CN114119066A

CN114119066A - Data processing-based shopping guide method and system for shopping malls

Info

Publication number: CN114119066A
Application number: CN202111265939.7A
Authority: CN
Inventors: 徐志华; 刘小平; 林成友; 刘芸
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-10-28
Filing date: 2021-10-28
Publication date: 2022-03-01

Abstract

The invention provides a data processing-based shopping guide method and system, and relates to the technical field of data processing. Analyzing the historical shopping behavior of each shopping user based on the obtained multiple historical shopping behavior monitoring videos to obtain a shopping behavior analysis result corresponding to each shopping user; determining whether a shopping behavior analysis result corresponding to each target shopping user is determined based on the historical shopping behavior monitoring video for each target shopping user currently located in the target market; and aiming at each target shopping user currently positioned in the target market, if the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, carrying out shopping guide processing on the target shopping user based on the shopping behavior analysis result. Based on the method, the problem that the shopping guide effect of the user is poor in the prior art can be improved.

Description

Data processing-based shopping guide method and system for shopping malls

Technical Field

The invention relates to the technical field of data processing, in particular to a market shopping guide method and system based on data processing.

Background

With the continuous development of computer technology, the application range of data processing technology is increased, for example, the data processing technology can be used for analyzing the behavior of a user, so that monitoring, early warning, guidance and the like are realized. For example, in a shopping mall environment, because there are many shopping users, there is a great demand for analyzing shopping behaviors in the shopping mall. Among them, in some high-precision shopping scenarios, such as self-service shopping scenarios, it is necessary for the user to be familiar with various steps (actions) of shopping, and therefore, action guidance is required. However, the inventor researches to find that, in the prior art, corresponding display devices are generally configured in various shopping areas to display standard shopping actions, so that the shopping guide effect for the user is not good due to different actual requirements of each shopping user.

Disclosure of Invention

In view of the above, the present invention provides a method and a system for guiding shopping in a shopping mall based on data processing, so as to solve the problem of poor effect of guiding shopping for a user in the prior art.

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

a market shopping guiding method based on data processing is applied to a shopping behavior monitoring server, the shopping behavior monitoring server is in communication connection with a plurality of shopping behavior monitoring devices, and the market shopping guiding method based on data processing comprises the following steps:

analyzing and processing the historical shopping behavior of each shopping user in the plurality of historical shopping behavior monitoring videos based on a plurality of historical shopping behavior monitoring videos acquired by a plurality of acquired shopping behavior monitoring devices to obtain a shopping behavior analysis result corresponding to each shopping user, wherein the plurality of shopping behavior monitoring devices are respectively arranged in different shopping areas of a target mall and are used for respectively acquiring images of the different shopping areas to obtain corresponding historical shopping behavior monitoring videos;

determining whether a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video for each target shopping user currently located in the target market;

and aiming at each target shopping user currently positioned in the target market, if the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, carrying out shopping guide processing on the target shopping user based on the shopping behavior analysis result.

In some preferred embodiments, in the data-processing-based mall shopping guiding method, the step of determining, for each target shopping user currently located in a target mall, whether there is a shopping behavior analysis result corresponding to the target shopping user determined based on the historical shopping behavior monitoring video includes:

acquiring target shopping behavior monitoring video frames currently acquired by the plurality of shopping behavior monitoring devices to obtain multi-frame target shopping behavior monitoring video frames corresponding to the plurality of shopping behavior monitoring devices;

monitoring video frames for each of the plurality of frames of target shopping behavior monitoring video frames, performing object discrimination processing on the target shopping behavior monitoring video frame to determine whether a target shopping user in the target shopping behavior monitoring video frame belongs to a monitoring user in the plurality of historical shopping behavior monitoring videos, and when it is determined that the target shopping behavior monitoring video frame contains a plurality of monitoring users in the historical shopping behavior monitoring videos, determining that the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, and upon determining that the targeted shopping behavior monitoring video frame does not include a monitoring user in the plurality of historical shopping behavior monitoring videos, and determining that the shopping behavior analysis result corresponding to the target shopping user is not determined based on the historical shopping behavior monitoring video.

In some preferred embodiments, in the data processing-based guidance method for shopping malls, the step of obtaining target shopping behavior monitoring video frames currently collected by the plurality of shopping behavior monitoring devices to obtain multiple frames of target shopping behavior monitoring video frames corresponding to the plurality of shopping behavior monitoring devices includes:

judging whether the current time belongs to preset target time, wherein the target time is determined based on the opening time of the target market;

if the current time belongs to the target time, generating corresponding monitoring starting notification information, and sending the monitoring starting notification information to each shopping behavior monitoring device in the plurality of shopping behavior monitoring devices, wherein each shopping behavior monitoring device starts image acquisition based on the monitoring starting notification information, and sends a currently acquired target shopping behavior monitoring video frame to the shopping behavior monitoring server;

and respectively acquiring a target shopping behavior monitoring video frame currently acquired and sent by each shopping behavior monitoring device based on the monitoring starting notification information.

In some preferred embodiments, in the data processing-based mall shopping guiding method, if it is determined that there is a shopping behavior analysis result corresponding to the target shopping user based on the historical shopping behavior monitoring video for each target shopping user currently located in the target mall, the step of performing shopping guiding processing on the target shopping user based on the shopping behavior analysis result includes:

for each target shopping user currently located in a target market, if a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, acquiring a target shopping behavior monitoring video frame currently having the target shopping user, and performing action recognition processing on the target shopping behavior monitoring video frame to obtain an action recognition result corresponding to the target shopping user, wherein the action recognition result is used for representing target shopping action type information of the target shopping user in the target shopping behavior monitoring video frame;

for each target shopping user currently located in a target market, if it is determined that a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, determining whether shopping action type information in the shopping behavior analysis result includes target shopping action type information represented by an action recognition result corresponding to the target shopping user;

for each target shopping user currently located in a target mall, if the shopping action type information in the shopping behavior analysis result corresponding to the target shopping user does not include the target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a standard shopping action image corresponding to the target shopping action type information from a target action image database, and performing shopping guide processing on the target shopping user based on the standard shopping action image;

for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information, and performing shopping guide processing on the target shopping user based on the historical shopping action monitoring video frame.

In some preferred embodiments, in the data processing-based mall shopping guiding method, for each target shopping user currently located in a target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by an action recognition result corresponding to the target shopping user, a historical shopping action monitoring video frame of a shopping action of the target shopping user having the target shopping action type information is obtained, and a step of performing shopping guiding processing on the target shopping user based on the historical shopping action monitoring video frame includes:

for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user comprises target shopping action type information represented by an action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information, and determining guiding duration information for carrying out shopping guiding based on the historical shopping action monitoring video frame;

and aiming at each target shopping user currently positioned in the target market, carrying out shopping guide processing on the target shopping user based on the historical shopping behavior monitoring video frame corresponding to the target shopping user and the guide duration information.

In some preferred embodiments, in the data processing-based mall shopping guiding method, for each target shopping user currently located in a target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by an action recognition result corresponding to the target shopping user, the step of obtaining a historical shopping action monitoring video frame of a shopping action of the target shopping user having the target shopping action type information, and determining guiding duration information of shopping guiding based on the historical shopping action monitoring video frame includes:

for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information;

for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action identification result corresponding to the target shopping user, determining guiding duration information for carrying out shopping guiding based on a historical shopping action monitoring video frame based on the quantity ratio of the target shopping action type information in the shopping action analysis result, wherein the guiding duration information and the quantity ratio have a negative correlation relationship.

In some preferred embodiments, in the above data processing-based mall shopping guiding method, after the step of determining whether there is a shopping behavior analysis result corresponding to each target shopping user currently located in a target mall based on the historical shopping behavior monitoring video is performed, the mall shopping guiding method further includes:

for each target shopping user currently located in a target market, if it is determined that a shopping behavior analysis result corresponding to the target shopping user is not determined based on the historical shopping behavior monitoring video, acquiring a target shopping behavior monitoring video frame currently having the target shopping user, and performing action recognition processing on the target shopping behavior monitoring video frame to obtain an action recognition result corresponding to the target shopping user, wherein the action recognition result is used for representing target shopping action type information of the target shopping user in the target shopping behavior monitoring video frame;

and aiming at each target shopping user currently positioned in the target market, acquiring a standard shopping action image corresponding to the target shopping action type information corresponding to the target shopping user from a target action image database, and performing shopping guide processing on the target shopping user based on the standard shopping action image.

The embodiment of the invention also provides a data processing-based shopping guide system for shopping malls, which is applied to a shopping behavior monitoring server, wherein the shopping behavior monitoring server is in communication connection with a plurality of shopping behavior monitoring devices, and the data processing-based shopping guide system for shopping malls comprises:

the shopping behavior analyzing and processing module is used for analyzing and processing the historical shopping behavior of each shopping user in the plurality of historical shopping behavior monitoring videos based on a plurality of historical shopping behavior monitoring videos acquired by a plurality of acquired shopping behavior monitoring devices to obtain a shopping behavior analysis result corresponding to each shopping user, wherein the plurality of shopping behavior monitoring devices are respectively arranged in different shopping areas of a target mall and are used for respectively acquiring images of the different shopping areas to obtain corresponding historical shopping behavior monitoring videos;

the behavior analysis result determining module is used for determining whether a shopping behavior analysis result corresponding to each target shopping user is determined based on the historical shopping behavior monitoring video for each target shopping user currently located in the target market;

and the user shopping guide processing module is used for carrying out shopping guide processing on each target shopping user currently located in the target market based on the shopping behavior analysis result if the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video.

In some preferred embodiments, in the data-processing-based guidance system for shopping in a shopping mall, the behavior analysis result determination module is specifically configured to:

In some preferred embodiments, in the data processing-based mall shopping guide system, the user shopping guide processing module is specifically configured to:

In the method and system for guiding shopping in shopping mall based on data processing provided by the embodiment of the invention, after analyzing and processing the historical shopping behaviors of the shopping users based on the obtained multiple historical shopping behavior monitoring videos to obtain the shopping behavior analysis result corresponding to each shopping user, aiming at each target shopping user currently located in the target shopping mall, whether the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video or not can be determined, so that after the shopping behavior analysis result corresponding to the target shopping user is determined, the shopping guide process may be performed for the targeted shopping user based on the shopping behavior analysis result, and thus, different shopping guide processing can be performed for different shopping users to a greater extent so as to guarantee the effect of shopping instructions and improve the problem of poor effect of shopping guide for users in the prior art.

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 a shopping behavior monitoring server according to an embodiment of the present invention.

Fig. 2 is a schematic flow chart of a data processing-based shopping guide method for a shopping mall according to an embodiment of the present invention.

Fig. 3 is a schematic block diagram of a data processing-based shopping guide system 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 a shopping behavior monitoring server. Wherein the shopping behavior monitoring server may include a memory and a processor.

Optionally, in a preferred embodiment, 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 can be used for executing the executable computer program stored in the memory, so as to realize the data processing-based shopping guide method provided by the embodiment of the invention.

Alternatively, in a preferred embodiment, the Memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like.

Alternatively, in a preferred embodiment, 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.

Alternatively, in a preferred embodiment, the structure shown in fig. 1 is only schematic, and the shopping behavior monitoring server may further include more or fewer components than those shown in fig. 1, or have a different configuration than that shown in fig. 1, for example, may include a communication unit for information interaction with other devices (such as shopping behavior monitoring devices, etc.).

With reference to fig. 2, an embodiment of the present invention further provides a data processing-based shopping guide method, which is applicable to the shopping behavior monitoring server. The method steps defined by the flow related to the data processing-based shopping guide method for the shopping mall can be realized by the shopping behavior monitoring server, and the shopping behavior monitoring server is in communication connection with a plurality of shopping behavior monitoring devices. The specific process shown in FIG. 2 will be described in detail below.

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

Step 100, analyzing and processing the historical shopping behavior of each shopping user in the plurality of historical shopping behavior monitoring videos based on a plurality of historical shopping behavior monitoring videos acquired by a plurality of acquired shopping behavior monitoring devices to obtain a shopping behavior analysis result corresponding to each shopping user.

In the embodiment of the present invention, the shopping behavior monitoring server may analyze and process the historical shopping behavior of each shopping user in the plurality of historical shopping behavior monitoring videos based on the obtained plurality of historical shopping behavior monitoring videos collected by the plurality of shopping behavior monitoring devices, so as to obtain a shopping behavior analysis result corresponding to each shopping user. The shopping behavior monitoring devices are respectively arranged in different shopping areas of a target market and used for respectively carrying out image acquisition on the different shopping areas to obtain corresponding historical shopping behavior monitoring videos.

And 200, determining whether a shopping behavior analysis result corresponding to the target shopping user determined based on the historical shopping behavior monitoring video exists or not for each target shopping user currently located in the target market.

In the embodiment of the present invention, the shopping behavior monitoring server may determine, for each target shopping user currently located in a target mall, whether there is a shopping behavior analysis result corresponding to the target shopping user determined based on the historical shopping behavior monitoring video.

Step 300, for each target shopping user currently located in the target mall, if it is determined that there is a shopping behavior analysis result corresponding to the target shopping user based on the historical shopping behavior monitoring video, performing shopping guidance processing on the target shopping user based on the shopping behavior analysis result.

In the embodiment of the present invention, the shopping behavior monitoring server may perform, for each target shopping user currently located in a target mall, a shopping behavior guidance process for the target shopping user based on the shopping behavior analysis result if it is determined that the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video.

Based on the steps of the method, after analyzing the historical shopping behaviors of the shopping users based on the obtained multiple historical shopping behavior monitoring videos to obtain the shopping behavior analysis result corresponding to each shopping user, aiming at each target shopping user currently located in the target market, whether the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video or not can be determined, so that after the shopping behavior analysis result corresponding to the target shopping user is determined, the shopping guide process may be performed for the targeted shopping user based on the shopping behavior analysis result, and thus, different shopping guide processing can be performed for different shopping users to a greater extent so as to guarantee the effect of shopping instructions and improve the problem of poor effect of shopping guide for users in the prior art.

Optionally, in a preferred embodiment, step 100 in the above embodiment may further include step 110, step 120 and step 130, as described below.

Step 110, obtaining historical shopping behavior monitoring videos respectively collected by a plurality of shopping behavior monitoring devices, and obtaining a plurality of historical shopping behavior monitoring videos corresponding to the plurality of shopping behavior monitoring devices.

In the embodiment of the present invention, the shopping behavior monitoring server may obtain historical shopping behavior monitoring videos respectively collected by a plurality of shopping behavior monitoring devices, and obtain a plurality of historical shopping behavior monitoring videos corresponding to the plurality of shopping behavior monitoring devices. The shopping behavior monitoring devices are respectively arranged in different shopping areas of a target market and used for respectively carrying out image acquisition on the different shopping areas to obtain corresponding historical shopping behavior monitoring videos.

And 120, processing the plurality of historical shopping behavior monitoring videos to obtain a historical shopping behavior video of each shopping user in the plurality of historical shopping behavior monitoring videos.

In the embodiment of the present invention, the shopping behavior monitoring server may process the plurality of historical shopping behavior monitoring videos to obtain a historical shopping behavior video of each shopping user in the plurality of historical shopping behavior monitoring videos. Wherein, the historical shopping behavior video comprises each frame of historical shopping behavior video with a shopping user.

Step 130, analyzing and processing the historical shopping behavior of the shopping user based on the historical shopping behavior video corresponding to the shopping user for the shopping user corresponding to each obtained historical shopping behavior video to obtain a shopping behavior analysis result corresponding to the shopping user.

In the embodiment of the present invention, the shopping behavior monitoring server may analyze, based on the historical shopping behavior video corresponding to the shopping user, the historical shopping behavior of the shopping user for the shopping user corresponding to each obtained historical shopping behavior video, so as to obtain a shopping behavior analysis result corresponding to the shopping user.

Based on the steps included in the method, after the plurality of historical shopping behavior monitoring videos corresponding to the plurality of shopping behavior monitoring devices are obtained, the plurality of historical shopping behavior monitoring videos can be processed to obtain the historical shopping behavior video of each shopping user in the plurality of historical shopping behavior monitoring videos, so that the historical shopping behavior of each shopping user can be analyzed based on the historical shopping behavior video corresponding to the shopping user to obtain the shopping behavior analysis result corresponding to the shopping user, the problem of mutual interference among the shopping users in the same frame of video frame can be avoided, the analysis effect is guaranteed, and the problem of poor effect of analyzing the shopping behavior of the shopping mall in the prior art is solved.

Optionally, in a preferred embodiment, the step 110 in the above embodiment may further include the following steps:

firstly, acquiring current time information and determining whether the current time information reaches target time information; if it is determined that the current time information reaches the target time information, generating historical video acquisition request information, and sending the historical video acquisition request information to each shopping behavior monitoring device of a plurality of shopping behavior monitoring devices in communication connection, wherein each shopping behavior monitoring device is used for sending historical shopping behavior monitoring videos acquired before the target time information to the shopping behavior monitoring server based on the historical video acquisition request information;

secondly, historical shopping behavior monitoring videos sent by each shopping behavior monitoring server based on the historical video acquisition request information are acquired respectively, and a plurality of historical shopping behavior monitoring videos corresponding to the plurality of shopping behavior monitoring devices are obtained.

Optionally, in another preferred embodiment, the step 110 in the foregoing embodiment may also further include the following steps:

firstly, acquiring current time information and determining whether the current time information reaches target time information; if it is determined that the current time information reaches the target time information, generating historical video acquisition request information, and sending the historical video acquisition request information to a historical video storage data server in communication connection (for example, the shopping behavior monitoring device cannot store more monitoring videos), wherein the historical video storage data server is used for sending historical shopping behavior monitoring videos acquired by the plurality of shopping behavior monitoring devices respectively before the target time information to the shopping behavior monitoring server based on the historical video acquisition request information;

and secondly, acquiring the historical shopping behavior monitoring videos sent by the historical video storage data server based on the historical video acquisition request information to obtain a plurality of historical shopping behavior monitoring videos corresponding to the plurality of shopping behavior monitoring devices.

Optionally, in a preferred embodiment, the step 120 in the above embodiment may further include the following steps:

firstly, aiming at each historical shopping behavior monitoring video in the multiple historical shopping behavior monitoring videos, carrying out object recognition processing on a historical shopping behavior monitoring video frame included in the historical shopping behavior monitoring video so as to determine whether a shopping user exists in the historical shopping behavior monitoring video frame;

secondly, screening out each frame of historical shopping behavior monitoring video frame without the shopping user in the historical shopping behavior monitoring videos aiming at each historical shopping behavior monitoring video in the plurality of historical shopping behavior monitoring videos, and obtaining updated historical shopping behavior monitoring videos corresponding to the historical shopping behavior monitoring videos based on each frame of historical shopping behavior monitoring video frame with the shopping user in the historical shopping behavior monitoring videos, wherein each frame of historical shopping behavior monitoring video frame has each historical shopping behavior monitoring video of the shopping user, and the historical shopping behavior monitoring videos are used as the corresponding updated historical shopping behavior monitoring videos;

then, each updated historical shopping behavior monitoring video (each frame of video has a shopping user) is processed to obtain a historical shopping behavior video of each shopping user in the plurality of historical shopping behavior monitoring videos.

Optionally, in a preferred embodiment, the step "processing each updated historical shopping behavior monitoring video to obtain a historical shopping behavior video of each shopping user in the multiple historical shopping behavior monitoring videos" in the foregoing embodiment may further include:

firstly, counting the number of shopping users in each frame of historical shopping behavior monitoring video frame included in each updated historical shopping behavior monitoring video to obtain the number of users corresponding to the historical shopping behavior monitoring video frame;

secondly, determining each frame of historical shopping behavior monitoring video frame included in each updated historical shopping behavior monitoring video as a frame of historical shopping behavior video frame if the number of users corresponding to the historical shopping behavior monitoring video frame is 1;

then, for each frame of historical shopping behavior monitoring video frame included in each updated historical shopping behavior monitoring video, if the number of users corresponding to the historical shopping behavior monitoring video frame is greater than 1, performing video frame segmentation processing on the basis of monitoring users of the historical shopping behavior monitoring video frame to obtain a corresponding user number frame of historical shopping behavior video frame, wherein each frame of historical shopping behavior video frame includes all image information of one monitoring user, and multiple frames of historical shopping behavior videos corresponding to the same frame of historical shopping behavior monitoring video are spliced to form the historical shopping behavior monitoring video based on a segmentation relation of the video segmentation processing;

then classifying the obtained multiple frames of historical shopping behavior video frames based on whether shopping users in each frame of historical shopping behavior video frame are the same or not to obtain at least one historical video frame set corresponding to the multiple frames of historical shopping behavior video frames, wherein each historical video frame set comprises at least one historical shopping behavior video frame;

and finally, sequencing each frame of historical shopping behavior video frames included in the historical video frame set according to the corresponding video frame acquisition time aiming at each historical video frame set to obtain the historical shopping behavior video of the monitoring user corresponding to the historical video frame set.

Optionally, in a preferred embodiment, the step 130 in the above embodiment may further include the following steps:

firstly, aiming at a shopping user corresponding to each obtained historical shopping behavior video, carrying out duplicate removal screening processing on the historical shopping behavior video corresponding to the shopping user to obtain a historical shopping behavior screening video corresponding to the shopping user, wherein each historical shopping behavior screening video comprises at least one frame of historical shopping behavior video frame;

secondly, for each shopping user, screening historical shopping behavior video frames included in the video based on the historical shopping behavior corresponding to the shopping user, and analyzing and processing the historical shopping behavior of the shopping user to obtain a shopping behavior analysis result corresponding to the shopping user.

Optionally, in a preferred embodiment, the step "performing, for a shopping user corresponding to each obtained historical shopping behavior video, deduplication screening processing on the historical shopping behavior video corresponding to the shopping user to obtain a historical shopping behavior screening video corresponding to the shopping user" in the above embodiment may further include:

firstly, determining whether the historical shopping behavior video has historical shopping behavior video segments or not according to each obtained historical shopping behavior video, wherein each historical shopping behavior video segment comprises at least two continuous same historical shopping behavior video frames;

secondly, aiming at each obtained historical shopping behavior video, if the historical shopping behavior video has at least one historical shopping behavior video segment, performing duplicate removal screening processing on each historical shopping behavior video segment to obtain a historical shopping behavior screening video corresponding to a shopping user corresponding to the historical shopping behavior video;

then, for each obtained historical shopping behavior video, if the historical shopping behavior video does not have at least one historical shopping behavior video segment, the historical shopping behavior video is used as a historical shopping behavior screening video corresponding to a shopping user corresponding to the historical shopping behavior video.

Optionally, in a preferred embodiment, the step "for each obtained historical shopping behavior video, if the historical shopping behavior video has at least one historical shopping behavior video segment, performing deduplication screening processing on each historical shopping behavior video segment to obtain a historical shopping behavior screening video corresponding to a shopping user corresponding to the historical shopping behavior video" in the above embodiment may further include:

and for each obtained historical shopping behavior video, if the historical shopping behavior video has at least one historical shopping behavior video segment, retaining one frame of historical shopping behavior video frame included in each historical shopping behavior video segment and other historical shopping behavior video frames except the historical shopping behavior video segment, and obtaining a historical shopping behavior screening video corresponding to the shopping user corresponding to the historical shopping behavior video.

Optionally, in a preferred embodiment, the step "for each shopping user, screening a historical shopping behavior video frame included in a video based on the historical shopping behavior corresponding to the shopping user, and performing analysis processing on the historical shopping behavior of the shopping user to obtain a shopping behavior analysis result corresponding to the shopping user" in the foregoing embodiment may further include:

firstly, for each shopping user, carrying out target sampling and screening processing on a historical shopping behavior video frame included in a historical shopping behavior screening video corresponding to the shopping user to obtain a historical shopping behavior representative video corresponding to the shopping user;

secondly, analyzing and processing the historical shopping behaviors of the shopping users based on the historical shopping behavior video frames included in the historical shopping behavior representative video corresponding to the shopping users to obtain the shopping behavior analysis results corresponding to the shopping users.

Optionally, in a preferred embodiment, the target sample screening process in the foregoing embodiment may further include:

firstly, performing pixel value calculation processing on each frame of historical shopping behavior video frame included in the historical shopping behavior screening video, determining a pixel value and a value corresponding to each frame of the historical shopping behavior video frame, calculating a discrete degree value of the pixel value of each pixel point in the historical shopping behavior video frame aiming at each frame of the historical shopping behavior video frame, and determining one frame of the historical shopping behavior video frame with the maximum discrete degree value;

secondly, for each pixel value interval (such as 0-49, 50-99 and the like) in a plurality of continuous pixel value intervals divided in advance, constructing and obtaining a historical shopping behavior video frame sequence corresponding to the pixel value interval based on the corresponding pixel value and each historical shopping behavior video frame of which the value belongs to the pixel value interval, determining the historical shopping behavior video frame sequence corresponding to the historical shopping behavior video frame with the maximum discrete degree value as a first historical shopping behavior video frame sequence, and determining each other historical shopping behavior video frame sequence except the first historical shopping behavior video frame sequence as a second historical shopping behavior video frame sequence;

thirdly, counting the number of frames of historical shopping behavior video frames included in the first historical shopping behavior video frame sequence to obtain a first statistical frame number corresponding to the first historical shopping behavior video frame sequence, and determining each second historical shopping behavior video frame sequence of which the number of frames of the historical shopping behavior video frames is greater than or equal to the first statistical frame number to serve as a candidate second historical shopping behavior video frame sequence;

fourthly, determining a target statistical frame number (any one or the first statistical frame number) which is less than or equal to the first statistical frame number, determining continuous historical shopping behavior video frames of the target statistical frame number in the first historical shopping behavior video frame sequence to form a corresponding first historical video frame subsequence, and determining continuous historical shopping behavior video frames of the target statistical frame number in each candidate second historical shopping behavior video frame sequence to form a corresponding second historical video frame subsequence respectively;

fifthly, aiming at each second historical video frame subsequence, matching each frame of historical shopping behavior video frame in the second historical video frame subsequence with the historical shopping behavior video frame at the corresponding sequence position in the first historical video frame subsequence, and determining a target historical shopping behavior video frame (if the video frame similarity is greater than a preset threshold) matched with the historical shopping behavior video frame at the corresponding sequence position in the first historical video frame subsequence in the second historical video frame subsequence;

sixthly, determining whether a corresponding second historical video frame subsequence is a target second historical video frame subsequence matched with the first historical video frame subsequence (if the number of the target historical shopping behavior video frames included by the target second historical video frame subsequence is larger than or equal to the target frame number), and determining a collection time interval formed by video frame collection time of the historical shopping behavior video frames included by each target second historical video frame subsequence;

seventhly, determining whether a candidate second historical shopping behavior video frame sequence corresponding to the target second historical video frame subsequence is a target second historical shopping behavior video frame sequence or not based on the ratio of the acquisition time interval of the target second historical video frame subsequence to the number of frames of the target historical shopping behavior video frames included in the target second historical video frame subsequence for each target second historical video frame subsequence, and each frame of historical shopping behavior video frame included in the first historical shopping behavior video frame sequence and each frame of historical shopping behavior video frame included in the target second historical shopping behavior video frame sequence are used as historical shopping behavior representative videos corresponding to shopping users, and the ratio corresponding to the target second historical video frame subsequence corresponding to the target second historical shopping behavior video frame sequence is less than or equal to a preset frame ratio threshold value.

Optionally, in a preferred embodiment, the step "for each shopping user, analyzing the historical shopping behavior of the shopping user based on a historical shopping behavior video frame included in the historical shopping behavior representative video corresponding to the shopping user to obtain a shopping behavior analysis result corresponding to the shopping user" in the foregoing embodiment may further include:

firstly, aiming at each shopping user, performing action recognition processing on each frame of historical shopping behavior video frame included in a historical shopping behavior representative video corresponding to the shopping user to obtain shopping action type information corresponding to each frame of historical shopping behavior video frame;

secondly, counting the number ratio of the historical shopping behavior video frames corresponding to each shopping action type information corresponding to each shopping user, and updating the number ratio of the historical shopping behavior video frames corresponding to each shopping action type information corresponding to each shopping user based on the number ratio of the historical shopping action video frames corresponding to each shopping action type information corresponding to the associated shopping user having an association relationship with the shopping user (for example, if the number ratio of the B type action of the shopping user A is C, and the number ratio of the B type action of the associated shopping user D is E, then updating C based on E can be performed, wherein the value of E is larger, the value of the updated C is larger, for example, the sum of E and C is directly calculated, or the product of E and a coefficient smaller than 1 can be calculated first, and then calculating the sum of the product and C) to obtain the updated number ratio of the historical shopping behavior video frames corresponding to each shopping action type information corresponding to the shopping user as the shopping behavior analysis result corresponding to the shopping user, wherein the number of the associated shopping user and the number of the shopping user in the same frame of historical shopping behavior monitoring video frame are more than the preset number of frames.

Optionally, in a preferred embodiment, the step 200 in the above embodiment may further include the following steps:

firstly, acquiring target shopping behavior monitoring video frames currently acquired by the plurality of shopping behavior monitoring devices, and acquiring multi-frame target shopping behavior monitoring video frames corresponding to the plurality of shopping behavior monitoring devices;

secondly, performing object discrimination processing (for example, discrimination based on an object discrimination model obtained by training in the prior art) on each target shopping behavior surveillance video frame in the multiple frames of target shopping behavior surveillance video frames to determine whether a target shopping user in the target shopping behavior surveillance video frame belongs to a surveillance user in the multiple historical shopping behavior surveillance videos, and when determining that the target shopping user in the target shopping behavior surveillance video frame belongs to a surveillance user in the multiple historical shopping behavior surveillance videos, determining that a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior surveillance video, and when determining that the target shopping user in the target shopping behavior surveillance video frame does not belong to a surveillance user in the multiple historical shopping behavior surveillance videos, and determining that the shopping behavior analysis result corresponding to the target shopping user is not determined based on the historical shopping behavior monitoring video.

Optionally, in a preferred embodiment, the step "obtaining target shopping behavior monitoring video frames currently collected by the multiple shopping behavior monitoring devices to obtain multiple frames of target shopping behavior monitoring video frames corresponding to the multiple shopping behavior monitoring devices" in the above embodiment further includes:

firstly, judging whether the current time belongs to preset target time, wherein the target time is determined based on the opening time of the target market;

secondly, if the current time belongs to the target time, generating corresponding monitoring starting notification information, and sending the monitoring starting notification information to each shopping behavior monitoring device in the plurality of shopping behavior monitoring devices, wherein each shopping behavior monitoring device starts image acquisition based on the monitoring starting notification information and sends a currently acquired target shopping behavior monitoring video frame to the shopping behavior monitoring server;

and then, acquiring a target shopping behavior monitoring video frame currently acquired and sent by each shopping behavior monitoring device based on the monitoring starting notification information.

Optionally, in a preferred embodiment, the step 300 in the above embodiment may further include the following steps:

firstly, for each target shopping user currently located in a target market, if a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, acquiring a target shopping behavior monitoring video frame currently having the target shopping user, and performing action recognition processing on the target shopping behavior monitoring video frame to obtain an action recognition result corresponding to the target shopping user, wherein the action recognition result is used for representing target shopping action type information of the target shopping user in the target shopping behavior monitoring video frame;

secondly, for each target shopping user currently located in a target market, if it is determined that a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, determining whether shopping action type information in the shopping behavior analysis result includes target shopping action type information represented by an action identification result corresponding to the target shopping user;

then, for each target shopping user currently located in a target mall, if the shopping action type information in the shopping behavior analysis result corresponding to the target shopping user does not include the target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a standard shopping action image corresponding to the target shopping action type information from a target action image database, and performing shopping guide processing on the target shopping user based on the standard shopping action image (for example, controlling a display device located in an area where the target shopping user is located to display the standard shopping action image);

finally, for each target shopping user currently located in the target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes the target shopping action type information represented by the action identification result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information, and performing shopping guide processing on the target shopping user based on the historical shopping action monitoring video frame.

Optionally, in a preferred embodiment, the step "in the above embodiment, for each target shopping user currently located in a target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by an action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of a shopping action of the target shopping user having the target shopping action type information, and performing shopping guide processing on the target shopping user based on the historical shopping action monitoring video frame", may further include:

firstly, for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by an action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information, and determining guiding duration information for carrying out shopping guiding based on the historical shopping action monitoring video frame;

secondly, aiming at each target shopping user currently located in the target market, based on the historical shopping behavior monitoring video frame and the guiding duration information corresponding to the target shopping user, carrying out shopping guiding processing on the target shopping user.

Optionally, in a preferred embodiment, the step "in the above embodiment, for each target shopping user currently located in the target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user having the target shopping action type information, and determining guidance duration information for guiding shopping based on the historical shopping action monitoring video frame", may further include:

firstly, for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by an action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information;

secondly, for each target shopping user currently located in the target mall, if the shopping action type information in the shopping behavior analysis result corresponding to the target shopping user includes the target shopping action type information represented by the action identification result corresponding to the target shopping user, determining guiding duration information for carrying out shopping guiding based on the historical shopping behavior monitoring video frame based on the quantity ratio of the target shopping action type information in the shopping behavior analysis result, wherein the guiding duration information and the quantity ratio have a negative correlation (namely, the more familiar the action is, the shorter the guiding duration is).

Optionally, in a preferred embodiment, after performing step 200 in the above embodiment, the data processing-based mall shopping guiding method may further include the following steps:

firstly, for each target shopping user currently located in a target market, if it is determined that a shopping behavior analysis result corresponding to the target shopping user is not determined based on the historical shopping behavior monitoring video, acquiring a target shopping behavior monitoring video frame currently having the target shopping user, and performing action recognition processing on the target shopping behavior monitoring video frame to obtain an action recognition result corresponding to the target shopping user, wherein the action recognition result is used for representing target shopping action type information of the target shopping user in the target shopping behavior monitoring video frame;

next, for each target shopping user currently located in the target mall, a standard shopping motion image corresponding to the target shopping motion type information corresponding to the target shopping user is acquired from the target motion image database, and the target shopping user is subjected to shopping guide processing based on the standard shopping motion image (refer to the related example described above).

With reference to fig. 3, an embodiment of the present invention further provides a data processing-based shopping guide system for a shopping mall, which is applicable to the shopping behavior monitoring server. Wherein, the market shopping guiding system based on data processing may comprise:

a shopping behavior analyzing and processing module (as in step 100 above) configured to analyze and process a historical shopping behavior of each shopping user in a plurality of historical shopping behavior monitoring videos acquired by a plurality of obtained shopping behavior monitoring devices to obtain a shopping behavior analysis result corresponding to each shopping user, where the plurality of shopping behavior monitoring devices are respectively disposed in different shopping areas of a target mall and are configured to respectively perform image acquisition on the different shopping areas to obtain corresponding historical shopping behavior monitoring videos;

a behavior analysis result determining module (as in step 200 above) configured to determine, for each target shopping user currently located in a target mall, whether there is a shopping behavior analysis result corresponding to the target shopping user determined based on the historical shopping behavior monitoring video;

the user shopping guide processing module (as the step 300) is configured to, for each target shopping user currently located in the target mall, perform shopping guide processing on the target shopping user based on the shopping behavior analysis result if it is determined that the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video.

Optionally, in a preferred embodiment, the behavior analysis result determining module in the foregoing embodiment is specifically configured to:

acquiring target shopping behavior monitoring video frames currently acquired by the plurality of shopping behavior monitoring devices to obtain multi-frame target shopping behavior monitoring video frames corresponding to the plurality of shopping behavior monitoring devices; monitoring video frames for each of the plurality of frames of target shopping behavior monitoring video frames, performing object discrimination processing on the target shopping behavior monitoring video frame to determine whether a target shopping user in the target shopping behavior monitoring video frame belongs to a monitoring user in the plurality of historical shopping behavior monitoring videos, and when it is determined that the target shopping behavior monitoring video frame contains a plurality of monitoring users in the historical shopping behavior monitoring videos, determining that the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, and upon determining that the targeted shopping behavior monitoring video frame does not include a monitoring user in the plurality of historical shopping behavior monitoring videos, and determining that the shopping behavior analysis result corresponding to the target shopping user is not determined based on the historical shopping behavior monitoring video.

Optionally, in a preferred embodiment, the user shopping guide processing module in the foregoing embodiment is specifically configured to:

for each target shopping user currently located in a target market, if a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, acquiring a target shopping behavior monitoring video frame currently having the target shopping user, and performing action recognition processing on the target shopping behavior monitoring video frame to obtain an action recognition result corresponding to the target shopping user, wherein the action recognition result is used for representing target shopping action type information of the target shopping user in the target shopping behavior monitoring video frame; for each target shopping user currently located in a target market, if it is determined that a shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video, determining whether shopping action type information in the shopping behavior analysis result includes target shopping action type information represented by an action recognition result corresponding to the target shopping user; for each target shopping user currently located in a target mall, if the shopping action type information in the shopping behavior analysis result corresponding to the target shopping user does not include the target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a standard shopping action image corresponding to the target shopping action type information from a target action image database, and performing shopping guide processing on the target shopping user based on the standard shopping action image; for each target shopping user currently located in a target market, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action recognition result corresponding to the target shopping user, acquiring a historical shopping action monitoring video frame of the shopping action of the target shopping user with the target shopping action type information, and performing shopping guide processing on the target shopping user based on the historical shopping action monitoring video frame.

In summary, the present invention provides a method and a system for guiding shopping in shopping mall based on data processing, after analyzing the historical shopping behaviors of the shopping users based on the obtained multiple historical shopping behavior monitoring videos to obtain a shopping behavior analysis result corresponding to each shopping user, aiming at each target shopping user currently located in a target market, whether the shopping behavior analysis result corresponding to the target shopping user is determined based on the historical shopping behavior monitoring video or not can be determined, so that after the shopping behavior analysis result corresponding to the target shopping user is determined, the shopping guide process may be performed for the targeted shopping user based on the shopping behavior analysis result, and thus, different shopping guide processing can be performed for different shopping users to a greater extent so as to guarantee the effect of shopping instructions and improve the problem of poor effect of shopping guide for users 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

1. A market shopping guiding method based on data processing is characterized in that the method is applied to a shopping behavior monitoring server, the shopping behavior monitoring server is in communication connection with a plurality of shopping behavior monitoring devices, and the market shopping guiding method based on data processing comprises the following steps:

2. A mall shopping guiding method based on data processing as claimed in claim 1, wherein said step of determining whether there is a shopping behavior analysis result corresponding to the target shopping user determined based on the historical shopping behavior monitoring video for each target shopping user currently located in the target mall comprises:

3. A mall shopping guiding method based on data processing as claimed in claim 2, wherein said step of obtaining target shopping behavior monitoring video frames currently collected by said plurality of shopping behavior monitoring devices to obtain multi-frame target shopping behavior monitoring video frames corresponding to said plurality of shopping behavior monitoring devices comprises:

4. A mall shopping guidance method according to claim 1, wherein if it is determined that there is a shopping behavior analysis result corresponding to the target shopping user based on the historical shopping behavior monitoring video, the step of performing shopping guidance processing on the target shopping user based on the shopping behavior analysis result comprises:

5. The data processing-based mall shopping guiding method according to claim 4, wherein for each target shopping user currently located in the target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes the target shopping action type information represented by the action recognition result corresponding to the target shopping user, the step of obtaining a historical shopping action monitoring video frame of the shopping action of the target shopping user having the target shopping action type information, and performing shopping guiding processing on the target shopping user based on the historical shopping action monitoring video frame comprises:

6. The data-processing-based mall shopping guiding method according to claim 5, wherein for each target shopping user currently located in the target mall, if the shopping action type information in the shopping action analysis result corresponding to the target shopping user includes target shopping action type information represented by the action recognition result corresponding to the target shopping user, the step of obtaining a historical shopping action monitoring video frame of the shopping action of the target shopping user having the target shopping action type information, and determining guiding duration information for guiding shopping based on the historical shopping action monitoring video frame comprises:

7. The data-processing-based mall shopping guiding method according to any one of claims 1-6, wherein after the step of determining whether there is a shopping behavior analysis result corresponding to each target shopping user currently located in the target mall based on the historical shopping behavior monitoring video, the mall shopping guiding method further comprises:

8. The utility model provides a market shopping guide system based on data processing which characterized in that is applied to shopping behavior monitoring server, shopping behavior monitoring server communication connection has a plurality of shopping behavior monitoring devices, market shopping guide system based on data processing includes:

9. A data processing-based mall shopping guide system according to claim 8, wherein said behavior analysis result determining module is specifically configured to:

10. A mall shopping guide system based on data processing as claimed in claim 8, wherein said user shopping guide processing module is specifically configured to: