Model loading method, electronic device and storage medium

Abstract

The present application discloses a model loading method, electronic device, and storage medium. The model loading method includes: a main card is activated in response to the target device where the main card is located, and determines whether the target network connected to the target device is the same as the preset network, where the target device includes the main card and at least one sub-card; in response to the target network being different from the preset network, a communication connection is established between the main card and each sub-card in the target device; and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. The above scheme can improve the effectiveness of model loading.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a model loading method, electronic device, and storage medium. Background Art

[0002] In the field of video surveillance, the types of intelligent analysis that require simultaneous processing are increasing, such as facial analysis, fingerprint analysis, and vehicle analysis. If these analysis processes are handled by a single central processing unit (CPU), it would be difficult to complete the analysis tasks. In this case, smart cards are typically used to perform intelligent analysis tasks. In current common solutions, multiple smart cards are used for intelligent analysis tasks, each of which performs only one type of intelligent analysis task. It should be noted that the smart cards that handle a specific type of intelligent analysis task are called smart daughter cards. Each type of intelligent analysis task is pre-compressed into an intelligent model package and stored on the master card. During implementation, the master card handles the processing sequence and common business logic for these multiple smart daughter cards. A master-slave architecture is typically used, with one master card and multiple daughter cards. Multiple physical transmission lines are provided between the master and the daughter cards. The master card uses a standard CPU to handle the processing sequence and overall scheduling logic for the daughter cards, while the smart daughter cards are used for different types of intelligent analysis tasks. It is understood that in a master-slave architecture, the master card uses a standard CPU for common business operations, while the slave cards use smart cards for intelligent algorithm analysis. Large smart devices often feature a single main card with multiple smart daughter cards. Although multiple physical transmission lines connect the main card and the daughter cards, allowing them to perform intelligent algorithm analysis, network conflicts can cause the daughter cards to malfunction during analysis, hindering model loading.

[0003] In view of the existing technical defects, how to provide an effective model loading solution is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0004] This application at least provides a model loading method, electronic device and storage medium.

[0005] The present application provides a model loading method, comprising: a main card is started in response to a target device where the main card is located, and determines whether a target network connected to the target device is the same as a preset network, wherein the target device includes the main card and at least one sub-card; in response to the target network being different from the preset network, establishing a communication connection between the main card and each sub-card in the target device; and sending a first model configuration instruction to each sub-card so that each sub-card performs data analysis using an algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction.

[0006] The present application provides a model loading device, comprising: a judgment module, an establishment module and a sending module; the judgment module is used for a main card to start up in response to a target device where the main card is located, and to judge whether a target network accessed by the target device is the same as a preset network, wherein the target device includes a main card and at least one sub-card; the establishment module is used for establishing a communication connection between the main card and each sub-card in the target device in response to the target network being different from the preset network; the sending module is used for sending a first model configuration instruction to each sub-card so that each sub-card performs data analysis using an algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction.

[0007] The present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned model loading method.

[0008] The present application provides a computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned model loading method when the program instructions are executed by a processor.

[0009] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0010] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0012] Figure 1 This is a flow chart of an embodiment of the model loading method of the present application;

[0013] Figure 2 This is a schematic diagram of the effect of the virtual bridge in an embodiment of the model loading method of the present application;

[0014] Figure 3 This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 1 ;

[0015] Figure 4 This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 2 ;

[0016] Figure 5 This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 3 ;

[0017] Figure 6 This is a structural diagram of an embodiment of the model loading device of the present application;

[0018] Figure 7 This is a structural diagram of an embodiment of an electronic device of the present application;

[0019] Figure 8 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0020] The following describes the embodiments of the present application in detail with reference to the accompanying drawings.

[0021] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0022] The term "and / or" in this article is simply a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0023] The present application provides some model loading methods and model loading devices. The application scenarios of the model loading method include but are not limited to intelligent analysis tasks. The execution subject of the model loading method can be a model loading device. For example, the model loading device can be set in a terminal device or a server or other processing device, including user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, etc. In some possible implementations, the model loading method can be implemented by a processor calling computer-readable instructions stored in a memory.

[0024] See also Figure 1 , Figure 1This is a flow chart of an embodiment of the model loading method of the present application. Specifically, the model loading method may include the following steps:

[0025] The existing solution has the problem of conflict between internal and external network IP addresses. When the virtual network segment of the sub-card is the same as the external network, the sub-card IP address may be the same as the external network device IP address. In this case, the conflicting sub-card in the device will not work properly.

[0026] In the existing framework, daughter cards lack permanent storage media. Instead, their intelligent models are stored on the main card. When a daughter card boots up, it mounts the main control storage media to the daughter card via a master-slave network. The daughter card then accesses the mount path to load the model. As business scenarios expand, the variety of intelligent algorithms increases, and the number of algorithm combinations required for different scenarios increases. Due to device resource constraints, a single product cannot integrate all algorithms simultaneously. Therefore, different combinations require different products, resulting in longer product development and delivery times for new combinations.

[0027] Step S11: The main card starts up in response to the target device where the main card is located, and determines whether the target network accessed by the target device is the same as the preset network. The target device includes the main card and at least one sub-card.

[0028] The target device may be a backend analysis device capable of performing intelligent analysis tasks. The backend analysis device may be a storage device with intelligent analysis capabilities. Specifically, the target device may be an intelligent video surveillance server (IVSS). The target device may employ a master-slave architecture. The master chip of the target device may be a master card. The slave chips of the target device may be multiple daughter cards. The master card may be the processor of the target device. The master card may have permanent storage media. In intelligent analysis tasks, the daughter cards may be intelligent modules capable of processing a single type of intelligent analysis task. Each daughter card may have a physical transmission line to the master card. The daughter cards may be intelligent modules without permanent storage media. It is understood that the master control unit may refer to the system control unit on the master card, which is responsible for managing and coordinating all components of the target device's entire computer system. Therefore, the master control unit can be considered the system on the master card. The target device's system may be the master control unit. It is understood that the model loading method may be executed by the model loading device. Specifically, the model loading method may be executed by the master control unit of the target device. Furthermore, the model loading method may be executed by the master card.

[0029] In some application scenarios, the main card can sense that the target device is started. The model loading device includes a judgment module. The judgment module can be used to determine whether the target network connected to the target device is the same as the preset network. The input of the judgment module can be the target network and the preset network. The output of the judgment module can be the judgment result. The judgment result can be that the target network is the same as the preset network or that the target network is different from the preset network. After the main card responds to the target device where the main card is located being started, the main card can use the judgment module to determine whether the target network connected to the target device is the same as the preset network. In some application scenarios, the model loading device includes an acquisition module. The acquisition module can be used to obtain the target network connected to the target device, and can also be used to obtain the preset network. The target network connected to the target device can be the target device's external network. The preset network set for the target device can be the target device's external network.

[0030] It is understandable that after the main card starts up in response to the target device where the main card is located, the main card uses the judgment module to judge whether the external network and the internal network of the target device are the same.

[0031] Step S12: In response to the target network being different from the preset network, establishing a communication connection between the main card and each sub-card in the target device.

[0032] The model loading device may include an establishment module. The establishment module is configured to establish a communication connection between the main card and each sub-card in the target device. In step S11 above, the determination module outputs a determination result that the target network is different from the preset network. In response to the determination that the target network is different from the preset network, the main card establishes a communication connection between the main card and each sub-card in the target device. It is understood that by establishing a communication connection between the main card and each sub-card, the main card enables data exchange, resource sharing, and control scheduling between the main card and each sub-card. In some application scenarios, data exchange between the main card and each sub-card may be a communication connection between the main card and each sub-card, allowing data to be transferred between them. Information, commands, and status, etc., can be transmitted between the main card and each sub-card via the communication connection, thereby enabling collaboration between the main card and each sub-card in the target device and expanding intelligent analysis functions. In some application scenarios, resource sharing between the main card and each sub-card may be a communication connection established by the main card, allowing the main card and each sub-card to share resources, such as memory. This can improve system utilization and performance, allowing different sub-cards to operate simultaneously or prioritize resource use as needed. In some application scenarios, control and scheduling between the main card and each sub-card can be achieved through a communication connection, enabling the main card to control and schedule each sub-card. The main card can send instructions and control signals to the sub-cards to enable them to operate in a predetermined manner. This allows for intelligent control and collaborative operation of target devices.

[0033] Step S13: Sending the first model configuration instruction to each daughter card so that each daughter card performs data analysis using the algorithm model corresponding to the first model configuration instruction after receiving the first model configuration instruction.

[0034] The first model configuration instruction may be related to an already installed algorithm model. In some application scenarios, the daughter card may determine the already installed algorithm model corresponding to the first model configuration instruction based on the first model configuration instruction. The main card may send the first model configuration instruction to each daughter card. After the main card issues the first model configuration instruction to each daughter card, each daughter card may receive the first model configuration instruction issued by the main card. After each daughter card receives the first model configuration instruction, each daughter card may use the algorithm model corresponding to the first model configuration instruction to perform data analysis. It is understandable that each daughter card may first load the algorithm model corresponding to the first model configuration instruction, and then each daughter card may implement the algorithm model corresponding to the first model configuration instruction to perform data analysis.

[0035] It is understandable that before the main card receives the first model configuration instruction, the algorithm model corresponding to the first model configuration instruction in each sub-card may have been loaded. After each sub-card receives the first model configuration instruction, each sub-card can perform data analysis on the loaded algorithm model.

[0036] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0037] In some embodiments, the model loading method may further include the following steps: first, in response to the target network being the same as the preset network, adjusting the preset network to another network, the other network being different from the target network; and controlling the target device to restart, wherein the network accessed by the target device after the restart is the target network.

[0038] The model loading device may include an adjustment module. The adjustment module is configured to adjust the preset network to another network. In step S11 above, the judgment module outputs a judgment result that the target network is the same as the preset network. After the main card responds that the target network is the same as the preset network, the main card uses the adjustment module to adjust the preset network to another network. The other network is a network that is different from the target network. In some application scenarios, after the main card adjusts the preset network to another network, the main card controls the target device to restart so that the network connected to by the target device after the restart is the target network.

[0039] In some application scenarios, the adjustment module may be configured to adjust the preset network to another network that is different from the target network accessed by the target device. Specifically, the adjustment module may modify the preset network corresponding to the default configuration of the target device, add one to the third digit of the gateway of the preset network to obtain the other network, and make the other network different from the target network corresponding to the external network.

[0040] In some application scenarios, after the master card adjusts the preset network to another network, the master card controls the target device to restart. In response to the target device restarting, the master card determines whether the target network connected to the target device is the same as the other network. In response to the target network being different from the other network, the master card establishes a communication connection between the master card and each sub-card in the target device. The master card then executes step S13.

[0041] It is understood that at this point, the master card adjusts the internal network to a different network than the external network, so that no conflict arises between the internal and external networks after the target device is restarted. The model loading device can execute step S13 above, and in the absence of conflict between the internal and external networks, each sub-card in the target device can load the algorithm model normally, thereby achieving the intelligent analysis task of each sub-card.

[0042] In some embodiments, step S12 may include the following steps: first, the main card creates a virtual network bridge and virtual network cards corresponding to each sub-card. Second, each virtual network card is bound to each virtual port in the virtual network bridge. Finally, the virtual network card configuration information is sent to each sub-card, so that each sub-card establishes a connection with each virtual network card based on the virtual network card configuration information. The main card and each sub-card communicate based on the virtual network bridge.

[0043] After the target device boots up, the main card can create a virtual network bridge and virtual network cards corresponding to each sub-card. The virtual network bridge created by the main card can be a logical bridge created by connecting multiple network interfaces. The virtual network bridge can connect multiple network interfaces together, enabling communication between the main card and each sub-card on these network interfaces. It is understood that the main card can correspond to a primary network interface. By creating a virtual network bridge, the main card can connect the primary network interface corresponding to the main card with the multiple network interfaces corresponding to each sub-card, enabling communication and data transmission between different networks. It can be assumed that, through the virtual network bridge created by the main card, the model loading device can enable communication and data transmission between the target network connected to the main card and the preset network corresponding to the default configuration of the target device. In other application scenarios, after the aforementioned step of controlling the target device to restart, the main card establishes a communication connection between the main card and each sub-card in the target device in response to the target network being different from the other networks. In this case, through the virtual network bridge created by the main card, the model loading device can enable communication and data transmission between the target network connected to the main card and other networks corresponding to the default configuration of the target device.

[0044] See also Figure 2 , Figure 2 This is a schematic diagram of the effect of the virtual bridge in an embodiment of the model loading method of the present application.

[0045] After the main card creates a virtual network bridge, it can also create virtual network cards corresponding to each sub-card according to the number of sub-cards. Figure 2As shown, the virtual network cards corresponding to each subcard can be represented as virtual network card 0, virtual network card 1, and virtual network card 2, etc. The number of virtual network cards corresponding to each subcard can be the same as the number of subcards. A virtual network bridge contains multiple virtual ports. A virtual port in a virtual network bridge can be a network interface of a subcard. The number of virtual ports in a virtual network bridge can be the same as the number of subcards. A subcard's virtual network card is a virtualized network device associated with the subcard, serving as a connection channel between the subcard and the virtual network bridge. A virtual network card can be considered a physical interface of the subcard, used to exchange data with virtual machines, containers, or other virtual devices. In some application scenarios, each subcard has its own virtual network card for configuring and managing network connections. A virtual network card can have various network functions, such as IP settings, network policies, and security controls. A subcard's virtual port is the network interface of the subcard when it runs in a virtual machine or container. In some application scenarios, a virtual port is a virtual device created using virtualization technology and is associated with the subcard's virtual network card. In a virtual machine or container, a virtual port is part of the network stack and handles the sending and receiving of network data. Each virtual machine or container has its own virtual port, which acts as a bridge between the virtual machine or container and the virtual bridge, enabling communication between the virtual device and the physical network. It should be understood that the virtual machine, container, or other virtual device can also be another daughter card connected to the same virtual bridge as this daughter card.

[0046] It is understandable that the virtual network card can be regarded as the physical interface of the daughter card, and the virtual port can be regarded as the network interface of the daughter card when it is running.

[0047] The master card binds each virtual network card to each virtual port in the virtual bridge. In some application scenarios, the master card binds the virtual network card to a virtual port list in the virtual bridge. The virtual port list can be used to represent each virtual port, and the virtual port list can be represented as a list port_lis. The virtual port list contains multiple virtual ports. For example, the virtual port list can include virtual port 1, virtual port 2, virtual port 3, and so on. It is understood that binding the virtual network cards and virtual ports of the daughter cards can achieve network isolation and management. In some application scenarios, in the virtual bridge, the master card needs to bind the virtual network card of the daughter card to the virtual port to establish a connection and communication between the daughter card and the virtual bridge. Binding the virtual network card of the daughter card to the virtual port of the master card enables data transmission and exchange. When the virtual network card of the daughter card is bound to the virtual bridge, the virtual bridge can receive and send data from the daughter card and forward it to other devices connected to the same virtual bridge. Devices on the same virtual bridge can include the master card, other daughter cards, and the virtual network cards of other daughter cards. The binding relationship between each daughter card and each virtual port in the virtual bridge establishes connections and communication links between devices in the virtual network. In other application scenarios, the binding relationship between each daughter card and each virtual port in the virtual bridge can also enable network parameter configuration and management. By binding a daughter card to the virtual port of the virtual bridge, the daughter card's virtual port can exchange and configure network parameters such as IP address, subnet mask, and gateway through the virtual bridge. This allows the network stack running in the virtual machine or container to obtain the required network information through the virtual port and communicate with other devices. In other application scenarios, administrators can configure independent network parameters such as IP address, subnet mask, and gateway for each daughter card, achieving more granular network management. In some application scenarios, by binding the daughter card's virtual network card to the virtual port of the virtual bridge, each daughter card can be network isolated from the main card. This effectively separates network traffic between different daughter cards, avoiding interference and conflicts.

[0048] The main card can send virtual network card configuration information to each sub-card, allowing each sub-card to establish a connection with the virtual network card based on the virtual network card configuration information. Communication between the main card and each sub-card is based on a virtual network bridge. After a sub-card is started, it can obtain the IP configuration information of the corresponding virtual network card from the main card via the bus and configure its own virtual network card (which may be Virtual Network Card 0). After the sub-card obtains the virtual network card configuration information, the sub-card's virtual network card may be the same as or different from Virtual Network Card 0. After obtaining the virtual network card configuration information, each sub-card establishes a connection with each virtual network card based on the virtual network card configuration information, thereby enabling communication between the main card and each sub-card for quality inspection.

[0049] In some embodiments, the model loading method may further include the following steps: First, the main card traverses the model directory to determine the first name of the algorithm model that the target device can run, and the model directory is used to record the first name of the algorithm model that the target device can run. Secondly, the first name of each algorithm model is sent to the preset recipient so that the preset recipient displays the first name of each algorithm model on the configuration interface of the preset recipient. Then, the first model configuration instruction sent by the preset recipient is received, and the first model configuration instruction is issued by the preset recipient in response to the selection operation of the displayed algorithm model.

[0050] The model directory can be related to the algorithm models that the target device can run. The model directory can be related to the algorithm models that have been installed. The model directory can include algorithm frameworks and algorithm packages. The algorithm framework can be the basis for the work of the algorithm package. The algorithm framework can contain the services of all algorithm models within the framework. The algorithm package in the model directory can correspond to the dynamic library and algorithm model of the algorithm package, and the file name of the algorithm package is named using the major category of intelligent business. An algorithm package in the model directory can contain multiple algorithm models of the same type of intelligent business. An algorithm package in the model directory can contain an algorithm model corresponding to an intelligent business.

[0051] In some application scenarios, a model directory is used to record the first names of algorithm models that can be run on a target device. Specifically, the model directory can be a directory containing the first names of the algorithm models and the installation paths of the algorithm models. The preset recipient can be a client. There can be multiple preset recipients. The configuration interface of the preset recipient can be a display interface that can respond to user operations. The main card traverses the model directory to determine the first names of the algorithm models that can be run on the target device. The main card sends the obtained first names of each algorithm model that can be run on the target device to the preset recipient, so that the preset recipient displays the first names of each algorithm model on the configuration interface of the preset recipient. The main card receives a first model configuration instruction sent by the preset recipient. The first model configuration instruction is issued by the preset recipient in response to a selection operation on a displayed algorithm model. The algorithm model displayed on the configuration interface can be the obtained first names of each algorithm model that can be run on the target device. Exemplarily, the first model configuration instruction received by the main card from the preset recipient is a configuration instruction for an already installed algorithm model A, and the first model configuration instruction includes the first name of algorithm model A. It is understandable that the algorithm model corresponding to the first name displayed on the configuration interface may be an algorithm model that can be run by the target device, or an algorithm model that can be loaded by each sub-card.

[0052] In some embodiments, the step of sending the first model configuration instruction to each daughter card may include the following steps: sending the first model configuration instruction to a virtual network bridge so that the virtual network bridge forwards the first model configuration instruction to each daughter card.

[0053] After receiving the first model configuration instruction from the predetermined recipient, the main card sends the first model configuration instruction to the virtual network bridge. For example, the main card sends the first model configuration instruction for the installed algorithm model A to the virtual network bridge. At this point, the virtual network bridge can forward the first model configuration instruction to each daughter card. After the virtual network bridge forwards the first model configuration instruction for algorithm model A to each daughter card, each daughter card can first load the algorithm model A corresponding to the first model configuration instruction, and then each daughter card can implement the algorithm model A corresponding to the first model configuration instruction to perform data analysis.

[0054] In some embodiments, the first model configuration instruction also includes parameter information of the data to be analyzed. The model loading method may further include the following steps: first, receiving data analysis results from each daughter card, where each data analysis result is obtained by each daughter card performing data analysis on the data to be analyzed based on the parameter information after running the algorithm model; and second, forwarding each data analysis result to a predetermined recipient, so that the predetermined recipient can display the data analysis result.

[0055] The first model configuration instruction also includes parameter information of the data to be analyzed. The data to be analyzed may be input data of the algorithm model corresponding to the first model configuration instruction. After the model loading device inputs the data to be analyzed into the algorithm model corresponding to the first model configuration instruction, the algorithm model may output a data analysis result. The parameter information of the data to be analyzed may be directly the data to be analyzed, or may be an index that can be used to obtain the data to be analyzed. Based on the parameter information of the data to be analyzed, the model loading device may obtain the data to be analyzed corresponding to the parameter information. After the main card receives the data analysis results of each sub-card. The main card forwards each data analysis result to a preset recipient so that the preset recipient displays the data analysis result.

[0056] For example, each sub-card may first load the algorithm model A corresponding to the first model configuration instruction. After receiving the parameter information of the data to be analyzed in the first model configuration instruction, each sub-card obtains the data to be analyzed based on the parameter information. Each sub-card performs data analysis on the data to be analyzed in algorithm model A to obtain data analysis results. Algorithm model A may output the data analysis results. Each sub-card may output each data analysis result. Each sub-card may send each data analysis result to the main card. After the main card receives the data analysis results of each sub-card, it forwards each data analysis result to a predetermined recipient client. After receiving the data analysis results output by algorithm model A, the client displays the data analysis results output by algorithm model A. In some embodiments, the model loading method may further include the following steps: first, receiving a newly added algorithm model from a predetermined recipient, where the newly added algorithm model is an algorithm model imported by the predetermined recipient. Second, installing the newly added algorithm model to a model directory to obtain a new model directory. Subsequently, the main card traverses the new model directory to determine the second name of the algorithm model currently capable of running on the target device. Finally, the name of the algorithm model that the target device can currently run is sent to the preset recipient, so that the preset recipient displays the second name on the configuration interface of the preset recipient.

[0057] Based on the needs of intelligent analysis tasks, the model loading device can add new algorithm models to meet the needs of obtaining more intelligent capabilities. In response to a user's import operation on the configuration display interface, the preset recipient imports the algorithm model corresponding to the import operation. The newly added algorithm model is the algorithm model corresponding to the import operation. The preset recipient can send the newly added algorithm model to the main card. In response to receiving the newly added algorithm model sent by the preset recipient, the main card can install the newly added algorithm model to the model directory. The main card traverses the new model directory to determine the name of the algorithm model currently capable of running on the target device. In some application scenarios, the main card traverses the new model directory to determine the second name of the algorithm model currently capable of running on the target device and can add the second name corresponding to the algorithm model. The main card then sends the name of the algorithm model currently capable of running on the target device to the preset recipient, so that the preset recipient displays the first name and the second name on the preset recipient's configuration interface. The first name can be the algorithm model that the target device could run before the newly added algorithm model was installed in the model directory. The second name can be the name of the newly added algorithm model.

[0058] It can be understood that before the above-mentioned main card receives the newly added algorithm model sent by the preset recipient, the algorithm model corresponding to the second name displayed on the configuration interface may be an algorithm model that the target device cannot run, or an algorithm model that each sub-card cannot load.

[0059] In some embodiments, after the above-mentioned step of the main card traversing the new model directory to determine the second name of the algorithm model that the target device can run, the model loading method may further include the following steps: first, sending a new notification corresponding to the newly added algorithm model to each sub-card so that each sub-card can load the newly added algorithm model. And / or, receiving a second model configuration instruction sent by a preset recipient, the second model configuration instruction is issued by the preset recipient in response to a second selection operation on the displayed algorithm model. Subsequently, sending the second model configuration instruction to the virtual bridge so that the virtual bridge forwards the second model configuration instruction to each sub-card.

[0060] In some application scenarios, the main card sends a notification corresponding to a newly added algorithm model to each sub-card, so that each sub-card can load the newly added algorithm model. The notification may be related to the newly added algorithm model. The notification may indicate the loading parameter information of the newly added algorithm model on each sub-card. For example, the newly added algorithm model may be algorithm model B. After each sub-card receives the notification, each sub-card may obtain the loading parameter information of algorithm model B stored on the main card through a communication connection with the virtual network bridge. Based on the loading parameter information corresponding to the newly added algorithm model, each sub-card may load the newly added algorithm model B on each sub-card. It is understood that after receiving the notification corresponding to the newly added algorithm model, each sub-card may pre-load the newly added algorithm model, so that the newly added algorithm model is already loaded on each sub-card before the main card receives the second model configuration instruction sent by the predetermined recipient, or before the main card sends the second model configuration instruction to the virtual network bridge.

[0061] In some application scenarios, the main card receives a second model configuration instruction sent by a predetermined recipient. The second model configuration instruction is issued by the predetermined recipient in response to a second selection operation on a displayed algorithm model. The configuration interface of the predetermined recipient may display a selection button corresponding to the newly added algorithm model B. In response to the second selection operation on the selection button corresponding to the newly added algorithm model B, the predetermined recipient sends the second model configuration instruction corresponding to the newly added algorithm model B to the main card. After receiving the second model configuration instruction from the predetermined recipient, the main card sends the second model configuration instruction to the virtual bridge, so that the virtual bridge forwards the second model configuration instruction to each sub-card.

[0062] In other application scenarios, the main card sends a notification corresponding to the newly added algorithm model to each daughter card, so that each daughter card can load the newly added algorithm model. The main card receives a second model configuration instruction sent by a predetermined recipient, which is issued by the predetermined recipient in response to a second selection operation on the displayed algorithm model. The main card sends the second model configuration instruction to the virtual bridge, so that the virtual bridge forwards the second model configuration instruction to each daughter card.

[0063] In some embodiments, before the above-mentioned main card traverses the model directory to determine the first name of the algorithm model that the target device can run, the model loading method may also include the following steps: first, through the virtual network bridge, the main card mounts the model directory to each sub-card, so that each sub-card loads each algorithm model in the model directory.

[0064] The main card mounts the model directory to each daughter card. In some application scenarios, the main card mounts the algorithm models in the model directory that the target device can run to each daughter card, so that each daughter card loads each algorithm model in the model directory.

[0065] In some application scenarios, the main card can mount the loading parameter information in the model directory to each sub-card. The loading parameter information in the model directory corresponds to the algorithm model. After each sub-card obtains the target loading parameter information, each sub-card can load the algorithm model corresponding to the target loading parameter information in the model directory into each sub-card. Each sub-card can obtain the target loading parameter information sent by the main card through a virtual network bridge. The above-mentioned new notification may include target loading parameter information. The target loading parameter information in the new notification may point to the newly added algorithm model in the new model directory. After each sub-card obtains the target loading parameter information sent by the virtual network bridge, it loads the newly added algorithm model corresponding to the target loading parameter information mounted in each sub-card.

[0066] In the present application, the model loading device includes an intelligent-related module. The intelligent-related module can be a master control terminal or a master card involving an intelligent configuration module, a data display module, and a storage-related module. The intelligent-related module can be used for the master card to receive various model configuration instructions issued by a preset recipient and various model configuration instructions issued by the master card to a virtual network bridge. The data display module can be used for the master card to receive data analysis results from each sub-card and for the master card to forward each data analysis result to a preset recipient. The storage-related module can be a master card that can store algorithm models that can be run by target devices related to the model target. Among them, different algorithm models in the model directory are packaged independently. Specifically, the algorithm models corresponding to the major categories of intelligent services are packaged independently.

[0067] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0068] See also Figure 3 , Figure 3This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 1 .

[0069] The main card sequentially executes steps S31, S32, and S33. Step S31: The main card boots up in response to the target device where the main card is located. Step S32: Obtain the target network to which the target device is connected. Step S33: The main card determines whether the target network is the same as the preset network. If the result of step S33 is that the target network is different from the preset network, the main card may sequentially execute steps S34, S35, and S36. Step S34: The main card creates a virtual network bridge and virtual network cards corresponding to each sub-card. Step S35: Binds each virtual network card to each virtual port in the virtual network bridge. Step S36: Sends virtual network card configuration information to each sub-card. It will be understood that after step S36, the virtual network card configuration information is sent to each sub-card so that each sub-card can establish a connection with the virtual network card based on the virtual network card configuration information. The main card and each sub-card communicate based on the virtual network bridge.

[0070] If the result of step S33 is that the target network is the same as the preset network, the master card may proceed to step S37. Step S37: Adjust the preset network to another network. After executing step S37, the master card may control the target device to restart. After controlling the target device to restart, the master card may sequentially execute steps S31 and S32. After executing step S32, the master card may proceed to step S33. In this case, in step S33, the target network may be the network connected to the target device after the restart, and the preset network may be another network obtained after the preset network is adjusted after step S37. It is understood that step S33 may also include determining whether the target network connected to the target device after the restart is the same as the other network obtained after the preset network is adjusted. In other words, determining whether the target network is the same as the other network. If the result of step S33 is that the target network is different from the other network, the master card sequentially executes steps S34, S35, and S36. This enables the master card to establish a communication connection with each sub-card in the target device. The main card communicates with each sub-card based on a virtual network bridge.

[0071] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0072] See also Figure 4 , Figure 4 This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 2 .

[0073] Step S41: The main card traverses the current model directory to determine the names of algorithm models that the target device can run. It is understood that step S41 may involve the main controller in the main card traversing the current model directory to determine the names of algorithm models that the target device can run. The main controller in the main card may obtain the intelligent capabilities corresponding to the algorithm models supported by the target device. In some application scenarios, after the main card determines the names of the algorithm models that the target device can run, it may send target loading parameter information to each daughter card, so that each daughter card can load the target algorithm model based on the target loading parameter information. The target algorithm model may be the algorithm model that the main card determines the target device can run. Specifically, the main card sends the target loading parameter information to the virtual network bridge, so that the virtual network bridge forwards the target loading parameter information to each daughter card. It is understood that the name of the algorithm model that the target device can run may be the first name described above or the second name described above. The target algorithm model may be the algorithm model corresponding to the first model configuration instruction or a newly added algorithm model corresponding to the second model configuration instruction. The target loading parameter information may be sent to each daughter card after the main card traverses the current model directory to determine the names of the algorithm models that the target device can run.

[0074] In some application scenarios, after step S41, the master card may determine the first name of the algorithm model. The master card may send a first model configuration instruction corresponding to the first name of the algorithm model to the slave card. In other application scenarios, after step S41, the master card may determine the second name of the algorithm model. The master card may send a second model configuration instruction corresponding to the second name of the algorithm model to the slave card.

[0075] The master card sends the first name of each algorithm model to a predetermined recipient, so that the predetermined recipient displays the first name of each algorithm model on its configuration interface. The master card receives a first model configuration instruction sent by the predetermined recipient, the first model configuration instruction being issued by the predetermined recipient in response to a selection operation on a displayed algorithm model. The master card sends the first model configuration instruction to a virtual network bridge, so that the virtual network bridge forwards the first model configuration instruction to each daughter card.

[0076] Step S42: Sending a target model configuration instruction to each sub-card, so that each sub-card performs data analysis using an algorithm model corresponding to the target model configuration instruction after receiving the target model configuration instruction.

[0077] It is understandable that the algorithm model corresponding to the target model configuration instruction can be pre-loaded in each daughter card of the target device. After waiting for the main card to send the target model configuration instruction to each daughter card, each daughter card can receive the target model configuration instruction. Based on the target model configuration instruction, each daughter card activates the algorithm model corresponding to the pre-loaded target model configuration instruction, so that the algorithm model corresponding to the target model configuration instruction performs data analysis and obtains the target data analysis result. Each daughter card can send the target data analysis result output by the algorithm model corresponding to the target model configuration instruction to the virtual bridge, so that the virtual bridge forwards the target data analysis result to the main card.

[0078] It is understandable that the target model configuration instruction can be a first model configuration instruction or a second model configuration instruction. The algorithm model corresponding to the target model configuration instruction can be a target algorithm model. Specifically, the target algorithm model can be the initial algorithm model corresponding to the first model configuration instruction or a newly added algorithm model corresponding to the second model configuration instruction.

[0079] After step S42, the master card may also receive target data analysis results from each sub-card. Each target data analysis result is obtained by each sub-card after running the target algorithm model and performing data analysis on the data to be analyzed based on the target parameter information. The target model configuration instruction may include target parameter information for the target algorithm model. The target parameter information may be data input for the target algorithm model. The target parameter information may also be call information for the data input of the target algorithm model. Based on this call information, each sub-card may call data from a relevant database as data input. Based on this call information, each sub-card may obtain the data stream required for the intelligent analysis task as data input. It is understood that each sub-card may obtain the data input of the target algorithm model based on the target parameter information, so that the target algorithm model performs data analysis on the target algorithm model based on the data input to obtain the target data analysis result. Each sub-card may send the target data analysis result to the master card.

[0080] Step S43: The master card forwards each target data analysis result to a preset recipient, so that the preset recipient displays the target data analysis result.

[0081] The main card receives the target data analysis results. It is understood that the target data analysis results received by the main card may be the target data analysis results sent by each sub-card forwarded to the main card by the virtual bridge. The main card may forward the target data analysis results to a predetermined recipient, so that the predetermined recipient displays the target data analysis results on a display interface.

[0082] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0083] See also Figure 5 , Figure 5 This is a schematic diagram of the working of the main card in the embodiment of the model loading method of this application. Figure 3 .

[0084] Step S501: The master card traverses the model directory to determine the first name of an algorithm model that the target device can run. Prior to step S501, the target device boots up. In response to the target device booting up, each daughter card automatically boots up and mounts the master control model directory. Specifically, each daughter card mounts the algorithm package path in the model directory. After mounting the model directory, each daughter card launches its own intelligent program. It is understood that after mounting the model directory, each daughter card launches its own intelligent program, which can be an algorithm model that the target device can run, and in this case, the algorithm model supported by the target device. Launching each daughter card's intelligent program can be considered as preloading the initial algorithm model that the target device can run. The initial algorithm model can be the algorithm model that each daughter card can preload based on the mounted model directory before adding new algorithm capabilities. After completing the preloading of the initial algorithm model, each daughter card waits for the target algorithm model configuration instruction to be issued to each daughter card, thereby implementing data analysis. Step S501 can be in response to the target device booting up, with the master card traversing the model directory. Specifically, the master card traverses the algorithm package installation path and obtains the device's intelligent capabilities. As can be understood, assuming the target device has algorithm model A installed, the algorithm capability supported by the target device is algorithm package [A]. The master card traverses the model directory to determine that the first algorithm model that the target device can run is named A.

[0085] Step S502: The master card sends the first name of each algorithm model to a preset recipient.

[0086] The main card sends the first name of each algorithm model to the preset recipient. The main card can report the algorithm capability A supported by the target device to the preset recipient. It can be understood that the main card can send the name of the algorithm capability supported by the target device to the preset recipient, thereby completing the main card reporting the algorithm capability to the preset recipient. After step S502, the display interface of the preset recipient can display the first name A of the algorithm model currently supported by the target device. The preset recipient can generate a first model configuration instruction in response to the selection operation of the displayed algorithm model. The preset recipient can send the first model configuration instruction to the main card.

[0087] Step S503: The primary card receives a first model configuration instruction sent by a preset recipient.

[0088] Step S504: the main card sends a first model configuration instruction to the virtual network bridge, so that the virtual network bridge forwards the first model configuration instruction to each sub-card.

[0089] After step S504, each daughter card can set the algorithm configuration corresponding to algorithm model A based on the received first model configuration instruction, implement data analysis of algorithm model A, and obtain data analysis results. After obtaining the data analysis results, each daughter card can forward the data analysis results to the virtual bridge to the main card.

[0090] Step S505: The master card obtains the first data analysis result and sends it to the preset recipient. After obtaining the first data analysis result forwarded by the virtual network bridge, the master card sends it to the preset recipient. After receiving the data analysis result, the preset recipient displays the first data analysis result on its display interface.

[0091] Step S506: The primary card receives the newly added algorithm model sent by the preset recipient.

[0092] The preset recipient can import algorithm model B, also known as algorithm package B. The preset recipient sends the package to the master card for installation. The master card receives the newly added algorithm model B sent by the preset recipient.

[0093] Step S507: The master card installs the newly added algorithm model into the model directory to obtain a new model directory.

[0094] The main card installs the newly added algorithm model B into the model directory, creating a new model directory. It is understood that the main card can install the newly added algorithm model B into the model directory using a specified installation path. The newly added algorithm model B can be a corresponding algorithm package B. Each algorithm package is independently packaged within the installation path within the model directory. The algorithm package can correspond to the algorithm's dynamic library and algorithm model, and the algorithm package file name is named using the intelligent business category.

[0095] Step S508: The master card traverses the new model directory to determine the second name of the algorithm model that the target device can currently run.

[0096] After the main card completes the installation of the newly added algorithm model B, it traverses the new model directory (that is, the algorithm package installation directory) again to obtain the capabilities supported by the current target device. It is understandable that at this time, the algorithm capabilities that the target device can support are algorithm model A and the newly added algorithm model B. The main card reports the capabilities to the preset recipient, and at the same time, the main card knows that the sub-card reacquires the algorithm capabilities. In other application scenarios, after step S508, the display interface of the preset recipient can display the second name A and B of the algorithm model currently supported by the target device. The preset recipient can generate a second model configuration instruction in response to the selection operation of the displayed algorithm model. It is understandable that the second model configuration instruction can be to send down the configuration only for algorithm model A or to send down the configuration only for algorithm model B or to send down the configuration only for algorithm models A and B.

[0097] Step S509: The master card sends the name of the algorithm model that the target device can currently run to the preset recipient.

[0098] The algorithm capabilities reported by the master card to the preset recipient may specifically be that the algorithm capabilities supported by the target device are algorithm model A and the newly added algorithm model B.

[0099] Step S510: The master card sends a notification corresponding to the newly added algorithm model to each daughter card, allowing each daughter card to load the newly added algorithm model. The notification allows each daughter card to reacquire the algorithm capabilities of the target device. Specifically, each daughter card can be restarted to obtain the algorithm capabilities supported by the target device, pre-loaded with algorithm model A and the newly added algorithm model B. Each daughter card can also obtain the pre-load corresponding to the newly added algorithm model B based only on the notification, without repeatedly pre-loading algorithm model A. Each daughter card loads the newly added algorithm model B. Each daughter card then waits for the master card to issue a second model configuration instruction.

[0100] Step S511: the master card receives a second model configuration instruction sent by a preset recipient.

[0101] After receiving the second model configuration instruction sent by the preset recipient, the main card sends the second model configuration instruction to the virtual network bridge.

[0102] Step S512: the main card sends a second model configuration instruction to the virtual network bridge, so that the virtual network bridge forwards the second model configuration instruction to each sub-card.

[0103] For example, the second model configuration instruction is used to configure algorithm models A and B. After step S512, each daughter card receives the second model configuration instruction and can set the corresponding algorithm configurations for algorithm model A and the newly added algorithm model B based on the received second model configuration instruction, perform data analysis for algorithm model A and the newly added algorithm model B, and obtain second data analysis results. After obtaining the second data analysis results, each daughter card can forward the second data analysis results to the virtual bridge to the master card.

[0104] Step S513: The master card obtains the second data analysis result and sends it to the preset recipient. After obtaining the second data analysis result forwarded by the virtual network bridge, the master card sends it to the preset recipient. After receiving the second data analysis result, the preset recipient displays the second data analysis result on its display interface. The preset recipient's display interface displays the relevant interfaces corresponding to the second data analysis results corresponding to the data of algorithm model A and the newly added algorithm model B.

[0105] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0106] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of an embodiment of the model loading device of the present application. The model loading device 60 includes a judgment module 61, an establishment module 62, and a sending module 63. The judgment module 61 is used by the main card to respond to the target device where the main card is located and determine whether the target network connected to the target device is the same as the preset network. The target device includes the main card and at least one sub-card; the establishment module 62 is used to establish a communication connection between the main card and each sub-card in the target device in response to the target network being different from the preset network; and the sending module 63 is used to send a first model configuration instruction to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction.

[0107] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0108] Please refer to the model loading method for the functions performed by each module, which will not be repeated here.

[0109] See also Figure 7 , Figure 7 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. Electronic device 70 includes memory 71 and processor 72. Processor 72 is configured to execute program instructions stored in memory 71 to implement the steps of the above-described model loading method embodiment. In a specific implementation scenario, electronic device 70 may include, but is not limited to, a microcomputer and a server. Furthermore, electronic device 70 may also include mobile devices such as laptops and tablet computers, which are not limited herein.

[0110] Specifically, the processor 72 is used to control itself and the memory 71 to implement the steps in the above-mentioned model loading method embodiment. The processor 72 can also be called a CPU (Central Processing Unit). The processor 72 may be an integrated circuit chip with signal processing capabilities. The processor 72 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 72 can be implemented by an integrated circuit chip.

[0111] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0112] See also Figure 8 , Figure 8 The computer-readable storage medium 80 stores program instructions 801, which, when executed by a processor, implement the steps of any of the above-mentioned model loading method embodiments.

[0113] In the above scheme, the target device includes a main card and at least one sub-card. The main card is started in response to the target device where the main card is located. In response to the target network connected to the target device being different from the preset network, a communication connection is established between the main card and each sub-card in the target device, and a first model configuration instruction is sent to each sub-card so that each sub-card performs data analysis using the algorithm model corresponding to the model configuration instruction after receiving the model configuration instruction. Compared with the situation where the sub-card cannot perform data analysis due to network conflicts, the present application can improve the effectiveness of model loading.

[0114] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0115] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation methods described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, 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, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0117] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various implementation methods of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

Claims

1. A model loading method, characterized in that: The method comprises: The main card is activated in response to a target device where the main card is located, and determines whether a target network accessed by the target device is the same as a preset network, wherein the target device includes the main card and at least one sub-card; In response to the target network being different from the preset network, establishing a communication connection between the main card and each of the sub-cards in the target device; A first model configuration instruction is sent to each of the daughter cards so that each of the daughter cards performs data analysis using an algorithm model corresponding to the first model configuration instruction after receiving the first model configuration instruction.

2. The method according to claim 1, characterized in that The method further comprises: In response to the target network being the same as the preset network, adjusting the preset network to another network, where the other network is different from the target network; The target device is controlled to restart, wherein the network to which the target device accesses after restarting is the target network.

3. The method according to claim 1, characterized in that The establishing of a communication connection between the main card and each sub-card in the target device includes: The main card creates a virtual network bridge and a virtual network card corresponding to each of the sub-cards; Binding each of the virtual network cards to each virtual port in the virtual network bridge; The configuration information of the virtual network card is sent to each of the sub-cards, so that each of the sub-cards establishes a connection with each of the virtual network cards based on the configuration information of the virtual network card, wherein the main card and each of the sub-cards communicate based on the virtual network bridge.

4. The method according to claim 3, characterized in that The method further comprises: The master card traverses the model directory to determine the first name of the algorithm model that the target device can run, and the model directory is used to record the first name of the algorithm model that the target device can run; Sending the first name of each algorithm model to a preset recipient, so that the preset recipient displays the first name of each algorithm model on a configuration interface of the preset recipient; receiving a first model configuration instruction sent by the preset recipient, where the first model configuration instruction is sent by the preset recipient in response to a selection operation on a displayed algorithm model; The sending the first model configuration instruction to each of the sub-cards includes: The first model configuration instruction is sent to the virtual network bridge, so that the virtual network bridge forwards the first model configuration instruction to each of the daughter cards.

5. The method according to claim 4, characterized in that The first model configuration instruction also includes parameter information of the data to be analyzed, and the method further includes: receiving data analysis results of each of the sub-cards, where each of the data analysis results is obtained by each of the sub-cards performing data analysis on the data to be analyzed based on the parameter information after running an algorithm model; Forwarding each of the data analysis results to the preset recipient so that the preset recipient displays the data analysis result.

6. The method according to claim 4, characterized in that The method further comprises: Receiving a newly added algorithm model sent by the preset recipient, where the newly added algorithm model is the algorithm model imported by the preset recipient; Install the newly added algorithm model to the model directory to obtain a new model directory; The master card traverses the new model directory to determine the second name of the algorithm model that the target device can currently run; The name of the algorithm model that the target device can currently run is sent to a preset recipient, so that the preset recipient displays the second name on the configuration interface of the preset recipient.

7. The method according to claim 6, characterized in that After the master card traverses the new model directory to determine the second name of the algorithm model that can be run by the target device, the method further includes: Sending a new notification corresponding to the new algorithm model to each of the sub-cards so that each of the sub-cards loads the new algorithm model; And / or, receiving a second model configuration instruction sent by the preset recipient, wherein the second model configuration instruction is issued by the preset recipient in response to a second selection operation on the displayed algorithm model; sending the second model configuration instruction to the virtual bridge so that the virtual bridge forwards the second model configuration instruction to each of the sub-cards.

8. The method according to claim 4, characterized in that Before the master card traverses the model directory to determine the first name of the algorithm model that can be run by the target device, the method further includes: Through the virtual network bridge, the main card mounts the model directory to each of the sub-cards, so that each of the sub-cards loads each algorithm model in the model directory.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores program instructions, and the processor calls the program instructions from the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that include: A program file is stored, and when the program file is executed by a processor, it is used to implement the method according to any one of claims 1 to 8.

Images