Method, device and equipment for monitoring operation of fusion gateway based on artificial intelligence

Abstract

The artificial intelligence-based fusion gateway operation monitoring method, device and equipment provided in this application relate to the field of artificial intelligence technology. In this application, first, the hardware operation status data and hardware operation environment data of the target fusion gateway are obtained; secondly, semantic feature mining operations are performed on the hardware operation status data and the hardware operation environment data respectively, and the hardware operation status features corresponding to the hardware operation status data and the hardware operation environment features corresponding to the hardware operation environment data are output; then, based on the hardware operation environment features, a focused mining operation is performed on the hardware operation status features, and the state environment focused features are output; finally, the operation status is evaluated based on the state environment focused features, and the operation status evaluation results are obtained to realize the operation monitoring of the target fusion gateway. Based on the above content, the problem of relatively low reliability of the operation monitoring of the fusion gateway existing in the prior art can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to an artificial intelligence-based fusion gateway operation monitoring method, device, and equipment. Background Art

[0002] With the rapid development of information technology and the continuous innovation of artificial intelligence, converged gateways, as key devices connecting multiple networks and systems, have been widely used in various information processing and communication scenarios, such as the Internet of Things, smart homes, and industrial automation. The main function of converged gateways is to effectively integrate devices with different communication protocols and data formats, enabling unified information management and transmission.

[0003] For example, an IPTV converged gateway is a device that integrates an optical modem and a set-top box in the same housing, and can simultaneously realize the functions of fiber-optic Internet access (such as OTT services, Over-The-Top, which refers to the transmission of video, audio and other media content through the Internet without the transmission pipeline of traditional TV service providers) and watching TV (such as IPTV services, Internet Protocol Television, which uses the Internet protocol to transmit TV programs and video content. Unlike traditional cable or satellite TV, IPTV uses the Internet as a transmission medium, allowing users to watch TV content through a network connection).

[0004] However, in the existing technology, there are still some shortcomings in the operation monitoring of the integrated gateway. For example, the current integrated gateway operation status monitoring methods mostly rely on traditional threshold detection and periodic inspection methods. This method is difficult to obtain and analyze the hardware operation status in real time and accurately. Therefore, there is a problem that the reliability of the operation monitoring of the integrated gateway is relatively low. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide an artificial intelligence-based fusion gateway operation monitoring method, device and equipment to improve the problem of relatively low reliability of fusion gateway operation monitoring in the prior art.

[0006] To achieve the above objectives, this application adopts the following technical solutions:

[0007] An artificial intelligence-based fusion gateway operation monitoring method, comprising:

[0008] Obtaining hardware operating status data and hardware operating environment data of the target converged gateway, wherein the hardware operating status data is used to reflect the operating status of at least one hardware device in the target converged gateway, and the hardware operating environment data includes environmental data of the at least one hardware device, and the environmental data includes at least temperature data and power supply data;

[0009] Performing semantic feature mining operations on the hardware operating state data and the hardware operating environment data respectively through a semantic feature mining unit included in an operating state evaluation model, and outputting hardware operating state features corresponding to the hardware operating state data and hardware operating environment features corresponding to the hardware operating environment data, wherein the operating state evaluation model is a neural network model, and the operating state evaluation model further includes a focus mining unit and an operating state evaluation unit;

[0010] By means of the focused mining unit, a focused mining operation is performed on the hardware operating state feature based on the hardware operating environment feature, and a state environment focused feature is output, wherein the state environment focused feature is used to reflect semantic information associated with the hardware operating environment feature mined from the hardware operating state feature;

[0011] The operating status evaluation unit evaluates the operating status of the target fusion gateway based on the state environment focus feature, and obtains the operating status evaluation result corresponding to the target fusion gateway, so as to realize the operation monitoring of the target fusion gateway.

[0012] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the semantic feature mining unit included in the operation status evaluation model performs semantic feature mining operations on the hardware operation status data and the hardware operation environment data, respectively, and outputs the hardware operation status features corresponding to the hardware operation status data and the hardware operation environment features corresponding to the hardware operation environment data, including:

[0013] Performing semantic embedding operations on the hardware operating state data and the hardware operating environment data respectively through a semantic embedding subunit in a semantic feature mining unit included in the operating state evaluation model, and outputting operating state embedding features corresponding to the hardware operating state data and operating environment embedding features corresponding to the hardware operating environment data;

[0014] Performing a deep mining operation on the operating status embedded feature through the first deep mining sub-unit in the semantic feature mining unit to output the hardware operating status feature corresponding to the hardware operating status data;

[0015] A first deep mining sub-unit in the semantic feature mining unit performs a deep mining operation on the operating environment embedded features, and outputs hardware operating environment features corresponding to the hardware operating environment data.

[0016] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the step of performing a deep mining operation on the operation status embedded feature through the first deep mining sub-unit in the semantic feature mining unit and outputting the hardware operation status feature corresponding to the hardware operation status data includes:

[0017] Loading the operating state embedded feature into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a first mapping branch and a second mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping;

[0018] Performing self-attention processing on the running state embedded feature to form a running state attention feature corresponding to the running state embedded feature;

[0019] Performing a mapping operation on the running state attention feature through the first mapping branch to form a first running state mapping feature corresponding to the running state attention feature;

[0020] performing a mapping operation on the running state attention feature through the second mapping branch to form a second running state mapping feature corresponding to the running state attention feature;

[0021] Cross-attention processing is performed on the first operating state mapping feature and the second operating state mapping feature to form a hardware operating state feature corresponding to the hardware operating state data.

[0022] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the step of performing a deep mining operation on the embedded features of the operating environment by the first deep mining sub-unit in the semantic feature mining unit and outputting the hardware operating environment features corresponding to the hardware operating environment data includes:

[0023] Loading the runtime environment embedded features into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a third mapping branch and a fourth mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping;

[0024] Performing self-attention processing on the operating environment embedded feature to form an operating environment attention feature corresponding to the operating environment embedded feature;

[0025] Performing a mapping operation on the operating environment attention feature through the third mapping branch to form a first operating environment mapping feature corresponding to the operating environment attention feature;

[0026] performing a mapping operation on the operating environment attention feature through the fourth mapping branch to form a second operating environment mapping feature corresponding to the operating environment attention feature;

[0027] Cross-attention processing is performed on the first operating environment mapping feature and the second operating environment mapping feature to form a hardware operating environment feature corresponding to the hardware operating environment data.

[0028] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the step of performing a focused mining operation on the hardware operation status feature based on the hardware operation environment feature by the focused mining unit and outputting the state environment focused feature includes:

[0029] performing a first focused mining operation on the hardware operating state feature based on the hardware operating environment feature through a first focused branch in the focused mining unit, and outputting a first focused feature;

[0030] performing a second focused mining operation on the hardware operating state feature based on the hardware operating environment feature through a second focused branch in the focused mining unit, and outputting a second focused feature;

[0031] Perform mean calculation on the first focus feature, the second focus feature, and the hardware operating state feature, and output a state environment focus feature.

[0032] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the step of performing a first focused mining operation on the hardware operation status feature based on the hardware operation environment feature through the first focused branch in the focused mining unit and outputting the first focused feature includes:

[0033] Performing a first spatial conversion operation on the hardware operating environment feature using a first spatial conversion matrix of a first focusing branch in the focused mining unit, so that the hardware operating environment feature is converted from a current semantic space to a semantic space where the hardware operating state feature is located, thereby obtaining a corresponding operating environment conversion feature;

[0034] Determine the associated parameter distribution between the operating environment conversion feature and the hardware operating status feature, and after normalizing the associated parameter distribution, perform weighted processing on the hardware operating status feature based on the normalized associated parameter distribution to output a first focused feature.

[0035] In a preferred embodiment of the present application, in the above-mentioned artificial intelligence-based fusion gateway operation monitoring method, the step of performing a second focused mining operation on the hardware operation status feature based on the hardware operation environment feature through the second focused branch in the focused mining unit and outputting the second focused feature includes:

[0036] Performing a second spatial conversion operation on the hardware operating state feature using a second spatial conversion matrix of a second focusing branch in the focused mining unit, so that the hardware operating state feature is converted from a current semantic space to a semantic space where the hardware operating environment feature is located, thereby obtaining a corresponding operating state conversion feature;

[0037] Determine the associated parameter distribution between the hardware operating environment feature and the operating state transition feature, and after normalizing the associated parameter distribution, perform weighted processing on the operating state transition feature based on the normalized associated parameter distribution to output a second focused feature.

[0038] In a preferred embodiment of the present application, the above-mentioned artificial intelligence-based fusion gateway operation monitoring method further includes:

[0039] Obtain hardware operating status samples and hardware operating environment samples;

[0040] Performing semantic feature mining operations on the hardware operating state sample and the hardware operating environment sample respectively through the semantic feature mining unit included in the candidate operating state evaluation model, and outputting hardware operating state features corresponding to the hardware operating state sample and hardware operating environment features corresponding to the hardware operating environment sample;

[0041] By using the focused mining unit included in the candidate operating state evaluation model, a focused mining operation is performed on the hardware operating state features corresponding to the hardware operating state sample based on the hardware operating environment features corresponding to the hardware operating environment sample, and a state environment focused feature sample is output;

[0042] By using the operation status evaluation unit included in the candidate operation status evaluation model, the operation status of the corresponding fusion gateway is evaluated based on the state environment focus feature sample to obtain corresponding operation status evaluation data;

[0043] Based on the error between the running status evaluation data and the running status label of the corresponding fusion gateway, the model parameters of the candidate running status evaluation model are updated until the error converges, thereby obtaining a trained running status evaluation model.

[0044] This application also provides an artificial intelligence-based fusion gateway operation monitoring device, including:

[0045] An operation data acquisition module is used to obtain hardware operation status data and hardware operation environment data of the target converged gateway, wherein the hardware operation status data is used to reflect the operation status of at least one hardware device in the target converged gateway, and the hardware operation environment data includes environmental data of the at least one hardware device, and the environmental data includes at least temperature data and power supply data;

[0046] a semantic feature mining module, configured to perform semantic feature mining operations on the hardware operating state data and the hardware operating environment data respectively through a semantic feature mining unit included in an operating state evaluation model, and output hardware operating state features corresponding to the hardware operating state data and hardware operating environment features corresponding to the hardware operating environment data, wherein the operating state evaluation model is a neural network model and further includes a focus mining unit and an operating state evaluation unit;

[0047] a focused mining module, configured to perform a focused mining operation on the hardware operating state feature based on the hardware operating environment feature through the focused mining unit, and output a state environment focused feature, wherein the state environment focused feature is used to reflect semantic information associated with the hardware operating environment feature mined from the hardware operating state feature;

[0048] An operation status evaluation module is used to evaluate the operation status of the target fusion gateway based on the state environment focus feature through the operation status evaluation unit, and obtain the operation status evaluation result corresponding to the target fusion gateway to realize operation monitoring of the target fusion gateway.

[0049] Based on the above, the present application further provides an electronic device, including:

[0050] memory for storing computer programs;

[0051] The processor connected to the memory is used to execute the computer program stored in the memory to implement the above-mentioned artificial intelligence-based fusion gateway operation monitoring method.

[0052] The present application provides an artificial intelligence-based fusion gateway operation monitoring method, device, and equipment. First, the hardware operation status data and hardware operation environment data of the target fusion gateway are obtained; secondly, semantic feature mining operations are performed on the hardware operation status data and the hardware operation environment data respectively, and the hardware operation status features corresponding to the hardware operation status data and the hardware operation environment features corresponding to the hardware operation environment data are output. Then, a focused mining operation is performed on the hardware operation status features based on the hardware operation environment features to output the state environment focused features; finally, the operation status is evaluated based on the state environment focused features to obtain the operation status evaluation results, so as to realize the operation monitoring of the target fusion gateway. Based on the above content, on the one hand, the powerful learning ability of the neural network model is utilized to improve the reliability of the operation status evaluation to a certain extent. On the other hand, since after obtaining the hardware operation status features, focused mining is also performed based on the hardware operation environment features, semantic features with higher representation accuracy, namely, state environment focused features, can be further mined. Therefore, when the state evaluation is performed based on the state environment focused features, it can have a higher reliability, thereby improving the relatively low reliability problem of the operation monitoring of the fusion gateway in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings.

[0054] Figure 1 This is a structural block diagram of the electronic device provided in an embodiment of the present application.

[0055] Figure 2 A flowchart of an artificial intelligence-based fusion gateway operation monitoring method provided in an embodiment of the present application.

[0056] Figure 3 A schematic diagram of semantic feature mining provided in an embodiment of the present application.

[0057] Figure 4 A schematic diagram of focused mining provided in an embodiment of the present application.

[0058] Figure 5 A block diagram of an artificial intelligence-based fusion gateway operation monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0060] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0061] like Figure 1 As shown, an embodiment of the present application provides an electronic device. The electronic device may include a memory, a processor, and an artificial intelligence-based fusion gateway operation monitoring device.

[0062] In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, the memory and the processor can be electrically connected through one or more communication buses or signal lines. The artificial intelligence-based fusion gateway operation monitoring device includes at least one software function module stored in the memory in the form of software or firmware. The processor is used to execute the executable computer program stored in the memory, for example, the software function module and computer program included in the artificial intelligence-based fusion gateway operation monitoring device, so as to realize the artificial intelligence-based fusion gateway operation monitoring method provided in the embodiment of the present application.

[0063] Optionally, the memory may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0064] Furthermore, the processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be 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.

[0065] I understand. Figure 1 The structure shown is for illustration only. The electronic device may also include Figure 1 More or fewer components than shown, or with Figure 1 The different configurations shown may, for example, further include a communication unit for exchanging information with other devices.

[0066] Combine Figure 2 , the embodiment of the present application also provides an artificial intelligence-based integrated gateway operation monitoring method applicable to the above electronic device. Among them, the method steps defined in the process related to the artificial intelligence-based integrated gateway operation monitoring method can be implemented by the electronic device. Figure 2 The specific process shown is explained in detail.

[0067] Step S110: Acquire the hardware operating status data and hardware operating environment data of the target converged gateway.

[0068] In an embodiment of the present application, the electronic device can obtain the hardware operating status data and hardware operating environment data of the target fusion gateway. Wherein, the hardware operating status data is used to reflect the operating status of at least one hardware device in the target fusion gateway, and the hardware operating environment data includes the environmental data of the at least one hardware device, and the environmental data includes at least temperature data and power supply data. Exemplarily, the hardware status data may include CPU usage (high CPU load may cause the device to respond slowly or crash), memory usage (memory leak or overload may cause device performance to decline), disk read speed, disk write speed, disk usage (high disk utilization may mean that the hard disk is heavily loaded, which may affect performance) and disk bad sectors, etc. In other embodiments, more or different hardware operating states may also be included. In addition, the hardware operating environment data may refer to the temperature data and power supply data corresponding to the aforementioned hardware devices, wherein the power supply data may refer to voltage, current (fluctuations in voltage and current may also affect the status of the corresponding hardware), etc. In other embodiments, other data may also be included. In addition, both the hardware operating status data and the hardware operating environment data can be represented in text form.

[0069] Step S120, through the semantic feature mining unit included in the operation status evaluation model, semantic feature mining operations are performed on the hardware operation status data and the hardware operation environment data respectively, and the hardware operation status features corresponding to the hardware operation status data and the hardware operation environment features corresponding to the hardware operation environment data are output.

[0070] In an embodiment of the present application, after obtaining the hardware operating status data and the hardware operating environment data, the electronic device can perform semantic feature mining operations on the hardware operating status data and the hardware operating environment data respectively through the semantic feature mining unit included in the operating status evaluation model, and output the hardware operating status features corresponding to the hardware operating status data and the hardware operating environment features corresponding to the hardware operating environment data (for example, in an embodiment of the present application, the expression form of each feature can be a vector, that is, the potential semantic information is mined and represented in the form of a vector). Wherein, the operating status evaluation model is a neural network model (which can be formed by learning based on the corresponding samples and labels on the basis of the initial neural network model), and the operating status evaluation model also includes a focus mining unit and an operating status evaluation unit.

[0071] Step S130 : performing a focused mining operation on the hardware operating state feature based on the hardware operating environment feature through the focused mining unit, and outputting a state environment focused feature.

[0072] In an embodiment of the present application, after mining the hardware operating environment features and the hardware operating status features, the electronic device can perform a focused mining operation on the hardware operating status features based on the hardware operating environment features through the focused mining unit, and output a state environment focused feature. The state environment focused feature is used to reflect the semantic information associated with the hardware operating environment features mined from the hardware operating status features. That is, since the semantic information of one dimension has an associated relationship with the semantic information of another dimension, it can be shown that the corresponding semantic information is important. In this way, it can be mined, thereby achieving the focus on important semantic information and improving the semantic representation ability of the state environment focused feature.

[0073] Step S140 , the operating status evaluation unit evaluates the operating status of the target converged gateway based on the state environment focus feature, and obtains an operating status evaluation result corresponding to the target converged gateway to implement operation monitoring of the target converged gateway.

[0074] In an embodiment of the present application, after obtaining the state environment focus feature, the electronic device can evaluate the operation state of the target fusion gateway based on the state environment focus feature through the operation state evaluation unit, and obtain the operation state evaluation result corresponding to the target fusion gateway, so as to realize the operation monitoring of the target fusion gateway. Exemplarily, the operation state evaluation unit can perform full connection processing on the state environment focus feature to obtain the corresponding fully connected feature, wherein the size of the fully connected feature can be 1*n, and n can be the number of operation state types (such as good, general, and poor, a total of 3 types of operation states). Then, the fully connected feature can be mapped and output based on the softmax function to obtain the probability of each operation state type. Finally, the operation state type with the highest probability can be used as the operation state evaluation result.

[0075] Based on the above, the powerful learning capabilities of neural network models are leveraged to improve the reliability of operational status assessments to a certain extent. Furthermore, after obtaining hardware operational status features, focused mining is performed based on hardware operational environment features, allowing for the extraction of even more accurate semantic features, namely, state-environment-focused features. Consequently, when assessing status based on state-environment-focused features, reliability is increased, thereby improving the relatively low reliability of converged gateway operational monitoring in existing technologies.

[0076] In the embodiment of the present application, it is also necessary to explain that for step S120, the specific method of performing semantic feature mining operations on the hardware operating status data and the hardware operating environment data respectively is not limited and can be selected accordingly according to actual needs.

[0077] For example, in an alternative embodiment, in order to capture more detailed information in the process of semantic feature mining, the above step S120 may further include step S121, step S122 and step S123, and the specific content of each step is as follows (combined with Figure 3 ).

[0078] Step S121, through the semantic embedding sub-unit in the semantic feature mining unit included in the operation status evaluation model, semantic embedding operations are performed on the hardware operation status data and the hardware operation environment data respectively, and the operation status embedding features corresponding to the hardware operation status data and the operation environment embedding features corresponding to the hardware operation environment data are output.

[0079] In an embodiment of the present application, the semantic embedding subunit in the semantic feature mining unit included in the operating status evaluation model can be used to perform semantic embedding operations on the hardware operating status data and the hardware operating environment data, respectively, to output operating status embedding features corresponding to the hardware operating status data and operating environment embedding features corresponding to the hardware operating environment data. The semantic embedding subunit can be a word embedding model, so that the corresponding data can be segmented and embedded, and then the embedding vectors of each word can be spliced ​​or cascaded to form corresponding operating status embedding features and operating environment embedding features.

[0080] Step S122 : performing a deep mining operation on the operation status embedded feature through the first deep mining sub-unit in the semantic feature mining unit, and outputting the hardware operation status feature corresponding to the hardware operation status data.

[0081] In an embodiment of the present application, after obtaining the operating status embedded feature, the operating status embedded feature can be deep mined by the first deep mining sub-unit in the semantic feature mining unit to output the hardware operating status feature corresponding to the hardware operating status data. In this way, the deep semantic information in the operating status embedded feature can be captured, thereby improving the semantic representation capability of the hardware operating status feature.

[0082] Step S123 , performing a deep mining operation on the operating environment embedded features through the first deep mining sub-unit in the semantic feature mining unit, and outputting the hardware operating environment features corresponding to the hardware operating environment data.

[0083] In an embodiment of the present application, after obtaining the operating environment characteristics, the first deep mining sub-unit in the semantic feature mining unit can be used to perform deep mining operations on the operating environment embedded characteristics to output the hardware operating environment characteristics corresponding to the hardware operating environment data. In this way, the deep semantic information in the operating environment embedded characteristics can be captured, thereby improving the semantic representation capability of the hardware operating environment characteristics.

[0084] It is understood that, in the above step S122, the specific manner of performing the deep mining operation on the operating status embedded feature is not limited. For example, in an alternative embodiment, in order to improve the reliability of the deep mining operation, the above step S122 may include the following:

[0085] First, the operating state embedding feature can be loaded into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a first mapping branch and a second mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping;

[0086] Secondly, self-attention processing can be performed on the operating state embedded feature to form an operating state attention feature corresponding to the operating state embedded feature. Based on this, since the operating state embedded feature contains state semantic information of multiple hardware devices, and the states of hardware devices generally have a correlation, by performing self-attention processing on the operating state embedded feature, the state semantic information of different hardware devices can be associated and fused.

[0087] Then, the running state attention feature can be mapped by the first mapping branch to form a first running state mapping feature corresponding to the running state attention feature; exemplarily, the first mapping branch can include a first weight matrix, a first bias matrix and a first nonlinear mapping function, so that the first weight matrix and the running state attention feature can be multiplied to obtain the corresponding weighted feature, and then the weighted feature and the first bias matrix can be added. Then, the matrix obtained by the addition can be activated based on the first nonlinear mapping function (such as tanh (hyperbolic tangent function)) to obtain the first running state mapping feature. In this way, the richness of the captured semantic information can be improved to a certain extent;

[0088] Furthermore, the second mapping branch can be used to perform a mapping operation on the running state attention feature to form a second running state mapping feature corresponding to the running state attention feature; exemplarily, the second mapping branch may include a second weight matrix, a second bias matrix, and a second nonlinear mapping function, so that the second weight matrix and the running state attention feature can be multiplied to obtain the corresponding weighted feature, and then the weighted feature and the second bias matrix can be added. Then, the matrix obtained by the addition can be activated based on the second nonlinear mapping function (such as tanh (hyperbolic tangent function)) to obtain the second running state mapping feature; based on this, different mappings of the running state attention feature can be achieved, thereby capturing different semantic information in the running state attention feature;

[0089] Finally, the first operating state mapping feature and the second operating state mapping feature can be cross-attention processed to form the hardware operating state feature corresponding to the hardware operating state data; based on this, since the first operating state mapping feature and the second operating state mapping feature respectively reflect different semantic information in the operating state attention feature, the association fusion of different semantic information can be achieved through cross-attention processing, that is, by mapping the features differently and performing cross-attention based on these two mapping features, it can help the model capture information from multiple dimensions and improve the diversity, flexibility and robustness of feature expression.

[0090] It is understood that, in the above step S123, the specific manner of performing the deep mining operation on the embedded features of the operating environment is not limited. For example, in an alternative embodiment, in order to improve the reliability of the deep mining operation, the above step S123 may include the following:

[0091] First, the runtime environment embedded feature can be loaded into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a third mapping branch and a fourth mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping;

[0092] Secondly, self-attention processing can be performed on the operating environment embedded feature to form an operating environment attention feature corresponding to the operating environment embedded feature. Based on this, since the operating environment embedded feature contains the environmental semantic information of multiple hardware devices, and the environments between hardware devices generally have a correlation, by performing self-attention processing on the operating environment embedded feature, the environmental semantic information of different hardware devices can be associated and fused.

[0093] Then, the operating environment attention feature can be mapped through the third mapping branch to form a first operating environment mapping feature corresponding to the operating environment attention feature. Exemplarily, the third mapping branch can include a third weight matrix, a third bias matrix and a third nonlinear mapping function. In this way, the third weight matrix and the operating environment attention feature can be multiplied to obtain the corresponding weighted feature, and then the weighted feature and the third bias matrix can be added. Then, the matrix obtained by addition can be activated based on the third nonlinear mapping function (such as tanh (hyperbolic tangent function)) to obtain the first operating environment mapping feature. In this way, the richness of the captured semantic information can be improved to a certain extent.

[0094] Furthermore, the fourth mapping branch can be used to perform a mapping operation on the operating environment attention feature to form a second operating environment mapping feature corresponding to the operating environment attention feature. Exemplarily, the fourth mapping branch can include a fourth weight matrix, a fourth bias matrix, and a fourth nonlinear mapping function. In this way, the fourth weight matrix and the operating environment attention feature can be multiplied to obtain the corresponding weighted feature, and then the weighted feature and the fourth bias matrix can be added. Then, the matrix obtained by the addition can be activated based on the fourth nonlinear mapping function (such as tanh (hyperbolic tangent function)) to obtain the second operating environment mapping feature. In this way, the richness of the captured semantic information can be improved to a certain extent.

[0095] Finally, the first operating environment mapping feature and the second operating environment mapping feature can be cross-attention processed to form the hardware operating environment feature corresponding to the hardware operating environment data; based on this, since the first operating environment mapping feature and the second operating environment mapping feature respectively reflect different semantic information in the operating environment attention feature, the association fusion of different semantic information can be achieved through cross-attention processing, that is, by mapping the features differently and performing cross-attention based on these two mapping features, it can help the model capture information from multiple dimensions and improve the diversity, flexibility and robustness of feature expression.

[0096] In the embodiment of the present application, it is also necessary to explain step S130 that the specific method of focusing on and mining the hardware operating status characteristics based on the hardware operating environment characteristics is not limited and can be selected according to actual needs.

[0097] For example, in an alternative embodiment, in order to fully mine the associated information between the hardware operating environment characteristics and the hardware operating status characteristics through the focused mining operation, the above step S130 may further include step S131, step S132 and step S133, and the specific content of each step is as follows (combined with Figure 4 ).

[0098] Step S131 : performing a first focused mining operation on the hardware operating state feature based on the hardware operating environment feature through a first focused branch in the focused mining unit, and outputting a first focused feature.

[0099] In an embodiment of the present application, a first focusing branch in the focusing mining unit may perform a first focusing mining operation on the hardware operating state feature based on the hardware operating environment feature to output a first focusing feature.

[0100] Step S132 : performing a second focused mining operation on the hardware operating state feature based on the hardware operating environment feature through the second focused branch in the focused mining unit, and outputting a second focused feature.

[0101] In an embodiment of the present application, a second focused mining operation is performed on the hardware operating state feature based on the hardware operating environment feature via a second focused branch in the focused mining unit, outputting a second focused feature. Exemplarily, the first focused branch and the second focused branch are different, i.e., the first focused mining operation and the second focused mining operation are different, so that different focused mining operations can be performed on the hardware operating environment feature and the hardware operating state feature, thereby mining different associated semantic information, thereby increasing the richness and diversity of the semantic information.

[0102] Step S133: Calculate the mean of the first focus feature, the second focus feature, and the hardware operating state feature, and output a state environment focus feature.

[0103] In an embodiment of the present application, in order to avoid the problem of excessive focus on associated semantic information in the focused mining operation leading to the loss of some irrelevant important semantic information, the first focused feature, the second focused feature and the hardware operating status feature can be averaged, that is, the fusion of multiple semantic information is achieved, thereby outputting a state environment focused feature with richer semantics.

[0104] It is understandable that, in the above step S131, the specific manner of performing the first focused mining operation on the hardware operating state feature based on the hardware operating environment feature is not limited. For example, in an alternative embodiment, in order to enable reliable fusion of features of different semantic spaces during the focused mining process, the above step S131 may include:

[0105] First, a first spatial conversion operation can be performed on the hardware operating environment feature using a first spatial conversion matrix of a first focusing branch in the focused mining unit, so that the hardware operating environment feature is converted from a current semantic space to a semantic space where the hardware operating state feature is located, thereby obtaining a corresponding operating environment conversion feature. Exemplarily, the first spatial conversion matrix and the hardware operating environment feature can be multiplied to obtain the operating environment conversion feature.

[0106] Secondly, the association parameter distribution between the operating environment conversion feature and the hardware operating status feature can be determined (for example, the dot product between the operating environment conversion feature and the transposed feature of the hardware operating status feature can be calculated), and after the association parameter distribution is normalized, the hardware operating status feature is weighted based on the normalized association parameter distribution to output the first focused feature; based on this, due to the dot product calculation, the similarity of each parameter between the operating environment conversion feature and the hardware operating status feature can be determined, and then, based on the similarity, weighted processing can be performed so that the weights corresponding to similar features are larger, thereby achieving focus and characterization; in addition, since the hardware operating environment feature will be converted from the current semantic space to the semantic space where the hardware operating status feature is located, subsequent association fusion can be performed in the same semantic space, thereby improving its fusion accuracy.

[0107] It is understandable that, in the above step S132, the specific manner of performing the second focused mining operation on the hardware operating state feature based on the hardware operating environment feature is not limited. For example, in an alternative embodiment, in order to enable reliable fusion of features of different semantic spaces during the focused mining process, the above step S132 may include:

[0108] First, a second spatial conversion operation can be performed on the hardware operating state feature using a second spatial conversion matrix of a second focusing branch in the focused mining unit, so that the hardware operating state feature is converted from a current semantic space to a semantic space where the hardware operating environment feature is located, thereby obtaining a corresponding operating state conversion feature. Exemplarily, the second spatial conversion matrix and the hardware operating state feature can be multiplied to obtain the operating state conversion feature.

[0109] Secondly, determine the association parameter distribution between the hardware operating environment feature and the operating state transition feature (for example, the dot product between the transposed features of the hardware operating environment feature and the operating state transition feature can be calculated), and after normalizing the association parameter distribution, perform weighted processing on the operating state transition feature based on the normalized association parameter distribution to output a second focused feature; based on this, due to the dot product calculation, the similarity of each parameter between the hardware operating environment feature and the operating state transition feature can be determined, and then, based on the similarity, weighted processing can be performed so that the weights corresponding to similar features are larger, thereby achieving focused attention and characterization; in addition, since the hardware operating state feature will be converted from the current semantic space to the semantic space where the hardware operating environment feature is located, subsequent association fusion can be performed in the same semantic space, thereby improving its fusion accuracy.

[0110] Based on this, since the semantic features corresponding to the operating status have a direct characterization function, and the semantic features corresponding to the operating environment have an auxiliary characterization function, when executing the step of "calculating the mean of the first focusing feature, the second focusing feature and the hardware operating status feature, and outputting the status environment focusing feature", that is, when executing step S133, a weighted mean calculation can be performed, wherein the corresponding weighting coefficients can be sorted from large to small as the hardware operating status feature, the first focusing feature and the second focusing feature; that is, the weighting coefficient corresponding to the hardware operating status feature can be greater than the weighting coefficient corresponding to the first focusing feature, and the weighting coefficient corresponding to the first focusing feature can be greater than the weighting coefficient corresponding to the second focusing feature. In this way, full characterization of the original semantic information and associated semantic information can be achieved.

[0111] In the embodiment of the present application, it should be noted that in order to ensure that the operation status evaluation model has better evaluation capabilities, corresponding training can be performed in advance so that the mapping relationship between samples and corresponding labels can be learned. Therefore, the artificial intelligence-based fusion gateway operation monitoring method can further include the following content:

[0112] First, a hardware operating status sample and a hardware operating environment sample may be obtained, and the relevant explanations of step S110 may be referred to;

[0113] Secondly, the semantic feature mining unit included in the candidate operating state evaluation model can perform semantic feature mining operations on the hardware operating state sample and the hardware operating environment sample, respectively, and output hardware operating state features corresponding to the hardware operating state sample and hardware operating environment features corresponding to the hardware operating environment sample. Please refer to the relevant explanation of step S120;

[0114] Then, the focused mining unit included in the candidate operating state evaluation model may perform a focused mining operation on the hardware operating state features corresponding to the hardware operating state sample based on the hardware operating environment features corresponding to the hardware operating environment sample, and output a state environment focused feature sample. For details, please refer to the relevant explanation of step S130.

[0115] Afterwards, the operating state evaluation unit included in the candidate operating state evaluation model may evaluate the operating state of the corresponding converged gateway based on the state environment focused feature sample to obtain corresponding operating state evaluation data. For details, see the relevant explanation of step S140.

[0116] Finally, based on the error between the operating status evaluation data and the operating status label of the corresponding fusion gateway (such as a cross-entropy error, for example, the operating status evaluation data can be a probability distribution of each operating status type, such as (0.1, 0.2, 0.7), and the operating status label can also be a probability distribution of each operating status type, such as (0, 0, 1). In this way, the cross entropy between (0.1, 0.2, 0.7) and (0, 0, 1) can be calculated), the model parameters of the candidate operating status evaluation model can be updated (i.e., the parameters are updated in a direction of reducing the error) until the error converges (e.g., the error is less than a preset error or the reduction in the error is less than a preset value), thereby obtaining a trained operating status evaluation model, that is, learning a reliable mapping relationship between samples and labels, so that in subsequent applications, the mapping relationship can be used to achieve reliable evaluation.

[0117] Combine Figure 5The present application also provides an artificial intelligence-based converged gateway operation monitoring device applicable to the aforementioned electronic device. The artificial intelligence-based converged gateway operation monitoring device may include an operation data acquisition module, a semantic feature mining module, a focus mining module, and an operation status assessment module.

[0118] In detail, the operation data acquisition module can be used to obtain the hardware operation status data and hardware operation environment data of the target fusion gateway, wherein the hardware operation status data is used to reflect the operation status of at least one hardware device in the target fusion gateway, and the hardware operation environment data includes the environment data of the at least one hardware device, and the environment data includes at least temperature data and power supply data. In the embodiment of the present application, the operation data acquisition module can be used to execute Figure 2 As shown in step S110, for the relevant content of the operation data acquisition module, reference can be made to the above description of step S110.

[0119] In detail, the semantic feature mining module can be used to perform semantic feature mining operations on the hardware operating state data and the hardware operating environment data respectively through the semantic feature mining unit included in the operating state evaluation model, and output the hardware operating state features corresponding to the hardware operating state data and the hardware operating environment features corresponding to the hardware operating environment data, wherein the operating state evaluation model belongs to a neural network model, and the operating state evaluation model also includes a focus mining unit and an operating state evaluation unit. In the embodiment of the present application, the semantic feature mining module can be used to perform Figure 2 As shown in step S120, for the relevant content of the semantic feature mining module, reference can be made to the above description of step S120.

[0120] In detail, the focus mining module can be used to perform a focus mining operation on the hardware operating state feature based on the hardware operating environment feature through the focus mining unit, and output a state environment focus feature, wherein the state environment focus feature is used to reflect the semantic information associated with the hardware operating environment feature mined from the hardware operating state feature. In the embodiment of the present application, the focus mining module can be used to perform Figure 2 As shown in step S130, for the relevant content of the focus mining module, reference may be made to the above description of step S130.

[0121] In detail, the operation status evaluation module can be used to evaluate the operation status of the target fusion gateway based on the state environment focus feature through the operation status evaluation unit, and obtain the operation status evaluation result corresponding to the target fusion gateway to realize the operation monitoring of the target fusion gateway. In the embodiment of the present application, the operation status evaluation module can be used to perform Figure 2 As shown in step S140, for the relevant content of the operating status evaluation module, reference can be made to the above description of step S140.

[0122] In an embodiment of the present application, corresponding to the above-mentioned artificial intelligence-based fusion gateway operation monitoring method applied to the electronic device, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is run, the various steps of the artificial intelligence-based fusion gateway operation monitoring method are executed.

[0123] Among them, the steps executed when the aforementioned computer program is running will not be described one by one here. Please refer to the previous explanation of the artificial intelligence-based fusion gateway operation monitoring method.

[0124] In summary, the artificial intelligence-based fusion gateway operation monitoring method, device and equipment provided by the present application first obtains the hardware operation status data and hardware operation environment data of the target fusion gateway; secondly, performs semantic feature mining operations on the hardware operation status data and the hardware operation environment data respectively, outputs the hardware operation status features corresponding to the hardware operation status data and the hardware operation environment features corresponding to the hardware operation environment data, then performs focused mining operations on the hardware operation status features based on the hardware operation environment features, outputs the state environment focused features; finally, evaluates the operation status based on the state environment focused features, obtains the operation status evaluation results, and realizes the operation monitoring of the target fusion gateway. Based on the above content, on the one hand, the powerful learning ability of the neural network model is utilized to improve the reliability of the operation status evaluation to a certain extent. On the other hand, since after obtaining the hardware operation status features, focused mining is also performed based on the hardware operation environment features, it is possible to further mine semantic features with higher representation accuracy, namely, the state environment focused features. Therefore, when the state evaluation is performed based on the state environment focused features, it can have a higher reliability, thereby improving the relatively low reliability problem of the operation monitoring of the fusion gateway in the prior art.

[0125] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0127] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly contributed to the prior art or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. It should be noted that, in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0128] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for monitoring the operation of a fusion gateway based on artificial intelligence, characterized in that: include: Obtaining hardware operating status data and hardware operating environment data of the target converged gateway, wherein the hardware operating status data is used to reflect the operating status of at least one hardware device in the target converged gateway, and the hardware operating environment data includes environmental data of the at least one hardware device, and the environmental data includes at least temperature data and power supply data; Performing semantic feature mining operations on the hardware operating state data and the hardware operating environment data respectively through a semantic feature mining unit included in an operating state evaluation model, and outputting hardware operating state features corresponding to the hardware operating state data and hardware operating environment features corresponding to the hardware operating environment data, wherein the operating state evaluation model is a neural network model, and the operating state evaluation model further includes a focus mining unit and an operating state evaluation unit; The first spatial conversion operation is performed on the hardware operating environment feature through the first spatial conversion matrix of the first focusing branch in the focused mining unit, so that the hardware operating environment feature is converted from the current semantic space to the semantic space where the hardware operating status feature is located, thereby obtaining the corresponding operating environment conversion feature; determining the associated parameter distribution between the operating environment conversion feature and the hardware operating status feature, and, after normalizing the associated parameter distribution, performing weighted processing on the hardware operating status feature based on the normalized associated parameter distribution to output the first focused feature; performing a second spatial conversion operation on the hardware operating status feature through the second spatial conversion matrix of the second focusing branch in the focused mining unit operation, so that the hardware operating state feature is converted from the current semantic space to the semantic space where the hardware operating environment feature is located, thereby obtaining a corresponding operating state transition feature; determining the associated parameter distribution between the hardware operating environment feature and the operating state transition feature, and, after normalizing the associated parameter distribution, performing weighted processing on the operating state transition feature based on the normalized associated parameter distribution to output a second focused feature; performing mean calculation on the first focused feature, the second focused feature, and the hardware operating state feature to output a state environment focused feature, wherein the state environment focused feature is used to reflect the semantic information associated with the hardware operating environment feature mined from the hardware operating state feature; The operating status evaluation unit evaluates the operating status of the target fusion gateway based on the state environment focus feature, and obtains the operating status evaluation result corresponding to the target fusion gateway, so as to realize the operation monitoring of the target fusion gateway.

2. The method for monitoring the operation of a fusion gateway based on artificial intelligence according to claim 1, characterized in that: The semantic feature mining unit included in the operation status assessment model performs semantic feature mining operations on the hardware operation status data and the hardware operation environment data respectively, and outputs hardware operation status features corresponding to the hardware operation status data and hardware operation environment features corresponding to the hardware operation environment data, including: Performing semantic embedding operations on the hardware operating state data and the hardware operating environment data respectively through a semantic embedding subunit in a semantic feature mining unit included in the operating state evaluation model, and outputting operating state embedding features corresponding to the hardware operating state data and operating environment embedding features corresponding to the hardware operating environment data; Performing a deep mining operation on the operating status embedded feature through the first deep mining sub-unit in the semantic feature mining unit to output the hardware operating status feature corresponding to the hardware operating status data; A first deep mining sub-unit in the semantic feature mining unit performs a deep mining operation on the operating environment embedded features, and outputs hardware operating environment features corresponding to the hardware operating environment data.

3. The method for monitoring the operation of a fusion gateway based on artificial intelligence according to claim 2, characterized in that: The step of performing a deep mining operation on the operating status embedded feature by the first deep mining sub-unit in the semantic feature mining unit to output the hardware operating status feature corresponding to the hardware operating status data includes: Loading the operating state embedded feature into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a first mapping branch and a second mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping; Performing self-attention processing on the running state embedded feature to form a running state attention feature corresponding to the running state embedded feature; Performing a mapping operation on the running state attention feature through the first mapping branch to form a first running state mapping feature corresponding to the running state attention feature; Performing a mapping operation on the running state attention feature through the second mapping branch to form a second running state mapping feature corresponding to the running state attention feature; Cross-attention processing is performed on the first operating state mapping feature and the second operating state mapping feature to form a hardware operating state feature corresponding to the hardware operating state data.

4. The method for monitoring the operation of a fusion gateway based on artificial intelligence according to claim 2, characterized in that: The step of performing a deep mining operation on the operating environment embedded features by the first deep mining sub-unit in the semantic feature mining unit and outputting the hardware operating environment features corresponding to the hardware operating environment data includes: Loading the runtime environment embedded features into a first deep mining subunit in the semantic feature mining unit, wherein the first deep mining subunit has a third mapping branch and a fourth mapping branch, and both mapping branches include a linear mapping and a nonlinear mapping; Performing self-attention processing on the operating environment embedded feature to form an operating environment attention feature corresponding to the operating environment embedded feature; Performing a mapping operation on the operating environment attention feature through the third mapping branch to form a first operating environment mapping feature corresponding to the operating environment attention feature; performing a mapping operation on the operating environment attention feature through the fourth mapping branch to form a second operating environment mapping feature corresponding to the operating environment attention feature; Cross-attention processing is performed on the first operating environment mapping feature and the second operating environment mapping feature to form a hardware operating environment feature corresponding to the hardware operating environment data.

5. The method for monitoring the operation of a fusion gateway based on artificial intelligence according to any one of claims 1 to 4, characterized in that: Also includes: Obtain hardware operating status samples and hardware operating environment samples; Performing semantic feature mining operations on the hardware operating state sample and the hardware operating environment sample respectively through the semantic feature mining unit included in the candidate operating state evaluation model, and outputting hardware operating state features corresponding to the hardware operating state sample and hardware operating environment features corresponding to the hardware operating environment sample; By using the focused mining unit included in the candidate operating state evaluation model, a focused mining operation is performed on the hardware operating state features corresponding to the hardware operating state sample based on the hardware operating environment features corresponding to the hardware operating environment sample, and a state environment focused feature sample is output; By using the operation status evaluation unit included in the candidate operation status evaluation model, the operation status of the corresponding fusion gateway is evaluated based on the state environment focus feature sample to obtain corresponding operation status evaluation data; Based on the error between the running status evaluation data and the running status label of the corresponding fusion gateway, the model parameters of the candidate running status evaluation model are updated until the error converges, thereby obtaining a trained running status evaluation model.

6. An artificial intelligence-based fusion gateway operation monitoring device, characterized in that: include: An operation data acquisition module is used to obtain hardware operation status data and hardware operation environment data of the target converged gateway, wherein the hardware operation status data is used to reflect the operation status of at least one hardware device in the target converged gateway, and the hardware operation environment data includes environmental data of the at least one hardware device, and the environmental data includes at least temperature data and power supply data; a semantic feature mining module, configured to perform semantic feature mining operations on the hardware operating state data and the hardware operating environment data respectively through a semantic feature mining unit included in an operating state evaluation model, and output hardware operating state features corresponding to the hardware operating state data and hardware operating environment features corresponding to the hardware operating environment data, wherein the operating state evaluation model is a neural network model and further includes a focus mining unit and an operating state evaluation unit; A focused mining module is configured to perform a first spatial conversion operation on the hardware operating environment feature through a first spatial conversion matrix possessed by a first focusing branch in the focused mining unit, so that the hardware operating environment feature is converted from a current semantic space to a semantic space where the hardware operating state feature is located, thereby obtaining a corresponding operating environment conversion feature; determine the associated parameter distribution between the operating environment conversion feature and the hardware operating state feature, and, after normalizing the associated parameter distribution, perform weighted processing on the hardware operating state feature based on the normalized associated parameter distribution to output a first focused feature; perform a second spatial conversion operation on the hardware operating state feature through a second focusing branch in the focused mining unit A spatial conversion operation is performed to convert the hardware operating state feature from the current semantic space to the semantic space where the hardware operating environment feature is located, thereby obtaining a corresponding operating state transition feature; determining the associated parameter distribution between the hardware operating environment feature and the operating state transition feature, and, after normalizing the associated parameter distribution, performing weighted processing on the operating state transition feature based on the normalized associated parameter distribution to output a second focused feature; performing mean calculation on the first focused feature, the second focused feature, and the hardware operating state feature to output a state environment focused feature, wherein the state environment focused feature is used to reflect the semantic information associated with the hardware operating environment feature mined from the hardware operating state feature; An operation status evaluation module is used to evaluate the operation status of the target fusion gateway based on the state environment focus feature through the operation status evaluation unit, and obtain the operation status evaluation result corresponding to the target fusion gateway to realize operation monitoring of the target fusion gateway.

7. An electronic device, characterized in that: include: memory for storing computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the artificial intelligence-based fusion gateway operation monitoring method described in any one of claims 1 to 5.

Images