CN115860860A - Smart community choice commodity big data group purchase method and system based on artificial intelligence - Google Patents
Smart community choice commodity big data group purchase method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115860860A CN115860860A CN202211476162.3A CN202211476162A CN115860860A CN 115860860 A CN115860860 A CN 115860860A CN 202211476162 A CN202211476162 A CN 202211476162A CN 115860860 A CN115860860 A CN 115860860A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- commodity
- resident
- community
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent community selected commodity big data group purchase method and system based on artificial intelligence, and relates to the technical field of data processing. The method comprises the following steps: acquiring face template images of a plurality of age groups; judging the age bracket of the resident; counting and pushing corresponding commodities to the community residents according to the overall age proportion of the community residents; displaying the three-dimensional reconstruction result of the commodity to residents of the community; calculating and judging and marking the immersion degree of the resident according to the similarity between each facial expression image and the high-immersion degree face template image; if the immersion degree of the resident is high, commodity purchase confirmation information is generated and sent to the resident, and deduction is carried out in the corresponding resident account; and counting and judging whether the preset group purchase requirement is met or not according to the commodity purchase data of the residents in the community, and if so, calculating and returning the corresponding commodity price difference to the corresponding resident account. The invention realizes accurate and efficient commodity group purchase by matching various methods.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a big data group purchase method and system for smart community selected commodities based on artificial intelligence.
Background
In recent years, the construction of smart communities has received high attention from the nation and society. Especially, with the progress of science and technology, more and more smart communities appear in cities and play more and more important roles. The intelligent group purchase is used as an emerging consumption mode of the intelligent community, and huge life convenience is provided for community residents in an intelligent consumption mode.
However, the traditional intelligent group purchase often has no good pertinence, and the commodity recommendation cannot be carried out according to the age distribution of community residents and the immersion degree of the residents in watching the commodity, so that the practical application value of the intelligent group purchase is remarkably reduced. With the development of the technology in the field of artificial intelligence, direct technical support is provided for high-quality group purchase of the smart community. Therefore, how to combine the artificial intelligence technology to realize the high-efficiency smart community choice commodity big data group purchase becomes a problem which needs to be solved urgently.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, embodiments of the present invention provide a method and a system for smart community big data group purchase of selected commodities based on artificial intelligence, which implement accurate and efficient commodity group purchase by using a sparse matching method based on core saliency region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multi-scale hash coding similarity matching method, and the like.
The embodiment of the invention is realized by the following steps:
in a first aspect, an embodiment of the invention provides an intelligent community choice commodity big data group purchase method based on artificial intelligence, which includes the following steps:
acquiring face template images of a plurality of age groups;
for any resident entering and exiting the community, extracting a face image of the resident as a face image to be detected, respectively calculating the similarity between the face image to be detected and the face template image of each age group by using a sparse matching method based on core significance region detection, generating and judging the age group of the resident according to the corresponding similarity value;
according to a preset acquisition period, judging the age groups of all residents entering and exiting the community, counting and pushing corresponding commodities to the residents in the community according to the integral age proportion of the residents in the community;
for any commodity pushed to residents in the community, performing three-dimensional reconstruction on the commodity image by using a preferred three-dimensional reconstruction method based on the image enhancement result to obtain and display the three-dimensional reconstruction result of the commodity to the residents in the community;
selecting a high-immersion face template image;
when any resident of the community watches the three-dimensional reconstruction result of the commodity, the identity of the resident is recognized by using a face recognition technology, a face expression video when the resident watches the commodity is collected, and a plurality of face expression images are extracted from the face expression video at the same intervals;
calculating and judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high immersion degree face template image by using a multi-scale-based Hash coding similarity matching method;
if the immersion degree information of the resident is high, commodity purchase confirmation information is generated and sent to the resident, and deduction is carried out in a corresponding resident account according to the resident confirmation result;
and counting and judging whether the preset group purchase requirement is met or not according to the commodity purchase data of the residents in the community, if so, confirming that the grouping is successful, calculating and returning the corresponding commodity price difference to the corresponding resident account to finish the group purchase.
In order to solve the problems in the prior art, the method respectively calculates the similarity between the facial image to be detected and various template images by using a sparse matching method based on core significance region detection, and judges the age bracket corresponding to the resident by using the similarity, thereby providing direct support for measuring and calculating the integral age ratio of the residents in the community. The method also utilizes a three-dimensional reconstruction method based on image enhancement result optimization to carry out high-quality three-dimensional reconstruction on the commodity image, and remarkably improves the three-dimensional display effect of the commodity. By utilizing the multi-scale Hash coding similarity matching method, the immersion degree of the residents watching the three-dimensional model display of the commodity is more accurately evaluated, and the residents are timely reminded if the immersion degree is high, so that the residents can use the immersion degree as an important reference for purchasing the commodity. The method realizes accurate and efficient commodity group purchase by utilizing the cooperation of various methods such as a sparse matching method based on core significance region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multi-scale Hash coding similarity matching method and the like.
Based on the first aspect, in some embodiments of the present invention, the method for calculating the similarity between the face image to be detected and the face template images of each age group respectively by using the sparse matching method based on the core saliency region detection includes the following steps:
respectively carrying out core significance region detection on the face image to be detected and each face template image to obtain a corresponding core significance region image of the face to be detected and a plurality of core significance region images of the face templates;
and respectively carrying out sparse coding on the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates, and calculating the similarity between the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates by using the Euclidean distance.
Based on the first aspect, in some embodiments of the present invention, the method for detecting a core significant region of a face image to be detected and each face template image respectively includes the following steps:
respectively carrying out significance detection on the face image to be detected and each face template image so as to obtain a corresponding first face significant image to be detected and a plurality of first face template significant images;
carrying out depth denoising on the face image to be detected and each face template image by using an image denoising method to obtain and carry out significance detection on the denoised image to be detected and the denoised images of various templates so as to obtain a corresponding second face significant image to be detected and a plurality of second face template significant images;
and taking the superposed part of the first to-be-detected face significant image and the second to-be-detected face significant image as a to-be-detected face core significant area image, and taking the superposed part of each corresponding first face template significant image and the corresponding second face template significant image as a corresponding face template core significant area image.
Based on the first aspect, in some embodiments of the present invention, the method for three-dimensionally reconstructing the commodity image by using the three-dimensional reconstruction method based on the image enhancement result preferably includes the following steps:
enhancing the commodity images by using a plurality of image enhancement methods to obtain a plurality of commodity enhanced images;
carrying out peak signal-to-noise ratio detection on each commodity enhanced image to obtain and select an optimal commodity enhanced image according to each peak signal-to-noise ratio result;
and performing three-dimensional reconstruction on the optimal commodity enhanced image by using a single image-based three-dimensional reconstruction technology.
Based on the first aspect, in some embodiments of the present invention, the above method for calculating and determining and marking the immersion degree information of the resident according to the similarity between each facial expression image and the high immersion degree face template image by using the multi-scale based hash coding similarity matching method includes the following steps:
respectively carrying out multi-scale reconstruction on each facial expression image and each high-immersion face template image to obtain facial expression images and high-immersion face template images under multiple scales;
and respectively carrying out Hash coding on the facial expression image and the high-immersion face template image under each scale, and calculating the similarity between the corresponding facial expression image and the high-immersion face template image under each scale by using the Euclidean distance so as to obtain and judge and mark the immersion information of the residents according to the similarity results under multiple scales.
In a second aspect, an embodiment of the present invention provides an intelligent community choice commodity big data group purchase system based on artificial intelligence, including: age bracket template module, age bracket judge module, age statistics module, commodity show module, the module is selected to the immersion degree, people's face acquisition module, immersion degree judge module, commodity purchase module and piece together and judge the module, wherein:
the age group template module is used for acquiring face template images of a plurality of age groups;
the age group judging module is used for extracting the face image of any resident entering and exiting the community as a face image to be detected, respectively calculating the similarity between the face image to be detected and the face template image of each age group by using a sparse matching method based on core significance region detection, generating and judging the age group of the resident according to the corresponding similarity value;
the age counting module is used for judging the age groups of all residents entering and exiting the community according to a preset acquisition period, counting and pushing corresponding commodities to the community residents according to the integral age proportion of the community residents;
the commodity display module is used for carrying out three-dimensional reconstruction on the commodity image by utilizing a three-dimensional reconstruction method based on image enhancement result optimization for any commodity pushed to the community residents so as to obtain and display the three-dimensional reconstruction result of the commodity to the community residents;
the immersion degree selecting module is used for selecting a high-immersion degree face template image;
the face acquisition module is used for identifying the identity of any resident in the community by using a face recognition technology when the resident watches the three-dimensional reconstruction result of the commodity, acquiring a face expression video when the resident watches the face expression video and extracting a plurality of face expression images from the face expression video at the same interval;
the immersion degree judging module is used for calculating, judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high-immersion degree face template image by utilizing a multi-scale-based Hash coding similarity matching method;
the commodity purchasing module is used for generating and sending commodity purchasing confirmation information to the resident if the immersion degree information of the resident is high, and obtaining and deducting money in a corresponding resident account according to the resident confirmation result;
and the group-piecing judging module is used for counting and judging whether the preset group-buying requirement is met or not according to the commodity purchasing data of residents in the community, if so, the group-piecing is confirmed to be successful, and the corresponding commodity price difference is calculated and returned to the corresponding resident account to complete the group-buying.
In order to solve the problems in the prior art, the system is matched with a plurality of modules such as an age group template module, an age group judging module, an age counting module, a commodity display module, an immersion degree selecting module, a face collecting module, an immersion degree judging module, a commodity purchasing module and a grouping judging module through the age group template module, the similarity of a face image to be detected and various template images is respectively calculated by using a sparse matching method based on core significance region detection, the age group corresponding to a resident is judged by using the similarity, and direct support is provided for measuring the integral age proportion of the resident in the community. The system also performs high-quality three-dimensional reconstruction on the commodity image by using a three-dimensional reconstruction method based on image enhancement result optimization, and remarkably improves the three-dimensional display effect of the commodity. By utilizing the multi-scale Hash coding similarity matching method, the immersion degree of the residents watching the three-dimensional model display of the commodity is more accurately evaluated, and the residents are timely reminded if the immersion degree is high, so that the residents can use the immersion degree as an important reference for purchasing the commodity. The method realizes accurate and efficient commodity group purchase by matching various methods such as a sparse matching method based on core significance region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multiscale Hash coding similarity matching method and the like.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory for storing one or more programs; a processor. The program or programs, when executed by a processor, implement the method of any of the first aspects as described above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method according to any one of the first aspect described above.
The embodiment of the invention at least has the following advantages or beneficial effects:
the embodiment of the invention provides a smart community selected commodity big data group purchase method and system based on artificial intelligence, and accurate and efficient commodity group purchase is realized by matching various methods such as a sparse matching method based on core significance region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multiscale Hash coding similarity matching method and the like.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart of a smart community big data group purchase method for selected commodities based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a sparse matching method based on core saliency region detection to calculate similarity in an intelligent community choice commodity big data group purchase method based on artificial intelligence according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating three-dimensional reconstruction of a commodity image by using a three-dimensional reconstruction method based on image enhancement result optimization in a group purchase method of smart community culled commodity big data based on artificial intelligence according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a smart community choice commodity big data group purchase system based on artificial intelligence according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Description of reference numerals: 100. an age group template module; 200. an age group determination module; 300. an age statistics module; 400. a merchandise display module; 500. an immersion level selection module; 600. a face acquisition module; 700. an immersion degree determination module; 800. a commodity purchasing module; 900. a grouping judgment module; 101. a memory; 102. a processor; 103. a communication interface.
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 some, but not all, embodiments of the present invention. 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.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
Example (b):
as shown in fig. 1-3, in a first aspect, an embodiment of the present invention provides a method for intelligent community big data group purchase of selected commodities based on artificial intelligence, including the following steps:
s1, collecting face template images of a plurality of age groups; and collecting representative old people face template images, middle-aged people face template images, young people face template images and children face template images respectively, and providing accurate image reference of different age groups for follow-up.
S2, for any resident entering and exiting the community, extracting a face image of the resident as a face image to be detected, respectively calculating the similarity between the face image to be detected and the face template image of each age group by using a sparse matching method based on core salient region detection, generating and judging the age group of the resident according to the corresponding similarity value;
further, as shown in fig. 2, the method includes:
s21, respectively carrying out core significance region detection on the face image to be detected and each face template image to obtain a corresponding to-be-detected face core significance region image and a plurality of face template core significance region images;
and S22, respectively carrying out sparse coding on the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates, and calculating the similarity between the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates by using the Euclidean distance.
Further, the method for respectively detecting the core saliency areas of the face image to be detected and each face template image comprises the following steps:
respectively carrying out significance detection on the face image to be detected and each face template image so as to obtain a corresponding first face significant image to be detected and a plurality of first face template significant images; carrying out depth denoising on the face image to be detected and each face template image by using an image denoising method to obtain and carry out significance detection on the denoised image to be detected and the denoised images of various templates so as to obtain a corresponding second face significant image to be detected and a plurality of second face template significant images; and taking the superposed part of the first face significant image to be detected and the second face significant image to be detected as a core significant area image of the face to be detected, and taking the superposed part of the corresponding first face template significant image and the second face template significant image as a core significant area image of the corresponding face template.
In some embodiments of the present invention, for any one of the residents entering and exiting the community, the facial image of the resident is extracted as the facial image to be detected. And respectively calculating the similarity of the face image to be detected and the 4 template images by using a sparse matching method based on core significance region detection, and judging the age bracket corresponding to the resident by using the similarity (for example, the resident is determined to be the old if the similarity of the image to be detected and the old face template image is the highest).
The sparse matching method based on the core significance region detection comprises the following steps: and performing core significance region detection on the face image to be detected and 4 face template images, and performing sparse coding on the core significance region of the face image to be detected and the core significance regions of all template images respectively. And calculating the similarity between the core salient region of the face image to be detected and the core salient region of each template image by using the Euclidean distance. The similarity between the core saliency region of the face image to be detected and the core saliency region of the template image is the highest, and the age bracket of the resident is directly determined to be the same as the age bracket corresponding to the template image.
The method for detecting the core salient region comprises the following steps: firstly, directly carrying out saliency detection on an original image to obtain a saliency area A; then, carrying out depth denoising on the original image by using an image denoising method, and carrying out saliency detection on the original image on the basis to obtain a saliency area B; and finally, taking the overlapped part of the saliency area A and the saliency area B as a core saliency area. And further obtain more accurate image.
S3, judging the age groups of all residents entering and exiting the community according to a preset acquisition period, counting and pushing corresponding commodities to the community residents according to the overall age proportion of the community residents; and for a certain time (usually, only a few days), all the in-and-out residents judge the age bracket by using the method, measure the overall age ratio of the community residents, and push commodities to the community residents according to the age ratio of the community residents. For example, if the ratio of the population to the elderly in the community is measured to be 70%, and the ratios of the elderly, the young and the children are each 10%, the community is recommended with a product suitable for the elderly.
S4, for any commodity pushed to residents in the community, performing three-dimensional reconstruction on the commodity image by using a preferred three-dimensional reconstruction method based on the image enhancement result to obtain and display a three-dimensional reconstruction result of the commodity to the residents in the community;
further, as shown in fig. 3, the method includes:
s41, enhancing the commodity images by utilizing a plurality of image enhancement methods to obtain a plurality of commodity enhanced images;
s42, carrying out peak signal-to-noise ratio detection on each commodity enhanced image to obtain and select an optimal commodity enhanced image according to each peak signal-to-noise ratio result;
and S43, performing three-dimensional reconstruction on the optimal commodity enhanced image by using a single image-based three-dimensional reconstruction technology.
In some embodiments of the present invention, for any commodity (illustrated by using fish oil as a commodity) pushed to the community, a three-dimensional reconstruction method based on image enhancement results is used to perform three-dimensional reconstruction on the commodity image, and the three-dimensional reconstruction result of the commodity is displayed to residents of the community (the commodity is displayed through an electronic commodity display screen of the community).
The three-dimensional reconstruction method based on the image enhancement result comprises the following steps: respectively enhancing the commodity images by using a plurality of image enhancement methods; on the basis of enhancing the commodity image by using different image enhancement methods, peak signal-to-noise ratio detection is carried out on a plurality of image enhancement results, and only the image enhancement result with the highest peak signal-to-noise ratio is reserved and is taken as the optimal image enhancement result. And performing three-dimensional reconstruction on the optimal image enhancement result by using a single image-based three-dimensional reconstruction technology to obtain a final three-dimensional reconstruction model of the commodity.
S5, selecting a high-immersion face template image;
s6, when any resident of the community watches the three-dimensional reconstruction result of the commodity, the identity of the resident is recognized by using a face recognition technology, a face expression video when the resident watches the face expression video is collected, and a plurality of face expression images are extracted from the face expression video at the same intervals;
s7, calculating and judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high-immersion degree face template image by using a multi-scale-based Hash coding similarity matching method;
further, comprising:
respectively carrying out multi-scale reconstruction on each facial expression image and each high-immersion face template image to obtain facial expression images and high-immersion face template images under multiple scales; and performing Hash coding on the facial expression image and the high immersion degree facial template image respectively under each scale, and calculating the similarity between the facial expression image and the high immersion degree facial template image corresponding to each scale by using the Euclidean distance so as to obtain, judge and mark the immersion degree information of the residents according to the similarity results under multiple scales.
S8, if the immersion degree information of the resident is high, commodity purchase confirmation information is generated and sent to the resident, and deduction is carried out in a corresponding resident account according to the confirmation result of the resident;
and S9, counting and judging whether the preset group purchase requirement is met or not according to the commodity purchase data of the residents in the community, if so, confirming that the grouping is successful, calculating and returning the corresponding commodity price difference to the corresponding resident account to finish the group purchase.
In some embodiments of the invention, a high-immersion face template image is selected. When a certain community resident watches the display of the three-dimensional reconstruction model of the commodity through an electronic commodity display screen of the community, the identity of a user is firstly identified by using a face identification technology. Meanwhile, a facial expression video displayed by a resident watching a three-dimensional model of the commodity is shot, and 5 facial expression images are extracted from the video at the same interval. And calculating the similarity of each facial expression image and each high-immersion face template image by using a multi-scale Hash coding similarity matching method, and if the similarity of most facial expression images and high-immersion face template images is high, determining that the immersion degree of the residents is high, and reminding the residents of watching the immersion degree displayed by the three-dimensional commodity reconstruction model. At the same time, the resident is allowed to confirm whether or not to purchase the commodity. If the commodity is determined to be purchased, deduction is made in the individual account of the resident directly according to the identity of the resident.
The multi-scale-based hash coding similarity matching method comprises the following steps: and performing multi-scale reconstruction on one of the facial expression image and the immersion face template image. And carrying out Hash coding on the facial expression image and the immersion degree facial template image under each scale, and calculating the similarity of the facial expression image and the immersion degree facial template image under each scale by using the Euclidean distance. And if the similarity between the facial expression image and the immersion face template image is higher in each scale, directly determining that the similarity between the facial expression image and the immersion face template image is higher.
For the commodity pushed to the community, when other residents watch the three-dimensional reconstruction model display of the commodity, the resident still confirms whether to purchase the commodity or not by using the method, and if so, personal account deduction is carried out. When a plurality of residents watch the three-dimensional reconstructed model display of the commodity and buy the commodity (for example, 30 people select the fish oil and meet the requirement of the number of people for group purchase), the group is directly pieced together, and the commodity price difference is returned to the user (for example, the price of the fish oil is 50 yuan, the group purchase price is 40 yuan, and the account of each purchasing user returns 10 yuan).
In order to solve the problems in the prior art, the method respectively calculates the similarity between the facial image to be detected and various template images by using a sparse matching method based on core significance region detection, and judges the age bracket corresponding to the resident by using the similarity, thereby providing direct support for measuring and calculating the integral age ratio of the residents in the community. The method also utilizes a three-dimensional reconstruction method based on image enhancement result optimization to carry out high-quality three-dimensional reconstruction on the commodity image, and remarkably improves the three-dimensional display effect of the commodity. By utilizing the multi-scale Hash coding similarity matching method, the immersion degree of the residents watching the three-dimensional model display of the commodity is more accurately evaluated, and the residents are timely reminded if the immersion degree is high, so that the residents can use the immersion degree as an important reference for purchasing the commodity. The method realizes accurate and efficient commodity group purchase by utilizing the cooperation of various methods such as a sparse matching method based on core significance region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multi-scale Hash coding similarity matching method and the like.
In a second aspect, as shown in fig. 4, an embodiment of the present invention provides an artificial intelligence based smart community choice commodity big data group buying system, including: age group template module 100, age group determination module 200, age statistics module 300, merchandise display module 400, immersion level selection module 500, face acquisition module 600, immersion level determination module 700, merchandise purchase module 800 and piece together determination module 900, wherein:
an age group template module 100, configured to collect face template images of multiple age groups;
the age group judgment module 200 is configured to, for any resident entering and exiting the community, extract a face image of the resident as a face image to be detected, respectively calculate similarities between the face image to be detected and face template images of all age groups by using a sparse matching method based on core saliency region detection, generate and judge an age group of the resident according to a corresponding similarity value;
the age counting module 300 is configured to perform age group judgment on all residents entering and exiting the community according to a preset collection period, count the age groups, and push corresponding commodities to the community residents according to the overall age proportion of the community residents;
the commodity display module 400 is used for carrying out three-dimensional reconstruction on a commodity image by utilizing a three-dimensional reconstruction method based on image enhancement result optimization for any commodity pushed to residents in the community to obtain and display a three-dimensional reconstruction result of the commodity to the residents in the community;
the immersion degree selecting module 500 is used for selecting a high-immersion degree face template image;
the face acquisition module 600 is configured to, when any one of the residents in the community watches the three-dimensional reconstruction result of the commodity, identify the identity of the resident by using a face recognition technology, acquire a facial expression video when the resident watches the face, and extract a plurality of facial expression images from the facial expression video at the same interval;
the immersion degree judging module 700 is used for calculating and judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high-immersion degree face template image by using a multi-scale Hash coding similarity matching method;
the commodity purchasing module 800 is configured to generate and send commodity purchasing confirmation information to the resident if the immersion information of the resident is high, and obtain and deduct money from a corresponding resident account according to a resident confirmation result;
and the grouping judgment module 900 is used for counting and judging whether the preset group purchase requirement is met according to the commodity purchase data of the residents in the community, if so, confirming that grouping is successful, calculating and returning the corresponding commodity price difference to the corresponding resident account, and finishing group purchase.
In order to solve the problems in the prior art, the system respectively calculates the similarity of the facial image to be detected and various template images by matching a plurality of modules such as an age group template module 100, an age group judging module 200, an age counting module 300, a commodity display module 400, an immersion degree selecting module 500, a face collecting module 600, an immersion degree judging module 700, a commodity purchasing module 800 and a grouping judging module 900 through a sparse matching method based on core significance region detection, judges the age group corresponding to the resident through the similarity, and provides direct support for measuring the integral age proportion of the residents in the community. The system also performs high-quality three-dimensional reconstruction on the commodity image by using a three-dimensional reconstruction method based on image enhancement result optimization, and remarkably improves the three-dimensional display effect of the commodity. By utilizing the multi-scale Hash coding similarity matching method, the immersion degree of the residents watching the three-dimensional model display of the commodity is more accurately evaluated, and the residents are timely reminded if the immersion degree is high, so that the residents can use the immersion degree as an important reference for purchasing the commodity. The method realizes accurate and efficient commodity group purchase by matching various methods such as a sparse matching method based on core significance region detection, a three-dimensional reconstruction method based on image enhancement result optimization, a multiscale Hash coding similarity matching method and the like.
As shown in fig. 5, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The one or more programs, when executed by the processor 102, implement the method of any of the first aspects as described above.
Also included is a communication interface 103, with the memory 101, processor 102, and communication interface 103 being electrically connected to each other, directly or indirectly, to enable transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, and the processor 102 executes the software programs and modules stored in the memory 101 to thereby execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 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 102 may be an integrated circuit chip having signal processing capabilities. The processor 102 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method, system and method may be implemented in other ways. The method and system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by the processor 102, implements the method according to any one of the first aspect described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The present invention has been described in terms of the preferred embodiment, and it is not intended to be limited to the embodiment. 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.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (8)
1. A big data group purchase method of smart community selected commodities based on artificial intelligence is characterized by comprising the following steps:
acquiring face template images of a plurality of age groups;
for any resident entering and exiting the community, extracting a face image of the resident as a face image to be detected, respectively calculating the similarity between the face image to be detected and the face template image of each age group by using a sparse matching method based on core significance region detection, generating and judging the age group of the resident according to the corresponding similarity value;
according to a preset acquisition period, judging the age groups of all residents entering and exiting the community, counting and pushing corresponding commodities to the residents in the community according to the integral age proportion of the residents in the community;
for any commodity pushed to residents in the community, performing three-dimensional reconstruction on the commodity image by using a preferred three-dimensional reconstruction method based on the image enhancement result to obtain and display the three-dimensional reconstruction result of the commodity to the residents in the community;
selecting a high-immersion face template image;
when any resident of the community watches the three-dimensional reconstruction result of the commodity, the identity of the resident is recognized by using a face recognition technology, a face expression video when the resident watches the commodity is collected, and a plurality of face expression images are extracted from the face expression video at the same intervals;
calculating and judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high immersion degree face template image by using a multi-scale-based Hash coding similarity matching method;
if the immersion degree information of the resident is high, commodity purchase confirmation information is generated and sent to the resident, and deduction is carried out in a corresponding resident account according to the confirmation result of the resident;
and counting and judging whether the preset group purchase requirement is met or not according to the commodity purchase data of the residents in the community, if so, confirming that the grouping is successful, calculating and returning the corresponding commodity price difference to the corresponding resident account to finish the group purchase.
2. The intelligent community choice commodity big data group purchase method based on artificial intelligence is characterized in that the method for respectively calculating the similarity between the face image to be detected and the face template images of all ages by using the sparse matching method based on core significance region detection comprises the following steps:
respectively carrying out core significance region detection on the face image to be detected and each face template image to obtain a corresponding core significance region image of the face to be detected and a plurality of core significance region images of the face templates;
and respectively carrying out sparse coding on the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates, and calculating the similarity between the image of the core salient region of the face to be detected and the images of the core salient regions of the face templates by using the Euclidean distance.
3. The intelligent community choice commodity big data group purchase method based on artificial intelligence, as claimed in claim 2, wherein the method for detecting the core saliency area of the face image to be detected and each face template image respectively comprises the following steps:
respectively carrying out significance detection on the face image to be detected and each face template image so as to obtain a corresponding first face significant image to be detected and a plurality of first face template significant images;
carrying out depth denoising on the face image to be detected and each face template image by using an image denoising method to obtain and carry out significance detection on the denoised image to be detected and the denoised images of various templates so as to obtain a corresponding second face significant image to be detected and a plurality of second face template significant images;
and taking the superposed part of the first face significant image to be detected and the second face significant image to be detected as a core significant area image of the face to be detected, and taking the superposed part of the corresponding first face template significant image and the second face template significant image as a core significant area image of the corresponding face template.
4. The method for group purchase of selected commodity big data in the smart community based on artificial intelligence, as claimed in claim 1, wherein the method for three-dimensionally reconstructing the commodity image by using the three-dimensional reconstruction method based on image enhancement result comprises the following steps:
respectively carrying out enhancement processing on the commodity images by utilizing a plurality of image enhancement methods to obtain a plurality of commodity enhancement images;
carrying out peak signal-to-noise ratio detection on each commodity enhanced image to obtain and select an optimal commodity enhanced image according to each peak signal-to-noise ratio result;
and performing three-dimensional reconstruction on the optimal commodity enhanced image by using a single image-based three-dimensional reconstruction technology.
5. The intelligent community choice commodity big data group purchase method based on artificial intelligence, as claimed in claim 1, wherein the method for calculating and determining and marking the immersion degree information of the resident according to the similarity between each facial expression image and the high immersion degree face template image by using the multi-scale based hash coding similarity matching method comprises the following steps:
respectively carrying out multi-scale reconstruction on each facial expression image and each high-immersion face template image to obtain facial expression images and high-immersion face template images under multiple scales;
and respectively carrying out Hash coding on the facial expression image and the high-immersion face template image under each scale, and calculating the similarity between the corresponding facial expression image and the high-immersion face template image under each scale by using the Euclidean distance so as to obtain and judge and mark the immersion information of the residents according to the similarity results under multiple scales.
6. The utility model provides a choice commodity big data group purchase system of wisdom community based on artificial intelligence which characterized in that includes: age bracket template module, age bracket judge module, age statistics module, commodity show module, the module is selected to the immersion degree, people's face acquisition module, immersion degree judge module, commodity purchase module and piece together and judge the module, wherein:
the age group template module is used for acquiring face template images of a plurality of age groups;
the age group judging module is used for extracting the face image of any resident entering and exiting the community as a face image to be detected, respectively calculating the similarity between the face image to be detected and the face template image of each age group by using a sparse matching method based on core significance region detection, generating and judging the age group of the resident according to the corresponding similarity value;
the age counting module is used for judging the age groups of all residents entering and exiting the community according to a preset acquisition period, counting and pushing corresponding commodities to the community residents according to the integral age proportion of the community residents;
the commodity display module is used for carrying out three-dimensional reconstruction on the commodity image by utilizing a three-dimensional reconstruction method based on image enhancement result optimization for any commodity pushed to the community residents so as to obtain and display the three-dimensional reconstruction result of the commodity to the community residents;
the immersion degree selecting module is used for selecting a high-immersion degree face template image;
the face acquisition module is used for identifying the identity of any resident in the community by using a face recognition technology when the resident watches the three-dimensional reconstruction result of the commodity, acquiring a face expression video when the resident watches the face expression video and extracting a plurality of face expression images from the face expression video at the same interval;
the immersion degree judging module is used for calculating, judging and marking the immersion degree information of the residents according to the similarity between each facial expression image and each high-immersion degree face template image by utilizing a multi-scale-based Hash coding similarity matching method;
the commodity purchasing module is used for generating and sending commodity purchasing confirmation information to the resident if the immersion degree information of the resident is high, and obtaining and deducting money in a corresponding resident account according to the resident confirmation result;
and the grouping judgment module is used for counting and judging whether the preset group purchase requirement is met or not according to the residential commodity purchase data of the community, if so, confirming that grouping is successful, calculating and returning the corresponding commodity price difference to the corresponding residential account to finish group purchase.
7. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the one or more programs, when executed by the processor, implement the method of any of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211476162.3A CN115860860A (en) | 2022-11-23 | 2022-11-23 | Smart community choice commodity big data group purchase method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211476162.3A CN115860860A (en) | 2022-11-23 | 2022-11-23 | Smart community choice commodity big data group purchase method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115860860A true CN115860860A (en) | 2023-03-28 |
Family
ID=85665439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211476162.3A Pending CN115860860A (en) | 2022-11-23 | 2022-11-23 | Smart community choice commodity big data group purchase method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860860A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116739704A (en) * | 2023-06-07 | 2023-09-12 | 北京海上升科技有限公司 | E-commerce platform interest analysis type commodity recommendation method and system based on artificial intelligence |
-
2022
- 2022-11-23 CN CN202211476162.3A patent/CN115860860A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116739704A (en) * | 2023-06-07 | 2023-09-12 | 北京海上升科技有限公司 | E-commerce platform interest analysis type commodity recommendation method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256568B (en) | Plant species identification method and device | |
| US20050102272A1 (en) | Methods for estimating the seasonality of groups of similar items of commerce data sets based on historical sales data values and associated error information | |
| CN109284413A (en) | Method of Commodity Recommendation, device, equipment and storage medium based on recognition of face | |
| CN111611877B (en) | Anti-age-interference face recognition method based on multi-time-space information fusion | |
| TW202026992A (en) | Industry identification model determination method and device | |
| CN115019374B (en) | Intelligent classroom student concentration degree low-consumption detection method and system based on artificial intelligence | |
| CN115860860A (en) | Smart community choice commodity big data group purchase method and system based on artificial intelligence | |
| CN111652669A (en) | Intelligent terminal shopping guide system and method | |
| CN108053322A (en) | The customer investment return evaluation method and system of vehicle | |
| CN115100640B (en) | Intelligent supermarket commodity sales big data detection method and system based on artificial intelligence | |
| CN111553729A (en) | Method and device for generating portrait data of e-commerce user and computing equipment | |
| CN116562991B (en) | Commodity big data information identification method and system for meta-space electronic commerce platform | |
| Song et al. | Conditional random field-based mesh saliency | |
| CN113313217B (en) | Method and system for accurately identifying dip angle characters based on robust template | |
| CN115496566A (en) | Regional specialty recommendation method and system based on big data | |
| Cetateanu et al. | A novel methodology for identifying environmental exposures using GPS data | |
| CN112884508A (en) | System for collecting and/or pushing information based on selling equipment user information | |
| CN115661833A (en) | Target commodity big data accurate identification method and system based on simple photographing | |
| CN105069836A (en) | Electronic fitting system based on stereoscopic vision and multi-feature image retrieval | |
| CN112365315A (en) | Commodity display position recommendation method, device and system and storage medium | |
| CN111008320A (en) | Data processing method and device and electronic equipment | |
| CN111311233A (en) | Passive code scanning method and device based on multi-trigger mode | |
| Ke et al. | An automatic instrument recognition approach based on deep convolutional neural network | |
| CN115713750A (en) | Lane line detection method and device, electronic equipment and storage medium | |
| CN109670939A (en) | Refund data processing method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |