Device data intelligent supervision system and method based on artificial intelligence

Abstract

The invention discloses an intelligent equipment data supervision system and method based on artificial intelligence, and relates to the technical field of equipment data management, the system comprises an equipment data interconnection module, a data attribute analysis module, an artificial intelligence processing module and a supervision feedback module; the output end of the equipment data interconnection module is connected with the input end of the data attribute analysis module; the output end of the data attribute analysis module is connected with the input end of the artificial intelligence processing module; the output end of the artificial intelligence processing module is connected with the input end of the supervision feedback module. According to the method, the smooth interconnection communication of the equipment is ensured, and the behavior of each piece of equipment in the equipment interconnection network is detected based on different security attributes between the equipment, so that the probability that the equipment with low security performance becomes a platform for potential attackers of the interconnection network to find vulnerabilities is reduced, and the equipment interconnection security is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment data management, and in particular to an intelligent equipment data monitoring system and method based on artificial intelligence. Background Art

[0002] With the development of artificial intelligence and Internet of Things technology, smart devices as carriers of artificial intelligence and Internet of Things technology are becoming increasingly mature. In the current smart device technology, there are usually several smart devices forming a complex network to transmit information between smart devices. A common example is smart home devices. Multiple home devices are interconnected to form an entire home network to serve users. However, in such scenarios, data privacy issues are becoming increasingly serious. Although device interconnection has greatly improved the overall intelligence and convenience of devices, it also brings greater hidden dangers. Due to the different security attributes between devices, for example, in the home scenario, the security attributes between smart door locks and smart voice-controlled lamps are completely different. The data security level of smart door locks is much higher than that of smart voice-controlled lamps. Once smart door locks and smart voice-controlled lamps belong to the same Internet network, when any device becomes a node for attackers to invade, the Internet network between devices becomes a platform for potential attackers to find vulnerabilities. Attackers can use this device to spread malicious code or control other devices in the network, causing a larger range of privacy leaks. At present, there is still a lack of a regulatory system for security risks in this regard. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent monitoring system and method for equipment data based on artificial intelligence to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solution: an intelligent monitoring method for device data based on artificial intelligence, the method comprising the following steps: S1. Build a device data supervision system, which includes several device interconnection networks. Any device interconnection network includes several devices, and each device interconnection network is different; S2. The system records the network data attributes of each device interconnection network, constructs an attribute function, sets a time period, and updates the attribute function every time period; S3. The system marks each device Internet network with an error, obtains the names of all devices in the marked device Internet network, performs intelligent analysis, outputs the device safety sequence list, and feeds back to the administrator port.

[0005] According to the above technical solution, the network data attributes include: data flow, time, data type and data efficiency; The data flow refers to the communication data flow between devices and device interconnection networks, which is counted once for each time period; the time refers to the operating time of the device in the device interconnection network, including intermittent operation and continuous operation. The intermittent operation refers to intermittent operation in each time period, and the continuous operation refers to continuous operation in each time period; the data type refers to the communication data type between devices and device interconnection networks; the data efficiency refers to the proportion of data fed back by the device to the device operation network that is valid data. The valid data refers to functional data related to the device itself. For example, for smart lamps, the feedback data is continuous lighting for N hours, which is valid data. If the feedback data is connected to the smart door lock switch, the door lock is opened, and the lamp is on, it is non-valid data. That is, in this application, valid data refers to only the functional data brought by the device itself, and the linkage data between the device and other devices in the device interconnection network is non-valid data; the proportion refers to the proportion of valid data in the data flow in each time period.

[0006] According to the above technical solution, in step S2, it also includes: Construct a time period, taking a whole day as an interval, where each hour is a time period, with the endpoint being the hour before and excluding the hour after, to form a property function for each time period in a day; The network data attributes of the same time period in each interval are selected, among which the system sets four constant items Used to measure time and data types, where intermittent operation takes a constant term within a time period ; Constant term for continuous operation ; In a time period, if there is a data type that has not appeared before, take the constant term ; If all existing data types have appeared before, take the constant term ; Based on the selection method, a set of network data attributes in the same time period in each interval is formed ,in Refers to the data flow within a time period; Refers to the time within the time period, taking or ; The data type within the time period is or ; Data efficiency within the time period; Perform function fitting on the set of network data attributes in the same time period to form an attribute function: ; in, Represents the evaluation function of the network data attribute of the same time period in each interval. The value range is set by the system and is recorded as ,in, Respectively refer to the two endpoints of the value range, the value range includes , when each network data attribute set is obtained, a value is randomly selected from the value range as the evaluation function of the obtained network data attribute set; After each interval, when the same time period is reached, the evaluation function of all network data attribute sets in the historical state is reselected, and function fitting is performed to realize the update of attribute function.

[0007] According to the above technical solution, it also includes: Obtain the network data attributes in the current time period, select the network data attributes of the same time period in each interval based on the current time period, randomly obtain the evaluation function, and form the attribute function corresponding to the current time period; Substitute the network data attributes in the current time period into the attribute function corresponding to the current time period. If there is an output value that does not belong to the value range set by the system, perform a secondary test; The secondary detection means: if the network data attributes of the next time period are substituted into the attribute function of the next period corresponding to the current time period, and the output value still does not fall within the value range set by the system, then an error is reported for the device interconnection network.

[0008] According to the above technical solution, in step S3, it also includes: Obtain all device names of the Internet of marked devices, select device names that appear twice or more and send them to the first record table; obtain all device names of the Internet of unmarked devices, select device names that overlap with those in the first record table, and delete them from the first record table; obtain the remaining device names in the first record table, and form a device safety sequence table from most to least according to the number of appearances.

[0009] An intelligent monitoring system for equipment data based on artificial intelligence, the system comprising: an equipment data interconnection module, a data attribute analysis module, an artificial intelligence processing module and a monitoring feedback module; The device data interconnection module is used to read a number of device interconnection networks, any device interconnection network includes a number of devices, and each device interconnection network is different; the data attribute analysis module is used to record the network data attributes of each device interconnection network, construct an attribute function, set a time period, and update the attribute function every time period; the artificial intelligence processing module is used to mark each device interconnection network with an error, obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output the device safety sequence list; the supervision feedback module is used to read the device safety sequence list, feed back to the administrator port, and remind the administrator to perform device processing; The output end of the device data interconnection module is connected to the input end of the data attribute analysis module; the output end of the data attribute analysis module is connected to the input end of the artificial intelligence processing module; the output end of the artificial intelligence processing module is connected to the input end of the supervision feedback module.

[0010] According to the above technical solution, the device data interconnection module includes a device internet network reading unit and a device internet network classification unit; The device interconnection network reading unit is used to read a plurality of device interconnection networks, any of which includes a plurality of devices; the device interconnection network classification unit is used to search each device interconnection network, and classify the device interconnection networks with completely identical devices in the network as the same type of device interconnection networks; The output end of the device interconnection network reading unit is connected to the input end of the device interconnection network classification unit.

[0011] According to the above technical solution, the data attribute analysis module includes an attribute function construction unit and a periodic update unit; The attribute function construction unit is used to record the network data attributes of each device interconnection network and construct the attribute function; the periodic updating unit is used to set the time period and update the attribute function every other time period; The output end of the attribute function construction unit is connected to the input end of the periodic updating unit.

[0012] According to the above technical solution, the artificial intelligence processing module includes an intelligent marking unit and an analysis unit; The intelligent marking unit is used to mark each device interconnection network where an error is reported; the analysis unit is used to obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output a device safety sequence list; The output end of the intelligent marking unit is connected to the input end of the analysis unit.

[0013] According to the above technical solution, the supervision feedback module includes a device safety supervision unit and a data feedback unit; The device safety supervision unit is used to read the device safety sequence list; the data feedback unit is used to feed back the device safety sequence list to the administrator port to remind the administrator to perform device processing; The output end of the equipment safety supervision unit is connected to the input end of the data feedback unit.

[0014] Compared with the prior art, the beneficial effect of the present invention is that while ensuring smooth communication between device interconnections, the present invention detects the behavior of each device in the device interconnection network based on the different security attributes between devices, thereby reducing the probability that devices with low security performance become platforms for potential attackers in the Internet to find vulnerabilities, thereby improving the security of device interconnection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a flowchart of an intelligent device data supervision method based on artificial intelligence. DETAILED DESCRIPTION

[0016] 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.

[0017] Example: Figure 1 As shown, the present invention provides an intelligent device data supervision method based on artificial intelligence, the method comprising: constructing a device data supervision system, the system comprising a plurality of device interconnection networks, any device interconnection network comprising a plurality of devices, and each device interconnection network is different; In this embodiment, a smart home is used as an artificial intelligence device, and several devices such as lamps, door locks, air conditioners, sofas, curtains, etc. in the smart home are taken as examples for explanation. The device Internet network includes two groups, namely, lamps, door locks, and air conditioners belong to the same control Internet network; air conditioners, sofas, and curtains belong to the same control Internet network; The system records the network data attributes of each device interconnection network, constructs attribute functions, sets time periods, and updates attribute functions every time period; The network data attributes include: data flow, time, data type and data efficiency; The data traffic refers to the communication data traffic between devices and device Internet networks, which is counted once for each time period; the time refers to the operating time of the device in the device Internet network, including intermittent operation and continuous operation. The intermittent operation refers to intermittent operation in each time period, and the continuous operation refers to continuous operation in each time period; the data type refers to the communication data type between devices and device Internet networks; the data efficiency refers to the proportion of data fed back by the device to the device operation network that is valid data, and the valid data refers to functional data related to the device itself; the proportion refers to the proportion of valid data in the data traffic in each time period.

[0018] In this embodiment, a time period is constructed, with a whole day as an interval, where each hour is a time period, and the endpoint is the hour, including the hour before and excluding the hour after, to form a property function for each time period in a day; that is, 24 hours is taken as an interval, and 0 o'clock to 1 o'clock is taken as the first time period of the interval; The network data attributes of the same time period in each interval are selected, among which the system sets four constant items Used to measure time and data types, where intermittent operation takes a constant term within a time period ; Constant term for continuous operation ; In a time period, if there is a data type that has not appeared before, take the constant term ; If all existing data types have appeared before, take the constant term ; Based on the selection method, a set of network data attributes in the same time period in each interval is formed ,in Refers to the data flow within a time period; Refers to the time within the time period, taking or ; The data type within the time period is or ; Data efficiency within the time period; Perform function fitting on the set of network data attributes in the same time period to form an attribute function: ; in, Represents the evaluation function of the network data attribute of the same time period in each interval. The value range is set by the system and is recorded as ,in, Respectively refer to the two endpoints of the value range, the value range includes , when each network data attribute set is obtained, a value is randomly selected from the value range as the evaluation function of the obtained network data attribute set; After each interval, when the same time period is reached, the evaluation function of all network data attribute sets in the historical state is reselected, and function fitting is performed to realize the update of attribute function.

[0019] Obtain the network data attributes in the current time period, select the network data attributes of the same time period in each interval based on the current time period, randomly obtain the evaluation function, and form the attribute function corresponding to the current time period; Substitute the network data attributes in the current time period into the attribute function corresponding to the current time period. If there is an output value that does not belong to the value range set by the system, perform a secondary test; The secondary detection means: if the network data attributes of the next time period are substituted into the attribute function of the next period corresponding to the current time period, and the output value still does not fall within the value range set by the system, then an error is reported for the device interconnection network.

[0020] The system marks each device internet network that has an error, obtains all device names of the marked device internet network, selects device names that appear twice or more and sends them to the first record table; obtains all device names of unmarked device internet networks, selects device names that overlap with those in the first record table, and deletes them from the first record table; obtains the remaining device names in the first record table, and forms a device safety sequence table from most to least according to the number of appearances.

[0021] In this embodiment, an intelligent monitoring system for device data based on artificial intelligence is also provided, which includes: a device data interconnection module, a data attribute analysis module, an artificial intelligence processing module and a monitoring feedback module; The device data interconnection module is used to read a number of device interconnection networks, any device interconnection network includes a number of devices, and each device interconnection network is different; the data attribute analysis module is used to record the network data attributes of each device interconnection network, construct an attribute function, set a time period, and update the attribute function every time period; the artificial intelligence processing module is used to mark each device interconnection network with an error, obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output the device safety sequence list; the supervision feedback module is used to read the device safety sequence list, feed back to the administrator port, and remind the administrator to perform device processing; The output end of the device data interconnection module is connected to the input end of the data attribute analysis module; the output end of the data attribute analysis module is connected to the input end of the artificial intelligence processing module; the output end of the artificial intelligence processing module is connected to the input end of the supervision feedback module.

[0022] The device data interconnection module includes a device interconnection network reading unit and a device interconnection network classification unit; The device interconnection network reading unit is used to read a plurality of device interconnection networks, any of which includes a plurality of devices; the device interconnection network classification unit is used to search each device interconnection network, and classify the device interconnection networks with completely identical devices in the network as the same type of device interconnection networks; The output end of the device interconnection network reading unit is connected to the input end of the device interconnection network classification unit.

[0023] The data attribute analysis module includes an attribute function construction unit and a periodic update unit; The attribute function construction unit is used to record the network data attributes of each device interconnection network and construct the attribute function; the periodic updating unit is used to set the time period and update the attribute function every other time period; The output end of the attribute function construction unit is connected to the input end of the periodic updating unit.

[0024] The artificial intelligence processing module includes an intelligent marking unit and an analysis unit; The intelligent marking unit is used to mark each device interconnection network where an error is reported; the analysis unit is used to obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output a device safety sequence list; The output end of the intelligent marking unit is connected to the input end of the analysis unit.

[0025] The supervision feedback module includes a device safety supervision unit and a data feedback unit; The device safety supervision unit is used to read the device safety sequence list; the data feedback unit is used to feed back the device safety sequence list to the administrator port to remind the administrator to perform device processing; The output end of the equipment safety supervision unit is connected to the input end of the data feedback unit.

[0026] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent monitoring method for equipment data based on artificial intelligence, characterized in that: The method comprises the following steps: S1. Build a device data supervision system, which includes several device interconnection networks. Any device interconnection network includes several devices, and each device interconnection network is different; S2. The system records the network data attributes of each device interconnection network, constructs an attribute function, sets a time period, and updates the attribute function every time period; S3. The system marks each device Internet network with an error, obtains the names of all devices in the marked device Internet network, performs intelligent analysis, outputs the device safety sequence list, and feeds back to the administrator port.

2. The method for intelligent monitoring of equipment data based on artificial intelligence according to claim 1, characterized in that: The network data attributes include: data flow, time, data type and data efficiency; The data traffic refers to the communication data traffic between devices and device Internet networks, which is counted once for each time period; the time refers to the operating time of the device in the device Internet network, including intermittent operation and continuous operation. The intermittent operation refers to intermittent operation in each time period, and the continuous operation refers to continuous operation in each time period; the data type refers to the communication data type between devices and device Internet networks; the data efficiency refers to the proportion of data fed back by the device to the device operation network that is valid data, and the valid data refers to functional data related to the device itself; the proportion refers to the proportion of valid data in the data traffic in each time period.

3. The method for intelligent monitoring of equipment data based on artificial intelligence according to claim 2, characterized in that: In step S2, it also includes: Construct a time period, with a whole day as an interval, where each hour is a time period, and the endpoint is the hour, including the hour before and excluding the hour after, to form the attribute function of each time period in a day; The network data attributes of the same time period in each interval are selected, among which the system sets four constant items Used to measure time and data types, where intermittent operation takes a constant term within a time period ; Constant term for continuous operation ; In a time period, if there is a data type that has not appeared before, take the constant term ; If all existing data types have appeared before, take the constant term ; Based on the selection method, a set of network data attributes in the same time period in each interval is formed ,in Refers to the data flow within a time period; Refers to the time within the time period, taking or ; The data type within the time period is or ; Data efficiency within the time period; Perform function fitting on the set of network data attributes in the same time period to form an attribute function: ； in, Represents the evaluation function of the network data attribute of the same time period in each interval. The value range is set by the system and is recorded as ,in, Respectively refer to the two endpoints of the value range, the value range includes , when each network data attribute set is obtained, a value is randomly selected from the value range as the evaluation function of the obtained network data attribute set; After each interval, when the same time period is reached, the evaluation function of all network data attribute sets in the historical state is reselected, and function fitting is performed to realize the update of attribute function.

4. The method for intelligently supervising device data based on artificial intelligence according to claim 3 is characterized in that: Also includes: Obtain the network data attributes in the current time period, select the network data attributes of the same time period in each interval based on the current time period, randomly obtain the evaluation function, and form the attribute function corresponding to the current time period; Substitute the network data attributes in the current time period into the attribute function corresponding to the current time period. If there is an output value that does not belong to the value range set by the system, perform a secondary test; The secondary detection means: if the network data attributes of the next time period are substituted into the attribute function of the next period corresponding to the current time period, and the output value still does not fall within the value range set by the system, then an error is reported for the device interconnection network.

5. The method for intelligent monitoring of equipment data based on artificial intelligence according to claim 1, characterized in that: In step S3, it also includes: Obtain all device names of the Internet of marked devices, select device names that appear twice or more and send them to the first record table; obtain all device names of the Internet of unmarked devices, select device names that overlap with those in the first record table, and delete them from the first record table; obtain the remaining device names in the first record table, and form a device safety sequence table from most to least according to the number of appearances.

6. An intelligent monitoring system for equipment data based on artificial intelligence, characterized in that: The system includes: equipment data interconnection module, data attribute analysis module, artificial intelligence processing module and supervision feedback module; The device data interconnection module is used to read a number of device interconnection networks, any device interconnection network includes a number of devices, and each device interconnection network is different; the data attribute analysis module is used to record the network data attributes of each device interconnection network, construct an attribute function, set a time period, and update the attribute function every time period; the artificial intelligence processing module is used to mark each device interconnection network with an error, obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output the device safety sequence list; the supervision feedback module is used to read the device safety sequence list, feed back to the administrator port, and remind the administrator to perform device processing; The output end of the device data interconnection module is connected to the input end of the data attribute analysis module; the output end of the data attribute analysis module is connected to the input end of the artificial intelligence processing module; the output end of the artificial intelligence processing module is connected to the input end of the supervision feedback module.

7. The intelligent monitoring system for equipment data based on artificial intelligence according to claim 6 is characterized by: The device data interconnection module includes a device interconnection network reading unit and a device interconnection network classification unit; The device internet network reading unit is used to read a plurality of device internet networks, any one of which includes a plurality of devices; the device internet network classification unit is used to search each device internet network, and classify the device internet networks with completely identical devices in the network as the same type of device internet networks; The output end of the device interconnection network reading unit is connected to the input end of the device interconnection network classification unit.

8. The device data intelligent monitoring system based on artificial intelligence according to claim 6 is characterized by: The data attribute analysis module includes an attribute function construction unit and a periodic update unit; The attribute function construction unit is used to record the network data attributes of each device interconnection network and construct the attribute function; the periodic updating unit is used to set the time period and update the attribute function every other time period; The output end of the attribute function construction unit is connected to the input end of the periodic updating unit.

9. The intelligent monitoring system for equipment data based on artificial intelligence according to claim 6 is characterized by: The artificial intelligence processing module includes an intelligent marking unit and an analysis unit; The intelligent marking unit is used to mark each device interconnection network where an error is reported; the analysis unit is used to obtain the names of all devices in the marked device interconnection network, perform intelligent analysis, and output a device safety sequence list; The output end of the intelligent marking unit is connected to the input end of the analysis unit.

10. The intelligent monitoring system for equipment data based on artificial intelligence according to claim 6, characterized in that: The supervision feedback module includes a device safety supervision unit and a data feedback unit; The device safety supervision unit is used to read the device safety sequence list; the data feedback unit is used to feed back the device safety sequence list to the administrator port to remind the administrator to perform device processing; The output end of the equipment safety supervision unit is connected to the input end of the data feedback unit.

Images