Environment guiding method and device based on smart home equipment, and home server

Abstract

The invention relates to an environment guiding method and device based on smart home equipment and a home server. The method comprises the following steps: acquiring whole house state data; according to the whole house state data, information field intensity, acceptability and guiding factors for different environment guiding strategies corresponding to each family member are determined, the information field intensity is used for representing the original intensity of a guiding field generated at the position of each family member, the acceptability is used for representing the degree that each family member is willing to be disturbed, and the guiding factors are used for different environment guiding strategies. The guidance factors are used for representing amplification degrees of guidance effects on different environment guidance strategies; according to the information field intensity, the acceptability and the guidance factors, effective information perceptibility of each family member under different environment guidance strategies is calculated; and selecting the optimal effective information perceptibility from the plurality of effective information perceptibility obtained by calculation, and carrying out environment guidance based on the optimal effective information perceptibility. In this way, harmonious and non-interference environment guidance can be formed.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to an environment guidance method, device, and home server based on smart home devices. Background Technology

[0002] With the rapid development of IoT technology, the use of smart home devices is becoming increasingly widespread. However, in existing technologies, smart home devices typically use generic reminder methods (such as voice broadcasts) to remind family members. When there are multiple family members in the house, generic reminder methods cannot adapt to the individual differences and social relationships among family members, easily leading to disharmonious and disruptive environmental guidance. Therefore, how to create a harmonious and non-disruptive environmental guidance has become an urgent technical problem to be solved. Summary of the Invention

[0003] This application provides an environment guidance method, device, and home server based on smart home devices, in order to solve the problem that the existing smart home devices usually adopt a generalized reminder method, which easily leads to disharmonious and disruptive environment guidance.

[0004] In a first aspect, embodiments of this application provide an environment guidance method based on smart home devices, the method comprising: Acquire whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; Based on the whole-house status data, the information field strength, acceptability, and guidance factor for different environmental guidance strategies are determined for each family member. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies. Based on the information field strength, the acceptability, and the guidance factor, the effective information perception of each family member under different environmental guidance strategies is calculated; The optimal effective information perception is selected from multiple calculated effective information perceptions, and environmental guidance is performed based on the optimal effective information perception.

[0005] Optionally, the whole-house status data includes the location information of each family member, the physiological status of each family member, the environmental acoustic events generated by each family member, and the status data of each smart home device; Based on the whole-house status data, the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member are determined, including: The location information of each family member and the status data of each smart home device are input into a pre-trained potential demand prediction model to obtain the demand probability of each family member for the target information. Based on the demand probability, the information field strength is determined. The target information is any information that any family member currently wants to pay attention to. The information field strength is positively correlated with the demand probability. The physiological state of each family member and the environmental acoustic events generated by each family member are input into a pre-trained member state classifier to obtain the acceptability. The guidance factors are obtained by analyzing the guidance strategies for each environment based on the information field strength or the acceptability.

[0006] Optionally, the analysis of guidance strategies for each environment based on the information field strength or the acceptability to obtain the guidance factor includes: Based on the information field strength, determine whether the probability of demand for all family members is greater than a first preset threshold. If it is determined that the probability of need for all family members is greater than the first preset threshold, the value of the guiding factor is determined to be greater than 1; If it is determined that the probability of need for all family members is not greater than the first preset threshold, the value of the guiding factor is determined to be less than 1.

[0007] Optionally, the analysis of guidance strategies for each environment based on the information field strength or the acceptability to obtain the guidance factor includes: Based on the acceptability, it is determined whether the target environment guidance strategy causes physical stimulation to the target family member, and whether the acceptability of the target family member is less than a second preset threshold, wherein the target environment guidance strategy is any environment guidance strategy, and the target family member is any family member; If it is determined that the target environment guidance strategy causes physical stimulation to the target family member and the acceptability of the target family member is less than the second preset threshold, the value of the guidance factor is determined to be less than 1. If it is determined that the target environment guidance strategy does not produce physical stimulation to the target family member, and / or the acceptability of the target family member is greater than or equal to the second preset threshold, the value of the guidance factor is determined to be greater than 1.

[0008] Optionally, the effective information perception of each family member under different environmental guidance strategies can be calculated using the following formula: ; in, Family members At any moment For target information Effective information perception Indicates at time Target information In family members Location The intensity of the information field generated at that location, Family members At any moment Acceptability Represents all family members The guiding factor at time t.

[0009] Optionally, selecting the optimal effective information perception from multiple calculated effective information perceptions includes: Select the effective information perception values ​​that are greater than a third preset threshold from the plurality of effective information perception values; The selected effective information perception levels are sorted in descending order, and the optimal effective information perception level is determined based on the sorting results.

[0010] Optionally, the environmental guidance based on the optimal effective information perception includes: Based on the optimal effective information perception level, environmental control instructions are generated; The environmental control command is sent to the target controlled object so that the target controlled object can perform environmental guidance according to the environmental control command. The target controlled object can be any one of the following: light strip, directional speaker, and temperature control module.

[0011] Secondly, embodiments of this application also provide an environment guidance device based on smart home devices, the device comprising: The acquisition module is used to acquire whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; The determination module is used to determine the information field strength, acceptability, and guidance factor for different environmental guidance strategies for each family member based on the whole house status data. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies. The calculation module is used to calculate the effective information perception of each family member under different environmental guidance strategies based on the information field strength, the acceptability, and the guidance factor. The environment guidance module is used to select the optimal effective information perception from multiple calculated effective information perceptions, and to perform environment guidance based on the optimal effective information perception.

[0012] Thirdly, embodiments of this application also provide a home server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the environment guidance method based on smart home devices described in the first aspect.

[0013] Fourthly, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the environment guidance method based on smart home devices described in the first aspect.

[0014] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; based on the whole-house status data, the information field strength, acceptability, and guidance factor for different environmental guidance strategies corresponding to each family member are determined respectively, wherein the information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification degree of the guidance effect of different environmental guidance strategies; based on the information field strength, the acceptability, and the guidance factor, the effective information perception degree of each family member under different environmental guidance strategies is calculated; the optimal effective information perception degree is selected from the multiple calculated effective information perception degrees, and environmental guidance is performed based on the optimal effective information perception degree. By comprehensively considering the information field strength, acceptability, and guidance factors of different environmental guidance strategies for each family member, the effective information perception of each family member under different environmental guidance strategies is determined. Based on the effective information perception, the environmental guidance strategy that best meets the individual differences and social relationships of each family member is determined, thereby forming a harmonious and non-intrusive environmental guidance, effectively solving the problem of disharmonious and intrusive environmental guidance caused by using a general reminder method. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 A flowchart illustrating an environment guidance method based on smart home devices provided in this application embodiment; Figure 2 A flowchart illustrating an environment guidance method based on smart home devices provided in an embodiment of this application; Figure 3 A schematic diagram of an environment guidance device based on a smart home device is provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a home server provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0021] To address the problem that existing smart home devices typically use generic reminder methods, which can easily lead to disharmonious and disruptive environmental guidance, this application provides an environmental guidance method, device, and home server based on smart home devices, which can create a harmonious and non-disruptive environmental guidance.

[0022] See Figure 1 , Figure 1 This is a flowchart illustrating an environment guidance method based on smart home devices, provided as an embodiment of this application. Figure 1 As shown, the environment guidance method based on smart home devices may include the following steps: Step S101: Obtain whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house.

[0023] Specifically, the aforementioned whole-house status data may include, but is not limited to, the status data of each family member (such as the location information, physiological state, and environmental acoustic events generated by each family member) and the status data of each smart home device (such as the status data of the oven, air conditioner, and lights).

[0024] When acquiring whole-house status data, it can be obtained from preset indoor positioning anchor points (used to collect the location information of each family member), microphone arrays (used to collect the environmental acoustic events of each family member), smart device gateways (used to collect the status data of each smart home device), wearable devices (used to collect the physiological status of each family member), and other devices.

[0025] Step S102: Based on the whole house status data, determine the information field strength, acceptability, and guidance factor for different environmental guidance strategies for each family member. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies.

[0026] Specifically, the whole-house status data can be input into a pre-trained potential demand prediction model and a member status classifier to obtain the information field strength and acceptability of each family member. Then, based on the information field strength or acceptability, the guidance strategies for each environment can be analyzed to obtain guidance factors. Alternatively, the whole-house status data can be input into a pre-trained machine learning model to obtain the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member. This application does not impose any specific limitations.

[0027] Step S103: Calculate the effective information perception of each family member under different environmental guidance strategies based on information field strength, acceptability, and guidance factor.

[0028] Specifically, the aforementioned effective information perception level is determined by comprehensively considering information field strength, acceptability, and guiding factors.

[0029] When determining the effective information perception level, the effective information perception level of each family member under different environmental guidance strategies can be determined by calculating the product between information field strength, acceptability, and guidance factor; alternatively, the effective information perception level of each family member under different environmental guidance strategies can be determined by calculating the sum of the weights between information field strength, acceptability, and guidance factor. This application does not impose specific limitations on these methods.

[0030] Step S104: Select the optimal effective information perception from the multiple effective information perceptions obtained from the calculation, and guide the environment based on the optimal effective information perception.

[0031] Specifically, the optimal effective information perception score mentioned above is the effective information perception score with the highest score. Based on this effective information perception score, it is possible to determine which environmental guidance strategy to adopt and which person to guide, which to some extent resolves the contradiction between information push and harassment from family members.

[0032] By comprehensively considering the information field strength, acceptability, and guidance factors of different environmental guidance strategies for each family member, the effective information perception of each family member under different environmental guidance strategies is determined. Based on the effective information perception, the environmental guidance strategy that best meets the individual differences and social relationships of each family member is determined, thereby forming a harmonious and non-intrusive environmental guidance, effectively solving the problem of disharmonious and intrusive environmental guidance caused by using a general reminder method.

[0033] In one optional embodiment, the whole-house status data includes the location information of each family member, the physiological status of each family member, the environmental acoustic events generated by each family member, and the status data of each smart home device; In step S102 above, based on the whole-house status data, the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member are determined, including: The location information of each family member and the status data of each smart home device are input into a pre-trained potential demand prediction model to obtain the demand probability of each family member for the target information. Based on the demand probability, the information field strength is determined. The target information is any information that any family member currently wants to pay attention to. The information field strength is positively correlated with the demand probability. The physiological state of each family member and the environmental acoustic events generated by each family member are input into a pre-trained member state classifier to obtain the acceptability. Based on the information field strength or acceptability, guidance strategies for various environments are analyzed to obtain guidance factors.

[0034] It should be noted that the aforementioned potential demand prediction model can be implemented using Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Convolutional Long Short-Term Memory (ConvLSTM), etc. As an optional implementation, an LSTM model can be used as the potential demand prediction model. This model can continuously analyze the contextual information stream, such as the location information of each family member and the status data of each smart home device, and output the probability of each family member's demand for the target information. Furthermore, based on the probability of each family member's need for target information... Determine the information field strength of each family member. The information field strength It can reflect the family members At any moment For target information Demand probability Information field strength With demand probability They are positively correlated.

[0035] When training this potential demand prediction model, a large amount of family environment context data (as shown below) and corresponding real feedback from family members (e.g., whether family members actively searched for information in this context) can be collected. or information (Whether family members dealt with it immediately after it occurred). The model is trained using this contextual data and real feedback from family members as sample data. This contextual data may include the following information: Location of family members: for example, "study", "living room", etc.; Current time: for example, "18:30", because demand is strongly correlated with time (such as mealtime).

[0036] Appliance status: For example, "Oven status: Running, time remaining: 120 seconds".

[0037] Historical interaction data (implicit): As a time series model, LSTM uses its memory units to analyze the recent behavioral patterns of family members, such as "whether family member B has been to the kitchen in the past 5 minutes".

[0038] The trained latent demand prediction model excels at capturing long-term dependencies. For example, it can understand the sequence "Family member B is in the living room + oven is almost done + it is evening" as implying the probability of family member B needing the information about the "oven status". Very high. This latent demand forecasting model can output a demand probability for each piece of latent information (such as "oven status", "door and window safety", etc.). .

[0039] The aforementioned member state classifier can be implemented using Gradient Boosting Decision Tree (GBDT), Random Forest, Support Vector Machine (SVM), etc. As an optional implementation, the GBDT model can be used as the member state classifier. The goal of the GBDT model is to quantify the status of family members in... The degree to which one is willing to be disturbed at any time , which is a value between [0,1].

[0040] When training this member status classifier, multiple sets of feature data can be collected (as shown below), and the current acceptability status can be labeled (e.g., Do Not Disturb, Slight Reminder Allowed, Reminder Allowed at Any Time, etc.). These can be used as sample data for model training. The trained member status classifier can then learn the relationship between the feature data and the acceptability status. The feature data can include the following information: Physiological data: primarily from wearable devices, such as heart rate variability (HRV). For example, family member A has an HRV of 38 ms (typically associated with stress or focus), while family member B has an HRV of 62 ms (typically associated with relaxation).

[0041] Operating status labels: Primarily derived from acoustic event recognition from the ambient microphone array. For example, identifying "conference voice" and "keyboard typing" in family member A's environment, and "children playing" and "background music" in family member B's environment.

[0042] Other contexts (implicit): may also include the location of family members (e.g., “study”, “living room”), time (e.g., “late at night”, “evening”), etc.

[0043] The trained member-state classifier excels at handling heterogeneous data that mixes continuous values ​​(such as HRV) and class values ​​(such as acoustic labels). It makes decisions through an ensemble of decision trees. For family member A: When the model sees the input as [HRV=38ms, event='conference voice', event='keyboard tapping', location='study'], it judges that this set of features highly matches the categories of "focused on work" or "does not want to be disturbed" in the training data, and therefore outputs a value close to 0.

[0044] For family member B: When the model sees the input [HRV=62ms, event='children playing', location='living room'], it determines that this set of features matches the category of "relaxation and leisure", and therefore outputs a value close to 1.

[0045] In this embodiment, the location information of each family member and the status data of each smart home device can be input into a pre-trained potential demand prediction model to obtain the demand probability of each family member for the target information. Based on the demand probability, the information field strength is determined. The physiological state of each family member and the environmental acoustic events generated by each family member are input into a pre-trained member state classifier to obtain the acceptability. Then, based on the information field strength or acceptability, the guidance strategies of each environment are analyzed to obtain the guidance factor.

[0046] In this way, based on the whole-house status data, the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member can be accurately determined. This facilitates the subsequent calculation of the effective information perception of each family member under different environmental guidance strategies based on the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member.

[0047] In an optional embodiment, the above steps, including analyzing guidance strategies for each environment based on information field strength or acceptability, to obtain guidance factors, include: Based on the information field strength, determine whether the probability of the needs corresponding to all family members is greater than the first preset threshold. If the probability of need for all family members is greater than the first preset threshold, the value of the guiding factor is determined to be greater than 1. If it is determined that the probability of need for all family members is not greater than the first preset threshold, the value of the guiding factor is determined to be less than 1.

[0048] Specifically, based on the information field strength, it can be determined whether the probability of demand corresponding to all family members is greater than a first preset threshold. This first preset threshold can be set according to actual needs and is not specifically limited here. If the probability of demand corresponding to all family members is greater than the first preset threshold, the value of the guiding factor is greater than 1; if the probability of demand corresponding to all family members is not greater than the first preset threshold, the value of the guiding factor is less than 1.

[0049] For example, obtaining target information (e.g., "Movie download complete") and collections (Assuming it includes family member A and family member B) All family members have this information Demand probability If family member A's >First preset threshold, and family member B's If the first preset threshold is met, it can be determined that family member A and family member B share a common need. In this case, a value greater than 1 can be output as a guiding factor, such as... This is to enhance joint guidance for both family members.

[0050] This can amplify the guiding effect when multiple family members have a potential need for the same target information.

[0051] In an optional embodiment, the above steps, including analyzing guidance strategies for each environment based on information field strength or acceptability, to obtain guidance factors, include: Based on acceptability, it is determined whether the target environment guidance strategy causes physical stimulation to the target family member, and whether the acceptability of the target family member is less than a second preset threshold, wherein the target environment guidance strategy is any environment guidance strategy, and the target family member is any family member; If it is determined that the target environment guidance strategy causes physical stimulation to the target family members and the acceptability of the target family members is less than the second preset threshold, the value of the guidance factor is determined to be less than 1. If the target environment guidance strategy does not produce physical stimulation to the target family members, and / or the acceptability of the target family members is greater than or equal to the second preset threshold, the value of the guidance factor is determined to be greater than 1.

[0052] Specifically, based on acceptability, it can be determined whether the target environment guidance strategy produces physical stimulation to the target family members and whether the acceptability of the target family members is less than a second preset threshold. If the target environment guidance strategy produces physical stimulation to the target family members and the acceptability of the target family members is less than the second preset threshold, then the value of the guidance factor can be determined to be less than 1. If the target environment guidance strategy does not produce physical stimulation to the target family members and / or the acceptability of the target family members is greater than or equal to the second preset threshold, then the value of the guidance factor can be determined to be greater than 1.

[0053] For example, suppose the target environment guidance strategy is a sound reminder strategy, and the target family member is family member A reading in the study. If the sound reminder strategy provides physical stimulation to family member A, and family member A's acceptability is... If the value is less than the second preset threshold, then it can be determined as "high interference". In this case, a value less than 1 can be output as a guiding factor, such as... .

[0054] Assuming the target environment guidance strategy is a light-based alert strategy, it can be determined that the living room lights will not physically stimulate family member A, thus classifying it as "no interference." In this case, a value of 1 can be output as the guidance factor, such as... .

[0055] In this way, guidance factors can be comprehensively determined based on whether the target environment guidance strategy produces physical stimulation for the target family members and the acceptability of the target family members, thereby selecting the degree of amplification of the guidance effect and the environmental guidance strategy.

[0056] In an optional embodiment, the effective information perception level of each family member under different environmental guidance strategies is calculated using the following formula: ; in, Family members At any moment For target information Effective information perception Indicates at time Target information In family members Location The intensity of the information field generated at that location, Family members At any moment Acceptability Represents all family members The guiding factor at time t.

[0057] in, It is a scalar that can serve as the ultimate basis for guiding decisions on whether and how to implement them. It represents a specific family member. It represents a specific potential information need, such as "oven status" or "door and window safety". Represents time. Information field strength. This represents the location of information i within a family member's home. The original strength of the generated guiding field. It is calculated by a latent demand prediction model, which uses an LSTM architecture to continuously analyze the contextual information flow such as the location, time, and appliance status of family members, and outputs the probability of family member u's demand for information i. The value of F and Positive correlation. Acceptability among family members. This is a factor with a value between [0,1] that quantifies the degree to which a family member is willing to be disturbed at time t. It is calculated by a family member state classifier (such as a gradient boosting decision tree GBDT model). The input to this model includes physiological data such as HRV from wearable devices, as well as environmental acoustic events such as "keyboard tapping" and "conference calls" identified through environmental microphones. The value approaches 0 when the family member is focused on work or sleeping; it approaches 1 when the family member is relaxed. (Guidance Factor) It is calculated by a social arbitration logic module, which can be used to adjust guidance strategies in multi-family environments. This is useful when the needs of multiple family members resonate (e.g., they are all waiting for the same movie to finish downloading). >1. Amplify the guiding effect; when guiding one family member might interfere with another family member who is in a low-acceptance state, <1, suppress the guiding intensity or change the guiding modality (such as converting sound into light).

[0058] In this way, the above formula can be used to accurately calculate the effective information perception of each family member under different environmental guidance strategies, which makes it convenient to select the optimal effective information perception from the multiple calculated effective information perceptions and to conduct environmental guidance based on the optimal effective information perception.

[0059] In an optional embodiment, step S104, selecting the optimal effective information perception from the calculated multiple effective information perceptions, includes: Select the valid information perception values ​​that are greater than the third preset threshold from multiple valid information perception values; The selected effective information perception levels are sorted in descending order, and the optimal effective information perception level is determined based on the sorting results.

[0060] Specifically, after calculating multiple effective information perception values, effective information perception values ​​with values ​​greater than a third preset threshold can be selected from these multiple effective information perception values. Then, the selected effective information perception values ​​are sorted in descending order, and based on the sorting results, the effective information perception value with the highest ranking is determined as the optimal effective information perception value. Here, the third preset threshold can be set according to actual needs and is not specifically limited.

[0061] Using the above method, the optimal effective information perception can be accurately determined from multiple effective information perceptions, which facilitates subsequent environmental guidance based on this optimal effective information perception.

[0062] In an optional embodiment, step S104, which involves providing environmental guidance based on optimal effective information perception, includes: Based on the optimal effective information perception, environmental control commands are generated; Environmental control commands are sent to the target controlled object so that the target controlled object can guide the environment according to the environmental control commands. The target controlled object can be any one of the following: light strip, directional speaker, and temperature control module.

[0063] Specifically, after determining the optimal effective information perception level, environmental control commands can be generated based on this level. These commands are then sent to the target controlled object, enabling it to guide the environment accordingly. The target controlled object can be any one of the following: an LED strip, a directional speaker, or a temperature control module. Thus, environmental guidance can be achieved by controlling any one of these components.

[0064] It should be noted that "strategy templates" or "guidance primitives" can be preset for information categories and guidance strategies. For example, designers can predefine information... =Kitchen Affairs, Guiding Strategy=The primitive template of "Light", specifically {Control Object: 'Living Room LED', Color Temperature Range: [2700K, 4000K], Brightness Range: [30%, 100%], Animation Type: ['Static', 'Breathing', 'Flowing'], Direction: 'Pointing to Kitchen'}. Then, based on the score of optimal effective information perception, the parameters in the primitive template can be dynamically adjusted to achieve the effect of quantifying the guidance intensity.

[0065] For example, assuming the effective range of effective information perception is [execution threshold 0.5, theoretical maximum 1.0], and the current optimal score of effective information perception is 0.72, then the following parameters in the primitive template can be adjusted: (1) Brightness mapping: Map the position of 0.72 in the interval [0.5, 1.0] to the interval [30%, 100%].

[0066] (2) Brightness = (Rounded to 70%).

[0067] (3) Color temperature mapping: a lower EIP (indicating a lower urgency) corresponds to a warmer color temperature, and a higher EIP corresponds to a cooler color temperature.

[0068] (4) Color temperature = (Rounded to 3000K).

[0069] (5) Animation Mapping: The optimal effective information perception score also determines the "intensity" of the animation. 0.72 is at a medium intensity, and "breathing flow" can be selected. If the optimal effective information perception score is 0.95 (very urgent), "rapid flashing" can be selected.

[0070] To facilitate understanding, the following specific scenarios illustrate the environmental guidance process in detail. Imagine a scenario where the father (family member A) is attending an important video conference in his study, requiring absolute quiet; the mother (family member B) is playing with her child in the living room in a relaxed atmosphere; meanwhile, the oven in the kitchen is about to finish baking.

[0071] The traditional approach is to use a smart speaker in the living room to issue a generic voice alert: "Ding! The oven is done." This sound is likely to penetrate the walls, disturbing the father who is in a meeting, causing unnecessary embarrassment and disruption.

[0072] The approach taken in this application is as follows: First, multiple sensors in the home detect that the father is in a meeting (by recognizing meeting audio and continuous keyboard typing), and determine that his "acceptability" at that moment is extremely low, meaning he strongly dislikes being disturbed. Simultaneously, the system also detects that the mother and child are in a relaxed, leisurely state. This allows it to predict that the information "the oven is almost done" is more important and relevant to the mother. When deciding how to remind her, considering the father's need for quiet, any reminder options that might generate noise are automatically rejected. At this time, the smart light strip on the living room ceiling can be controlled to emit a warm, soft, and slowly flowing dynamic light effect towards the kitchen. This subtle change in light can be subtly (within her limbic awareness) noticed by the relaxed mother, who naturally understands that something in the kitchen needs her attention. Throughout the entire process, the father in the study remains undisturbed, and the tranquility and focused atmosphere of the family are perfectly preserved.

[0073] The hardware architecture structure involved in the embodiments of this application may include: a sensor layer (such as indoor positioning anchors, microphone arrays, smart device gateways, wearable devices, etc.), a cognitive engine (which can be deployed on a local home server to run a demand prediction module, a state classification module, and a social arbitration module), and an actuator layer (such as LED light strips, directional speakers, temperature control modules, etc.).

[0074] Its environment guidance process is as follows: Figure 2 As shown, the specific steps include the following: Step S201: Data input.

[0075] The cognitive engine collects raw data from the sensor layer at a high frequency (e.g., 5Hz) to obtain whole-house status data, which includes the following information: Family member A's location: [Study]; Family member A's ambient acoustic events: ['Conference audio', 'Keyboard typing']; Family member A's physiological data: {'HRV': 38ms} (from their smartwatch); Family member B's location: [Living room]; Family member B's environmental acoustic events: ['Children playing', 'Background music']; Family member B's physiological data: {'HRV': 62ms}; Device status: {'Oven': {'Status':'Running','Remaining time':'120 seconds'}}; Step S202, Cognitive Computing.

[0076] The whole-house status data is sent to three core modules for analysis: Demand Forecasting Module: The LSTM model (i.e., the latent demand forecasting model mentioned above) analyzes the data and concludes that the oven event has a high correlation with family member B, with an output F=0.9; while the correlation with family member A is lower.

[0077] State Classification Module: The GBDT model (i.e., the member state classifier mentioned above) determines that family member A should not be disturbed based on their meeting state and low HRV value, outputting R_A=0.1. Based on family member B's leisure state and higher HRV value, it determines that guidance is acceptable, outputting R_B=0.8.

[0078] Social Arbitration Module: This module assesses that sound alerts generated in the living room would severely interfere with family member A (who has low tolerance for sound leakage) in the study due to sound leakage. Therefore, a strong inhibition factor I_s(sound) = 0.1 is assigned to the sound modality. Light guidance, however, is confined to the living room and has no impact on family member A; hence, I_s(light) = 1.0.

[0079] Step S203: Decision-making and execution.

[0080] Based on the above analysis results, the final scores for different guidance schemes are calculated: Output (Sound Solution Evaluation): EIP (sound) = F × R_B × I_s (sound) = 0.9 × 0.8 × 0.1 = 0.072.

[0081] Output (Light Scheme Evaluation): EIP (ray) = F × R_B × I_s (ray) = 0.9 × 0.8 × 1.0 = 0.72.

[0082] Since the EIP score of the light-guided scheme (0.72) is much higher than the preset execution threshold (e.g., 0.5) and much higher than the sound-guided scheme, the light-guided scheme can be adopted in the end.

[0083] Step S204: Generate and execute the environment boot.

[0084] The EIP score (0.72) is converted into specific device control parameters. The following instructions are generated and sent to the living room gateway via the local network. The controlled object is the ceiling LED light strip. The control parameters are: {color temperature: 3000K, brightness: 70%, animation: 'breathing flow', direction: 'pointing to the kitchen'}.

[0085] Thus, a complete closed loop from perception, understanding, decision-making to execution is completed, realizing the harmonious, intelligent, and interference-free family member experience in the aforementioned example scenario.

[0086] Therefore, this application innovatively introduces a quantitative approach to the acceptability of family members' willingness to be disturbed, and a guiding factor to regulate information conflicts among multiple family members, based on traditional information guidance theory. It no longer views family members as isolated individuals constantly ready to receive information, but rather as a collection within complex social relationships and dynamic personal states (work, rest, entertainment). This enables smart home devices to make intelligent and human-centered judgments, achieving breakthroughs in the three levels of "whether to say it," "to whom to say it," and "how to say it," thus resolving to some extent the contradiction between information push and family member harassment. Furthermore, the calculated effective information perception can be mapped in real-time to the coordinated control of various media in the environment (such as light, sound, and microclimate). This involves precisely adjusting the color temperature / brightness / dynamics of light, the volume / timbre / direction of directional sound fields, and the temperature of micro-thermal control elements to create a subtle, immersive "information field" that is directed towards the information source and can be perceived by the peripheral consciousness of family members, rather than simply triggering an alarm. This greatly reduces disturbance to family members, protects their focus and the tranquil atmosphere of the home, and reduces their cognitive load through natural and intuitive guidance, creating a new living experience where people, home, and information coexist harmoniously.

[0087] See Figure 3 , Figure 3 This is a schematic diagram of an environment guidance device based on a smart home device, provided as an embodiment of this application. Figure 3 As shown, the environment guidance device 300 based on smart home devices includes: The acquisition module 301 is used to acquire whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; The determination module 302 is used to determine the information field strength, acceptability, and guidance factor for different environmental guidance strategies for each family member based on the whole house status data. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies. The calculation module 303 is used to calculate the effective information perception of each family member under different environmental guidance strategies based on information field strength, acceptability and guidance factors. The environment guidance module 304 is used to select the optimal effective information perception from multiple calculated effective information perceptions and to perform environment guidance based on the optimal effective information perception.

[0088] Furthermore, the whole-house status data includes the location information of each family member, the physiological status of each family member, the environmental acoustic events generated by each family member, and the status data of each smart home device; the determination module 302 includes: The first input submodule is used to input the location information of each family member and the status data of each smart home device into the pre-trained potential demand prediction model to obtain the demand probability of each family member for the target information, and to determine the information field strength based on the demand probability. The target information is any information that any family member currently wants to pay attention to, and the information field strength is positively correlated with the demand probability. The second input submodule is used to input the physiological state of each family member and the environmental acoustic events generated by each family member into a pre-trained member state classifier to obtain the acceptability. The analysis submodule is used to analyze the guidance strategies of various environments based on the information field strength or acceptability, and obtain guidance factors.

[0089] Furthermore, the analysis submodule includes: The first judgment unit is used to determine, based on the information field strength, whether the probability of demand for all family members is greater than the first preset threshold. The first determining unit is used to determine that the value of the guiding factor is greater than 1 when the probability of the demand corresponding to all family members is greater than the first preset threshold. The second determining unit is used to determine that the value of the guiding factor is less than 1 if the probability of demand corresponding to all family members is not greater than the first preset threshold.

[0090] Furthermore, the analysis submodule also includes: The second judgment unit is used to determine, based on acceptability, whether the target environment guidance strategy causes physical stimulation to the target family member, and whether the acceptability of the target family member is less than a second preset threshold, wherein the target environment guidance strategy is any environment guidance strategy, and the target family member is any family member; The third determining unit is used to determine that the value of the guiding factor is less than 1 when it is determined that the target environment guidance strategy produces physical stimulation to the target family members and the acceptability of the target family members is less than the second preset threshold. The fourth determining unit is used to determine that the value of the guiding factor is greater than 1 when it is determined that the guiding strategy of the target environment does not produce physical stimulation to the target family members and / or the acceptability of the target family members is greater than or equal to the second preset threshold.

[0091] Furthermore, the effective information perception of each family member under different environmental guidance strategies is calculated using the following formula: ; in, Family members At any moment For target information Effective information perception Indicates at time Target information In family members Location The intensity of the information field generated at that location, Family members At any moment Acceptability Represents all family members The guiding factor at time t.

[0092] Furthermore, the environment guidance module 304 includes: The selection submodule is used to select the valid information perception values ​​that are greater than a third preset threshold from multiple valid information perception values. The sorting submodule is used to sort the selected effective information perception in descending order, and determine the optimal effective information perception based on the sorting results.

[0093] Furthermore, the environment guidance module 304 also includes: The generation submodule is used to generate environmental control commands based on the optimal effective information perception. The sending submodule is used to send environmental control commands to the target controlled object so that the target controlled object can perform environmental guidance according to the environmental control commands. The target controlled object can be any one of the following: light strip, directional speaker, and temperature control module.

[0094] It should be noted that the environment guidance device 300 based on smart home devices can implement the environment guidance method based on smart home devices provided in any of the aforementioned method embodiments, and can achieve the same technical effect, which will not be elaborated here.

[0095] See Figure 4This application also provides a home server, including a processor 411, a communication interface 412, a memory 413, and a communication bus 414, wherein the processor 411, the communication interface 412, and the memory 413 communicate with each other through the communication bus 414. Memory 413 is used to store computer programs; In one embodiment of this application, when the processor 411 executes the program stored in the memory 413, it implements the environment booting method based on smart home devices provided in any of the foregoing method embodiments.

[0096] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the environment guidance method based on smart home devices as provided in any of the foregoing method embodiments.

[0097] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0099] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0100] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An environment guidance method based on smart home devices, characterized in that, The method includes: Acquire whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; Based on the whole-house status data, the information field strength, acceptability, and guidance factor for different environmental guidance strategies are determined for each family member. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies. Based on the information field strength, the acceptability, and the guidance factor, the effective information perception of each family member under different environmental guidance strategies is calculated; The optimal effective information perception is selected from multiple calculated effective information perceptions, and environmental guidance is performed based on the optimal effective information perception.

2. The method according to claim 1, characterized in that, The whole-house status data includes the location information of each family member, the physiological status of each family member, the environmental acoustic events generated by each family member, and the status data of each smart home device; Based on the whole-house status data, the information field strength, acceptability, and guidance factors for different environmental guidance strategies for each family member are determined, including: The location information of each family member and the status data of each smart home device are input into a pre-trained potential demand prediction model to obtain the demand probability of each family member for the target information. Based on the demand probability, the information field strength is determined. The target information is any information that any family member currently wants to pay attention to. The information field strength is positively correlated with the demand probability. The physiological state of each family member and the environmental acoustic events generated by each family member are input into a pre-trained member state classifier to obtain the acceptability. The guidance factors are obtained by analyzing the guidance strategies for each environment based on the information field strength or the acceptability.

3. The method according to claim 2, characterized in that, The analysis of guidance strategies for each environment based on the information field strength or the acceptability yields the guidance factors, including: Based on the information field strength, determine whether the probability of demand for all family members is greater than a first preset threshold. If it is determined that the probability of need for all family members is greater than the first preset threshold, the value of the guiding factor is determined to be greater than 1; If it is determined that the probability of need for all family members is not greater than the first preset threshold, the value of the guiding factor is determined to be less than 1.

4. The method according to claim 2, characterized in that, The analysis of guidance strategies for each environment based on the information field strength or the acceptability yields the guidance factors, including: Based on the acceptability, it is determined whether the target environment guidance strategy causes physical stimulation to the target family member, and whether the acceptability of the target family member is less than a second preset threshold, wherein the target environment guidance strategy is any environment guidance strategy, and the target family member is any family member; If it is determined that the target environment guidance strategy causes physical stimulation to the target family member and the acceptability of the target family member is less than the second preset threshold, the value of the guidance factor is determined to be less than 1. If it is determined that the target environment guidance strategy does not produce physical stimulation to the target family member, and / or the acceptability of the target family member is greater than or equal to the second preset threshold, the value of the guidance factor is determined to be greater than 1.

5. The method according to claim 1, characterized in that, The effective information perception of each family member under different environmental guidance strategies is calculated using the following formula: ； in, Family members At any moment For target information Effective information perception Indicates at time Target information In family members Location The intensity of the information field generated at that location, Family members At any moment Acceptability Represents all family members The guiding factor at time t.

6. The method according to claim 1, characterized in that, The step of selecting the optimal effective information perception from multiple calculated effective information perceptions includes: Select the effective information perception values ​​that are greater than a third preset threshold from the plurality of effective information perception values; The selected effective information perception levels are sorted in descending order, and the optimal effective information perception level is determined based on the sorting results.

7. The method according to claim 1, characterized in that, The environmental guidance based on the optimal effective information perception includes: Based on the optimal effective information perception level, environmental control instructions are generated; The environmental control command is sent to the target controlled object so that the target controlled object can perform environmental guidance according to the environmental control command. The target controlled object can be any one of the following: light strip, directional speaker, and temperature control module.

8. An environment guidance device based on smart home devices, characterized in that, The device includes: The acquisition module is used to acquire whole-house status data, wherein the whole-house status data is used to characterize the current status of each family member and each smart home device in the whole house; The determination module is used to determine the information field strength, acceptability, and guidance factor for different environmental guidance strategies for each family member based on the whole house status data. The information field strength is used to characterize the original strength of the guidance field generated at the location of each family member, the acceptability is used to characterize the degree to which each family member is willing to be disturbed, and the guidance factor is used to characterize the amplification of the guidance effect of different environmental guidance strategies. The calculation module is used to calculate the effective information perception of each family member under different environmental guidance strategies based on the information field strength, the acceptability, and the guidance factor. The environment guidance module is used to select the optimal effective information perception from multiple calculated effective information perceptions, and to perform environment guidance based on the optimal effective information perception.

9. A home server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the environment guidance method based on any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the environment guidance method based on any one of claims 1-7.

Images