Edge AI collaborative enabling platform and data processing method of edge AI equipment

Abstract

The embodiment of the invention provides an edge AI collaborative enabling platform and a data processing method of edge AI equipment, and the edge AI collaborative enabling platform comprises a batch algorithm switching system, a configuration docking equipment alarm system, an atomic power scene fusion system, a cloud edge collaborative system and a local area network system. According to the invention, the alarm event of the edge AI device can be checked at the cloud, and a closed-loop processing flow is set for the alarm event, so that the application requirement of the client to the end is effectively met, and the edge AI device is effectively managed. Meanwhile, the edge AI collaborative enabling platform in the embodiment of the invention can realize large-scale data storage and complex calculation.

Description

Technical Field

[0001] The present invention relates to the field of games, and in particular to an edge AI collaborative empowerment platform and a data processing method for edge AI devices. Background Art

[0002] In scenarios such as industry, campus, and bank, customers have high requirements for algorithm latency and security. However, currently, on the one hand, cloud algorithms cannot fully meet the user's timeliness requirements, and on the other hand, they cannot meet the requirement of keeping data within the park. Therefore, in some projects, edge devices are considered for delivery. Devices such as AI edge boxes and all-in-one machines have the characteristics of timely response, local computing, and the ability to reuse old devices, becoming a powerful supplement to cloud computing.

[0003] In the process of delivering existing edge AI boxes / all-in-one machines, they can only support local area network data transmission, and it is difficult for data communication between boxes. At the same time, alarm events can only be viewed locally in the browser and cannot be transmitted to users. Moreover, there is a lack of a closed-loop handling process for alarm events, which cannot solve the end-to-end application requirements of the client, and remote management is difficult, lacking an effective tool for edge device management.

[0004] Edge computing and cloud computing are two different computing models. Edge computing is generally located in a local area network, and data is processed on devices close to the data source without the need to be transmitted to a remote cloud server. The computing power of edge devices is relatively limited and usually can only handle small-scale and simple computing tasks, not suitable for large-scale data storage and complex computing. Summary of the Invention

[0005] In view of the above problems, an edge AI collaborative empowerment platform and a data processing method for edge AI devices are proposed to overcome or at least partially solve the above problems, including:

[0006] An edge AI collaborative empowerment platform, the edge AI collaborative empowerment platform includes a batch algorithm switching system, a configuration-based docking device alarm system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system, wherein:

[0007] The batch algorithm switching system is used to add edge AI devices and the start-stop algorithms corresponding to the edge AI devices in a target park, and switch the start-stop algorithms according to the scenario of the target park;

[0008] The configuration-based docking device alarm system is used to receive alarm data generated by the edge AI devices and parse the alarm data;

[0009] The atomic capability scenario fusion system is used to establish a full-process closed-loop processing mechanism for events and process the alarm events corresponding to the edge AI devices according to the full-process closed-loop processing mechanism for events;

[0010] The cloud-edge collaboration system is used to push the alarm data parsed by the configured docking device alarm system to the cloud;

[0011] The local area network system is used for data transmission between the batch algorithm switching system, the configured docking device alarm system, the atomic capability scenario fusion system, and the local area network system.

[0012] Optionally, when the configured docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data, it is specifically used for:

[0013] Create the alarm attributes of the edge AI device, and when receiving the alarm data of the edge AI device, parse it according to the alarm attributes corresponding to the alarm data.

[0014] Optionally, the configured docking device alarm system is used to generate an alarm push message based on the parsed alarm data and send the alarm push message to the cloud-edge collaboration system.

[0015] Optionally, the configured docking device alarm system is used to adjust the configuration information of the pushed alarm.

[0016] Optionally, the cloud-edge collaboration system is used to create the user dynamic binding permissions of the third-party user and the edge AI collaborative empowerment platform, and push the alarm push message to the third party through the cloud according to the dynamic binding permissions.

[0017] Optionally, the cloud-edge collaboration system is further used to obtain the personnel information and / or organizational structure information in the target park and upload the personnel information and / or organizational structure information to the cloud.

[0018] Optionally, the cloud-edge collaboration system is further used to control the cloud to reverse-control the local area network end through a private protocol.

[0019] A data processing method for an edge AI device, which is applied to any one of the methods described in claim 1, and the method includes:

[0020] When an alarm event is triggered by the edge AI device in the target park, obtain the alarm data generated by the edge AI device;

[0021] Parse the alarm data;

[0022] Push the parsed alarm data to the cloud.

[0023] An electronic device includes a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the data processing method of the edge AI device as described above.

[0024] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the data processing method of the edge AI device as described above.

[0025] The embodiments of the present invention have the following advantages:

[0026] In the embodiments of the present invention, it is possible to view the alarm events of the edge AI device in the cloud, and set a closed-loop processing flow for the alarm events, effectively solving the application requirements of the client side and effectively managing the edge AI device. At the same time, the edge AI collaborative empowerment platform in the embodiments of the present invention can achieve large-scale data storage and complex calculations. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for the description of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 FIG. is a schematic structural diagram of an edge AI collaborative empowerment platform provided by an embodiment of the present invention;

[0029] Figure 2 FIG. is a flowchart of the steps of a data processing method for an edge AI device provided by an embodiment of the present invention;

[0030] Figure 3 FIG. is a flowchart of the steps of a data processing method for an edge AI device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0032] The concept of the device in the embodiments of the present invention:

[0033] Edge computing: It is a distributed computing framework designed to move data processing and storage closer to the data source, thereby reducing latency and bandwidth consumption and improving response speed and real-time performance.

[0034] Collaborative empowerment: It refers to enhancing the functions and efficiency of the overall system through cooperation and information sharing among different systems or devices, enabling each participating party to jointly achieve the goal.

[0035] Refer to Figure 1 , which shows a schematic structural diagram of an edge AI collaborative empowerment platform provided by an embodiment of the present invention. The edge AI collaborative empowerment platform 100 includes a batch algorithm switching system 101, a configured docking device alarm system 102, an atomic capability scenario fusion system 103, a cloud-edge collaboration system 104, and a local area network system 105, wherein:

[0036] The batch algorithm switching system 101 can be used to add edge AI devices and the start-stop algorithms corresponding to the edge AI devices in the target park, and switch the start-stop algorithms according to the scenarios of the target park;

[0037] Among them, the current park can be a scenario park such as industrial, campus, bank, etc. This scenario park has scenarios with high requirements for algorithm latency and security. The edge AI device can be a device for monitoring the park situation in the target park, such as cameras distributed in the target park. This device can apply start-stop algorithms, that is, algorithms for starting or stopping, which can be used to implement starting or stopping the edge AI algorithm. This start-stop algorithm can be an edge algorithm. The type of algorithm can be specifically set according to the actual situation.

[0038] The batch algorithm switching system can manage multiple edge AI devices at the same time and can switch each start-stop algorithm based on its powerful computing power according to the real-time scenario changes in the target park.

[0039] In the embodiment of the present invention, the batch algorithm switching system can manage the association relationships among different cameras, algorithms, monitoring areas, and algorithm parameters, and then call different AI devices to add different camera devices and start-stop algorithms on this basis, so as to quickly switch the algorithms of different cameras. On the other hand, it can reduce customer costs and meet the AI transformation needs of the entire park with a small number of edge AI devices.

[0040] The configured docking device alarm system 102 can be used to receive the alarm data generated by the edge AI device and parse the alarm data; in practical applications, during the operation of the edge AI device in the target park in the embodiments of the present invention, abnormalities may occur. To ensure the normal operation of the edge AI device, for the alarm handling process of the edge AI device, when the edge AI device is abnormal, alarm data can be generated. Furthermore, the configured docking device alarm system 102 receives the alarm data sent by the edge AI device and can parse the alarm data to determine the actual situation of the alarm.

[0041] The atomic capability scenario fusion system 103 can be used to establish an event full-process closed-loop processing mechanism and process the alarm events corresponding to the edge AI device according to the event full-process closed-loop processing mechanism.

[0042] In the embodiments of the present invention, an event full-process closed-loop processing mechanism can be established in the atomic capability scenario fusion system 103. The event full-process closed-loop processing mechanism can include the full process of event recognition - reach - processing - reply, and thus, it can be realized to sort out and analyze the business logic and data processing process and build the event encapsulation capability.

[0043] In an embodiment of the present invention, the event full-process closed-loop processing mechanism can be set based on the experience of historical processing events and can be updated regularly. Thus, a perfect event processing mechanism can be established to effectively handle various events that may occur in the target park.

[0044] The cloud-edge collaboration system 104 can be used to push the alarm data parsed by the configured docking device alarm system to the cloud. From this, it can be realized to synchronize and back up between the cloud and the edge side to ensure the consistency of the data information between the cloud and the edge side.

[0045] The local area network system 105 can be used for data transmission between the batch algorithm switching system, the configured docking device alarm system, the atomic capability scenario fusion system, and the local area network system.

[0046] In an embodiment of the present invention, when the configured docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data, it is specifically used for: creating the alarm attributes of the edge AI device, and when receiving the alarm data of the edge AI device, parsing according to the alarm attributes corresponding to the alarm data.

[0047] Among them, the configuration-based docking device alarm system may include a standard attribute corresponding subsystem, which can formulate standard alarm attributes. Then, when the edge AI device generates an alarm message, it can perform standard configuration on the alarm messages of different devices. Furthermore, every time the configuration-based docking device alarm system receives the alarm data (i.e., the alarm message) from the edge AI device, it can automatically perform corresponding and parsing, so as to achieve the purpose of automatically receiving alarms from devices of different manufacturers, enhancing the scalability of the edge AI collaborative empowerment platform.

[0048] In an embodiment of the present invention, the configuration-based docking device alarm system is used to generate an alarm push message based on the parsed alarm data and send the alarm push message to the cloud-edge collaboration system.

[0049] In practical applications, the configuration-based docking device alarm system may include a custom push message subsystem, which can support a third-party business system to customize an alarm push message, build a standard alarm event subscription and push mode, and then integrate into the AI algorithm management system.

[0050] In an embodiment of the present invention, the configuration-based docking device alarm system is used to adjust the configuration information of the pushed alarm. The configuration-based docking device alarm system may further include a custom push rule subsystem, and the custom push rule system has the ability to build push rules for the edge AI collaborative empowerment platform, allowing the scenario library to specify the configuration information of the pushed alarm according to actual needs. The configuration information may include capabilities such as type, frequency, quantity, and duration, reducing the amount of irrelevant data and enhancing the availability of the platform.

[0051] In an embodiment of the present invention, the cloud-edge collaboration system may be used to create a dynamic binding permission between a third-party user and the edge AI collaborative empowerment platform, and push the alarm push message to the third party through the cloud according to the dynamic binding permission. By setting the dynamic binding permission, the security of data transmission with the third party can be ensured.

[0052] In an embodiment of the present invention, the third party may be a WeChat mini program / official account. Furthermore, a WeChat mini program / official account service system can be built in the cloud-edge collaboration system, and then a dynamic binding permission between WeChat users and system users can be built, with strict authorization management; at the same time, alarm events are pushed to WeChat, automatically filtering different tenants, reducing the event reach threshold for timely processing; and supporting real-time query of camera, box, and alarm details on the WeChat mini program side. The data information includes personnel information, organizational structure information, and alarm information.

[0053] In an embodiment of the present invention, the cloud-edge collaboration system is further configured to obtain the personnel information and / or organizational structure information in the target park, and upload the personnel information and / or organizational structure information to the cloud.

[0054] In an embodiment of the present invention, the cloud-edge collaboration system is further configured to control the cloud to reverse-control the local area network side through a private protocol.

[0055] In an embodiment of the present invention, a typical alarm message is as follows:

[0056] {

[0057] "alarmType":"ALARM_DIMISSION_DETECTION",

[0058] "snapImage":"http: / / 192.168.4.210:9998 / vpaas-store-9999 / perm / 20240821 / 00000024082015010301000000000016 / perm20240821114241799ppzlsN0QMEO.jpg",

[0059] "alarmTime":"2024-08-21 11:42:41",

[0060] "alarmId":"acs20240821114241869IbLZUxxDMFXJ",

[0061] "alarmTypeName":"Dismissal Detection Alarm",

[0062] "alarmLevel":"2",

[0063] "deviceId":"00000024082015010301000000000016",

[0064] "deviceName":"Office Camera 001"

[0065] }

[0066] For regular alarm reception, this message needs to be parsed in the program, and the value of each attribute is obtained separately, and then all the data is organized and stored in the database.

[0067] The local area network system in the embodiments of the present invention may include an AI box, an anti-bullying all-in-one machine, a pick-up microphone, an alarm, sensors, a second-level response control plugin, a sound column device, and a streaming media service module, an NVR management module, an alarm audio playback module, a video playback module, a custom patrol module, an offline event encapsulation module, and an AI box algorithm control module within the local area network.

[0068] As an application in the embodiments of the present invention:

[0069] In the embodiments of the present invention, by designing an API call interface and establishing a user authentication mechanism, the ability to push alarm information through WeChat official accounts / miniprograms is achieved. At the same time, various notification services such as SMS services and in-site pushes are integrated, making the channels for relevant personnel to obtain information diversified, ensuring the timely and accurate push of alarm information, and supporting real-time query of details such as cameras, boxes, and alarms on the WeChat mini-program side. This enables managers to understand the operating status and real-time situation of devices in a timely manner without relying on professional equipment or reaching a specified location, so as to make a correct response in a timely manner, achieve remote management, and improve the operating efficiency of the system.

[0070] By establishing a multi-level organizational structure tree in the system to achieve decentralized and domain-based management of local area network devices in the collaborative empowerment system, and cooperating with the cloud / edge management sand table to overview data such as device status, alarm event analysis, AI box resources, and device usage on a single screen in the remote monitoring large screen, the processing efficiency of emergencies and the mastery of the address information of alarm events are improved, thereby quickly locating the event occurrence location and improving the response and handling efficiency of events.

[0071] In the embodiments of the present invention, the edge AI collaborative empowerment platform includes a batch algorithm switching system, a configured docking device alarm system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system. Through the collaborative effect between the systems, it is possible to view alarm events of edge AI devices in the cloud, and set a closed-loop processing process for alarm events, effectively solving the application requirements of the client-to-end, and effectively managing edge AI devices. At the same time, the edge AI collaborative empowerment platform in the embodiments of the present invention can achieve large-scale data storage and complex calculations.

[0072] Refer to Figure 2 , which shows a step flowchart of a data processing method for an edge AI device provided by an embodiment of the present invention, applied to an edge AI collaborative empowerment platform. The edge AI collaborative empowerment platform includes a batch algorithm switching system, a configured docking device alarm system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system, wherein:

[0073] The batch algorithm switching system is used to add edge AI devices and the corresponding start-stop algorithms for the edge AI devices in the target park, and switch the start-stop algorithms according to the scenarios of the target park; the batch algorithm switching system can quickly switch the algorithms of different cameras, on the other hand, it can reduce customer costs and meet the AI transformation needs of the entire park with a small number of edge AI devices.

[0074] The configuration docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data; among them, the configuration docking device alarm system can include a standard attribute corresponding subsystem, which can formulate standard alarm attributes. Then, when the edge AI device generates an alarm message, it can perform standard configuration on the alarm messages of different devices. Furthermore, every time the configuration docking device alarm system receives the alarm data (i.e., the alarm message) of the edge AI device, it can automatically perform corresponding and parsing, so as to achieve the purpose of automatically receiving alarms from devices of different manufacturers and enhance the scalability of the edge AI collaborative empowerment platform.

[0075] The atomic capability scenario fusion system is used to establish an event full-process closed-loop processing mechanism and process the alarm events corresponding to the edge AI device according to the event full-process closed-loop processing mechanism; the atomic capability scenario fusion system creates an event recognition - reach - processing - receipt full-process closed-loop processing mechanism, sorts out and analyzes the business logic and data processing process, and constructs the event encapsulation capability.

[0076] The cloud-edge collaboration system is used to push the alarm data parsed by the configuration docking device alarm system to the cloud; in one example, the cloud-edge collaboration system can be used to create a dynamic binding permission for third-party users and the users of the edge AI collaborative empowerment platform, and push the alarm push message to the third party through the cloud according to the dynamic binding permission. By setting the dynamic binding permission, the security of data transmission with the third party can be ensured.

[0077] The local area network system is used for data transmission among the batch algorithm switching system, the configuration docking device alarm system, the atomic capability scenario fusion system, and the local area network system.

[0078] Furthermore, the data processing method for the edge AI device based on the above-mentioned edge AI collaborative empowerment platform may include the following steps:

[0079] Step S201, when an alarm event is triggered by an edge AI device in the target park, obtain the alarm data generated by the edge AI device;

[0080] Among them, the current park can be a park for scenarios such as industry, campus, and bank. This scenario park has scenarios with relatively high requirements for algorithm latency and security. The edge AI device can be a device used to monitor the park situation within the target park, such as cameras distributed within the target park. This device can apply a start-stop algorithm, that is, an algorithm for starting or stopping, which can be used to implement starting or stopping the edge AI algorithm. This start-stop algorithm can be an edge algorithm. Specifically, the type of the algorithm can be set according to the actual situation.

[0081] In practical applications, an event full-process closed-loop processing mechanism can be established for the edge AI devices within the target park, thereby effectively coping with various events of the edge AI devices. This event full-process closed-loop mechanism can include the alarm events in the embodiments of the present invention. In the case of triggering an alarm event, the edge AI device can generate alarm data.

[0082] In an embodiment of the present invention, the edge AI collaborative empowerment platform can pre-create the alarm attributes of the edge AI device through the configured docking device alarm system. These alarm attributes can be used for the edge AI system to generate alarm data in a corresponding format. Thus, even AI devices from different manufacturers can generate alarm data in a unified format, facilitating unified management of multiple edge AI devices within the target park. Furthermore, in this configured docking device alarm system, the alarm data can also be parsed based on the alarm attributes to effectively confirm the alarm content, thereby facilitating subsequent data processing.

[0083] Step S202, parse the alarm data;

[0084] After the edge AI collaborative empowerment platform obtains the alarm data, it can parse the alarm data. Specifically, the alarm data can be parsed according to the alarm attributes stored in the configured docking device alarm system. Among them, the alarm attributes can include what each field of the alarm data corresponds to.

[0085] Step S203, push the parsed alarm data to the cloud.

[0086] After parsing the alarm data, the parsed data is pushed to the cloud to achieve cloud backup and synchronization.

[0087] In addition, in the embodiments of the present invention, during the process of docking with the cloud, the personnel information and / or organizational structure information in the target park can also be sent to the cloud for synchronization.

[0088] In an embodiment of the present invention, the cloud can also be connected to a third-party platform. Thus, the cloud data can be sent to the third platform to remotely view the relevant data of the edge AI device in the third-party platform.

[0089] In an embodiment of the present invention, the edge AI collaborative empowerment system designs an API call interface and establishes a user authentication mechanism to achieve the ability to push warning messages through WeChat official accounts / miniprograms. Meanwhile, it integrates various notification services such as SMS services and in-site pushes, diversifying the information acquisition channels for relevant personnel, ensuring the timely and accurate push of warning messages, and supporting real-time query of details such as cameras, boxes, and warnings on the WeChat mini-program side. This enables management personnel to understand the operating status and real-time situation of devices in a timely manner without relying on professional equipment or reaching a designated location, so as to make a correct response in a timely manner, achieve remote management, and improve the operating efficiency of the system.

[0090] In addition, the edge AI collaborative empowerment system establishes a multi-level organizational structure tree in the system to achieve decentralized and domain-based management of LAN devices in the collaborative empowerment system. It cooperates with the cloud / edge management sand table to overview data such as device status, warning event analysis, AI box resources, and device usage on a single screen in the remote monitoring large screen, improving the processing efficiency of emergencies and the mastery of the address information of warning events, thereby quickly locating the event occurrence location and improving the response and processing efficiency of events.

[0091] In an embodiment of the present invention, the edge AI collaborative empowerment platform includes a batch algorithm switching system, a configured docking device warning system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system. Each part collaborates to obtain the warning data generated by the edge AI device when a warning event is triggered by the edge AI device in the target park; parse the warning data; and push the parsed warning data to the cloud. It realizes viewing the warning events of the edge AI device in the cloud and sets a closed-loop processing process for the warning events, effectively solving the application requirements of the client-to-end, and effectively managing the edge AI device. At the same time, the edge AI collaborative empowerment platform in the embodiment of the present invention can achieve large-scale data storage and complex calculations.

[0092] Refer to Figure 3 FIG. [FIGURE NUMBER] shows a flowchart of the steps of a data processing method for an edge AI device provided by an embodiment of the present invention, which is applied to an edge AI collaborative empowerment platform. The edge AI collaborative empowerment platform includes a batch algorithm switching system, a configured docking device warning system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system, wherein:

[0093] The batch algorithm switching system is used to add edge AI devices and the start-stop algorithms corresponding to the edge AI devices in the target park, and switch the start-stop algorithms according to the scenarios of the target park; the batch algorithm switching system can quickly switch the algorithms of different cameras. On the other hand, it can reduce customer costs and meet the AI transformation needs of the entire park with a small number of edge AI devices.

[0094] The configured docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data. Among them, the configured docking device alarm system may include a standard attribute corresponding subsystem, which can formulate standard alarm attributes. Then, when the edge AI device generates an alarm message, it can perform standard configuration on the alarm messages of different devices. Furthermore, every time the configured docking device alarm system receives the alarm data (i.e., the alarm message) of the edge AI device, it can automatically perform corresponding and parsing, so as to achieve the purpose of automatically receiving alarms from devices of different manufacturers, enhancing the scalability of the edge AI collaborative empowerment platform.

[0095] The atomic capability scenario fusion system is used to establish an event full-process closed-loop processing mechanism and process the alarm events corresponding to the edge AI device according to the event full-process closed-loop processing mechanism. The atomic capability scenario fusion system creates an event recognition - reach - processing - receipt full-process closed-loop processing mechanism, sorts out and analyzes the business logic and data processing flow, and constructs the event encapsulation capability.

[0096] The cloud-edge collaboration system is used to push the alarm data parsed by the configured docking device alarm system to the cloud. In one example, the cloud-edge collaboration system can be used to create a dynamic binding permission for third-party users and the users of the edge AI collaborative empowerment platform, and push the alarm push message to the third party through the cloud according to the dynamic binding permission. By setting the dynamic binding permission, the security of data transmission with the third party can be ensured.

[0097] The local area network system is used for data transmission between the batch algorithm switching system, the configured docking device alarm system, the atomic capability scenario fusion system, and the local area network system.

[0098] Furthermore, the data processing method of the edge AI device based on the above-mentioned edge AI collaborative empowerment platform may include the following steps:

[0099] Step S301, when an alarm event is triggered by the edge AI device in the target park, obtain the alarm data generated by the edge AI device;

[0100] Among them, the current park can be a scenario park such as industrial, campus, bank, etc. This scenario park has scenarios with high requirements for algorithm latency and security. The edge AI device can be a device used to monitor the park situation in the target park, such as cameras distributed in the target park. This device can apply a start-stop algorithm, that is, an algorithm for starting or stopping, which can be used to implement starting or stopping the edge AI algorithm. This start-stop algorithm can be an edge algorithm. The type of algorithm can be specifically set according to the actual situation.

[0101] In practical applications, an event full - process closed - loop processing mechanism can be established for edge AI devices in a target park, so as to effectively handle various events of edge AI devices. This event full - process closed - loop mechanism can include the alarm events in the embodiments of the present invention. When an alarm event is triggered, the edge AI device can generate alarm data.

[0102] In an embodiment of the present invention, the edge AI collaborative empowerment platform can pre - create the alarm attributes of the edge AI device through the configured docking device alarm system. These alarm attributes can be used for the edge AI system to generate alarm data in a corresponding format. Thus, even AI devices from different manufacturers can generate alarm data in a unified format, which is convenient for unified management of multiple edge AI devices in the target park. Furthermore, in this configured docking device alarm system, the alarm data can also be parsed based on the alarm attributes to effectively confirm the alarm content, thereby facilitating subsequent data processing.

[0103] Step S302: Obtain the alarm attributes of the edge AI device, and parse the alarm data according to the alarm attributes.

[0104] In practical applications, create the alarm attributes of the edge AI device. When receiving the alarm data of the edge AI device, parse it according to the alarm attributes corresponding to the alarm data.

[0105] Create the alarm attributes of the edge AI device. When receiving the alarm data of the edge AI device, parse it according to the alarm attributes corresponding to the alarm data.

[0106] Step S303: Push the parsed alarm data to the cloud.

[0107] In practical applications, in the edge AI collaborative empowerment platform, the parsed alarm data can be transmitted from the configured docking device alarm system to the cloud - edge collaboration system through the local area network system, so as to achieve data backup and synchronization.

[0108] In an embodiment of the present invention, the personnel information and / or organizational structure information in the target park are also backed up and synchronized.

[0109] Step S304: Obtain the dynamic binding permissions of the third - party user and the user of the edge AI collaborative empowerment platform.

[0110] By setting dynamic binding permissions, secure data interaction with third - party users can be effectively ensured.

[0111] Step S305: Push the alarm push message to the third - party through the cloud according to the dynamic binding permissions.

[0112] In an embodiment of the present invention, the anti-bullying all-in-one machine can support private deployment, the pickup supports wired and 4G access, keyword alarm, and can automatically store the voice for 16 seconds before and after the alarm.

[0113] In an embodiment of the present invention, data parameter templates for different edge AI devices and different algorithms can also be formulated, supporting quick selection of different cameras and different algorithms, and batch setting of algorithms into edge AI devices.

[0114] In an embodiment of the present invention, the camera can be configured with a personnel white list algorithm. The same camera can be configured with a stranger alarm algorithm (to determine whether there are strangers), a face comparison algorithm (to determine whether it is a specified person), and a region intrusion algorithm (to determine whether there is someone), and then various algorithms can be combined to implement push alarms.

[0115] In an embodiment of the present invention, the cloud can also be connected to a third-party platform. Furthermore, the cloud data can be sent to the third platform to remotely view the relevant data of the edge AI device in the third-party platform.

[0116] In an embodiment of the present invention, the edge AI collaborative empowerment system, by designing an API call interface and establishing a user authentication mechanism at the same time, realizes the ability to push alarm information through WeChat official accounts / miniprograms, and integrates various notification services such as SMS services and in-site pushes, making the channels for relevant personnel to obtain information diversified, ensuring the timely and accurate push of alarm information, and supporting real-time query of details such as cameras, boxes, and alarms on the WeChat mini-program side, so that managers can understand the operation status and real-time situation of the device in a timely manner without relying on professional equipment or reaching a specified location, so as to avoid making a correct response in a timely manner, realize remote management, and improve the operation efficiency of the system.

[0117] In addition, the edge AI collaborative empowerment system, by establishing a multi-level organizational structure tree in the system, realizes decentralized and domain-based management of the LAN devices in the collaborative empowerment system, and cooperates with the cloud / edge management sand table to overview data such as device status, alarm event analysis, AI box resources, and device usage on a single screen in the remote monitoring large screen, so as to improve the processing efficiency of emergencies and the mastery of the address information of alarm events, and then quickly locate the event occurrence location and improve the response and processing efficiency of the event.

[0118] As an application in an embodiment of the present invention:

[0119] In the embodiments of the present invention, an API call interface is designed, and a user authentication mechanism is established at the same time to realize the ability to push alarm information through WeChat official accounts / miniprograms. At the same time, various notification services such as SMS services and in-site pushes are integrated, making the information acquisition channels for relevant personnel diverse, ensuring the timely and accurate push of alarm information, and supporting the real-time query of details such as cameras, boxes, and alarms on the WeChat mini-program side, so that managers can understand the operating status and real-time situation of the devices in a timely manner without relying on professional equipment or reaching a specified location, so as to avoid making correct responses in a timely manner, realize remote management, and improve the operation efficiency of the system;

[0120] By establishing a multi-level organizational structure tree in the system, decentralized and domain-based management of LAN devices in the collaborative empowerment system is realized. In cooperation with the cloud / edge management sand table, data such as device status, alarm event analysis, AI box resources, and device usage can be overviewed on a single screen in the remote monitoring large screen, so as to improve the processing efficiency of emergencies and the mastery of the address information of alarm events, and then quickly locate the event occurrence location and improve the response and handling efficiency of the event.

[0121] In the embodiments of the present invention, the edge AI collaborative empowerment platform includes a batch algorithm switching system, a configured docking device alarm system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system. Each part cooperates to obtain the alarm data generated by the edge AI device when an alarm event is triggered by the edge AI device in the target park; parse the alarm data; and push the parsed alarm data to the cloud. The alarm events of the edge AI device can be viewed in the cloud, and a closed-loop processing process is set for the alarm events, effectively solving the end-to-end application requirements of the client and effectively managing the edge AI device. At the same time, the edge AI collaborative empowerment platform in the embodiments of the present invention can realize large-scale data storage and complex calculations.

[0122] It should be noted that for the method embodiments, for the sake of simple description, they are expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequence, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0123] An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above data processing method for the edge AI device;

[0124] When an edge AI device in the target park triggers an alarm event, obtain the alarm data generated by the edge AI device;

[0125] Parse the alarm data;

[0126] Push the parsed alarm data to the cloud.

[0127] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the data processing method of the edge AI device as described above is implemented:

[0128] When an edge AI device in the target park triggers an alarm event, obtain the alarm data generated by the edge AI device;

[0129] Parse the alarm data;

[0130] Push the parsed alarm data to the cloud.

[0131] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiment.

[0132] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to describe the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0133] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0134] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate for implementing the process Figure 1 one process or multiple processes and / or blocks Figure 1a device for the functions specified in one or more boxes.

[0135] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more processes and / or boxes Figure 1 a box or multiple boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process. Thus, the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one or more processes and / or boxes Figure 1 a box or multiple boxes.

[0137] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0138] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or terminal device including the said element.

[0139] The above has introduced in detail a data processing method for an edge AI collaborative empowerment platform and edge AI devices provided. In this article, specific examples are used to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An edge AI collaborative empowerment platform, characterized in that, The edge AI collaborative enabling platform includes a batch algorithm switching system, a configured docking device alarm system, an atomic capability scenario fusion system, a cloud-edge collaboration system, and a local area network system, where: The batch algorithm switching system is used to add edge AI devices and the start-stop algorithms corresponding to the edge AI devices in the target park, and switch the start-stop algorithms according to the scenarios of the target park; The configured docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data; The atomic capability scenario fusion system is used to establish an event full-process closed-loop processing mechanism and process the alarm events corresponding to the edge AI device according to the event full-process closed-loop processing mechanism; The cloud-edge collaboration system is used to push the alarm data parsed by the configured docking device alarm system to the cloud; The local area network system is used for data transmission between the batch algorithm switching system, the configured docking device alarm system, the atomic capability scenario fusion system, and the local area network system.

2. The edge AI collaborative empowerment platform according to claim 1, characterized in that, When the configured docking device alarm system is used to receive the alarm data generated by the edge AI device and parse the alarm data, it is specifically used for: Creating the alarm attributes of the edge AI device, and parsing according to the alarm attributes corresponding to the alarm data when receiving the alarm data of the edge AI device.

3. The edge AI collaborative empowerment platform according to claim 1, characterized in that, The configured docking device alarm system is used to generate an alarm push message based on the parsed alarm data and send the alarm push message to the cloud-edge collaboration system.

4. The edge AI collaborative empowerment platform according to claim 1, characterized in that The configured docking device alarm system is used to adjust the configuration information of the pushed alarm.

5. The edge AI collaborative empowerment platform according to claim 3, wherein The cloud-edge collaboration system is used to create a user dynamic binding permission between a third-party user and the edge AI collaborative enabling platform, and push the alarm push message to the third party through the cloud according to the dynamic binding permission.

6. The edge AI collaborative empowerment platform according to claim 1, wherein The cloud-edge collaboration system is further used to obtain the personnel information and / or organizational structure information in the target park and upload the personnel information and / or organizational structure information to the cloud.

7. The edge AI collaborative empowerment platform according to claim 1, wherein, The cloud-edge collaboration system is further used to control the cloud to reverse-control the local area network end through a private protocol.

8. A data processing method for an edge AI device, characterized in that, Applied to the method described in any one of claims 1 to 7, the method includes: When an alarm event is triggered by an edge AI device in the target park, obtaining the alarm data generated by the edge AI device; Parsing the alarm data; Pushing the parsed alarm data to the cloud.

9. An electronic device, characterized in that, Including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implements the data processing method of the edge AI device described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the data processing method of the edge AI device described in any one of claims 1 to 7.

Images