Control method and device of smart home system, smart home system

Abstract

The application discloses a kind of control method and device of smart home system, smart home system. Among them, the method comprises: obtaining the multi-dimensional characteristic information of smart home system;Determine the acceptance degree of system operation behavior of smart home system based on multi-dimensional characteristic information;According to the acceptance degree, the current trust degree of smart home system is adjusted, and the updated trust degree of smart home system is obtained;According to the updated trust degree, the current trust level of smart home system is determined;According to the current trust level, the smart home system is controlled.The application solves the technical problems that the smart home control scheme in the related art lacks user subjective trust modeling and dynamic permission adjustment mechanism, leading to AI decision only meets behavior habits and is difficult to obtain user recognition, and the automatic process lacks progressive adjustment and abnormal degradation ability.

Description

Technical Field

[0001] This invention relates to the field of smart home control technology, and more specifically, to a control method and device for a smart home system, and a smart home system. Background Technology

[0002] Currently, existing smart home control technologies primarily rely on users' historical behavior data, device operating status, and environmental parameters. These data are used to automatically generate device control strategies through rule engines or machine learning models to achieve automated control of home appliances. For example, the system learns users' habits of adjusting air conditioning temperature at different times and automatically adjusts air conditioning operating parameters, or it automatically triggers the linkage of devices such as lights and curtains based on sensor data. While these solutions improve the level of home automation to some extent, their core logic remains limited to "behavior fitting" or "rule matching," failing to deeply consider users' subjective feelings and psychological acceptance.

[0003] While existing technologies optimize control by learning user habits through neural network models and achieve adaptive adjustment by analyzing user habits, these approaches all have significant limitations. They primarily focus on "what the user did," neglecting whether the user "approves" of the system's behavior and lacking modeling of the user's subjective level of trust. This means that while AI decisions may statistically align with users' historical habits, they may not be truly accepted by users in practice due to a lack of controllability.

[0004] Furthermore, existing systems generally lack dynamic permission adjustment mechanisms during automated management. Once automated management is enabled, the system often polarizes between "continuous automatic execution" and "complete reliance on manual control," failing to make gradual permission adjustments based on real-time user feedback and the trust-building process. This rigid control model either easily leads to user resentment and insecurity due to excessive automation, or reduces the user experience due to insufficient automation, making it difficult to meet the comprehensive needs of modern smart homes for security, controllability, and trust in human-machine collaborative control.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a control method and device for a smart home system, as well as a smart home system, to at least solve the technical problems in related technologies where smart home control schemes lack user subjective trust modeling and dynamic permission adjustment mechanisms, resulting in AI decisions that only conform to behavioral habits and are difficult to gain user approval, and the automation process lacks the ability to make gradual adjustments and abnormal degradation.

[0007] According to one aspect of the present invention, a control method for a smart home system is provided, comprising: acquiring multi-dimensional feature information of the smart home system, wherein the multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user feature data; determining the degree of acceptance of system operation behavior of the smart home system based on the multi-dimensional feature information; adjusting the current trust level of the smart home system according to the degree of acceptance to obtain an updated trust level of the smart home system; determining the current trust level of the smart home system according to the updated trust level; and controlling the smart home system according to the current trust level.

[0008] Optionally, acquiring multi-dimensional feature information of the smart home system includes: acquiring environmental context data through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity, and air quality, time period, and user presence status; acquiring device operating status data through a smart gateway or central control system in the smart home system; and searching a database to obtain user historical behavior data and user feature data.

[0009] Optionally, determining the acceptance level of system operation behavior of the smart home system based on multi-dimensional feature information includes: packaging the multi-dimensional feature information in a timestamp-associative manner to form a multi-dimensional feature vector; preprocessing the multi-dimensional feature vector to identify display interaction data and implicit behavior data, wherein the display interaction data includes control commands, evaluation tags, or confirmation signals directly input through an interactive interface or voice interface, and the implicit behavior data includes: state change logs generated by directly operating smart devices in the smart home system, corrective behavior data for the results of system automation execution, reverse operation commands or state reset operations received within a preset time window after the smart device executes control commands, and ignoring behavior data of system suggestions; marking the display interaction data as display feedback signals, and analyzing the time difference and difference magnitude of at least one of user operations, system suggestions, and automatic execution actions based on the implicit behavior data to identify implicit correction signals; and obtaining the acceptance level based on the display feedback signals and the implicit correction signals.

[0010] Optionally, obtaining the acceptance level based on the displayed feedback signal and the implicit correction signal includes: performing weighted fusion processing on the displayed feedback signal and the implicit correction signal to obtain a standardized feedback score sequence; and determining the acceptance level based on the standardized feedback score sequence.

[0011] Optionally, adjusting the current trust level of the smart home system based on the acceptance level to obtain the updated trust level of the smart home system includes: calculating a trust increment or trust decrement based on positive or negative feedback in a standardized feedback scoring sequence used to characterize the acceptance level and a preset weight parameter; and adjusting the current trust level based on the trust increment or trust decrement to obtain the updated trust level.

[0012] Optionally, adjusting the current trust level based on the trust increment or the trust decrement to obtain the updated trust level includes: combining the current trust level with the trust increment or the trust decrement using an exponential moving average algorithm or a recursive formula to obtain the updated trust level.

[0013] Optionally, determining the current trust level of the smart home system based on the updated trust level includes: comparing the updated trust level with each preset trust level interval to obtain a comparison result; and determining the current trust level based on the comparison result.

[0014] Optionally, after determining the current trust level of the smart home system based on the updated trust level, the control method further includes: determining the trust level change trend of the smart home system; and determining the trust evolution stage of the smart home system based on the trust level change trend.

[0015] Optionally, controlling the smart home system according to the current trust level includes: determining the control permissions of the smart home system according to the current trust level or the trust evolution stage, and controlling the smart home system according to the control permissions.

[0016] Optionally, determining the control permissions of the smart home system based on the current trust level or the trust evolution stage includes: forcibly reducing control permissions when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level; and maintaining or increasing control permissions when the current trust level is determined to be in a stable stage and the trust level is higher than a preset trust level.

[0017] Optionally, after controlling the smart home system according to the current trust level, the control method further includes: monitoring the real-time interactive feedback information of the smart home system; when the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined time, determining that the task execution has failed and recording negative feedback; when the real-time interactive feedback information indicates that the task to be confirmed has been confirmed or cannot be responded to, determining that the task execution has been successful and recording positive feedback.

[0018] According to another aspect of the present invention, a control device for a smart home system is also provided, comprising: an acquisition unit for acquiring multi-dimensional feature information of the smart home system, wherein the multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user feature data; a first determination unit for determining the degree of acceptance of system operation behavior of the smart home system based on the multi-dimensional feature information; an adjustment unit for adjusting the current trust level of the smart home system according to the degree of acceptance to obtain an updated trust level of the smart home system; a second determination unit for determining the current trust level of the smart home system according to the updated trust level; and a control unit for controlling the smart home system according to the current trust level.

[0019] Optionally, the acquisition unit includes: a first acquisition module, configured to acquire the environmental context data through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity, and air quality, time period, and user presence status; a second acquisition module, configured to acquire the device operating status data through a smart gateway or central control system in the smart home system; and a search module, configured to search the database to obtain the user's historical behavior data and the user characteristic data.

[0020] Optionally, the first determining unit includes: a packaging module, used to package the multidimensional feature information in a timestamp-associated manner to form a multidimensional feature vector; a preprocessing module, used to preprocess the multidimensional feature vector to identify display interaction data and implicit behavior data, wherein the display interaction data includes control commands, evaluation tags, or confirmation signals directly input through an interactive interface or voice interface, and the implicit behavior data includes: status change logs generated by directly operating smart devices in the smart home system, corrective behavior data for the system's automated execution results, reverse operation commands or status reset operations received within a preset time window after the smart device executes control commands, and ignore behavior data for system suggestions; a marking module, used to mark the display interaction data as display feedback signals, and analyze the time difference and difference magnitude of at least one of user operations, system suggestions, and automated execution actions based on the implicit behavior data to identify implicit correction signals; and a third acquisition module, used to obtain the acceptance level based on the display feedback signals and the implicit correction signals.

[0021] Optionally, the first determining unit includes: a processing module, configured to perform weighted fusion processing on the displayed feedback signal and the displayed implicit correction signal to obtain a standardized feedback scoring sequence; and a first determining module, configured to determine the acceptance level based on the standardized feedback scoring sequence.

[0022] Optionally, the adjustment unit includes: a calculation module, configured to calculate a trust increment or trust decrement based on positive or negative feedback in a standardized feedback scoring sequence used to characterize the acceptance level, and a preset weight parameter; and an adjustment module, configured to adjust the current trust level based on the trust increment or the trust decrement to obtain the updated trust level.

[0023] Optionally, the adjustment unit includes a combination submodule, used to combine the current trust level with the trust increment or the trust decrement using an exponential moving average algorithm or a recursive formula to obtain the updated trust level.

[0024] Optionally, the second determining unit includes: a comparison module, used to compare the updated trust level with each preset trust level interval to obtain a comparison result; and a second determining module, used to determine the current trust level based on the comparison result.

[0025] Optionally, the control method further includes: a third determining unit, configured to determine the trust level change trend of the smart home system after determining the current trust level of the smart home system based on the updated trust level; and a fourth determining unit, configured to determine the trust evolution stage of the smart home system based on the trust level change trend.

[0026] Optionally, the control unit includes a third determining module, configured to determine the control permissions of the smart home system based on the current trust level or the trust evolution stage, and control the smart home system according to the control permissions.

[0027] Optionally, the third determining module includes: a reduction submodule, used to forcibly reduce control permissions when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level; and a maintenance submodule, used to maintain or increase control permissions when the current trust level is determined to be in a stable stage and the trust level is higher than a preset trust level.

[0028] Optionally, the control method further includes: a detection unit, configured to monitor real-time interactive feedback information of the smart home system after controlling the smart home system according to the current trust level; a fifth determination unit, configured to determine that the task execution has failed and record negative feedback when the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined time period; and a sixth determination unit, configured to determine that the task execution has been successful and record positive feedback when the real-time interactive feedback information indicates that the task to be confirmed has been confirmed or that there is no response.

[0029] According to another aspect of the present invention, a smart home system is also provided, wherein the smart home system uses the control method of the smart home system described in any one of the above embodiments.

[0030] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method of the smart home system described in any one of the above embodiments.

[0031] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes the control method of the smart home system described in any one of the above embodiments.

[0032] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, which, when executed by a processor, perform the control method of the smart home system described in any one of the above embodiments.

[0033] By applying the above-described technical solution of this application, multi-dimensional feature information of a smart home system is obtained. This multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user characteristic data. Based on this multi-dimensional feature information, the acceptance level of the smart home system's operational behavior is determined. The current trust level of the smart home system is adjusted according to the acceptance level to obtain the updated trust level. The current trust level of the smart home system is determined based on the updated trust level. The smart home system is controlled according to the current trust level. This achieves dynamic updates to the trust level by constructing a multi-dimensional user trust modeling mechanism, integrating explicit feedback and implicit behavior correction data, and establishing a mapping relationship between trust level and control permissions based on the trust evolution path. This completes the dynamic transition from suggested execution to fully automatic execution and automatic degradation in abnormal situations. This solves the technical problems in related technologies where smart home control schemes lack user subjective trust modeling and dynamic permission adjustment mechanisms, resulting in AI decisions that only conform to behavioral habits and are difficult to gain user approval, and where the automation process lacks gradual adjustment and abnormal degradation capabilities. Attached Figure Description

[0034] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0035] Figure 1 This is a hardware structure block diagram of a mobile terminal for a control method of a smart home system according to an embodiment of the present invention.

[0036] Figure 2This is a flowchart of a control method for a smart home system according to an embodiment of the present invention;

[0037] Figure 3 This is a system structure diagram according to an embodiment of the present invention;

[0038] Figure 4 This is a flowchart illustrating the trust evolution process according to an embodiment of the present invention;

[0039] Figure 5 This is a schematic diagram of the control device for a smart home system according to an embodiment of the present invention.

[0040] The above figures include the following reference numerals:

[0041] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0042] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0043] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0044] As described in the background section, related smart home control solutions lack user subjective trust modeling and dynamic permission adjustment mechanisms. This results in AI decisions merely conforming to behavioral habits and failing to gain user approval. Furthermore, the automation process lacks the ability to progressively adjust and mitigate abnormal degradation. In embodiments of this invention, a control method and apparatus for a smart home system, a smart home system, a computer-readable storage medium, a processor, and a computer program product are provided.

[0045] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0046] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a control method of a smart home system according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0047] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the control method of the smart home system in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0048] Example 1

[0049] According to an embodiment of the present invention, a method embodiment for controlling a smart home system is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0050] Figure 2 This is a flowchart of a control method for a smart home system according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0051] Step S202: Obtain multi-dimensional feature information of the smart home system, including: environmental context data, device operating status data, user historical behavior data, and user feature data.

[0052] In this embodiment, in a typical home application scenario, the user's home is equipped with smart devices such as air conditioners, lights, curtains, and air purifiers, which are connected to a unified control platform through a smart gateway or central control system. During the initial operation phase, the system collects basic data on the home environment, such as indoor temperature, humidity, air quality, time information, and whether the user is at home, while also recording the operating status of each device.

[0053] This method uses multi-source data fusion technology to construct a three-dimensional data view that can comprehensively reflect the operating status of smart homes and the history of user interactions. Specifically, the system simultaneously collects environmental context data reflecting the current physical environment, device operating status data reflecting the real-time operating conditions of devices, user history behavior data recording past user operating habits, and user characteristic data characterizing user identity attributes, and integrates these heterogeneous data.

[0054] By implementing this control method, rich and multi-dimensional basic data support is provided for subsequent user trust modeling, enabling the system to not only understand how the device should act in the current environment, but also to comprehensively judge the rationality of the user's behavior by combining the user's past preferences and the user's identity, thereby effectively distinguishing between the objective correctness and subjective acceptability of AI decisions.

[0055] Step S204: Determine the level of acceptance of the system operation behavior of the smart home system based on multi-dimensional feature information.

[0056] In this embodiment, when the system first enables the AI-managed function, it does not immediately perform automatic control but instead enters a relatively conservative phase. For example, if the system detects a high indoor temperature at night, it will generate a prompt message suggesting that the air conditioner be turned on and set to 26 degrees Celsius, which will be pushed to the user via voice or an app. The user can choose to accept, reject, or ignore the suggestion. The system will record the user's action as initial feedback and initialize the trust level of the corresponding device to a low level.

[0057] This method transforms multidimensional user feedback into a computable trust value through a quantification algorithm. Specifically, the system first packages multidimensional information such as environment, device, history, and user characteristics into a multidimensional feature vector by associating them with timestamps. Then, after preprocessing, it separates the explicit user input display interaction data and the implicit behavior data identified through behavioral anomalies. Subsequently, it generates a standardized feedback scoring sequence through weighted fusion processing, and finally calculates the user's acceptance level of the system operation behavior based on this sequence.

[0058] By implementing this control method, it is possible to accurately distinguish between the objective correctness of AI behavior and the user's subjective acceptance. By combining explicit evaluations and implicit corrective signals, the true level of user acceptance of AI-managed behavior can be objectively quantified, providing a scientific basis for subsequent dynamic adjustment of control permissions.

[0059] Step S206: Adjust the current trust level of the smart home system according to the level of acceptance to obtain the updated trust level of the smart home system.

[0060] In this embodiment, as the system continues to run, various user behaviors generated during daily use are gradually collected. For example, users manually turning on the air conditioner, adjusting the temperature, turning off the device, or making secondary adjustments after the system automatically performs certain operations are all identified as implicit feedback. Simultaneously, when users express "it's a bit cold" via voice or evaluate an automatic operation in the app, this information is recorded as explicit feedback. The system then fuses this multi-source data. For example, if the system automatically turns on the air conditioner and the user turns it off shortly afterward, this behavior is identified as a negative correction signal; if the user does not intervene after the system's execution, it is considered positive feedback. Furthermore, if the user gives a clear negative evaluation of an operation, this feedback has a higher weight than ordinary behavioral data. Based on this fused feedback, the system scores each managed behavior and uses this score to update the corresponding trust level.

[0061] This method uses the degree of acceptance as a dynamic adjustment factor to iteratively update the trust value maintained by the system. Specifically, the system inputs the degree of acceptance (i.e. the user recognition level reflected by the standardized feedback rating sequence) calculated in step S204 into the trust update model, and corrects the current trust value in real time through preset algorithm logic (such as increasing the trust increment brought by positive acceptance or reducing the trust reduction caused by negative acceptance).

[0062] By implementing this control method, the dynamic evolution and closed-loop management of trust levels are realized, enabling the system to keenly capture subtle changes in user attitudes and reflect them in the trust model in real time. This ensures that the trust level always matches the user's true psychological expectations, providing accurate and real-time status basis for subsequent hierarchical control of permissions based on trust levels.

[0063] Step S208: Determine the current trust level of the smart home system based on the updated trust level.

[0064] In this embodiment, Table 1 is a trust level classification table, where T1, T2, T3, and T4 are preset threshold parameters that can be dynamically configured according to different device types, user preferences, or system policies, or adaptively adjusted through a learning model. In specific implementation, the system establishes trust level values ​​for different devices and scenarios, and performs hierarchical processing through parameterized thresholds. Table 1 defines a five-level trust level classification system based on parameterized thresholds, dividing trust into five intervals from L1 to L5, corresponding to low trust, relatively low trust, medium trust, high trust, and very high trust, respectively. The boundaries between each level are defined by preset dynamic thresholds T1 to T4, which can be adaptively adjusted according to device type, user preferences, or system policies, thereby providing a quantitative basis for hierarchical access control at different trust stages.

[0065] Table 1

[0066]

[0067] This method discretizes continuously changing trust values ​​into specific trust levels through a preset threshold mapping mechanism. Specifically, the system compares the updated trust value calculated in step S206 with these threshold intervals based on preset parameterized thresholds (such as T1, T2, T3, T4) to determine which trust level the user is currently at among L1 to L5.

[0068] By implementing this control method, a logical bridge is established between quantified trust values ​​and control strategies, enabling the system to transform abstract trust levels into explicit management states. This provides a standardized decision-making basis for matching corresponding control permissions based on trust levels, ensuring that automated control behavior always remains within the user's acceptable trust boundaries.

[0069] Step S210: Control the smart home system according to the current trust level.

[0070] In this embodiment, in actual deployment, the method can be integrated into smart speakers, home gateways, or cloud control platforms through software upgrades, without requiring modifications to existing device structures, and has good compatibility and promotional value.

[0071] Figure 3 This is a system structure diagram according to an embodiment of the present invention, such as... Figure 3 As shown, the system first acquires raw data from multiple sources, including environment, devices, and user behavior, through a multi-dimensional data acquisition module. This data is then passed to a managed decision module equipped with an AI Agent to make an initial intelligent managed judgment. Next, the user feedback analysis module mines subjective user evaluation information, which is then sent to a trust modeling module for multi-dimensional feature fusion and hierarchical trust value calculation. The generated trust score is then passed to a trust evolution management module, which dynamically updates the trust status based on stage migration and trust degradation mechanisms. Subsequently, based on the dynamic trust results, the permission hierarchical control module matches corresponding access and operation permissions. Finally, the decision interpretation module outputs the judgment basis and process description for each link in the entire chain, thus fully realizing an integrated security trust management system from data acquisition, intelligent decision-making, trust calculation, dynamic trust evolution, permission allocation to interpretable results.

[0072] This method establishes a mapping execution mechanism between trust levels and control policies. Specifically, the system queries a preset mapping table (i.e., the permission level control policy in Table 2) based on the current trust level (such as L1 to L5) determined in step S208, determines the corresponding control permission level (P1 to P5), and executes the corresponding control action according to the permission level. For example, at a low trust level, only suggestions or requests for confirmation are issued, while at a high trust level, automated control is directly executed.

[0073] By implementing this control method, the level of automation of the smart home system can be dynamically and adaptively adjusted, ensuring that the AI-managed behavior always matches the user's level of trust. This avoids user resentment caused by excessive automation and ensures that convenient automated services are provided when the user trusts the system, thereby significantly improving the user's acceptance of the smart home system, sense of security, and overall user experience.

[0074] As described above, in this embodiment, multi-dimensional feature information of the smart home system is obtained, including environmental context data, device operating status data, user historical behavior data, and user feature data. Based on this multi-dimensional feature information, the acceptance level of the smart home system's operational behavior is determined. The current trust level of the smart home system is adjusted according to the acceptance level to obtain the updated trust level. The current trust level of the smart home system is determined based on the updated trust level. The smart home system is controlled according to the current trust level. This achieves the goal of dynamically updating the trust level by constructing a multi-dimensional user trust modeling mechanism, integrating explicit feedback and implicit behavior correction data, and establishing a mapping relationship between trust level and control permissions based on the trust evolution path. This completes the dynamic transition from suggested execution to fully automatic execution and the automatic degradation of abnormal situations. It effectively distinguishes the correctness and acceptance level of AI behavior, achieves dynamic adjustment of automation level and automatic degradation of abnormal situations, and significantly improves user acceptance, satisfaction, and system security of the smart home hosting system.

[0075] Therefore, the technical solutions provided by the above embodiments of the present invention solve the technical problems in related technologies where smart home control solutions lack user subjective trust modeling and dynamic permission adjustment mechanisms, resulting in AI decisions that only conform to behavioral habits and are difficult to gain user approval, and where the automation process lacks the ability to make gradual adjustments and abnormal degradation.

[0076] According to the above embodiments of the present invention, obtaining multi-dimensional feature information of a smart home system includes: obtaining environmental context data through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity and air quality, time period and user presence status; obtaining device operating status data through a smart gateway or central control system in the smart home system; and searching for user historical behavior data and user feature data from a database.

[0077] In this embodiment, acquiring environmental context data refers to using various sensors deployed in the smart home system to collect objective indicators reflecting the physical state of the living environment and the presence of users. Specifically, this includes environmental parameters such as indoor temperature, humidity, and air quality, as well as spatiotemporal and personnel attribute information such as time period and user presence. Acquiring device operation status data refers to reading and controlling the current operating parameters and status information of various smart devices (such as air conditioners, lights, curtains, etc.) in real time through a smart gateway or central control system. Acquiring user historical behavior data and user characteristic data refers to retrieving static or long-term accumulated data such as users' past operation records, habit preferences, and user identity characteristics from the historical database stored in the system.

[0078] This method comprehensively constructs the operational profile of a smart home system through a multi-source heterogeneous data acquisition mechanism. Specifically, the system uses various sensors deployed in the home environment to collect data reflecting the current physical environment (such as temperature, humidity, air quality, time, and user presence) in real time. At the same time, it obtains the real-time operating status of the devices through a smart gateway or central control system, and retrieves the user's historical operation records and identity attribute information from the database, integrating these three types of data into multi-dimensional feature information.

[0079] By implementing this control method, a rich and comprehensive data foundation is provided for trust modeling, enabling the system to not only perceive the current physical environment and device status, but also to make comprehensive judgments by combining the user's historical habits and identity characteristics. This effectively makes up for the limitations of existing technologies that rely solely on single behavioral or environmental data, and improves the accuracy and comprehensiveness of trust assessment.

[0080] According to the above embodiments of the present invention, determining the acceptance level of system operation behavior of a smart home system based on multi-dimensional feature information includes: packaging multi-dimensional feature information in a timestamp-associative manner to form a multi-dimensional feature vector; preprocessing the multi-dimensional feature vector to identify display interaction data and implicit behavior data, wherein the display interaction data includes control commands, evaluation tags, or confirmation signals directly input through an interactive interface or voice interface, and the implicit behavior data includes: status change logs generated by directly operating smart devices in the smart home system, corrective behavior data for the results of automated system execution, reverse operation commands or status reset operations received within a preset time window after the smart device executes control commands, and ignoring behavior data of system suggestions; marking the display interaction data as display feedback signals, and analyzing the time difference and difference magnitude of at least one of user operations, system suggestions, and automated execution actions based on implicit behavior data to identify implicit correction signals; and obtaining the acceptance level based on the display feedback signals and the implicit correction signals.

[0081] In this embodiment, packaging multidimensional feature information into a multidimensional feature vector by associating it with timestamps refers to aligning and integrating the aforementioned acquired environmental context data, device operating status data, user historical behavior data, and user feature data according to the chronological order of occurrence, constructing a structured data set containing time dimensions and multi-source heterogeneous data. Preprocessing the multidimensional feature vector to identify explicit interaction data and implicit behavioral data involves classifying and parsing the packaged data. Explicit interaction data specifically refers to explicit commands, rating tags, or confirmation signals actively issued by the user through the APP interface or voice assistant, while implicit behavioral data refers to state changes caused by the user directly operating the device without explicit commands, corrections to the system's automatic execution results (such as the user manually turning off the air conditioner after the system turns it on), and reverse operations within a preset time window. The system includes actions such as resetting the state and ignoring system suggestions; marking interactive data as display feedback signals; and analyzing the time difference and magnitude of at least one of user operations, system suggestions, and automated actions based on implicit behavioral data to identify implicit correction signals. Implicit correction signals directly convert explicit data into positive or negative trust signals. For implicit data, the system calculates the time lag (time difference) between the user's actual operation and the system suggestion or automated action, as well as the deviation (magnitude of difference) between the operation result and the system's expected result, to determine whether the user has made substantial intervention or correction. The acceptance level based on the display feedback signals and implicit correction signals refers to comprehensively considering explicit direct evaluation and implicit behavioral correction, using a weighted or algorithmic model to calculate a numerical value or level reflecting the user's current level of acceptance of AI-managed behavior.

[0082] This method quantifies users' subjective acceptance through multi-source data fusion and explicit / implicit feedback separation. Specifically, the system first packages multi-dimensional feature information into feature vectors by timestamp, then preprocesses and separates explicit interaction data directly input by users through the interface or voice as explicit feedback signals, and identifies implicit behavioral data such as device status changes, secondary corrections, or ignoring suggestions from logs to generate implicit correction signals. Finally, the acceptance level is calculated by combining these two types of signals.

[0083] By implementing this control method, the limitations of traditional technologies that rely solely on behavior fitting are overcome. By integrating explicit user evaluations with implicit behavior corrections (such as automatic execution followed by manual shutdown), the objective correctness of AI decisions and the user's subjective acceptance can be accurately distinguished, thereby more realistically reflecting the user's trust boundaries and acceptance level regarding smart home management behavior.

[0084] According to the above embodiments of the present invention, the acceptance level is obtained based on the displayed feedback signal and the implicit correction signal, including: performing weighted fusion processing on the displayed feedback signal and the implicit correction signal to obtain a standardized feedback score sequence; and determining the acceptance level based on the standardized feedback score sequence.

[0085] In this embodiment, the weighted fusion processing of the displayed feedback signal and the implicit correction signal to obtain the standardized feedback score sequence refers to the mathematical combination and integration of the previously identified displayed feedback signal, which represents the user's direct evaluation, and the implicit correction signal, which represents the user's implicit behavioral intervention, according to preset weight coefficients or learning models. The units are unified to eliminate the magnitude differences between different data sources, ultimately generating a numerical set of feedback scores arranged in chronological order. Determining the acceptance level based on the standardized feedback score sequence means calculating the user's level of acceptance or trust in the smart home system's managed behavior at the current moment, based on the aforementioned standardized feedback score sequence and using a specific trust update algorithm or threshold mapping rule.

[0086] This method transforms heterogeneous explicit and implicit feedback signals into unified quantifiable indicators through a weighted fusion algorithm. Specifically, the system assigns different weight coefficients to explicit feedback signals (such as explicit evaluation labels) and implicit correction signals (such as operation time difference and difference magnitude) for weighted fusion, generating a standardized feedback scoring sequence, and then derives the final acceptance level value based on this sequence through mapping or calculation.

[0087] By implementing this control method, the problem of the one-sidedness of a single feedback source is solved. By integrating direct subjective evaluations and indirect behavioral data, it is possible to more comprehensively and objectively reflect the user's true acceptance of the system operation, improve the accuracy of trust modeling, and provide a scientific and reliable basis for the subsequent dynamic adjustment of trust.

[0088] According to the above embodiments of the present invention, adjusting the current trust level of the smart home system based on the level of acceptance to obtain the updated trust level of the smart home system includes: calculating the trust increment or trust decrement based on positive or negative feedback in a standardized feedback scoring sequence used to characterize the level of acceptance and a preset weight parameter; and adjusting the current trust level based on the trust increment or trust decrement to obtain the updated trust level.

[0089] In this embodiment, the trust level is not fixed during system operation, but is continuously and dynamically updated based on user feedback. For example, in the initial stage (corresponding to L1 or L2), the system mainly provides prompts or suggestions without automatic control; when the user repeatedly accepts the system's suggestions without making corrections, the trust level gradually increases to L3 or L4, at which point the system can automatically perform operations in some scenarios; when the trust level further increases to L5, the system can directly execute control strategies when specific conditions are met, without user intervention.

[0090] This method utilizes positive and negative feedback signals in a standardized feedback scoring sequence and dynamically calculates the increment or decrement of trust value by combining preset weight parameters. Specifically, the system identifies positive feedback reflecting user approval or negative feedback reflecting user disapproval in the scoring sequence, calculates the corresponding trust increment or decrement based on preset weights, and adds this change to the current trust level to obtain the updated trust level value.

[0091] By implementing this control method, dynamic adaptive updates of trust levels are achieved, enabling the system to adjust the level of trust in AI-managed behavior in real time based on users' immediate feedback. This ensures that the trust model can keenly capture changes in user attitudes, providing accurate and timely status information for subsequent fine-grained control of permissions.

[0092] According to the above embodiments of the present invention, adjusting the current trust level based on trust increment or trust decrement to obtain the updated trust level includes: using an exponential moving average algorithm or a recursive formula to combine the current trust level with the trust increment or trust decrement to obtain the updated trust level.

[0093] In this embodiment, in a multi-user family environment, the system can also differentiate and process feedback from different users. For example, when there are multiple members in the family, the system can record each user's behavior and feedback based on their identity, and calculate the trust level comprehensively through a weighted method to avoid the behavior of a single user having too much influence on the overall system decision-making.

[0094] This method uses an exponential moving average (EMA) or a recursive algorithm to smoothly update the trust level. Specifically, the system calculates the updated trust level by weighting the current trust level with the latest calculated trust increment or decrement, giving higher weight to recent feedback and gradually attenuating the influence of historical feedback.

[0095] By implementing this control method, the severe impact of a single extreme feedback on the system's trust model is effectively suppressed, achieving a smooth transition and stability in trust evolution. This ensures the system's ability to respond quickly to new user feedback while avoiding trust fluctuations caused by volatile data, thus guaranteeing the consistency and security of smart home hosting permission adjustments.

[0096] According to the above embodiments of the present invention, determining the current trust level of a smart home system based on the updated trust level includes: comparing the updated trust level with each preset trust level interval to obtain a comparison result; and determining the current trust level based on the comparison result.

[0097] In this embodiment, based on the trust levels in Table 1, the system further establishes a mapping relationship between trust level and control permissions to achieve tiered release of AI managed capabilities. The control strategy is shown in Table 2. Table 2 is the permission tiered control strategy (mapping relationship) table, mapping trust levels L1 to L5 to five permission levels P1 to P5, specifically covering five modes: prohibit execution, provide suggestions only, execute after confirmation, semi-automatic execution, and fully automatic execution. The permission level is dynamically determined based on the current trust level using the mapping function f(Trust), and the mapping relationship supports pre-configuration or adaptive adjustment. Its function is to achieve a gradual release and automatic degradation of AI managed capabilities, ensuring that the system gradually grants higher control as the user builds trust, while promptly revoking permissions when trust decreases to ensure security, thereby achieving a dynamic balance between automation efficiency and user controllability.

[0098] Table 2

[0099]

[0100] This method discretizes continuous trust values ​​through an interval mapping mechanism. Specifically, the system constructs multiple trust intervals based on preset parameterized thresholds (such as T1, T2, T3, T4), compares the updated trust values ​​obtained in step S206 with the boundaries of these intervals one by one, and determines the user's current trust level in L1 to L5 based on the range of the intervals they fall into.

[0101] By implementing this control method, a logical bridge is established between quantified trust values ​​and control strategies, enabling the system to transform abstract trust levels into explicit management states. This provides a standardized decision-making basis for matching corresponding control permissions based on trust levels, ensuring that automated control behavior always remains within the user's acceptable trust boundaries.

[0102] According to the above embodiments of the present invention, after determining the current trust level of the smart home system based on the updated trust level, the control method further includes: determining the trust level change trend of the smart home system; and determining the trust evolution stage of the smart home system based on the trust level change trend.

[0103] In this embodiment, the system introduces a trust evolution path mechanism to manage the trust change process in stages. During the cold start phase, the system strictly limits automated behavior; after entering the learning phase, the system gradually attempts to execute some operations and observes user feedback; when it enters the stable phase, the system has a high degree of autonomous control capability; however, in actual operation, once continuous negative feedback is detected, such as users frequently canceling or modifying system operations, the system will trigger a degradation mechanism, causing the trust level to decrease and automatically reducing the control privilege, for example, from P5 to P3 or P2, thus returning to a control mode based primarily on user confirmation.

[0104] This method identifies the dynamic evolution trajectory of trust through a time-series analysis mechanism. Specifically, the system analyzes the direction (rise, fall, or fluctuation) and rate of change of trust values ​​or level sequences at multiple historical time points, thereby determining whether the system is currently in a specific trust evolution stage such as cold start, learning, stabilization, or degradation.

[0105] By implementing this control method, the system is given the ability to perceive the evolution of trust status in a macroscopic way, enabling it to predict the trend of changes in user trust in advance. This allows the system to adopt a conservative strategy in the early stage of trust establishment, release higher privileges in the stable period, or trigger downgrade protection in advance when a trend of trust decline is detected, thereby enhancing the system's foresight and adaptability in response to changes in user attitudes.

[0106] According to the above embodiments of the present invention, controlling a smart home system based on the current trust level includes: determining the control permissions of the smart home system based on the current trust level or trust evolution stage, and controlling the smart home system based on the control permissions.

[0107] In this embodiment, determining the control permissions of the smart home system based on the current trust level or trust evolution stage means using the aforementioned mapping function f(Trust) to dynamically match the real-time calculated current trust level (L1 to L5) or the trust evolution stage (cold start, learning, stable, or degenerate stage) of the system to the corresponding control permission level (as shown in Table 2, P1 to P5). Controlling the smart home system according to the control permissions means executing the corresponding device control logic based on the determined control permission level. For example, under P1 / P2 permissions, only prompts or suggestions are issued; under P3 permissions, user confirmation is requested; under P4 permissions, execution is followed by notification; or under P5 permissions, control commands are executed directly. At the same time, combined with the degradation mechanism in the trust evolution stage, the permission level is automatically reduced when continuous negative feedback is detected.

[0108] This method establishes a dynamic mapping execution mechanism between trust levels / stages and control strategies. Specifically, the system queries the preset mapping relationship (as shown in Table 2 for the permission hierarchical control strategy) based on the current trust level (L1-L5) determined in step S208 or the trust evolution stage determined in step S212, determines the corresponding control permission level (P1-P5), and executes different levels of control actions from "providing information only" to "fully automatic execution".

[0109] By implementing this control method, the degree of automation of the smart home system can be adaptively adjusted, ensuring that the AI-managed behavior always matches the user's level of trust and acceptance. When trust is insufficient, a low-privilege strategy is used to protect the user's sense of security and control, while a high-privilege strategy is used to provide convenient services after trust is established. This effectively solves the problems of rigid automation strategies and lack of dynamic permission adjustment in existing technologies, and significantly improves the security and user experience of human-machine collaborative control.

[0110] According to the above embodiments of the present invention, determining the control authority of a smart home system based on the current trust level or trust evolution stage includes: when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level, forcibly reducing the control authority; when it is determined that the current trust level is in a stable stage and the trust level is higher than a preset trust level, maintaining or increasing the control authority.

[0111] In this embodiment, when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is low, the forced reduction of control permissions means that when the system detects continuous negative feedback from the user (such as frequent corrections, rejection of suggestions, or explicit negative evaluations), causing the trust level to drop and triggering the degradation stage in the trust evolution path, or when the currently calculated trust level is in the L1 (low trust) or L2 (lower trust) range, the system automatically performs a permission downgrade operation, for example, switching directly from fully automatic execution (P5) or semi-automatic execution (P4) to execution after requesting user confirmation (P3) or even just providing suggestions (P2). When it is determined that the current trust level is in a stable stage and the trust level is higher than the preset trust level, maintaining or increasing control permissions means that when the system runs smoothly and the user feedback is continuously positive, causing the trust level to rise to L3 (medium trust) or above and enter the "stable stage" in the trust evolution path, the system maps it to a higher control permission level (such as from P3 to P4 or P5) according to the current trust level value, and maintains this high permission state until the trust level changes.

[0112] Figure 4 This is a trust evolution flowchart according to an embodiment of the present invention, such as... Figure 4As shown, the trust thresholds T1, T3, and T4 are used to divide the process into four transitional states: When the initial trust value Trust ≤ T1, it is in the cold start stage. After accumulating positive feedback, the trust increases and enters the learning stage of T1 < Trust ≤ T3. During the learning stage, positive feedback is continuously received, and the trust value breaks through T3 to reach T3 < Trust ≤ T4 or above, switching to the high trust stable stage. If negative feedback is continuously accumulated in the high trust stable stage, the trust value continues to decline, triggering the degradation process and reverting to the downgraded stable stage where the trust declines. At this time, the learning mechanism can be used to return to the learning stage and rely on positive behavior to improve the trust again, forming a closed-loop trust life cycle evolution logic that can be increased or decreased and supports repair.

[0113] This method dynamically adjusts control permissions based on a dual logic of status warning and achievement confirmation. Specifically, when the system detects that the trust evolution has entered a degradation stage or the current trust level is low, a forced downgrade mechanism is triggered to reduce control permissions. When the system determines that it is in a stable stage and the trust level is higher than a preset threshold, the operation of maintaining or upgrading permissions is performed.

[0114] By implementing this control method, a security closed loop and incentive feedback mechanism for the smart home system is constructed. This mechanism can quickly converge automated behavior to avoid risks and ensure user safety when user trust decreases or the system performs poorly, and can fully release AI capabilities to improve the automation experience when trust is stable. This effectively balances the intelligence level and controllability of the smart home system.

[0115] According to the above embodiments of the present invention, after controlling the smart home system according to the current trust level, the control method further includes: monitoring the real-time interactive feedback information of the smart home system; when the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined time, determining that the task execution has failed and recording negative feedback; when the real-time interactive feedback information indicates that the task to be confirmed has been confirmed or that there is no response, determining that the task execution has been successful and recording positive feedback.

[0116] In this embodiment, monitoring the real-time interactive feedback information of the smart home system means that after the system issues a task to be confirmed (such as requesting the user to confirm whether to execute a certain automatic control), it continuously listens to and collects the user's immediate response data to the task, including real-time signals such as the user's voice response, APP click operation, or silence. When the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined time, the task is determined to have failed and negative feedback is recorded. This means that when the system detects that the user neither gives a positive confirmation nor a clear rejection (i.e., silence or no response) within the set predetermined time, or when the user clearly issues a rejection command, the system determines that this interaction is a task execution failure and marks the result as a negative feedback signal and stores it in the record.

[0117] This method establishes a task execution result judgment and feedback collection mechanism based on real-time interactive response. Specifically, the system continuously monitors the real-time interaction data between the user and the smart home system. It judges whether the user responds to the AI-initiated task to be confirmed within a predetermined time. If there is no response or explicit rejection, the task is judged as a failure and negative feedback is recorded. If the user confirms the execution or the system automatically completes it successfully, the task is judged as a success and positive feedback is recorded.

[0118] By implementing this control method, state awareness and data accumulation in closed-loop control are achieved, transforming users' real-time interactive behaviors into structured trust update criteria. This ensures that the system can accurately capture users' acceptance of specific tasks, providing real-time and objective data support for subsequent precise adjustments to trust levels, thereby improving the timeliness and accuracy of trust modeling.

[0119] As can be seen from the above, the technical solution provided by the above embodiments of the present invention constructs a multi-dimensional user trust evaluation model that integrates explicit feedback (such as voice evaluation and App rating) and implicit corrective behaviors (such as manual shutdown and temperature readjustment), realizing a paradigm shift from behavior learning to trust learning. Based on this trust model, a dynamically evolving permission hierarchical control system is established. Through a four-stage trust evolution path of cold start—learning—stabilization—degradation, the trust level and control permissions (from prompting only to fully automatic execution) are intelligently mapped, enabling the system to adaptively improve or downgrade automation capabilities according to the user's acceptance level. This significantly enhances the user's sense of control, security, and long-term usage willingness while ensuring an intelligent experience, achieving true human-machine trust collaboration.

[0120] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to 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 device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0122] Example 2

[0123] According to embodiments of the present invention, a control device for a smart home system for implementing the control method of the above-described smart home system is also provided. Figure 5 This is a schematic diagram of a control device for a smart home system according to an embodiment of the present invention, such as... Figure 5 As shown, the device includes: an acquisition unit 501, a first determination unit 503, an adjustment unit 505, a second determination unit 507, and a control unit 509. The device will now be described in detail.

[0124] The acquisition unit 501 is used to acquire multi-dimensional feature information of the smart home system, including: environmental context data, device operating status data, user historical behavior data, and user feature data.

[0125] The first determining unit 503 is used to determine the degree of acceptance of the system operation behavior of the smart home system based on multi-dimensional feature information.

[0126] The adjustment unit 505 is used to adjust the current trust level of the smart home system according to the level of acceptance, so as to obtain the updated trust level of the smart home system.

[0127] The second determining unit 507 is used to determine the current trust level of the smart home system based on the updated trust level.

[0128] Control unit 509 is used to control the smart home system according to the current trust level.

[0129] It should be noted that the above-mentioned acquisition unit 501, first determination unit 503, adjustment unit 505, second determination unit 507 and control unit 509 correspond to steps S202 to S210 in the above embodiments. The five units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0130] As can be seen from the above, in the solution described in the above embodiments of the present invention, an acquisition unit can be used to acquire multi-dimensional feature information of the smart home system, wherein the multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user feature data; a first determining unit is used to determine the degree of acceptance of the system operation behavior of the smart home system based on the multi-dimensional feature information; an adjustment unit is used to adjust the current trust level of the smart home system according to the degree of acceptance to obtain the updated trust level of the smart home system; a second determining unit is used to determine the current trust level of the smart home system according to the updated trust level; and a control unit is used to control the smart home system according to the current trust level. The above technical solution achieves the goal of dynamically updating trust levels by constructing a multi-dimensional user trust modeling mechanism, integrating explicit feedback and implicit behavioral correction data, and establishing a mapping relationship between trust levels and control permissions based on the trust evolution path. This enables a dynamic transition from suggested execution to fully automatic execution and automatic degradation in abnormal situations. It effectively distinguishes the correctness and acceptance of AI behavior, dynamically adjusts the degree of automation, and automatically degrades abnormal situations, significantly improving users' acceptance, satisfaction, and security of the smart home hosting system.

[0131] Therefore, the technical solutions provided by the above embodiments of the present invention solve the technical problems in related technologies where smart home control solutions lack user subjective trust modeling and dynamic permission adjustment mechanisms, resulting in AI decisions that only conform to behavioral habits and are difficult to gain user approval, and where the automation process lacks the ability to make gradual adjustments and abnormal degradation.

[0132] Optionally, the acquisition unit includes: a first acquisition module, used to acquire environmental context data through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity and air quality, time period and user presence status; a second acquisition module, used to acquire device operating status data through a smart gateway or central control system in the smart home system; and a search module, used to search for user historical behavior data and user characteristic data from the database.

[0133] Optionally, the first determining unit includes: a packaging module, used to package multi-dimensional feature information in a timestamp-associated manner to form a multi-dimensional feature vector; a preprocessing module, used to preprocess the multi-dimensional feature vector to identify display interaction data and implicit behavioral data, wherein the display interaction data includes control commands, evaluation labels, or confirmation signals directly input through the interactive interface or voice interface, and the implicit behavioral data includes: status change logs generated by directly operating smart devices in the smart home system, corrective behavioral data for the results of system automation execution, reverse operation commands or status reset operations received within a preset time window after the smart device executes control commands, and ignoring behavioral data of system suggestions; a marking module, used to mark the display interaction data as display feedback signals, and analyze the time difference and difference magnitude of at least one of user operations, system suggestions, and automatic execution actions based on the implicit behavioral data to identify implicit corrective signals; and a third acquisition module, used to obtain the acceptance level based on the display feedback signals and the implicit corrective signals.

[0134] Optionally, the first determining unit includes: a processing module, used to perform weighted fusion processing on the displayed feedback signal and the shown implicit correction signal to obtain a standardized feedback score sequence; and a first determining module, used to determine the degree of acceptance based on the standardized feedback score sequence.

[0135] Optionally, the adjustment unit includes: a calculation module for calculating trust increment or trust decrement based on positive or negative feedback in a standardized feedback scoring sequence used to characterize acceptance level, and preset weight parameters; and an adjustment module for adjusting the current trust level based on the trust increment or trust decrement to obtain the updated trust level.

[0136] Optionally, the adjustment unit includes a combination submodule, which uses an exponential moving average algorithm or a recursive formula to combine the current trust level with the trust increment or trust decrement to obtain the updated trust level.

[0137] Optionally, the second determining unit includes: a comparison module, used to compare the updated trust level with each preset trust level interval to obtain a comparison result; and a second determining module, used to determine the current trust level based on the comparison result.

[0138] Optionally, the control method further includes: a third determining unit, used to determine the trust level change trend of the smart home system after determining the current trust level of the smart home system based on the updated trust level; and a fourth determining unit, used to determine the trust evolution stage of the smart home system based on the trust level change trend.

[0139] Optionally, the control unit includes: a third determining module, used to determine the control permissions of the smart home system based on the current trust level or trust evolution stage, and to control the smart home system according to the control permissions.

[0140] Optionally, the third determining module includes: a reduction submodule, used to forcibly reduce control permissions when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level; and a maintenance submodule, used to maintain or increase control permissions when the current trust level is determined to be in a stable stage and the trust level is higher than the preset trust level.

[0141] Optionally, the control method further includes: a detection unit, used to monitor the real-time interactive feedback information of the smart home system after controlling the smart home system according to the current trust level; a fifth determination unit, used to determine that the task execution has failed and record negative feedback when the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined time; and a sixth determination unit, used to determine that the task execution has been successful and record positive feedback when the real-time interactive feedback information indicates that the task to be confirmed has been confirmed or that there is no response.

[0142] According to another aspect of the present invention, a smart home system is also provided, wherein the smart home system uses the control method of any of the above-described smart home systems.

[0143] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the control method of the smart home system described above.

[0144] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the control method of the smart home system described above.

[0145] According to another aspect of the present invention, a computer program product is also provided, including computer instructions, which, when executed by a processor, perform a control method for a smart home system according to any of the above-described embodiments.

[0146] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0147] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring multi-dimensional feature information of the smart home system, wherein the multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user feature data; determining the degree of acceptance of system operation behavior of the smart home system based on the multi-dimensional feature information; adjusting the current trust level of the smart home system according to the degree of acceptance to obtain the updated trust level of the smart home system; determining the current trust level of the smart home system according to the updated trust level; and controlling the smart home system according to the current trust level.

[0148] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring environmental context data through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity and air quality, time period and user presence status; acquiring device operating status data through the smart gateway or central control system in the smart home system; and searching for user historical behavior data and user characteristic data from the database.

[0149] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: packaging multidimensional feature information in a timestamp-associated manner to form a multidimensional feature vector; preprocessing the multidimensional feature vector to identify display interaction data and implicit behavioral data, wherein the display interaction data includes control commands, evaluation tags, or confirmation signals directly input through an interactive interface or voice interface, and the implicit behavioral data includes: status change logs generated by directly operating smart devices in the smart home system, corrective behavioral data for the results of system automation execution, reverse operation commands or status reset operations received within a preset time window after the smart device executes control commands, and ignoring behavioral data of system suggestions; marking the display interaction data as display feedback signals, and analyzing the time difference and difference magnitude of at least one of user operations, system suggestions, and automated execution actions based on the implicit behavioral data to identify implicit corrective signals; and obtaining the acceptance level based on the display feedback signals and the implicit corrective signals.

[0150] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: performing weighted fusion processing on the displayed feedback signal and the shown implicit correction signal to obtain a standardized feedback score sequence; and determining the degree of acceptance based on the standardized feedback score sequence.

[0151] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: calculating a trust increment or trust decrement based on positive or negative feedback in a standardized feedback scoring sequence used to characterize the degree of acceptance, and a preset weight parameter; adjusting the current trust level based on the trust increment or trust decrement to obtain an updated trust level.

[0152] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: combining the current trust level with the trust increment or trust decrement using an exponential moving average algorithm or a recursive formula to obtain an updated trust level.

[0153] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: comparing the updated trust level with each preset trust level interval to obtain a comparison result; and determining the current trust level based on the comparison result.

[0154] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the trust level change trend of the smart home system; and determining the trust evolution stage of the smart home system based on the trust level change trend.

[0155] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the control permissions of the smart home system based on the current trust level or trust evolution stage, and controlling the smart home system according to the control permissions.

[0156] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level, forcibly reduce the control authority; when it is determined that the current trust level is in a stable stage and the trust level is higher than the preset trust level, maintain or increase the control authority.

[0157] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: monitoring real-time interactive feedback information of the smart home system; determining that the task execution has failed and recording negative feedback when the real-time interactive feedback information indicates that there is no response or rejection of the task to be confirmed within a predetermined period of time; and determining that the task execution has succeeded and recording positive feedback when the real-time interactive feedback information indicates that the task to be confirmed has been confirmed or there is no response.

[0158] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0163] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0164] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for a smart home system, characterized in that, include: The system acquires multi-dimensional feature information of a smart home system, including: environmental context data, device operating status data, user historical behavior data, and user feature data. The degree of acceptance of the system operation behavior of the smart home system is determined based on multi-dimensional feature information; The current trust level of the smart home system is adjusted based on the level of acceptance to obtain the updated trust level of the smart home system. The current trust level of the smart home system is determined based on the updated trust level. Control the smart home system based on the current trust level.

2. The control method for a smart home system according to claim 1, characterized in that, Obtain multi-dimensional feature information of the smart home system, including: The environmental context data is acquired through sensors deployed in the smart home system, wherein the environmental context data includes at least one of the following: indoor temperature, humidity and air quality, time period and user presence status; The device's operating status data is obtained through the smart gateway or central control system in the smart home system; The user's historical behavior data and user characteristic data are obtained by searching the database.

3. The control method for a smart home system according to claim 1, characterized in that, Determining the level of acceptance of system operation behaviors of the smart home system based on multi-dimensional feature information includes: The multidimensional feature information is packaged using a timestamp association method to form a multidimensional feature vector; The multidimensional feature vector is preprocessed to identify explicit interaction data and implicit behavioral data. The explicit interaction data includes control commands, evaluation tags, or confirmation signals directly input through an interactive interface or voice interface. The implicit behavioral data includes: status change logs generated by directly operating smart devices in the smart home system, corrective behavior data for the results of system automation execution, reverse operation commands or status reset operations received within a preset time window after the smart device executes control commands, and ignoring behavior data of system suggestions. The display interaction data is marked as display feedback signals, and the time difference and difference magnitude of at least one of user operations, system suggestions and automatic execution actions are analyzed based on the implicit behavior data to identify implicit correction signals. The degree of acceptance is determined based on the displayed feedback signal and the implicit correction signal shown.

4. The control method for the smart home system according to claim 3, characterized in that, The degree of acceptance is determined based on the displayed feedback signal and the implicit correction signal, including: The displayed feedback signal and the implicit correction signal are weighted and fused to obtain a standardized feedback scoring sequence; The level of acceptance is determined based on the standardized feedback scoring sequence.

5. The control method for a smart home system according to claim 1, characterized in that, The current trust level of the smart home system is adjusted based on the acceptance level to obtain the updated trust level of the smart home system, including: Based on the positive or negative feedback in the standardized feedback scoring sequence used to characterize the degree of acceptance, and a preset weighting parameter, calculate the trust increment or trust decrement. The current trust level is adjusted based on the trust increment or the trust decrement to obtain the updated trust level.

6. The control method for a smart home system according to claim 5, characterized in that, The current trust level is adjusted based on the trust increment or the trust decrement to obtain the updated trust level, including: The updated trust level is obtained by combining the current trust level with the trust increment or the trust decrement using an exponential moving average algorithm or a recursive formula.

7. The control method for a smart home system according to claim 1, characterized in that, Determining the current trust level of the smart home system based on the updated trust level includes: The updated trust level is compared with each preset trust level interval to obtain the comparison results; The current trust level is determined based on the comparison results.

8. The control method for a smart home system according to any one of claims 1 to 7, characterized in that, After determining the current trust level of the smart home system based on the updated trust level, the control method further includes: Determine the trend of trust level changes in the smart home system; The trust evolution stage of the smart home system is determined based on the trend of trust changes.

9. The control method for a smart home system according to claim 8, characterized in that, Controlling the smart home system based on the current trust level includes: The control permissions of the smart home system are determined based on the current trust level or the trust evolution stage, and the smart home system is controlled according to the control permissions.

10. The control method for a smart home system according to claim 9, characterized in that, Determining the control permissions of the smart home system based on the current trust level or the trust evolution stage includes: When the trust evolution stage indicates that the smart home system is in a degradation stage or the current trust level is a low trust level, control permissions are forcibly reduced. When the current trust level is determined to be in a stable phase and the trust level is higher than the preset trust level, control permissions are maintained or increased.

11. The control method for a smart home system according to claim 1, characterized in that, After controlling the smart home system according to the current trust level, the control method further includes: Monitor the real-time interactive feedback information of the smart home system; When the real-time interactive feedback information indicates that there is no response or rejection of the pending confirmation task within a predetermined time period, the task execution is determined to have failed, and negative feedback is recorded. The real-time interactive feedback information indicates that when a task pending confirmation is confirmed or cannot be responded to, the task is determined to have been successfully executed, and positive feedback is recorded.

12. A control device for a smart home system, characterized in that, include: The acquisition unit is used to acquire multi-dimensional feature information of the smart home system, wherein the multi-dimensional feature information includes: environmental context data, device operating status data, user historical behavior data, and user feature data; The first determining unit is used to determine the degree of acceptance of the system operation behavior of the smart home system based on multi-dimensional feature information; An adjustment unit is used to adjust the current trust level of the smart home system according to the acceptance level, so as to obtain the updated trust level of the smart home system. The second determining unit is used to determine the current trust level of the smart home system based on the updated trust level. A control unit for controlling the smart home system based on the current trust level.

13. A smart home system, characterized in that, The smart home system uses the control method of the smart home system described in any one of claims 1 to 11.

Images