for each person within the area, a radio frequency positioning network deployed throughout the area, and multimodal visual recognition devices. The method includes: The radio frequency positioning network is used to obtain a rough area location information of a person, and a corresponding visual recognition device is dispatched based on the rough area location information. The attribute category and location information of the person in the area are determined by recognizing the dynamic coded tag, including: The radio frequency positioning network periodically detects signals to obtain rough location information of each person in the area; Based on the rough area location information, visual recognition devices deployed above the corresponding area are scheduled to acquire images of the target area; During the image acquisition process, the image is analyzed to detect whether there are areas where people block each other or where dynamically coded tags overlap. The encoding information of the dynamically coded tags includes a periodically dynamically updated visible light portion and / or a fluorescent hidden portion, and is associated with the personnel attribute category information in the background database. If present, at least two visual recognition devices with different spectral characteristics are scheduled to perform collaborative image acquisition and multimodal image fusion processing on the target area to resolve the occluded dynamic coded label. From the acquired images and the fused images, locate and identify the current encoding information of the dynamic coded tag worn by each person; The identified current encoding information is matched with the background database to obtain the corresponding personnel attribute category, and the personnel's location information is determined by combining image and radio frequency signal analysis. Based on the identified attribute categories and location information of the personnel, the overall personnel density of the target area is calculated in real time, and at the same time, at least one attribute sub-density based on the personnel attribute classification is calculated. The attribute sub-density is the density obtained by statistically analyzing the personnel with the same attribute category in the target area. The overall personnel density and the attribute sub-density calculated in real time are compared with a preset dynamic threshold rule library to determine whether there is an abnormal density situation. The dynamic threshold rule library includes attribute sub-density thresholds set based on different attribute category combinations and / or different spatiotemporal scenarios. If an abnormal density situation is determined, corresponding management operation instructions are generated and executed based on the anomaly type and the preset management contingency plan library. Before scheduling the visual recognition device, the method further includes extracting and analyzing the multi-dimensional radio frequency features of the radio frequency positioning network signal to optimize the visual recognition strategy. The process of optimizing the visual recognition strategy includes: Based on the multipath delay difference characteristics, it is determined whether there is a densely populated sub-region within the approximate area location. If so, the visual recognition device is scheduled to prioritize the multimodal collaborative acquisition and fusion recognition of the region. Based on the signal strength gradient characteristics, the relative distance distribution between different people in the approximate area is calculated to determine the focusing and field of view segmentation parameters when the visual recognition device collects data. Based on the characteristics of the signal's dynamic rate of change, the visual acquisition frame rate is dynamically adjusted, using a high frame rate for moving personnel and a low frame rate for stationary personnel.

2. The method according to claim 1, characterized in that, The attribute sub-density includes at least one of the function sub-density, behavior state sub-density, and spatiotemporal compliance sub-density; The functional sub-density is obtained by classifying and statistically analyzing the job functions of personnel; The behavioral state sub-density is obtained by classifying and statistically analyzing the human behavioral states identified through visual posture analysis or radio frequency signal features. The spatiotemporal compliance sub-density is obtained by classifying and statistically analyzing the matching results of personnel's scheduling information, access history, and real-time location information.

3. The method according to claim 2, characterized in that, The real-time calculated overall population density and attribute sub-densities are compared with a preset dynamic threshold rule base to determine whether there is an abnormal density situation, including: The overall population density is compared with the maximum carrying density threshold calculated based on the regional three-dimensional terrain structure, passage capacity and real-time event status. When the overall population density exceeds the threshold and the duration exceeds the preset time, it is determined to be an abnormal regional cluster density. Based on the functional sub-density and the spatiotemporal compliance sub-density, a dual compliance detection method, including job absence detection and unauthorized trajectory analysis, is used to determine whether there is an abnormal functional compliance density. Monitor the instantaneous change rate and spatial distribution entropy value of the specific functional sub-density. When the instantaneous change rate generated by the concentration of specific functional personnel exceeds the dynamic risk threshold in a short period of time, and the spatial distribution entropy value changes abruptly from a uniform distribution to a highly clustered distribution, it is determined that the functional cluster density is abnormal, and cross-validation based on the behavioral state sub-density within the region is triggered. The specific density of the behavior state is compared in real time with the state alarm threshold preset based on the scene safety rules. At the same time, the spatial propagation speed of the behavior state and the direction of personnel flow are monitored. When the state alarm threshold is exceeded and a trend of spreading to key areas is shown, it is determined that the state aggregation density is abnormal.

4. The method according to claim 3, characterized in that, The process of generating management operation instructions for evacuation guidance based on multi-dimensional attribute collaboration triggered by the abnormal regional agglomeration density includes: The movement status of people in the area is classified based on the identified behavioral state sub-density, and the people are grouped by function based on the identified functional sub-density. By calculating the optimal path load for people to reach each safety exit within the area, and combining this with the abnormal dwelling areas identified by the spatiotemporal compliance sub-density, differentiated evacuation route planning is generated. Based on the differentiated evacuation route plan, evacuation instructions with different priorities and different route guidance are sent to the smart terminals held by different functional groups.

5. The method according to claim 3, characterized in that, The execution process of the dual compliance check includes: The functional sub-density of each key area is compared with the expected functional density distribution map dynamically generated based on scheduling information and workflow dependencies. The job shortage detection result is determined by detecting whether the functional sub-density corresponding to the necessary functions is lower than the minimum configuration threshold and whether the duration exceeds the business process tolerance window. The spatiotemporal compliance sub-density is matched with a predefined three-dimensional permission matrix. When an unauthorized target is detected whose real-time location information does not match the authorized spatiotemporal range, the historical trajectory and current activity pattern of the unauthorized target are back-analyzed to construct an abnormal behavior sequence in order to determine the unauthorized trajectory analysis results.

6. The method according to claim 3, characterized in that, The cross-validation process based on the density of behavioral state sub-states within the region includes: When the functional aggregation density is determined to be abnormal, the behavioral state sub-density is obtained within the same time period and spatial range as the abnormal functional aggregation, and the time series change curve of the functional sub-density is aligned and the correlation is calculated with the concurrent change curve of the behavioral state sub-density. If the calculation results show that the occurrence time of functional aggregation is highly correlated with the outbreak time of abnormal behavior and the spatial range highly overlaps, then the confidence level of the functional aggregation density anomaly is increased, and it is determined to be a high-probability emergency response event; otherwise, the confidence level of the functional aggregation density anomaly is decreased.

7. The method according to claim 1, characterized in that, When assessing density anomalies, the following should also be included: Real-time monitoring and comparison of the changing trends of attribute sub-densities of the same attribute category across different regions; When a specific attribute sub-density in the first region is detected to decrease significantly within a certain period of time, and the same attribute sub-density in the second region adjacent to the first region increases significantly within a similar period of time, and the changes are correlated, it is determined that a cross-regional personnel transfer event has occurred, and the root cause is inferred by combining the other sub-density trends of the first region and the second region.

8. The method according to claim 1, characterized in that, After determining the attribute category and location information of the personnel within the area by identifying the dynamic coded tag, the method further includes: Obtain a causal knowledge graph containing prior business rules for the scenario; The attribute categories and location information of the personnel within the area determined by identifying the dynamic coding tags, along with the causal knowledge graph, are input into the causal inference engine for logical consistency verification. If the logical consistency check finds a conflict, an identity verification process is triggered, which includes: Re-identification and verification of dynamic coded tags of relevant personnel based on multimodal image fusion; If the verification is correct, based on the personnel's historical behavior data and shift information, combined with the causal knowledge graph, the conflicting attribute categories are probabilistically corrected until the attribute category matching result that conforms to the prior business logic of the scenario is output.

9. A regional personnel intelligent management device, characterized in that, Including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the regional personnel intelligent management method as described in any one of claims 1-8.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the regional personnel intelligent management method as described in any one of claims 1-8.

11. A computer program product, comprising a computer program, characterized in that, The computer program is executed by the processor to perform the various steps of the regional personnel intelligent management method as described in any one of claims 1-8.

12. A dynamic coded tag for use in the regional personnel intelligent management method as described in any one of claims 1-8, characterized in that, include: Label base; A visible light coding area is disposed on the label substrate, the visible light coding area containing a combination of numbers and letters that are periodically and dynamically updated; A fluorescent material layer disposed on or within the label substrate, the fluorescent material layer exhibiting a hidden coded pattern under excitation light of a specific wavelength; A microcontroller is used to control the encoding of the visible light encoding area to be synchronously updated according to the personnel attribute category information in the background database.

Images