CN109165992A

CN109165992A - A kind of intelligent shopping guide method, apparatus, system and computer storage medium

Info

Publication number: CN109165992A
Application number: CN201810779063.XA
Authority: CN
Inventors: 梁喆; 周舒畅; 何蔚然; 朱雨; 李广
Original assignee: Beijing Megvii Technology Co Ltd
Current assignee: Beijing Megvii Technology Co Ltd
Priority date: 2018-07-16
Filing date: 2018-07-16
Publication date: 2019-01-08

Abstract

The present invention provides a kind of intelligent shopping guide method, apparatus, system and computer storage mediums.The intelligent shopping guide purchase method includes: the real-time image information for obtaining customer；The shopping record, human body attribute and/or surrounding enviroment of the customer are determined based on the real-time image information of the customer；According to the shopping record, human body attribute and/or surrounding enviroment of the customer, to the customer recommendation commodity.According to the method for the present invention, device, system and computer storage medium, image recognition technology is combined with purchasing article, it can be by acquiring the image information of customer, to set up intelligent recommendation or shopping guide's service, potential revenue opportunities are brought to businessman, improve the shopping experience of customer.

Description

A kind of intelligent shopping guide method, apparatus, system and computer storage medium

Technical field

The present invention relates to technical field of image processing, relate more specifically to a kind of intelligent shopping guide method and device.

Background technique

The various shopping mall supermarket types of merchandize in China are ten hundreds of at present, with the expansion of supermarket's scale and consumer's purchase Object select diversification, can encounter such as can not quickly in supermarket accurately find want purchase commodity, to similar commodity not With brand merchandise news understand it is insufficient, the quantity and price detail of smart shopper car purchase commodity are not known about, do shopping Peak time arranges the problems such as very long team waits clearing etc. on cashier's counter side.Existing intelligent shopping trolley RFID reads commodity nearby, Lead to will appear on screen tens or ten several goods catalogue on shelf nearby, itself for user from radical change customer Purchasing habits, the various selection error rate of subject is high when causing to choose, and certainly will subtract due to once reading tens kinds of commodity reaction speeds Slowly.

Therefore, the shopping cart that market or supermarket exists in the prior art has a single function, and is only used for containing the goods of customer The problem of object.

Summary of the invention

The present invention is proposed in view of the above problem.The present invention provides a kind of intelligent shopping guide method, apparatus, system and Computer storage medium, to set up intelligent recommendation or shopping guide's service, can give businessman by acquiring custom image information Potential revenue opportunities are brought, the shopping experience of customer is improved.

According to an aspect of the present invention, a kind of intelligent shopping guide method is provided, which is characterized in that the described method includes:

Obtain the real-time image information of customer；

The shopping record, human body attribute and/or peripheral ring of the customer are determined based on the real-time face image of the customer Border；

According to the shopping record of the customer, human body attribute and/or surrounding enviroment human body attribute, to the customer recommendation quotient Product.

Illustratively, the real-time image information based on the customer determines the shopping record of the customer, human body category Property and/or surrounding enviroment, comprising: the real-time image information of the customer is sent to server；Receive what the server was sent Shopping record, human body attribute and/or the surrounding enviroment of the customer, the shopping record, human body attribute and/or surrounding enviroment are The server is determined based on the real-time image information.

Illustratively, the real-time image information includes the human face image information of the customer；It is described to be based on the customer Real-time image information determine the shopping record of the customer, comprising: human face image information based on the customer carries out identity Identification, determines the identification result of the customer；It is recorded according to the shopping of customer described in the identification result queries.

Illustratively, the real-time image information based on the customer determines that the human body attribute of the customer includes: base Face character identification is carried out in the human face image information of the customer, determines the attribute of the customer, the human body category of the customer Property includes at least one of gender, age, expression, dressing.

Illustratively, the real-time image information further includes the human body image information of the customer, described to be based on the Gu The real-time image information of visitor determines the human body attribute of the customer, further includes: the human body image information based on the customer carries out Human body Attribute Recognition, determines the human body attribute of the customer, the human body attribute of the customer include clothing, height, movement posture, Whether at least one of special article is dressed.

Illustratively, the real-time image information further includes the background image information of the customer, described to be based on the Gu The real-time image information of visitor determines the surrounding enviroment of the customer, comprising: the background image information based on the customer is carried on the back Scape identification, determines the surrounding enviroment of the customer.

Illustratively, the intelligent shopping guide method further include:, will if not getting the shopping record of the customer The human face image information of the customer is stored to face bottom library, and stores this shopping record of the client.

Illustratively, the intelligent shopping guide method further include: if not getting the shopping record of the customer, to The preassigned commodity of customer recommendation.

Illustratively, described to the customer recommendation commodity, comprising: to show the information of the commodity, institute on a display screen Display location is stated on intelligent shopping guide device.

Illustratively, it is described according to purchaser record to the method for customer recommendation commodity include: will shopping record commodity point For consumables and durable goods two major classes, according to different classes of selection Generalization bounds.

Illustratively, the method according to different classes of selection Generalization bounds includes: when the commodity purchasing of consumables Between more than the first preset value when, the commodity of identical and similar promotion are added and recommend list of articles.

Illustratively, the method according to different classes of selection Generalization bounds further include: according to the shopping story of durable goods The commodity of association class, which are added, for record recommends list of articles.

Illustratively, the intelligent shopping guide method further include: obtain the image information of all registered customers, and based on described The image information of registered customers establishes face bottom library.

Illustratively, described to the customer recommendation commodity, comprising: to show the commodity, the display on a display screen Screen is located on intelligent shopping guide device.

According to a further aspect of the invention, a kind of intelligent shopping guide device is provided, comprising:

Image collection module, for obtaining the real-time image information of customer；

Customer Information module, based on customer real-time face image determine the shopping record of the customer, human body attribute and/ Or surrounding enviroment；

Commercial product recommending module, for according to the shopping record of the customer, human body attribute and/or surrounding enviroment human body category Property, to the customer recommendation commodity.

Illustratively, described image, which obtains module, to further include:

Image information receiving module, for receiving the real-time image information of customer；

Framing module carries out video image framing for the video data in the real-time image information to the customer；

Face detection module, the single-frame images or the framing module for exporting to described image information receiving module are defeated Each frame in multiple image out carries out Face detection and tracking, obtains the real-time face image of customer；

Judgment module is obtained, whether contains face information in the real-time image information for judging the customer, if there is Next step is then carried out, the real-time image information for obtaining customer is otherwise continued.

Illustratively, the Customer Information module further include: human body attribute module, for the real-time figure based on the customer As information determines the human body attribute of the customer.

Illustratively, the face character module can further include: face characteristic dimensionality reduction module, care for for generating The dimension of customer's face characteristic is reduced after objective real-time face feature.

Illustratively, the real-time image information further includes the background image information of the customer, and Customer Information module is also The surrounding enviroment of the customer are determined for carrying out Background Recognition based on the background image information including surrounding enviroment module.

Illustratively, the Customer Information module may include: communication module, for sending the customer's to server Real-time image information；Receive shopping record, human body attribute and/or the surrounding enviroment of the customer that the server is sent, institute Stating shopping record, human body attribute and/or surrounding enviroment is that the server is determined based on the real-time image information.

Illustratively, the Customer Information module may include: shopping logging modle, for the face based on the customer Image information carries out identification, determines the identification result of the customer；According to the identification result queries The shopping of customer records.

Illustratively, the Customer Information module may include: storage medium module, for storing established face bottom Library, customer shopping record and human body attribute.

Illustratively, the Customer Information module can further include: if the identification result is nothing The customer records without shopping；Otherwise the shopping record of the customer is inquired.

Illustratively, the commercial product recommending module can also further include:

Data obtaining module, for obtaining the shopping record and/or human body attribute of the customer；

Commercial product recommending policy module, for the shopping record and/or human body attribute according to the customer, to customer recommendation quotient Product；

Merchandise news output module, for exporting the commodity of the recommendation.

Illustratively, the Recommendations include Recommendations information and its advertisement.

Illustratively, it if commercial product recommending policy module includes: the shopping record for not getting customer, is pushed away to customer Recommend preassigned commodity or according to the human body attribute of the customer and/or surrounding enviroment to the customer recommendation commodity；If The shopping record for getting customer, then according to the shopping record of the customer, human body attribute and/or surrounding enviroment to customer recommendation Commodity.

Illustratively, it is described according to purchaser record to the method for the customer recommendation commodity include: by shopping record quotient Product are divided into consumables and durable goods two major classes, according to different classes of selection Generalization bounds.Because consumables and durable goods are consumption Habit is different, for example the consumables such as daily necessaries, bath accessory will be finished in a short time, and be finished to buy again；And The durable goods such as pots and pans then use for a long time, and user will not generally replace in a short time.

Intelligent shopping guide method and apparatus according to an embodiment of the present invention, can be by acquiring custom image information, to build Intelligent recommendation or shopping guide's service are erected, potential revenue opportunities is brought to businessman, improves the shopping experience of customer.

Detailed description of the invention

The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention, Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings, Identical reference label typically represents same parts or step.

Fig. 1 is for realizing the signal of the exemplary electronic device of intelligent shopping guide method and apparatus according to an embodiment of the present invention Property block diagram；

Fig. 2 is the schematic flow chart of intelligent shopping guide method according to an embodiment of the present invention；

Fig. 3 is the schematic block diagram of intelligent shopping guide device according to an embodiment of the present invention；

Fig. 4 is the schematic block diagram of intelligent shopping guide system according to an embodiment of the present invention.

Specific embodiment

In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.

Firstly, being described with reference to Figure 1 the exemplary electron of the intelligent shopping guide method and apparatus for realizing the embodiment of the present invention Equipment 100.

As shown in Figure 1, electronic equipment 100 include one or more processors 102, it is one or more storage device 104, defeated Enter device 106, output device 108, imaging sensor 110, the company that these components pass through bus system 112 and/or other forms The interconnection of connection mechanism (not shown).It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, rather than Restrictive, as needed, the electronic equipment also can have other assemblies and structure.

The processor 102 can be central processing unit (CPU), graphics processing unit (GPU) or have at data The processing unit of reason ability and/or the other forms of instruction execution capability, and can control its in the electronic equipment 100 Its component is to execute desired function.

The storage device 104 may include one or more computer program products, and the computer program product can To include various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described easy The property lost memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non- Volatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..In the computer readable storage medium On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or The various data etc. generated.

The input unit 106 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat One or more of gram wind and touch screen etc..

The output device 108 can export various information (such as image or sound) to external (such as user), and It may include one or more of display, loudspeaker etc..

Described image sensor 110 can be shot the desired image of user (such as photo, video etc.), and will be captured Image be stored in the storage device 104 for other components use.In one embodiment, described image sensor 110 are set on shopping cart, for acquiring the real-time image information of customer.

Illustratively, the exemplary electronic device for realizing intelligent shopping guide method and apparatus according to an embodiment of the present invention can To be implemented as smart phone, tablet computer, video acquisition end of access control system etc..

Intelligent shopping guide method 200 according to an embodiment of the present invention is described next, with reference to Fig. 2.

Firstly, obtaining the real-time image information of customer in step S210；

In step S220, the shopping record of the customer, human body attribute are determined based on the real-time image information of the customer And/or surrounding enviroment.

In step S230, according to the shopping record, human body attribute and/or surrounding enviroment of the customer to the customer recommendation Commodity.

It can be according to any information in shopping record, human body attribute and surrounding enviroment three come to customer recommendation quotient Product, can also be according to two or three of combined information in three come to customer recommendation commodity.In Recommendations, synthesis is examined Consider the above much information, personalized recommendation service can be provided for customer, be conducive to improve customer satisfaction and recommend at Power.

Illustratively, intelligent shopping guide method according to an embodiment of the present invention can be in setting with memory and processor It is realized in standby, device or system.

Intelligent shopping guide method according to an embodiment of the present invention can be deployed at Image Acquisition end, for example, can be deployed in At personal terminal, intelligent shopping guide device, shopping cart etc..

Alternatively, intelligent shopping guide method according to an embodiment of the present invention can also be deployed in server end (or cloud with being distributed End) and personal terminal at.It, can be with for example, the realtime graphic of acquisition is transferred to server end (or cloud) by image capture device Real-time face image is generated in server end (or cloud), server end (or cloud) is by real-time face image generated, people Body image and/or background image pass to personal terminal, and personal terminal is according to the received real-time face image of institute, human body image And/or background image carries out intelligent shopping guide.For another example real-time face image, human body can be generated in server end (or cloud) Image and/or background image, the figure for video information and the non-image sensor acquisition that personal terminal acquires imaging sensor As information passes to server end (or cloud), then server end (or cloud) is into intelligent shopping guide.

Intelligent shopping guide method according to an embodiment of the present invention, can be by acquiring custom image information, to set up intelligence It can recommend or shopping guide services, bring potential revenue opportunities to businessman, improve the shopping experience of customer.

According to embodiments of the present invention, the intelligent shopping guide method further comprises before executing step 210: obtaining The image information of all registered customers, and the image information based on the registered customers is to establish face bottom library.

Illustratively, the face bottom library of establishing includes: the registered customers image letter for obtaining the face comprising registered customers Breath, after pre-processing to the registered customers image information, generates corresponding registered customers facial image, is based on the registration Customer's facial image extracts feature and obtains registered customers face characteristic, and by the registered customers facial image and its corresponding note Volume customer's face characteristic storage is stored to face bottom library, or by the registered customers face characteristic to face bottom library.

Illustratively, face bottom library can be established respectively according to single registered customers or multiple registered customers, In the case where multiple registered customers, each customer possesses the individual face image feature database for corresponding to oneself.Face bottom library In include the registered customers facial image and/or corresponding registered customers face characteristic, the registered customers facial image and/ Or corresponding registered customers face characteristic is properly termed as face base map.

Illustratively, the registered customers image information includes single-frame images or continuous multiple image or discontinuous The selected multiple image of meaning.

Illustratively, the registered customers facial image is by carrying out Face datection to the registered customers image information With the picture frame for determined by face tracking processing including registered customers face.Specifically, can by such as template matching, The various method for detecting human face commonly used in the art such as SVM (support vector machines), neural network are in the starting comprising target face The size and location that the target face is determined in picture frame, colouring information, local feature or movement then based on target face Information etc. tracks the target face, so that it is determined that including each frame image of target face in video.Above by people Face detection and face tracking determination include that the processing of the picture frame of target face is common processing in field of image processing, this Place is no longer described in greater detail.

According to embodiments of the present invention, step 210 can further include: obtaining the real-time image information of customer, judge Whether contain face information in the real-time image information, if there is then carrying out next step, otherwise continues the reality for obtaining customer When image information.

Illustratively, described to judge in the real-time image information whether to be by the customer containing face information It include the picture frame of customer's face determined by real-time image information progress Face datection and face tracking processing.Pass through face Detection and face tracking determination include that the processing of the picture frame of target face is common processing in field of image processing, herein No longer it is described in greater detail.

Illustratively, the real-time image information of the customer includes human face image information, and the human face image information includes Facial image and/or the face characteristic extracted according to the facial image.

Illustratively, the real-time image information of the customer can also be the original image that image capture device takes, Also the image after may be pretreated, can also be plucked out from the original image taken come facial image and/or Human body image can also be the face characteristic extracted through neural network and/or characteristics of human body.Illustratively, the real-time figure Position or customer as where information can also can indicate customer including the background image information of customer, the background image information The merchandise classification of position.

According to embodiments of the present invention, step 220 can further include: the realtime graphic letter based on the customer Breath determines shopping record, human body attribute and/or the surrounding enviroment of the customer, comprising:

The real-time image information of the customer is sent to server；

Receive shopping record, human body attribute and/or the surrounding enviroment of the customer that the server is sent, the shopping Record, human body attribute and/or surrounding enviroment are that the server is determined based on the real-time image information.

According to embodiments of the present invention, the real-time image information includes the human face image information of the customer.Correspondingly, it walks Rapid 220 may include: the shopping record that the real-time image information based on the customer determines the customer, comprising: be based on The human face image information of the customer carries out identification, determines the identification result of the customer；Known according to the identity The shopping of customer described in other result queries records.

Illustratively, the human body attribute include the gender of the customer, the age, expression, in hair style at least one of it is (logical It crosses face Attribute Recognition to obtain)；Optionally, can also include clothing, height, whether wear a pair of spectacles, whether be branded as, whether take out Cigarette, whether knapsack, whether dress special article, movement posture etc. at least one of (being obtained by human body Attribute Recognition)；Its In, special article can be ornaments, or mark object (such as badge) etc..

In one embodiment, the real-time image information further includes the background image information of the customer.Correspondingly, it walks In rapid 220, the real-time image information based on the customer determines the surrounding enviroment of the customer, comprising: is based on the Gu The background image information of visitor carries out Background Recognition, determines the surrounding enviroment of the customer.By determining the surrounding enviroment of customer, energy Enough more convenient recommendation customers may interested commodity.For example, if customer is located at fruit area or the Background of customer There is fruit as in, then it can be to customer recommendation fruit.In one embodiment, image collecting device is arranged in smart shopper Che Shang acquires the real-time image information of customer, which is sent to server by intelligent shopping trolley, by server into Row identification, human body Attribute Recognition and/or Background Recognition.

In one embodiment, the realtime graphic letter that customer is acquired on intelligent shopping trolley is arranged in image collecting device Breath carries out face character identification and/or human body Attribute Recognition by intelligent shopping trolley oneself.

Illustratively, the real-time image information based on the customer determines the shopping record of the customer, can be with It include: that the dimension that the real-time face feature is reduced after the real-time face feature is generated according to the real-time image information of the customer Degree；Real-time face feature after the reduction dimension is compared in the library of face bottom, to accelerate the speed compared.

Illustratively, the feature extraction can use such as LBP (local binary patterns), HoG (direction gradient histogram Figure), the various face feature extraction methods appropriate such as PCA (Principal Component Analysis) or neural network carry out feature extraction simultaneously Generate the multiple feature vector.Optionally, equal for the target face in each frame image in the face picture sequence Feature vector is generated using identical feature extracting method.The integrality being merely to illustrate that below, to institute in the present embodiment The face feature extraction method of use carries out simple illustration.

In one embodiment, using the feature extracting method based on convolutional neural networks to the face picture sequence in video It is corresponding multiple with the target face in the face picture sequence respectively to generate that target face in column carries out feature extraction Feature vector.For example, determination is wherein corresponding with target face firstly for each frame image in the face picture sequence Facial image region；Then, convolutional neural networks are based on to the facial image region and carry out feature extraction, to generate and the frame figure The corresponding feature vector of target face as in.Herein, which can be subjected to spy as a whole Sign is extracted, and can also carry out feature extraction respectively in the different sub-image areas in the facial image region.

Illustratively, the real-time image information based on the customer determines the shopping record of the customer, can be with Include: that customer's real-time face feature is compared in the library of face bottom, obtains several similarity scores；According to the similarity Score and recognition threshold obtain identification result.

Illustratively, if several similarity scores are respectively less than recognition threshold, obtaining identification result is nothing； It is greater than or equal to the phase of recognition threshold if at least one of described several similarity scores are greater than or equal to recognition threshold It is scored at high similarity score like degree, the identification result is determined by least one described high similarity score.

In one embodiment, described to determine that the identification result includes: choosing by least one high similarity score Customer Information corresponding to the highest facial image of similarity score or face is selected as identification result.

In one embodiment, described to determine that the identification result includes: logical by least one high similarity score It crosses input unit and receives selection of the user in the facial image or face in multiple high similarity scores, according to the user's choice Determine the identification result.

Illustratively, the identification result includes at least one of the ID of customer, title, identification card number.Into one Step ground, the identification result can also include the facial image and/or face characteristic of customer.

Illustratively, the real-time image information based on the customer determines the shopping record of the customer, can wrap It includes: customer's real-time face feature being compared in the library of face bottom, obtains comparing result；According to the comparing result and identification Threshold value obtains identification result.

In one embodiment, the comparing result refers to that the real-time face feature scans for comparing in the library of face bottom To the highest result of obtained similarity score.

In one embodiment, the comparing result refers to that customer's real-time face feature compares in the library of face bottom When, the face ID of that highest face base map of similarity.In one embodiment, comparing result and face base map can make It is indicated with ID, such as digital number 0123 indicates that in the face bottom library comprising 10000 face base maps, face ID is 0123 base map.When face characteristic to be identified compares in the library of face bottom, comparing result is returned, can be corresponding Face id number.

In one embodiment, can also further include: if the comparing result is searched in the library of face bottom Similarity score is less than recognition threshold, then obtaining identification result is nothing；If similarity score is greater than or equal to identification threshold It is comparing result that value, which then obtains identification result,.In one embodiment, full marks are 100 timesharing, and ballot threshold value is 90 points.

Step 220 can also further include: the customer is without shopping story if the identification result is nothing Record；Otherwise the shopping record of the customer is inquired.

Illustratively, if the customer without shopping record and without identification as a result, if by the face characteristic of the customer And relevant information is stored to face bottom library, and stores this shopping record of the client；If the customer without shopping record but There is identification as a result, then storing this shopping record of the client.

According to embodiments of the present invention, step 230 can further include: if customer records without shopping, to customer Recommend preassigned commodity or according to the human body attribute of the customer to the customer recommendation commodity.

Illustratively, if customer has shopping to record, according to shopping record and/or the human body attribute of the customer to Gu Objective Recommendations.

Illustratively, the Recommendations include whether Recommendations information (such as title, function, price, has activity Deng) and its advertisement.

Illustratively, described recorded according to shopping to the method for the customer recommendation commodity includes: by the quotient of shopping record Product are divided into consumables and durable goods two major classes, according to different classes of selection Generalization bounds.Because consumables and durable goods are consumption Habit is different, for example the consumables such as daily necessaries, bath accessory will be finished in a short time, and be finished to buy again；And The durable goods such as pots and pans then use for a long time, and user will not generally replace in a short time.

Illustratively, the method according to different classes of selection Generalization bounds includes: when the commodity purchasing of consumables Between more than the first preset value when, the commodity of identical and similar promotion are added and recommend list of articles.Recommended to consume according to the time Product can precisely hold the consumption habit of user, and the commodity of recommendation more meet user demand.

In one embodiment, from the point of view of the history of customer shopping record, or so client's generally per two weeks will be bought 10 kilograms of rice, then can be using 15 days as the first preset value of this commodity of rice, when customer bought apart from last time Rice is more than two weeks, can recommend rice to user when client comes to do shopping, user is reminded to buy rice.Further Ground can also recommend specific rice according to the brand and model that customer buys.

Illustratively, the method according to different classes of selection Generalization bounds further include: according to the shopping story of durable goods The commodity of association class, which are added, for record recommends list of articles.For example, there is High relevancy, inevitable frying pan between many durable goods And slice, sand stews and spoon, gas stove and smoke exhaust ventilator etc., and customer just goes back after may having bought a commodity, forgets Relevant commodity are bought, fallback must be carried out several times just and can purchased and is complete.Customer recommends other not buy after buying a durable goods Associated articles, allow user shopping more efficiently.

According to embodiments of the present invention, step 230 can further include: described to the customer recommendation commodity, comprising: Show or play the information of the commodity.

Illustratively, show that the commodity include: the information that the commodity are shown on display device (such as display screen), The display device is located on intelligent shopping guide device.

Illustratively, play the commodity include: by the information of voice playing device (such as loudspeaker) commodity, The voice playing device is located on intelligent shopping guide device.

Fig. 3 shows the schematic block diagram of intelligent shopping guide device 300 according to an embodiment of the present invention.

As shown in figure 3, intelligent shopping guide device 300 according to an embodiment of the present invention includes image collection module 310, Gu Kexin Cease module 320, commercial product recommending module 330.

Image collection module 310, for obtaining the real-time image information of customer；

Customer Information module 320, based on the customer real-time image information determine the customer shopping record and/or Human body attribute；

Commercial product recommending module 330, according to the shopping record, human body attribute and/or surrounding enviroment of the customer, to the Gu Objective Recommendations.

Intelligent shopping guide device 300 according to an embodiment of the present invention, can be by acquiring custom image information, to set up Intelligent recommendation or shopping guide's service, bring potential revenue opportunities to businessman, improve the shopping experience of customer.

According to embodiments of the present invention, described image, which obtains module 310, to further include:

Image information receiving module, for receiving the real-time image information including customer；

Illustratively, described to judge in the real-time image information whether to be that face detection module passes through containing face information Single-frame images or framing module to the output of image information receiving module export every frame image and carry out Face datection and face tracking It include the picture frame of target face determined by processing.Specifically, face detection module can by such as template matching, The various method for detecting human face commonly used in the art such as SVM (support vector machines), neural network are in the starting comprising target face The size and location that the target face is determined in picture frame, colouring information, local feature or movement then based on target face Information etc. tracks the target face, so that it is determined that including each frame image of target face in video.Above by people Face detection and face tracking determination include that the processing of the picture frame of target face is common processing in field of image processing, this Place is no longer described in greater detail.

Illustratively, the real-time image information of the customer includes single-frame images or continuous multiple image or discontinuous Arbitrarily selected multiple image.

Illustratively, the real-time image information of the customer can also be the original image that image capture device takes, Also the image after may be pretreated, can also be plucked out from the original image taken come facial image and/or Human body image can also be the face characteristic extracted through neural network and/or characteristics of human body.

According to embodiments of the present invention, the Customer Information module 320 may include:

Human body attribute module 321, for determining the human body attribute of the customer based on the real-time image information of the customer.

Illustratively, the human body attribute include the gender of the customer, the age, expression, in hair style at least one of it is (logical It crosses face Attribute Recognition to obtain)；Optionally, can also include clothing, height, whether wear a pair of spectacles, whether be branded as, whether take out Cigarette, whether knapsack, whether dress special article, movement posture etc. at least one of (being obtained by human body Attribute Recognition)；Its In, special article can be ornaments, or mark object (such as badge) etc..Wherein, the face character identification and human body attribute Identification belongs to the common processing of this field, is no longer described in greater detail herein.

In one embodiment, the real-time image information further includes the background image information of the customer, Customer Information Module 320 further includes surrounding enviroment module (not shown), for carrying out Background Recognition based on the background image information, really The surrounding enviroment of the fixed customer.

In one embodiment, the realtime graphic letter that customer is acquired on intelligent shopping trolley is arranged in image collecting device Breath carries out identification, human body Attribute Recognition and/or Background Recognition by intelligent shopping trolley oneself.

Illustratively, the face character module 321 can further include: face characteristic dimensionality reduction module, for giving birth to At the dimension for reducing customer's face characteristic after customer's real-time face feature.

Communication module 322, for sending the real-time image information of the customer to server；The server is received to send The customer shopping record, human body attribute and/or surrounding enviroment, shopping record, human body attribute and/or surrounding enviroment It is that the server is determined based on the real-time image information.

In one embodiment, image collecting device is arranged on intelligent shopping trolley, acquires the real-time image information of customer, The real-time image information is sent to server by intelligent shopping trolley, by server carry out identification, human body Attribute Recognition and/or Background Recognition.

According to embodiments of the present invention, the Customer Information module 320 can further include:

Logging modle 323 of doing shopping determines the Gu for the human face image information progress identification based on the customer The identification result of visitor；It is recorded according to the shopping of customer described in the identification result queries.

Illustratively, the shopping logging modle 323 can also include: by customer's real-time face feature in the library of face bottom It is compared, obtains several similarity scores；Identification result is obtained according to the similarity score and recognition threshold.

Illustratively, the shopping logging modle 323 can also include: by customer's real-time face feature in the library of face bottom It is compared, obtains comparing result；Identification result is obtained according to the comparing result and recognition threshold.

Storage medium module 324, for storing the shopping record and human body attribute in established face bottom library, customer.

Illustratively, storage medium module 324 can also further include: the shopping record and human body attribute difference It is corresponding with the customer in the library of the face bottom.

Illustratively, face bottom library can be established respectively according to single registered customers or multiple registered customers, In the case where multiple registered customers, each registered customers possess the individual face image feature database for corresponding to oneself.

According to embodiments of the present invention, the Customer Information module 320 can be further used for: if the identification As a result for nothing, then the customer records without shopping；Otherwise the shopping record of the customer is inquired.

Illustratively, if the customer without shopping record and without identification as a result, if by the face characteristic of the customer And relevant information is stored to face bottom library, and storage medium module 324 is recorded in this shopping for storing the client；If described Customer is without shopping record but has identification as a result, then storing this shopping record storage medium module 324 of the client.

According to embodiments of the present invention, the commercial product recommending module 330 can also further include:

Commercial product recommending policy module, the quotient different for the shopping record and/or human body Attributions selection according to the customer Product Generalization bounds are to customer recommendation commodity；

Merchandise news output module, for exporting commodity and its advertisement of the recommendation.

Illustratively, it if commercial product recommending policy module includes: that customer records without shopping, is preassigned to customer recommendation Commodity or according to the human body attribute of the customer and/or surrounding enviroment to the customer recommendation commodity；If customer has shopping Record, then according to shopping record, human body attribute and/or surrounding enviroment to customer recommendation commodity.

Illustratively, the commercial product recommending policy module further include: the commodity of shopping record are divided into consumables and durable Product two major classes, according to different classes of selection Generalization bounds.Because consumables and durable goods are that consumption habit is different, such as The consumables such as daily necessaries, bath accessory will be finished in a short time, and be finished to buy again；And the durable goods such as pots and pans are then grown Time uses, and user will not generally replace in a short time.

Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed The scope of the present invention.

Fig. 4 shows the schematic block diagram of intelligent shopping guide system 400 according to an embodiment of the present invention.Intelligent shopping guide system 400 include imaging sensor 410, storage device 430 and processor 440.

Imaging sensor 410 is for acquiring image information.

The storage of storage device 430 is for realizing the corresponding steps in intelligent shopping guide method according to an embodiment of the present invention Program code.

The processor 440 is for running the program code stored in the storage device 430, to execute according to the present invention The corresponding steps of the intelligent shopping guide method of embodiment, and for realizing in intelligent shopping guide device according to an embodiment of the present invention Image collection module 310, Customer Information module 320, commercial product recommending module 330.

In one embodiment, following steps are executed when said program code is run by the processor 440:

Obtain the real-time image information of customer；

According to the shopping record, human body attribute and/or surrounding enviroment of the customer, to the customer recommendation commodity.

In addition, also executing following steps when said program code is run by the processor 440:

Illustratively,

The real-time image information based on the customer determines the shopping record, human body attribute and/or week of the customer Surrounding environment, comprising:

The real-time image information of the customer is sent to server；

Illustratively, the real-time image information includes the human face image information of the customer；

The real-time image information based on the customer determines the shopping record of the customer, comprising: is based on the Gu The human face image information of visitor carries out identification, determines the identification result of the customer；According to the identification result Inquire the shopping record of the customer.

Illustratively, the real-time image information based on the customer determines that the human body attribute of the customer includes:

Human face image information based on the customer carries out face character identification, determines the attribute of the customer, the Gu The human body attribute of visitor includes at least one of gender, age, expression, dressing.

Illustratively, the real-time image information further includes the human body image information of the customer,

The real-time image information based on the customer determines the shopping record human body attribute of the customer, further includes:

Human body image information based on the customer carries out human body Attribute Recognition, determines the human body attribute of the customer, institute The human body attribute for stating customer includes clothing, height, movement posture, whether dresses at least one of special article.

Illustratively, the intelligent shopping guide method further include:, will if not getting the shopping record of the customer The face characteristic and relevant information of the customer is stored to face bottom library, and stores this shopping record of the client.

Illustratively, the real-time image information includes the human body image information of the customer, described to be based on the customer Real-time image information determine the customer shopping record human body attribute, further includes: based on the customer human body image letter Breath carries out human body Attribute Recognition, determines that the human body attribute of the customer, the human body attribute of the customer include clothing, height, move It gestures, whether dress at least one of special article.

Illustratively, the intelligent shopping guide system 400 further includes for storing the picture number acquired by imaging sensor 410 According to, including video data and non-video data.

Illustratively, the storage mode of the video data may include one of following storage mode: local (local) is deposited Storage, database purchase, distributed file system (hdfs) storage and long-range storage, storing service address may include server IP and Service-Port.Wherein, it is locally stored and refers to the received video data of intelligent shopping guide system institute in system local；Data Library storage refer to by intelligent shopping guide system institute received video data be stored in the database of system, database purchase needs exist Corresponding database is installed on intelligent shopping guide system；Distributed file system storage refers to the received view of intelligent shopping guide system institute According to being stored in distributed file system, distributed file system storage needs to install on intelligent shopping guide system distributed frequency File system；Long-range storage, which refers to, transfers to other storage services to store the received video data of intelligent shopping guide system institute. In other examples, the storage mode configured also may include the storage mode of other any suitable types, and the present invention is to this With no restriction.

Illustratively, it is above-mentioned video data is accessed when, can carry out in the form of streaming.For example, can use The transmission mode of binary stream realizes the access to video data.The intelligent shopping guide system 400 sends file in the form of streaming Afterwards, when storage service gets file stream, start to save file.Different from reading in the mode of memory, the interactive access at both ends will It can quickly carry out in the form of streaming, without waiting for sending again after file is read in memory by either party.Similarly, the intelligence When energy purchase guiding system 400 obtains file from storage service, and use such mode.Storage service passes file in the form of streaming It is defeated to arrive the intelligent shopping guide system 400, it is not to read in memory to retransmit.When file spread it is defeated imperfect, both ends connection break When, both service can cause exception, and service is captured, and can attempt to reacquire at this time after waiting such as several seconds some time Or storage file.Efficient quick file access may be implemented in the access for carrying out file in a streaming manner.

In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage Instruction, when described program instruction is run by computer or processor for executing the intelligent shopping guide method of the embodiment of the present invention Corresponding steps, and for realizing the corresponding module in intelligent shopping guide device according to an embodiment of the present invention.The storage medium It such as may include the storage card of smart phone, the storage unit of tablet computer, the hard disk of personal computer, read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage, Or any combination of above-mentioned storage medium.The computer readable storage medium can be one or more computer-readable deposit Any combination of storage media, such as a computer readable storage medium include by being randomly generated based on action command sequence The readable program code of calculation machine, another computer readable storage medium include for carrying out the computer-readable of intelligent shopping guide Program code.

In one embodiment, the computer program instructions may be implemented real according to the present invention when being run by computer Each functional module of the intelligent shopping guide device of example is applied, and/or intelligent shopping guide according to an embodiment of the present invention can be executed Method.

In one embodiment, the computer program instructions execute following steps when being run by computer: obtaining and care for The real-time image information of visitor；Based on the customer real-time face image determine the shopping record of the customer, human body attribute and/ Or surrounding enviroment；According to the shopping record, human body attribute and/or surrounding enviroment of the customer, to the customer recommendation commodity.

In addition, the computer program instructions also execute following steps when being run by computer:

Illustratively, the real-time image information based on the customer determines shopping record and/or the people of the customer Body attribute, comprising:

The real-time image information of the customer is sent to server；

Receive the shopping record and/or human body attribute of the customer that the server is sent, the shopping record and institute Stating human body attribute is that the server is determined based on the real-time image information.

Illustratively, the real-time image information includes the human body image information of the customer, described to be based on the customer Real-time image information determine the customer shopping record human body attribute, further includes:

Each module in intelligent shopping guide system according to an embodiment of the present invention can pass through intelligence according to an embodiment of the present invention Can the processor computer program instructions that store in memory of operation of electronic equipment of shopping guide realize, or can be in root The computer instruction stored in computer readable storage medium according to the computer program product of the embodiment of the present invention is by computer It is realized when operation.

Intelligent shopping guide method and device, intelligent shopping guide equipment and storage medium according to an embodiment of the present invention, by image Identification technology is combined with shopping cart, then can be by acquiring custom image information, to set up intelligent recommendation or shopping guide Service, brings potential revenue opportunities to businessman, improves the shopping experience of customer.

The embodiment of the invention also provides a kind of intelligent shopping guide vehicle, which includes:

Shopping cart；And

The intelligent shopping guide device as described in Fig. 3 or the intelligent shopping guide system as described in Fig. 4 being mounted on the shopping cart.

Intelligent shopping guide vehicle according to an embodiment of the present invention can provide personalized recommendation clothes in customer purchase for customer Business is conducive to the shopping experience for promoting customer.

Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary , and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims Within required the scope of the present invention.

In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.

In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail And technology, so as not to obscure the understanding of this specification.

Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects, To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure, Or in descriptions thereof.However, the method for the invention should not be construed to reflect an intention that i.e. claimed The present invention claims features more more than feature expressly recited in each claim.More precisely, as corresponding As claims reflect, inventive point is that all features less than some disclosed single embodiment can be used Feature solves corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the tool Body embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.

It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.

In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any Can in any combination mode come using.

Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to an embodiment of the present invention The some or all functions of block.The present invention is also implemented as a part or complete for executing method as described herein The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention can store On a computer-readable medium, it or may be in the form of one or more signals.Such signal can be from internet Downloading obtains on website, is perhaps provided on the carrier signal or is provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame Claim.

The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim Subject to protection scope.

Claims

1. a kind of intelligent shopping guide method, which is characterized in that the intelligent shopping guide method includes:

Obtain the real-time image information of customer；

The shopping record, human body attribute and/or surrounding enviroment of the customer are determined based on the real-time image information of the customer；

2. intelligent shopping guide method as described in claim 1, which is characterized in that

The real-time image information based on the customer determines the shopping record, human body attribute and/or peripheral ring of the customer Border, comprising:

The real-time image information of the customer is sent to server；

Receive shopping record, human body attribute and/or the surrounding enviroment of the customer that the server is sent, the shopping story Record, the human body attribute and/or the surrounding enviroment are that the server is determined based on the real-time image information.

3. intelligent shopping guide method as described in claim 1, which is characterized in that

The real-time image information includes the human face image information of the customer；

The real-time image information based on the customer determines the shopping record of the customer, comprising:

Human face image information based on the customer carries out identification, determines the identification result of the customer；

It is recorded according to the shopping of customer described in the identification result queries.

4. intelligent shopping guide method as claimed in claim 3, which is characterized in that the real-time image information based on the customer The human body attribute for determining the customer includes:

Human face image information based on the customer carries out face character identification, determines the human body attribute of the customer, the Gu The human body attribute of visitor includes at least one of gender, age, expression, dressing.

5. intelligent shopping guide method as described in claim 3 or 4, which is characterized in that

The real-time image information further includes the human body image information of the customer,

The real-time image information based on the customer determines the human body attribute of the customer, further includes:

Human body image information based on the customer carries out human body Attribute Recognition, determines the human body attribute of the customer, the Gu The human body attribute of visitor includes clothing, height, movement posture, whether dresses at least one of special article.

6. intelligent shopping guide method as described in claim 3 or 4, which is characterized in that

The real-time image information further includes the background image information of the customer,

The real-time image information based on the customer determines the surrounding enviroment of the customer, comprising:

Background image information based on the customer carries out Background Recognition, determines the surrounding enviroment of the customer.

7. intelligent shopping guide method as claimed in claim 3, which is characterized in that the intelligent shopping guide method further include: if do not had There is the shopping record for getting the customer, then stores the human face image information of the customer to face bottom library, and store the visitor This shopping record at family；And/or it if not getting the shopping record of the customer, is preassigned to customer recommendation Commodity.

8. intelligent shopping guide method as claimed in claim 1 or 2, which is characterized in that it is described according to purchaser record to customer recommendation The method of commodity includes: that the commodity of shopping record are divided into consumables and durable goods two major classes, is recommended according to different classes of selection Strategy.

9. intelligent shopping guide method as claimed in claim 8, which is characterized in that described according to different classes of selection Generalization bounds Method includes: to push away the commodity addition of identical and similar promotion when the commodity purchasing time of consumables being more than the first preset value Recommend list of articles；And/or the commodity of association class are added according to the shopping record of durable goods and recommend list of articles.

10. intelligent shopping guide method as claimed in claim 1 or 2, which is characterized in that the intelligent shopping guide method further include: obtain The image information of all registered customers is taken, and the image information based on the registered customers establishes face bottom library.

11. intelligent shopping guide method as claimed in claim 1 or 2, which is characterized in that described to the customer recommendation commodity, packet It includes:

The information of the commodity is shown on a display screen, and the display location is on intelligent shopping guide device.

12. a kind of intelligent shopping guide device, which is characterized in that the intelligent shopping guide device includes:

Customer Information module, for determining shopping record, the human body category of the customer based on the real-time image information of the customer Property and/or surrounding enviroment；

Commercial product recommending module, for being recorded according to the shopping, human body attribute and/or surrounding enviroment are to the customer recommendation quotient Product.

13. a kind of intelligent shopping guide system, including memory, processor and it is stored on the memory and on the processor The computer program of operation, which is characterized in that the processor is realized in claim 1 to 11 when executing the computer program The step of any one the method.

14. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is counted The step of calculation machine realizes any one of claims 1 to 11 the method when executing.

15. a kind of intelligent shopping guide vehicle characterized by comprising

Shopping cart；And

Intelligent shopping guide device as claimed in claim 12 or the intelligence as claimed in claim 13 being mounted on the shopping cart It can purchase guiding system.