Intelligent file cabinet safe unlocking management system based on multivariate data fusion

Abstract

The invention relates to the technical field of unlocking management, in particular to an intelligent file cabinet safety unlocking management system based on multivariate data fusion, which comprises a safety management platform, a lock control information unit, a dynamic evaluation unit, an image self-checking unit, a network interference unit, a lock control safety unit and a management response unit, on the premise that the unlocking efficiency is qualified, analysis is carried out from the two aspects of the file cabinet lock and the file cabinet lock network, so that the unlocking safety of the file cabinet lock is improved, and on the premise that the file cabinet lock operates normally, safety supervision is carried out on the condition of the file cabinet lock collecting end, and the safety of the file cabinet lock collecting end is improved. Interference of a file cabinet lock acquisition end on unlocking of the file cabinet lock is avoided, analysis is carried out from the perspective of the file cabinet lock network to reduce the abnormal risk rate of the file cabinet lock network, and on the premise that the file cabinet lock and the file cabinet lock network are normal, the actual unlocking condition of the file cabinet lock is known, so that the user experience is improved. Meanwhile, according to the following unlocking condition, unlocking risk prediction is carried out, so that optimization processing is carried out in advance according to the information feedback condition.

Description

Technical Field

[0001] The present invention relates to the technical field of unlocking management, and in particular to an intelligent filing cabinet security unlocking management system based on multivariate data fusion. Background Art

[0002] With the rapid development of digital archives in my country, new and higher requirements have been put forward for the management systems of archives (rooms) at all levels and of all types. In particular, how to integrate archive protection work with the establishment of digital archives is still a new topic to be studied.

[0003] However, in the prior art, it is impossible to supervise and analyze the historical unlocking of the filing cabinet lock, and thus it is impossible to optimize and adjust the filing cabinet lock, which is not conducive to the stable unlocking of the filing cabinet lock and reduces the unlocking efficiency of the filing cabinet lock. In addition, the identification and network of the filing cabinet lock are securely supervised, thereby reducing the unlocking security and unlocking efficiency of the filing cabinet lock, and it is impossible to understand the actual unlocking situation of the filing cabinet lock, which is not conducive to the rational management of the filing cabinet lock.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent filing cabinet security unlocking management system based on multivariate data fusion to solve the above-mentioned technical defects. The present invention analyzes from the perspective of historical information to understand the unlocking efficiency of the filing cabinet lock. On the premise that the unlocking efficiency is qualified, the security of the filing cabinet lock unlocking is improved by analyzing from two perspectives: the filing cabinet lock itself and the filing cabinet lock network. On the premise that the filing cabinet lock itself operates normally, the situation of the filing cabinet lock collection end is safely supervised to avoid the filing cabinet lock collection end from interfering with the unlocking of the filing cabinet lock. The analysis is performed from the perspective of the filing cabinet lock network to reduce the abnormal risk rate of the filing cabinet lock network, which helps to improve the unlocking security and stability of the filing cabinet lock. On the premise that the filing cabinet lock itself and the filing cabinet lock network are normal, the unlocking real-time data is trend-forecasted and supervised to understand the actual unlocking situation of the filing cabinet lock. At the same time, the unlocking risk is predicted according to the next unlocking situation, so as to optimize the processing in advance according to the information feedback situation, so as to improve the overall unlocking security and stability of the filing cabinet lock, and improve the efficiency of unlocking the filing cabinet lock.

[0006] The object of the present invention can be achieved by the following technical solutions: an intelligent filing cabinet security unlocking management system based on multivariate data fusion, comprising a security management platform, a lock control information unit, a dynamic evaluation unit, an image self-checking unit, a network interference unit, a lock control security unit and a management response unit;

[0007] The lock control information unit is used to collect historical data of the filing cabinet lock, the historical data including historical unlocking times and historical parts replacement information, and send the historical data to the dynamic evaluation unit;

[0008] After receiving the historical data, the dynamic evaluation unit immediately performs unlocking efficiency supervision evaluation and analysis on the historical data, sends the obtained qualified signal to the image self-check unit and the network interference unit, and sends the obtained unqualified signal to the management response unit;

[0009] After receiving the qualified signal, the image self-inspection unit immediately collects the unlocking interference data of the filing cabinet lock, the unlocking interference data includes the state assessment coefficient and the zoom control value, and performs unlocking interference risk supervision analysis on the unlocking interference data, sends the obtained control signal and interference signal to the management response unit, and sends the obtained valid signal to the lock control safety unit;

[0010] After receiving the qualified signal, the network interference unit immediately collects the identification obstruction data of the filing cabinet lock network, the identification obstruction data represents the safety assessment coefficient, and performs unlocking identification obstruction supervision assessment analysis on the identification obstruction data, sends the obtained stable signal to the lock control safety unit, and sends the obtained risk signal to the management response unit;

[0011] After receiving the valid signal and the stable signal, the lock control security unit immediately records the real-time unlocking data of the cabinet lock, which includes the actual portrait recognition time and the actual number of portrait recognitions. It also performs trend prediction and supervision analysis on the real-time unlocking data and sends the obtained management signal to the management response unit.

[0012] Preferably, the unlocking efficiency supervision evaluation and analysis process of the dynamic evaluation unit is as follows:

[0013] S1: Set the monitoring cycle and set it as the time threshold, obtain the time from the end time of the most recent portrait update to the current time within the time threshold, and set it as the operation time, obtain the historical unlocking times of the filing cabinet lock within the operation time, and then obtain the portrait recognition time and the single unlocking repetition times corresponding to each historical unlocking time. The portrait recognition time represents the time from the start time of portrait collection to the successful portrait authentication time. Take the number as the X-axis, and the portrait recognition time and the single unlocking repetition times as the Y-axis to establish a rectangular coordinate system, draw the portrait recognition time curve and the single unlocking repetition times curve by drawing points, obtain the change trend value of the portrait recognition time curve and the change trend value of the single unlocking repetition times curve, and set them as the recognition disturbance magnification and the unlocking obstruction magnification respectively;

[0014] S2: Obtain the historical parts replacement information of the filing cabinet lock within the time threshold. The parts replacement information includes the number of parts replacements and the compatible risk value. The compatible risk value represents the ratio between the number of times the replaced parts are not brand new and the number of times the replaced parts are brand new. The brand new state means that the newly replaced parts have never been used, and the non-brand new state means that the newly replaced parts have been used more than twice. The product value obtained by normalizing the number of parts replacements and the compatible risk value is set as the compatible interference value. The identification interference ratio, the unlocking obstruction ratio and the compatible interference value are labeled SR, KZ and JG respectively.

[0015] S3: The dynamic change interference coefficient G is obtained according to the formula, and the dynamic change interference coefficient G is compared and analyzed with the preset dynamic change interference coefficient threshold value recorded and stored internally:

[0016] If the ratio between the dynamically changing interference coefficient G and the preset dynamically changing interference coefficient threshold is less than 1, a qualified signal is generated;

[0017] If the ratio between the dynamically changing interference coefficient G and the preset dynamically changing interference coefficient threshold is greater than or equal to 1, a failure signal is generated.

[0018] Preferably, the unlocking interference risk supervision and analysis process of the image self-check unit is as follows:

[0019] The time threshold is divided into i sub-time periods, where i is a natural number greater than zero, and the state evaluation coefficient of the filing cabinet lock in each sub-time period is obtained. The state evaluation coefficient represents the ratio of the number of times the operating temperature of the filing cabinet lock exceeds the preset operating temperature threshold to the average of the interval duration after data normalization, and then the product value obtained by normalizing the data with the number of interference times. The number of interference times is analyzed as follows: the duration corresponding to the number of times the operating temperature exceeds the preset operating temperature threshold, the number of times the duration exceeds the preset threshold is set as the number of interferences, and a set A of state evaluation coefficients is constructed, the discrete coefficient of set A is obtained, and the discrete coefficient of set A is set as the state discrete value;

[0020] Compare and analyze the state discrete value with the preset state discrete value threshold value stored in the internal storage:

[0021] If the ratio between the state discrete value and the preset state discrete value threshold is greater than or equal to 1, a control signal is generated;

[0022] If the ratio between the state discrete value and the preset state discrete value threshold is less than 1, a feedback instruction is generated.

[0023] Preferably, when the image self-checking unit generates a feedback instruction:

[0024] T1: Obtain the zoom control value of the filing cabinet lock portrait collection end within the time threshold. The zoom control value represents the product of the proportion of incorrect zoom times and the proportion of delayed zoom control times in the total number of historical zoom times after data normalization processing;

[0025] T2: Obtain the interference assessment value of the filing cabinet lock portrait collection end within the time threshold. The interference assessment value indicates the duration of time that the value corresponding to the environmental interference parameter exceeds the preset threshold, and the product value obtained after data normalization processing of the volume change trend value of the dust particles on the collection end mirror within the duration. The environmental interference parameters include the environmental humidity value and the environmental dust concentration value;

[0026] T3: Compare and analyze the zoom control value and the interference assessment value with the preset zoom control value threshold and the preset interference assessment value threshold stored in the internal storage:

[0027] If the zoom control value is less than the preset zoom control value threshold, and the interference assessment value is less than the preset interference assessment value threshold, a valid signal is generated;

[0028] If the zoom control value is greater than or equal to a preset zoom control value threshold, or the interference evaluation value is greater than or equal to a preset interference evaluation value threshold, an interference signal is generated.

[0029] Preferably, the unlocking identification and obstruction supervision assessment analysis process of the network interference unit is as follows:

[0030] The security assessment coefficient of the filing cabinet lock network in each sub-time period is obtained. The security assessment coefficient represents the product of the number of disconnections and the disconnection ratio of the filing cabinet lock network after data normalization. The number of disconnections represents the sum of the number of network interruptions and the number of connections. The disconnection ratio represents the ratio of the number of network interruptions whose interval duration is less than the preset threshold. A rectangular coordinate system is established with the number of sub-time periods as the X-axis and the security assessment coefficient as the Y-axis. A security assessment coefficient curve is drawn by plotting points. The security assessment coefficient value AQ1 corresponding to the security assessment coefficient curve is collected once every t1 time period, the security assessment coefficient value AQ2 corresponding to the security assessment coefficient curve is collected once every t2 time period, and the security assessment coefficient value AQg corresponding to the security assessment coefficient curve is collected once every tg time period, where g is a natural number greater than zero. A set of security assessment coefficient values ​​AQ1…AQg is constructed, and the discrete coefficients of each set are obtained, and are set as security floating coefficients AF1…AFg.

[0031] The safety floating coefficient AF1…AFg is compared and analyzed with the preset safety floating coefficient threshold stored, and the proportion of the number of safety floating coefficients AF1…AFg that are greater than the preset safety floating coefficient threshold is set as the fluctuation proportion, and the fluctuation proportion is compared and analyzed with the preset fluctuation proportion threshold stored internally:

[0032] If the ratio between the volatility ratio and the preset volatility ratio threshold is less than 1, a stable signal is generated;

[0033] If the ratio of the volatility ratio to the preset volatility ratio threshold is greater than or equal to 1, a risk signal is generated.

[0034] Preferably, the trend prediction supervision and analysis process of the lock control safety unit is as follows:

[0035] The actual portrait recognition duration of the filing cabinet lock within the time threshold is obtained, and the actual number of portrait recognitions of the filing cabinet lock within the time threshold is obtained, as well as the actual network rate average of the filing cabinet lock network within the time threshold. The product value obtained after data normalization of the actual portrait recognition duration, the actual number of portrait recognitions and the actual network rate average is set as the actual evaluation coefficient, and the actual evaluation coefficient is compared and analyzed with the preset actual evaluation coefficient threshold value recorded and stored internally:

[0036] If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is less than 1, no signal is generated;

[0037] If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is greater than or equal to 1, a dynamic supervision instruction is generated.

[0038] Preferably, when the lock control safety unit generates a dynamic supervision instruction:

[0039] Get the actual evaluation coefficient Kj of the filing cabinet lock within the next j time thresholds, where j is a natural number greater than zero, and get the proportion of the actual evaluation coefficient Kj within the j time thresholds that is greater than or equal to the time threshold corresponding to the preset actual evaluation coefficient threshold, and set it as the optimization demand coefficient, and compare and analyze the optimization demand coefficient with the preset optimization demand coefficient threshold stored in the internal entry:

[0040] If the ratio between the optimized demand factor and the preset optimized demand factor threshold is less than 1, no signal is generated;

[0041] If the ratio between the optimized demand coefficient and the preset optimized demand coefficient threshold is greater than or equal to 1, a management signal is generated.

[0042] The beneficial effects of the present invention are as follows:

[0043] (1) The present invention analyzes from the perspective of historical information to understand the unlocking efficiency of the filing cabinet lock, so as to remind the management personnel to update the filing cabinet lock in time according to the information feedback, so as to improve the recognition efficiency and unlocking stability of the filing cabinet lock. At the same time, under the premise of qualified unlocking efficiency, the present invention analyzes from the perspectives of the filing cabinet lock itself and the filing cabinet lock network to improve the security of the filing cabinet lock unlocking, and analyzes the operation of the filing cabinet lock itself to provide data support for subsequent analysis, that is, under the premise of normal operation of the filing cabinet lock itself, the situation of the filing cabinet lock collection end is safely supervised to avoid interference of the filing cabinet lock collection end with the unlocking of the filing cabinet lock;

[0044] (2) The present invention analyzes from the perspective of the filing cabinet lock network, that is, performs unlocking identification obstacle supervision and assessment analysis on the identification obstacle data to determine whether the filing cabinet lock network risk is too high, so as to make reasonable network security adjustments based on information feedback to reduce the abnormal risk rate of the filing cabinet lock network, and at the same time help to improve the unlocking security and stability of the filing cabinet lock. On the premise that the filing cabinet lock itself and the filing cabinet lock network are normal, the unlocking real-time data is subjected to trend prediction supervision and analysis to understand the actual unlocking situation of the filing cabinet lock, and at the same time, the unlocking risk is predicted based on the next unlocking situation, so as to perform advance optimization processing based on the information feedback, so as to improve the overall unlocking security and stability of the filing cabinet lock, and to improve the efficiency of unlocking the filing cabinet lock. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further described below in conjunction with the accompanying drawings;

[0046] Figure 1 It is a flowchart of the system of the present invention;

[0047] Figure 2 It is a partial reference diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Embodiment 1:

[0050] See also Figure 1 to Figure 2As shown, the present invention is an intelligent filing cabinet security unlocking management system based on multivariate data fusion, including a security management platform, a lock control information unit, a dynamic evaluation unit, an image self-checking unit, a network interference unit, a lock control security unit and a management response unit, the security management platform is connected to the lock control information unit in a one-way communication, the lock control information unit is connected to the dynamic evaluation unit in a one-way communication, the dynamic evaluation unit is connected to the image self-checking unit, the network interference unit and the management response unit in a one-way communication, the image self-checking unit and the network interference unit are connected to the lock control security unit and the management response unit in a one-way communication, and the lock control security unit is connected to the management response unit in a one-way communication;

[0051] When the security management platform generates an operation and management instruction, it sends the operation and management instruction to the lock control information unit. After receiving the operation and management instruction, the lock control information unit immediately collects the historical data of the filing cabinet lock, which includes the historical unlocking times and historical parts replacement information, and sends the historical data to the dynamic evaluation unit. After receiving the historical data, the dynamic evaluation unit immediately performs unlocking efficiency supervision, evaluation and analysis on the historical data to determine whether the unlocking efficiency of the filing cabinet lock is qualified, so as to timely perform unlocking optimization and adjustment to improve the unlocking efficiency and stability of the filing cabinet lock. The specific unlocking efficiency supervision, evaluation and analysis process is as follows:

[0052] Set a monitoring cycle and set it as a time threshold, obtain the time from the end time of the most recent portrait update to the current time within the time threshold, and set it as the operation time, obtain the historical unlocking times of the filing cabinet lock within the operation time, and then obtain the portrait recognition time and the single unlocking repetition times corresponding to each historical unlocking time. The portrait recognition time represents the time from the start of portrait collection to the successful portrait authentication time. Take the number of times as the X-axis, and the portrait recognition time and the single unlocking repetition times as the Y-axis to establish a rectangular coordinate system. Draw the portrait recognition time curve and the single unlocking repetition times curve by drawing points, obtain the change trend value of the portrait recognition time curve and the change trend value of the single unlocking repetition times curve, and set them as the recognition disturbance magnification and the unlocking obstruction magnification respectively. It should be noted that the recognition disturbance magnification and the unlocking obstruction magnification are two parameters affecting the efficiency of portrait recognition;

[0053] The historical parts replacement information of the filing cabinet lock within the time threshold is obtained. The parts replacement information includes the number of parts replacements and the compatible risk value. The compatible risk value indicates the ratio between the number of times the replaced parts are not brand new and the number of times the replaced parts are brand new. The brand new state indicates that the newly replaced parts have never been used, and the non-brand new state indicates that the newly replaced parts have been used more than 2 times. The product value obtained by normalizing the number of parts replacements and the compatible risk value is set as the compatible interference value. It should be noted that the larger the value of the compatible interference value, the higher the risk of abnormal operation of the filing cabinet lock. The identification interference ratio, the unlocking obstruction ratio and the compatible interference value are labeled SR, KZ and JG respectively.

[0054] According to the formula The dynamically changing interference coefficient is obtained, wherein a1, a2 and a3 are preset proportional factor coefficients for identifying the disturbance magnification, unlocking obstruction magnification and compatible interference value respectively, and a4 is a preset correction factor coefficient. The proportional factor coefficient is used to correct the deviation of various parameters in the formula calculation process, so as to make the calculation result more accurate. a1, a2, a3 and a4 are all greater than zero, and G is the dynamically changing interference coefficient. The dynamically changing interference coefficient G is compared and analyzed with the preset dynamically changing interference coefficient threshold value stored in the internal input:

[0055] If the ratio between the dynamic change interference coefficient G and the preset dynamic change interference coefficient threshold is less than 1, a qualified signal is generated and sent to the image self-checking unit and the network interference unit;

[0056] If the ratio between the dynamic change interference coefficient G and the preset dynamic change interference coefficient threshold is greater than or equal to 1, an unqualified signal is generated and sent to the management response unit. After receiving the unqualified signal, the management response unit immediately displays the preset warning text corresponding to the unqualified signal to remind the management personnel to update the file cabinet lock in time to improve the recognition efficiency and recognition stability of the file cabinet lock;

[0057] After receiving the qualified signal, the image self-inspection unit immediately collects the unlocking interference data of the filing cabinet lock. The unlocking interference data includes the state evaluation coefficient and the zoom control value, and performs unlocking interference risk supervision analysis on the unlocking interference data to determine whether the operating state of the filing cabinet lock is normal and whether the abnormal collection risk of the collection end is too high, so as to provide timely early warning feedback management, so as to remind the management personnel to manage the filing cabinet lock in time, so as to improve the operating stability of the filing cabinet lock. The specific unlocking interference risk supervision analysis process is as follows:

[0058] The time threshold is divided into i sub-time periods, where i is a natural number greater than zero, and the state evaluation coefficient of the filing cabinet lock in each sub-time period is obtained. The state evaluation coefficient represents the ratio of the number of times the operating temperature of the filing cabinet lock exceeds the preset operating temperature threshold to the average of the interval duration after data normalization, and then the product value obtained by normalizing the data with the number of interferences. The number of interferences is analyzed as follows: the duration corresponding to the number of times the operating temperature exceeds the preset operating temperature threshold, the number of times the duration exceeds the preset threshold is set as the number of interferences, and a set A of state evaluation coefficients is constructed, and the discrete coefficient of set A is obtained, and the discrete coefficient of set A is set as the state discrete value. It should be noted that the larger the value of the state discrete value, the greater the risk of abnormal fluctuation in the operation of the filing cabinet lock;

[0059] Compare and analyze the state discrete value with the preset state discrete value threshold value stored in the internal storage:

[0060] If the ratio between the state discrete value and the preset state discrete value threshold is greater than or equal to 1, a control signal is generated and sent to the management response unit. After receiving the control signal, the management response unit immediately displays the preset warning text corresponding to the control signal to remind the management personnel to manage the file cabinet lock in time to improve the operation stability of the file cabinet lock;

[0061] If the ratio between the state discrete value and the preset state discrete value threshold is less than 1, a feedback instruction is generated. When the feedback instruction is generated, the zoom control value of the file cabinet lock portrait collection end within the time threshold is obtained. The zoom control value represents the product of the proportion of the number of wrong zooms in the total number of historical zooms and the proportion of the number of delayed zoom control times after data normalization. It should be noted that the larger the value of the zoom control value, the greater the risk of recognition obstruction at the file cabinet lock portrait collection end;

[0062] Obtain the interference assessment value of the file cabinet lock portrait collection end within the time threshold. The interference assessment value indicates the duration of time that the value corresponding to the environmental interference parameter exceeds the preset threshold, and the product value obtained after data normalization of the volume change trend value of the dust particles on the collection end mirror within the duration. The environmental interference parameters include the environmental humidity value, the environmental dust concentration value, etc. It should be noted that the larger the interference assessment value, the greater the risk of recognition obstruction of the file cabinet lock portrait collection end;

[0063] The zoom control value and the interference assessment value are compared and analyzed with the preset zoom control value threshold and the preset interference assessment value threshold stored in the internal storage:

[0064] If the zoom control value is less than the preset zoom control value threshold, and the interference assessment value is less than the preset interference assessment value threshold, a valid signal is generated and sent to the lock control safety unit;

[0065] If the zoom control value is greater than or equal to the preset zoom control value threshold, or the interference assessment value is greater than or equal to the preset interference assessment value threshold, an interference signal is generated and sent to the management response unit. After receiving the interference signal, the management response unit immediately displays the preset warning text corresponding to the interference signal to remind the management personnel to manage the file cabinet lock collection end in time to avoid the file cabinet lock collection end interfering with the unlocking of the file cabinet lock, so as to improve the efficiency of unlocking the file cabinet lock.

[0066] Embodiment 2:

[0067] After receiving the qualified signal, the network interference unit immediately collects the identification obstruction data of the filing cabinet lock network. The identification obstruction data represents the security assessment coefficient, and performs unlocking identification obstruction supervision assessment analysis on the identification obstruction data to determine whether the filing cabinet lock network risk is too high, so as to make reasonable network security adjustments based on information feedback to reduce the abnormal risk rate of the filing cabinet lock network, and at the same time help improve the unlocking security and stability of the filing cabinet lock. The specific unlocking identification obstruction supervision assessment analysis process is as follows:

[0068] The security assessment coefficient of the filing cabinet lock network in each sub-time period is obtained. The security assessment coefficient represents the product of the number of disconnections and the disconnection ratio of the filing cabinet lock network after data normalization. The number of disconnections represents the sum of the number of network interruptions and the number of connections. The disconnection ratio represents the ratio of the number of network interruptions whose interval duration is less than the preset threshold. A rectangular coordinate system is established with the number of sub-time periods as the X-axis and the security assessment coefficient as the Y-axis. The security assessment coefficient curve is drawn by plotting points. The security assessment coefficient value corresponding to the security assessment coefficient curve is collected every t1 time period. AQ1, collect the security assessment coefficient value AQ2 corresponding to the security assessment coefficient curve every t2 time, and so on, collect the security assessment coefficient value AQg corresponding to the security assessment coefficient curve every tg time, g is a natural number greater than zero, t1, t2...tg are not equal, and gradually increase, construct a set of security assessment coefficient values ​​AQ1...AQg, obtain the discrete coefficient of each set, and set it as the security floating coefficient AF1...AFg. It should be noted that the larger the value of the security floating coefficient, the greater the risk of abnormal stability performance of the filing cabinet lock network;

[0069] The safety floating coefficient AF1…AFg is compared and analyzed with the preset safety floating coefficient threshold stored, and the proportion of the number of safety floating coefficients AF1…AFg that are greater than the preset safety floating coefficient threshold is set as the fluctuation proportion, and the fluctuation proportion is compared and analyzed with the preset fluctuation proportion threshold stored internally:

[0070] If the ratio between the fluctuation ratio and the preset fluctuation ratio threshold is less than 1, a stable signal is generated and sent to the lock control safety unit;

[0071] If the ratio of the fluctuation ratio to the preset fluctuation ratio threshold is greater than or equal to 1, a risk signal is generated and sent to the management response unit. After receiving the risk signal, the management response unit immediately displays the preset warning text corresponding to the risk signal, so as to remind the management personnel to manage the file cabinet lock network in time, so as to avoid the file cabinet lock network from interfering with the unlocking of the file cabinet lock, so as to improve the efficiency of the unlocking of the file cabinet lock, and at the same time help to improve the unlocking security of the file cabinet lock;

[0072] After receiving the valid signal and the stable signal, the lock control security unit immediately files the real-time unlocking data of the cabinet lock, which includes the actual portrait recognition time and the actual number of portrait recognitions, and performs trend forecasting, supervision and analysis on the real-time unlocking data, so as to optimize the processing in advance according to the information feedback. The specific trend forecasting, supervision and analysis process is as follows:

[0073] The actual portrait recognition duration of the filing cabinet lock within the time threshold is obtained, and the actual number of portrait recognitions of the filing cabinet lock within the time threshold is obtained, as well as the actual network rate average of the filing cabinet lock network within the time threshold. The product value obtained after data normalization of the actual portrait recognition duration, the actual number of portrait recognitions and the actual network rate average is set as the actual evaluation coefficient, and the actual evaluation coefficient is compared and analyzed with the preset actual evaluation coefficient threshold value recorded and stored internally:

[0074] If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is less than 1, no signal is generated;

[0075] If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is greater than or equal to 1, a dynamic supervision instruction is generated. When the dynamic supervision instruction is generated, the actual evaluation coefficient Kj of the filing cabinet lock within the next j time thresholds is obtained, where j is a natural number greater than zero, and the proportion of the actual evaluation coefficient Kj within the j time thresholds that is greater than or equal to the preset actual evaluation coefficient threshold corresponding to the time threshold is obtained, and it is set as the optimization demand coefficient, and the optimization demand coefficient is compared and analyzed with the preset optimization demand coefficient threshold stored in the internal input:

[0076] If the ratio between the optimized demand factor and the preset optimized demand factor threshold is less than 1, no signal is generated;

[0077] If the ratio between the optimization demand coefficient and the preset optimization demand coefficient threshold is greater than or equal to 1, a management signal is generated and sent to the management response unit. After receiving the management signal, the management response unit immediately displays the preset warning text corresponding to the management signal, so as to remind the management personnel to optimize and adjust the overall filing cabinet lock in a timely manner, so as to improve the overall unlocking safety and stability of the filing cabinet lock, so as to improve the efficiency of unlocking the filing cabinet lock;

[0078] In summary, the present invention analyzes from the perspective of historical information to understand the unlocking efficiency of the filing cabinet lock, so as to remind the management personnel to update the filing cabinet lock in time according to the information feedback, so as to improve the recognition efficiency and unlocking stability of the filing cabinet lock. At the same time, under the premise of qualified unlocking efficiency, the security of the filing cabinet lock unlocking is improved by analyzing from two perspectives: the filing cabinet lock itself and the filing cabinet lock network, and the operation of the filing cabinet lock itself is analyzed to provide data support for subsequent analysis, that is, under the premise of normal operation of the filing cabinet lock itself, the situation of the filing cabinet lock collection end is safely supervised to avoid interference of the filing cabinet lock collection end with the unlocking of the filing cabinet lock, and from the filing cabinet lock network from the perspective of, that is, to conduct unlocking identification obstacle supervision assessment analysis on the identification obstacle data to determine whether the filing cabinet lock network risk is too high, so as to make reasonable network security adjustments based on information feedback to reduce the abnormal risk rate of the filing cabinet lock network, and at the same time help to improve the unlocking security and stability of the filing cabinet lock. On the premise that the filing cabinet lock itself and the filing cabinet lock network are normal, the unlocking real-time data is subjected to trend prediction supervision analysis to understand the actual situation of filing cabinet lock unlocking, and at the same time, the unlocking risk is predicted according to the next unlocking situation, so as to perform advance optimization processing according to the information feedback, so as to improve the overall unlocking security and stability of the filing cabinet lock, and to improve the efficiency of unlocking the filing cabinet lock.

[0079] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0080] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. Intelligent filing cabinet security unlocking management system based on multivariate data fusion, characterized by: It includes a security management platform, a lock control information unit, a dynamic evaluation unit, an image self-checking unit, a network interference unit, a lock control security unit and a management response unit; The lock control information unit is used to collect historical data of the filing cabinet lock, the historical data including historical unlocking times and historical parts replacement information, and send the historical data to the dynamic evaluation unit; After receiving the historical data, the dynamic evaluation unit immediately performs unlocking efficiency supervision evaluation and analysis on the historical data, sends the obtained qualified signal to the image self-check unit and the network interference unit, and sends the obtained unqualified signal to the management response unit; After receiving the qualified signal, the image self-inspection unit immediately collects the unlocking interference data of the filing cabinet lock, the unlocking interference data includes the state assessment coefficient and the zoom control value, and performs unlocking interference risk supervision analysis on the unlocking interference data, sends the obtained control signal and interference signal to the management response unit, and sends the obtained valid signal to the lock control safety unit; After receiving the qualified signal, the network interference unit immediately collects the identification obstruction data of the filing cabinet lock network, the identification obstruction data represents the safety assessment coefficient, and performs unlocking identification obstruction supervision assessment analysis on the identification obstruction data, sends the obtained stable signal to the lock control safety unit, and sends the obtained risk signal to the management response unit; After receiving the valid signal and the stable signal, the lock control security unit immediately records the real-time unlocking data of the cabinet lock, which includes the actual portrait recognition time and the actual number of portrait recognitions. It also performs trend prediction and supervision analysis on the real-time unlocking data and sends the obtained management signal to the management response unit.

2. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 1 is characterized in that: The unlocking efficiency supervision evaluation and analysis process of the dynamic evaluation unit is as follows: S1: Set the monitoring cycle and set it as the time threshold, obtain the time from the end time of the most recent portrait update to the current time within the time threshold, and set it as the operation time, obtain the historical unlocking times of the filing cabinet lock within the operation time, and then obtain the portrait recognition time and the single unlocking repetition times corresponding to each historical unlocking time. The portrait recognition time represents the time from the start time of portrait collection to the successful portrait authentication time. Take the number as the X-axis, and the portrait recognition time and the single unlocking repetition times as the Y-axis to establish a rectangular coordinate system, draw the portrait recognition time curve and the single unlocking repetition times curve by drawing points, obtain the change trend value of the portrait recognition time curve and the change trend value of the single unlocking repetition times curve, and set them as the recognition disturbance magnification and the unlocking obstruction magnification respectively; S2: Obtain the historical parts replacement information of the filing cabinet lock within the time threshold. The parts replacement information includes the number of parts replacements and the compatible risk value. The compatible risk value represents the ratio between the number of times the replaced parts are not brand new and the number of times the replaced parts are brand new. The brand new state means that the newly replaced parts have never been used, and the non-brand new state means that the newly replaced parts have been used more than twice. The product value obtained by normalizing the number of parts replacements and the compatible risk value is set as the compatible interference value. The identification interference ratio, the unlocking obstruction ratio and the compatible interference value are labeled SR, KZ and JG respectively. S3: The dynamic change interference coefficient G is obtained according to the formula, and the dynamic change interference coefficient G is compared and analyzed with the preset dynamic change interference coefficient threshold value recorded and stored internally: If the ratio between the dynamically changing interference coefficient G and the preset dynamically changing interference coefficient threshold is less than 1, a qualified signal is generated; If the ratio between the dynamically changing interference coefficient G and the preset dynamically changing interference coefficient threshold is greater than or equal to 1, a failure signal is generated.

3. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 1 is characterized in that: The unlocking interference risk supervision and analysis process of the image self-check unit is as follows: The time threshold is divided into i sub-time periods, where i is a natural number greater than zero, and the state evaluation coefficient of the filing cabinet lock in each sub-time period is obtained. The state evaluation coefficient represents the ratio of the number of times the operating temperature of the filing cabinet lock exceeds the preset operating temperature threshold to the average of the interval duration after data normalization, and then the product value obtained by normalizing the data with the number of interference times. The number of interference times is analyzed as follows: the duration corresponding to the number of times the operating temperature exceeds the preset operating temperature threshold, the number of times the duration exceeds the preset threshold is set as the number of interferences, and a set A of state evaluation coefficients is constructed, the discrete coefficient of set A is obtained, and the discrete coefficient of set A is set as the state discrete value; Compare and analyze the state discrete value with the preset state discrete value threshold value stored in the internal storage: If the ratio between the state discrete value and the preset state discrete value threshold is greater than or equal to 1, a control signal is generated; If the ratio between the state discrete value and the preset state discrete value threshold is less than 1, a feedback instruction is generated.

4. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 3 is characterized in that: When the image self-checking unit generates a feedback instruction: T1: Obtain the zoom control value of the filing cabinet lock portrait collection end within the time threshold. The zoom control value represents the product of the proportion of incorrect zoom times and the proportion of delayed zoom control times in the total number of historical zoom times after data normalization processing; T2: Obtain the interference assessment value of the filing cabinet lock portrait collection end within the time threshold. The interference assessment value indicates the duration of time that the value corresponding to the environmental interference parameter exceeds the preset threshold, and the product value obtained after data normalization processing of the volume change trend value of the dust particles on the collection end mirror within the duration. The environmental interference parameters include the environmental humidity value and the environmental dust concentration value; T3: Compare and analyze the zoom control value and the interference assessment value with the preset zoom control value threshold and the preset interference assessment value threshold stored in the internal storage: If the zoom control value is less than the preset zoom control value threshold, and the interference assessment value is less than the preset interference assessment value threshold, a valid signal is generated; If the zoom control value is greater than or equal to a preset zoom control value threshold, or the interference evaluation value is greater than or equal to a preset interference evaluation value threshold, an interference signal is generated.

5. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 1 is characterized in that: The unlocking identification and obstruction supervision assessment analysis process of the network interference unit is as follows: The security assessment coefficient of the filing cabinet lock network in each sub-time period is obtained. The security assessment coefficient represents the product of the number of disconnections and the disconnection ratio of the filing cabinet lock network after data normalization. The number of disconnections represents the sum of the number of network interruptions and the number of connections. The disconnection ratio represents the ratio of the number of network interruptions whose interval duration is less than the preset threshold. A rectangular coordinate system is established with the number of sub-time periods as the X-axis and the security assessment coefficient as the Y-axis. A security assessment coefficient curve is drawn by plotting points. The security assessment coefficient value AQ1 corresponding to the security assessment coefficient curve is collected once every t1 time period, the security assessment coefficient value AQ2 corresponding to the security assessment coefficient curve is collected once every t2 time period, and the security assessment coefficient value AQg corresponding to the security assessment coefficient curve is collected once every tg time period, where g is a natural number greater than zero. A set of security assessment coefficient values ​​AQ1…AQg is constructed, and the discrete coefficients of each set are obtained, and are set as security floating coefficients AF1…AFg. The safety floating coefficient AF1…AFg is compared and analyzed with the preset safety floating coefficient threshold stored, and the proportion of the number of safety floating coefficients AF1…AFg that are greater than the preset safety floating coefficient threshold is set as the fluctuation proportion, and the fluctuation proportion is compared and analyzed with the preset fluctuation proportion threshold stored internally: If the ratio between the volatility ratio and the preset volatility ratio threshold is less than 1, a stable signal is generated; If the ratio of the volatility ratio to the preset volatility ratio threshold is greater than or equal to 1, a risk signal is generated.

6. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 1 is characterized in that: The trend prediction supervision and analysis process of the lock control safety unit is as follows: The actual portrait recognition duration of the filing cabinet lock within the time threshold is obtained, and the actual number of portrait recognitions of the filing cabinet lock within the time threshold is obtained, as well as the actual network rate average of the filing cabinet lock network within the time threshold. The product value obtained after data normalization of the actual portrait recognition duration, the actual number of portrait recognitions and the actual network rate average is set as the actual evaluation coefficient, and the actual evaluation coefficient is compared and analyzed with the preset actual evaluation coefficient threshold value recorded and stored internally: If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is less than 1, no signal is generated; If the ratio between the actual evaluation coefficient and the preset actual evaluation coefficient threshold is greater than or equal to 1, a dynamic supervision instruction is generated.

7. The intelligent filing cabinet security unlocking management system based on multivariate data fusion according to claim 6 is characterized in that: When the lock control safety unit generates a dynamic supervision instruction: Get the actual evaluation coefficient Kj of the filing cabinet lock within the next j time thresholds, where j is a natural number greater than zero, and get the proportion of the actual evaluation coefficient Kj within the j time thresholds that is greater than or equal to the time threshold corresponding to the preset actual evaluation coefficient threshold, and set it as the optimization demand coefficient, and compare and analyze the optimization demand coefficient with the preset optimization demand coefficient threshold stored in the internal entry: If the ratio between the optimized demand factor and the preset optimized demand factor threshold is less than 1, no signal is generated; If the ratio between the optimized demand coefficient and the preset optimized demand coefficient threshold is greater than or equal to 1, a management signal is generated.

Images