Digital intelligent residential district security decision-making system and method based on end-side-cloud collaboration

Abstract

The invention relates to the technical field of security and protection monitoring, in particular to a digital intelligent residential area security and protection decision-making system and method based on end-edge-cloud collaboration, and the method specifically comprises the steps: collecting security and protection data and security and protection strategy data of edge equipment and a cloud server; calculating to obtain a security energy efficiency value and an equipment state influence value; constructing a security decision model, substituting the security energy efficiency value and the equipment state influence value into the security decision model, and calculating a security decision value of the digital intelligent residential area; and evaluating and optimizing the security policy of the digital intelligent residential area according to the calculated security decision value. The problem that in the prior art, security and protection data lacks an effective data integration means and comprehensive evaluation analysis, and consequently dynamic evaluation and optimization are difficult is solved.

Description

Technical Field

[0001] The present invention relates to the field of security monitoring technology, and is a digital intelligent residential security decision-making system and method based on end-edge-cloud collaboration. Background Art

[0002] In existing security systems, the data of various security devices and sensors are usually stored independently, and there is a lack of effective data integration and analysis methods, which makes it impossible to form a unified decision-making basis based on the data. In addition, existing security systems mainly rely on single sensor data or equipment status for risk assessment, and lack the integration and analysis of multi-dimensional data, making it difficult to comprehensively assess the overall risk of the security system. In addition, when evaluating the energy efficiency of security equipment, existing technologies often only consider the operating data of the equipment, ignoring important factors such as equipment failure rate, maintenance times, and false alarm rate, resulting in inaccurate energy efficiency assessment results. Summary of the invention

[0003] The technical problem to be solved by the present invention is that in the prior art, security data lacks effective data integration means and comprehensive evaluation and analysis, which makes dynamic evaluation and optimization difficult.

[0004] In order to achieve the above-mentioned object, the technical solution of the digital intelligent residential security decision-making method based on end-edge-cloud collaboration of the present invention includes the following steps:

[0005] S1: Collect security data of each terminal security device in the digital residential area, including: security device status, device operation data, and sensor data;

[0006] S2: Synchronously collect security strategy data of edge devices and cloud servers in the digital residential area, including: security equipment deployment strategy, security plan data, and security resource configuration data;

[0007] S3: Substitute the security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value;

[0008] S4: Substitute sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital residential area;

[0009] S5: Construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital residential area;

[0010] S6: Based on the calculated security decision value, the security strategy of the digital residential area is evaluated and optimized.

[0011] Specifically, S1 includes the following specific steps:

[0012] S11: Establish a dynamic management platform for security equipment to automatically discover new or removed security equipment and update the equipment list in real time;

[0013] S12: Collect security data of each terminal security device in the digital intelligent residential area, use machine learning algorithms to intelligently classify the security devices, automatically identify the types of security devices and the types of security data, and add metadata annotations for each data type, the metadata annotations include: timestamp, geographic location, device ID;

[0014] The equipment operation data includes: monthly operation failure data of security equipment in the past year ,in, is the operation failure data of the security equipment in the i-th month, i=1, 2, ..., 12;

[0015] It should be noted that the operation fault data is the difference between the actual operation parameters of the security device and the target operation parameters when the security device is identified as a fault state;

[0016] The sensor data includes: the total number of security events , Number of abnormal events , data on response waiting time for abnormal events, and number of timely response events and response completion time data for timely response incidents;

[0017] S13: Integrate noise filtering algorithm to remove noise and interference in the collected security data, and compress and encrypt the collected security data for transmission.

[0018] Specifically, the encrypted transmission includes:

[0019] When no security alarm is generated, the security data is encrypted and transmitted through an adaptive encryption strength adjustment strategy;

[0020] Extract the number of data bytes of security data and the timestamp of security data updates, calculate the time interval between two adjacent updates, and count the number of updates per unit time to quantify the frequency of changes;

[0021] Set up a security data sensitivity classification system to quantify the data sensitivity level;

[0022] Preferably, the security data sensitivity classification system includes: low sensitivity level, medium sensitivity level and high sensitivity level; the security data of the low sensitivity level includes: environmental temperature and humidity data; the security data of the medium sensitivity level includes: operating parameters of security equipment; the security data of the high sensitivity level includes: switch records of the access control system and personnel identification information;

[0023] Construct a data feature analysis model, and use the data feature analysis model to extract and analyze the extracted security data;

[0024] Input real-time security data into the trained data feature analysis model and output the corresponding encryption strength level;

[0025] Adaptively adjusting the encryption strength according to the encryption strength level, including: setting an update frequency comparison value of security data for each security period, and using the AES-128 algorithm to encrypt security data whose update frequency is lower than the update frequency comparison value and whose data sensitivity level is a low sensitivity level;

[0026] It should be noted that the AES-128 algorithm has high encryption efficiency and certain security, and can reduce the computing resource consumption of encryption and decryption while ensuring the security of security data.

[0027] For security data with an update frequency higher than the update frequency comparison value and a data sensitivity level of medium or high sensitivity, the AES-256 algorithm is used for encryption;

[0028] It should be noted that the AES-256 algorithm provides a higher level of security and can effectively protect sensitive data from being stolen or tampered with.

[0029] For security data that contains low sensitivity level, medium sensitivity level and high sensitivity level, a layered encryption method is adopted. The low sensitivity level security data is first encrypted using the AES-128 algorithm, and then the high sensitivity level security data is encrypted using the AES-256 algorithm. Finally, the encrypted security data is combined for transmission;

[0030] An RSA key exchange mechanism is established between the edge device and the cloud server, wherein the RSA key exchange mechanism includes: for each set of security data, a pair of RSA public and private keys are generated on the edge device and the cloud server, respectively, with the public key being made public and the private key being kept secret;

[0031] Before encrypting and transmitting security data, the edge device uses the public key of the cloud server to encrypt the AES key required for the security data, and sends the encrypted AES key and security data to the cloud server;

[0032] After receiving the AES key and security data, the cloud server uses the private key to decrypt the AES key, and then uses the AES key to decrypt the security data.

[0033] Specifically, the encrypted transmission also includes:

[0034] When a security alarm is generated, a quantum key distribution device is deployed in the security system of the digital residential area. The edge device and the cloud server obtain a one-time quantum key through the quantum key distribution channel, and use the quantum key to encrypt the alarm data.

[0035] When the edge device sends alarm data to the cloud server, the hardware fingerprint is used to verify the edge device. When the hardware fingerprint matches successfully, the security data is received and transmitted to the next data node.

[0036] Specifically, the security strategy includes an incident response strategy;

[0037] The event response strategy includes: automatic alarm response at the edge and manual takeover response at the cloud;

[0038] Edge automatic alarm response includes: after the system detects an abnormal event, the edge device automatically analyzes and triggers the alarm system automatically, without the intervention of the cloud server, and calculates and counts the monthly alarm trigger frequency of the system ;

[0039] Monthly alarm trigger frequency of the system The calculation formula is:

[0040] ;

[0041] A is the system alarm sensitivity, r is the average response time of the operating security equipment, and n is the total number of alarm system triggers;

[0042] Manual cloud takeover response includes: after the system detects an abnormal event, the cloud server needs to manually take over the response and operate to trigger the alarm system;

[0043] Calculate and count the jth alarm trigger frequency of the cloud server in the cloud manual takeover response , the calculation formula is: , j is the index of the number of times the cloud server alarm is triggered, j=1, 2, …, n.

[0044] Specifically, in S3, the security energy efficiency evaluation strategy includes:

[0045] S31: Based on the deployment location and type of security equipment in the digital residential area, obtain the monthly average failure data of other similar security equipment at the deployment location ;

[0046] S32: Calculate the relative difference in failure rate between the security equipment and similar security equipment at the deployment location , , i=1,2,…,12;

[0047] S33: When the event response strategy is edge automatic alarm response, based on the relative difference in failure rate Calculate the security energy efficiency value of security equipment , security energy efficiency value The calculation strategy is: ;

[0048] S34: When the event response strategy is manual takeover response by the cloud, during the security device monitoring cycle, calculate the security energy efficiency value of the security device when the jth alarm of the cloud server is triggered. , security energy efficiency value The calculation strategy is: .

[0049] Specifically, in S4, the device status impact assessment strategy includes:

[0050] S41. Calculate the proportion of abnormal events , Proportion of waiting time for abnormal event processing , where L is the unit duration of the security equipment's status self-check;

[0051] Indicates the average response waiting time for n alarm triggers;

[0052] S42. Calculate the proportion of timely response events , Proportion of time spent on timely response to incidents ; represents the mean response completion time of m timely response events;

[0053] S43. According to S41 and S42, the device state impact value F is assigned a value by using a device state impact value judgment formula, wherein the device state impact value judgment formula is:

[0054] ;

[0055] in, represents the union, wb is the device false alarm rate data, is the device standard state threshold, F is the device state impact value, when the device state impact value judgment formula is established, F is assigned a value of 1; otherwise, F is assigned a value of 0.

[0056] Specifically, the security decision model in S5 includes:

[0057] S51. When the event response strategy is edge automatic alarm response, establish an edge automatic alarm response security risk assessment model and output the security decision value of edge automatic alarm response , the calculation formula is: ,in, is the security decision value when the edge automatic alarm responds, are the parameters of the edge automatic alarm response security risk assessment model, and their sum is 1;

[0058] S52. When the event response strategy is a manual takeover response on the cloud, a security risk assessment model for a manual takeover response on the cloud is established, and a security decision value for a manual takeover response on the cloud is output. , the calculation formula is: ,in, It is the security decision value when the cloud manually takes over the response. They are the parameters of the cloud manual takeover response security risk assessment model, and their sum is 1.

[0059] Specifically, S6 includes the following specific steps:

[0060] S61, when , it means that the security equipment will generate security risks in the edge automatic alarm response mode. The larger the value, the greater the risk of security equipment abnormality. When , it indicates that the security equipment is operating normally in the edge automatic alarm response mode;

[0061] S62, when , it means that the security device will generate security risks in the cloud manual takeover response mode. The larger the value, the greater the risk of security equipment abnormality. , indicating that the security device cannot operate in the edge automatic alarm response mode normally, and it is necessary to connect to the security center to switch the operation mode of the security device to the cloud manual takeover response mode.

[0062] In addition, the digital intelligent residential security decision-making system based on end-edge-cloud collaboration of the present invention includes the following modules:

[0063] Data acquisition module, security energy efficiency evaluation module, equipment status evaluation module, security decision value calculation module and security optimization module;

[0064] The data acquisition module is used to collect security data of each terminal security device in the digital intelligent residential area, security strategy data of edge devices and cloud servers;

[0065] The security energy efficiency evaluation module is used to substitute security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value;

[0066] The device status assessment module is used to substitute sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital intelligent residential area;

[0067] The security decision value calculation module is used to construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital intelligent residential area;

[0068] The security optimization module evaluates and optimizes the security strategy of the digital intelligent residential area based on the calculated security decision value.

[0069] Compared with the prior art, the technical effects of the present invention are as follows:

[0070] 1. The beneficial effects of the technical solution of the present invention are achieved by collecting the operating data and sensor data of the security equipment (such as equipment status, equipment operation status, sensor detection data, etc.) in real time on the end side, and the edge device performs real-time calculation and analysis to ensure the real-time and accuracy of the data, improve data processing efficiency, and provide timely and reliable data support for subsequent security decisions.

[0071] 2. The present invention calculates the security energy efficiency value through edge devices based on the security data collected in real time and the security strategy data synchronized with the cloud server, dynamically adjusts and optimizes the security strategy, overcomes the shortcomings of static strategies, improves the adaptability and flexibility of security strategies, and ensures the best security effect under different operating conditions.

[0072] 3. The present invention comprehensively evaluates and manages the potential risks of the security system through the equipment status impact value judgment formula and the security risk assessment model, realizes a comprehensive risk assessment of the security system, reduces the one-sidedness of single data evaluation, improves the accuracy and comprehensiveness of risk management, and ensures the safety and reliability of the system.

[0073] 4. The present invention combines the edge automatic alarm response and the cloud manual takeover response strategy to achieve rapid response and processing of abnormal events, automatically trigger the alarm system or manual intervention. It reduces the time and cost of manual intervention, improves the response speed and efficiency of the security system, and ensures that various abnormal situations can be handled quickly and effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0075] Figure 1 It is a flow chart of the digital intelligent residential security decision-making method based on end-edge-cloud collaboration of the present invention;

[0076] Figure 2This is a structural diagram of the digital residential security decision-making system based on end-edge-cloud collaboration of the present invention. DETAILED DESCRIPTION

[0077] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0078] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0080] Embodiment 1:

[0081] like Figure 1 As shown, the digital intelligent residential security decision-making method based on end-edge-cloud collaboration in an embodiment of the present invention includes the following specific steps:

[0082] S1: Collect security data of each terminal security device in the digital residential area, including: security device status, device operation data, and sensor data;

[0083] S1 includes the following specific steps:

[0084] S11: Establish a dynamic management platform for security equipment to automatically discover new or removed security equipment and update the equipment list in real time;

[0085] S12: Collect security data of each terminal security device in the digital intelligent residential area, use machine learning algorithms to intelligently classify the security devices, automatically identify the types of security devices and the types of security data, and add metadata annotations for each data type, the metadata annotations include: timestamp, geographic location, device ID;

[0086] The equipment operation data includes: monthly operation failure data of security equipment in the past year ,in, is the operation failure data of the security equipment in the i-th month, i=1, 2, ..., 12;

[0087] It should be noted that the operation fault data is the difference between the actual operation parameters of the security device and the target operation parameters when the security device is identified as a fault state;

[0088] The sensor data includes: the total number of security events , Number of abnormal events , data on response waiting time for abnormal events, and number of timely response events and response completion time data for timely response incidents;

[0089] S13: Integrate noise filtering algorithm to remove noise and interference in the collected security data, and compress and encrypt the collected security data for transmission.

[0090] The encrypted transmission includes:

[0091] When no security alarm is generated, the security data is encrypted and transmitted through an adaptive encryption strength adjustment strategy;

[0092] Extract the number of data bytes of security data and the timestamp of security data updates, calculate the time interval between two adjacent updates, and count the number of updates per unit time to quantify the frequency of changes;

[0093] Set up a security data sensitivity classification system to quantify the data sensitivity level;

[0094] Preferably, the security data sensitivity classification system includes: low sensitivity level, medium sensitivity level and high sensitivity level; the security data of the low sensitivity level includes: environmental temperature and humidity data; the security data of the medium sensitivity level includes: operating parameters of security equipment; the security data of the high sensitivity level includes: switch records of the access control system and personnel identification information;

[0095] Construct a data feature analysis model, and use the data feature analysis model to extract and analyze the extracted security data;

[0096] Input real-time security data into the trained data feature analysis model and output the corresponding encryption strength level;

[0097] Adaptively adjusting the encryption strength according to the encryption strength level, including: setting an update frequency comparison value of security data for each security period, and using the AES-128 algorithm to encrypt security data whose update frequency is lower than the update frequency comparison value and whose data sensitivity level is a low sensitivity level;

[0098] It should be noted that the AES-128 algorithm has high encryption efficiency and certain security, and can reduce the computing resource consumption of encryption and decryption while ensuring the security of security data.

[0099] For security data with an update frequency higher than the update frequency comparison value and a data sensitivity level of medium or high sensitivity, the AES-256 algorithm is used for encryption;

[0100] It should be noted that the AES-256 algorithm provides a higher level of security and can effectively protect sensitive data from being stolen or tampered with.

[0101] For security data that contains low sensitivity level, medium sensitivity level and high sensitivity level, a layered encryption method is adopted. The low sensitivity level security data is first encrypted using the AES-128 algorithm, and then the high sensitivity level security data is encrypted using the AES-256 algorithm. Finally, the encrypted security data is combined for transmission;

[0102] An RSA key exchange mechanism is established between the edge device and the cloud server, wherein the RSA key exchange mechanism includes: for each set of security data, a pair of RSA public and private keys are generated on the edge device and the cloud server, respectively, with the public key being made public and the private key being kept secret;

[0103] Before encrypting and transmitting security data, the edge device uses the public key of the cloud server to encrypt the AES key required for the security data, and sends the encrypted AES key and security data to the cloud server;

[0104] After receiving the AES key and security data, the cloud server uses the private key to decrypt the AES key, and then uses the AES key to decrypt the security data.

[0105] The encrypted transmission also includes:

[0106] When a security alarm is generated, a quantum key distribution device is deployed in the security system of the digital residential area. The edge device and the cloud server obtain a one-time quantum key through the quantum key distribution channel, and use the quantum key to encrypt the alarm data.

[0107] When the edge device sends alarm data to the cloud server, the hardware fingerprint is used to verify the edge device. When the hardware fingerprint matches successfully, the security data is received and transmitted to the next data node.

[0108] S2: Synchronously collect security strategy data of edge devices and cloud servers in the digital residential area, including: security equipment deployment strategy, security plan data, and security resource configuration data;

[0109] The security strategy includes an incident response strategy;

[0110] The event response strategy includes: automatic alarm response at the edge and manual takeover response at the cloud;

[0111] Edge automatic alarm response includes: after the system detects an abnormal event, the edge device automatically analyzes and triggers the alarm system automatically, without the intervention of the cloud server, and calculates and counts the monthly alarm trigger frequency of the system ;

[0112] Monthly alarm trigger frequency of the system The calculation formula is:

[0113] ;

[0114] A is the system alarm sensitivity, r is the average response time of the operating security equipment, and n is the total number of alarm system triggers;

[0115] Manual cloud takeover response includes: after the system detects an abnormal event, the cloud server needs to manually take over the response and operate to trigger the alarm system;

[0116] Calculate and count the jth alarm trigger frequency of the cloud server in the cloud manual takeover response , the calculation formula is: , j is the index of the number of times the cloud server alarm is triggered, j=1, 2, …, n.

[0117] S3: Substitute the security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value;

[0118] In S3, the security energy efficiency evaluation strategy includes:

[0119] S31: Based on the deployment location and type of security equipment in the digital residential area, obtain the monthly average failure data of other similar security equipment at the deployment location ;

[0120] S32: Calculate the relative difference in failure rate between the security equipment and similar security equipment at the deployment location , , i=1,2,…,12;

[0121] S33: When the event response strategy is edge automatic alarm response, based on the relative difference in failure rate Calculate the security energy efficiency value of security equipment , security energy efficiency value The calculation strategy is: ;

[0122] S34: When the event response strategy is manual takeover response by the cloud, during the security device monitoring cycle, calculate the security energy efficiency value of the security device when the jth alarm of the cloud server is triggered. , security energy efficiency value The calculation strategy is: .

[0123] S4: Substitute sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital residential area;

[0124] In S4, the device status impact assessment strategy includes:

[0125] S41. Calculate the proportion of abnormal events , Proportion of waiting time for abnormal event processing , where L is the unit duration of the security equipment's status self-check;

[0126] Indicates the average response waiting time for n alarm triggers;

[0127] S42. Calculate the proportion of timely response events , Proportion of time spent on timely response to incidents ; represents the mean response completion time of m timely response events;

[0128] S43. According to S41 and S42, the device state impact value F is assigned a value by using a device state impact value judgment formula, wherein the device state impact value judgment formula is:

[0129] ;

[0130] in, represents the union, wb is the device false alarm rate data, is the device standard state threshold, F is the device state impact value, when the device state impact value judgment formula is established, F is assigned a value of 1; otherwise, F is assigned a value of 0.

[0131] S5: Construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital residential area;

[0132] The security decision model described in S5 includes:

[0133] S51. When the event response strategy is edge automatic alarm response, establish an edge automatic alarm response security risk assessment model and output the security decision value of edge automatic alarm response , the calculation formula is: ,in, is the security decision value when the edge automatic alarm responds, are the parameters of the edge automatic alarm response security risk assessment model, and their sum is 1;

[0134] S52. When the event response strategy is a manual takeover response on the cloud, a security risk assessment model for a manual takeover response on the cloud is established, and a security decision value for a manual takeover response on the cloud is output. , the calculation formula is: ,in, It is the security decision value when the cloud manually takes over the response. They are the parameters of the cloud manual takeover response security risk assessment model, and their sum is 1.

[0135] S6: Based on the calculated security decision value, the security strategy of the digital residential area is evaluated and optimized.

[0136] S6 includes the following specific steps:

[0137] S61, when , it means that the security equipment will generate security risks in the edge automatic alarm response mode. The larger the value, the greater the risk of security equipment abnormality. When , it indicates that the security equipment is operating normally in the edge automatic alarm response mode;

[0138] S62, when , it means that the security device will generate security risks in the cloud manual takeover response mode. The larger the value, the greater the risk of security equipment abnormality. , indicating that the security device cannot operate in the edge automatic alarm response mode normally, and it is necessary to connect to the security center to switch the operation mode of the security device to the cloud manual takeover response mode.

[0139] Embodiment 2:

[0140] like Figure 2 As shown, the digital intelligent residential security decision-making system based on end-edge-cloud collaboration of an embodiment of the present invention includes the following modules:

[0141] Data acquisition module, security energy efficiency evaluation module, equipment status evaluation module, security decision value calculation module and security optimization module;

[0142] The data acquisition module is used to collect security data of each terminal security device in the digital intelligent residential area, security strategy data of edge devices and cloud servers;

[0143] The security energy efficiency evaluation module is used to substitute security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value;

[0144] The device status assessment module is used to substitute sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital intelligent residential area;

[0145] The security decision value calculation module is used to construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital intelligent residential area;

[0146] The security optimization module evaluates and optimizes the security strategy of the digital intelligent residential area based on the calculated security decision value.

[0147] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0150] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0154] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0155] 1. The beneficial effects of the technical solution of the present invention are achieved by collecting the operating data and sensor data of the security equipment (such as equipment status, equipment operation status, sensor detection data, etc.) in real time on the end side, and the edge device performs real-time calculation and analysis to ensure the real-time and accuracy of the data, improve data processing efficiency, and provide timely and reliable data support for subsequent security decisions.

[0156] 2. The present invention calculates the security energy efficiency value through edge devices based on the security data collected in real time and the security strategy data synchronized with the cloud server, dynamically adjusts and optimizes the security strategy, overcomes the shortcomings of static strategies, improves the adaptability and flexibility of security strategies, and ensures the best security effect under different operating conditions.

[0157] 3. The present invention comprehensively evaluates and manages the potential risks of the security system through the equipment status impact value judgment formula and the security risk assessment model, realizes a comprehensive risk assessment of the security system, reduces the one-sidedness of single data evaluation, improves the accuracy and comprehensiveness of risk management, and ensures the safety and reliability of the system.

[0158] 4. The present invention combines the edge automatic alarm response and the cloud manual takeover response strategy to achieve rapid response and processing of abnormal events, automatically trigger the alarm system or manual intervention. It reduces the time and cost of manual intervention, improves the response speed and efficiency of the security system, and ensures that various abnormal situations can be handled quickly and effectively.

[0159] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A digital intelligent residential security decision-making method based on end-edge-cloud collaboration, characterized in that: The method comprises the following specific steps: S1: Collect security data of each terminal security device in the digital residential area, including: security device status, device operation data, and sensor data; S2: Synchronously collect security strategy data of edge devices and cloud servers in the digital residential area, including: security equipment deployment strategy, security plan data, and security resource configuration data; S3: Substitute the security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value; S4: Substitute the sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital residential area; S5: Construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital residential area; S6: Based on the calculated security decision value, the security strategy of the digital residential area is evaluated and optimized.

2. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 1 is characterized in that: S1 includes the following specific steps: S11: Establish a dynamic management platform for security equipment to automatically discover new or removed security equipment and update the equipment list in real time; S12: Collect security data of each terminal security device in the digital intelligent residential area, use machine learning algorithms to intelligently classify the security devices, automatically identify the types of security devices and the types of security data, and add metadata annotations for each data type, the metadata annotations include: timestamp, geographic location, device ID; The equipment operation data includes: monthly operation failure data of security equipment in the past year ,in, is the operation failure data of the security equipment in the i-th month, i=1, 2, ..., 12; The sensor data includes: the total number of security events , Number of abnormal events , data on response waiting time for abnormal events, and number of timely response events and response completion time data for timely response incidents; S13: Integrate noise filtering algorithm to remove noise and interference in the collected security data, and compress and encrypt the collected security data for transmission.

3. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 2 is characterized in that: The encrypted transmission includes: When no security alarm is generated, the security data is encrypted and transmitted through an adaptive encryption strength adjustment strategy; Extract the number of data bytes of security data and the timestamp of security data updates, calculate the time interval between two adjacent updates, and count the number of updates per unit time to quantify the frequency of changes; Setting up a security data sensitivity grading system to quantify the data sensitivity level; the security data sensitivity grading system includes: low sensitivity level, medium sensitivity level and high sensitivity level; Construct a data feature analysis model, and use the data feature analysis model to extract and analyze the extracted security data; Input real-time security data into the trained data feature analysis model and output the corresponding encryption strength level; Adaptively adjusting the encryption strength according to the encryption strength level, including: setting an update frequency comparison value of security data for each security period, and using the AES-128 algorithm to encrypt security data whose update frequency is lower than the update frequency comparison value and whose data sensitivity level is a low sensitivity level; For security data with an update frequency higher than the update frequency comparison value and a data sensitivity level of medium or high sensitivity, the AES-256 algorithm is used for encryption; For security data that contains low sensitivity level, medium sensitivity level and high sensitivity level, a layered encryption method is adopted. The low sensitivity level security data is first encrypted using the AES-128 algorithm, and then the high sensitivity level security data is encrypted using the AES-256 algorithm. Finally, the encrypted security data is combined for transmission; An RSA key exchange mechanism is established between the edge device and the cloud server, wherein the RSA key exchange mechanism includes: for each set of security data, a pair of RSA public and private keys are generated on the edge device and the cloud server, respectively, with the public key being made public and the private key being kept secret; Before encrypting and transmitting security data, the edge device uses the public key of the cloud server to encrypt the AES key required for the security data, and sends the encrypted AES key and security data to the cloud server; After receiving the AES key and security data, the cloud server uses the private key to decrypt the AES key, and then uses the AES key to decrypt the security data.

4. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 3 is characterized in that: The encrypted transmission also includes: When a security alarm is generated, a quantum key distribution device is deployed in the security system of the digital residential area. The edge device and the cloud server obtain a one-time quantum key through the quantum key distribution channel, and use the quantum key to encrypt the alarm data. When the edge device sends alarm data to the cloud server, the hardware fingerprint is used to verify the edge device. When the hardware fingerprint matches successfully, the security data is received and transmitted to the next data node.

5. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 4 is characterized in that: The security strategy includes an incident response strategy; The event response strategy includes: automatic alarm response at the edge and manual takeover response at the cloud; Edge automatic alarm response includes: after the system detects an abnormal event, it automatically triggers the alarm system through autonomous analysis by the edge device, and calculates and counts the system's monthly alarm trigger frequency ; The cloud manual takeover response includes: after the system detects an abnormal event, the cloud server manually takes over the response and operates to trigger the alarm system, calculates and counts the jth alarm trigger frequency of the cloud server .

6. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 5 is characterized in that: In S3, the security energy efficiency evaluation strategy includes: S31: Based on the deployment location and type of security equipment in the digital residential area, obtain the monthly average failure data of other similar security equipment at the deployment location ; S32: Calculate the relative difference in failure rate between the security equipment and similar security equipment at the deployment location ; S33: When the event response strategy is edge automatic alarm response, based on the relative difference in failure rate Calculate the security energy efficiency value of security equipment ; S34: When the event response strategy is manual takeover response by the cloud, during the security device monitoring cycle, calculate the security energy efficiency value of the security device when the jth alarm of the cloud server is triggered. .

7. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 6 is characterized in that: In S4, the device status impact assessment strategy includes: S41. Calculate the proportion of abnormal events , Proportion of waiting time for abnormal event processing ; S42. Calculate the proportion of timely response events , Proportion of time spent on timely response to incidents ; S43. According to S41 and S42, the device state impact value F is assigned a value through the device state impact value judgment formula. When the device state impact value judgment formula is established, F is assigned a value of 1; otherwise, F is assigned a value of 0.

8. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 7 is characterized in that: The security decision model described in S5 includes: S51. When the event response strategy is edge automatic alarm response, establish an edge automatic alarm response security risk assessment model and output the security decision value of edge automatic alarm response ; S52. When the event response strategy is a manual takeover response on the cloud, a security risk assessment model for a manual takeover response on the cloud is established, and a security decision value for a manual takeover response on the cloud is output. .

9. The digital intelligent residential security decision-making method based on end-edge-cloud collaboration according to claim 8 is characterized in that: S6 includes the following specific steps: S61, when , it means that the security equipment will generate security risks in the edge automatic alarm response mode. The larger the value, the greater the risk of security equipment abnormality. When , it indicates that the security equipment is operating normally in the edge automatic alarm response mode; S62, when , it means that the security device will generate security risks in the cloud manual takeover response mode. The larger the value, the greater the risk of security equipment abnormality. , indicating that the security device cannot operate normally in the edge automatic alarm response mode. By connecting to the security center, the operation mode of the security device can be switched to the cloud manual takeover response mode.

10. A digital intelligent residential security decision-making system based on end-edge-cloud collaboration, used to implement the digital intelligent residential security decision-making method based on end-edge-cloud collaboration as described in any one of claims 1 to 9, characterized in that: The system includes the following modules: Data acquisition module, security energy efficiency evaluation module, equipment status evaluation module, security decision value calculation module and security optimization module; The data acquisition module is used to collect security data of each terminal security device in the digital intelligent residential area, security strategy data of edge devices and cloud servers; The security energy efficiency evaluation module is used to substitute security data and security strategy data into the security energy efficiency evaluation strategy to calculate and obtain the security energy efficiency value; The device status assessment module is used to substitute sensor data and security strategy data into the device status impact assessment strategy to calculate the device status impact value of the security equipment in the digital intelligent residential area; The security decision value calculation module is used to construct a security decision model, substitute the security energy efficiency value and the equipment status impact value into the security decision model, and calculate the security decision value of the digital intelligent residential area; The security optimization module evaluates and optimizes the security strategy of the digital intelligent residential area based on the calculated security decision value.

Images