A user binding method and system based on smart home

Abstract

The present invention provides a user binding method and system based on smart home, which relates to the field of data processing technology. In the present invention, each of the multiple users to be bound is marked as a target user in turn; based on the corresponding historical user behavior data and current user behavior data, the target user is subjected to user feature analysis and processing, and the target user feature information corresponding to the target user is analyzed; based on the corresponding target user feature information, the multiple users to be bound are classified and combined to form at least one user classification combination, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not meet the correlation condition; based on the user classification combination, the multiple users to be bound are subjected to user binding processing to form a user binding relationship between the users to be bound. Based on the above method, the reliability of user binding can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a user binding method and system based on smart home. Background Art

[0002] Smart home, also known as intelligent home, is a living environment that uses the residence as a platform to install the intelligent home system. The process of implementing the intelligent home system is called intelligent home integration. With the residence as a platform, the facilities related to home life are integrated using integrated wiring technology, network communication technology, security technology, automatic control technology, and audio and video technology to 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. Smart home needs to be understood in two parts, intelligence and home. Home refers to all kinds of equipment in people's lives; intelligence is the focus of smart home, which should be automatically controlled and managed without manual operation and control, and can learn the current user's usage habits to better meet people's needs.

[0003] Among them, in the application of smart home, it may be necessary to perform relationship binding processing on the corresponding users. However, in the prior art, there is a problem of poor reliability of user relationship binding. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a user binding method and system based on smart home to improve the reliability of user binding.

[0005] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] A user binding method based on smart home, comprising:

[0007] Marking each of the multiple users to be bound as a target user in turn;

[0008] Based on the corresponding historical user behavior data and current user behavior data, a user feature analysis process is performed on the target user to analyze target user feature information corresponding to the target user;

[0009] Based on the corresponding target user feature information, the multiple users to be bound are classified and combined to form at least one user classification combination, wherein the correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition;

[0010] Based on the user classification combination, user binding processing is performed on the multiple users to be bound, so as to form a user binding relationship between the users to be bound.

[0011] In some preferred embodiments, in the above-mentioned user binding method based on smart home, the step of classifying and combining the multiple users to be bound based on the corresponding characteristic information of the target user to form at least one user classification combination includes:

[0012] For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is inconsistent or correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound; or

[0013] Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound.

[0014] In some preferred embodiments, in the above-mentioned user binding method based on smart home, the step of performing user binding processing on the multiple users to be bound based on the user classification combination to form a user binding relationship between the users to be bound includes:

[0015] For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound;

[0016] For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

[0017] In some preferred embodiments, in the above-mentioned user binding method based on smart home, for every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the step of determining the user binding relationship of the two users to be bound to determine whether to establish a corresponding user binding relationship between the two users to be bound includes:

[0018] For any two users to be bound that do not belong to the same user classification combination, the two users to be bound are marked as a first user to be bound and a second user to be bound respectively;

[0019] Performing user-associated device determination processing on the first user to be bound to output a first user-associated device set corresponding to the first user to be bound, and performing user-associated device determination processing on the second user to be bound to output a second user-associated device set corresponding to the second user to be bound, wherein each first user-associated device included in the first user-associated device set is associated with the first user to be bound, and each second user-associated device included in the second user-associated device set is associated with the second user to be bound;

[0020] Based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, a user binding relationship determination process is performed on the first user to be bound and the second user to be bound to determine whether a user binding relationship is established between the first user to be bound and the second user to be bound.

[0021] In some preferred embodiments, in the above-mentioned user binding method based on smart home, the step of determining the user binding relationship between the first user to be bound and the second user to be bound based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set to determine whether to establish a user binding relationship between the first user to be bound and the second user to be bound includes:

[0022] Determine the device overlap degree based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, so as to output the device overlap degree between the first user to be bound and the second user to be bound;

[0023] collecting a first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to form a first associated data set, wherein the first associated user behavior sequence is used to reflect the usage behavior of the first to-be-bound user on the first user associated device;

[0024] collecting a second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set to form a second associated data set, wherein the second associated user behavior sequence is used to reflect the usage behavior of the second to-be-bound user on the second user associated device;

[0025] Determining a behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output a corresponding behavior sequence relevance;

[0026] Based on the device overlap and the behavior sequence correlation, a user binding relationship determination process is performed on the first user to be bound and the second user to be bound to determine whether a user binding relationship is established between the first user to be bound and the second user to be bound.

[0027] In some preferred embodiments, in the above-mentioned user binding method based on smart home, the step of determining the behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output the corresponding behavior sequence relevance includes:

[0028] performing feature mining processing on each first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to output a corresponding first associated feature vector set, wherein each first associated feature vector included in the first associated feature vector set corresponds to one first associated user behavior sequence;

[0029] performing feature mining processing on the second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set, respectively, to output a corresponding second associated feature vector set, wherein each second associated feature vector included in the second associated feature vector set corresponds to one second associated user behavior sequence;

[0030] For each of the first associated feature vectors, a related first associated feature vector of the first associated feature vector is determined in the first associated feature vector set, and a related significant feature analysis is performed on the first associated feature vector based on the related first associated feature vector to output a first significant feature vector corresponding to the first associated feature vector, wherein a device interaction relationship between a first user-associated device corresponding to a first associated user behavior sequence corresponding to the related first associated feature vector and a first user-associated device corresponding to the first associated user behavior sequence corresponding to the first associated feature vector satisfies a pre-configured target device interaction relationship;

[0031] For each of the second associated feature vectors, a related second associated feature vector of the second associated feature vector is determined in the set of second associated feature vectors, and a related significant feature analysis is performed on the second associated feature vector based on the related second associated feature vector to output a second significant feature vector corresponding to the second associated feature vector, wherein a device interaction relationship between a second user associated device corresponding to the second associated user behavior sequence corresponding to the related second associated feature vector and a second user associated device corresponding to the second associated user behavior sequence corresponding to the second associated feature vector satisfies a pre-configured target device interaction relationship;

[0032] Based on the vector similarity between the first significant feature vector and the second significant feature vector, a corresponding behavior sequence correlation is determined.

[0033] In some preferred embodiments, in the above-mentioned user binding method based on smart home, the step of performing user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data to analyze the target user feature information corresponding to the target user includes:

[0034] Analyzing a behavior representative parameter corresponding to the current user behavior data based on a current behavior feature vector corresponding to the current user behavior data and historical user behavior data in a historical user behavior sequence, wherein the current user behavior data and the historical user behavior data in the historical user behavior sequence are generated based on the target user's usage behavior of the smart home device;

[0035] Determining behavior correlation representation data between the current user behavior data and the historical user behavior data;

[0036] Using a data comparison and analysis network, based on the behavior correlation characterization data and the behavior representative parameters, determining whether to perform a data screening operation on the historical user behavior sequence;

[0037] In the case where it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, a data screening analysis network is utilized to extract the historical user behavior data to be screened out from the historical user behavior sequence based on the behavior correlation characterization data, so as to perform user feature analysis processing on the target user based on the historical user behavior sequence retained after screening and the current user behavior data, and analyze the corresponding target user feature information.

[0038] The embodiment of the present invention further provides a user binding system based on smart home, comprising:

[0039] A user marking module, used to mark each of the multiple users to be bound as a target user in turn;

[0040] A user feature analysis module, used to perform user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data, and analyze the target user feature information corresponding to the target user;

[0041] A classification and combination processing module, configured to perform classification and combination processing on the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination, wherein the correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition;

[0042] The user binding processing module is used to perform user binding processing on the multiple users to be bound based on the user classification combination, so as to form a user binding relationship between the users to be bound.

[0043] In some preferred embodiments, in the above-mentioned user binding system based on smart home, the classification and combination processing module is specifically used for:

[0044] For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is inconsistent or correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound; or

[0045] Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound.

[0046] In some preferred embodiments, in the above-mentioned user binding system based on smart home, the user binding processing module is specifically used for:

[0047] For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound;

[0048] For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

[0049] A user binding method and system based on smart home provided by an embodiment of the present invention can mark each of a plurality of users to be bound as a target user in turn; based on the corresponding historical user behavior data and current user behavior data, perform user feature analysis on the target user to analyze the target user's corresponding target user feature information; based on the corresponding target user feature information, perform classification and combination processing on a plurality of users to be bound to form at least one user classification combination, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not meet the correlation condition; based on the user classification combination, perform user binding processing on a plurality of users to be bound to form a user binding relationship between the users to be bound. Based on the aforementioned steps, since the target user feature information corresponding to the user to be bound is determined first, reliable binding can be performed based on the target user feature information. Therefore, compared with the conventional technical solution that simply binds based on the position between users, the reliability of user binding can be higher.

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A structural block diagram of a smart home-based user binding platform provided in an embodiment of the present invention.

[0052] Figure 2 A flowchart of the steps of the user binding method based on smart home provided by an embodiment of the present invention.

[0053] Figure 3 A schematic diagram of various modules included in the smart home-based user binding system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0055] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] like Figure 1 As shown, an embodiment of the present invention provides a user binding platform based on smart home. Wherein, the user binding platform based on smart home may include a memory and a processor.

[0057] In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they can be electrically connected to each other through one or more communication buses or signal lines. The memory may store at least one software function module (computer program) that may exist in the form of software or firmware. The processor may be used to execute the executable computer program stored in the memory, thereby realizing the user binding method based on smart home provided by the embodiment of the present invention (as described later).

[0058] Optionally, in some embodiments, the memory may be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

[0059] Optionally, in some embodiments, the processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0060] Optionally, in some implementations, the smart home-based user binding platform may be a server with data processing capabilities.

[0061] Combination Figure 2 The embodiment of the present invention further provides a user binding method based on smart home, which can be applied to the user binding platform based on smart home. The method steps defined in the process related to the user binding method based on smart home can be implemented by the user binding platform based on smart home. Figure 2 The specific process shown is explained in detail.

[0062] Step S100: Mark each of the multiple users to be bound as a target user in turn.

[0063] In an embodiment of the present invention, the smart home-based user binding platform can mark each of the multiple users to be bound as a target user in turn.

[0064] Step S200 , based on the corresponding historical user behavior data and current user behavior data, user feature analysis is performed on the target user to obtain target user feature information corresponding to the target user.

[0065] In an embodiment of the present invention, the smart home-based user binding platform can perform user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data, and analyze the target user feature information corresponding to the target user.

[0066] Step S300: Based on the corresponding target user feature information, the multiple users to be bound are classified and combined to form at least one user classification combination.

[0067] In an embodiment of the present invention, the smart home-based user binding platform can classify and combine the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination. The correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition.

[0068] Step S400: Based on the user classification combination, user binding processing is performed on the multiple users to be bound, so as to form a user binding relationship between the users to be bound.

[0069] In an embodiment of the present invention, the smart home-based user binding platform can perform user binding processing on the multiple users to be bound based on the user classification combination to form a user binding relationship between the users to be bound.

[0070] Based on the aforementioned steps, i.e., step S100, step S200, step S300 and step S400, since the target user characteristic information corresponding to the user to be bound is first determined, reliable binding can be performed based on the target user characteristic information. Therefore, compared with the conventional technical solution that simply binds based on the locations between users, the reliability of user binding can be higher.

[0071] Optionally, in some embodiments, the step of performing user feature analysis on the target user based on the corresponding historical user behavior data and the current user behavior data to analyze the target user feature information corresponding to the target user may further include the following contents, such as subsequent steps S110, S120, S130 and S140.

[0072] Step S110 , based on the current behavior feature vector corresponding to the current user behavior data and the historical user behavior data in the historical user behavior sequence, analyzing the behavior representative parameters corresponding to the current user behavior data.

[0073] In an embodiment of the present invention, the smart home-based user binding platform can analyze the behavior representative parameters corresponding to the current user behavior data based on the current behavior feature vector corresponding to the current user behavior data and the historical user behavior data in the historical user behavior sequence. The current user behavior data and the historical user behavior data in the historical user behavior sequence are generated based on the target user's use behavior of the smart home device and can be recorded in text data.

[0074] Step S120: determining behavior correlation representation data between the current user behavior data and the historical user behavior data.

[0075] In an embodiment of the present invention, the smart home-based user binding platform can determine the behavior correlation characterization data between the current user behavior data and the historical user behavior data, the similarity between the corresponding feature vectors, etc.

[0076] Step S130 , using a data comparison and analysis network, based on the behavior correlation characterization data and the behavior representative parameters, it is determined whether to perform a data screening operation on the historical user behavior sequence.

[0077] In an embodiment of the present invention, the smart home-based user binding platform can utilize a data comparison and analysis network to determine whether to perform a data screening operation on the historical user behavior sequence based on the behavior correlation characterization data and the behavior representative parameters.

[0078] Step S140, when it is determined that the historical user behavior sequence needs to be subjected to data screening operation, the historical user behavior data to be screened out is extracted from the historical user behavior sequence based on the behavior correlation characterization data by using the data screening analysis network, so as to perform user feature analysis processing on the target user based on the historical user behavior sequence retained after screening and the current user behavior data, and analyze the corresponding target user feature information.

[0079] In an embodiment of the present invention, the smart home-based user binding platform can, when it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, utilize a data screening and analysis network to extract the historical user behavior data to be screened out from the historical user behavior sequence based on the behavior correlation characterization data, so as to perform user feature analysis on the target user based on the historical user behavior sequence retained after screening and the current user behavior data, and analyze the corresponding target user feature information. The target user feature information can be used as a classification label, such as 1, 2, 3, 4, 5, etc., which does not have any meaning, or can be information with specific feature meanings, such as high-value users, low-value users, etc.

[0080] Based on this, that is, based on the above-mentioned steps S110, S120, S130 and S140, since the historical user behavior data will be screened before the user feature analysis is performed, and the current user behavior data will be combined during the screening process, the reliability of the screening is higher, thereby ensuring that the filtered historical user behavior data is more effective, which can improve the reliability of the user feature analysis, and further improve the problem of poor reliability existing in the prior art.

[0081] Optionally, in some implementations, the step of determining the behavior correlation characterization data between the current user behavior data and the historical user behavior data may further include the following content:

[0082] Determine the local behavior correlation characterization data between the current user behavior data and each of the historical user behavior data, such as respectively calculating the correlation between the local behavior correlation characterization data between the current user behavior data and each of the historical user behavior data, such as calculation of semantic similarity and text similarity, to obtain corresponding local behavior correlation characterization data; and, based on the local behavior correlation characterization data, analyze the global behavior correlation characterization data between the current user behavior data and the historical user behavior sequence, such as performing mean calculation on each of the local behavior correlation characterization data to obtain the global behavior correlation characterization data between the current user behavior data and the historical user behavior sequence.

[0083] Based on this, the step of using the data comparison and analysis network to determine whether to perform a data screening operation on the historical user behavior sequence based on the behavior correlation characterization data and the behavior representative parameters may further include the following contents:

[0084] Loading the global behavior correlation characterization data and the behavior representative parameters to load into a data comparison and analysis network, and using the data comparison and analysis network to analyze the global correlation value between the current user behavior data and the historical user behavior sequence;

[0085] Based on the global correlation value, determine whether to perform a data filtering operation on the historical user behavior sequence. For example, when the global correlation value is greater than or equal to a preset global correlation value, that is, the current user behavior data can represent the historical user behavior sequence. Therefore, it can be determined that a data filtering operation is performed on the historical user behavior sequence to reduce the amount of data for subsequent processing; when the global correlation value is less than the preset global correlation value, that is, the current user behavior data cannot represent the historical user behavior sequence. Therefore, it can be determined that a data filtering operation is not performed on the historical user behavior sequence.

[0086] Optionally, in some implementations, the user binding method based on smart home may further include the following content:

[0087] Based on the first dimension learning cost index of the nth round, the data comparison and analysis network is optimized, and based on the optimized data comparison and analysis network, it is determined whether to perform the data screening operation of the nth round;

[0088] In the case where it is determined that an n-th round of data screening operation is required, based on the n-th historical user behavior sequence retained after the n-th screening operation obtained after the n-th round of data screening operation, analyzing the n-th behavior representative parameter corresponding to the current user behavior data;

[0089] Based on the nth behavior representative parameter and the mth behavior representative parameter (the difference between them), the first dimension learning cost index of the yth round of the data comparison and analysis network is analyzed, and based on the first dimension learning cost index of the yth round, the data comparison and analysis network is optimized to form a new optimized data comparison and analysis network, nm=1.

[0090] Optionally, in some implementations, the step of loading the global behavior correlation characterization data and the behavior representative parameters to load into a data comparison and analysis network, and using the data comparison and analysis network to analyze the global correlation value between the current user behavior data and the historical user behavior sequence may further include the following contents:

[0091] Determining nth global behavior correlation representation data between the current user behavior data and the historical user behavior data in the nth historical user behavior sequence retained after being screened out;

[0092] Based on the nth behavior representative parameter and the nth global behavior correlation representation data, a corresponding nth situation feature vector is analyzed. Exemplarily, the nth behavior representative parameter and the nth global behavior correlation representation data may be encoded to obtain the corresponding nth situation feature vector;

[0093] According to the optimized data comparison and analysis network corresponding to the first dimension learning cost indicator of the nth round, the nth situation feature vector is fully connected to output the corresponding nth fully connected feature vector. Exemplarily, the nth situation feature vector can be weighted based on the first parameter, and then the result of the weighted processing is superimposed based on the second parameter to output the corresponding nth fully connected feature vector. The first parameter and the second parameter can be used as network parameters of the data comparison and analysis network for optimization;

[0094] According to the weight representation parameters included in the data comparison and analysis network, the nth fully connected feature vector is analyzed to output the global correlation value between the current user behavior data and the historical user behavior sequence. Exemplarily, the nth fully connected feature vector can be weighted based on a third parameter, and then, the result of the weighted processing can be subjected to incentive mapping processing. Then, based on the weight representation parameters and the negative correlation parameters of the weight representation parameters, the result of the incentive mapping processing and the negative correlation parameters of the result of the incentive mapping processing can be weighted and summed. The sum value between the negative correlation parameters of the weight representation parameters and the weight representation parameters can be equal to 1, and the sum value between the result of the incentive mapping processing and the negative correlation parameters of the result of the incentive mapping processing can be equal to 1.

[0095] Optionally, in some implementations, the step of determining the behavior correlation characterization data between the current user behavior data and the historical user behavior data may further include the following content:

[0096] Determine the local behavior correlation characterization data between the current user behavior data and each of the historical user behavior data, as described above.

[0097] Based on this, when it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, the step of using a data screening analysis network to extract the historical user behavior data to be screened out from the historical user behavior sequence based on the behavior correlation characterization data, and performing user feature analysis processing on the target user based on the historical user behavior sequence retained after the screening and the current user behavior data to analyze the corresponding target user feature information may further include the following contents:

[0098] In the case where it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, the xth local behavior correlation representation data corresponding to the xth historical user behavior data is loaded and processed so as to be loaded into a data screening and analysis network, and the data screening and analysis network is used to analyze the local correlation value between the current user behavior data and the xth historical user behavior data; and, based on the local correlation value, it is determined whether the xth historical user behavior data belongs to the historical user behavior data to be screened out. For example, in the case where the local correlation value is greater than or equal to a preset value, it can be determined that the xth historical user behavior data needs to be screened out, and in the case where the local correlation value is less than the preset value, it can be determined that the xth historical user behavior data does not need to be screened out; and, based on the historical user behavior sequence retained after screening and the current user behavior data, a user feature analysis process is performed on the target user to analyze the corresponding target user feature information.

[0099] Optionally, in some implementations, the user binding method based on smart home may further include the following content:

[0100] Based on the second dimension learning cost indicator of the ath round, the data screening and analysis network is optimized, and based on the optimized data screening and analysis network, the historical user behavior data to be screened out is analyzed;

[0101] Analyze the ath behavior representative parameter of the current user behavior data based on the ath historical user behavior sequence retained after the ath round of data screening operation;

[0102] Based on the a-th behavior representative parameter and the b-th behavior representative parameter (the difference between them), a first local learning cost indicator is analyzed, the b-th behavior representative parameter is obtained based on the historical user behavior sequence retained after the b-th screening operation after the b-th round of data screening operation, ab=1;

[0103] Analyze the data matching degree between each historical user behavior data in the a-th historical user behavior sequence retained after screening and the current user behavior data, such as semantic relevance, and analyze a second local learning cost indicator based on multiple data matching degrees (the second local learning cost indicator may have a negatively correlated corresponding relationship with the data matching degree);

[0104] Based on the first local learning cost indicator and the second local learning cost indicator (such as performing a sum or weighted sum calculation on the first local learning cost indicator and the second local learning cost indicator), the second dimension learning cost indicator of the cth round of the data screening and analysis network is analyzed, and based on the second dimension learning cost indicator of the cth round, the data screening and analysis network is optimized to form an optimized data screening and analysis network, ca=1.

[0105] Optionally, in some implementations, when it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, the step of loading the xth local behavior correlation representation data corresponding to the xth historical user behavior data to load it into a data screening analysis network, and using the data screening analysis network to analyze the local correlation value between the current user behavior data and the xth historical user behavior data may further include the following contents:

[0106] In the case where it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, determining an xth local behavior correlation representation data between the current user behavior data and the xth historical user behavior data;

[0107] Based on the x-th local behavior correlation representation data, analyzing the corresponding x-th situation feature vector, such as encoding the x-th local behavior correlation representation data;

[0108] According to the optimized data screening and analysis network corresponding to the second dimension learning cost indicator of the ath round, the xth condition feature vector is fully connected, as described above, to output the corresponding xth fully connected feature vector;

[0109] According to the weight characterization parameters of the data screening and analysis network, the x-th fully connected feature vector is analyzed as described above to output a local correlation value between the current user behavior data and the x-th historical user behavior data.

[0110] Among them, it can be selected that, in some implementations, the step of analyzing the behavior representative parameter corresponding to the current user behavior data based on the current behavior feature vector corresponding to the current user behavior data and the historical user behavior data in the historical user behavior sequence can further include the following content:

[0111] Based on the historical user behavior data in the historical user behavior sequence, mining corresponding historical behavior feature vectors, such as performing feature mining or key information mining;

[0112] Based on the historical behavior feature vector and the current behavior feature vector corresponding to the current user behavior data, the behavior representative parameters corresponding to the current user behavior data are analyzed. Exemplarily, vector similarity calculation can be performed on the historical behavior feature vector and the current behavior feature vector to obtain the behavior representative parameters corresponding to the current user behavior data.

[0113] Wherein, it may be selected that, in some implementations, the step of mining the corresponding historical behavior feature vector based on the historical user behavior data in the historical user behavior sequence may further include the following contents:

[0114] The historical behavior feature vectors corresponding to the historical user behavior data in the historical user behavior sequence retained after the nth screening after the nth round of data screening operation are averaged to output the corresponding nth historical behavior feature vector, and the nth historical behavior feature vector is used to analyze the nth behavior representative parameter corresponding to the current user behavior data.

[0115] Optionally, in some implementations, the step of classifying and combining the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination may further include the following content:

[0116] For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is inconsistent or not correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound.

[0117] Optionally, in some implementations, the step of classifying and combining the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination may further include the following content:

[0118] Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to the other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound, and so on. The cycle is repeated to form at least one user classification combination.

[0119] Optionally, in some implementations, the step of performing user binding processing on the multiple users to be bound based on the user classification combination to form a user binding relationship between the users to be bound may further include the following content:

[0120] For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound;

[0121] For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

[0122] Alternatively, in some implementations, for every two users to be bound that do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the step of determining the user binding relationship of the two users to be bound to determine whether to establish a corresponding user binding relationship between the two users to be bound may further include the following contents:

[0123] For any two users to be bound that do not belong to the same user classification combination, the two users to be bound are marked as a first user to be bound and a second user to be bound respectively;

[0124] Performing user-associated device determination processing on the first user to be bound to output a first user-associated device set corresponding to the first user to be bound, and performing user-associated device determination processing on the second user to be bound to output a second user-associated device set corresponding to the second user to be bound, wherein each first user-associated device included in the first user-associated device set is associated with the first user to be bound, that is, the first user to be bound has used the first user-associated device, and each second user-associated device included in the second user-associated device set is associated with the second user to be bound, that is, the second user to be bound has used the second user-associated device;

[0125] Based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, a user binding relationship is determined for the first user to be bound and the second user to be bound to determine whether a user binding relationship is established between the first user to be bound and the second user to be bound.

[0126] Optionally, in some implementations, the step of performing a user binding relationship determination process on the first user to be bound and the second user to be bound based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set to determine whether to establish a user binding relationship between the first user to be bound and the second user to be bound may further include the following content:

[0127] Determine the device overlap based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, so as to output the device overlap between the first user to be bound and the second user to be bound, where the device overlap reflects the proportion of the number of identical devices between the sets;

[0128] collecting a first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to form a first associated data set, wherein the first associated user behavior sequence is used to reflect the usage behavior of the first to-be-bound user on the first user associated device;

[0129] collecting a second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set to form a second associated data set, wherein the second associated user behavior sequence is used to reflect the usage behavior of the second to-be-bound user on the second user associated device;

[0130] Determining a behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output a corresponding behavior sequence relevance;

[0131] Based on the device overlap and the behavior sequence correlation, a user binding relationship determination process is performed on the first user to be bound and the second user to be bound to determine whether to establish a user binding relationship between the first user to be bound and the second user to be bound. Exemplarily, a weighted sum calculation can be performed on the device overlap and the behavior sequence correlation to obtain a corresponding weighted sum value. Then, when the weighted sum value is greater than or equal to a preset value, a user binding relationship can be established between the first user to be bound and the second user to be bound. When the weighted sum value is less than the preset value, a user binding relationship is not established between the first user to be bound and the second user to be bound.

[0132] Optionally, in some implementations, the step of determining the behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output the corresponding behavior sequence relevance may further include the following content:

[0133] performing feature mining processing on each first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to output a corresponding first associated feature vector set, wherein each first associated feature vector included in the first associated feature vector set corresponds to one first associated user behavior sequence;

[0134] performing feature mining processing on the second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set, respectively, to output a corresponding second associated feature vector set, wherein each second associated feature vector included in the second associated feature vector set corresponds to one second associated user behavior sequence;

[0135] For each of the first associated feature vectors, a related first associated feature vector of the first associated feature vector is determined in the first associated feature vector set, and a related significant feature analysis is performed on the first associated feature vector based on the related first associated feature vector (exemplarily, the related first associated feature vector may be transposed to obtain a first transposed feature vector, and then the first transposed feature vector and the first associated feature vector may be multiplied and divided by the vector dimension of the first associated feature vector, and then the calculation result may be activated, and finally, the related first associated feature vector and the result of the activation process may be multiplied to achieve related significant feature analysis, that is, based on the related first associated feature vector, important and key information is mined from the first associated feature vector), so as to output a first significant feature vector corresponding to the first associated feature vector, and the device interaction relationship between the first user-associated device corresponding to the first associated user behavior sequence corresponding to the related first associated feature vector and the first user-associated device corresponding to the first associated user behavior sequence corresponding to the first associated feature vector satisfies a pre-configured target device interaction relationship, such as a maximum amount of interaction data;

[0136] For each of the second associated feature vectors, a related second associated feature vector of the second associated feature vector is determined in the set of the second associated feature vectors, and a related significant feature analysis is performed on the second associated feature vector based on the related second associated feature vector to output a second significant feature vector corresponding to the second associated feature vector, wherein the device interaction relationship between the second user associated device corresponding to the second associated user behavior sequence corresponding to the related second associated feature vector and the second user associated device corresponding to the second associated user behavior sequence corresponding to the second associated feature vector satisfies a pre-configured target device interaction relationship, such as a maximum amount of interaction data;

[0137] Based on the vector similarity between the first significant feature vector and the second significant feature vector, the corresponding behavior sequence correlation is determined. Exemplarily, the vector similarity between the first significant feature vector and the second significant feature vector can be directly used as the behavior sequence correlation, or the behavior sequence correlation can also be determined based on other relationships.

[0138] Combination Figure 3 The embodiment of the present invention further provides a user binding system based on smart home, which can be applied to the user binding platform based on smart home. The user binding system based on smart home can include the following software function modules:

[0139] A user marking module, used to mark each of the multiple users to be bound as a target user in turn;

[0140] A user feature analysis module, used to perform user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data, and analyze the target user feature information corresponding to the target user;

[0141] A classification and combination processing module, configured to perform classification and combination processing on the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination, wherein the correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition;

[0142] The user binding processing module is used to perform user binding processing on the multiple users to be bound based on the user classification combination, so as to form a user binding relationship between the users to be bound.

[0143] Optionally, in some implementations, the classification and combination processing module is specifically used to:

[0144] For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is inconsistent or correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound; or

[0145] Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound.

[0146] Optionally, in some implementations, the user binding processing module is specifically used to:

[0147] For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound;

[0148] For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

[0149] In summary, the user binding method and system based on smart home provided by the present invention can mark each of the multiple users to be bound as a target user in turn; based on the corresponding historical user behavior data and current user behavior data, perform user feature analysis on the target user to analyze the target user's corresponding target user feature information; based on the corresponding target user feature information, perform classification and combination processing on the multiple users to be bound to form at least one user classification combination, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not meet the correlation condition; based on the user classification combination, perform user binding processing on the multiple users to be bound to form a user binding relationship between the users to be bound. Based on the aforementioned steps, since the target user feature information corresponding to the user to be bound is determined first, reliable binding can be performed based on the target user feature information. Therefore, compared with the conventional technical solution that simply binds based on the position between users, the reliability of user binding can be higher.

[0150] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A user binding method based on smart home, characterized in that: include: Marking each of the multiple users to be bound as a target user in turn; Based on the corresponding historical user behavior data and current user behavior data, a user feature analysis process is performed on the target user to analyze target user feature information corresponding to the target user; Based on the corresponding target user feature information, the multiple users to be bound are classified and combined to form at least one user classification combination, wherein the correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition; Based on the user classification combination, performing user binding processing on the multiple users to be bound, so as to form a user binding relationship between the users to be bound; The step of performing user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data to analyze target user feature information corresponding to the target user includes: Analyzing a behavior representative parameter corresponding to the current user behavior data based on a current behavior feature vector corresponding to the current user behavior data and historical user behavior data in a historical user behavior sequence, wherein the current user behavior data and the historical user behavior data in the historical user behavior sequence are generated based on the target user's usage behavior of the smart home device; Determining behavior correlation representation data between the current user behavior data and the historical user behavior data; Using a data comparison and analysis network, based on the behavior correlation characterization data and the behavior representative parameters, determining whether to perform a data screening operation on the historical user behavior sequence; In the case where it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, a data screening analysis network is utilized to extract the historical user behavior data to be screened out from the historical user behavior sequence based on the behavior correlation characterization data, so as to perform user feature analysis processing on the target user based on the historical user behavior sequence retained after screening and the current user behavior data, and analyze the corresponding target user feature information.

2. The user binding method based on smart home as claimed in claim 1, characterized in that: The step of classifying and combining the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination includes: For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is not consistent or correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound; or Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound.

3. The user binding method based on smart home as claimed in claim 1, characterized in that: The step of performing user binding processing on the multiple users to be bound based on the user classification combination to form a user binding relationship between the users to be bound includes: For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound; For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

4. The user binding method based on smart home as claimed in claim 3, characterized in that: The step of determining a user binding relationship between two users to be bound that do not belong to the same user classification combination based on at least one other user characteristic information other than the target user characteristic information to determine whether to establish a corresponding user binding relationship between the two users to be bound includes: For any two users to be bound that do not belong to the same user classification combination, the two users to be bound are marked as a first user to be bound and a second user to be bound respectively; Performing user-associated device determination processing on the first user to be bound to output a first user-associated device set corresponding to the first user to be bound, and performing user-associated device determination processing on the second user to be bound to output a second user-associated device set corresponding to the second user to be bound, wherein each first user-associated device included in the first user-associated device set is associated with the first user to be bound, and each second user-associated device included in the second user-associated device set is associated with the second user to be bound; Based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, a user binding relationship determination process is performed on the first user to be bound and the second user to be bound to determine whether a user binding relationship is established between the first user to be bound and the second user to be bound.

5. The user binding method based on smart home as claimed in claim 4, characterized in that: The step of determining a user binding relationship between the first user to be bound and the second user to be bound based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set to determine whether to establish a user binding relationship between the first user to be bound and the second user to be bound includes: Determine the device overlap degree based on the first user-associated device included in the first user-associated device set and the second user-associated device included in the second user-associated device set, so as to output the device overlap degree between the first user to be bound and the second user to be bound; collecting a first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to form a first associated data set, wherein the first associated user behavior sequence is used to reflect the usage behavior of the first to-be-bound user on the first user associated device; collecting a second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set to form a second associated data set, wherein the second associated user behavior sequence is used to reflect the usage behavior of the second to-be-bound user on the second user associated device; Determining a behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output a corresponding behavior sequence relevance; Based on the device overlap and the behavior sequence correlation, a user binding relationship determination process is performed on the first user to be bound and the second user to be bound to determine whether a user binding relationship is established between the first user to be bound and the second user to be bound.

6. The user binding method based on smart home as claimed in claim 5, characterized in that: The step of determining the behavior sequence relevance based on the first associated user behavior sequence and the second associated user behavior sequence to output the corresponding behavior sequence relevance includes: performing feature mining processing on each first associated user behavior sequence corresponding to each first user associated device included in the first user associated device set to output a corresponding first associated feature vector set, wherein each first associated feature vector included in the first associated feature vector set corresponds to one first associated user behavior sequence; performing feature mining processing on the second associated user behavior sequence corresponding to each second user associated device included in the second user associated device set, respectively, to output a corresponding second associated feature vector set, wherein each second associated feature vector included in the second associated feature vector set corresponds to one second associated user behavior sequence; For each of the first associated feature vectors, a related first associated feature vector of the first associated feature vector is determined in the first associated feature vector set, and a related significant feature analysis is performed on the first associated feature vector based on the related first associated feature vector to output a first significant feature vector corresponding to the first associated feature vector, wherein a device interaction relationship between a first user-associated device corresponding to a first associated user behavior sequence corresponding to the related first associated feature vector and a first user-associated device corresponding to the first associated user behavior sequence corresponding to the first associated feature vector satisfies a pre-configured target device interaction relationship; For each of the second associated feature vectors, a related second associated feature vector of the second associated feature vector is determined in the set of second associated feature vectors, and a related significant feature analysis is performed on the second associated feature vector based on the related second associated feature vector to output a second significant feature vector corresponding to the second associated feature vector, wherein a device interaction relationship between a second user associated device corresponding to the second associated user behavior sequence corresponding to the related second associated feature vector and a second user associated device corresponding to the second associated user behavior sequence corresponding to the second associated feature vector satisfies a pre-configured target device interaction relationship; Based on the vector similarity between the first significant feature vector and the second significant feature vector, a corresponding behavior sequence correlation is determined.

7. A user binding system based on smart home, characterized in that: include: A user marking module, used to mark each of the multiple users to be bound as a target user in turn; A user feature analysis module, used to perform user feature analysis on the target user based on the corresponding historical user behavior data and current user behavior data, and analyze the target user feature information corresponding to the target user; A classification and combination processing module, configured to perform classification and combination processing on the multiple users to be bound based on the corresponding target user feature information to form at least one user classification combination, wherein the correlation between the target user feature information corresponding to each two users to be bound in the same user classification combination satisfies a pre-configured correlation condition, and the correlation between the target user feature information corresponding to each two users to be bound in different user classification combinations does not satisfy the correlation condition; A user binding processing module, configured to perform user binding processing on the plurality of users to be bound based on the user classification combination, so as to form a user binding relationship between the users to be bound; The user characteristic analysis processing is performed on the target user based on the corresponding historical user behavior data and the current user behavior data to analyze the target user characteristic information corresponding to the target user, including: Analyzing a behavior representative parameter corresponding to the current user behavior data based on a current behavior feature vector corresponding to the current user behavior data and historical user behavior data in a historical user behavior sequence, wherein the current user behavior data and the historical user behavior data in the historical user behavior sequence are generated based on the target user's usage behavior of the smart home device; Determining behavior correlation representation data between the current user behavior data and the historical user behavior data; Using a data comparison and analysis network, based on the behavior correlation characterization data and the behavior representative parameters, determining whether to perform a data screening operation on the historical user behavior sequence; In the case where it is determined that the historical user behavior sequence needs to be subjected to a data screening operation, a data screening analysis network is utilized to extract the historical user behavior data to be screened out from the historical user behavior sequence based on the behavior correlation characterization data, so as to perform user feature analysis processing on the target user based on the historical user behavior sequence retained after screening and the current user behavior data, and analyze the corresponding target user feature information.

8. The user binding system based on smart home as claimed in claim 7, characterized in that: The classification and combination processing module is specifically used for: For every two users to be bound among the multiple users to be bound, the target user feature information corresponding to the two users to be bound is analyzed for consistency or correlation, and every two users to be bound whose corresponding target user feature information is consistent or correlated are placed in the same user classification combination, and every two users to be bound whose corresponding target user feature information is inconsistent or correlated are placed in different user classification combinations, so as to form at least one user classification combination corresponding to the multiple users to be bound, each of which includes at least one user to be bound; or Based on the multiple users to be bound, a target user set is constructed, and one user to be bound is arbitrarily selected from the target user set as the target user to be bound, and the target user to be bound is placed in an empty user classification combination, and the target user to be bound is screened out from the target user set, and then other users to be bound in the target user set are traversed in sequence, so that when the target user feature information corresponding to other users to be bound currently traversed is consistent or correlated with the target user feature information corresponding to the target user to be bound, the other users to be bound are placed in the user classification combination, and the other users to be bound are screened out from the target user set, until each other user to be bound is traversed in sequence, and then a user to be bound is re-determined in the target user set as a new target user to be bound, so as to determine the user classification combination corresponding to the target user to be bound.

9. The user binding system based on smart home as claimed in claim 7, characterized in that: The user binding processing module is specifically used for: For every two users to be bound that belong to the same user classification combination, binding processing is performed on the two users to be bound to form a user binding relationship between the two users to be bound; For every two users to be bound who do not belong to the same user classification combination, based on at least one other user characteristic information other than the target user characteristic information, the user binding relationship of the two users to be bound is determined to determine whether a corresponding user binding relationship is established between the two users to be bound.

Images