Smart host-based whole-house smart control system

Abstract

The application relates to the technical field of intelligent control, in particular to a whole-house intelligent control system based on an intelligent host. The system comprises an operation data acquisition module, which is used for acquiring control operation records of each intelligent device in the whole-house intelligent control system and constructing a control operation vector of each intelligent device; a privatization analysis module, which is used for determining a privatization coefficient of each intelligent device; a position analysis module, which is used for constructing a position change vector of each intelligent device; a recognition degree analysis module, which is used for determining an operation change amplitude of each intelligent device; in combination with the privatization coefficient, the position change vector and the operation change amplitude, the personal behavior recognition degree of each intelligent device is determined; and a device parameter determination module, which is used for carrying out spline interpolation processing between each two operations, using the processed data, extracting a user portrait and acquiring optimal control parameters of the corresponding intelligent device. The application generates a more personalized and effective intelligent home control strategy.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a whole-house intelligent control system based on an intelligent host. Background Art

[0002] The existing concept of smart home refers to using the house as a platform, utilizing integrated wiring technology, network communication technology, security technology, automatic control technology, and audio and video technology to integrate home life-related equipment or facilities, build an efficient management system for residential facilities and family schedule affairs, improve home safety, convenience, comfort, and artistry, and achieve an environmentally friendly and energy-saving living environment. However, if today's whole-house smart home control is only controlled according to user habits without considering the scenarios of multiple users performing home control, the accuracy and applicability of personal and home smart control will be reduced.

[0003] Since existing user behavior data is usually collected through the operation values ​​of smart home devices, this limitation will have a significant impact on behavior discrimination and user portrait extraction, because relying solely on the operation values ​​of smart devices for analysis may lead to a one-sided understanding of the user's true behavior. Many key factors used to distinguish multiple user identity information cannot be directly captured, resulting in the whole-house smart control system having a low adaptability problem when controlling smart devices. Summary of the Invention

[0004] In order to solve the technical problem that the whole-house intelligent control system has low adaptability when controlling intelligent devices, the purpose of the present invention is to provide a whole-house intelligent control system based on an intelligent host. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a whole-house intelligent control system based on an intelligent host, the system comprising the following modules:

[0006] The operation data acquisition module is used to obtain the control operation records of each smart device in the whole-house smart control system and construct the control operation vector of each smart device;

[0007] A personalization analysis module, used to determine the personalization coefficient of each smart device based on different control operation records;

[0008] The location analysis module is used to mark the areas where smart devices in the whole-house smart control system are located according to the functional areas of the whole house and construct the location change vector of each smart device;

[0009] a recognition degree analysis module, configured to determine an operation change range based on the operation behavior of each smart device; and determine the individual behavior recognition degree of each smart device by combining the personalization coefficient, the position change vector, and the operation change range;

[0010] The device parameter determination module is used to determine the number of interpolable data points between two operations based on the operating behavior of each smart device between the two operations and the recognition of individual behavior; based on the number of interpolable data points, spline interpolation processing is performed between each two operations, and the processed data is used to extract the user portrait and obtain the optimal control parameters of the smart device corresponding to the user.

[0011] In a second aspect, a whole-house intelligent control method based on an intelligent host is provided, the method comprising the following steps:

[0012] Obtain the control operation records of each smart device in the whole-house smart control system and construct the control operation vector of each smart device;

[0013] Determine the personalization coefficient of each smart device based on different control operation records;

[0014] According to the functional areas of the whole house, the smart devices in the whole house intelligent control system are marked in their respective areas, and the position change vector of each smart device is constructed;

[0015] Determining an operation change range based on the operation behavior of each smart device; and determining a personal behavior recognition degree of each smart device by combining the personalization coefficient, the position change vector, and the operation change range.

[0016] Based on the operating behavior of each smart device between two operations and the recognition of personal behavior, the number of interpolable data points between two operations is determined; based on the number of interpolable data points, spline interpolation processing is performed between each two operations, and the processed data is used to extract user portraits and obtain the optimal control parameters of the smart device corresponding to the user.

[0017] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0019] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute various possible implementations of the first aspect.

[0020] The embodiments of the present invention have at least the following beneficial effects:

[0021] In order to solve the technical problem that only the operation values ​​in the operation behavior of smart devices are analyzed, which leads to low adaptability of the whole-house smart control system when controlling smart devices. The present invention combines three factors: different control operations of different smart devices, changes in the position of smart devices in different functional areas, and the operation behavior of smart devices to determine the personal behavior recognition of smart devices; the location factor of the smart device is combined because the user's location factor also has an important impact on the behavior pattern of the smart device, such as the activity frequency and preference in different functional areas may have obvious differences. According to the operation behavior of each smart device between two operations and the personal behavior recognition, the number of interpolable data points between the two operations is determined. Based on the number of interpolable data points, spline interpolation processing is performed between each two operations. The processed data is used to extract user profiles and obtain the optimal control parameters of the corresponding smart devices. The present invention combines the dynamic changes of user location to improve the accuracy of user behavior recognition and user profile analysis, which helps to generate more personalized and effective smart home control strategies, thereby optimizing user experience and improving the efficiency of smart host analysis and device operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0023] Figure 1 A system block diagram of a whole-house intelligent control system based on an intelligent host provided by one embodiment of the present invention;

[0024] Figure 2 A flowchart of a whole-house intelligent control method based on an intelligent host provided by one embodiment of the present invention;

[0025] Figure 3 A schematic structural diagram of a computer device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation method, structure, characteristics and effects of the whole-house intelligent control system based on the intelligent host proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0027] In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0028] In the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0030] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0031] The embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0032] The specific scheme of the whole-house intelligent control system based on the intelligent host provided by the present invention is described in detail below with reference to the accompanying drawings. Example 1

[0033] See also Figure 1 , which shows a system block diagram of a whole-house intelligent control system based on an intelligent host provided by an embodiment of the present invention. The system includes the following modules:

[0034] The operation data acquisition module 10 is used to obtain the control operation record of each smart device in the whole-house smart control system and construct the control operation vector of each smart device.

[0035] In a multi-room smart furniture environment with smart devices installed, the information collection process for multiple users can be divided into the following steps:

[0036] (1) Install the required smart devices in each room, such as smart lamps, smart air conditioners, smart cameras, and smart speakers, and connect each smart home device to the central smart host. The whole-house smart control system is composed of all the smart devices in the multi-room smart furniture environment and the central smart host.

[0037] (2) Configure the network connection between the central intelligent host and each intelligent device to ensure that each device can transmit data in real time.

[0038] (3) Users register through the smart home application and provide basic user information, such as user nickname. The smart home application can use internal numbering of the local area network, such as S01, S02, etc., for identity identification within the local area network.

[0039] (4) Use identity recognition technology, such as mobile phone Bluetooth, to distinguish different users.

[0040] (5) Record device operations and user interactions with each smart device, such as turning lights on and off, adjusting air conditioning temperature, playing music, etc. This data can be automatically collected from each smart device through the central smart host.

[0041] (6) Perform timestamp recording, and record each operation of each smart device and each location change of the smart device with a timestamp.

[0042] (7) The collected user behavior data and location information are transmitted in real time to the central database of the central intelligent host or cloud storage.

[0043] (8) Ensure the security of data transmission and use encryption technology to protect user privacy.

[0044] Because user behavior can only be collected from information received by smart devices, it can affect behavior identification and user profile extraction. This single-minded data collection method may lead to neglecting diverse user behaviors, which in turn affects the integrity of user profiles. For example, the frequency of a user's activities in a particular room may be an important factor influencing their preferences. However, if this behavior is not effectively recorded, the user profile will be inaccurate. Therefore, a spline interpolation algorithm is needed to determine the degree of user behavior recognition.

[0045] Therefore, in the embodiment of the present invention, the personalized attributes of the smart device are first analyzed, and then the single behavior identification characteristics of the behavior on the smart device are analyzed. Then, the number of interpolable data points of the spline interpolation is adjusted in combination with the location information. Finally, the result after the final spline interpolation processing is subjected to user portrait analysis, marked as different user behaviors, and corresponding smart device control is performed.

[0046] First, the operation records of each smart device in the whole-house smart control system are obtained and the operation behavior vector of each smart device is constructed. The control operation records of smart devices include various control behaviors: central smart host control, smart device control, and manual control.

[0047] Centralized intelligent host control can also be understood as users controlling smart devices through the central intelligent host. For example, someone in the living room calls Xiao Ai to turn on the fan. Here, Xiao Ai is the central intelligent host, and the fan is the smart device controlled by the central intelligent host. Smart device control is remotely controlling a smart device through a smartphone. Manual control is directly controlling a smart device using the controller of the smart device, such as controlling a smart device through an air conditioner remote control.

[0048] Different types of control behaviors are numbered, for example, the number corresponding to the central intelligent host control is set as A01, the number corresponding to the intelligent device control is set as A02, and the number corresponding to the manual control is set as A03; accordingly, all types of control behaviors in each historical period are counted, that is, all control operation records in each historical period are counted, and the control operation vector of each intelligent device is constructed according to the order of the control operation records in each historical period. ,For example .

[0049] It should be noted that each smart device has its own corresponding control operation vector for different historical time periods. In the embodiment of the present invention, the length of the historical period is set to 7 days. In other embodiments, the length of the historical period can be adjusted by the implementer based on actual conditions. It should be noted that for the current moment, the 7 days before the current moment are the first historical period, and the 7 days before the first historical period are the second historical period. The historical period corresponding to each day is continuously updated.

[0050] The personalization analysis module 20 is used to determine the personalization coefficient of each smart device according to different control operation records.

[0051] Since the whole-house intelligent control system includes multiple operable intelligent devices in addition to the central intelligent host, as subsidiary controllable terminals, some or all of the devices can be intelligently controlled according to their permissions. Therefore, the behavioral data of some users is collected through the operation records of smart home devices, and then analyzed from the local area network where the whole-house intelligent devices are located. Whether the user operation behavior information of the intelligent devices belongs to the same user will be affected by the nature of the devices themselves. For example, mobile phones, computers and other devices have more obvious private attributes, that is, they will be controlled by the same user for a long time. Correspondingly, switches, lamps, etc. are more inclined to be used when there is a common need. Therefore, it is necessary to define the personal attributes of the devices based on the performance of the data collected by the devices.

[0052] For smart devices, the types of user manipulations they receive are limited, and their control behaviors tend to be distributed in clusters based on the number of users. Therefore, a multidimensional vector space is constructed with each control operation vector The type of control behavior corresponding to the element of is taken as a single dimension, and the proportion of the number of control behaviors in the control operation vector is taken as the numerical value of the dimension.

[0053] First, the number of registered users N in the whole-house intelligent control system is obtained. The number of registered users here refers to the number of users in the same whole-house intelligent control system.

[0054] Based on the similarity between different control operation vectors, the control operation vectors of all smart devices are clustered to obtain operation clusters. The control operation vectors include control operation vectors acquired over multiple historical time periods; the control operation records include: central intelligent host control, smart device control, and manual control. In this embodiment of the present invention, the similarity between different control operation vectors can be calculated using cosine similarity.

[0055] Compare the difference between the number of operation clusters and the number of registered users to obtain the user's behavioral interleaving feature value. More specifically, calculate the difference between the number of operation clusters and the number of registered users as the user's behavioral interleaving feature value.

[0056] When the number of operation clusters exceeds the number of registered users, the largest operation cluster is considered to be a cluster of multi-user behavior, and the remaining operation clusters are the performance of a single user on the terminal device. The greater the number of operation clusters exceeds the number of registered users, the more obvious the data aggregation characteristics formed by the multi-user behavior interweaving.

[0057] The corresponding personalization attribute of a single smart device is represented by the proportion of control operation vectors of the smart device under different operation clusters. The more the operation clusters belong to the same operation cluster and the more obvious the user behavior intersection is in the overall clustering performance, the higher the personalization coefficient.

[0058] Taking any smart device as the target smart device, calculate the proportion of control operation vectors corresponding to the target smart device in each operation cluster as the degree of personalization;

[0059] The personalization coefficient of each smart device is determined by combining the behavioral interleaving characteristic value and the personalization degree, wherein both the behavioral interleaving characteristic value and the personalization degree are positively correlated with the personalization coefficient; and the personalization coefficient is a normalized value.

[0060] As a preferred embodiment of the present invention, a product value of the behavior interleaving characteristic value and the personalization degree is calculated as a personalization coefficient of each smart device.

[0061] In some embodiments, As an example, the target smart device is a smart device. Personalization coefficient of smart devices The calculation formula is: in, is the normalization function; is the number of operation clusters; is the number of registered users; Interleave feature values ​​for user behavior; is the normalization function; For the Smart devices in the The number of control operation vectors in an operation cluster; For the The total number of control operation vectors in the operation cluster; That is the first Smart devices in the The proportion of control operation vectors in the operation cluster, that is, The degree of personalization of a smart device.

[0062] in, The larger the value of , the more obvious the smart device is controlled by a single user during daily use, the greater the probability of its personalization, and the larger the corresponding personalization coefficient.

[0063] The location analysis module 30 is used to mark the areas where the smart devices in the whole-house smart control system are located according to the functional areas of the whole house, and to construct a location change vector for each smart device.

[0064] According to the existing functional areas in the whole-house intelligent control system, multiple rooms are divided into functional areas such as bedroom, living room and study. The location areas of all the smart devices in the whole house are marked as corresponding functional areas. Since some devices are movable, the functional area of ​​the area where the smart device is located at each sampling moment is marked. The functional area can be changed. For example, the functional area of ​​the living room is marked as , the functional area of ​​the restaurant is marked with , the functional area of ​​the study is marked with .

[0065] Obtain the position change path sequence of a single smart device in a functional area and de-name it, retaining only the corresponding label number of the functional area to represent the position change relationship. Construct a position change vector based on the label numbers of the functional areas where the smart device is located in time sequence. The elements in the position change vector are also the label numbers of the functional areas where the smart device is located. For example, the position change vector .

[0066] For each functional area of ​​a smart device, the lower the personalization coefficient, the greater the possibility of multi-user interaction in the user operation on the smart device. Correspondingly, from the perspective of operation changes, the more common the differences in user behavior habits corresponding to a single operation, the lower its credibility, that is, the lower the recognition of the single behavior at the device location.

[0067] The recognition analysis module 40 is used to determine the operation change range based on the operation behavior of each smart device; and to determine the personal behavior recognition of each smart device by combining the personalization coefficient, the position change vector and the operation change range.

[0068] For the differences in user behavior habits for a single operation, the significance of the specific operation amplitude compared with the previous one is used here. For example, for the change in the temperature of the air conditioner, the greater the temperature change, the stronger the significance of the operation amplitude.

[0069] Take any smart device as the target smart device, calculate the difference between the operation value corresponding to the current user operation and the previous user operation of the target smart device, standardize the difference value, and obtain the operation change amplitude corresponding to the current user operation of the target smart device; wherein, the operation value corresponding to the user operation is the control value when the user controls the smart device. For example, for a smart air conditioner, the operation value is the adjusted temperature value. It should be noted that for smart lamps, different lighting of the smart lamps can be set as different operation values, for example, setting warm light as , neutral light is , cold light is .

[0070] In this embodiment of the present invention, the difference between the operation values ​​corresponding to the current user operation and the previous user operation on the target smart device is the absolute value of the difference between the operation values ​​corresponding to the current user operation and the previous user operation on the target smart device. The normalization process is a normalization process, and in this embodiment of the present invention, a maximum-minimum normalization algorithm can be used to normalize the data.

[0071] After obtaining the personalization coefficient, the position change vector, and the operation change range, the personal behavior recognition degree of each smart device is determined by combining the personalization coefficient, the position change vector, and the operation change range.

[0072] Specifically: taking any user operation as a target user operation, determining the position similarity based on the similarity between the position change vector corresponding to the target user operation and the standard position change vector of the smart device;

[0073] The standard position change vector is the vector obtained by averaging all historical position change vectors of the smart device. It should be noted that position change vectors of different lengths are averaged after optimal matching using a dynamic regularization algorithm.

[0074] Based on the personalization coefficient, operation change range and location similarity, the personal behavior recognition of each smart device under the target user's operation is determined. Specifically: the product of the personalization coefficient and the operation change range is used as the numerator, the location similarity is used as the denominator, and the normalized value of the ratio formed by the numerator and denominator is used as the personal behavior recognition.

[0075] In some embodiments, on the smart device For example, the first user operation on the smart device Personal behavior recognition of user operations The calculation formula is: ;in, No. The personalization coefficient of each smart device; For the On smart devices The magnitude of the change in the user's operation; For the The first smart device The position change vector corresponding to the user operation; For the The mean of the position change vectors of the smart devices.

[0076] The larger the value of personal behavior recognition, the less the smart device is affected by data collection during the user operation.

[0077] The device parameter determination module 50 is used to determine the number of interpolable data points between two operations based on the operating behavior of each smart device between the two operations and the personal behavior recognition; based on the number of interpolable data points, spline interpolation processing is performed between each two operations, and the processed data is used to extract the user portrait and obtain the optimal control parameters of the corresponding smart device.

[0078] In order to analyze the collected data of each smart device in the whole-house intelligent control system for collaborative filtering, the data is processed to realize the construction of user portrait, and the central intelligent host realizes the recognition degree of the user corresponding device behavior, so in the embodiment of the application, the single personal behavior recognition degree of the obtained smart device in different operations is used to adjust and process the user operation behavior of the obtained original data, through the data difference, the data set is expanded, the smoothness of the user operation on the single smart device is improved, the accuracy of the obtained user portrait is enhanced, and the whole-house intelligent device control operation is more accurate and humanized.

[0079] For the target smart device, the difference between the operation values of the target smart device between two operations is calculated as the operation behavior difference, the difference between the personal behavior recognition degrees of the target smart device between two operations is calculated as the recognition degree difference, and the value obtained by taking the integer part of the ratio of the operation behavior difference and the recognition degree difference is taken as the number of interpolation data points between two operations of the target smart device.

[0080] Taking the user behavior operation data interpolation on the first smart device as an example, the specific values between any two operation data on the original operation data are extracted, which are respectively represented as the operation value of the first smart device at the first user operation and the operation value of the first smart device at the first user operation.

[0081] The personal behavior recognition degrees corresponding to the two operations are obtained respectively, which are respectively represented as the operation value personal behavior recognition degree of the first smart device at the first user operation and the operation value personal behavior recognition degree of the first smart device at the first user operation.

[0082] The number of interpolation data points between the two operations is calculated, which is the calculation formula of the first smart device at the first user operation and the first user operation . ; wherein, is the floor symbol.

[0083] Thus, the rounded-down value is obtained by analysis, and the number of data points that need to be interpolated between the two operations is obtained, recorded as the number of interpolable data points, and uniform interpolation is performed between the two operations.

[0084] Therefore, the processing of discrete data points is achieved, and the subsequent spline interpolation processing steps are completed, including segmented interval division, construction of spline functions and other processing steps, to achieve the processing of all data.

[0085] Finally, using all data after spline interpolation based on the number of interpolable data points, collaborative filtering is performed to extract user profiles for all users. This is then used to perform collaborative filtering on the target user and their neighboring users. When the target user operates a smart device at the corresponding location, optimal control parameter settings for the smart device are automatically recommended. The intelligent host then adjusts all smart devices in the house to these optimal control parameters, achieving precise control of the smart devices in the whole-house intelligent control system.

[0086] As a preferred embodiment of the present invention, a more specific method for obtaining the optimal control parameters is:

[0087] The combination of all the operation values ​​of all smart devices in a single whole-house smart control system at the same time is used as the combination of all the item items corresponding to the user item in collaborative filtering. Each combination is analyzed as a separate user item. It should be noted that the operation value of each smart device also corresponds to an item.

[0088] Construct a user-item interaction matrix: This involves converting user-item behaviors (i.e., the action values ​​assigned to smart devices) into a matrix. The behavioral user items are listed as item items, and the action intensity value is the normalized difference between the action value of a single smart device and the minimum action value. Note that the minimum action value is readily available and varies from smart device to smart device.

[0089] Calculate user similarity: Use cosine similarity or Pearson correlation coefficient to measure the similarity between users in setting the smart device operation values.

[0090] Filter similar user neighbors: select k users with the highest similarity to the target user as the neighbor set; the value of k can be determined by the implementer according to actual conditions. In the embodiment of the present invention, the value of k is 10.

[0091] Generate recommendation predictions: Based on the similarity between neighbor users and the target user, the interest of the target user is weightedly predicted; that is, based on the similarity between neighbor users and the target user, the behavior intensity values ​​of all neighbor users of a single item are weighted summed to obtain the degree of interest.

[0092] Select the item with the highest degree of interest corresponding to the target user, and make an overall recommendation of the item combination consisting of the item, that is, recommend the item combination consisting of all smart devices in the same whole-house smart control system. The parameters in the item combination are the optimal control parameters for each smart device. Example 2

[0093] See also Figure 2 , Figure 2 The present invention provides a flowchart of a whole-house intelligent control method based on an intelligent host, which includes the following steps:

[0094] Obtain the control operation records of each smart device in the whole-house smart control system and construct the control operation vector of each smart device;

[0095] Determine the personalization coefficient of each smart device based on different control operation records;

[0096] According to the functional areas of the whole house, the smart devices in the whole house intelligent control system are marked in their respective areas, and the position change vector of each smart device is constructed;

[0097] Determining an operation change range based on the operation behavior of each smart device; and determining a personal behavior recognition degree of each smart device by combining the personalization coefficient, the position change vector, and the operation change range.

[0098] Based on the operating behavior of each smart device between two operations and the recognition of personal behavior, the number of interpolable data points between two operations is determined; based on the number of interpolable data points, spline interpolation processing is performed between each two operations, and the processed data is used to extract user portraits and obtain the optimal control parameters of the smart device corresponding to the user.

[0099] Optionally, the transmission medium may be a wired link, such as but not limited to coaxial cable, optical fiber, and digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth, and mobile device network.

[0100] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0101] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3As shown, the computer device 300 includes: a memory 310, a processor 320, and a computer program 330 stored in the memory 310 and running on the processor 320, wherein when the processor 320 executes the computer program 330, the computer device can execute any of the smart host-based whole-house smart control systems introduced above.

[0102] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the whole-house intelligent control system based on the intelligent host provided by the embodiment of the present invention.

[0103] In embodiments of the present invention, the device may be divided into functional modules based on the above-described method examples. For example, these modules may correspond to individual functional modules, or two or more functions may be integrated into a single processing module. The integrated modules may be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be employed.

[0104] In the case of dividing each module into modules corresponding to each function, the device may further include a signal uploading module, a determination module, an adjustment module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0105] It should be understood that the device provided in the embodiment of the present invention is used to execute the above-mentioned whole-house intelligent control system based on the intelligent host, and therefore can achieve the same effect as the above-mentioned implementation method.

[0106] When an integrated unit is employed, the device may include a processing module and a storage module. When the device is applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module can be a processor or controller that can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, etc. The storage module can be a memory.

[0107] In addition, the device provided in the embodiment of the present invention can specifically be a chip, component or module, and the chip may include a connected processor and memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the whole-house intelligent control system based on the intelligent host provided in the above embodiment.

[0108] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement the whole-house intelligent control system based on the intelligent host provided in the above embodiment.

[0109] An embodiment of the present invention also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute the above-mentioned related steps to implement the whole-house intelligent control system based on the intelligent host provided in the above embodiment.

[0110] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways.

[0111] The device embodiments described above are merely illustrative. For example, the division into modules or units represents only one logical functional division. Actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another device, or omitting or disabling certain features. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through an interface, or indirect coupling or communication connection between devices or units may be electrical, mechanical, or otherwise.

[0112] It should also be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or terminal device comprising the element.

[0113] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0115] The above content is only a specific implementation method of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A whole-house intelligent control system based on an intelligent host, characterized in that: The system includes the following modules: The operation data acquisition module is used to obtain the control operation records of each smart device in the whole-house smart control system and construct the control operation vector of each smart device; A personalization analysis module, used to determine the personalization coefficient of each smart device based on different control operation records; The location analysis module is used to mark the areas where smart devices in the whole-house smart control system are located according to the functional areas of the whole house and construct the location change vector of each smart device; a recognition degree analysis module, configured to determine an operation change range based on the operation behavior of each smart device; and determine the individual behavior recognition degree of each smart device by combining the personalization coefficient, the position change vector, and the operation change range; The device parameter determination module is used to determine the number of interpolable data points between two operations based on the operating behavior of each smart device between the two operations and the recognition of individual behavior; based on the number of interpolable data points, spline interpolation processing is performed between each two operations, and the processed data is used to extract the user portrait and obtain the optimal control parameters of the smart device corresponding to the user.

2. The whole-house intelligent control system based on the intelligent host according to claim 1 is characterized in that: Before determining the personalization coefficient of each smart device according to different control operation records, the method further includes: Based on the similarity between different control operation vectors, the control operation vectors of all smart devices are clustered to obtain operation clusters; the control operation vectors include the control operation vectors obtained in multiple historical periods; the control operation records include: central smart host control, smart device control and manual control.

3. The whole-house intelligent control system based on the intelligent host according to claim 2 is characterized in that: Determining the personalization coefficient of each smart device according to different control operation records includes: Get the number of registered users in the whole-house intelligent control system; Compare the difference between the number of operation clusters and the number of registered users to obtain the user's behavioral interleaving feature value; Taking any smart device as the target smart device, calculate the proportion of control operation vectors corresponding to the target smart device in each operation cluster as the degree of personalization; The personalization coefficient of each smart device is determined by combining the behavior interleaving characteristic value and the personalization degree.

4. The whole-house intelligent control system based on the intelligent host according to claim 3 is characterized in that: The determining of the personalization coefficient of each smart device by combining the behavior interleaving characteristic value and the personalization degree includes: A product value of the behavior interleaving characteristic value and the personalization degree is calculated as a personalization coefficient of each smart device.

5. The whole-house intelligent control system based on the intelligent host according to claim 1 is characterized in that: Determining the operation change range based on the operation behavior of each smart device includes: Taking any smart device as the target smart device, calculate the difference between the operation values ​​corresponding to the current user operation and the previous user operation of the target smart device, standardize the difference value, and obtain the operation change amplitude corresponding to the current user operation of the target smart device; wherein the operation value corresponding to the user operation is the control value when the user controls the smart device.

6. The whole-house intelligent control system based on the intelligent host according to claim 1 is characterized in that: The determining of the personal behavior recognition degree of each smart device by combining the personalization coefficient, the position change vector, and the operation change amplitude includes: Taking any user operation as the target user operation, the position similarity is determined based on the similarity between the position change vector corresponding to the target user operation and the standard position change vector of the smart device; Based on the personalization coefficient, operation change range and location similarity, the personal behavior recognition of each smart device under the target user's operation is determined.

7. The whole-house intelligent control system based on the intelligent host according to claim 6 is characterized in that: The method for obtaining the standard position change vector is as follows: a vector obtained by averaging all historical position change vectors of the smart device is used as the standard position change vector.

8. The whole-house intelligent control system based on the intelligent host according to claim 6 is characterized in that: Determining the personal behavior recognition of each smart device under the target user's operation based on the personalization coefficient, the operation change range, and the location similarity includes: The product of the personalization coefficient and the operation change amplitude is used as the numerator, the position similarity is used as the denominator, and the normalized value of the ratio formed by the numerator and denominator is used as the personal behavior recognition.

9. The whole-house intelligent control system based on the intelligent host according to claim 5 is characterized in that: Determining the number of interpolable data points between two operations based on the operational behavior of each smart device between the two operations and the individual behavior recognition includes: For the target smart device, the difference in the operation value of the target smart device between the two operations is calculated as the operation behavior difference; the difference in the personal behavior recognition of the target smart device between the two operations is calculated as the recognition difference; the ratio of the operation behavior difference and the recognition difference is rounded down to an integer, and the value is used as the number of interpolable data points between the two operations of the target smart device.

10. The whole-house intelligent control system based on the intelligent host according to claim 1 is characterized in that: The method includes: performing spline interpolation between each two operations based on the number of interpolable data points, extracting user portraits using the processed data, and obtaining optimal control parameters for the corresponding smart device, including: All data after spline interpolation processing based on the number of interpolable data points are used to extract all user portraits for collaborative filtering. When the user operates the smart device at the corresponding location, the optimal control parameter setting recommendation for the smart device is automatically obtained, and the corresponding smart devices in the whole house are adjusted to the optimal control parameters through the smart host.

Images