CN114201676A - User recommendation method and system based on intelligent cell user matching - Google Patents

Abstract

The invention provides a user recommendation method and system based on intelligent cell user matching, and relates to the technical field of intelligent cells. In the invention, the user matching relationship information among a plurality of target cell users corresponding to the acquired monitoring data of a plurality of cell areas is determined; for each target cell user in a plurality of target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the determined user matching relationship information; and aiming at each target cell user in a plurality of target cell users, sending the user recommendation request information of the target cell user to a target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user. Based on the method, the problem that the reliability of user recommendation in the prior art is poor can be solved.

Description

User recommendation method and system based on intelligent cell user matching

Technical Field

The invention relates to the technical field of intelligent cells, in particular to a user recommendation method and system based on intelligent cell user matching.

Background

The intelligent community is a new idea of community intelligent management, and modules such as property, owners, intelligent hardware, public services and the like are integrated through the internet technology. In the prior art, in an intelligent cell, in order to meet a certain requirement, user recommendation may need to be performed between cell users, but generally, one user is directly recommended to other users in the cell, and thus, there may be a problem that reliability of user recommendation is not good.

Disclosure of Invention

In view of the above, the present invention provides a user recommendation method and system based on smart cell user matching to solve the problem of poor reliability of user recommendation in the prior art.

In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:

a user recommendation method based on intelligent community user matching is applied to an intelligent community user data processing server, the intelligent community user data processing server is in communication connection with a plurality of user data acquisition devices, the plurality of user data acquisition devices are respectively arranged at a plurality of community area positions of a target intelligent community, and the user recommendation method comprises the following steps:

after cell area monitoring data obtained by respectively acquiring data of a corresponding cell area position in the cell area positions by each user data acquisition device in the user data acquisition devices is obtained, and a plurality of corresponding cell area monitoring data are obtained, determining user matching relationship information among a plurality of target cell users corresponding to the cell area monitoring data;

for each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the user matching relationship information;

and aiming at each target cell user in the target cell users, sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user so as to realize the user recommendation processing corresponding to the target cell user.

In some preferred embodiments, in the method for recommending users based on smart cell user matching, the step of determining, for each target cell user in the multiple target cell users, a target cell user to be recommended, which corresponds to the target cell user, among target cell users other than the target cell user based on the user matching relationship information includes:

analyzing and processing user recommendation request information corresponding to the target cell user aiming at each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell user;

for each target cell user in the target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request feature information corresponding to the target cell user, wherein the recommendation request type information comprises a similar user recommendation type and an opposite user recommendation type;

and aiming at each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the recommendation request type information corresponding to the target cell user and the user matching relation information.

In some preferred embodiments, in the aforementioned method for recommending users based on smart cell user matching, the step of analyzing, for each target cell user in the multiple target cell users, user recommendation request information corresponding to the target cell user to obtain recommendation request feature information corresponding to the target cell user includes:

aiming at each target cell user in the target cell users, carrying out keyword identification processing on user recommendation request information corresponding to the target cell user to obtain at least one target keyword corresponding to the target cell user;

and aiming at each target cell user in the target cell users, taking the at least one target keyword corresponding to the target cell user as the recommendation request characteristic information corresponding to the target cell user.

In some preferred embodiments, in the method for recommending users based on smart cell user matching, the step of determining, for each target cell user in the multiple target cell users, a target cell user to be recommended, which corresponds to the target cell user, among other target cell users except the target cell user based on the recommendation request type information and the user matching relationship information corresponding to the target cell user includes:

for each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the similar user recommendation type, determining each other target cell user having a matching relationship with the target cell user in other target cell users except the target cell user based on the user matching relationship information, and using the other target cell users as target cell users to be recommended corresponding to the target cell user;

and for each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the opposite user recommendation type, determining each other target cell user which does not have a matching relationship with the target cell user from other target cell users except the target cell user based on the user matching relationship information, and taking the other target cell users as the target cell user to be recommended corresponding to the target cell user.

In some preferred embodiments, in the aforementioned method for recommending users based on smart cell user matching, the step of sending, for each target cell user in the multiple target cell users, user recommendation request information of the target cell user to a target cell user to be recommended corresponding to the target cell user, so as to implement user recommendation processing corresponding to the target cell user includes:

for each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user;

for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user;

and aiming at each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user, wherein the user recommendation request information comprises user identity information of the corresponding target cell user.

In some preferred embodiments, in the aforementioned method for recommending users based on smart cell user matching, the step of determining, for each target cell user in the multiple target cell users, a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user includes:

for each target cell user in the target cell users, determining the number of occurrence frames of the target cell user in each corresponding cell area monitoring data respectively based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the number of occurrence frames to obtain the average value of the number of occurrence frames corresponding to the target cell user, wherein the cell area monitoring data are monitoring videos comprising multiple frames of monitoring video frames;

for each target cell user in the target cell users, determining the interactive video frame number of a monitoring video frame having an interactive relation with other target cell users in each corresponding cell area monitoring data of the target cell user based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the interactive video frame number to obtain the interactive video frame average frame number corresponding to the target cell user;

for each target cell user in the target cell users, respectively calculating proportion information between the number of the interactive video frames and the number of the appearing frames of the target cell user in each corresponding cell region monitoring data to obtain at least one piece of frame number proportion information corresponding to the target cell user, and calculating an average value of the at least one piece of frame number proportion information to obtain frame number proportion average value information corresponding to the target cell user;

for each target cell user in the target cell users, obtaining a first user recommendation degree with positive correlation based on the occurrence frame number average value corresponding to the target cell user, obtaining a second user recommendation degree with positive correlation based on the interactive video frame number average value corresponding to the target cell user, and obtaining a third user recommendation degree with positive correlation based on the frame number proportion average value information corresponding to the target cell user;

and for each target cell user in the target cell users, performing weighted summation calculation on the first user recommendation degree, the second user recommendation degree and the third user recommendation degree corresponding to the target cell user based on a first weight coefficient corresponding to the occurrence frame number average, a second weight coefficient corresponding to the interactive video frame number average and a third weight coefficient corresponding to the frame number proportional average information to obtain the user recommendation degree corresponding to the target cell user, wherein the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient.

In some preferred embodiments, in the aforementioned method for recommending users based on smart cell user matching, the step of determining, for each target cell user in the multiple target cell users, a first target cell user to be recommended, which corresponds to the target cell user, from target cell users to be recommended, which correspond to the target cell user based on the user recommendation degree corresponding to the target cell user includes:

aiming at each target cell user to be recommended corresponding to each target cell user in the target cell users, calculating the product of the representation value of the user matching relationship information between the target cell user and the target cell user to be recommended and the user recommendation degree corresponding to the target cell user to be recommended, and obtaining the recommendation priority value corresponding to the target cell user to be recommended;

and for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user and the recommendation priority value corresponding to each target cell user to be recommended in the target cell users to be recommended corresponding to the target cell user, wherein the first target cell user to be recommended is one or more target cell users to be recommended with the largest corresponding recommendation priority value.

The embodiment of the invention also provides a user recommendation system based on intelligent cell user matching, which is applied to an intelligent cell user data processing server, wherein the intelligent cell user data processing server is in communication connection with a plurality of user data acquisition devices, the plurality of user data acquisition devices are respectively arranged at a plurality of cell area positions of a target intelligent cell, and the user recommendation system comprises:

a user matching relationship determining module, configured to determine user matching relationship information between multiple target cell users corresponding to multiple cell area monitoring data after cell area monitoring data obtained by data acquisition of a corresponding cell area position in multiple cell area positions by each user data acquisition device in the multiple user data acquisition devices is obtained, and multiple corresponding cell area monitoring data are obtained;

a to-be-recommended user determining module, configured to determine, for each target cell user in the multiple target cell users, a to-be-recommended target cell user corresponding to the target cell user from target cell users other than the target cell user based on the user matching relationship information;

and the user recommendation processing module is used for sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user aiming at each target cell user in the target cell users so as to realize the user recommendation processing corresponding to the target cell user.

In some preferred embodiments, in the aforementioned system for recommending users based on smart cell user matching, the module for determining users to be recommended is specifically configured to:

analyzing and processing user recommendation request information corresponding to the target cell user aiming at each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell user;

for each target cell user in the target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request feature information corresponding to the target cell user, wherein the recommendation request type information comprises a similar user recommendation type and an opposite user recommendation type;

and aiming at each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the recommendation request type information corresponding to the target cell user and the user matching relation information.

In some preferred embodiments, in the aforementioned system for recommending users based on smart cell user matching, the user recommendation processing module is specifically configured to:

for each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user;

for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user;

and aiming at each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user, wherein the user recommendation request information comprises user identity information of the corresponding target cell user.

After determining the user matching relationship information among a plurality of target cell users corresponding to the obtained monitoring data of a plurality of cell areas, the user recommendation method and the system based on the intelligent cell user matching provided by the embodiment of the invention can firstly determine the target cell user to be recommended corresponding to the target cell user in other target cell users except the target cell user based on the determined user matching relationship information aiming at each target cell user in the plurality of target cell users, so that the user recommendation request information of the target cell user can be further sent to the target cell user to be recommended corresponding to the target cell user aiming at each target cell user in the plurality of target cell users, so as to realize the user recommendation processing corresponding to the target cell user, namely, the target cell user to be recommended is firstly determined based on the user matching relationship information, the basis of the user recommendation processing has better reliability, so that the problem of poor reliability of the user recommendation 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 a block diagram of an intelligent cell user data processing server according to an embodiment of the present invention.

Fig. 2 is a flowchart illustrating steps included in a user recommendation method based on smart cell user matching according to an embodiment of the present invention.

Fig. 3 is a schematic diagram illustrating modules included in a user recommendation system based on smart cell user matching 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 intelligent cell user data processing server. Wherein the smart cell user data processing server may include a memory and a processor.

In particular, the memory and the processor are electrically connected, directly or indirectly, to enable transmission or interaction of data. 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 user recommendation method based on smart cell user matching provided by the embodiments of the present invention (as described later).

Specifically, 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 recommendation method based on smart cell user matching, which is applicable to the smart cell user data processing server. The method steps defined by the flow related to the user recommendation method based on intelligent cell user matching can be realized by the intelligent cell user data processing server. The intelligent community user data processing server is in communication connection with a plurality of user data acquisition devices, and the plurality of user data acquisition devices are respectively arranged at the positions of a plurality of community areas of a target intelligent community.

The specific process shown in FIG. 2 will be described in detail below.

Step 100, determining user matching relationship information among a plurality of target cell users corresponding to the obtained plurality of cell area monitoring data.

In this embodiment of the present invention, the smart cell user data processing server may determine user matching relationship information between a plurality of target cell users corresponding to the obtained plurality of cell area monitoring data after obtaining cell area monitoring data obtained by performing data acquisition on a corresponding cell area position in the plurality of cell area positions by each of the plurality of user data acquisition devices, and obtaining the corresponding plurality of cell area monitoring data.

Step 300, for each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the user matching relationship information.

In this embodiment of the present invention, the smart cell user data processing server may determine, for each target cell user in the multiple target cell users, a target cell user to be recommended, which corresponds to the target cell user, among other target cell users other than the target cell user, based on the user matching relationship information.

Step 500, for each target cell user in the plurality of target cell users, sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user, so as to implement the user recommendation processing corresponding to the target cell user.

In the embodiment of the present invention, the smart cell user data processing server may send, for each target cell user of the multiple target cell users, user recommendation request information of the target cell user to a target cell user to be recommended corresponding to the target cell user, so as to implement user recommendation processing corresponding to the target cell user.

Based on the method, after determining the user matching relationship information among the target cell users corresponding to the obtained multiple cell area monitoring data, the target cell user to be recommended corresponding to the target cell user can be determined among other target cell users except the target cell user based on the determined user matching relationship information for each target cell user in the multiple target cell users, so that the user recommendation request information of the target cell user can be further sent to the target cell user to be recommended corresponding to the target cell user for each target cell user in the multiple target cell users, so as to realize the user recommendation processing corresponding to the target cell user, that is, the target cell user to be recommended is determined based on the user matching relationship information, so that the basis of the user recommendation processing has better reliability, therefore, the problem that the reliability of user recommendation in the prior art is poor is solved.

Specifically, as an alternative embodiment, step 110 in the above embodiment may further include the following steps, such as step 110, step 120, and step 130.

Step 110, respectively obtaining cell area monitoring data obtained by each user data acquisition device of the plurality of user data acquisition devices performing data acquisition on a corresponding cell area position of the plurality of cell area positions, and obtaining a plurality of corresponding cell area monitoring data.

In this embodiment of the present invention, the smart cell user data processing server may respectively obtain cell area monitoring data obtained by each user data collecting device of the plurality of user data collecting devices performing data collection on a corresponding cell area position of the plurality of cell area positions, so as to obtain a plurality of corresponding cell area monitoring data.

And 120, performing user behavior analysis processing on the multiple cell area monitoring data to obtain user behavior feature information corresponding to each target cell user in multiple target cell users in the target intelligent cell.

In this embodiment of the present invention, the smart cell user data processing server may perform user behavior analysis processing on the multiple cell area monitoring data, so as to obtain user behavior feature information corresponding to each target cell user of multiple target cell users in the target smart cell. And the user behavior characteristic information is used for representing the user characteristics of the corresponding target cell user in the target intelligent cell.

Step 130, determining user matching relationship information among the target cell users based on the user behavior feature information corresponding to each target cell user in the target cell users.

In this embodiment of the present invention, the smart cell user data processing server may determine user matching relationship information between the multiple target cell users based on user behavior feature information corresponding to each target cell user in the multiple target cell users.

Based on the method, after cell area monitoring data obtained by acquiring data of a corresponding cell area position in a plurality of cell area positions by each user data acquisition device in a plurality of user data acquisition devices is respectively obtained, user behavior analysis processing can be carried out on the obtained plurality of cell area monitoring data to obtain user behavior characteristic information corresponding to each target cell user in a plurality of target cell users in a target intelligent cell, so that user matching relationship information among a plurality of target cell users can be determined based on the user behavior characteristic information corresponding to each target cell user in the plurality of target cell users, that is, the user behavior characteristic information is used as a basis for determining the user matching relationship information among the target cell users, and the reliability of user matching can be guaranteed to a certain extent, therefore, the problem of poor effect on user matching in the prior art is solved.

Specifically, as an alternative embodiment, step 110 in the foregoing embodiment may further include the following steps:

firstly, determining whether each cell area position in the plurality of cell area positions can be used as a monitoring area object for monitoring the cell area;

secondly, for each of the plurality of cell area positions, if it is determined that the cell area position can be used as a monitoring area object for cell area monitoring, generating corresponding monitoring notification information, and sending the monitoring notification information to user data acquisition equipment corresponding to the cell area position, wherein each user data acquisition equipment is used for acquiring cell area monitoring data obtained by acquiring data of the corresponding cell area position after receiving the corresponding monitoring notification information, and sending the cell area monitoring data to the smart cell user data processing server;

then, for each of the plurality of cell area positions, after the user data acquisition device corresponding to the cell area position acquires and transmits the cell area monitoring data based on the corresponding monitoring notification information, the cell area monitoring data acquired and transmitted by the user data acquisition device corresponding to the cell area position is received.

Specifically, as an alternative embodiment, the step of determining, for each of the plurality of cell area positions, whether the cell area position can be used as a monitoring area object for cell area monitoring may further include the following steps:

firstly, aiming at each cell area position in the plurality of cell area positions, generating area monitoring confirmation information corresponding to the cell area position, and sending the area monitoring confirmation information to user terminal equipment corresponding to each cell user in the target smart cell, wherein each user terminal equipment is used for displaying the area monitoring confirmation information to the corresponding cell user after receiving the area monitoring confirmation information, so that the cell user performs monitoring confirmation operation based on the area monitoring confirmation information to generate corresponding monitoring confirmation information, and sends the monitoring confirmation information to the smart cell user data processing server;

secondly, for each of the plurality of cell area positions, receiving monitoring confirmation information sent by the user terminal equipment corresponding to each cell user in the target smart cell based on the area monitoring confirmation information corresponding to the cell area position, obtaining a plurality of pieces of monitoring confirmation information corresponding to the cell area position, and determining whether the cell area position can be used as a monitoring area object for cell area monitoring based on the plurality of pieces of monitoring confirmation information, wherein if each piece of monitoring confirmation information in the plurality of monitoring confirmation information represents that the corresponding cell user agrees to perform area monitoring on the corresponding cell area position, the cell area position is determined to be used as the monitoring area object for cell area monitoring, and if at least one piece of monitoring confirmation information in the plurality of monitoring confirmation information represents that the corresponding cell user does not agree to perform area monitoring on the corresponding cell area position, it is determined that the cell area location cannot be a monitored area object for cell area monitoring.

Specifically, as an alternative embodiment, step 120 in the foregoing embodiment may further include the following steps:

firstly, for each cell area monitoring data in the cell area monitoring data, performing user identification processing on the cell area monitoring data to obtain a target cell user corresponding to the cell area monitoring data, wherein each cell area monitoring data corresponds to one target cell user or corresponds to a plurality of target cell users;

secondly, constructing a cell user set comprising a plurality of target cell users based on the target cell users corresponding to each of the cell area monitoring data in the cell area monitoring data;

then, for each target cell user in the cell user set, performing user behavior analysis processing on the target cell user based on each cell area monitoring data corresponding to the target cell user to obtain user behavior characteristic information corresponding to the target cell user.

Specifically, as an alternative implementation manner, the step of, for each target cell user in the cell user set, performing user behavior analysis processing on the target cell user based on each cell area monitoring data corresponding to the target cell user to obtain user behavior feature information corresponding to the target cell user may further include the following steps:

firstly, counting the number of cell area monitoring data corresponding to each target cell user in the cell user set to obtain the data counting number corresponding to the target cell user, and determining the size relationship between the data counting number and a pre-configured counting number threshold, wherein the counting number threshold is greater than or equal to 2;

secondly, for each target cell user in the cell user set, if the data statistics number corresponding to the target cell user is greater than or equal to the statistics number threshold, performing position distance determination processing on two cell area positions corresponding to every two cell area monitoring data corresponding to the target cell user to obtain area position distance information corresponding to every two cell area monitoring data corresponding to the target cell user, determining a relative size relationship between the area position distance information and preconfigured area position distance threshold information, and determining two cell area monitoring data corresponding to each piece of area position distance information which is less than or equal to the area position distance threshold information as two cell area monitoring data with a distance association relationship;

then, for each target cell user in the cell user set, respectively performing behavior continuity identification processing on every two cell area monitoring data which are corresponding to the target cell user and have a distance association relation to obtain a user behavior continuity identification result corresponding to the two cell area monitoring data, and when the user behavior continuity identification result represents that the two cell area monitoring data have user behavior continuity, performing monitoring data merging processing on the two cell area monitoring data, and replacing the two cell area monitoring data with the obtained one cell area monitoring data;

finally, for each target cell user in the cell user set, performing user behavior analysis processing on each cell region monitoring data currently corresponding to the target cell user respectively to obtain user behavior feature information of each cell region monitoring data currently corresponding to the target cell user, so as to obtain at least one piece of user behavior feature information corresponding to the target cell user (for example, performing motion recognition on a video frame based on a neural network recognition model obtained through pre-training, and the like).

Specifically, as an alternative implementation manner, the step of performing behavior continuity identification processing on each two pieces of cell area monitoring data, which are corresponding to each target cell user in the cell user set and have a distance association relationship, respectively to obtain a user behavior continuity identification result corresponding to the two pieces of cell area monitoring data, and performing monitoring data combination processing on the two pieces of cell area monitoring data when the user behavior continuity identification result represents that the two pieces of cell area monitoring data have user behavior continuity, and replacing the two pieces of cell area monitoring data with the obtained piece of cell area monitoring data may further include the following steps:

firstly, for every two pieces of cell area monitoring data which are corresponding to each target cell user in the cell user set and have a distance association relationship, respectively determining first time information appearing for the first time and second time information appearing for the last time in the two pieces of cell area monitoring data of the target cell user, respectively calculating a time interval between the first time information corresponding to one piece of cell area monitoring data and the second time information corresponding to the other piece of cell area monitoring data to obtain two corresponding time interval information, and taking one time interval information with a smaller value in the two pieces of time interval information as the target time interval information corresponding to the two pieces of cell area monitoring data, wherein the cell area monitoring data are monitoring videos obtained by image acquisition;

secondly, for every two pieces of cell area monitoring data which are corresponding to each target cell user in the cell user set and have a distance association relationship, performing behavior continuity identification processing based on the area position distance information and the target time interval information corresponding to the two pieces of cell area monitoring data to obtain a user behavior continuity identification result corresponding to the two pieces of cell area monitoring data, performing monitoring data merging processing on the two pieces of cell area monitoring data when the user behavior continuity identification result represents that the two pieces of cell area monitoring data have user behavior continuity, and replacing the two pieces of cell area monitoring data with the obtained one piece of cell area monitoring data.

Specifically, as an alternative embodiment, the step 130 in the foregoing embodiment may further include the following steps:

firstly, aiming at every two target cell users in the target cell users, calculating the feature similarity between the user behavior feature information corresponding to the two target cell users;

secondly, determining the relative size relationship between the characteristic similarity between the user behavior characteristic information corresponding to two target cell users and a similarity threshold value configured in advance for the target intelligent cell aiming at each two target cell users in the target cell users;

then, for each two target cell users in the target cell users, if the feature similarity between the user behavior feature information corresponding to the two target cell users is greater than or equal to the similarity threshold, it is determined that there is a matching relationship between the two target cell users, and if the feature similarity between the user behavior feature information corresponding to the two target cell users is less than the similarity threshold, it is determined that there is no matching relationship between the two target cell users.

Specifically, as an alternative embodiment, the step of calculating, for each two target cell users in the multiple target cell users, a feature similarity between user behavior feature information corresponding to the two target cell users may further include the following steps:

firstly, for every two target cell users in the target cell users, calculating the similarity between each piece of user behavior characteristic information corresponding to a first target cell user in the two target cell users and each piece of user behavior characteristic information corresponding to a second target cell user to obtain at least one behavior similarity corresponding to the two target cell users;

secondly, determining the behavior similarity with the maximum value in the at least one behavior similarity corresponding to the two target cell users as the representative behavior similarity corresponding to the two target cell users aiming at every two target cell users in the plurality of target cell users;

thirdly, calculating the average value of the at least one behavior similarity corresponding to the two target cell users aiming at every two target cell users in the target cell users to obtain the similarity average value corresponding to the two target cell users, and determining a first similarity coefficient corresponding to the two target cell users based on the similarity average value, wherein the first similarity coefficient and the similarity average value have positive correlation;

fourthly, aiming at every two target cell users in the target cell users, determining whether the cell area monitoring data of the two target cell users exist at the same time in the cell area monitoring data, and counting the number of the cell area monitoring data of the two target cell users at the same time to obtain the number of the co-occurrence data corresponding to the two target cell users;

fifthly, aiming at every two target cell users in the target cell users, determining the time length of the two target cell users appearing at the same time in each cell area monitoring data simultaneously provided with the two target cell users, obtaining at least one user duration corresponding to the two target cell users, and calculating the average value of the at least one user duration to obtain the average value of the user duration corresponding to the two target cell users;

then, for each two target cell users in the target cell users, determining a second similarity coefficient corresponding to the two target cell users based on the statistical number of the co-occurrence data corresponding to the two target cell users, and determining a third similarity coefficient corresponding to the two target cell users based on the user duration average corresponding to the two target cell users, where the second similarity coefficient has a positive correlation with the statistical number of the co-occurrence data, the third similarity coefficient has a positive correlation with the user duration average, and the first similarity coefficient belongs to a preconfigured first coefficient interval, the second similarity coefficient belongs to a preconfigured second coefficient interval, the third similarity coefficient belongs to a preconfigured third coefficient interval, and an upper limit value of the first coefficient interval is greater than an upper limit value of the second coefficient interval, the upper limit value of the second coefficient interval is greater than that of the first coefficient interval;

finally, for each two target cell users of the target cell users, performing fusion processing on the representative behavior similarity, the first similarity coefficient, the second similarity coefficient, and the third similarity coefficient corresponding to the two target cell users (for example, a product of the representative behavior similarity, the first similarity coefficient, the second similarity coefficient, and the third similarity coefficient may be calculated as corresponding feature similarity), so as to obtain feature similarity between user behavior feature information corresponding to the two target cell users.

Specifically, as an alternative embodiment, step 120 in the foregoing embodiment may further include the following steps:

firstly, analyzing and processing user recommendation request information corresponding to each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell users;

secondly, for each target cell user in the plurality of target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request characteristic information corresponding to the target cell user, wherein the recommendation request type information comprises similar user recommendation types and opposite user recommendation types;

then, for each target cell user in the target cell users, based on the recommendation request type information and the user matching relationship information corresponding to the target cell user, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user.

Specifically, as an alternative implementation manner, the step of analyzing, for each target cell user in the multiple target cell users, user recommendation request information corresponding to the target cell user to obtain recommendation request feature information corresponding to the target cell user may further include the following steps:

firstly, aiming at each target cell user in the target cell users, carrying out keyword identification processing on user recommendation request information corresponding to the target cell user to obtain at least one target keyword corresponding to the target cell user;

secondly, aiming at each target cell user in the target cell users, taking the at least one target keyword corresponding to the target cell user as recommendation request characteristic information corresponding to the target cell user.

Specifically, as an alternative implementation manner, the step of determining, for each target cell user in the multiple target cell users, a target cell user to be recommended, which corresponds to the target cell user, among other target cell users except the target cell user based on the recommendation request type information and the user matching relationship information corresponding to the target cell user may further include the following steps:

firstly, aiming at each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the similar user recommendation type, determining each other target cell user having a matching relationship with the target cell user in other target cell users except the target cell user based on the user matching relationship information, and taking the other target cell users as target cell users to be recommended corresponding to the target cell user;

secondly, for each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the opposite user recommendation type, determining each other target cell user which does not have a matching relationship with the target cell user in other target cell users except the target cell user based on the user matching relationship information, and using the other target cell users as the target cell user to be recommended corresponding to the target cell user.

Specifically, as an alternative embodiment, the step 130 in the foregoing embodiment may further include the following steps:

firstly, aiming at each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user;

secondly, for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user;

then, for each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to implement user recommendation processing corresponding to the target cell user, wherein the user recommendation request information includes user identity information of the corresponding target cell user.

Specifically, as an alternative implementation manner, the step of determining, for each target cell user in the multiple target cell users, a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user may further include the following steps:

firstly, aiming at each target cell user in a plurality of target cell users, respectively determining the occurrence frame number of the target cell user in each corresponding cell area monitoring data based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the occurrence frame number to obtain the average value of the occurrence frame number corresponding to the target cell user, wherein the cell area monitoring data is a monitoring video comprising a plurality of frames of monitoring video frames;

secondly, aiming at each target cell user in the target cell users, determining the interactive video frame number of a monitoring video frame having an interactive relation with other target cell users in each corresponding cell area monitoring data of the target cell user based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the interactive video frame number to obtain the average value of the interactive video frame number corresponding to the target cell user;

then, for each target cell user in the target cell users, respectively calculating proportion information between the number of the interactive video frames and the number of the appearing frames of the target cell user in each corresponding cell region monitoring data to obtain at least one piece of frame number proportion information corresponding to the target cell user, and calculating an average value of the at least one piece of frame number proportion information to obtain frame number proportion average value information corresponding to the target cell user;

then, aiming at each target cell user in the target cell users, obtaining a first user recommendation degree with positive correlation based on the occurrence frame number average value corresponding to the target cell user, obtaining a second user recommendation degree with positive correlation based on the interactive video frame number average value corresponding to the target cell user, and obtaining a third user recommendation degree with positive correlation based on the frame number proportion average value information corresponding to the target cell user;

and finally, for each target cell user in the target cell users, performing weighted summation calculation on the first user recommendation degree, the second user recommendation degree and the third user recommendation degree corresponding to the target cell user based on the first weight coefficient corresponding to the occurrence frame number average value, the second weight coefficient corresponding to the interactive video frame number average value and the third weight coefficient corresponding to the frame number proportional average value information to obtain the user recommendation degree corresponding to the target cell user, wherein the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient.

Specifically, as an alternative implementation manner, the step of determining, for each target cell user in the multiple target cell users, a first target cell user to be recommended, which corresponds to the target cell user, among target cell users to be recommended, which correspond to the target cell user, based on the user recommendation degree corresponding to the target cell user may further include the following steps:

firstly, aiming at each target cell user to be recommended corresponding to each target cell user in the target cell users, calculating the product of a representation value (the feature similarity corresponding to the content) of the user matching relationship information between the target cell user and the target cell user to be recommended and the user recommendation degree corresponding to the target cell user to be recommended, and obtaining a recommendation priority value corresponding to the target cell user to be recommended;

secondly, for each target cell user in the target cell users, based on the user recommendation degree corresponding to the target cell user, determining a first target cell user to be recommended corresponding to the target cell user based on the recommendation priority value corresponding to each target cell user to be recommended in the target cell users to be recommended corresponding to the target cell user, wherein the first target cell user to be recommended is one or more (the number of the first target cell user to be recommended is determined based on the user recommendation degree corresponding to the target cell user, and has positive correlation) target cell users to be recommended with the largest recommendation priority value.

With reference to fig. 3, an embodiment of the present invention further provides a user recommendation system based on smart cell user matching, which is applicable to the smart cell user data processing server. The user recommendation system based on smart cell user matching may include the following modules:

a user matching relationship determining module, configured to determine user matching relationship information between multiple target cell users corresponding to multiple cell area monitoring data after cell area monitoring data obtained by data acquisition of a corresponding cell area position in multiple cell area positions by each user data acquisition device in the multiple user data acquisition devices is obtained, and multiple corresponding cell area monitoring data are obtained;

a to-be-recommended user determining module, configured to determine, for each target cell user in the multiple target cell users, a to-be-recommended target cell user corresponding to the target cell user from target cell users other than the target cell user based on the user matching relationship information;

and the user recommendation processing module is used for sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user aiming at each target cell user in the target cell users so as to realize the user recommendation processing corresponding to the target cell user.

Specifically, as an alternative implementation manner, the to-be-recommended user determining module is specifically configured to: analyzing and processing user recommendation request information corresponding to the target cell user aiming at each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell user; for each target cell user in the target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request feature information corresponding to the target cell user, wherein the recommendation request type information comprises a similar user recommendation type and an opposite user recommendation type; and aiming at each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the recommendation request type information corresponding to the target cell user and the user matching relation information.

Specifically, as an alternative implementation, the user recommendation processing module is specifically configured to: for each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user; for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user; and aiming at each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user, wherein the user recommendation request information comprises user identity information of the corresponding target cell user.

In summary, after determining the user matching relationship information among the target cell users corresponding to the obtained monitoring data of the cell areas, the user recommendation method and system based on the intelligent cell user matching provided by the present invention may determine the target cell user to be recommended corresponding to the target cell user in other target cell users than the target cell user based on the determined user matching relationship information for each target cell user in the target cell users, so as to further send the user recommendation request information of the target cell user to be recommended corresponding to the target cell user for each target cell user in the target cell users, so as to implement the user recommendation process corresponding to the target cell user, that is, determine the target cell user to be recommended based on the user matching relationship information, the basis of the user recommendation processing has better reliability, so that the problem of poor reliability of the user recommendation in the prior art is solved.

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 utility model provides a user recommendation method based on wisdom district user matches which characterized in that, is applied to wisdom district user data processing server, wisdom district user data processing server communication connection has a plurality of user data acquisition equipment, a plurality of user data acquisition equipment set up respectively in a plurality of district regional positions of target wisdom district, user recommendation method includes:

after cell area monitoring data obtained by respectively acquiring data of a corresponding cell area position in the cell area positions by each user data acquisition device in the user data acquisition devices is obtained, and a plurality of corresponding cell area monitoring data are obtained, determining user matching relationship information among a plurality of target cell users corresponding to the cell area monitoring data;

for each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the user matching relationship information;

and aiming at each target cell user in the target cell users, sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user so as to realize the user recommendation processing corresponding to the target cell user.

2. The method as claimed in claim 1, wherein the step of determining, for each target cell user in the target cell users, a target cell user to be recommended from among target cell users other than the target cell user based on the user matching relationship information includes:

analyzing and processing user recommendation request information corresponding to the target cell user aiming at each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell user;

for each target cell user in the target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request feature information corresponding to the target cell user, wherein the recommendation request type information comprises a similar user recommendation type and an opposite user recommendation type;

and aiming at each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the recommendation request type information corresponding to the target cell user and the user matching relation information.

3. The method as claimed in claim 2, wherein the step of analyzing the user recommendation request information corresponding to the target cell user to obtain the recommendation request feature information corresponding to the target cell user comprises:

aiming at each target cell user in the target cell users, carrying out keyword identification processing on user recommendation request information corresponding to the target cell user to obtain at least one target keyword corresponding to the target cell user;

and aiming at each target cell user in the target cell users, taking the at least one target keyword corresponding to the target cell user as the recommendation request characteristic information corresponding to the target cell user.

4. The method as claimed in claim 2, wherein the step of determining, for each target cell user in the plurality of target cell users, a target cell user to be recommended from target cell users other than the target cell user based on the recommendation request type information and the user matching relationship information corresponding to the target cell user, comprises:

for each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the similar user recommendation type, determining each other target cell user having a matching relationship with the target cell user in other target cell users except the target cell user based on the user matching relationship information, and using the other target cell users as target cell users to be recommended corresponding to the target cell user;

and for each target cell user in the target cell users, if the recommendation request type information corresponding to the target cell user belongs to the opposite user recommendation type, determining each other target cell user which does not have a matching relationship with the target cell user from other target cell users except the target cell user based on the user matching relationship information, and taking the other target cell users as the target cell user to be recommended corresponding to the target cell user.

5. The method as claimed in claim 1, wherein the step of sending the user recommendation request information of each target cell user of the target cell users to the target cell user to be recommended corresponding to the target cell user to implement the user recommendation process corresponding to the target cell user comprises:

for each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user;

for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user;

and aiming at each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user, wherein the user recommendation request information comprises user identity information of the corresponding target cell user.

6. The method as claimed in claim 5, wherein the step of determining the user recommendation degree corresponding to each target cell user based on the cell area monitoring data corresponding to the target cell user for each target cell user of the plurality of target cell users comprises:

for each target cell user in the target cell users, determining the number of occurrence frames of the target cell user in each corresponding cell area monitoring data respectively based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the number of occurrence frames to obtain the average value of the number of occurrence frames corresponding to the target cell user, wherein the cell area monitoring data are monitoring videos comprising multiple frames of monitoring video frames;

for each target cell user in the target cell users, determining the interactive video frame number of a monitoring video frame having an interactive relation with other target cell users in each corresponding cell area monitoring data of the target cell user based on each corresponding cell area monitoring data of the target cell user, and calculating the average value of the interactive video frame number to obtain the interactive video frame average frame number corresponding to the target cell user;

for each target cell user in the target cell users, respectively calculating proportion information between the number of the interactive video frames and the number of the appearing frames of the target cell user in each corresponding cell region monitoring data to obtain at least one piece of frame number proportion information corresponding to the target cell user, and calculating an average value of the at least one piece of frame number proportion information to obtain frame number proportion average value information corresponding to the target cell user;

for each target cell user in the target cell users, obtaining a first user recommendation degree with positive correlation based on the occurrence frame number average value corresponding to the target cell user, obtaining a second user recommendation degree with positive correlation based on the interactive video frame number average value corresponding to the target cell user, and obtaining a third user recommendation degree with positive correlation based on the frame number proportion average value information corresponding to the target cell user;

and for each target cell user in the target cell users, performing weighted summation calculation on the first user recommendation degree, the second user recommendation degree and the third user recommendation degree corresponding to the target cell user based on a first weight coefficient corresponding to the occurrence frame number average, a second weight coefficient corresponding to the interactive video frame number average and a third weight coefficient corresponding to the frame number proportional average information to obtain the user recommendation degree corresponding to the target cell user, wherein the first weight coefficient is smaller than the second weight coefficient, and the second weight coefficient is smaller than the third weight coefficient.

7. The method as claimed in claim 5, wherein the step of determining, for each target cell user of the target cell users, a first target cell user to be recommended from the target cell users corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user comprises:

aiming at each target cell user to be recommended corresponding to each target cell user in the target cell users, calculating the product of the representation value of the user matching relationship information between the target cell user and the target cell user to be recommended and the user recommendation degree corresponding to the target cell user to be recommended, and obtaining the recommendation priority value corresponding to the target cell user to be recommended;

and for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user and the recommendation priority value corresponding to each target cell user to be recommended in the target cell users to be recommended corresponding to the target cell user, wherein the first target cell user to be recommended is one or more target cell users to be recommended with the largest corresponding recommendation priority value.

8. The utility model provides a user recommendation system based on wisdom district user matches which characterized in that is applied to wisdom district user data processing server, wisdom district user data processing server communication connection has a plurality of user data acquisition equipment, a plurality of user data acquisition equipment set up respectively in a plurality of district regional positions of target wisdom district, user recommendation system includes:

a user matching relationship determining module, configured to determine user matching relationship information between multiple target cell users corresponding to multiple cell area monitoring data after cell area monitoring data obtained by data acquisition of a corresponding cell area position in multiple cell area positions by each user data acquisition device in the multiple user data acquisition devices is obtained, and multiple corresponding cell area monitoring data are obtained;

a to-be-recommended user determining module, configured to determine, for each target cell user in the multiple target cell users, a to-be-recommended target cell user corresponding to the target cell user from target cell users other than the target cell user based on the user matching relationship information;

and the user recommendation processing module is used for sending the user recommendation request information of the target cell user to be recommended corresponding to the target cell user aiming at each target cell user in the target cell users so as to realize the user recommendation processing corresponding to the target cell user.

9. The smart-cell-user-matching-based user recommendation system of claim 8, wherein the to-be-recommended-user determination module is specifically configured to:

analyzing and processing user recommendation request information corresponding to the target cell user aiming at each target cell user in the target cell users to obtain recommendation request characteristic information corresponding to the target cell user;

for each target cell user in the target cell users, determining recommendation request type information corresponding to user recommendation request information corresponding to the target cell user based on the recommendation request feature information corresponding to the target cell user, wherein the recommendation request type information comprises a similar user recommendation type and an opposite user recommendation type;

and aiming at each target cell user in the target cell users, determining a target cell user to be recommended corresponding to the target cell user from other target cell users except the target cell user based on the recommendation request type information corresponding to the target cell user and the user matching relation information.

10. The smart-cell-user-matching-based user recommendation system of claim 8, wherein the user recommendation processing module is specifically configured to:

for each target cell user in the target cell users, determining a user recommendation degree corresponding to the target cell user based on the cell area monitoring data corresponding to the target cell user, wherein the user recommendation degree is used for representing the user range of the target cell user to be recommended to the corresponding target cell user;

for each target cell user in the target cell users, determining a first target cell user to be recommended corresponding to the target cell user in target cell users to be recommended corresponding to the target cell user based on the user recommendation degree corresponding to the target cell user;

and aiming at each target cell user in the target cell users, sending user recommendation request information of the target cell user to each first target cell user to be recommended corresponding to the target cell user so as to realize user recommendation processing corresponding to the target cell user, wherein the user recommendation request information comprises user identity information of the corresponding target cell user.

Images