CN113673430A - User behavior analysis method based on Internet of things - Google Patents
User behavior analysis method based on Internet of things Download PDFInfo
- Publication number
- CN113673430A CN113673430A CN202110963149.XA CN202110963149A CN113673430A CN 113673430 A CN113673430 A CN 113673430A CN 202110963149 A CN202110963149 A CN 202110963149A CN 113673430 A CN113673430 A CN 113673430A
- Authority
- CN
- China
- Prior art keywords
- user behavior
- information
- user
- target
- internet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Abstract
The invention provides a user behavior analysis method based on the Internet of things, and relates to the technical field of the Internet of things. In the invention, user behavior information acquired by each piece of Internet of things equipment is acquired, wherein each piece of Internet of things equipment is used for acquiring user behavior in a monitoring area corresponding to the piece of Internet of things equipment to obtain the user behavior information; clustering a plurality of pieces of user behavior information at least based on one target characteristic dimension to obtain at least one user behavior cluster, wherein the information of any two pieces of user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a pre-configured clustering condition; analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior characteristic information, wherein the target user behavior characteristic information is used for representing the behavior characteristics of the users in the monitoring area of the Internet of things equipment. Based on the steps, the reliability of user behavior analysis can be improved.
Description
Technical Field
The invention relates to the technical field of Internet of things, in particular to a user behavior analysis method based on the Internet of things.
Background
With the continuous development of computer technology and internet technology, a lot of behavior information of a user can be collected, so that some corresponding applications can be performed based on the result of analyzing the behavior information to improve the convenience of life and work of the user, for example, behavior characteristics of the user are determined to perform corresponding security prediction or information push and the like. And with the development of the technology of the internet of things, the application of the user behavior analysis is combined, so that the quantity of behavior information for performing the user behavior analysis can be effectively guaranteed, and the basis of the user behavior analysis is improved.
However, the inventors have found that, in the prior art, generally, the obtained user behavior information is analyzed and processed in a unified manner, so that the effective user behavior information and the ineffective user behavior information are sufficiently mixed, and thus the reliability of the user behavior analysis is not high.
Disclosure of Invention
In view of this, the present invention provides a user behavior analysis method based on the internet of things, so as to improve reliability of user behavior analysis.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a user behavior analysis method based on the Internet of things is applied to an Internet of things background server, the Internet of things background server is in communication connection with a plurality of Internet of things devices, and the user behavior analysis method based on the Internet of things comprises the following steps:
the method comprises the steps of respectively obtaining user behavior information collected by each piece of Internet of things equipment to obtain a plurality of pieces of user behavior information, wherein each piece of Internet of things equipment is used for collecting user behaviors in a monitoring area corresponding to the piece of Internet of things equipment to obtain the user behavior information, and each piece of user behavior information is used for representing the user behavior of at least one user in the corresponding monitoring area;
clustering the plurality of pieces of user behavior information at least based on one target characteristic dimension to obtain at least one user behavior cluster, wherein each user behavior cluster comprises at least one piece of user behavior information, and the information of any two pieces of user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a pre-configured clustering condition;
analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior feature information, wherein the target user behavior feature information is used for representing behavior features of users in a monitoring area of the Internet of things equipment.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of obtaining the user behavior information collected by each piece of internet of things equipment to obtain a plurality of pieces of user behavior information includes:
judging whether a user behavior analysis instruction for instructing user behavior analysis is acquired or not;
if the user behavior analysis instruction is judged to be acquired, generating corresponding user behavior acquisition information based on the user behavior analysis instruction, and sending the user behavior acquisition information to each piece of Internet of things equipment, wherein the Internet of things equipment is used for sending the acquired user behavior information to the Internet of things background server based on the received user behavior acquisition information;
and acquiring user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of obtaining the user behavior information collected by each piece of internet of things equipment to obtain a plurality of pieces of user behavior information includes:
judging whether a time difference value between current time information and historical time information of the user behavior information obtained last time in history is larger than or equal to a preset time length threshold value, wherein the time length threshold value is determined based on the frequency of information acquisition of the Internet of things equipment;
if the time difference is judged to be greater than or equal to the duration threshold, generating corresponding user behavior acquisition information, and sending the user behavior acquisition information to each piece of Internet of things equipment, wherein the Internet of things equipment is used for sending the acquired user behavior information to the Internet of things background server based on the received user behavior acquisition information;
and acquiring user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of clustering the pieces of user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster includes:
for each piece of user behavior information, carrying out user identification processing on the user behavior information to determine whether the user behavior information contains behavior information of a user;
determining each piece of user behavior information containing user behavior information as target user behavior information;
clustering the target user behavior information based on at least one target characteristic dimension to obtain at least one user behavior cluster, wherein each user behavior cluster comprises at least one piece of target user behavior information, and the information of any two pieces of target user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a preset clustering condition.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of determining each piece of user behavior information including behavior information of a user as target user behavior information includes:
classifying each piece of user behavior information containing user behavior information based on whether the corresponding acquisition time information is the same or not to obtain at least one user behavior class, wherein each user behavior class comprises at least one piece of user behavior information, the acquisition time information corresponding to any two pieces of user behavior information belonging to the same user behavior class is the same, and the acquisition time information corresponding to any two pieces of user behavior information belonging to different user behavior classes is different;
determining whether the user behavior information of each piece of user behavior information included in each user behavior class is the same or not according to each user behavior class;
determining each piece of user behavior information different from the user behavior information of any other piece of user behavior information as target user behavior information;
and for each group of behavior information group with the same user behavior information, performing deduplication processing on the user behavior information included in the behavior information group, and taking the remaining user behavior information as target user behavior information corresponding to the behavior information group.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of clustering the target user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster includes:
for each piece of target user behavior information, determining user identification information corresponding to the target user behavior information, wherein the user identification information is used for representing identity information of a user in the corresponding target user behavior information;
and clustering the target user behavior information based on whether the user identification information is the same or not to obtain at least one user behavior cluster, wherein any two pieces of user identification information corresponding to the target user behavior information belonging to the same user behavior cluster are the same, and any two pieces of user identification information corresponding to the target user behavior information belonging to different user behavior clusters are different.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of determining, for each piece of target user behavior information, user identification information corresponding to the target user behavior information includes:
determining whether a plurality of users exist in the target user behavior information or not according to each piece of target user behavior information;
for each piece of target user behavior information with one user, determining user identification information corresponding to the target user behavior information;
and for each piece of target user behavior information with a plurality of users, determining a target user in the plurality of users of the target user behavior information, and determining the user identification information corresponding to the target user as the user identification information corresponding to the target user behavior information.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of determining, for each piece of target user behavior information, user identification information corresponding to the target user behavior information includes:
determining whether a plurality of users exist in the target user behavior information or not according to each piece of target user behavior information;
for each piece of target user behavior information with one user, determining user identification information corresponding to the target user behavior information;
and for each piece of target user behavior information with a plurality of users, generating corresponding quantity entry mark user behavior information based on the quantity of the users of the target user behavior information, and taking the user identification information of each user of the target user behavior information as the user identification information of each piece of target user behavior information corresponding to the target user behavior information.
In some preferred embodiments, in the method for analyzing user behaviors based on the internet of things, the step of analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior feature information includes:
for each user behavior cluster, performing user behavior feature extraction processing on each piece of user behavior information included in the user behavior cluster to obtain first user behavior feature information of a user corresponding to the user behavior cluster, wherein any two pieces of user behavior information belonging to the same user behavior cluster correspond to the same user, and any two pieces of user behavior information belonging to different user behavior clusters correspond to different users;
aiming at each user behavior cluster, determining other users having an association relation with the user corresponding to the user behavior cluster, and taking the first user behavior characteristic information of the other users as the second user behavior characteristic information of the user corresponding to the user behavior cluster;
and for each user behavior cluster, fusing the first user behavior characteristic information and the second user behavior characteristic information of the user corresponding to the user behavior cluster to obtain target user behavior characteristic information of the user corresponding to the user behavior cluster.
In some preferred embodiments, in the method for analyzing user behavior based on the internet of things, the step of fusing, for each user behavior cluster, the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster to obtain the target user behavior feature information of the user corresponding to the user behavior cluster includes:
for each user behavior cluster, comparing the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster to determine whether the first user behavior feature information and the second user behavior feature information have the same user behavior action information, wherein the first user behavior feature information and the second user behavior feature information are respectively formed on the basis of the user behavior action information corresponding to the user behavior information;
for each user behavior cluster, if the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster do not have the same user behavior feature information, taking the first user behavior feature information as target user behavior feature information of the user corresponding to the user behavior cluster;
and for each user behavior cluster, if the first user behavior characteristic information and the second user behavior characteristic information of the user corresponding to the user behavior cluster have the same user behavior characteristic information, updating the first user behavior characteristic information based on the second user behavior characteristic information to obtain target user behavior characteristic information of the user corresponding to the user behavior cluster.
According to the user behavior analysis method based on the Internet of things, after the plurality of pieces of user behavior information are obtained, the plurality of pieces of user behavior information are clustered based on at least one target characteristic dimension to obtain at least one user behavior cluster, and then the user behavior information included in each user behavior cluster can be analyzed to obtain at least one piece of target user behavior characteristic information. By adopting the scheme provided by the invention, clustering is carried out based on the target characteristic dimension, so that each user behavior information included in the same user behavior cluster has higher relevance under the target characteristic dimension, and the higher relevance among the bases (user behavior information) is ensured when the user behavior information included in the user behavior cluster is subjected to behavior analysis, so that the reliability of the user behavior analysis is improved, and the problem that the bases do not have higher relevance to cause mutual conflict so that the reliability of the user behavior analysis is not high in the prior art is solved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is an application block diagram of an internet of things background server provided by an embodiment of the present invention.
Fig. 2 is a schematic flow chart illustrating steps included in the method for analyzing user behavior based on the internet of things according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of functional modules included in a user behavior analysis system based on the internet of things according to an embodiment of the present invention.
Detailed Description
In order to make the objects, 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 with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides an internet of things background server. The internet of things background server can comprise a memory and a processor.
Optionally, the memory and the processor are electrically connected directly or indirectly to enable data transfer or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the method for analyzing user behavior based on internet of things according to the embodiment of the present invention (as described later).
Alternatively, the Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
With reference to fig. 2, an embodiment of the present invention further provides a user behavior analysis method based on the internet of things, which is applicable to the internet of things background server. The method steps defined by the flow related to the user behavior analysis method based on the internet of things can be realized by the internet of things background server.
The specific process shown in FIG. 2 will be described in detail below.
Step S100, user behavior information acquired by each Internet of things device is acquired respectively, and a plurality of pieces of user behavior information are acquired.
In this embodiment, the internet of things background server is communicatively connected with a plurality of pieces of internet of things equipment, and based on this, the internet of things background server may first execute step S100 to obtain each piece of user behavior information collected by the internet of things equipment, so as to obtain a plurality of pieces of user behavior information.
Each piece of Internet of things equipment is used for acquiring user behaviors in a monitoring area corresponding to the Internet of things equipment to obtain the user behavior information, and each piece of user behavior information is used for representing the user behavior of at least one user in the corresponding monitoring area.
And S200, clustering the plurality of pieces of user behavior information at least based on one target characteristic dimension to obtain at least one user behavior cluster.
In this embodiment, after the internet of things background server performs the step S100, the step S200 may be further performed to cluster the plurality of pieces of user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster.
Each user behavior cluster comprises at least one piece of user behavior information, and the information of any two pieces of user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a preset clustering condition.
Step S300, analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior characteristic information.
In this embodiment, after the internet of things background server performs the step S200, the step S300 may be further performed to analyze the user behavior information included in each user behavior cluster, so as to obtain at least one piece of target user behavior feature information.
The target user behavior feature information may be used to characterize behavior features of users in the monitoring area of the internet of things device.
Based on the above steps, after the pieces of user behavior information are obtained, the pieces of user behavior information are clustered based on at least one target characteristic dimension to obtain at least one user behavior cluster, and then the user behavior information included in each user behavior cluster can be analyzed to obtain at least one piece of target user behavior characteristic information. By adopting the scheme provided by the invention, clustering is carried out based on the target characteristic dimension, so that each user behavior information included in the same user behavior cluster has higher relevance under the target characteristic dimension, thus ensuring that higher relevance exists among the bases (user behavior information) when behavior analysis is carried out on the user behavior information included in the user behavior cluster, so as to improve the reliability of the user behavior analysis, and further solving the problem that the bases in the prior art (such as directly analyzing and processing the acquired user behavior information) have higher relevance to cause mutual conflict and further ensure that the reliability of the user behavior analysis is not high.
Optionally, in an example, the step S100 may include the following steps:
firstly, judging whether a user behavior analysis instruction for instructing user behavior analysis is acquired; secondly, if the user behavior analysis instruction is judged to be acquired, generating corresponding user behavior acquisition information based on the user behavior analysis instruction, and sending the user behavior acquisition information to each piece of internet of things equipment, wherein the internet of things equipment is used for sending the acquired user behavior information to the internet of things background server based on the received user behavior acquisition information; and finally, obtaining user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
Optionally, in another example, step S100 may include the following steps:
firstly, judging whether a time difference value between current time information and historical time information of user behavior information obtained last time in history is larger than or equal to a preset time length threshold value, wherein the time length threshold value is determined based on the frequency of information acquisition of the Internet of things equipment, if the frequency is higher, the corresponding time length threshold value is smaller, and if the frequency is lower, the corresponding time length threshold value is larger; secondly, if the time difference is judged to be larger than or equal to the time threshold, generating corresponding user behavior acquisition information, and sending the user behavior acquisition information to each piece of internet of things equipment, wherein the internet of things equipment is used for sending the acquired user behavior information to the internet of things background server based on the received user behavior acquisition information; and then, acquiring user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
Optionally, in an example, the step S200 may include the following steps:
firstly, for each piece of user behavior information, performing user identification processing on the user behavior information to determine whether the user behavior information contains behavior information of a user, wherein the user behavior information can be a frame of image acquired by an image acquisition device based on the user behavior information, and thus, whether the image contains the user such as a person can be determined;
secondly, determining each piece of user behavior information containing the behavior information of the user as target user behavior information, namely discarding the user behavior information not containing the behavior information of the user;
and then clustering the target user behavior information based on at least one target characteristic dimension to obtain at least one user behavior cluster, wherein each user behavior cluster comprises at least one piece of target user behavior information, and the information of any two pieces of target user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets the preset clustering condition.
Optionally, in an example, based on the above steps, the target user behavior information may be determined based on the following steps:
firstly, classifying each piece of user behavior information containing user behavior information based on whether the corresponding acquisition time information is the same or not to obtain at least one user behavior class, wherein each user behavior class comprises at least one piece of user behavior information, the acquisition time information corresponding to any two pieces of user behavior information belonging to the same user behavior class is the same, and the acquisition time information corresponding to any two pieces of user behavior information belonging to different user behavior classes is different;
secondly, determining whether the behavior information of the user, which is contained in each piece of user behavior information, of the user behavior class is the same or not;
then, determining each piece of user behavior information which is different from the user behavior information of any other piece of user behavior information as target user behavior information;
then, for each group of behavior information group having the same user behavior information, performing deduplication processing on the user behavior information included in the behavior information group, and taking the remaining user behavior information (for example, one piece of user behavior information may be reserved in the same user behavior information) as the target user behavior information corresponding to the behavior information group.
Optionally, in an example, on the basis of the above steps, the target user behavior information may be further clustered based on the following steps to obtain at least one user behavior cluster:
firstly, determining user identification information corresponding to each piece of target user behavior information, wherein the user identification information is used for representing identity information of a user in the corresponding target user behavior information (for example, in the identification process, different users are respectively labeled, such as user 1, user 2, user 3 and the like, or after a user can be identified, the user identification information is matched with an identity database to obtain corresponding identity information);
secondly, clustering the target user behavior information based on whether the user identification information is the same or not to obtain at least one user behavior cluster, wherein any two pieces of user identification information corresponding to the target user behavior information belonging to the same user behavior cluster are the same, and any two pieces of user identification information corresponding to the target user behavior information belonging to different user behavior clusters are different.
Optionally, in an example, on the basis of the above steps, the user identification information corresponding to the target user behavior information may be further determined based on the following steps:
firstly, for each piece of target user behavior information, determining whether a plurality of (such as more than two) users exist in the target user behavior information;
secondly, determining user identification information corresponding to the target user behavior information for each piece of target user behavior information with one user;
then, for each of the target user behavior information having a plurality of users, a target user (e.g., a user having the most information, such as a user having the largest occupied area in the image) in the plurality of users possessed by the target user behavior information is determined, and the user identification information corresponding to the target user is determined as the user identification information corresponding to the target user behavior information.
Optionally, in another example, on the basis of the above steps, the user identification information corresponding to the target user behavior information may also be further determined based on the following steps:
firstly, aiming at each piece of target user behavior information, determining whether a plurality of users exist in the target user behavior information;
secondly, determining user identification information corresponding to the target user behavior information for each piece of target user behavior information with one user;
then, for each of the target user behavior information having a plurality of users, generating corresponding number of pieces of entry mark user behavior information based on the number of users having the target user behavior information (if 5 users exist, 4 pieces of entry mark user behavior information may be copied, so that 5 pieces of entry mark user behavior information may be obtained by adding one piece of target user behavior information itself), and taking the user identification information of each user having the target user behavior information as the user identification information of each piece of target user behavior information corresponding to the target user behavior information (e.g., establishing a one-to-one correspondence relationship between the 5 users and the 5 pieces of entry mark user behavior information).
Optionally, in an example, the step S200 may include the following steps:
firstly, for each user behavior cluster, performing user behavior feature extraction processing on each piece of user behavior information included in the user behavior cluster to obtain first user behavior feature information of a user corresponding to the user behavior cluster, wherein any two pieces of user behavior information belonging to the same user behavior cluster correspond to the same user, and any two pieces of user behavior information belonging to different user behavior clusters correspond to different users;
secondly, for each user behavior cluster, determining other users having an association relationship with the user corresponding to the user behavior cluster (for example, one other user having an association relationship may be determined based on a connected identity database, or alternatively, based on the historically determined similarity between the historical user behavior feature information of each user, determining the other user corresponding to the historical user behavior feature information having the largest similarity as having an association relationship), and taking the first user behavior feature information of the other user as the second user behavior feature information of the user corresponding to the user behavior cluster;
and then, for each user behavior cluster, fusing the first user behavior characteristic information and the second user behavior characteristic information of the user corresponding to the user behavior cluster to obtain target user behavior characteristic information of the user corresponding to the user behavior cluster.
Optionally, in an example, on the basis of the above steps, the first user behavior feature information of the user corresponding to the user behavior cluster may be obtained further based on the following steps:
a first step, taking every two pieces of the user behavior information in the user behavior cluster as corresponding first user behavior information and second user behavior information (it can be understood that the series of steps may be for one user behavior cluster, and each user behavior cluster may obtain corresponding first user behavior feature information based on the series of steps);
a second step of determining, for the corresponding first user behavior information and second user behavior information, a user behavior association degree between the first user behavior information and the second user behavior information with respect to a corresponding acquisition time (taking a time association degree between acquisition times as a user behavior association degree);
thirdly, for each user behavior association degree which is greater than or equal to a preset user behavior association degree threshold, performing distributed network connection processing on the first user behavior information and the second user behavior information corresponding to the user behavior association degree to construct a corresponding user behavior distribution network, wherein in the user behavior distribution network, two pieces of user behavior information which are subjected to the distributed network connection processing can be directly connected, and two pieces of user behavior information which are not subjected to the distributed network connection processing are not directly connected;
fourthly, determining a network path connected between the user behavior information with the earliest acquisition time and the user behavior information with the latest acquisition time in the user behavior distribution network;
fifthly, for each network path, obtaining a behavior association degree characterization value (for example, calculating an average value of the user behavior association degrees) corresponding to the network path based on the user behavior association degrees among the user behavior information directly connected to the network path, and obtaining a first association coefficient having a positive correlation based on the number of the user behavior information included in the network path;
sixthly, determining a target network path in the obtained at least one network path based on the behavior association degree characteristic value corresponding to each network path and the corresponding first association coefficient, for example, calculating the product of the behavior association degree characteristic value and the corresponding first association coefficient, then obtaining the maximum product, and determining the network path corresponding to the maximum product as the target network path;
and seventhly, obtaining corresponding first user behavior characteristic information based on the user behavior action information corresponding to each piece of user behavior information included in the target network path (in this way, the corresponding user behavior actions are sequentially sequenced in the direction from the user behavior information with the earliest acquisition time to the user behavior information with the latest acquisition time to form a series of actions, namely the first user behavior characteristic information, for example, action 2 is followed by action 1, action 3 is followed by action 2, and the like).
Optionally, in an example, on the basis of the above steps, the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster may be further fused based on the following steps:
firstly, for each user behavior cluster, comparing the first user behavior feature information and the second user behavior feature information of a user corresponding to the user behavior cluster to determine whether the first user behavior feature information and the second user behavior feature information have the same user behavior action information, wherein the first user behavior feature information and the second user behavior feature information are respectively formed based on the user behavior action information corresponding to the user behavior information (action 1 is followed by action 2, and action 2 is followed by action 3 as described above);
secondly, for each user behavior cluster, if the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster do not have the same user behavior feature information, taking the first user behavior feature information as target user behavior feature information of the user corresponding to the user behavior cluster;
then, for each user behavior cluster, if the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster have the same user behavior feature information, updating the first user behavior feature information based on the second user behavior feature information to obtain target user behavior feature information of the user corresponding to the user behavior cluster (for example, if the first user behavior feature information has action 1, the action 1 is followed by action 3, the second user behavior feature information has action 1, the action 1 is followed by action 4, then, the user behavior association degree between the user behavior information corresponding to the action 1 and the action 3 is obtained from the first user behavior feature information, and the user behavior association degree between the user behavior information corresponding to the action 1 and the action 4 is obtained from the second user behavior feature information, and then calculating a difference value obtained by subtracting the previous user behavior association degree from the subsequent user behavior association degree, if the difference value is greater than a preset threshold value, updating the action 3 to be the action 4 in the first user behavior feature information, and if the difference value is less than or equal to the threshold value, keeping the action 3 in the first user behavior feature information).
With reference to fig. 3, an embodiment of the present invention further provides a user behavior analysis system based on the internet of things, which is applicable to the background server of the internet of things. The user behavior analysis system based on the internet of things can comprise the following functional modules:
the user behavior information acquiring module may be configured to acquire user behavior information acquired by each piece of internet of things equipment, respectively, to obtain a plurality of pieces of user behavior information, where each piece of internet of things equipment is configured to acquire a user behavior located in a monitoring area corresponding to the piece of internet of things equipment, to obtain the user behavior information, and each piece of user behavior information is used to represent a user behavior of at least one user in the corresponding monitoring area;
the user behavior information clustering module may be configured to cluster the plurality of pieces of user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster, where each user behavior cluster includes at least one piece of user behavior information, and information of any two pieces of user behavior information belonging to the same user behavior cluster in the target feature dimension satisfies a pre-configured clustering condition;
the user behavior information analyzing module may be configured to analyze the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior feature information, where the target user behavior feature information is used to characterize behavior features of users in a monitoring area of the internet of things device.
In summary, according to the user behavior analysis method based on the internet of things provided by the present invention, after a plurality of pieces of user behavior information are obtained, the plurality of pieces of user behavior information are clustered based on at least one target feature dimension to obtain at least one user behavior cluster, and then, the user behavior information included in each user behavior cluster can be analyzed to obtain at least one piece of target user behavior feature information. By adopting the scheme provided by the invention, clustering is carried out based on the target characteristic dimension, so that each user behavior information included in the same user behavior cluster has higher relevance under the target characteristic dimension, thus ensuring that higher relevance exists among the bases (user behavior information) when behavior analysis is carried out on the user behavior information included in the user behavior cluster, so as to improve the reliability of the user behavior analysis, and further solving the problem that the bases do not have higher relevance to cause mutual conflict so that the reliability of the user behavior analysis is not high in the prior art.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The user behavior analysis method based on the Internet of things is applied to an Internet of things background server, the Internet of things background server is in communication connection with a plurality of Internet of things devices, and the user behavior analysis method based on the Internet of things comprises the following steps:
the method comprises the steps of respectively obtaining user behavior information collected by each piece of Internet of things equipment to obtain a plurality of pieces of user behavior information, wherein each piece of Internet of things equipment is used for collecting user behaviors in a monitoring area corresponding to the piece of Internet of things equipment to obtain the user behavior information, and each piece of user behavior information is used for representing the user behavior of at least one user in the corresponding monitoring area;
clustering the plurality of pieces of user behavior information at least based on one target characteristic dimension to obtain at least one user behavior cluster, wherein each user behavior cluster comprises at least one piece of user behavior information, and the information of any two pieces of user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a pre-configured clustering condition;
analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior feature information, wherein the target user behavior feature information is used for representing behavior features of users in a monitoring area of the Internet of things equipment.
2. The method for analyzing user behavior based on the internet of things of claim 1, wherein the step of obtaining the user behavior information collected by each piece of internet of things equipment to obtain a plurality of pieces of user behavior information comprises:
judging whether a user behavior analysis instruction for instructing user behavior analysis is acquired or not;
if the user behavior analysis instruction is judged to be acquired, generating corresponding user behavior acquisition information based on the user behavior analysis instruction, and sending the user behavior acquisition information to each piece of Internet of things equipment, wherein the Internet of things equipment is used for sending the acquired user behavior information to the Internet of things background server based on the received user behavior acquisition information;
and acquiring user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
3. The method for analyzing user behavior based on the internet of things of claim 1, wherein the step of obtaining the user behavior information collected by each piece of internet of things equipment to obtain a plurality of pieces of user behavior information comprises:
judging whether a time difference value between current time information and historical time information of the user behavior information obtained last time in history is larger than or equal to a preset time length threshold value, wherein the time length threshold value is determined based on the frequency of information acquisition of the Internet of things equipment;
if the time difference is judged to be greater than or equal to the duration threshold, generating corresponding user behavior acquisition information, and sending the user behavior acquisition information to each piece of Internet of things equipment, wherein the Internet of things equipment is used for sending the acquired user behavior information to the Internet of things background server based on the received user behavior acquisition information;
and acquiring user behavior information sent by each piece of Internet of things equipment based on the user behavior acquisition information to obtain a plurality of pieces of user behavior information.
4. The internet of things-based user behavior analysis method according to claim 1, wherein the step of clustering the plurality of pieces of user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster comprises:
for each piece of user behavior information, carrying out user identification processing on the user behavior information to determine whether the user behavior information contains behavior information of a user;
determining each piece of user behavior information containing user behavior information as target user behavior information;
clustering the target user behavior information based on at least one target characteristic dimension to obtain at least one user behavior cluster, wherein each user behavior cluster comprises at least one piece of target user behavior information, and the information of any two pieces of target user behavior information belonging to the same user behavior cluster in the target characteristic dimension meets a preset clustering condition.
5. The method for analyzing user behavior based on internet of things according to claim 4, wherein the step of determining each piece of user behavior information including behavior information of a user as target user behavior information comprises:
classifying each piece of user behavior information containing user behavior information based on whether the corresponding acquisition time information is the same or not to obtain at least one user behavior class, wherein each user behavior class comprises at least one piece of user behavior information, the acquisition time information corresponding to any two pieces of user behavior information belonging to the same user behavior class is the same, and the acquisition time information corresponding to any two pieces of user behavior information belonging to different user behavior classes is different;
determining whether the user behavior information of each piece of user behavior information included in each user behavior class is the same or not according to each user behavior class;
determining each piece of user behavior information different from the user behavior information of any other piece of user behavior information as target user behavior information;
and for each group of behavior information group with the same user behavior information, performing deduplication processing on the user behavior information included in the behavior information group, and taking the remaining user behavior information as target user behavior information corresponding to the behavior information group.
6. The internet of things-based user behavior analysis method according to claim 4, wherein the step of clustering the target user behavior information based on at least one target feature dimension to obtain at least one user behavior cluster comprises:
for each piece of target user behavior information, determining user identification information corresponding to the target user behavior information, wherein the user identification information is used for representing identity information of a user in the corresponding target user behavior information;
and clustering the target user behavior information based on whether the user identification information is the same or not to obtain at least one user behavior cluster, wherein any two pieces of user identification information corresponding to the target user behavior information belonging to the same user behavior cluster are the same, and any two pieces of user identification information corresponding to the target user behavior information belonging to different user behavior clusters are different.
7. The internet of things-based user behavior analysis method according to claim 6, wherein the step of determining, for each piece of target user behavior information, user identification information corresponding to the target user behavior information includes:
determining whether a plurality of users exist in the target user behavior information or not according to each piece of target user behavior information;
for each piece of target user behavior information with one user, determining user identification information corresponding to the target user behavior information;
and for each piece of target user behavior information with a plurality of users, determining a target user in the plurality of users of the target user behavior information, and determining the user identification information corresponding to the target user as the user identification information corresponding to the target user behavior information.
8. The internet of things-based user behavior analysis method according to claim 6, wherein the step of determining, for each piece of target user behavior information, user identification information corresponding to the target user behavior information includes:
determining whether a plurality of users exist in the target user behavior information or not according to each piece of target user behavior information;
for each piece of target user behavior information with one user, determining user identification information corresponding to the target user behavior information;
and for each piece of target user behavior information with a plurality of users, generating corresponding quantity entry mark user behavior information based on the quantity of the users of the target user behavior information, and taking the user identification information of each user of the target user behavior information as the user identification information of each piece of target user behavior information corresponding to the target user behavior information.
9. The internet of things-based user behavior analysis method according to any one of claims 1 to 8, wherein the step of analyzing the user behavior information included in each user behavior cluster to obtain at least one piece of target user behavior feature information includes:
for each user behavior cluster, performing user behavior feature extraction processing on each piece of user behavior information included in the user behavior cluster to obtain first user behavior feature information of a user corresponding to the user behavior cluster, wherein any two pieces of user behavior information belonging to the same user behavior cluster correspond to the same user, and any two pieces of user behavior information belonging to different user behavior clusters correspond to different users;
aiming at each user behavior cluster, determining other users having an association relation with the user corresponding to the user behavior cluster, and taking the first user behavior characteristic information of the other users as the second user behavior characteristic information of the user corresponding to the user behavior cluster;
and for each user behavior cluster, fusing the first user behavior characteristic information and the second user behavior characteristic information of the user corresponding to the user behavior cluster to obtain target user behavior characteristic information of the user corresponding to the user behavior cluster.
10. The method for analyzing user behavior based on the internet of things of claim 9, wherein the step of fusing the first user behavior feature information and the second user behavior feature information of the user corresponding to each user behavior cluster to obtain the target user behavior feature information of the user corresponding to the user behavior cluster comprises:
for each user behavior cluster, comparing the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster to determine whether the first user behavior feature information and the second user behavior feature information have the same user behavior action information, wherein the first user behavior feature information and the second user behavior feature information are respectively formed on the basis of the user behavior action information corresponding to the user behavior information;
for each user behavior cluster, if the first user behavior feature information and the second user behavior feature information of the user corresponding to the user behavior cluster do not have the same user behavior feature information, taking the first user behavior feature information as target user behavior feature information of the user corresponding to the user behavior cluster;
and for each user behavior cluster, if the first user behavior characteristic information and the second user behavior characteristic information of the user corresponding to the user behavior cluster have the same user behavior characteristic information, updating the first user behavior characteristic information based on the second user behavior characteristic information to obtain target user behavior characteristic information of the user corresponding to the user behavior cluster.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110963149.XA CN113673430A (en) | 2021-08-20 | 2021-08-20 | User behavior analysis method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110963149.XA CN113673430A (en) | 2021-08-20 | 2021-08-20 | User behavior analysis method based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113673430A true CN113673430A (en) | 2021-11-19 |
Family
ID=78544646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110963149.XA Withdrawn CN113673430A (en) | 2021-08-20 | 2021-08-20 | User behavior analysis method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673430A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115603973A (en) * | 2022-09-30 | 2023-01-13 | 浙江电科智盛科技有限公司（Cn） | Heterogeneous security monitoring method and system based on government affair information network |
-
2021
- 2021-08-20 CN CN202110963149.XA patent/CN113673430A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115603973A (en) * | 2022-09-30 | 2023-01-13 | 浙江电科智盛科技有限公司（Cn） | Heterogeneous security monitoring method and system based on government affair information network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109918498B (en) | Problem warehousing method and device | |
| CN114140713A (en) | Image recognition system and image recognition method | |
| CN114140712A (en) | Automatic image recognition and distribution system and method | |
| CN115091472B (en) | Target positioning method based on artificial intelligence and clamping manipulator control system | |
| CN113656255A (en) | Operation abnormity judgment method based on chip operation data | |
| CN112990080A (en) | Rule determination method based on big data and artificial intelligence | |
| CN113673430A (en) | User behavior analysis method based on Internet of things | |
| CN113672782A (en) | Internet of things equipment importance matching method based on data query | |
| CN113612645A (en) | Internet of things data processing method and system | |
| CN116757870A (en) | Intelligent energy monitoring data processing method and system for energy Internet of things | |
| CN116070149A (en) | Data analysis method and system based on artificial intelligence and cloud platform | |
| CN115457467A (en) | Building quality hidden danger positioning method and system based on data mining | |
| CN113673429A (en) | Internet of things equipment control method and system based on internet of things user behavior analysis | |
| CN113672810A (en) | Information recommendation method and system based on user behavior analysis of Internet of things | |
| CN114625786B (en) | Dynamic data mining method and system based on wind control technology | |
| CN116996403B (en) | Network traffic diagnosis method and system applying AI model | |
| CN116680323B (en) | User demand mining method and system based on big data security platform | |
| CN113672444A (en) | Chip detection data acquisition method | |
| CN113687217A (en) | Chip life prediction method and system based on chip detection | |
| CN115459941A (en) | Cloud security account management method and cloud security platform | |
| CN117251790A (en) | Intelligent logistics data acquisition method and system | |
| CN113688023A (en) | User behavior abnormity warning method and device based on Internet of things data | |
| CN116566766A (en) | Intelligent power gateway management and control method and system | |
| CN114880714A (en) | Data security verification method and system based on smart city data sharing | |
| CN117220939A (en) | Security monitoring method and system for Internet equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211119 |