A smart home control method and system

Abstract

The present invention relates to the field of intelligent control technology, and in particular to a smart home control method and system, the method comprising: obtaining multiple initial device groups according to operation control records of each smart device in a smart home list within multiple sampling periods; determining a user device cluster controlled by the user from the initial device group according to the use control record; forming a parameter set with operation parameters of each user device group in the user device cluster, and determining the user association of each parameter set; determining the user association of each parameter set based on environmental data and physiological data, sorting each parameter set in descending order of user association, selecting multiple parameter sets with top rankings, and user device groups corresponding to the multiple parameter sets to form a recommendation list; obtaining the parameter set selected by the user from the recommendation list, and controlling the operation of the corresponding user device group according to the parameter set; the present invention can improve the personalized matching degree of smart home control.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent home control method and system. Background Art

[0002] When smart home devices in related technologies are linked to different scenes, most of them pre-configure one or more smart home devices to be controlled in each scene in the application. This control method is fixed once set and cannot adapt to changes in user's living habits. It is also necessary to modify the control parameters of each smart home device one by one and repeat the operation. The setting efficiency is extremely low and it is difficult to meet the user's demand for personalized and intelligent home environment.

[0003] The development of smart devices has greatly facilitated people's lives. Take smart home devices as an example. They connect various devices in the user's home, such as audio and video equipment, lighting systems, curtain control, air conditioning control, etc., through the Internet of Things technology, so as to provide a variety of functions and means such as home appliance control, lighting control, indoor and outdoor remote control, HVAC control, etc. However, in traditional control schemes, automatic control of smart devices is usually achieved based on factory pre-set or user-defined automatic execution programs. It is impossible to dynamically adjust the operating parameters of the device according to changes in the user's own physiological state and environmental conditions, and the personalized matching degree of smart control is insufficient. Summary of the invention

[0004] The present invention aims to provide a smart home control method and system, aiming to improve the personalized matching degree of smart home control.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a smart home control method, the method comprising the following steps:

[0007] S100, obtaining operation control records of each smart device in a smart home list within multiple sampling periods, and clustering each smart device in the smart home list into multiple initial device groups according to the operation control records; wherein the operation control records include operation parameters of the smart devices and adjustment time of the operation parameters;

[0008] S200, obtaining a usage control record of a user in a current sampling period, and determining a user device cluster controlled by the user from the initial device group according to the usage control record; wherein the user device cluster includes at least one user device group, and the user device group includes at least one device pair; the usage control record includes environmental data and physiological data corresponding to the adjustment time of the user controlling the smart device;

[0009] S300, forming a parameter set from the operating parameters of each user device group in the user device cluster, determining an environmental relevance and a physiological relevance of each parameter set, and determining a user relevance of each parameter set according to the environmental relevance and the physiological relevance; wherein the environmental relevance indicates a degree of association between environmental data and the parameter set, and the physiological relevance indicates a degree of association between physiological data and the parameter set;

[0010] S400, obtaining current environmental data and physiological data, determining the user relevance of each parameter set based on the environmental data and physiological data, sorting the parameter sets in descending order of user relevance, and determining the user device groups corresponding to the parameter sets; selecting multiple parameter sets with the highest ranking and the user device groups corresponding to the multiple parameter sets to form a recommendation list;

[0011] S500, obtaining a parameter set selected by a user from the recommendation list, determining a user device group corresponding to the parameter set, and controlling the corresponding user device group to operate according to the parameter set.

[0012] In a second aspect, an embodiment of the present invention provides a smart home control system, the system comprising:

[0013] at least one processor;

[0014] at least one memory for storing at least one program;

[0015] When the at least one program is executed by the at least one processor, the at least one processor implements the smart home control method as described in any one of the first aspects.

[0016] The beneficial effects of the present invention are as follows: the present invention discloses a smart home control method and system, which forms the most basic and extensive initial device group by collecting operation control records within multiple sampling periods; forms a user device cluster that is strongly related to the user based on the initial device group by obtaining the user's usage control records within the current sampling period, obtains the environmental state of the home environment and the user's physiological state within the current sampling period, performs data analysis based on the current environmental state and the user's physiological state, and refreshes the recommendation list at regular intervals, which can adapt to the most recent environmental state and physiological state in terms of timeliness, and provide personalized smart control to the user in combination with the environmental state and the physiological state. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 is a flow chart of a smart home control method according to an embodiment of the present invention;

[0019] Figure 2 Schematic diagram of the structure of the smart home control system in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0021] In the related art, a widely used solution to the problem in the background art is to make the model provide the basis for judging whether it is correct while providing the confidence of its recognition. However, the above method can only provide uncertainty information of the data or model, but cannot use the uncertainty information to feed back to the network for training.

[0022] See also Figure 1 , Figure 1 1 is a flow chart of a smart home control method provided by the present invention, the method comprising the following steps:

[0023] S100, obtaining operation control records of each smart device in a smart home list within multiple sampling periods, and clustering each smart device in the smart home list into multiple initial device groups according to the operation control records; wherein the operation control records include operation parameters of the smart devices and adjustment time of the operation parameters;

[0024] It should be noted that each user in the family group obtains permission for the smart device in advance through a smart terminal (such as a mobile phone), the cloud server is respectively connected to the smart gateway and the smart terminal of each user, the smart home list has multiple smart devices, the smart gateway is connected to each smart device in the smart home list, and the smart gateway records the operation control records of the smart device in each sampling period in the form of a log; the method steps in the embodiment of the present invention are executed by the cloud server, and the permission of the smart gateway is obtained in advance with the permission of the user, and the permission includes data access and query to the smart gateway. In some embodiments, the sampling period can be set to one day. The adjustment time of the operating parameters refers to the time when the operating parameters of the smart device change, for example, the time to turn on, turn off and adjust the smart device; the smart gateway records the adjustment time in the form of a timestamp.

[0025] S200, obtaining a usage control record of a user in a current sampling period, and determining a user device cluster controlled by the user from the initial device group according to the usage control record; wherein the user device cluster includes at least one user device group, and the user device group includes at least one device pair; the usage control record includes environmental data and physiological data corresponding to the adjustment time of the user controlling the smart device;

[0026] S300, forming a parameter set from the operating parameters of each user device group in the user device cluster, determining an environmental relevance and a physiological relevance of each parameter set, and determining a user relevance of each parameter set according to the environmental relevance and the physiological relevance; wherein the environmental relevance indicates a degree of association between environmental data and the parameter set, and the physiological relevance indicates a degree of association between physiological data and the parameter set;

[0027] Specifically, for each user device group in the user device cluster, the operating parameters of all smart devices in the user device group are taken as a parameter set. Physiological data includes physiological data of the user, such as body temperature, heart rate data, respiratory rate data and body movement times; environmental data includes indoor temperature, indoor humidity, light, etc.

[0028] S400, obtaining current environmental data and physiological data, determining the user relevance of each parameter set based on the environmental data and physiological data, sorting the parameter sets in descending order of user relevance, and determining the user device groups corresponding to the parameter sets; selecting multiple parameter sets with the highest ranking and the user device groups corresponding to the multiple parameter sets to form a recommendation list;

[0029] Specifically, determine the environmental state of the current environmental data, and determine the physiological state of the current physiological data; for each parameter set, respectively determine the environmental correlation between the environmental state and the parameter set, respectively determine the physiological correlation between the physiological state and the parameter set, and calculate the user correlation of the parameter set according to the environmental correlation and the physiological correlation; sort each of the parameter sets in descending order of user correlation, and select multiple parameter sets with the highest rankings and user device groups corresponding to multiple parameter sets to form a recommendation list.

[0030] S500, obtaining a parameter set selected by a user from the recommendation list, determining a user device group corresponding to the parameter set, and controlling the corresponding user device group to operate according to the parameter set.

[0031] In some embodiments, the recommendation list is pushed to the smart terminal of the user, and the parameter set selected by the user on the smart terminal is obtained, or the parameter set selected by the user is obtained through voice interaction.

[0032] In this embodiment, by combining environmental data and physiological data, a user device group corresponding to the environmental data and the user's physiological data can be formed. By effectively sorting multiple user device groups, a recommended combination with strong scene adaptability is formed for users to choose from. This can match the user's personalized scene needs without the user having to make independent settings for each home. The user only needs to select a combination in the recommended list and make a simple modification, thereby improving the operational convenience of the smart parameter set and the user experience.

[0033] The present invention forms the most basic and extensive initial device group by collecting operation control records within multiple sampling periods; forms a user device cluster that is strongly related to the user based on the initial device group by obtaining the user's usage control records within the current sampling period, obtains the environmental state of the home environment and the physiological state of the user within the current sampling period, performs data analysis based on the current environmental state and the physiological state of the user, and refreshes the recommendation list regularly, which can adapt to the most recent environmental state and physiological state in terms of timeliness, and provide personalized intelligent control for the user in combination with the environmental state and the physiological state.

[0034] In some embodiments, clustering the smart devices in the smart home list into a plurality of initial device groups according to the operation control record includes:

[0035] S110, combining each smart device in the smart home list in pairs, calculating the difference in adjustment time between two smart devices in the combination as the time interval between the two smart devices, and associating two smart devices whose time interval is lower than a time interval threshold as a device pair;

[0036] It should be noted that if the operation records of two smart devices change, such as turning on or off, it can be considered that there is an association. Take two smart devices as a group, combine each smart device in the smart home list in pairs, and calculate the difference in the adjustment time of the two smart devices in the combination as the time interval between the two smart devices; compare the time interval with the time interval threshold to determine whether the two smart devices in the combination can form a device pair; the time interval threshold is set based on experience. Generally, when a user turns on or off two associated smart devices, the interval will not be too long. For example, the time interval threshold is set to 1 to 3 minutes. After determining the associated smart devices according to the adjustment time, the associated smart devices are formed into a device pair, so that multiple device pairs are preliminarily screened out based on the adjustment time.

[0037] S120, obtaining a distribution plan map including location information of each smart device in the smart home list, and determining an associated distance of each smart device in the smart home list according to the distribution plan map;

[0038] Specifically, the distribution plan can be to mark the location of each smart device in the floor plan, determine the room where each smart device is located in the floor plan, and then estimate the association distance between the smart devices based on the distance of the location of each room. For example, the association distance between two smart devices in the same room can be set to 1 meter, the association distance between smart devices in adjacent rooms can be set to 2 to 5 meters, and the association distance between smart devices in separate rooms can be set to 4 to 8 meters, and so on, and set it based on the actual situation.

[0039] S130, obtaining a start / stop time interval of two smart devices in a device pair, and performing association processing on the start / stop time interval of the device pair according to the association distance to obtain an association time;

[0040] Specifically, the time interval between the start and stop of each pair of smart devices is subtracted from the ratio of the associated distance and the walking speed to obtain the associated time, that is, the associated time = associated distance / walking speed. The associated time can be used to exclude the time consumed by the user when walking and identify the associated smart devices.

[0041] S140, obtaining a time weight correspondence table, the time weight correspondence table including a plurality of intervals, each interval having a corresponding time weight, and determining the time weight of the device pair according to the interval in which the associated time is located; wherein the size of the time weight is inversely correlated with the size of the interval;

[0042] Specifically, the value range of the time weight is (0, 1). The smaller the interval value, the greater the time weight. For example, when the interval is (0, 10 seconds), the time weight is 0.8; when the interval is (10 seconds, 20 seconds), the time weight is 0.6, and so on. When the interval is (60 seconds, Th), the time weight is 0.1, and Th is the time interval threshold.

[0043] S150, counting the number of associations of each device pair and the time weight of each association within multiple sampling periods; determining the association weight of each device pair according to the time weight and the number of associations;

[0044] S160, retaining device pairs whose association weights are greater than an association weight threshold, connecting the retained device pairs to obtain at least one initial device group, and removing duplicates from the obtained initial device group to form an initial device cluster.

[0045] The association weight reflects the degree of association between each smart device in the entire smart home list. If the association between two smart devices is relatively normal, it means that the two smart devices can be aggregated to achieve a corresponding scenario requirement; by counting the clusters of aggregated smart devices, the initial device groups corresponding to multiple scenarios can be obtained.

[0046] In some embodiments, the association weight of the device pair is calculated according to the following formula:

[0047]

[0048] Wherein, n represents the total number of sampling cycles, i represents the number of sampling cycles, j represents the number of times the device pair is associated, k represents the number of the device pair, K represents the total number of device pairs, mi represents the total number of times the device pair is associated in the i-th sampling cycle, mij represents the number of times the device pair is associated in the i-th sampling cycle, wij represents the time weight of the j-th association of the device pair in the i-th sampling cycle, wi represents the sampling weight of the i-th sampling cycle, and Wk represents the association weight of the k-th device pair.

[0049] Specifically, the sampling weight ranges from (0, 1), and the sampling weight is inversely correlated with the time interval between the sampling period and the current time. The longer the sampling period is from the current time, the smaller the sampling weight is; wi = e ti ,ti represents the number of intervals between the ith sampling period and the current period. The number of intervals between the most recent sampling period and the current period is 0. The value range of the calculated association weight is (0, 1).

[0050] In some embodiments, in S200, the acquiring of a usage control record of the user in the current sampling period, and determining a user device cluster controlled by the user from the initial device group according to the usage control record, includes:

[0051] S210, obtaining the adjustment time of the user controlling the smart device in the current sampling period, and determining the smart device whose operating parameters change within a time interval threshold after the adjustment time as the associated device of the smart device;

[0052] S220, searching for a device pair where the smart device and the associated device are located in the initial device group, and forming a user device group with the found device pairs;

[0053] S230: Form a user equipment cluster corresponding to the user by using a user equipment group formed in a current sampling period.

[0054] Specifically, the time when the user performs a control action on the smart device is taken as the adjustment time. During the adjustment time, the user controls at least one smart device. Subsequently, if other smart devices are controlled within a time interval threshold, the smart device and the associated devices must have formed a device pair in the initial device group. By searching whether there are other device pairs between the smart device and the associated devices, the found device pairs and the device pairs formed by the smart device and the associated devices are combined to obtain a user device group. The user device groups formed in each sampling period may be repeated. By deduplication, the user device cluster corresponding to the user contains at least one user device group.

[0055] In some embodiments, in S300, determining the environmental relevance and physiological relevance of each parameter set, and determining the user relevance of each parameter set according to the environmental relevance and physiological relevance, includes:

[0056] S310, obtaining environmental data in a current sampling period, dividing the environmental data into multiple environmental data intervals, each environmental data interval corresponding to an environmental state, corresponding a parameter set in the same environmental data interval to an environmental state, obtaining multiple environmental states, a parameter set corresponding to each environmental state, and a user device group executing the parameter set;

[0057] Specifically, one or more environmental data can be selected. For example, if indoor temperature is selected as environmental data, the indoor temperature is divided into multiple indoor temperature intervals; if indoor temperature, indoor humidity and light are selected as environmental data, the indoor temperature is divided into multiple indoor temperature intervals, the indoor humidity is divided into multiple indoor humidity intervals, and the light is divided into multiple illumination intervals; then they are combined into multiple environmental data intervals, and the multiple environmental data intervals correspond to the multiple environmental states one by one.

[0058] S320, for each parameter set, determining the environmental correlation between the parameter set and each environmental state;

[0059] S330, obtaining physiological data of the user in the current sampling period, dividing the physiological data into multiple physiological data intervals, each physiological data interval corresponds to a physiological state, and corresponding a parameter set of the same physiological data interval to a physiological state, thereby obtaining multiple physiological states and a parameter set corresponding to each physiological state;

[0060] Specifically, one or more physiological data can be selected. For example, if the perceived temperature is selected as the environmental data, the perceived temperature is divided into multiple perceived temperature intervals; if the perceived temperature, heart rate data, and respiratory rate data are selected together as the environmental data, the perceived temperature is divided into multiple perceived temperature intervals, the heart rate data is divided into multiple heart rate intervals, and the respiratory rate data is divided into multiple respiratory rate intervals; then multiple physiological data intervals are formed according to the combinations that appear.

[0061] The physiological state reflects the difference between users in different physiological states. When a user is in different physiological states, there will be greater or lesser differences in physiological data such as the perceived temperature, heart rate data, respiratory rate data, and body movement times. The physiological data can be collected from the human body through wearable devices. The present invention collects one or more of the user's perceived temperature, heart rate data, respiratory rate data, body movement data, and other data as the physiological data of the target object according to the actual application scenario.

[0062] S340, for each parameter set, determining the physiological correlation between the parameter set and each physiological state;

[0063] S350: Determine the user relevance of each parameter set according to the environmental relevance and the physiological relevance.

[0064] In some embodiments, in S320, for each parameter set, determining the environmental correlation between the parameter set and each environmental state includes:

[0065] S321, establishing a parameter set and an environment state set, wherein the parameter set includes all parameter sets executed by each user equipment group, and the environment state set includes a plurality of the environment states;

[0066] Specifically, for each environmental state, it may correspond to one or more user device groups, and each user device group may have one or more parameter sets. By counting the user device groups corresponding to each environmental state and the parameter sets of the user device groups, the user device groups corresponding to the environmental state and the parameter sets of the user device groups can be obtained, and then all parameter sets and environmental states can be corresponded. It can be understood that according to this correspondence, the user device group corresponding to each parameter set can be determined.

[0067] S322, determining a parameter set corresponding to each environmental state, and for each parameter set, determining an environmental relevance of executing the parameter set in each of the environmental states based on the parameter set and the environmental state set;

[0068] The calculation formula of the environmental correlation is:

[0069]

[0070] Wherein, the environment state set is represented as S, the parameter set is represented as A, s represents the environment state in the environment state set S, a represents the parameter set in the parameter set A, E(a|s) represents the environmental correlation between the parameter set a and the environment state s, C(a|s) is the first selection probability, which represents the probability of selecting the parameter set a under the environment state s; R(s,a) represents the first feedback value obtained by executing the parameter set a under the environment state s, γ is the discount factor, It represents the environmental correlation between the parameter set a and the environmental state s calculated in the previous sampling period. The environmental correlation of the first sampling period is set to 1.

[0071] By introducing the environmental correlation calculated in the previous sampling period, the consistency of environmental correlation is reflected. Combined with the first selection probability and the first feedback value, the adjustment of environmental correlation by real-time interaction in the current sampling period is reflected. The obtained environmental correlation can comprehensively reflect the current user feedback. The present value of the first feedback value in the future is calculated by introducing the discount factor γ, 0<γ<1.

[0072] The first selection probability is calculated by the following formula:

[0073]

[0074] Among them, η 1 is an adjustable parameter greater than 0, exp represents the exponential function, Q(s,a) represents the first association probability between parameter set a and environment state s, Q(s j ,a) represents parameter set a and environment state s j The first association probability of , j is the number of the environment state, s j is the jth environment state in the environment state set S, s jis a variable;

[0075] The first association probability is calculated by the following formula:

[0076]

[0077] Among them, n(s j ,a) represents parameter set a in environment state s j n(s,a) represents the number of times parameter set a is executed under environment state s;

[0078] The first association probability reflects the correlation ratio between parameter set a and environmental state s, which is the ratio of the number of times parameter set a is executed under environmental state s to the number of times parameter set a is executed under each environmental state in the environmental state set S. The larger the ratio, the larger the first association probability, indicating that the execution of parameter set a by the smart devices in the user device group is strongly correlated with the environmental state s.

[0079] The first feedback value is calculated by the following formula:

[0080]

[0081] Where n(s,a) represents the number of times parameter set a is executed under environment state s; n(s,a i ) means executing parameter set a in environment state s i The number of times, a i is the i-th parameter set in parameter set A, a i is a variable, i is the number of the parameter set in parameter set A.

[0082] Specifically, an environment state set S and a parameter set A are set. The environment state set S includes indoor temperature, humidity, and light intensity; the parameter set A includes a parameter set for controlling the operating parameters of smart devices such as adjusting the air conditioning temperature, lighting, and adjusting the opening and closing of curtains. The first feedback function R(s,a) is used to evaluate the user's feedback when executing the parameter set a under the environment state s. The feedback function reflects the feedback of the user's choice of agreement or opposition after the execution of the parameter set, and reflects the environmental correlation between the executed parameter set and the scene. Represents the total number of times the user executes each parameter set under the environment state s; in the calculation formulas of the first selection probability, the first association probability, and the first feedback value, the denominator is a normalization factor to ensure that the sum of the probabilities of all parameter sets is 1.

[0083] The degree of correlation between the operating parameters and the environmental data is reflected by the environmental correlation. The greater the environmental correlation, the closer the correlation between the parameter set a under the environmental state s. The parameter set closely related to the environmental data can be obtained through the environmental correlation. The parameter set suitable for the user can be screened out based on the environmental data, and the parameter set suitable for the user can be preliminarily screened out from the environmental state. By updating the environmental correlation under the current sampling period, we can learn how to better meet the needs of users and improve the level of intelligence in the continuous interaction with the environment.

[0084] In some embodiments, in S340, for each parameter set, determining the physiological correlation between the parameter set and each physiological state includes:

[0085] S341, establishing a physiological state set, wherein the physiological state set includes a plurality of the physiological states;

[0086] S342, determining a parameter set corresponding to each of the physiological states, and for each parameter set, determining a physiological correlation degree of executing the parameter set in each of the physiological states based on the parameter set and the physiological state set;

[0087] Specifically, for each physiological state, it may correspond to one or more user device groups, and each user device group may have one or more parameter sets. By counting the user device group corresponding to each physiological state and the parameter set of the user device group, the user device group corresponding to the physiological state and the parameter set of the user device group can be obtained, and then all parameter sets are corresponded to the physiological state. It can be understood that according to this correspondence, the user device group corresponding to each parameter set can be determined.

[0088] The calculation formula of the physiological correlation is:

[0089] E(a|p)=C(a|p)R(p,a);

[0090] Wherein, P is a physiological state set, p is a physiological state in the physiological state set P, E(a|p) represents the physiological correlation between parameter set a and physiological state s, C(a|p) is the second selection probability, which represents the probability of executing parameter set a under physiological state p; R(p,a) represents the second feedback value obtained by executing parameter set a under physiological state p;

[0091] The second choice probability is calculated by the following formula:

[0092]

[0093] Among them, η 2 is an adjustable parameter greater than 0, Q(p,a) represents the second association probability between parameter set a and physiological state p, a iis the set of parameters in set A, a i is a variable, Q(p k ,a) represents parameter set a and physiological state p k The second association probability, k is the number of the environment state, p k is the kth environment state in the environment state set P, p k is a variable;

[0094] The second association probability is calculated by the following formula:

[0095]

[0096] Among them, n(p k ,a) indicates that in the physiological state p k n(p,a) represents the number of times parameter set a is executed under physiological state p;

[0097] The second association probability reflects the correlation ratio between parameter set a and physiological state s, which is the ratio of the number of times parameter set a is executed under physiological state s to the number of times parameter set a is executed under each physiological state in the physiological state set S. The larger the ratio, the larger the second association probability, indicating that the execution of parameter set a by the smart devices in the user device group is strongly correlated with the physiological state s.

[0098] The second feedback value is calculated by the following formula:

[0099]

[0100] Where n(p,a) represents the number of times parameter set a is executed under physiological state p; n(p,a i ) represents the execution of parameter set a under physiological state p i The number of times.

[0101] In some embodiments, the user association degree of the parameter set is calculated by the following formula:

[0102] R(a)=λE(a|s)+E(a|p);

[0103] Among them, R(a) represents the user association of parameter set a, s represents the environmental state, E(a|s) represents the environmental association of executing parameter set a under environmental state s, p represents the physiological state, E(a|p) represents the physiological association of executing parameter set a under physiological state p, λ represents the adjustment weight, 0.1<λ<1.

[0104] If the environmental correlation is relatively small, it means that the correlation between the operating parameters and the environmental data is low, and the influence of the environmental data can be ignored; if the environmental correlation is relatively large, it means that the correlation between the operating parameters and the environmental data is high, which means that the parameter set and the environmental data are strongly correlated, and the corresponding user equipment group can be triggered to adjust to the parameter set;

[0105] If the physiological correlation is relatively small, the correlation between the operating parameters and the physiological data is low, and the influence of the physiological data can be ignored; if the physiological correlation is relatively large, the correlation between the operating parameters and the physiological data is high, indicating that the parameter set is strongly correlated with the physiological data, and the corresponding user device group can be triggered to adjust to the parameter set;

[0106] If the values ​​of the environmental correlation and the physiological correlation are both within the corresponding value ranges, the physiological correlation is used as the main influencing factor, and the environmental correlation is used as an auxiliary to make a joint judgment to determine whether to trigger the corresponding user equipment group to operate according to the parameter set.

[0107] In addition, refer to Figure 2 An embodiment of the present invention further provides a smart home control system, the system comprising:

[0108] at least one processor;

[0109] at least one memory for storing at least one program;

[0110] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0111] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0112] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor or controller, for example, by a processor in the above-mentioned electronic device embodiment, so that the above-mentioned processor can execute the smart home control method in the above-mentioned embodiment.

[0113] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0114] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CDROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0115] The above is a specific description of the preferred implementation of the present disclosure, but the present disclosure is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present disclosure. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present disclosure.

Claims

1. A smart home control method, characterized in that: The method comprises the following steps: S100, obtaining operation control records of each smart device in the smart home list within multiple sampling periods, and clustering each smart device in the smart home list into multiple initial device groups according to the operation control records; wherein, for each smart device in the smart home list, the operation control records include operation parameters of the smart devices and adjustment time of the operation parameters; S200, obtaining a usage control record of a user in a current sampling period, and determining a user device cluster controlled by the user from the initial device group according to the usage control record; wherein the user device cluster includes at least one user device group, and the user device group includes at least one device pair; the usage control record includes environmental data and physiological data corresponding to the adjustment time of the user controlling the smart device; S300, forming a parameter set from the operating parameters of each user device group in the user device cluster, determining an environmental relevance and a physiological relevance of each parameter set, and determining a user relevance of each parameter set according to the environmental relevance and the physiological relevance; wherein the environmental relevance indicates a degree of association between environmental data and the parameter set, and the physiological relevance indicates a degree of association between physiological data and the parameter set; S400, obtaining current environmental data and physiological data, determining the user relevance of each parameter set based on the environmental data and physiological data, sorting the parameter sets in descending order of user relevance, and determining the user device groups corresponding to the parameter sets; selecting multiple parameter sets with the highest ranking and the user device groups corresponding to the multiple parameter sets to form a recommendation list; S500, obtaining a parameter set selected by a user from the recommendation list, determining a user device group corresponding to the parameter set, and controlling the corresponding user device group to operate according to the parameter set.

2. A smart home control method according to claim 1, characterized in that: The step of clustering the smart devices in the smart home list into a plurality of initial device groups according to the operation control record includes: S110, calculating the difference between the adjustment times of two smart devices in the combination as the time interval between the two smart devices, and associating two smart devices whose time interval is lower than the time interval threshold as a device pair; S120, obtaining a distribution plan map including location information of each smart device in the smart home list, and determining an associated distance of each smart device in the smart home list according to the distribution plan map; S130, obtaining a start / stop time interval of two smart devices in a device pair, and performing association processing on the start / stop time interval of the device pair according to the association distance to obtain an association time; S140, obtaining a time weight correspondence table, the time weight correspondence table including a plurality of intervals, each interval having a corresponding time weight, and determining the time weight of the device pair according to the interval in which the associated time is located; wherein the size of the time weight is inversely correlated with the size of the interval; S150, counting the number of associations of each device pair and the time weight of each association within multiple sampling periods; determining the association weight of each device pair according to the time weight and the number of associations; S160, retaining device pairs whose association weights are greater than an association weight threshold, connecting the retained device pairs to obtain at least one initial device group, and removing duplicates from the obtained initial device group to form an initial device cluster.

3. A smart home control method according to claim 2, characterized in that: The association weight of the device pair is calculated according to the following formula: ； Wherein, n represents the total number of sampling cycles, i represents the number of sampling cycles, j represents the number of times the device pair is associated, k represents the number of the device pair, K represents the total number of device pairs, mi represents the total number of times the device pair is associated in the i-th sampling cycle, mij represents the number of times the device pair is associated in the i-th sampling cycle, wij represents the time weight of the j-th association of the device pair in the i-th sampling cycle, wi represents the sampling weight of the i-th sampling cycle, and Wk represents the association weight of the k-th device pair.

4. The smart home control method according to claim 1, characterized in that: The obtaining of the usage control record of the user in the current sampling period, and determining the user device cluster controlled by the user from the initial device group according to the usage control record, includes: S210, obtaining the adjustment time of the user controlling the smart device in the current sampling period, and determining the smart device whose operating parameters change within a time interval threshold after the adjustment time as the associated device of the smart device; S220, searching for a device pair where the smart device and the associated device are located in the initial device group, and forming a user device group with the found device pairs; S230: Form a user equipment cluster corresponding to the user by using a user equipment group formed in a current sampling period.

5. The smart home control method according to claim 1, characterized in that: The step of determining the environmental relevance and the physiological relevance of each parameter set, and determining the user relevance of each parameter set according to the environmental relevance and the physiological relevance, comprises: S310, obtaining environmental data in a current sampling period, dividing the environmental data into multiple environmental data intervals, each environmental data interval corresponding to an environmental state, corresponding a parameter set in the same environmental data interval to an environmental state, obtaining multiple environmental states, a parameter set corresponding to each environmental state, and a user device group executing the parameter set; S320, for each parameter set, determining the environmental correlation between the parameter set and each environmental state; S330, obtaining physiological data of the user in the current sampling period, dividing the physiological data into multiple physiological data intervals, each physiological data interval corresponds to a physiological state, and corresponding a parameter set of the same physiological data interval to a physiological state, thereby obtaining multiple physiological states and a parameter set corresponding to each physiological state; S340, for each parameter set, determining the physiological correlation between the parameter set and each physiological state; S350: Determine the user relevance of each parameter set according to the environmental relevance and the physiological relevance.

6. A smart home control method according to claim 5, characterized in that: The step of determining, for each parameter set, the degree of environmental association between the parameter set and each environmental state comprises: S321, establishing a parameter set and an environment state set, wherein the parameter set includes all parameter sets executed by each user equipment group, and the environment state set includes a plurality of the environment states; S322, determining a parameter set corresponding to each environmental state, and for each parameter set, determining an environmental relevance of executing the parameter set in each of the environmental states based on the parameter set and the environmental state set.

7. A smart home control method according to claim 6, characterized in that: For each parameter set, determining the physiological correlation between the parameter set and each physiological state includes: S341, establishing a physiological state set, wherein the physiological state set includes a plurality of the physiological states; S342, determining a parameter set corresponding to each of the physiological states, and for each parameter set, determining a physiological correlation of executing the parameter set under each of the physiological states based on the parameter set and the physiological state set.

8. A smart home control method according to claim 7, characterized in that: The user association degree of the parameter set is calculated by the following formula: R(a)=λE(a|s)+E(a|p); Where R(a) represents the user relevance of parameter set a, s represents the environmental state, E(a|s) represents the environmental relevance of executing parameter set a under environmental state s, p represents the physiological state, and E(a|p) represents the physiological relevance of executing parameter set a under physiological state p. Indicates adjustment weight, 0.1< <1.

9. A smart home control system, characterized in that: The system comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the smart home control method as described in any one of claims 1 to 8.

Images