Certificate access method and system, terminal equipment and readable storage medium

Abstract

The invention relates to the technical field of electric power certificate operation and maintenance management, and particularly discloses a certificate access method and system, terminal equipment and a readable storage medium, and the method comprises the steps: collecting multi-dimensional access data and access auxiliary data of certificate access in real time, carrying out the feature extraction of the collected historical data, and detecting and analyzing a user certificate access operation coefficient; based on time sequence analysis, carrying out time period aggregation and anomaly detection on a user certificate access operation coefficient, and dynamically identifying a potential peak period of certificate access; the method comprises the following steps: predicting an access demand evaluation factor of a certificate in a future fixed period based on a user certificate access purpose and a potential peak period, carrying out cabinet position resource allocation and certificate position optimization according to the access demand evaluation factor of the certificate, and adjusting an identity verification terminal and channel resource distribution at the same time to reduce queuing and waiting time in the peak period; the method can intelligently sense and predict the peak period, dynamically optimize the resource configuration, effectively relieve queuing waiting, and improve the certificate access efficiency.

Description

Technical Field

[0001] This invention relates to the field of power certificate operation and maintenance management technology, and more specifically, to a certificate access method, system, terminal device, and readable storage medium. Background Technology

[0002] In the existing power operation and maintenance management process, although some power companies have introduced electronic management systems to improve the efficiency of equipment dispatching and material statistics, significant management bottlenecks still exist during peak periods of document retrieval. Document retrieval behavior is affected by various factors such as personnel scheduling, inspection task arrangements, sudden failures, and individual operating habits, exhibiting significant randomness and uncertainty. Different personnel have significantly different needs for document retrieval and return at different times, and behaviors such as bulk retrieval, temporary borrowing, and delayed return occur frequently, making it difficult to form a stable behavioral pattern. Due to the uncontrollability of user behavior, historical data contains a large amount of random interference. Traditional prediction methods that rely on fixed-time period statistics or simple regression analysis are unable to accurately identify future peak periods for document retrieval and the corresponding document types in demand. This lack of prediction accuracy not only prevents the management system from allocating counter resources and verification channels in advance but also easily leads to equipment congestion, operational delays, and management chaos during peak periods, affecting document circulation efficiency and overall security, thereby interfering with operation and maintenance efficiency and overall power grid security.

[0003] Therefore, it is necessary to provide a document storage and retrieval method, system, terminal device, and readable storage medium to solve the above-mentioned technical problems. In order to solve the above problems, a technical solution is provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a document access method, system, terminal device and readable storage medium to solve the problem that, due to the uncontrollable user behavior, it is difficult to predict the peak periods of document access and the corresponding document types of demand through historical data analysis.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for storing and retrieving identification documents includes the following steps: Through intelligent storage lockers, identity recognition terminals and back-end management platforms, multi-dimensional storage and retrieval data of documents are collected in real time, and auxiliary data of document storage and retrieval are recorded during the document storage and retrieval operation. Feature extraction is performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set. Based on the user behavior feature set, the user document access operation coefficient is detected and analyzed. Based on time series analysis, the coefficients of user document access operations are aggregated by time period and anomaly detected to dynamically identify potential peak periods for document access. Based on the user's purpose of accessing documents and the assessment factors for document access demand during potential peak periods, counter resources are allocated and document locations are optimized according to the document access demand assessment factors. At the same time, the distribution of identity verification terminals and channel resources is adjusted to reduce queuing and waiting time during peak periods. The prediction model is adaptively corrected by comparing the predicted access demand assessment factors of the documents with the actual access demand assessment factors of the documents in real time and through deviation analysis.

[0006] As a further aspect of the present invention, the multi-dimensional access data includes document type, document collection time, document return time, and access frequency; the access auxiliary data includes the number of times the cabinet door is opened, the user's identity information, the purpose of document access, and the waiting time.

[0007] As a further aspect of the present invention, feature extraction is performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set. Based on the user behavior feature set, the user's document access operation coefficient is detected and analyzed. The specific steps are as follows: The system obtains the document collection time, return time, and access frequency corresponding to the document type from the user's historical multidimensional access data. Based on the document collection time and return time, it determines the operation duration of the target document. The system obtains the first behavioral feature based on the operation duration of the target document corresponding to the document type and the second behavioral feature based on the access frequency corresponding to the document type. Obtain the number of times the cabinet door is opened and the waiting time corresponding to the document type from the historical access auxiliary data. Obtain the third behavioral feature based on the number of times the cabinet door is opened according to the document type, and obtain the fourth behavioral feature based on the waiting time corresponding to the document type. A user behavior feature set is constructed based on the first behavior feature, the second behavior feature, the third behavior feature, and the fourth behavior feature. The user document access operation coefficient corresponding to the document type is predicted based on the user behavior feature set. Get the user document access operation coefficients corresponding to all types of user documents.

[0008] As a further aspect of the present invention, based on time series analysis, the user document access operation coefficients are aggregated by time period and anomaly detection is performed to dynamically identify potential peak periods for document access. The specific steps are as follows: Extract the user document access operation coefficients corresponding to the i-th document type, and construct the access operation time series by sorting them by time. ,in, For the first Each time sampling point, The time sampling length, Time sampling point The corresponding user document access operation coefficient, Time sampling point The corresponding user document access operation coefficient; The access operation time series are aggregated according to a preset time window, and the average value within each time window is calculated as the volatility assessment factor. Anomaly detection is performed based on volatility assessment factors to identify time windows with volatility exceeding the normal range as potential peak periods. The detected potential peak periods are clustered and their continuity is determined. If several potential peak periods exist, they are merged into a continuous peak interval. Based on the peak period distribution of different document types, a dynamic peak identification result set is generated. ,in, This represents the continuous peak interval corresponding to the i-th document type. The purpose of accessing user credentials for the i-th type of credential.

[0009] As a further aspect of the present invention, time windows with fluctuations exceeding the normal range are identified as potential peak periods. The specific identification criteria are: if the following conditions are met... If the j-th time window is considered a potential peak period, then... Let be the volatility assessment factor for the j-th time window. This is the average of the historical user document access operation coefficients. This is an adjustable sensitivity parameter. The standard deviation of the historical user document access operation coefficients.

[0010] As a further aspect of the present invention, based on the user's purpose of accessing identification documents and the assessment factor for predicting the demand for document access during a future fixed period based on potential peak periods, the specific steps are as follows: Extract historical dynamic peak identification result sets of different users, and perform document access peak matching analysis based on the historical dynamic peak identification result sets to obtain the peak time matching coefficient of the same document type among different users. The assessment factor for the demand for document access during peak hours is predicted based on the matching coefficient during peak hours and the type of document.

[0011] The assessment factors for predicting the demand for document access during future fixed periods based on the user's purpose of document access and potential peak periods are as follows: Extract historical dynamic peak identification result sets of different users, and perform document access peak matching analysis based on the historical dynamic peak identification result sets to obtain the peak time matching coefficient of the same document type among different users. The assessment factor for the demand for document access during peak hours is predicted based on the matching coefficient during peak hours and the type of document.

[0012] As a further aspect of the present invention, the formula for calculating the peak-hour matching coefficient for the same document type i is as follows: ; ; In the formula: Let i be the peak-hour matching coefficient for document type i. The similarity weighting coefficient is used for the continuous peak interval. The similarity weighting coefficient for the purpose of accessing user credentials. For user u, the continuous peak interval corresponding to the i-th type of identification document. For user v, the continuous peak interval corresponding to the i-th type of identification document. For user u, the purpose of accessing the user's ID document corresponding to the i-th ID document type is... The purpose of accessing user ID documents for user v with the i-th type of ID document.

[0013] A document storage and retrieval system includes a data acquisition module, a behavioral feature analysis module, a time-series peak identification module, a demand prediction and assessment module, a resource optimization and allocation module, and an adaptive model correction module. The data acquisition module is used to collect multi-dimensional access data of document storage and retrieval in real time through intelligent storage cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document storage and retrieval operation. The behavioral feature analysis module is used to extract features from the collected historical multidimensional access data and historical access auxiliary data, construct a user behavior feature set, and detect and analyze the user's document access operation coefficient based on the user behavior feature set. The time-series peak identification module is used to perform time-series analysis, aggregate user document access operation coefficients by time period, and detect anomalies to dynamically identify potential peak periods for document access. The demand forecasting and assessment module is used to predict the demand assessment factors for document access within a fixed period in the future based on the user's document access purpose and potential peak periods. Based on the document access demand assessment factors, the module allocates counter resources and optimizes document locations, while adjusting the distribution of identity verification terminals and channel resources to reduce queuing and waiting time during peak periods. The resource optimization and allocation module is used to compare the predicted access demand assessment factors of documents with the actual access demand assessment factors of documents in real time. Through deviation analysis, the prediction model is adaptively corrected, thereby continuously improving the accuracy of the prediction of the number of documents needed during peak periods. The adaptive model correction module is used to collect multi-dimensional access data of document access in real time through smart access cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document access operation.

[0014] A terminal device includes a memory and a processor. The memory stores a computer program. When the processor runs the computer program stored in the memory, the processor performs the steps of the document retrieval method described above.

[0015] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of a document retrieval method as described above.

[0016] The technical effects and advantages of this invention, which provides a method, system, terminal device, and readable storage medium for document retrieval, are as follows: This invention utilizes the collaborative operation of intelligent retrieval cabinets, identity recognition terminals, and a back-end management platform to collect multi-dimensional data and auxiliary information on document retrieval in real time. It extracts user behavior characteristics to construct an operational feature model and dynamically identifies peak periods for document retrieval based on time series analysis. Furthermore, by combining the user's document retrieval purpose, it predicts the retrieval demand for various documents within a fixed future time period. Based on the prediction results, it intelligently allocates cabinet resources, optimizes document placement, and dynamically adjusts the configuration of identity verification terminals and channel resources, thereby effectively alleviating queuing and waiting during peak periods. Simultaneously, by comparing predicted and actual values ​​in real time, it performs deviation analysis and adaptive model correction, achieving continuous model optimization and accuracy improvement. This not only improves the operational efficiency and user experience of the document retrieval system but also realizes intelligent control and dynamic optimal resource allocation during peak periods. This invention can intelligently sense and predict peak periods, dynamically optimize resource allocation, effectively alleviate queuing and waiting, improve document retrieval efficiency, and continuously improve prediction accuracy through an adaptive model, achieving efficient, intelligent, and self-optimizing management. Attached Figure Description

[0017] Figure 1 A flowchart of a document retrieval method provided in an embodiment of the present invention; Figure 2 This is a system block diagram of a document storage and retrieval system provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention.

[0019] like Figure 1 The diagram shown is a flowchart of a document retrieval method provided in an embodiment of the present invention. Figure 1The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned terminal devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S5 are detailed as follows: Step S1: Collect multi-dimensional access data for document access in real time through smart access cabinets, identity recognition terminals and back-end management platforms, and record access auxiliary data during the document access operation. Step S2: Extract features from the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set, and detect and analyze the user's document access operation coefficient based on the user behavior feature set. Step S3: Based on time series analysis, perform time period aggregation and anomaly detection on the user's document access operation coefficients to dynamically identify potential peak periods for document access. Step S4: Based on the user's purpose of accessing and retrieving documents and the potential peak periods, predict the document access demand assessment factors for future fixed periods. Based on the document access demand assessment factors, allocate counter resources and optimize document locations. At the same time, adjust the distribution of identity verification terminals and channel resources to reduce queuing and waiting time during peak periods. Step S5: In real time, compare the predicted document access demand assessment factor with the actual document access demand assessment factor, and adaptively correct the prediction model through deviation analysis, thereby continuously improving the accuracy of predicting the number of documents needed during peak periods.

[0020] Preferably, the multidimensional access data includes document type, document collection time, document return time, and access frequency; the access auxiliary data includes the number of times the cabinet door is opened, the user's identity information, the purpose of document access, and the waiting time.

[0021] This invention utilizes intelligent storage lockers, identity recognition terminals, and a back-end management platform to collect multi-dimensional storage and retrieval data and auxiliary data in real time during the document storage and retrieval process. The multi-dimensional storage and retrieval data includes information such as document type, retrieval time, return time, and storage and retrieval frequency, reflecting the user's usage cycle and operational patterns for different documents. For example, if a certain type of document, such as an official pass, is frequently retrieved and returned at concentrated times within a fixed daily period, it can be determined that the document exhibits high-frequency usage characteristics during that period.

[0022] Meanwhile, auxiliary data for access control includes the number of times the locker door is opened, the user's identity information, the purpose of document access, and the waiting time, which is used to further characterize the user's operational behavior and the status of locker resource utilization. For example, when it is detected that the same user opens the locker door multiple times in a short period of time but fails to complete the document access operation, it can be identified as high-frequency invalid opening behavior, and the locker resource shortage can be judged by combining the waiting time data. Furthermore, by analyzing the correspondence between the user's identity information and the purpose of document access, document usage patterns in different positions or task scenarios can be identified, providing a basis for decision-making in subsequent locker allocation and document location optimization.

[0023] By integrating and analyzing the aforementioned multi-dimensional access data and access auxiliary data, we can comprehensively reflect the operational patterns and behavioral characteristics of users in the process of document access. This not only provides accurate input for subsequent peak period identification and demand prediction, but also allows for dynamic adjustment of cabinet resource allocation strategies through historical data comparison, thereby achieving intelligent and efficient document management.

[0024] Preferably, feature extraction is performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set. Based on the user behavior feature set, the user's document access operation coefficient is detected and analyzed. The specific steps are as follows: The system obtains the document collection time, return time, and access frequency corresponding to the document type from the user's historical multidimensional access data. Based on the document collection time and return time, it determines the operation duration of the target document. The system obtains the first behavioral feature based on the operation duration of the target document corresponding to the document type and the second behavioral feature based on the access frequency corresponding to the document type. Obtain the number of times the cabinet door is opened and the waiting time corresponding to the document type from the historical access auxiliary data. Obtain the third behavioral feature based on the number of times the cabinet door is opened according to the document type, and obtain the fourth behavioral feature based on the waiting time corresponding to the document type. A user behavior feature set is constructed based on the first, second, third, and fourth behavioral features. The user document access operation coefficient corresponding to each document type is predicted based on this feature set. The formula for calculating the user document access operation coefficient corresponding to the i-th document type is as follows: ; In the formula: Let be the user document access operation coefficient corresponding to the i-th document type. The first behavioral feature corresponding to the i-th document type is... The second behavioral feature corresponding to the i-th document type. The third behavioral feature corresponding to the i-th document type The fourth behavioral feature corresponding to the i-th document type. This represents the total number of document types. For the a-th One user; Get the user document access operation coefficients corresponding to all types of user documents.

[0025] In this embodiment of the invention, feature extraction and behavior modeling are performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set and calculate the user document access operation coefficient.

[0026] First, the document type, document retrieval time, document return time, and access frequency for each user are extracted from historical multidimensional access data. For example, for power company user A with multiple documents such as passes, office permits, and vehicle use permits, the time nodes for each document retrieval and return are recorded, and the difference between the two is calculated to determine the operation duration of the target document. The operation duration of the target document reflects the average time occupied during the use of this type of document and is used as the first behavioral feature. At the same time, the access frequency of this document over a period of time is counted as the second behavioral feature to describe the usage activity of this document.

[0027] Secondly, the system extracts the number of times the locker door is opened and the waiting time information corresponding to the type of document from historical access auxiliary data. The number of times the locker door is opened is used to assess the user's operating habits and the level of locker resource occupancy during the document retrieval and return process, and this parameter is defined as the third behavioral feature; the waiting time reflects the degree of congestion of the locker during peak hours, and the system uses it as the fourth behavioral feature to quantify the user's waiting experience during the document retrieval and return process.

[0028] Subsequently, by integrating the above four categories of behavioral characteristics, a user behavior feature set is constructed for each user. The user document access operation coefficient calculation formula comprehensively considers document usage frequency, operation duration, cabinet usage intensity, and waiting time, quantifying the user's operational behavior patterns for different documents. For example, if a user has a high access frequency, short operation duration, and many cabinet openings for a certain type of document, the calculated access operation coefficient will be high, indicating that the user has high operational activity and efficiency with that document type. Integrating the access operation coefficients corresponding to all document types for each user forms a complete user behavior profile, which is used for subsequent time series analysis and peak-hour prediction model input, providing data support for dynamic resource scheduling and cabinet optimization.

[0029] Preferably, based on time series analysis, the user document access operation coefficients are aggregated by time period and anomaly detection is performed to dynamically identify potential peak periods for document access. The specific steps are as follows: Extract the user document access operation coefficients corresponding to the i-th document type, and construct the access operation time series by sorting them by time. ,in, For the first Each time sampling point, The time sampling length, Time sampling point The corresponding user document access operation coefficient, Time sampling point The corresponding user document access operation coefficient; The access operation time series are aggregated according to a preset time window, and the average value within each time window is calculated as the volatility assessment factor. The formula for calculating the volatility assessment factor is as follows: ; In the formula: Let be the volatility assessment factor for the j-th time window. Let j be the length of the j-th time window. Time sampling point The corresponding user document access operation coefficient; Anomaly detection is performed based on volatility assessment factors to identify time windows with volatility exceeding the normal range. The specific identification criteria are: if the following conditions are met... If the j-th time window is considered a potential peak period, then... Let be the volatility assessment factor for the j-th time window. This is the average of the historical user document access operation coefficients. This is an adjustable sensitivity parameter. The standard deviation of the historical user document access operation coefficients; The detected potential peak periods are clustered and their continuity is determined. If several potential peak periods exist, they are merged into a continuous peak interval. Based on the peak period distribution of different document types, a dynamic peak identification result set is generated. ,in, This represents the continuous peak interval corresponding to the i-th document type. The purpose of accessing user credentials for the i-th type of credential.

[0030] This invention uses time series analysis to aggregate and detect anomalies in user document access operation coefficients over time periods, thereby dynamically identifying potential peak periods for document access.

[0031] Specifically, firstly, for different types of documents, corresponding user document access operation coefficients are extracted, and access operation time series are constructed in chronological order. This time series can reflect the changing trends of user document operation behavior in different time periods, providing basic data support for subsequent dynamic peak identification.

[0032] Next, the above time series is aggregated according to preset time windows, such as 10 minutes, 30 minutes, or 1 hour. For each time window, the average value of the user ID access operation coefficient of all sampling points within the window is calculated as the fluctuation evaluation factor for that window, which is used to measure the activity and fluctuation range of user ID operations within a certain time range.

[0033] After completing the aggregation calculation, anomaly detection is performed on the fluctuation evaluation factors for all time windows. By calculating the average and standard deviation of historical user document access operation coefficients, a dynamic threshold determination is performed for each time window: if a certain time window meets... If a potential peak period is detected, that time window is identified. Subsequently, multiple potential peak periods are clustered and their continuity is determined. When several potential peak periods are temporally adjacent or overlap, they are automatically merged into a continuous peak interval, thus avoiding misjudgments caused by short-term fluctuations. By analyzing peak intervals for different document types, a dynamic peak identification result set is generated.

[0034] For example, in the document management system of a power distribution station, the above method identifies frequent access to access passes during 8:00–9:30 AM and 4:30–5:30 PM, corresponding to user document access for "get off work entry and exit verification." Meanwhile, official passes see peak access concentrated between 9:00–10:00 AM on Monday and Thursday mornings, corresponding to user document access for "meeting entry and exit approval." This forms a dynamic peak period identification result set, providing data for subsequent counter resource allocation, document location optimization, and identity verification channel scheduling. It enables real-time perception of temporal changes in document usage behavior, identification of peak period distribution characteristics, and improvement of the predictability of document management and the accuracy of resource allocation.

[0035] Preferably, the assessment factors for predicting the demand for document access within a fixed time period in the future, based on the user's purpose of document access and potential peak periods, are as follows: Extract historical dynamic peak identification result sets of different users, and perform document access peak matching analysis based on the historical dynamic peak identification result sets to obtain the peak time matching coefficient of the same document type among different users. The assessment factor for the demand for document access during peak hours is predicted based on the matching coefficient during peak hours and the type of document.

[0036] Based on the user's purpose of accessing and retrieving documents and potential peak periods, this invention predicts and quantifies the access needs of various documents within a fixed future period, thereby achieving dynamic scheduling and intelligent allocation of document resources.

[0037] Specifically, the system first extracts dynamic peak identification result sets for different users from historical operation records. By analyzing the peak interval distribution of different users for the same type of document, it identifies the overlapping access behavior patterns of multiple users over time. Then, it performs matching analysis on the peak periods of the same type of document among different users, calculating the peak period matching coefficient to characterize the degree of overlap in usage of the same type of document by different users. For example, when user A and user B's usage time intervals of the pass highly overlap, their peak matching coefficient is determined to be high; conversely, it is low. This matching coefficient reflects the intensity of sharing demand for a certain type of document within a specific time period, providing a quantitative basis for subsequent demand prediction.

[0038] Next, based on the obtained peak-period matching coefficients and document type distribution, a comprehensive calculation of the access demand assessment factor for various types of documents in a future fixed period is performed. This factor quantifies the overall demand intensity of a certain type of document in the predicted period, taking into account multiple dimensions such as the historical behavioral characteristics of different users, the overlap of peak times, and the purpose of document use. For example, when a certain document has been used by multiple people in the past, and their access purposes are all related to regular meetings, it can be predicted that the demand assessment factor for this document will be high in the same period in the future, thus providing an early warning of possible concentrated access during that period.

[0039] The above analysis enables dynamic prediction of future document access demand, providing a basis for decision-making regarding subsequent counter optimization, identity verification channel allocation, and peak-hour resource scheduling. Taking a government agency as an example, by modeling and analyzing the access data of different departments' users' access cards and official passes over the past three months, a fixed peak period for meeting-related documents was identified as Monday mornings from 9:00 to 10:00. Based on this, counter configuration and document distribution can be adjusted in advance to reduce waiting and congestion during peak hours, achieving intelligent document resource management.

[0040] Preferably, the formula for calculating the peak-hour matching coefficient for the same document type i is: ; ; In the formula: Let i be the peak-hour matching coefficient for document type i. The similarity weighting coefficient is used for the continuous peak interval. The similarity weighting coefficient for the purpose of accessing user credentials. For user u, the continuous peak interval corresponding to the i-th type of identification document. For user v, the continuous peak interval corresponding to the i-th type of identification document. For user u, the purpose of accessing the user's ID document corresponding to the i-th ID document type is... The purpose of accessing user ID documents for user v with the i-th type of ID document. Let be the overlap length of the continuous peak interval corresponding to the i-th type of ID for users u and v. Let be the length of the union of the continuous peak intervals corresponding to the i-th document type for users u and v. Let be the overlap length of the user's ID access destination corresponding to the i-th ID type. Let be the length of the union of the user's document access destinations corresponding to the i-th document type of user u.

[0041] After extracting the dynamic peak identification result sets for different users, this embodiment of the invention introduces a peak period matching coefficient to further quantify the overlap of peak periods and the similarity of usage purposes for different users with the same type of document. Specifically, for document type i, the continuous peak intervals for users u and v on that document, as well as the corresponding document access purposes, are extracted. By calculating the intersection and union of the two users' time intervals and access purposes, the overlap and similarity of their usage behaviors are evaluated. For example, in the document management system of a power authority, users A and B both frequently use "official travel permits". By analyzing historical dynamic peak identification results, the system finds that user A's continuous peak interval is 8:30-10:00 AM, corresponding to the access purpose of "outing for meetings"; user B's continuous peak interval is 9:00-10:30 AM, corresponding to the access purpose of "field business trips". The system calculates that the overlap time of the two peak intervals is approximately 60 minutes, with an overlap rate of approximately 67% of the union time; the similarity of access purposes is approximately 80%. If the system sets the similarity weight coefficient for the continuous peak period to 0.6 and the purpose similarity weight to 0.4, then the peak period matching coefficient for document type i is calculated to be 0.726. This result indicates that user A and user B have a high degree of overlap in time and purpose when using the "Official Travel Permit," suggesting a strong tendency for shared use of this document in similar future time periods.

[0042] This calculation method quantifies the correlation of usage patterns among different users for the same type of document, providing key parameter inputs for subsequent document access demand prediction and resource scheduling optimization. Simultaneously, this matching coefficient can dynamically reflect the convergence of document usage among different departments or positions within an organization under varying task cycles, thereby proactively identifying potential peak resource competition scenarios and enabling forward-looking management and optimized allocation of document resources.

[0043] Preferably, the assessment factor for the demand for document access during peak hours is predicted based on the peak-hour matching coefficient and document type, and the calculation formula is as follows: ; In the formula: This is an assessment factor for the access demand of document type i during peak hours. This represents the total number of document types. Let be the peak-time matching coefficient for user u and user v with document type i. For user pairs consisting of user u and user v, This represents the sum of the peak-time matching coefficients for document type i across all user pairs. This is the average of the matching coefficients for all document types across all user pairs during peak periods.

[0044] It should be noted that one scenario for assessing document access demand based on the document access demand assessment factor during peak hours is as follows: if the document access demand assessment factor during peak hours is greater than 1, it indicates that the peak concentration of document type i is higher than the average level, and it is a high-demand document; if the document access demand assessment factor during peak hours is less than or equal to 1, it indicates that the peak concentration of document type i is lower than the average level, and it is a non-high-demand document.

[0045] After calculating the peak-hour matching coefficients for the same document type among different users, this invention introduces a calculation model for a document access demand assessment factor to further evaluate the overall access demand level of various documents during future peak hours. This factor comprehensively considers the matching degree of all user pairs under the same document type, and reflects the relative demand intensity of a certain document type during peak hours by comparing its ratio with the average matching level of all document types. For example, in the intelligent document management system of a power agency, the system manages four types of documents: "Official Travel Permit," "Confidential Document Pass," "Meeting Access Permit," and "Vehicle Use Permit." Through historical usage data analysis, the total peak-hour matching coefficients for each document type among all user pairs are calculated as follows: Official Travel Permit... The confidential information pass corresponds to The meeting access pass corresponds to = The vehicle use certificate corresponds to Based on the above data, the average matching coefficient between users for all document types was calculated as: (2.84 + 1.12 + 1.96 + 0.98) / 4 = 1.725. Subsequently, the access demand assessment factor for each document type was calculated: Official Travel Permit: =2.84 / 1.725≈1.65; Confidential Document Access Pass: =1.12 / 1.725≈0.65; Conference access pass: =1.96 / 1.725≈1.14; Vehicle Use Certificate: =0.98 / 1.725≈0.57.

[0046] This shows that the access demand assessment factors for "Official Travel Pass" and "Meeting Access Pass" are both greater than 1, indicating that their access demand concentration during peak hours is significantly higher than the average level, classifying them as high-demand passes. Conversely, the assessment factors for "Confidential Document Pass" and "Vehicle Use Pass" are less than 1, indicating that their usage is more dispersed during peak hours, classifying them as low-demand passes. Based on these analysis results, in subsequent resource allocation and scheduling, "Official Travel Pass" and "Meeting Access Pass" are automatically allocated to smart kiosks near main channels or high-traffic areas. More identity verification terminals and auxiliary channel resources are also configured during the corresponding time periods to improve access efficiency and reduce queuing time during peak hours. Low-demand passes can be placed in peripheral kiosks or shared areas to improve the overall utilization rate of kiosks and service responsiveness. This method enables dynamic optimization of kiosks, not only improving access efficiency during peak hours but also balancing the overall distribution of kiosks, forming an intelligent kiosks management system driven by actual behavioral data.

[0047] Preferably, counter space resources are allocated and document locations are optimized based on assessment factors of document access needs, while the distribution of identity verification terminals and channels is adjusted to reduce queuing and waiting times during peak periods.

[0048] In embodiments of the present invention, based on the aforementioned calculation of the access demand assessment factor for document type i during peak hours, the counter space resources for document type i are dynamically allocated and their locations optimized. Specifically, when the access demand assessment factor value for a certain document type is significantly higher than the average level, it is determined that the access demand for that document is high during future peak hours. This type of document is then prioritized for allocation to fast-access counters near main entrances / exits or high-frequency channels to shorten the walking distance and operation time for users to retrieve and return their documents. For documents with access demand assessment factors that are not in high demand, they are adjusted to relatively secondary or backup counters to improve the overall space utilization of the counters.

[0049] Meanwhile, during the allocation of counter space resources, the distribution of user identity verification terminals and channel resources in real time will be taken into account to dynamically adjust the identity verification terminals. For example, when multiple high-demand documents are concentrated in a certain area, more identity verification terminals will be automatically added or activated in that area to share the verification load during peak periods and prevent users from having to wait in long queues.

[0050] Furthermore, based on counter layout and channel traffic data, the opening strategies for document retrieval and return channels are dynamically adjusted. When potential congestion risks are predicted for a specific channel during a certain period, backup channels can be opened in advance or some less frequently used documents can be temporarily moved to vacant areas, achieving coordinated optimization of counter and channel resources. Through this optimization process, while ensuring the secure management of documents, user waiting and queuing times during peak hours can be significantly reduced, improving document retrieval efficiency and resource utilization.

[0051] Preferably, the predicted access demand assessment factor for identification documents is compared with the actual access demand assessment factor for identification documents in real time. Deviation analysis is used to adaptively correct the prediction model, thereby continuously improving the accuracy of peak-hour and identification document demand predictions. Specifically, to ensure the long-term reliability and dynamic adaptability of identification document access demand prediction results, this embodiment of the invention introduces a prediction-actual deviation analysis and model adaptive correction mechanism during operation. Specifically, in the prediction stage, the predicted access demand assessment factor is calculated based on the historical peak-hour matching coefficient and the dynamic distribution of identification document types. In actual operation, the actual access behavior data of identification documents is monitored in real time to calculate the actual access demand assessment factor. Subsequently, the system compares the two to obtain the prediction deviation, which is used as the basis for model correction.

[0052] For example, in the intelligent certificate management system of power institutions, the model predicted the demand assessment factor for "official travel permits" to be 1.65 during the morning peak hours (8:00–9:10), while the actual monitored value was 1.42, resulting in a prediction deviation of 0.23. When the system detected that this deviation exceeded the preset threshold of 0.15, it automatically activated the adaptive correction module. This module adjusts the ratio of the peak matching coefficient weight parameters ω1 and ω2 based on the average deviation and trend of the same time period over the past three days. For example, it increases ω1 from 0.6 to 0.7 to enhance the model's sensitivity to the overlap of continuous peak periods, thereby correcting the weight allocation of time-period matching features in the future prediction model.

[0053] Meanwhile, for deviations that remain stable within a low range, the model parameters are kept unchanged, and only the deviation trend is recorded for long-term evaluation of subsequent model fitting. Through a week of continuous data accumulation, the prediction model gradually converged, reducing the overall prediction deviation rate from the initial 12.4% to 4.6%, significantly improving the accuracy of peak-hour and document demand predictions. Finally, based on the corrected model, dynamic optimization predictions are implemented: before the daily morning and evening peak hours, the system can predict potential high-demand periods for various documents, automatically allocate identity verification terminals and document retrieval channels, and flexibly adjust the number of open counters according to the predicted demand intensity, thereby effectively reducing queuing time and resource waste, ensuring the efficient and stable operation of the document storage and retrieval system.

[0054] A document storage and retrieval system includes a data acquisition module, a behavior feature analysis module, a time-series peak identification module, a demand prediction and assessment module, a resource optimization and allocation module, and an adaptive model correction module. The data acquisition module is connected to the behavior feature analysis module, the behavior feature analysis module is connected to the time-series peak identification module, the time-series peak identification module is connected to the demand prediction and assessment module, the demand prediction and assessment module is connected to the resource optimization and allocation module, and the resource optimization and allocation module is connected to the adaptive model correction module.

[0055] The data acquisition module is used to collect multi-dimensional access data of document storage and retrieval in real time through intelligent storage cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document storage and retrieval operation. The behavioral feature analysis module is used to extract features from the collected historical multidimensional access data and historical access auxiliary data, construct a user behavior feature set, and detect and analyze the user's document access operation coefficient based on the user behavior feature set. The time-series peak identification module is used to perform time-series analysis, aggregate user document access operation coefficients by time period, and detect anomalies to dynamically identify potential peak periods for document access. The demand forecasting and assessment module is used to predict the demand assessment factors for document access within a fixed period in the future based on the user's document access purpose and potential peak periods. Based on the document access demand assessment factors, the module allocates counter resources and optimizes document locations, while adjusting the distribution of identity verification terminals and channel resources to reduce queuing and waiting time during peak periods. The resource optimization and allocation module is used to compare the predicted access demand assessment factors of documents with the actual access demand assessment factors of documents in real time. Through deviation analysis, the prediction model is adaptively corrected, thereby continuously improving the accuracy of the prediction of the number of documents needed during peak periods. The adaptive model correction module is used to collect multi-dimensional access data of document access in real time through smart access cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document access operation.

[0056] like Figure 2 The diagram shown is a system block diagram of a document storage and retrieval system according to an embodiment of the present invention, which can be used to execute... Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0057] A terminal device includes a memory and a processor. The memory stores a computer program. When the processor runs the computer program stored in the memory, the processor executes the steps of a document access method, system, terminal device, and readable storage medium as described in any of the preceding claims. The terminal device includes: a processor, a memory, and a computer program; wherein... A memory is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0058] The processor is used to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0059] Alternatively, the memory can be either standalone or integrated with the processor.

[0060] When the memory is a device independent of the processor, the device may further include: A bus is used to connect the memory and the processor.

[0061] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of a document access method as described in any of the above claims.

[0062] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0063] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0064] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0065] Through the above embodiments, this invention utilizes the collaborative operation of intelligent access cabinets, identity recognition terminals, and a back-end management platform to collect multi-dimensional data and auxiliary information on document access in real time. It extracts user behavior characteristics to construct an operational feature model and dynamically identifies peak periods for document access based on time series analysis. Furthermore, by combining the user's document access purpose, it predicts the access needs of various documents within a fixed future time period. Based on the prediction results, it intelligently allocates cabinet resources, optimizes document placement, and dynamically adjusts the configuration of identity verification terminals and channel resources, thereby effectively alleviating queuing and waiting during peak periods. Simultaneously, by comparing predicted and actual values ​​in real time, it performs deviation analysis and adaptive model correction, achieving continuous model optimization and accuracy improvement. This not only improves the operational efficiency and user experience of the document access system but also realizes intelligent control and dynamic optimal resource allocation during peak periods. This invention can intelligently sense and predict peak periods, dynamically optimize resource allocation, effectively alleviate queuing, improve document access efficiency, and continuously improve prediction accuracy through an adaptive model, achieving efficient, intelligent, and self-optimizing management.

[0066] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0067] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for storing and retrieving identification documents, characterized in that, Includes the following steps: Through intelligent storage lockers, identity recognition terminals and back-end management platforms, multi-dimensional storage and retrieval data of documents are collected in real time, and auxiliary data of document storage and retrieval are recorded during the document storage and retrieval operation. Feature extraction is performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set. Based on the user behavior feature set, the user document access operation coefficient is detected and analyzed. Based on time series analysis, the coefficients of user document access operations are aggregated by time period and anomaly detected to dynamically identify potential peak periods for document access. Based on the user's purpose of accessing documents and the assessment factors for document access demand during potential peak periods, counter resources are allocated and document locations are optimized according to the document access demand assessment factors. At the same time, the distribution of identity verification terminals and channel resources is adjusted to reduce queuing and waiting time during peak periods. The prediction model is adaptively corrected by comparing the predicted access demand assessment factors of the documents with the actual access demand assessment factors of the documents in real time and through deviation analysis.

2. The document storage and retrieval method according to claim 1, characterized in that, Multidimensional access data includes document type, document collection time, document return time, and access frequency; access auxiliary data includes the number of times the cabinet door is opened, user identity information, purpose of document access, and waiting time.

3. The document storage and retrieval method according to claim 1, characterized in that, Feature extraction is performed on the collected historical multidimensional access data and historical access auxiliary data to construct a user behavior feature set. Based on the user behavior feature set, the user's document access operation coefficient is detected and analyzed. The specific steps are as follows: The system obtains the document collection time, return time, and access frequency corresponding to the document type from the user's historical multidimensional access data. Based on the document collection time and return time, it determines the operation duration of the target document. The system obtains the first behavioral feature based on the operation duration of the target document corresponding to the document type and the second behavioral feature based on the access frequency corresponding to the document type. Obtain the number of times the cabinet door is opened and the waiting time corresponding to the document type from the historical access auxiliary data. Obtain the third behavioral feature based on the number of times the cabinet door is opened according to the document type, and obtain the fourth behavioral feature based on the waiting time corresponding to the document type. A user behavior feature set is constructed based on the first behavior feature, the second behavior feature, the third behavior feature, and the fourth behavior feature. The user document access operation coefficient corresponding to the document type is predicted based on the user behavior feature set. Get the user document access operation coefficients corresponding to all types of user documents.

4. The document storage and retrieval method according to claim 1, characterized in that, Based on time series analysis, the coefficients of user document access operations are aggregated by time period and anomaly detected to dynamically identify potential peak periods for document access. The specific steps are as follows: Extract the user document access operation coefficients corresponding to the i-th document type, and construct the access operation time series by sorting them by time. ,in, For the first Each time sampling point, The time sampling length, Time sampling point The corresponding user document access operation coefficient, Time sampling point The corresponding user document access operation coefficient; The access operation time series are aggregated according to a preset time window, and the average value within each time window is calculated as the volatility assessment factor. Anomaly detection is performed based on volatility assessment factors to identify time windows with volatility exceeding the normal range as potential peak periods. The detected potential peak periods are clustered and their continuity is determined. If several potential peak periods exist, they are merged into a continuous peak interval. Based on the peak period distribution of different document types, a dynamic peak identification result set is generated. ,in, This represents the continuous peak interval corresponding to the i-th document type. The purpose of accessing user credentials for the i-th type of credential.

5. A method for storing and retrieving identification documents according to claim 4, characterized in that, Identify time windows that exceed the normal fluctuation range as potential peak periods. The specific identification criteria are: if the following conditions are met... If the j-th time window is considered a potential peak period, then... Let be the volatility assessment factor for the j-th time window. This is the average of the historical user document access operation coefficients. This is an adjustable sensitivity parameter. The standard deviation of the historical user document access operation coefficients.

6. The document storage and retrieval method according to claim 1, characterized in that, The assessment factors for predicting the demand for document access during future fixed periods based on the user's purpose of document access and potential peak periods are as follows: Extract historical dynamic peak identification result sets of different users, and perform document access peak matching analysis based on the historical dynamic peak identification result sets to obtain the peak time matching coefficient of the same document type among different users. The assessment factor for the demand for document access during peak hours is predicted based on the matching coefficient during peak hours and the type of document.

7. A method for storing and retrieving identification documents according to claim 6, characterized in that, The formula for calculating the peak-hour matching coefficient for the same document type i is: ； ； In the formula: Let i be the peak-hour matching coefficient for document type i. The similarity weighting coefficient is used for the continuous peak interval. The similarity weighting coefficient for the purpose of accessing user credentials. For user u, the continuous peak interval corresponding to the i-th type of identification document. For user v, the continuous peak interval corresponding to the i-th type of identification document. For user u, the purpose of accessing the user's ID document corresponding to the i-th ID document type is... The purpose of accessing user ID documents for user v with the i-th type of ID document.

8. A document storage and retrieval system, applied to a document storage and retrieval method as described in any one of claims 1-7, characterized in that, The system includes a data acquisition module, a behavioral feature analysis module, a time-series peak identification module, a demand prediction and evaluation module, a resource optimization and allocation module, and an adaptive model correction module. The data acquisition module is used to collect multi-dimensional access data of document storage and retrieval in real time through intelligent storage cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document storage and retrieval operation. The behavioral feature analysis module is used to extract features from the collected historical multidimensional access data and historical access auxiliary data, construct a user behavior feature set, and detect and analyze the user's document access operation coefficient based on the user behavior feature set. The time-series peak identification module is used to perform time-series analysis, aggregate user document access operation coefficients by time period, and detect anomalies to dynamically identify potential peak periods for document access. The demand forecasting and assessment module is used to predict the demand assessment factors for document access within a fixed period in the future based on the user's document access purpose and potential peak periods. Based on the document access demand assessment factors, the module allocates counter resources and optimizes document locations, while adjusting the distribution of identity verification terminals and channel resources to reduce queuing and waiting time during peak periods. The resource optimization and allocation module is used to compare the predicted access demand assessment factors of documents with the actual access demand assessment factors of documents in real time. Through deviation analysis, the prediction model is adaptively corrected, thereby continuously improving the accuracy of the prediction of the number of documents needed during peak periods. The adaptive model correction module is used to collect multi-dimensional access data of document access in real time through smart access cabinets, identity recognition terminals and back-end management platforms, and at the same time record access auxiliary data during the document access operation.

9. A terminal device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor runs the computer program stored in the memory, the processor performs the steps of a document retrieval method as described in any one of claims 1-7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the steps of a document access method as described in any one of claims 1-7.

Images