Quantitative evaluation method for intelligent level of multi-mode intelligent household electrical appliance

Abstract

The embodiment of the invention provides a quantitative evaluation method for the intelligent level of a multi-mode intelligent household electrical appliance, and the method comprises the steps: constructing a household electrical appliance intelligent performance evaluation model, simulating a first environment change process, and starting a household electrical appliance to recognize the first environment change process, so as to enable the household electrical appliance to obtain environment data; collecting a first data processing cycle process in the household appliance, evaluating the first data processing cycle process, and generating a first evaluation report; enabling the household appliance to execute an environment regulation and control action, identifying a second environment change process, evaluating the environment regulation and control capability of the household appliance according to the second environment change process, and generating a second evaluation report; according to the method provided by the embodiment of the invention, a unified and quantitative method can be established to carry out benchmark testing on the intelligence of the household appliances, and fair comparison between different household appliance types and models can be met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of household appliance performance evaluation, and particularly to a quantitative evaluation method for the intelligent level of multi-modal smart household appliances. BACKGROUND

[0002] The popularity of smart home devices has completely changed family life, embedding advanced sensing, data processing, and connectivity features into everyday household appliances. Today, devices such as thermostats, refrigerators, washing machines, and lighting systems can adapt to user preferences, optimize energy consumption, and seamlessly interact within an interconnected ecosystem. Despite these advances, there is still a significant gap in standardized and objective methods for evaluating and comparing the intelligence level of these different household appliances, which currently rely on subjective user experiences. Current evaluation methods are often qualitative, relying on subjective user experiences or manufacturer-provided self-declarations, and are unable to capture the different information processing capabilities of modern devices. The lack of a unified evaluation framework makes it difficult for consumers to make informed choices and hinders manufacturers from systematically improving the intelligence of household appliances. SUMMARY

[0003] The following is a summary of the subject matter of the detailed description herein. This summary is not intended to limit the scope of the claims.

[0004] The embodiments of the present application provide a quantitative evaluation method for the intelligent level of multi-modal smart household appliances, which can establish a unified and quantitative method to benchmark the intelligence of household appliances and meet fair comparisons between different types and models of household appliances.

[0005] To achieve the above-mentioned purpose, the first aspect of the embodiments of the present application proposes a quantitative evaluation method for the intelligent level of multi-modal smart household appliances, comprising: constructing a household appliance intelligent performance evaluation model, simulating a first environmental change process, starting a household appliance device to identify the first environmental change process to make the household appliance device acquire environmental data; collecting a first data processing cycle process in the household appliance device, evaluating the first data processing cycle process, and generating a first evaluation report; making the household appliance device perform an environmental regulation action, identifying a second environmental change process, evaluating the environmental regulation capability of the household appliance device according to the second environmental change process, and generating a second evaluation report.

[0006] In some embodiments, the first data processing cycle in the household appliance is collected, the first data processing cycle is evaluated, and a first evaluation report is generated, including: reading the acquisition data type and the corresponding environmental data of the household appliance in the first data processing cycle, constructing a data type matrix according to the acquisition data type, evaluating the ability of the household appliance to identify the environmental state according to the data type matrix, and solving the environmental unknown state before the household appliance perceives the environmental data to obtain environmental entropy; constructing an environmental information matrix according to the environmental data, re-evaluating the ability of the household appliance to perceive the environmental state according to the environmental information matrix to obtain a first conditional entropy; based on the environmental entropy and the first conditional entropy, judging the perception ability of the household appliance to the environmental unknown state using the environmental information matrix, determining the first environmental perception ability of the household appliance, and generating the first evaluation report according to the first environmental perception ability.

[0007] In some embodiments, the first data processing cycle in the household appliance is collected, the first data processing cycle is evaluated, and a first evaluation report is generated, further including: reading the encoding structure of the household appliance in the first data processing cycle, and the original features obtained by the sensor perceiving the environmental state, determining the encoding distortion degree of the household appliance to the environmental state information based on the difference between the original features and the encoded data under the encoding structure; evaluating the authenticity preservation of the encoding structure of the household appliance in the first data processing cycle based on the original features and the encoding structure, and determining the encoding entropy difference; based on the encoding distortion degree and the encoding entropy difference, analyzing the utilization efficiency of the household appliance to the environmental state information, and generating the first evaluation report.

[0008] In some embodiments, the household appliance is caused to perform an environmental regulation action, a second environmental change process is identified, the environmental regulation ability of the household appliance is evaluated according to the second environmental change process, and a second evaluation report is generated, including: reading the action instruction set inferred by the household appliance based on internal knowledge after receiving environmental data, judging the manipulation ability of the household appliance to the environment under the influence of the internal knowledge according to the action instruction set, and determining a second conditional entropy; mapping between the environmental data and the action instruction set, causing the household appliance to select and perform an environmental regulation action based on the action instruction set, obtaining an expected environmental state predicted by the household appliance based on the internal knowledge, determining an environmental state difference value based on a set target environmental state and the expected environmental state; evaluating the ability of the internal knowledge and the performance of the household appliance based on the second conditional entropy and the environmental state difference value, and generating the second evaluation report.

[0009] In some embodiments, the making the home appliance device perform the environment regulation action, identifying a second environment change process, evaluating the environment regulation capability of the home appliance device according to the second environment change process, and generating a second evaluation report further include: the home appliance device obtaining initial environment information and regulation environment information after the completion of the environment regulation action, and making the home appliance device update internal knowledge of the home appliance device based on the initial environment information and the regulation environment information; evaluating the update degree of the internal knowledge, determining knowledge gain of the internal knowledge, and generating a second evaluation report.

[0010] In some embodiments, the evaluating the update degree of the internal knowledge, determining the knowledge gain of the internal knowledge, and generating a second evaluation report include: making the internal knowledge gradually updated over time, sequentially determining discrete parameter change conditions of the internal knowledge before and after each update node, judging whether the internal knowledge converges based on the discrete parameter change conditions, and determining learning optimization efficiency of the internal knowledge; determining knowledge gain between the internal knowledge based on the internal knowledge before and after adjacent update nodes; and generating a second evaluation report based on the learning optimization efficiency and the knowledge gain.

[0011] In some embodiments, the method further includes: simulating a third environment change process, and controlling a home appliance group to regulate the third environment change process, wherein the home appliance group includes a plurality of home appliance devices that are communicatively connected to each other, and the home appliance group is arranged in a same test space; collecting a second data processing cycle process inside the home appliance group, and detecting interconnection and intercommunication conditions inside the home appliance group; and generating a third evaluation report based on the interconnection and intercommunication conditions.

[0012] In some embodiments, the generating a third evaluation report based on the interconnection and intercommunication conditions includes: collecting data interaction efficiency of the home appliance group in the process of interconnection and intercommunication of the home appliance group; collecting first environment information utilization efficiency of the home appliance device in the first environment change process; making the home appliance devices transmit environment information in the third environment change process, and collecting second environment information utilization efficiency of the home appliance device; determining first group effect based on the first environment information utilization efficiency and the second environment information utilization efficiency; detecting first regulation effect of the home appliance device on the environment after the second environment change process; detecting second regulation effect of the home appliance group on the environment after the third environment change process; and determining second group effect based on the first regulation effect and the second regulation effect; and generating a third evaluation report based on the data interaction efficiency, the first group effect, and the second group effect.

[0013] To achieve the above object, the second aspect of the present application provides an electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the quantitative evaluation method for the intelligent level of the multi-modal smart household appliance when executing the computer program.

[0014] To achieve the above object, the third aspect of the present application provides a storage medium, which stores a computer program, and the computer program implements the quantitative evaluation method for the intelligent level of the multi-modal smart household appliance when executed by a processor.

[0015] The embodiments of the present application at least have the following beneficial effects: the first evaluation report generated based on the first data processing cycle of the household appliance provides a quantitative standard for the intelligent performance of the household appliance, and meets the deep needs of the user for the self-management function of the device; in addition to the above-mentioned data processing cycle in the household appliance, the dynamic adaptation capability of the device in actual application is verified by controlling the household appliance to perform the environmental regulation action and analyzing the second environmental change process, so as to ensure that the device can continuously optimize the regulation strategy according to the feedback, and the second evaluation report can help to locate the problem and iteratively improve; by analyzing the correlation between the regulation result and the user demand, the household appliance can gradually realize the prediction and satisfaction of the unexplicit demand, and promote the evolution of the intelligent system to a higher level of active service.

[0016] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be achieved and obtained by the structure particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings are included to provide a further understanding of the technical scheme of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the technical scheme of the present application, and do not constitute a limitation on the technical scheme of the present application.

[0018] Figure 1 An optional flowchart of the quantitative evaluation method for the intelligent level of the multi-modal smart household appliance provided by the embodiments of the present application is shown in the following table: Figure 2 An optional flowchart of the evaluation environment sensing process provided by the embodiments of the present application is shown in the following table: Figure 3 An optional flowchart of the evaluation internal coding representation process provided by the embodiments of the present application is shown in the following table: Figure 4 An optional flowchart of the evaluation reasoning and decision-making process provided by the embodiments of the present application is shown in the following table: Figure 5An optional flowchart for evaluating the adaptive updating learning process provided by the embodiments of the present application is shown in FIG. 1. Figure 6 An optional flowchart for evaluating the interconnection process provided by the embodiments of the present application is shown in FIG. 2. Figure 7 An optional structural diagram of the intelligent performance evaluation device for household appliances provided by the embodiments of the present application is shown in FIG. 3. Figure 8 An optional hardware structural diagram of the electronic device provided by the embodiments of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0019] In order to make the objects, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0020] In the description of the present application, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, more than, etc. are understood as not including the number, above, below, etc. are understood as including the number.

[0021] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims or above are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0022] In the related art, the current evaluation method is usually qualitative, relying on subjective user experience or manufacturer-provided self-declaration, and cannot capture the different information processing capabilities of modern devices. The lack of a unified evaluation framework makes it difficult for consumers to make wise choices and hinders manufacturers from systematically improving the intelligence of household appliances.

[0023] Based on this, the embodiments of the present application provide a quantitative evaluation method for the intelligence level of multi-modal intelligent household appliances, which can establish a unified and quantitative method to benchmark test the intelligence of household appliances and meet the fair comparison between different types and models of household appliances.

[0024] The quantitative evaluation method for the intelligence level of multi-modal intelligent household appliances provided by the embodiments of the present application is described in detail as follows. First, the quantitative evaluation method for the intelligence level of multi-modal intelligent household appliances in the embodiments of the present application is described.

[0025] The application is operable in a variety of general purpose or special purpose computing system environments or configurations. Examples of computing systems, environments, and / or configurations that can be suitable for use with the application include personal computers, server computers, handheld or laptop devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in local and remote computer storage media including memory storage devices.

[0026] The embodiments of the application are further described below with reference to the accompanying drawings.

[0027] As Figure 1 shown, Figure 1 An optional flow diagram of a quantitative evaluation method for the intelligent level of a multi-modal smart home appliance provided by the embodiments of the application, which can be executed by a server, or can be executed by a terminal, or can be executed by a server in cooperation with a terminal, includes but is not limited to the following steps S110 to S130: Step S110, constructing a home appliance intelligent performance evaluation model, simulating a first environmental change process, starting the home appliance device to identify the first environmental change process to make the home appliance device acquire environmental data; Step S120, collecting a first data processing cycle process in the home appliance device, evaluating the first data processing cycle process, and generating a first evaluation report; Step S130, making the home appliance device execute an environmental regulation action, identifying a second environmental change process, evaluating the environmental regulation capability of the home appliance device according to the second environmental change process, and generating a second evaluation report.

[0028] Information theory provides a solid theoretical foundation for addressing this challenge by offering mathematical tools for quantifying uncertainty, information flow, and adaptability. The embodiments of the present application consider the functions of intelligent systems in home appliances (data acquisition, representation, inference, learning, and decision-making) as a unified process of reducing uncertainty and optimizing outcomes. This defines intelligence as a form of advanced information processing. To quantify the "intelligence" of home appliances as an index that can be calculated using information theory, the embodiments of the present application propose an information theory framework that decomposes the intelligence of home appliances into quantifiable evaluation dimensions, then uses basic methods of information theory to numerically evaluate each dimension, and finally establishes a unified, quantitative method for benchmarking the intelligence of home appliances and enabling fair comparisons between different types and models of home appliances.

[0029] The intelligence performance of home appliances can be broken down into the ability to acquire, convert, and utilize information in order to act autonomously, efficiently, and adaptively. The core of this definition is that home appliances can reduce uncertainty about their environment or operating environment and make decisions that align with user preferences, environmental constraints, and performance goals. For users, this manifests in three levels of needs: first, through intelligent technology that responds to environmental and user data, the device can autonomously manage its functions, thereby minimizing the need for human intervention; then, personalized services are provided according to individual user differences: customizing device functions to adapt to each user's unique preferences and circumstances, ensuring a customized and adaptive user experience; finally, using big data and advanced analytics to predict and meet user needs that users may not consciously recognize or express.

[0030] Based on the quantitative evaluation method for the intelligent level of multi-modal intelligent household appliances proposed in the embodiments of the present application, the embodiments of the present application construct a unified evaluation model to provide a benchmark environment for subsequent testing, guarantee the consistency and comparability of data collection, provide a basis for fair evaluation of cross-model and cross-brand devices, simulate the first environmental change process and start the device recognition function, can comprehensively test the response ability of household appliances under different environmental conditions, accurately identify the ability of the household appliance algorithm in data representation, reasoning and learning through the evaluation of the data processing cycle, integrate the data processing of the household appliance into quantifiable and repeatable indicators, generate a first evaluation report based on the first data processing cycle process of the household appliance, provide a quantitative standard for the intelligent performance of the household appliance, and at the same time meet the deep needs of users for the self-management function of the device; in addition to the above-mentioned data processing process inside the household appliance, by controlling the household appliance to perform environmental regulation actions and analyzing the second environmental change process, the dynamic adaptation ability of the device in actual application is verified to ensure that it can continuously optimize the regulation strategy according to the feedback, and combined with the second evaluation report, it can help to locate problems and iteratively improve, through analyzing the correlation between the regulation result and the user demand, the household appliance can gradually realize the prediction and satisfaction of unexplicit demands, and promote the intelligent system to evolve to a higher level of “active service”. The method proposed in the embodiments of the present application constructs a closed-loop evaluation system, deeply integrates the information theory framework and user demand, not only ensures the quantifiability of the intelligent performance of the household appliance in the data collection, processing and regulation links, but also realizes the fair comparison of cross-device types.

[0031] There are three computing tools in information theory. In information theory, entropy, mutual information and KL divergence (Kullback-Leibler divergence) are used to measure the uncertainty of data, the dependence between variables and the difference between probability distributions respectively: entropy quantifies the degree of disorder of data distribution, guides feature selection and controls the diversity of generative models; mutual information evaluates the correlation strength between two variables, which is used for feature screening and multi-modal alignment; and KL divergence compares the deviation between two distributions. From data preprocessing to model optimization, entropy, mutual information and KL divergence help the system to cope with uncertainty, capture key associations and correct deviations, and ensure the robustness of the algorithm in complex tasks.

[0032] From the perspective of information theory, a more intelligent household appliance should include the following intelligent directions: accurately acquiring relevant environmental data and user signals to reduce uncertainty; effectively encoding, storing and retrieving important information, saving key insights for future use; drawing meaningful inferences, making predictions and selecting actions that optimize results, using internal models to guide decision-making even in uncertain situations; continuously learning and adapting, improving its internal performance and strategies as conditions change or new information emerges; integrating and utilizing external resources, such as cloud-based knowledge bases and communication with other devices, to enhance its decision-making capabilities.

[0033] To grasp the multi-faceted nature of the intelligentization of home appliances, and to correspond to the above-mentioned intelligentization direction based on information theory, the embodiments of the present application define multiple core dimensions to constitute the complete information life cycle of the intelligentization of home appliances, from raw data collection to action selection and continuous adaptation, to quantify the reduction of uncertainty and the efficiency of using available information for home appliances.

[0034] First, the embodiments of the present application propose to evaluate the information acquisition and physical perception dimension, which focuses on the device's ability to perceive the environment. High intelligence requires accurate and reliable sensors to capture the world state and user input with minimal uncertainty. Information theory indicators (e.g., mutual information between sensor output and ground truth) indicate how effectively the device's perception ability reduces environmental ambiguity. As shown in Figure 2 Step S120 in Figure 1 includes but is not limited to the following steps S210 to S230: Step S210, read the data type acquired by the home appliance during the first data processing cycle and its corresponding environmental data, construct a data type matrix according to the data type, evaluate the ability of the home appliance to identify the environmental state according to the data type matrix, and solve the unknown state of the environment before the home appliance perceives the environmental data to obtain the environmental entropy; Step S220, construct an environmental information matrix according to the environmental data, and evaluate the ability of the home appliance to perceive the environmental state again according to the environmental information matrix to obtain the first conditional entropy; Step S230, based on the environmental entropy and the first conditional entropy, judge the perception ability of the home appliance to the unknown state of the environment based on the environmental information matrix, determine the first environmental perception ability of the home appliance, and generate a first evaluation report according to the first environmental perception ability.

[0035] In the field of smart home appliances, information acquisition and physical sensing refer to the ability of home appliances to capture and process environmental data in real time. These data usually include various physical parameters such as temperature, humidity, pressure, light intensity, etc., which can be sensed using various sensors. However, due to differences in design, cost and expected functionality of home appliances, they are usually equipped with different types of sensors, each with different sensitivity, accuracy and coverage.

[0036] The core difficulty of the method proposed in this dimension lies in quantifying to what extent these sensors reduce the uncertainty of the environment and capture how much relevant environmental information, especially when sensors differ in sensor type, data diversity and fusion capability. This not only concerns accuracy, but also concerns the diversity of sensors and how this diversity is well integrated and contributes to a comprehensive understanding of the environment.

[0037] The method proposed in this dimension conducts in-depth analysis on the types of data collected by home appliances and the response environmental data, evaluates the diversity of sensors, and the types of sensors in home appliances can include temperature, humidity, pressure, light, motion, and sound sensors, etc. The combination of multi-modal data of various different and cross-domain sensors can help home appliances to have a unified understanding of the environmental state. In addition, home appliances can also be connected with external devices, and by obtaining cloud data, the perception ability of home appliances can be enhanced, so as to have a deeper understanding of the environmental state and user behavior.

[0038] Firstly, the embodiment of the present application defines a matrix E to express the environmental information collected by home appliances, and each element in the data type matrix E represents a different environmental parameter and condition: .

[0039] represents the measurable environmental data, where i is an integer, and the value of i is in the range [1, n], and n represents the number of perceived environmental states.

[0040] The environmental state and sensor data are modeled in the form of a matrix, and the complex multi-dimensional environmental information and sensor output are organized in a structured form for further analysis and processing. Taking an intelligent air conditioning system as an example, it relies on multiple sensors to monitor different conditions of the environment to make corresponding adjustments. The sensors of the air conditioner can include: temperature sensor: to monitor the temperature of the room, humidity sensor: to monitor the humidity of the room, light sensor: to monitor the indoor light intensity, motion sensor: to detect whether there is a person in the room. These sensors collect data in real time, and the state of the environment at each moment can be regarded as a vector. These data can be organized and represented in the form of a matrix for further analysis.

[0041] Suppose the environmental parameters that the home appliance is concerned about are temperature, humidity, light, and motion. We will organize these environmental parameters into a matrix according to time and sensor type. Exemplarily, the home appliance collects environmental data at 2 time points, and each time point has these four parameters. The matrix can be represented as follows: .

[0042] represents the temperature at the ith moment, where i is an integer, and the value of i is in the range [1, 2], represents the humidity at the ith moment, where i is an integer, and the value of i is in the range [1, 2], represents the light intensity at the ith moment, where i is an integer, and the value of i is in the range [1, 2], represents the motion detection value at the i-th time point, where i is an integer and i takes values in the range [1, 2], the motion detection value is used to indicate the presence of a person, for example, when the motion detection value is 0, it represents that there is no person present, when the motion detection value is 1, it represents that there is a person present.

[0043] In this example, each row of the matrix represents the state of the environment at a specific time point, and each column represents the output of a different sensor at that time point.

[0044] At the same time, the household appliance obtains environmental data through sensors , where i is an integer and i takes values in the range [1, m], the environmental information matrix S is constructed by the readings of m sensors: .

[0045] By modeling the environmental state that the household appliance can obtain based on sensors, after the household appliance obtains environmental data, the environmental information matrix S is compared with the actual macro-environmental conditions to determine the amount of reduction in the uncertainty of the household appliance itself for the first environmental change process, thereby quantifying the ability of the household appliance to capture the environmental state.

[0046] Suppose there are multiple different sensors in the household appliance, for example, temperature sensors , humidity sensors , light sensors and motion sensors . Each sensor has different outputs at different time points, assuming the number of time points is two, organize these data by sensor and time into a matrix: .

[0047] wherein represents the output of the i-th sensor at the j-th time point, where i and j are integers, i takes values in the range [1, 4], and j takes values in the range [1, 2].

[0048] In practical applications, intelligent household appliances can process and analyze data collected from different sensors through such matrix modeling methods. For example, in an air conditioning system, the matrix model can help analyze the following contents: By integrating data from different sensors (temperature, humidity, light, etc.), the air conditioning system can comprehensively judge the comfort level of the room and make decisions accordingly, such as adjusting the temperature or turning on / off the air conditioner; through the analysis of matrix data, the air conditioning system can identify different environmental patterns, such as changes in environmental status during the day and night, or when there is someone in the room or not; based on these patterns, the air conditioning system can optimize its working efficiency, such as energy-saving mode; based on historical data matrix, the air conditioning system can predict future environmental changes and make adjustments in advance. For example, if the system detects that temperature and humidity have a certain fluctuation trend in the past few hours, it can make pre-adjustment in advance to ensure that the room reaches the optimal comfort level when the user enters.

[0049] The present application embodiment defines environmental entropy to represent the uncertainty of the environmental state, i.e. the amount of information needed to describe the environmental state, the following is the formula representation of environmental entropy: .

[0050] In the formula, represents the probability distribution of the i-th environmental information , where i is an integer, the entropy of the environmental parameter E, i.e. the "uncertainty" or "amount of information" of the system. The environmental parameter refers to a specific environmental variable perceived by the home appliance through sensors. These environmental parameters may include temperature, humidity, light intensity, motion detection, etc., which are real-time values collected by sensors. These environmental parameters represent the actual environmental conditions perceived by the home appliance. For example, the probability distribution of temperature information can represent the likelihood of different temperature values appearing in the room, such as being closer to 25 degrees Celsius during the day and closer to 20 degrees Celsius at night. For humidity information, the probability distribution may reflect the probability of different humidity values appearing in the room. For light intensity information, the probability distribution may represent the probability of light intensity changes in the room at different times of the day. In practical applications, these probability distributions can help the home appliance understand and adapt to its environment. For example, if the home appliance knows that a certain temperature range (such as 20 to 25 degrees Celsius) has a high probability of occurrence, it can adjust the working mode of the air conditioner or heating device more effectively based on this information.

[0051] In this case, the environmental entropy represents the "uncertainty" of the home appliance about the state of the environment before it perceives the data. If the home appliance can accurately predict the environmental parameters (i.e., the probability distribution is more concentrated and less variable), the entropy value is lower, indicating that the home appliance has a more certain understanding of the environment and can more effectively respond. In summary, the probability distribution of environmental parameters quantifies the uncertainty of the smart home appliance when facing environmental changes, which directly affects its ability to respond and adapt to environmental changes.

[0052] After collecting the environmental information, a first conditional entropy is defined to describe the uncertainty of the home appliance about the state of the environment after observing the sensor output, and the formula for the first conditional entropy is: .

[0053] wherein, represents the probability of observing the sensor output, represents the conditional probability of the environmental parameter given the sensor output . In this formula, is the output result of the home appliance sensor, which represents a specific environmental signal measured by the sensor, such as temperature, humidity, light, etc. represents the probability of the sensor outputting a specific value . For example, if the output value of the temperature sensor is = 22 degrees Celsius, it means that the probability of the sensor observing this temperature value within a certain time period.

[0054] In real-world applications, the probability of the output reflects the degree of feedback of the home appliance on the state of the environment and the reliability of the environmental data. If the output value of a sensor is common (e.g., the temperature sensor often outputs a temperature close to 22 degrees Celsius in a certain area), the will be higher, indicating that this output value is more common and stable.

[0055] In a home appliance, sensors will produce output values based on different environmental conditions. For example, a temperature sensor may output a variety of temperature values, and the frequency of these output values will be reflected in this parameter. If the sensor outputs between 22 degrees Celsius and 24 degrees Celsius most of the time, the probability of these output values will be higher.

[0056] The output probability not only reflects the frequency of the environmental state observed by the home appliance, but also may reveal the stability or variability of the environment. For example, if a temperature sensor frequently outputs temperatures between 20 degrees Celsius and 25 degrees Celsius in some cases, but rarely outputs these values in other cases, it can be inferred that the temperature of the environment where the home appliance is located has less fluctuation.

[0057] The probability of such an output can help the home appliance to judge the stability of the current environment and the validity of the environmental information. In the application of smart home appliances, if the output value of a certain sensor is relatively rare, it may indicate that the sensor has failed or that the environment has undergone extreme changes.

[0058] In the framework of information theory, this parameter not only helps to quantify the frequency and reliability of sensor measurements, but also relates to the decision-making process of the device in a dynamic environment. Smart home appliances can adjust their behavior according to the probability of these outputs, for example, automatically adjusting the operating mode when a certain output value is frequently detected, or issuing a warning or making adaptive adjustments when a rare output value appears.

[0059] In practical applications, by calculating the above entropy value, the smart home appliance can make efficient responses in a variable environment. By calculating the first conditional entropy, it can quantify how much uncertainty about the environment remains after the home appliance sets the perceived environmental state.

[0060] Mutual information (Mutual Information) can be used to measure the information shared by two random variables. In the case of knowing the uncertainty reduction of random variable X, the uncertainty reduction of random variable Y, or knowing the uncertainty reduction of random variable Y, the uncertainty reduction of random variable X, the present embodiment defines the first environmental perception ability of the home appliance based on the environmental entropy and the first conditional entropy calculated above. The first environmental perception ability can be directly represented using the first mutual information based on the environmental state, and its formula is: .

[0061] I( ) represents the function expression of mutual information. When the first mutual information is higher, it indicates that the environmental information obtained by the home appliance is more valuable and can effectively reduce uncertainty.

[0062] In a specific implementation, in order to standardize the evaluation of different home appliances with different sensor configurations, the present embodiment can also normalize the above first mutual information, and its processing formula is: .

[0063] After normalization, a value close to 1 indicates that the sensor is very effective in capturing environmental information, while a value of 0 indicates that the sensor has not captured meaningful environmental data.

[0064] Furthermore, after the appliance acquires and digitizes the environmental information, it must internally encode and store the data in a compact yet informative manner. This process can ensure that key environmental signals are preserved while redundancies and noise are eliminated. This stage involves balancing three core objectives including: preserving key environmental signals in order to enable downstream reasoning and decision making with minimal uncertainty; compressing the raw data into an internal representation that requires fewer computational and memory resources while maintaining the integrity of the appliance’s understanding of its environment; and accurately modeling the probabilistic structure of the environment to support reliable predictions, pattern recognition, and adaptive updates in response to changing conditions.

[0065] As shown in FIG. 3, this core dimension quantifies the encoding effectiveness and utilization efficiency of the appliance with respect to the environmental data, Figure 3 Figure 1 The step S120 in the method 100 further comprises steps S310-S330: In step S310, the encoding structure of the appliance in the first data processing cycle and the original features obtained by the sensor sensing the environmental state are read, and the encoding distortion degree of the appliance with respect to the environmental state information is determined based on the difference between the original features and the encoded data under the encoding structure; In step S320, the authenticity preservation of the encoding structure of the appliance in the first data processing cycle is evaluated based on the original features and the encoding structure, and the encoding entropy difference is determined. In step S330, the utilization efficiency of the appliance with respect to the environmental state information is analyzed based on the encoding distortion degree and the encoding entropy difference, and a first evaluation report is generated.

[0066] Considering the environmental state E described by a random vector and the reference distribution After the initial sensing and preprocessing, the appliance will construct an encoding structure I to encode the key environmental features, where the encoding process is defined as I processing the data S obtained from the sensor through a conversion function g(), which can be represented as a compression algorithm, a statistical model or an embedded machine learning, and the conversion function needs to resolve the environmental information S while minimizing redundancy.

[0067] In the embodiments of the present application, first, the reference distribution of the original features is obtained by estimating the true measurement of the environment The reference distribution reflects the true complexity of the environmental state space, and in the process of collecting environmental information, due to the limitations of machine coding, the process of encoding environmental information may lose the authenticity of the original signal, so the internal model distribution is obtained from the encoding structure of the appliance.

[0068] ​Similar to the above by sensing the dimension of the environment state, data discretization and probability estimation are necessary. Continuous variables are divided into discrete states, and a large sample set is used to construct stable probability estimates. Noise modeling and smoothing methods are used to ensure robust distribution approximation.

[0069] In fact, to obtain accurate reference distribution, the real expression of the machine inside A large amount of real data is required. Embodiments of the present application can collect usage logs for a representative period of time and apply robust statistical methods (such as kernel density estimation or histogram binning with smoothing) to estimate these distributions. Sensitivity analysis should be performed to assess the impact of estimation error.

[0070] By comparing the model distribution results represented by the encoding structure The reference distribution corresponding to the real environment The comparison can obtain the encoding distortion of the environment information inside the household appliance, where the encoding distortion is quantified using the KL divergence: .

[0071] The encoding distortion between the model distribution results represented by the encoding structure and the reference distribution corresponding to the real environment can measure the difference between the model distribution results and the reference distribution, so as to measure the amount of information lost when the model distribution results represented by the encoding structure approximate the reference distribution corresponding to the real environment , and a lower encoding distortion indicates that the encoding of the environment information inside the household appliance can approximate the real environment state, thereby reducing the calculation error of the model.

[0072] In addition, embodiments of the present application also propose to evaluate the authenticity of the environment information using the concept of mutual information based on encoding. First, considering the original feature R of the real environment state and its encoded data I, the entropy value of the original feature R is solved and the conditional entropy of the encoded data based on the original feature , the difference between the entropy values after encoding is calculated, and the encoding entropy difference represented by mutual information is obtained: .

[0073] In a specific embodiment, in order to normalize the expression of numerical values, from the above, represents the entropy of the original feature, represents the entropy of the internal encoding structure, and the difference - represents the amount of redundancy or noise in the environment state removed by the encoded feature, and here, the encoding entropy difference is normalized: The preservation of the original state information can be expressed, and when it is close to 1, it means that most of the environment-related information is preserved.

[0074] In order to generate a singleization evaluation value based on the encoding features, the embodiments of the present application can also perform weighted mixing on the above data: .

[0075] Among them, is a standardized weighting factor representing the relative importance between the fidelity of the encoding feature and its encoding efficiency, .

[0076] is a standardized constant representing the worst-case divergence scenario, in the actual implementation process, should be defined according to the worst case observed in the preliminary experiment, and the weighted mixing will be scaled to the range of [0, 1], and close to 1 indicates a high-efficiency and true internal encoding feature representation. By selecting an appropriate standardization and weighting scheme, this single score can be directly plotted on the radar chart axis to represent the performance of the device in terms of encoding and representation.

[0077] A high score indicates that the home appliance device successfully converts raw, possibly noisy sensor readings into stable, low-entropy internal encoding representations that closely match the real environment and preserve essential information. Because its internal state is accurate, compact, and easy to use, this enables the home appliance device to improve reasoning and decision-making.

[0078] On the contrary, a low score may indicate that the device's internal model does not align with reality, which can lead to prediction errors or suboptimal actions. It can also mean that excessive compression discards too much information, weakening the device's ability to reason about future states or adapt to new conditions.

[0079] It is worth noting that in practical applications, changes in environmental conditions and usage patterns will affect these scores. Therefore, it is recommended to recalibrate the indicators regularly and verify them against independent performance benchmarks to maintain accuracy.

[0080] Since these indicators rely on probability distributions and established information theory metrics, the evaluation is objective and repeatable. Different devices with different encoding strategies and memory architectures can be compared using the same indicators. This allows evaluators to identify bottlenecks, improve compression algorithms, or improve model training procedures.

[0081] After acquiring environmental data and converting it into an effective internal coded feature representation, the appliance must accurately infer hidden or future states and choose appropriate actions in the face of uncertainty to achieve its goals or tasks. Inference requires reasoning about hidden or future states of the environment (e.g., predicting how the room temperature might change in the next hour), while decision making involves choosing one action from possible alternatives in the face of uncertainty (e.g., adjusting cooling power or scheduling a cleaning cycle). This core dimension will detail the theoretical foundations of the above processes and introduce information theoretic measures that can provide normalized scores for the "inference and decision making under uncertainty" dimension.

[0082] Specifically as Figure 4 shown, Figure 1 Steps S130 in the above table, including but not limited to the following steps S410 to S430: Step S410, reading the action instruction set inferred by the appliance based on internal knowledge after receiving the environmental data, judging the manipulation ability of the appliance to the environment under the influence of internal knowledge according to the action instruction set, determining the second conditional entropy; Step S420, mapping between environmental data and action instruction set, making the appliance select and execute environmental regulation action based on the action instruction set, obtaining the expected environmental state predicted by the appliance based on internal knowledge, determining the environmental state difference based on the set target environmental state and the expected environmental state; Step S430, based on the second conditional entropy and the environmental state difference, evaluating the ability of internal knowledge and the performance of the appliance, and generating a second evaluation report.

[0083] Inference and decision making constitute the cognitive core of appliance intelligence, including predicting future or hidden environmental states and choosing the best action in the face of uncertainty. The appliance can maintain a probability model of potential states (e.g., upcoming temperature patterns, occupant behavior) and aims to select an action A that optimizes some objective (e.g., minimizing energy consumption or maintaining user comfort). Numerically, based on the above idea, let: I is the coded feature mentioned above, representing processed sensor data such as temperature, humidity, illumination, etc.

[0084] Z represents unobserved or future environmental states; represents a set of action instructions that the appliance can take based on the acquired environmental information.

[0085] After the appliance collects the coded feature representation I of the environmental information, information theory indicators are applied to reason about the second environmental change process, producing an environmental change probability distribution The process of deriving the inference output distribution can be derived by the following formula: .

[0086] The second conditional entropy is calculated according to the environment change probability distribution obtained by inference, which is used to measure the uncertainty of the inference of the environment change, and the second conditional entropy is specifically expressed as: .

[0087] Where s, z and i are elements in S, Z and I respectively, and the second conditional entropy with a low value indicates that the household appliance can accurately predict the unobserved environment state through the encoded features.

[0088] Here, the correlation between the internal encoded features I of the real-time environment information and the unobserved environment state Z is quantified again based on the concept of mutual information, and specifically, the formula is: .

[0089] In this formula, represents the entropy of the unobserved environment state Z, and represents the uncertainty of the environment state when there is no any environment information, is the conditional entropy of the environment state Z given the data I, which represents the remaining uncertainty about the environment state Z when the household appliance has already collected data I, and the mutual information represents the uncertainty about the environment state Z reduced by the data I, and the higher the value, the stronger the prediction ability of the data I on the environment state Z and the more information provided.

[0090] In addition, for the set of action instructions inside the household appliance, once the household appliance selects an action instruction , the result distribution becomes , assuming that the action instruction a represents a certain specific cooling strategy, can represent the room temperature and energy usage in the next period of time, and by accumulating these data, the can be estimated.

[0091] Specifically, the instruction distribution after selecting the action instruction represents the probability distribution of the expected result or consequence of the environment or system after the household appliance selects a certain specific action a, which describes which possible results a certain action will bring and the probability of these results occurring; and is the expected future environment state or system state after the action is executed, for example, the target indoor temperature after the air conditioner reduces the temperature.

[0092] For example, assume that an intelligent air conditioner decides whether to turn on the cooling function based on the current temperature in the room (I, which is sensed by a sensor). The air conditioner decides to perform the action of "turning on cooling" or to maintain the temperature according to user demand. Assume that the air conditioner decides to "turn on cooling". The change in indoor temperature is an uncertain process, which depends not only on the air conditioner settings but also on factors such as room insulation performance, external climate, and number of people, The multiple states that the indoor temperature can take after the "turn on cooling" action and their probabilities are described. For example, after the air conditioner turns on cooling, the temperature may drop to 22 degrees Celsius (probability 60%), 20 degrees Celsius (probability 30%), or 18 degrees Celsius (probability 10%). This probability distribution reflects environmental uncertainty.

[0093] In summary, the result distribution refers to the possible results and their probability distribution that an intelligent device (such as an air conditioner, robot, etc.) expects after performing a certain action. It reveals the uncertainty after the device makes a decision, reflecting the uncertainty of the environment or system response. This distribution helps the device make better decisions, as it quantifies the probability of each possible outcome and selects the optimal action in the face of uncertainty.

[0094] In this core dimension, the action driven by the action instruction is mapped to the expected environmental state. Once the device selects action a, it is expected to produce environmental state The effect of selecting action a on the expected environmental state is calculated based on the concept of mutual information: .

[0095] Here, if is large, it means that the implementation of the action instruction set A of the home appliance device significantly reduces the uncertainty of the environmental state and can timely guide the environmental state to the ideal state.

[0096] In most cases, the home appliance device aims to maximize the utility function which represents the desired environmental regulation result, such as a comfortable temperature range, minimum power consumption, energy efficiency, user comfort, or other performance standards, which are defined according to the specific appliance goals. The home appliance device combines the maximum utility function with the above mutual information to form a comprehensive evaluation result for the action instruction set, which can be specifically represented as where E() represents the calculation of the expected value, A0 represents a random or static strategy, and represents the expected environmental state under the random and static strategy.

[0097] To normalize the above evaluation information, integrate the above reasoning and decision-making, and ensure the accuracy of reasoning and the effectiveness of decision-making, the same calculation indicators are also given here: .

[0098] Among them, represents a weighting factor, used to evaluate the accuracy of the internal knowledge of the home appliance device in predicting unknown environment states, used to measure the effectiveness of the selected action instruction in affecting or optimizing future environment states.

[0099] It needs to be additionally explained that the internal knowledge of the home appliance device includes but is not limited to a pre-set linear instruction set, a statistical model, a pre-trained large model, or a hybrid decision-making module that combines multiple decision-making types. The internal knowledge is involved in tasks such as organizing environment information, analyzing environment states, and generating and invoking action instructions.

[0100] A high value of indicates that the device can reliably predict the environment or user state and select an operation that can produce better results. Conversely, a low value of may indicate that the home appliance device cannot accurately predict the future environment state, or that the action instruction set based on the home appliance device cannot limit the optimization of the current environment state.

[0101] By adopting these standardized, probability-based measures, the evaluation results remain objective, repeatable, and comparable across various product categories and operating environments. Suboptimal devices can be identified and improved by improving reasoning algorithms (e.g., Bayesian updates, machine learning models) or adjusting action selection strategies (e.g., reinforcement learning, rule-based optimization).

[0102] Calculating this index requires estimating probability distributions based on actual operational data. However, real-world environments are dynamic, and the probability distributions used here may change over time or with changes in the environment. In addition, the device may continuously learn from observed user interactions and environmental feedback to update its internal knowledge. The embodiments of the present application can use experience sampling techniques, real-world experiments, or validated simulation models to reliably obtain these parameters.

[0103] Intelligent home appliance devices not only have to perceive the environment and make wise decisions, but also have to continuously adjust their internal knowledge to cope with changing conditions or newly emerging data, thereby achieving continuous and continuously improving performance. This adaptive learning capability distinguishes true intelligent systems from static, pre-programmed devices. Whether the device is faced with changing user preferences, seasonal changes in environmental parameters, or new data streams from external sources, continuous learning enables more accurate reasoning, better decision-making, and sustained performance.

[0104] Therefore, the embodiments of the present application also provide how the electrical appliance quantifies its learning and adaptation process through information theory indicators. Similar to the previous dimensions, the ultimate goal is to derive a single numerical value that reflects the electrical appliance's ability to reduce uncertainty by updating its internal knowledge representation through repeated observations and changing conditions.

[0105] As shown in Figure 5 , Figure 1 In step S130, it further includes but is not limited to the following steps S510 to S520: Step S510, the household appliance acquires initial environment information and regulation environment information after completing the environment regulation action, so that the household appliance updates the internal knowledge of the household appliance based on the initial environment information and the regulation environment information; Step S520, the updating degree of the internal knowledge is evaluated, the knowledge gain of the internal knowledge is determined, and a second evaluation report is generated.

[0106] It should be noted that in the present embodiment, the internal knowledge specifically refers to a module integrated in the household appliance for analyzing data and participating in decision-making.

[0107] In the adaptive learning environment, the device maintains a dynamically evolving internal model that represents its current understanding of the temporal environmental state or user preferences. This model is regularly updated to incorporate new information and improve prediction accuracy. After acquiring new data (e.g., updated sensor readings, user feedback), the device refines its model from to . Optionally, the internal knowledge is updated in a Bayesian manner, and the adaptive learning process of the internal knowledge is as follows: .

[0108] The normalized Bayesian update equation explicitly shows that new data updates the internal knowledge of the device from to .

[0109] From the perspective of information theory, adaptive learning can be seen as a process of reducing entropy or minimizing divergence over time. Through the above Bayesian update, the internal knowledge of the household appliance will steadily reduce the gap between its internal model and the true distribution of the environmental state. The embodiments of the present application will design the response efficiency of the household appliance to update through new data, the improvement of the sensing effect on the environment (i.e., the uncertainty eliminated) with each update, and whether the internal knowledge can converge to an accurate description of the environment or user preferences within a limited number of updates.

[0110] To make the computation feasible, the internal knowledge should be explicitly discretized or parameterized (e.g. Gaussian mixture) at each iteration (time step). Defining the discretization or parameterization process explicitly helps to obtain stable and reliable probability estimates needed for accurate entropy and divergence computation, where these continuous distributions are represented as time The distribution

[0111] In addition, adaptive learning typically utilizes multiple sources of data: sensor readings, user interactions, or external knowledge. Each update step aggregates these sources into an updated model distribution. The resulting probability distribution must be normalized and smoothed or regularized to handle zero or low frequency bins.

[0112] And if there is real data or a perfect baseline distribution, the new model can be benchmarked to measure improvement or persistent inaccuracy.

[0113] To quantify the adaptive learning process, the learning optimization efficiency of the internal knowledge needs to be computed, which can be defined by the KL divergence: .

[0114] During the stepwise update process, when the value of the learning optimization efficiency is high, it indicates that the model has been substantially updated, which means that the newly observed data has significantly changed the device's understanding of the environment or user behavior. Conversely, a low divergence indicates that the novelty in recent data is minimal, or that the existing model has already well matched the environment. A low divergence indicates that the model is already accurate, or that the novelty provided by the new data is minimal. Over multiple update cycles, the learning optimization efficiency can reveal the speed and stability of learning.

[0115] In another specific embodiment, again referring to the reference distribution representing the true environment state , after the old model is updated to the new model , whether converges to can be measured to determine whether the update of the internal knowledge converges, and under this theory, the learning optimization efficiency can also be quantified by the formula .

[0116] Then, the embodiments of the present application also quantify the knowledge gain of the internal knowledge in each update process in the stepwise update process, and the old model and the new model when given new data ​The knowledge gain between two time points, which is denoted by the effective reduction of entropy through internal knowledge update, can be represented by the following equation: ; .

[0117] The knowledge gain quantifies the effective utilization of new data, where a larger AH reflects that better learning is achieved through the update, and the uncertainty of the internal knowledge in perceiving the environment is reduced.

[0118] In real-world scenarios, the precise probability distributions required for entropy and divergence computation can not be immediately available. To overcome this problem, the household appliance can leverage empirical sampling methods, statistical inference, or approximation techniques (e.g., particle filters, histogram estimation) to reliably estimate these distributions from limited datasets. This ensures that the metrics proposed by embodiments of the present application are not only theoretical but can also be implemented in practice, even in cases where computational or memory resources are limited.

[0119] Integrated learning score to integrate the numerical values of learning optimization efficiency and knowledge gain, the integrated learning score is defined as: .

[0120] wherein, represents the average value of AH within a preset update time range, represents the residual of learning optimization efficiency within the preset update time range, represents a preset weighting factor.

[0121] Optionally, to provide a standardized evaluation metric, embodiments of the present application also propose the definition of a normalized integrated learning score: .

[0122] In this formula, represents the theoretically maximum possible knowledge gain, represents the maximum learning optimization efficiency, is a preset weighting factor.

[0123] In summary, the integrated learning score, which combines learning optimization efficiency and knowledge gain, reflects how much the internal knowledge of the household appliance has improved over time and how close it is to the real behavior of the environment. A high score clearly indicates effective model adaptation and learning across multiple data updates, indicating that the appliance can reliably improve its internal knowledge over time.

[0124] In modern smart home ecosystems, home appliances rarely operate in isolation. Instead, they rely on network connectivity to exchange data with other devices, access cloud services, or leverage external knowledge bases. Therefore, the embodiments of the present application will also evaluate how effectively a home appliance can utilize interconnectivity and external resources to enhance its internal intelligence. By tapping into additional data and computational power beyond its own internal on-board resources, an appliance can reduce uncertainty, refine models, and make more informed decisions.

[0125] The final result of this core dimension should also be a single numerical value, reflecting the quality and impact of the appliance's external integration. This value will be combined with the other four dimensions in the radar chart to form a comprehensive multi-axis intelligence assessment.

[0126] As shown in Figure 6 , in some embodiments of the present application, the evaluation method proposed by the present application further includes the following steps S610 to S630: Step S610, simulate a third environmental change process, control the home appliance group to adjust the third environmental change process, wherein the home appliance group includes a plurality of home appliance devices in communication connection, and the home appliance group is arranged in the same test space; Step S620, collect a second data processing cycle process inside the home appliance group, and detect the interconnectivity inside the home appliance group; Step S630, generate a third evaluation report based on the interconnectivity.

[0127] It should be noted that the external entities that perform interconnectivity in the home appliance group include but are not limited to: cloud platform: offloading data storage or utilizing cloud-based AI / ML services; other smart devices: point-to-point or hub-mediated exchange with thermostats, cameras, or voice assistants; user devices: mobile phones, tablets, or wearable devices that provide user feedback or control signals; Internet of Things gateways: routers or dedicated smart home hubs that provide advanced coordination functions.

[0128] External resource utilization focuses on how these connections improve the performance of the device. For example, an appliance can retrieve weather forecasts from the cloud, or utilize centralized AI models trained on aggregated user data. The more effectively a device integrates this external information, the less uncertainty it can reduce, the more it can adjust its decisions, and the more it can enhance its learning process.

[0129] To quantify the degree and quality of external utilization, this core dimension also needs to capture the relevant probability distribution that describes how external data changes the appliance's internal encoding features I or expected outcome distribution .

[0130] Specifically, first construct the probability distribution of external data . Then, conditional probability distributions are constructed respectively. and It is used to assess how the coding characteristics and expected outcome distribution within home appliances change after receiving external data.

[0131] During the interconnection and interoperability process of home appliance groups, the data interaction efficiency within the home appliance group is evaluated. For a home appliance in the group that intends to perform calculations, the data throughput of that home appliance is assessed. Quantization, data throughput The data interaction efficiency is calculated by dividing the total amount of data transmitted and processed by the total time spent, and then obtaining the channel capacity C for communication between the home appliance and the outside world. .

[0132] Using mutual information theory again, we first calculate the entropy of the first environment information utilization efficiency under the influence of only the coding features within a single household appliance during the first environmental change process. In the process of change in the third environment of interconnection, the entropy of the uncertainty represented by the information utilization efficiency of the second environment through the influence of home appliance groups on the internal representation of the device. This is expressed as follows: The first group effect is determined by the efficiency of utilizing first and second environmental information. .

[0133] In addition, to assess how external inputs improve the accuracy of predicting future environmental conditions, the initial environmental regulation effect of a single household appliance was obtained after the second environmental change process. By gradually adding external devices with communication connections to home appliances, a third environmental change process is carried out sequentially to obtain the second adjustment effect of the environment. Then, the theory of mutual information is used to judge the second group effect of the interconnection process on the environmental optimization effect of home appliances: .

[0134] To assess the average impact of adding external devices on home appliances, the following definition is provided. The mean of the second group effect during the gradual addition of external devices. This is the second group effect after adding all theoretically possible external devices.

[0135] In order to standardize the evaluation scores for interoperability, this application defines the following in its embodiments: .

[0136] Here, All are weighting factors. .

[0137] high value Indicates that the device effectively uses external data and communication to enhance its intelligence. Conversely, when When the score is low, it indicates that the connection is limited or ineffective, and cannot take advantage of the potential of resource sharing and cloud-based analysis.

[0138] Based on the above five core dimensions, the embodiments of the present application provide a first evaluation report containing , a second evaluation report containing , and a third evaluation report containing , wherein information collection and physical sensing ( ) evaluates how the household appliance effectively reduces environmental uncertainty through accurate and reliable sensing, information encoding, storage and internal representation ( ) evaluates the efficiency and fidelity of the household appliance in encoding and retaining basic information, reasoning and decision-making under uncertainty ( ) measures the ability of the household appliance to predict future states and make optimal decisions based on uncertain information, adaptive information updating and learning ( ) quantifies the ability of the household appliance to continuously improve its internal model based on new data and changing conditions, interconnection and utilization of external resources ( ) measures how the household appliance effectively utilizes external data sources and computing resources to enhance its intelligence.

[0139] A high score in any one dimension does not necessarily guarantee superior overall intelligence. For example, although mutual information measures the ability of the appliance to capture relevant environmental signals, it may not cover the ability of the appliance to make timely or optimal decisions. Therefore, by combining the comprehensive evaluation of the five core dimensions, the evaluation report generated by the five core dimensions emphasizes the necessity of a multi-dimensional evaluation framework, and the balanced performance of each dimension better reflects the overall intelligence level of the device.

[0140] In addition, with reference to Figure 7 , the present application also provides a household appliance intelligence performance evaluation device 700, comprising: a simulation module 701 for constructing a household appliance intelligence performance evaluation model, simulating a first environmental change process, and starting the household appliance to identify the first environmental change process to enable the household appliance to obtain environmental data; a first evaluation module 702 for collecting a first data processing cycle process in the household appliance, evaluating the first data processing cycle process, and generating a first evaluation report; The second evaluation module 703 is configured to cause the home appliance to perform an environmental regulation action, identify a second environmental change process, evaluate the environmental regulation capability of the home appliance according to the second environmental change process, and generate a second evaluation report.

[0141] The home appliance intelligent performance evaluation apparatus 700 and the method for quantitatively evaluating the intelligent level of the multi-modal smart home appliance are based on the same inventive concept, and thus details are not repeated here.

[0142] In addition, with reference to Figure 8 , Figure 8 The hardware structure of the electronic device of another embodiment is illustrated, and the electronic device includes: The processor 801 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiments of the present application. The memory 802 can be implemented in the form of a ROM (Read Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory). The memory 802 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 802 and are called and executed by the processor 801 to implement the method for quantitatively evaluating the intelligent level of the multi-modal smart home appliance. The input / output interface 803 is configured to realize information input and output. The communication interface 804 is configured to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.). The bus 805 is configured to transmit information between various components (for example, the processor 801, the memory 802, the input / output interface 803, and the communication interface 804) of the device. The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are connected to each other through the bus 805 to realize the communication connection between them in the device.

[0143] The embodiment of the present application further provides a storage medium, which is a computer readable storage medium, used for computer readable storage, and stores one or more programs, which can be executed by one or more processors to implement the above-mentioned method for quantitatively evaluating the intelligent level of a multi-modal intelligent household appliance.

[0144] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0145] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0146] Those skilled in the art can understand that, Figures 1 to 6 The technical solutions shown in the above description do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0147] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separated, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0148] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the function modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0149] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of this application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of orderly or chronological mundane operation, reverse order operation, based on circuitry availability, based on stated preference or the like, and that "default" or other orderings are thus permissible. Further, the terms "comprise", "comprising", "include", "including", and the like, are specifically intended to be open-ended. That is, references to individual steps and the like do not suhstantially exclude the presence of two or more of a given step or its integral presence in the process, method, system, article, or apparatus having been made with a wider scope. The use of notation such as "first", "second", "third", etc. does not generally limit the areas, but can be used for clarity, and merely establishes the order of the steps or placement of components. Moreover, singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise.

[0150] It should be understood that, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or", used to describe the relationship between associated objects, means that there can be three relationships, for example, "A and / or B" can mean that there are only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or the like means any combination of these items, including single or multiple combinations. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be singular or plural.

[0151] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the above-mentioned units is only a logical functional division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0152] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0153] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0154] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in part, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions used to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various other media that can store programs.

[0155] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not intended to limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A quantitative evaluation method for the intelligence level of multimodal smart home appliances, characterized in that, include: A smart performance evaluation model for home appliances is constructed to simulate a first environmental change process. The home appliances are then activated to identify the first environmental change process so that they can acquire environmental data. The first data processing loop within the home appliance is collected, the first data processing loop is evaluated, and a first evaluation report is generated. The home appliance is made to perform environmental control actions, a second environmental change process is identified, the environmental control capability of the home appliance is evaluated based on the second environmental change process, and a second evaluation report is generated.

2. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 1, characterized in that, The first data processing loop process within the home appliance is collected, and the first data processing loop process is evaluated to generate a first evaluation report, including: The data types and corresponding environmental data acquired by the home appliance during the first data processing loop are read. A data type matrix is ​​constructed based on the acquired data types. The ability of the home appliance to identify the environmental state is evaluated based on the data type matrix. The unknown environmental state before the home appliance perceives the environmental data is solved to obtain the environmental entropy. An environmental information matrix is ​​constructed based on the environmental data. The ability of the home appliance to sense the environmental state is evaluated again based on the environmental information matrix to obtain the first conditional entropy. Based on the environmental entropy and the first conditional entropy, the ability of the home appliance to perceive the unknown state of the environment using the environmental information matrix is ​​evaluated, the first environmental perception capability of the home appliance is determined, and a first evaluation report is generated based on the first environmental perception capability.

3. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 1, characterized in that, The process of collecting data from the home appliance within a first data processing loop, evaluating the first data processing loop, and generating a first evaluation report further includes: The encoding structure of the home appliance in the first data processing loop and the original features obtained by the sensor sensing the environmental state are read. Based on the difference between the original features and the encoded data under the encoding structure, the encoding distortion of the home appliance for environmental state information is determined. Based on the original features and the coding structure, the authenticity of the coding structure of the home appliance is evaluated during the first data processing loop to determine the coding entropy difference; Based on the difference between the encoding distortion and the encoding entropy, the efficiency of the home appliance in utilizing environmental status information is analyzed, and a first evaluation report is generated.

4. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 1, characterized in that, The process of causing the home appliance to perform environmental control actions, identifying a second environmental change process, evaluating the home appliance's environmental control capabilities based on the second environmental change process, and generating a second evaluation report includes: After receiving environmental data, the home appliance reads the set of action commands inferred by the home appliance based on its internal knowledge. Based on the set of action commands, the home appliance's ability to control the environment under the influence of the internal knowledge is evaluated, and the second conditional entropy is determined. The environmental data is mapped to the set of action instructions, so that the home appliance selects and executes environmental control actions based on the set of action instructions, obtains the expected environmental state predicted by the home appliance based on the internal knowledge, and determines the environmental state difference based on the set target environmental state and the expected environmental state. The ability to assess the internal knowledge and the performance of the home appliances are evaluated based on the second conditional entropy and the difference in environmental state, and a second evaluation report is generated.

5. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 1, characterized in that, The process of causing the home appliance to perform environmental control actions, identifying a second environmental change process, evaluating the home appliance's environmental control capabilities based on the second environmental change process, and generating a second evaluation report further includes: The home appliance acquires initial environmental information and controlled environmental information after completing environmental control actions, enabling the home appliance to update its internal knowledge based on the initial environmental information and the controlled environmental information; The update level of the internal knowledge is evaluated, the knowledge gain of the internal knowledge is determined, and a second evaluation report is generated.

6. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 5, characterized in that, The process of evaluating the update level of the internal knowledge, determining the knowledge gain of the internal knowledge, and generating a second evaluation report includes: The internal knowledge is updated gradually over a period of time. The changes in the discrete parameters of the internal knowledge before and after each update node are determined in turn. Based on the changes in the discrete parameters, it is determined whether the internal knowledge has converged, and the learning optimization efficiency of the internal knowledge is determined. Based on the internal knowledge before and after the adjacent update nodes, determine the knowledge gain between the internal knowledge; A second evaluation report is generated based on the learning optimization efficiency and the knowledge gain.

7. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 1, characterized in that, The method further includes: The process of simulating a third environmental change is used to control a group of home appliances to adjust to the third environmental change process. The group of home appliances includes multiple home appliances that are interconnected and are set up in the same test space. The second data processing loop within the home appliance group is collected to detect the interconnection status within the home appliance group; A third assessment report is generated based on the aforementioned interconnectivity situation.

8. The quantitative evaluation method for the intelligence level of multimodal smart home appliances according to claim 7, characterized in that, The generation of the third assessment report based on the interconnection status includes: During the interconnection and interoperability process of the home appliance group, the data interaction efficiency of the home appliance group is collected; During the first environmental change process, the first environmental information utilization efficiency of the home appliances is obtained. During the third environmental change process, environmental information is transmitted between the home appliances, and the second environmental information utilization efficiency of the home appliances is collected. The first group effect is determined based on the first environmental information utilization efficiency and the second environmental information utilization efficiency. After the second environmental change process, the first adjustment effect of the home appliances on the environment is detected; after the third environmental change process, the second adjustment effect of the home appliance group on the environment is detected; and the second group effect is determined based on the first adjustment effect and the second adjustment effect. A third evaluation report is generated based on the data interaction efficiency, the first group effect, and the second group effect.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the quantitative evaluation method for the intelligence level of multimodal smart home appliances as described in any one of claims 1 to 8.

10. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the quantitative evaluation method for the intelligence level of multimodal smart home appliances as described in any one of claims 1 to 8.

Images