Smart home equipment control method and device, electronic equipment and medium

Abstract

The invention discloses a control method and device of smart home equipment, electronic equipment and a medium, and belongs to the technical field of equipment control. The method comprises the following steps: in response to an operation request for the smart home device, obtaining one or more pieces of authentication feature information of the smart home device; determining trust score data of the operation request according to each piece of authentication feature information and a fingerprint template which is pre-stored in the smart home equipment and is used for authentication; the fingerprint template is generated by the home host in a trained target model based on historical authentication feature information of the smart home device; determining an equipment control strategy corresponding to the trust score data; and executing the equipment control strategy for the smart home equipment. Through the embodiment of the invention, the credibility score can be calculated according to the multi-dimensional authentication feature information in the home network, and then the equipment control strategy is realized according to the credibility score without depending on cloud authentication processing.

Description

Technical Field

[0001] This application belongs to the field of equipment control technology, specifically relating to a control method for a smart home device, a control device for a smart home device, an electronic device, and a readable storage medium. Background Technology

[0002] Static authentication mechanisms are widely used in smart home systems to ensure device access security. Currently, most methods centralize core authentication and authorization logic on a cloud platform for device identity authentication and access control. However, this system architecture design centralizes core authentication and authorization logic on the cloud platform, while local devices (such as the home host) only act as policy enforcement points, lacking independent and complete authentication decision-making capabilities. Therefore, this authentication decision heavily relies on the cloud, leading to security function failure in offline scenarios.

[0003] In addition, the continuous verification engine of this solution relies on cloud computing resources for dynamic policy evaluation. When the home network is disconnected from the external network, the local device cannot complete real-time authentication, and high-risk operations (such as door lock control) cannot be executed, which greatly reduces the availability of the system. Summary of the Invention

[0004] The purpose of this application is to provide a control method for smart home devices, a control device for smart home devices, an electronic device, and a readable storage medium, which can solve the problem that local devices cannot be authenticated in real time when the external network is disconnected due to reliance on cloud-based device authentication.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a method for controlling a smart home device, the method comprising: In response to an operation request for the smart home device, obtain one or more authentication feature information of the smart home device; Trust score data for the operation request is determined based on each authentication feature and the fingerprint template pre-stored in the smart home device for authentication; the fingerprint template is generated by the home host based on the historical authentication feature information of the smart home device. Determine the device control strategy corresponding to the trust score data; The device control strategy is executed for the smart home device.

[0006] Optionally, determining the trust score data for the operation request based on each authentication feature and a fingerprint template pre-stored in the smart home device for authentication includes: Determine the similarity data between each authentication feature and the fingerprint template pre-stored in the smart home device for authentication; The trust score data for the operation request is determined based on the similarity data.

[0007] Optionally, determining the trust score data for the operation request based on the similarity data includes: Determine the weight data corresponding to each authentication feature; The trust score data for the operation request is determined based on the weight data and the similarity data.

[0008] Optionally, determining the device control policy corresponding to the trust score data includes: When determining whether the trust score data is greater than a preset first score data; When the trust score data is determined to be greater than or equal to the first score data, the device control strategy is determined to execute the operation request.

[0009] Optionally, determining the device control policy corresponding to the trust score data includes: When the trust score data is less than the first score data, it is determined whether the trust score data is less than a preset second score data, and the second score data is less than the first score data; When the trust score data is determined to be less than the second score data, the device control policy is determined to reject the operation request.

[0010] Optionally, determining the device control policy corresponding to the trust score data includes: When the trust score data is determined to be greater than or equal to the second score data and less than the first score data, the device control strategy is determined to push an authentication request to the application used to control the smart home device.

[0011] Optionally, the device control strategy further includes: Generate a security log corresponding to the operation request and store the security log; And / or, reduce the network access permissions of the smart home devices to the minimum. And / or, generate an alarm message corresponding to the operation request, and send the alarm message to the target user associated with the smart home device.

[0012] Optionally, determining the device control policy to reject the operation request when the trust score data is less than the second score data includes: When the trust score data corresponding to the operation request of the smart home device is less than the second score data for N consecutive times, one or more trusted home devices in the network corresponding to the operation request are identified. The device ID of the smart home device is sent to one or more trusted home devices to obtain device behavior data of the smart home device based on the device ID in the trusted home devices, and to determine the anomaly identification result of the smart home device based on the device behavior data; Receive the anomaly identification result sent by the trusted home device; If more than a preset number of anomaly identification results indicate that the smart home device is malfunctioning, then the device control policy is determined to reject the operation request.

[0013] Optionally, it also includes: Obtain the authentication feature data newly added by the smart home device within a preset time period; Based on the newly added authentication feature data, the local target model is incrementally trained to obtain the encrypted gradient data corresponding to the target model. The target model can generate the fingerprint template of the smart home device based on the input historical authentication feature data. The encrypted gradient data is uploaded to the cloud, whereby the model parameters of the target model are updated based on the received encrypted gradient data from multiple home hosts. Receive the target model updated based on the model parameters sent by the cloud.

[0014] Optionally, the authentication feature information includes any one or more of the following: Physical signal characteristics, behavior, and contextual characteristics.

[0015] Secondly, embodiments of this application provide a control device for a smart home device, the device comprising: The authentication feature information acquisition module is used to acquire one or more authentication feature information of the smart home device in response to an operation request for the smart home device; The trust score data generation module is used to determine the trust score data of the operation request based on each authentication feature information and the fingerprint template for authentication pre-stored by the smart home device; the fingerprint template is generated by the home host in the trained target model based on the historical authentication feature information of the smart home device; The device control strategy determination module is used to determine the device control strategy corresponding to the trust score data; The control strategy execution module is used to execute the device control strategy for the smart home device.

[0016] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0017] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0018] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0019] In this embodiment, a trust score is calculated based on multi-dimensional authentication feature information within the home network, and device control policies are implemented according to the trust score, without relying on cloud authentication processing. Even if the home network is disconnected from the external network, real-time authentication can still be performed based on local devices. Attached Figure Description

[0020] Figure 1a This is a flowchart illustrating a device control method for a smart home device according to an embodiment of this application; Figure 1b This is a flowchart illustrating a smart home dynamic authentication method based on device behavior fingerprints in an embodiment of this application. Figure 2 This is a flowchart illustrating another method for controlling a smart home device according to an embodiment of this application. Figure 3 This is a schematic diagram of the structure of a device control device for a smart home device according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0023] Static identity authentication mechanisms are widely used in smart home systems to ensure device access security.

[0024] For example, in the context of smart homes, a zero-trust-based smart home device security protection system and method are disclosed to improve the security protection capabilities of devices in smart homes. This system includes a distributed digital identity service, which provides unified identity management services for users, devices, and applications, responsible for generating unique identity IDs and issuing verifiable credentials to support device authentication; a dynamic data management module, which provides log management, smart home environmental factor management, and user-configured resource access policy management; and a continuous verification engine, which evaluates the access permissions of the access subject based on the data provided by the dynamic data management module, verifies the identity obtained by the access subject from the distributed digital identity service after the evaluation is passed, and provides access channels to smart home resources after successful verification. Furthermore, a smart home access control trust assessment method integrating edge computing is disclosed for practical applications. This method involves establishing an edge computing system for the smart home, employing the FCM clustering algorithm to binary classify network traffic into normal and abnormal traffic. At the edge computing center, the direct trust value of the user is calculated based on the proportion of abnormal traffic. This direct trust value is then uploaded to the cloud computing center, where a collaborative trust assessment is performed between different smart home systems to obtain indirect trust values. Finally, a comprehensive trust value (CV) is calculated by weighting the DV (Direct Trust Value) obtained from the edge computing center with the IDV (Indirect Trust Value) obtained from the cloud computing center. Access control using a token manager is then introduced.

[0025] However, in the above scheme, the authentication decision of smart home devices relies heavily on the cloud, which leads to the failure of the device's security functions in scenarios where the external network is disconnected.

[0026] In this embodiment, the home host obtains multi-dimensional authentication feature data of smart home devices, calculates trust scores, and realizes device authentication control without relying on the cloud. Thus, even when the home network is disconnected from the external network, dynamic device authentication control can still be realized in the home host.

[0027] The control method for smart home devices provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0028] Reference Figure 1a The diagram illustrates a flowchart of a control method for a smart home device according to an embodiment of this application. This control method is applied to a home host, which can specifically execute the following steps: Step S101: In response to an operation request for the smart home device, obtain one or more authentication feature information of the smart home device; In practical applications, smart home devices can operate on the same home network as the main unit, unaffected by external networks. These smart home devices can include various types such as door locks, air conditioners, and lighting fixtures. Users can control these devices through applications designed for device management.

[0029] When a target home device makes an operation request, the home host detects the request. To ensure the security of the operation request, it can obtain one or more authentication feature information of the smart home device to perform real-time authentication of the smart home device. The authentication feature information may include, but is not limited to, any one or more of the following: Physical signal characteristics, behavior, and contextual characteristics.

[0030] The home host can continuously collect Wi-Fi radio frequency signals from home devices at a high sampling rate (e.g., 1kHz) via its network interface (extracting I / Q data and carrier frequency offset), power consumption fluctuation curves, and electromagnetic noise spectrum. Simultaneously, the home host can record in real-time the communication behavior sequences of smart home devices (e.g., "heartbeat packet -> status query -> receive command"), operation time distribution, and associated user app operation habits—in other words, the behavioral and contextual characteristics of smart home devices.

[0031] In practical applications, physical signal characteristics are inherent to devices and difficult to clone at the physical layer. These characteristics are strongly correlated with the differences in device hardware circuits and components, making them extremely difficult to copy or remotely simulate by software. This provides a unique and stable hardware-level binding for device identity from the source, fundamentally defending against device cloning and spoofing attacks. Behavioral and contextual characteristics, on the other hand, are the software-related characteristics of the device.

[0032] By combining physical signal characteristics with behavioral and contextual characteristics, smart home devices can be identified comprehensively, enabling device authentication.

[0033] In one embodiment of this application, the step of obtaining one or more authentication feature information of the smart home device in response to an operation request for the smart home device includes: determining whether the operation request is a preset high-risk operation in response to an operation request for the smart home device; and obtaining one or more authentication feature information of the smart home device when the operation request is determined to be a preset high-risk operation.

[0034] In practical applications, when a home host receives an operation request from a smart home device, it can determine the risk type of the operation request and then trigger the dynamic authentication process in this application embodiment for high-risk operations.

[0035] Step S102: Determine the trust score data of the operation request based on each authentication feature information and the fingerprint template for authentication pre-stored in the smart home device; The home host can pre-store fingerprint templates of smart home devices, wherein the fingerprint templates are generated by the home host based on the historical authentication feature information of the smart home devices.

[0036] The fingerprint template is a unique identifier for smart home devices. Therefore, the trust score data for operation requests can be determined based on the degree of matching between the authentication feature information and the fingerprint template. It can be understood that the closer the authentication feature information is to the fingerprint template, the more the authentication feature information matches the fingerprint template, and the higher the trust score data.

[0037] In one embodiment of this application, a fingerprint template can be generated in the following manner: When a new smart home device is connected to the home network, the home host starts a security initialization and learning mode for a preset time period (such as 72 hours).

[0038] ① Physical layer feature acquisition: The home host continuously acquires the Wi-Fi radio frequency signal of the door lock (extracting I / Q data and carrier frequency offset) and the power consumption fluctuation curve through its network interface at a high sampling rate (such as 1kHz).

[0039] ② Behavioral and contextual feature recording: Record the device's communication behavior sequence (such as "heartbeat packet -> status query -> receive command"), operation time distribution, and associated user APP operation habits.

[0040] ③ Fingerprint Template Generation and Storage: The home host uses an integrated target model to perform unsupervised learning on the aforementioned multidimensional data to generate a unique behavioral fingerprint template for the smart home device. After hashing, this fingerprint template can be securely stored in the home host's TEE (Trusted Execution Environment).

[0041] The target model can be a lightweight LSTM-AE (Long Short-Term Memory Network-Autoencoder).

[0042] The process of generating a fingerprint template based on the target model is as follows: Data collection and processing: The home gateway will spend a period of time (such as 72 hours) carefully observing and recording the normal working data of smart home devices, such as the power consumption fluctuation patterns, signal characteristics, and typical operating sequences of smart home devices. Model learning and feature extraction: Home gateways can use an integrated lightweight LSTM-AE model to analyze this data. The core function of this target model is to identify stable, recurring patterns in the data and automatically extract the most critical features while ignoring accidental and unimportant fluctuations. Fingerprint Template Generation: Combining these extracted core features forms a "behavioral fingerprint template" representing the normal state of the smart home device, which is securely stored locally on the gateway. In practical applications, during the initial device access phase, the home host can collect physical layer features and combine them with the device's communication behavior sequences to generate a unique multi-dimensional behavioral fingerprint template.

[0043] In this embodiment, the target model can establish a fingerprint template of normal behavior benchmark by learning data from the normal operation of the device, rather than relying on preset fixed rules, thereby more accurately identifying anomalies.

[0044] In one embodiment of this application, determining the trust score data of the operation request based on each authentication feature information and a fingerprint template pre-stored in the smart home device for authentication includes: Determine the similarity data between each authentication feature and the fingerprint template pre-stored in the smart home device for authentication; determine the trust score data for the operation request based on the similarity data.

[0045] The higher the similarity, the more closely the authentication feature information matches, and thus the higher the trust score.

[0046] In one embodiment of this application, after obtaining the similarity data of authentication feature data of each dimension, the similarity data can be normalized, that is, the multiple similarity data are converted to the same range for trust score calculation, such as converting to 0 to 100.

[0047] Each authentication dimension can yield corresponding similarity data. A conversion relationship can be established between similarity data and trust score data. Then, based on the conversion relationship, the calculated similarity information from multiple categories can be comprehensively analyzed and calculated to obtain trust score data.

[0048] In one embodiment of this application, determining the trust score data of the operation request based on the similarity data includes: determining the weight data corresponding to each authentication feature information; and determining the trust score data of the operation request according to the weight data and the similarity data.

[0049] Different types of authentication feature information have varying degrees of credibility, and therefore, the weight data can be set according to the type of authentication feature information, with the sum of the weight data of multiple authentication feature information being 1. For example, physical layer features have the highest weight, highlighting their fundamental role.

[0050] After obtaining the weight data and similarity data, a weighted calculation can be performed to obtain the trust score data.

[0051] In this embodiment, the conversion relationship between similarity data and trust score data can be: Trust score data = Weight data of the first authentication feature information * Similarity data of the first authentication feature information + Weight data of the second authentication feature information * Similarity data of the second authentication feature information + ... For example, the trust score "S" is calculated using a weighted formula: S = 0.6 * S_{physical} + 0.3 * S_{behavior} + 0.1 * S_{context}, where the physical layer features have the highest weight, highlighting their fundamental role. The scoring range is 0-100 points.

[0052] Where S_{physical} is the physical feature similarity (0-100), S_{behavior} is the behavior sequence matching degree, and S_{context} is the context compliance.

[0053] Step S103: Determine the device control strategy corresponding to the trust score data; In practical applications, home control systems can pre-configure corresponding device control policies based on different trust score data ranges. After calculating the trust score data, the corresponding range can be determined, and thus the device control policy for that range can be established. This device control policy refers to the handling of operation requests or the processing of smart home devices.

[0054] In one embodiment of this application, determining the device control strategy corresponding to the trust score data includes: determining whether the trust score data is greater than a preset first score data; and determining the device control strategy to execute the operation request when the trust score data is greater than or equal to the first score data.

[0055] When the trust score is greater than the first score, the smart home device can be considered highly trustworthy. In this case, the corresponding device control strategy is that the operation request can be executed directly.

[0056] In one embodiment of this application, determining the device control policy corresponding to the trust score data includes: when the trust score data is less than the first score data, determining whether the trust score data is less than a preset second score data, wherein the second score data is less than the first score data; and when it is determined that the trust score data is less than the second score data, determining that the device control policy is to reject the operation request.

[0057] When the trust score is lower than the second score, the home host determines that the smart home device is highly abnormal or a potential attack. Therefore, the corresponding device control policy set for the operation request is to reject the operation request.

[0058] In one embodiment of this application, when a smart home device is highly abnormal or potentially under attack, the device control strategy may further include any one or more of the following: (1) Generate a security log corresponding to the operation request and store the security log; (2) Reduce the network access permissions of the smart home devices to the minimum. (3) Generate an alarm message corresponding to the operation request and send the alarm message to the target user associated with the smart home device.

[0059] In one embodiment of this application, determining the device control policy to reject the operation request when the trust score data is less than the second score data may specifically include the following sub-steps: Sub-step S11: When the trust score data corresponding to the operation request of the smart home device is less than the second score data N times consecutively, one or more trusted home devices in the network corresponding to the operation request are identified; where N is a positive integer greater than 1. Trusted home devices can be trusted home devices in the same home network, such as devices that have already been successfully authenticated.

[0060] Sub-step S12: Send the device ID of the smart home device to the one or more trusted home devices, so as to obtain the device behavior data of the smart home device based on the device ID in the trusted home devices, and determine the abnormal identification result of the smart home device based on the device behavior data; Sub-step S13: Receive the anomaly identification result sent by the trusted home device; Sub-step S14: If more than a preset number of anomaly identification results indicate that the smart home device is malfunctioning, then the device control strategy is determined to reject the operation request. The preset number can be set according to the actual scenario; for example, it can be set as a proportion of the total number of trusted home devices.

[0061] For example, if a door lock scores below 60 points in three consecutive requests, a consensus mechanism based on a local network can be initiated to prevent misjudgment by a single point of failure in the home host. The home host can request other trusted nodes in the network (such as smart speakers and NAS devices) to provide auxiliary judgments based on their observations of the door lock's behavior. If a majority of nodes consider it abnormal, they will collaboratively implement device isolation.

[0062] Specifically, when the home control system suspects a door lock is malfunctioning, to ensure accurate judgment, it will request confirmation from other trusted devices on the network (such as smart speakers or NAS devices): Sending a request for assistance: The home host will send a digitally signed request packet containing a suspicious door lock ID and a summary of unusual evidence (such as "asking questions unusually frequently in the early morning") to other devices. Independent verification: After receiving the request, other trusted devices do not simply agree with the host's opinion. Instead, they retrieve recent behavioral data about the door lock to be authenticated from the trusted device's logs (such as the signal strength and network request records observed for the door lock to be authenticated) for independent analysis, and then give the trusted device's judgment ("agree with the anomaly" or "no obvious anomaly found"). Collective decision-making: The home control unit can decide whether to isolate a door lock based on the independent judgments of most trusted devices. This method effectively avoids situations where a single device misjudges or is deceived.

[0063] In one embodiment of this application, determining the device control strategy corresponding to the trust score data includes: when it is determined that the trust score data is greater than or equal to the second score data and less than the first score data, determining that the device control strategy is to push an authentication request to the application used to control the smart home device.

[0064] In practical applications, when the trust score is greater than or equal to the second score but less than the first score, it is considered to have a certain degree of uncertainty. Therefore, the home control unit can push a secondary authentication request to the bound user's mobile app. This authentication request can require the user to confirm via fingerprint or facial recognition. This is called "step-by-step authentication." If the home control unit successfully receives an authentication request from the smart home device, it can continue to execute the operation request; if the authentication request fails, it will reject or block the operation request.

[0065] Step S104: Execute the device control strategy for the smart home device.

[0066] Reference Figure 1b The following is a flowchart illustrating a smart home dynamic authentication method based on device behavior fingerprints, as shown in an embodiment of this application. The main process is as follows: When a smart home device is powered on or connected for the first time, the gateway collects multi-dimensional features (including physical, behavioral, and contextual features); the gateway locally trains and generates a multi-dimensional behavioral fingerprint template; and stores the fingerprint template in the local secure area of ​​the network management system.

[0067] The device enters normal operating status; when the device initiates an operation request (such as remote unlocking); the gateway collects the current operating characteristics of the device in real time; calculates the similarity between the real-time characteristics and the fingerprint module; and generates a dynamic trust score (1-100).

[0068] When the trust score is greater than 80, the operation is automatically allowed; when the trust score is greater than 60 and less than or equal to 80, a second confirmation by the user (such as APP biometric recognition) can be triggered. If the user confirms and passes, the operation is automatically allowed. If the user fails, a log is recorded and the process ends; when the trust score is less than 60, the operation can be identified as abnormal and the device can be isolated. A security log is recorded and an alarm is sent to the user.

[0069] In this embodiment, a trust score is calculated based on multi-dimensional authentication feature information within the home network, and device policies are implemented according to the trust score, without relying on cloud-based authentication processing. Even if the home network is disconnected from the external network, real-time authentication can be performed based on local devices.

[0070] Reference Figure 2 The diagram illustrates a flowchart of a control method for a smart home device according to an embodiment of this application. This control method is applied to a home host, which can specifically execute the following steps: Step S201: In response to an operation request for the smart home device, obtain one or more authentication feature information of the smart home device; Step S202: Determine the trust score data of the operation request according to each authentication feature information and the fingerprint template for authentication pre-stored by the smart home device; the fingerprint template is generated by the home host based on the historical authentication feature information of the smart home device; Step S203: Determine the device control strategy corresponding to the trust score data; Step S204: Execute the device control strategy for the smart home device.

[0071] Step S205: Obtain the authentication feature data newly added by the smart home device within a preset time period; The preset time period can be a recent period of time, and the time span can be set according to actual needs.

[0072] Step S206: Incrementally train the local target model based on the newly added authentication feature data to obtain the encrypted gradient data corresponding to the target model. The target model can generate the fingerprint template of the smart home device based on the input historical authentication feature data. In practical applications, initial training is when the model "learns from scratch" to establish basic knowledge. Incremental training, on the other hand, involves the model continuously reviewing and fine-tuning itself with newly generated data based on existing knowledge. The goal is to enable the model to keep up with potential changes in device behavior (such as behavior adjustments after firmware upgrades) and prevent cognitive aging. In this embodiment of the application, the cloud can distribute the target model to each home host for storage after initial training. Then, during the actual operation of the home host, the target model can be continuously used and incrementally trained, that is, retrained based on the newly generated data. After training is completed, encrypted gradient data can be obtained.

[0073] During local training, the model calculates a set of values ​​(gradients), which indicate how the model parameters should be adjusted to achieve greater accuracy.

[0074] Step S207: Upload the encrypted gradient data to the cloud so as to update the model parameters of the target model on the cloud based on the received encrypted gradient data from multiple home hosts; In practical applications, before uploading encrypted gradient data, cryptographic techniques such as homomorphic encryption may be used to encrypt the gradient values ​​to ensure that the cloud cannot crack and restore the original data. In this embodiment of the application, by aggregating encrypted gradient data from a large number of home hosts, the cloud can calculate model updates that better reflect general patterns and the latest threat trends, enabling the local model of each home host to continuously evolve and collectively improve defense capabilities.

[0075] Step S208: Receive the target model updated based on the model parameters sent by the cloud.

[0076] In this embodiment, a target model can be introduced to generate fingerprint templates. The target model can be continuously optimized during actual operation to obtain encrypted gradient data. Then, the encrypted gradient data can be uploaded to the cloud for processing to update the target model in the cloud. The updated target model is then distributed to each home host to achieve the evolution of the overall protection capability of the system, without touching any home's original data throughout the process.

[0077] It should be noted that the control method for smart home devices provided in this application embodiment can be executed by a control device for the smart home device, or a control module within the control device for executing the method for loading the control of the smart home device. This application embodiment uses the example of a control device for the smart home device executing the method for loading the control of the smart home device to illustrate the control method for smart home devices provided in this application embodiment.

[0078] Reference Figure 3 The diagram shows a structural schematic of a control device for a smart home device according to an embodiment of this application. This control device can be applied to a home host, which may specifically include the following modules: The authentication feature information acquisition module 301 is used to acquire one or more authentication feature information of the smart home device in response to an operation request for the smart home device. The trust score data generation module 302 is used to determine the trust score data of the operation request based on each authentication feature information and the fingerprint template for authentication pre-stored by the smart home device; the fingerprint template is generated by the home host in the trained target model based on the historical authentication feature information of the smart home device. The device control strategy determination module 303 is used to determine the device control strategy corresponding to the trust score data; The control strategy execution module 304 is used to execute the device control strategy for the smart home device.

[0079] In one embodiment of this application, the trust scoring data generation module 302 may include: The similarity data determination submodule is used to determine the similarity data between each authentication feature information and the fingerprint template quality inspection pre-stored by the smart home device for authentication. The trust score data determination submodule is used to determine the trust score data of the operation request based on the similarity data.

[0080] In one embodiment of this application, the trust scoring data determination submodule may include: The weight data determination unit is used to determine the weight data corresponding to each type of authentication feature information; A trust score determination unit is used to determine the trust score data of the operation request based on the weight data and the similarity data.

[0081] In one embodiment of this application, the device control strategy determination module 303 may include: The first rating judgment submodule is used to determine whether the trust rating data is greater than a preset first rating data. The first control strategy determination submodule is used to determine the device control strategy as executing the operation request when it is determined that the trust score data is greater than or equal to the first score data.

[0082] In one embodiment of this application, the device control strategy determination module 303 may include: The second rating judgment submodule is used to determine whether the trust rating data is less than a preset second rating data when the trust rating data is less than the first rating data. The second rating data is less than the first rating data. The second control strategy submodule is used to determine that the device control strategy is to reject the operation request when the trust score data is less than the second score data.

[0083] In one embodiment of this application, the device control strategy determination module 303 may include: The third control strategy submodule is used to determine the device control strategy as pushing an authentication request to the application used to control the smart home device when it is determined that the trust score data is greater than or equal to the second score data and less than the first score data.

[0084] In one embodiment of this application, the device control strategy further includes: Generate a security log corresponding to the operation request and store the security log; And / or, reduce the network access permissions of the smart home devices to the minimum. And / or, generate an alarm message corresponding to the operation request, and send the alarm message to the target user associated with the smart home device.

[0085] 8. The method according to claim 5, wherein the second control strategy submodule may include: A trusted home device determination unit is configured to determine one or more trusted home devices in the network corresponding to the operation request when the trust score data corresponding to the operation request of the smart home device is less than the second score data for N consecutive times. The device ID sending unit is used to send the device ID of the smart home device to the one or more trusted home devices, so as to obtain the device behavior data of the smart home device based on the device ID in the trusted home devices, and determine the abnormal identification result of the smart home device based on the device behavior data; An anomaly identification result receiving unit is used to receive the anomaly identification result sent by the trusted home device; The control strategy determination unit is used to determine the device control strategy as rejecting the operation request if more than a preset number of anomaly identification results indicate that the smart home device is malfunctioning.

[0086] In one embodiment of this application, the apparatus further includes: A new data acquisition module is added to acquire authentication feature data of the smart home device added within a preset time period; The encrypted gradient data determination module is used to incrementally train the local target model based on the newly added authentication feature data to obtain the encrypted gradient data corresponding to the target model. The target model can generate the fingerprint template of the smart home device based on the input historical authentication feature data. An encrypted gradient data upload module is used to upload the encrypted gradient data to the cloud, so as to update the model parameters of the target model on the cloud based on the encrypted gradient data received from multiple home hosts; The target model update module is used to receive the updated target model based on the model parameters sent by the cloud.

[0087] In one embodiment of this application, the authentication feature information includes any one or more of the following: Physical signal characteristics, behavior, and contextual characteristics.

[0088] In this embodiment, a trust score is calculated based on multi-dimensional authentication feature information within the home network, and device policies are implemented according to the trust score, without relying on cloud-based authentication processing. Even if the home network is disconnected from the external network, real-time authentication can be performed based on local devices.

[0089] The control device for smart home devices in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0090] The control device for the smart home device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system used.

[0091] The control device for smart home devices provided in this application embodiment can achieve… Figures 1a to 2 The various processes implemented by the control device of the smart home device in the method embodiment will not be described again here to avoid repetition.

[0092] Optionally, this application embodiment also provides an electronic device, including a processor 1010, a memory 1009, and a program or instructions stored in the memory 1009 and executable on the processor 1010. When the program or instructions are executed by the processor 1010, they implement the various processes of the above-described smart home device control method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0093] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0094] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application. The electronic device 1000 includes, but is not limited to, the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.

[0095] The memory 1009 includes applications and an operating system; the user input unit 1007 may include a touch panel 10071 and other input devices 100072; the input unit 1004 may include an image processor 10041 and a microphone 10042; and the display unit 1006 may include a display panel 10061.

[0096] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here. This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described smart home device control method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0097] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0098] This application also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described control method embodiments for smart home devices and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0099] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0100] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0102] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A control method for a smart home device, characterized in that, Applied to a home console, the method includes: In response to an operation request for the smart home device, obtain one or more authentication feature information of the smart home device; Trust score data for the operation request is determined based on each authentication feature and the fingerprint template pre-stored in the smart home device for authentication; the fingerprint template is generated by the home host based on the historical authentication feature information of the smart home device. Determine the device control strategy corresponding to the trust score data; The device control strategy is executed for the smart home device.

2. The method according to claim 1, characterized in that, The step of determining the trust score data for the operation request based on each authentication feature and the fingerprint template pre-stored in the smart home device for authentication includes: Determine the similarity data between each authentication feature and the fingerprint template pre-stored in the smart home device for authentication; The trust score data for the operation request is determined based on the similarity data.

3. The method according to claim 2, characterized in that, The step of determining the trust score data for the operation request based on the similarity data includes: Determine the weight data corresponding to each authentication feature; The trust score data for the operation request is determined based on the weight data and the similarity data.

4. The method according to claim 1, characterized in that, The step of determining the device control strategy corresponding to the trust score data includes: When determining whether the trust score data is greater than a preset first score data; When the trust score data is determined to be greater than or equal to the first score data, the device control strategy is determined to execute the operation request.

5. The method according to claim 4, characterized in that, The step of determining the device control strategy corresponding to the trust score data includes: When the trust score data is less than the first score data, it is determined whether the trust score data is less than a preset second score data, and the second score data is less than the first score data; When the trust score data is determined to be less than the second score data, the device control policy is determined to reject the operation request.

6. The method according to claim 5, characterized in that, The step of determining the device control strategy corresponding to the trust score data includes: When the trust score data is determined to be greater than or equal to the second score data and less than the first score data, the device control strategy is determined to push an authentication request to the application used to control the smart home device.

7. The method according to claim 5, characterized in that, The device control strategy also includes: Generate a security log corresponding to the operation request and store the security log; And / or, reduce the network access permissions of the smart home devices to the minimum. And / or, generate an alarm message corresponding to the operation request, and send the alarm message to the target user associated with the smart home device.

8. The method according to claim 5, characterized in that, The step of determining the device control policy to reject the operation request when the trust score data is less than the second score data includes: When the trust score data corresponding to the operation request of the smart home device is less than the second score data for N consecutive times, one or more trusted home devices in the network corresponding to the operation request are identified. The device ID of the smart home device is sent to one or more trusted home devices to obtain device behavior data of the smart home device based on the device ID in the trusted home devices, and to determine the anomaly identification result of the smart home device based on the device behavior data; Receive the anomaly identification result sent by the trusted home device; If more than a preset number of anomaly identification results indicate that the smart home device is malfunctioning, then the device control policy is determined to reject the operation request.

9. The method according to any one of claims 1 to 8, characterized in that, Also includes: Obtain the authentication feature data newly added by the smart home device within a preset time period; Based on the newly added authentication feature data, the local target model is incrementally trained to obtain the encrypted gradient data corresponding to the target model. The target model can generate the fingerprint template of the smart home device based on the input historical authentication feature data. The encrypted gradient data is uploaded to the cloud, whereby the model parameters of the target model are updated based on the received encrypted gradient data from multiple home hosts. Receive the target model updated based on the model parameters sent by the cloud.

10. The method according to any one of claims 1 to 8, characterized in that, The authentication feature information includes any one or more of the following: Physical signal characteristics, behavior, and contextual characteristics.

11. A control device for a smart home device, characterized in that, For use with home consoles, the device includes: The authentication feature information acquisition module is used to acquire one or more authentication feature information of the smart home device in response to an operation request for the smart home device; The trust score data generation module is used to determine the trust score data of the operation request based on each authentication feature information and the fingerprint template for authentication pre-stored by the smart home device; the fingerprint template is generated by the home host in the trained target model based on the historical authentication feature information of the smart home device; The device control strategy determination module is used to determine the device control strategy corresponding to the trust score data; The control strategy execution module is used to execute the device control strategy for the smart home device.

12. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the control method for a smart home device as described in any one of claims 1-10.

13. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the control method for a smart home device as described in any one of claims 1-10.

Images