CN111784372A - Store commodity recommendation method and device - Google Patents
Store commodity recommendation method and device Download PDFInfo
- Publication number
- CN111784372A CN111784372A CN201910266797.2A CN201910266797A CN111784372A CN 111784372 A CN111784372 A CN 111784372A CN 201910266797 A CN201910266797 A CN 201910266797A CN 111784372 A CN111784372 A CN 111784372A
- Authority
- CN
- China
- Prior art keywords
- information
- commodity
- customer
- human body
- interest
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Abstract
The invention is suitable for the technical field of computers, and provides a store commodity recommendation method and device, wherein the store commodity recommendation method comprises the following steps: acquiring human body image information and voice information of a customer; when a preset face matched with face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information; determining a customer interest vector based on the historical consumption information; determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information; and determining recommended commodities based on the customer interest vector, the human body characteristic information and the consumption demand information. By carrying out human body feature recognition on the customer, the customer information is utilized to the maximum extent, the customer demand is judged by combining voice recognition, and the store big data is integrated to carry out targeted recommendation on the customer, so that the commodity recommendation of the store has pertinence.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a store commodity recommendation method and device.
Background
Although on-line shopping malls are popular at present, the on-line shopping malls have the problems of inconsistent sizes of clothes of different brands and difference between the upper body effect and the shop display effect, so that for clothes, many people tend to go to shops to try on and buy in person. The existing offline stores are often large in storefront and various in clothing types, cover all age groups, and are difficult to find the clothing needed by a user at the first time. In the conventional store commodity recommendation, whether a user is a member client of a store is judged through face recognition, and the consumption record of the customer in the store and the type of purchased clothes are called for recommendation.
However, recommending commodities by merely determining whether a user is a member client of a store and calling a consumption record of the customer at the store and a type of clothes to be purchased results in no pertinence of recommended commodities and poor user experience.
Disclosure of Invention
In view of this, embodiments of the present invention provide a store commodity recommendation method and device, so as to solve the problems in the prior art that recommended commodities are not targeted and user experience is poor because the commodities are recommended by calling consumption records of customers in stores and types of purchased garments according to whether a user is a member client of a store or not.
A first aspect of an embodiment of the present invention provides a store commodity recommendation method, including:
acquiring human body image information and voice information of a customer;
when a preset face matched with face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information;
determining a customer interest vector based on the historical consumption information;
determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information;
and determining recommended commodities based on the customer interest vector, the human body characteristic information and the consumption demand information.
A second aspect of an embodiment of the present invention provides an store commodity recommendation apparatus, including:
the system comprises a first acquisition unit, a second acquisition unit and a display unit, wherein the first acquisition unit is used for acquiring human body image information and voice information of a customer;
a second obtaining unit, configured to obtain, when a preset face that matches face information included in the human body image information exists in a preset face database, identity information corresponding to the preset face, and obtain, based on the identity information, historical consumption information corresponding to the identity information;
a first determination unit for determining a customer interest vector based on the historical consumption information;
a second determination unit for determining human body feature information based on the human body image information and determining consumption demand information based on the voice information;
and the third determining unit is used for determining recommended commodities based on the customer interest vector, the consumption demand information and the human body characteristic information.
A third aspect of the embodiments of the present invention provides a store merchandise recommendation apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the store merchandise recommendation method according to the first aspect when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the store merchandise recommendation method according to the first aspect described above.
In the embodiment of the invention, the human body image information and the voice information of a customer are acquired; when a preset face matched with face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information; determining a customer interest vector based on the historical consumption information; determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information; and determining recommended commodities based on the customer interest vector, the human body characteristic information and the consumption demand information. According to the method, the human body feature recognition is carried out on the customer, the customer information is utilized to the maximum extent, the customer demand is judged by combining the voice recognition, and the store big data is integrated to carry out targeted recommendation on the customer, so that the commodity recommendation of the store is more targeted.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart of an implementation of a store commodity recommendation method according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of S103 in a store commodity recommendation method according to an embodiment of the present invention;
fig. 3 is a flowchart of an implementation of S105 in a store commodity recommendation method according to an embodiment of the present invention;
FIG. 4 is a flow chart of another implementation of a store merchandise recommendation method according to an embodiment of the present invention;
FIG. 5 is a flow chart of another implementation of a store merchandise recommendation method according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a store commodity recommendation apparatus according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a store commodity recommendation device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a store product recommendation method according to an embodiment of the present invention. The store commodity recommendation method in this embodiment is applicable to stores with offline commodities, and the execution subject of the store commodity recommendation method in this embodiment is a device, for example, a store commodity recommendation device, and the store commodity recommendation device includes, but is not limited to, a terminal or a server. The store merchandise recommendation method shown in fig. 1 may include:
s101: and acquiring human body image information and voice information of the customer.
The equipment receives human body image information of a customer, wherein the human body image information comprises a face image and a limb image of the customer, and the human body image information of the customer can be collected by a camera installed at an entrance of a store and sent to the equipment. In this embodiment, the communication mode between the device and the camera may include third generation mobile communication technology/fourth generation mobile communication technology connection (3G/4G/5G), WiFi communication, bluetooth communication, and the like.
Further, to save power consumption, S101 may include: and when human body information in the preset range is detected, the human body image information and the voice information of the customer are acquired.
Because the pedestrian volume of the block or the market that the store is located is great, people nearby the store come and go, in order to save energy consumption, can set up when having human information in the predetermined scope, equipment sends the instruction that is used for acquireing customer's human image information and speech information again, acquires customer's human image information and speech information. In an embodiment that the device detects whether human body information exists in the preset range, the device may receive information sent by an infrared sensor installed at an entrance of a store, and determine whether a customer is currently approaching the current store according to the information, for example, when the information sent by the infrared sensor is set to be "1", that is, when the customer is currently approaching the current store, and when the information sent by the infrared sensor is set to be "0", that is, that no customer is currently approaching the current store; in another embodiment, the device may receive sound information received by a microphone installed at an entrance of the store, and if no sound or weak sound is received, it indicates that no customer is currently present in the store, and when it can be determined that a customer is present through the received sound information, it indicates that a customer is currently present in the store.
S102: when a preset face matched with the face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information.
The equipment obtains a preset face matched with face information contained in the human body image information in a preset face database, and when the preset face matched with the face information contained in the human body image information exists in the preset face database, the identity information corresponding to the preset face is obtained, wherein the identity information is used for judging whether a customer is a new store or not, and when the customer consumes at a store, the equipment can generate a preset face image of the customer, identity information matched with the preset face image of the customer and historical consumption information corresponding to the identity information.
The device can perform face recognition on the acquired face image, and perform preprocessing on the face image, wherein the preprocessing includes image color enhancement, graying, filtering, illumination normalization, contrast enhancement, image rotation and the like. Filtering an original image, and then extracting features of the preprocessed image to obtain facial feature information of a customer. The preset face characteristic information and the corresponding identity information are stored in the equipment. After the facial feature information of the equipment customer is obtained, the identity information of the customer is obtained based on the preset facial feature information and the corresponding identity information. The face recognition mainly depends on the difference of facial features of people, and the facial features of the faces are extracted through the input face information, so that the identities of the people in the images are recognized. In this embodiment, the face recognition method may include a geometric feature-based method, a template-based method, and a model-based method.
When the acquired identity information matched with the preset face indicates that the customer has a consumption behavior in the store, acquiring historical consumption information corresponding to the identity information based on the identity information matched with the preset face and the historical consumption information corresponding to the identity information, wherein the historical consumption information comprises the historical consumption information in the current store and the historical consumption information in other chain stores.
When the identity information matched with the preset face is not acquired, the customer has no consumption behavior in the store, and historical consumption information corresponding to the identity information in other chain stores is acquired based on the identity information matched with the preset face.
S103: a customer interest vector is determined based on the historical consumption information.
The device determines an interest vector of the customer based on the historical consumption information, wherein the interest vector of the customer comprises a plurality of dimensional data, the interest vector of the customer is used for representing the degree of interest of the customer in the historical consumption goods, and the interest vector of the customer can be determined according to the time of the customer for purchasing the goods, the quantity of the goods purchased by the customer and the like determined by the historical consumption information.
Further, in order to more accurately obtain the customer interest vector, S103 may include S1031 to S1033, as shown in fig. 2, where S1031 to S1033 are specifically as follows:
s1031: determining the interest goods of the customer based on the historical consumption information.
The equipment extracts the historical behaviors of the customer based on the historical consumption information, analyzes the historical behaviors of the customer, and obtains the commodities purchased by the customer, namely the commodities of interest of the customer. In this embodiment, if nb (u) is set as the product that customer u contacts in act b, the product set n (u) that customer u is interested in may be defined as:
s1032: and acquiring the purchase time of the interest commodities, and determining the interest weight of each interest commodity based on the purchase time.
The device obtains the purchasing time of the interested commodities based on the analysis of the historical behaviors of the customer, and determines the interest weight of each interested commodity based on the purchasing time, wherein the historical behaviors of the customer can comprise purchasing behaviors, goods returning behaviors, goods changing behaviors and the like, and the weights corresponding to different behaviors are different. The closer the time when the historical behavior of the customer occurs to the current time, the greater the interest weight of the customer on the commodity, so a time attenuation coefficient, t, is set at the momentb(u, i) is the time, γ, at which customer u has taken historical action b on item of interest ibThe interest weight expressed by the historical behavior b of the customer, the interest weight r of the customer on the commodity i in N (u)uiCalculated by the following formula:
where t is the current time, λ (λ)>0) Is the time attenuation coefficient. The above formula expresses Nb(u) cumulative result of interest weight of historical behavior corresponding to commodity, γbWith time exponentially decaying, λ is the decay coefficient, and if a customer has a lot of behaviors on a commodity and the behaviors occur in the near future, the customer has a larger interest weight on the commodity.
S1033: determining a customer interest vector based on the interest weight of each interest commodity and the commodity name of the interest commodity; wherein each element in the customer interest vector comprises a commodity name of an interest commodity and an interest weight thereof.
The device determines a customer interest vector based on the interest weight of each interest item and the item name of the interest item, wherein each element in the customer interest vector comprises the item name of one interest item and the interest weight thereof.
S104: determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information.
The equipment identifies the human body image information to determine human body characteristic information, wherein the human body characteristic information comprises age, gender, upper clothes color, lower clothes color, stature and the like. The human body attribute information such as age, gender and stature cannot be intuitively acquired from limb images, two methods are mainly used for identifying the human body attribute information, one method is a method based on an integral model, and a typical technology is a human body detector which is constructed by combining a Histogram of Oriented Gradients (HOG) with a Support Vector Machine (SVM), wherein the HOG divides the image into small connected regions which are called cell units, then the Gradient or edge direction histograms of all pixel points in the cell units are collected, and finally the histograms are combined to obtain feature description information. In this embodiment, when a limb image is acquired, skeleton information of a person in the limb image is extracted, wherein the skeleton information includes skeleton feature points and positions of the skeleton feature points in the image, and human body attribute information is acquired according to the skeleton information; another type of method is a local model-based method, which builds a body detector from the orientation and position of the limbs.
The device recognizes the voice information. The speech recognition is to take speech as a research object, and a machine automatically recognizes and understands human dictation language through speech signal processing and pattern recognition. Speech recognition technology is a high technology that allows machines to convert speech signals into corresponding text or commands through a recognition and understanding process. Speech recognition is a very extensive cross-discipline, which is very closely related to such disciplines as acoustics, phonetics, linguistics, information theory, pattern recognition theory, neurobiology, etc.
There are three common methods of speech recognition: vocal tract model and speech knowledge based methods, template matching methods, and methods utilizing artificial neural networks. The development of the template matching method is mature, and the practical stage is reached at present. In the template matching method, four steps are required: feature extraction, template training, template classification and judgment. There are three common techniques used in the identification process: dynamic Time Warping (DTW), hidden markov (HMM) theory, Vector Quantization (VQ) techniques. In this embodiment, taking an HMM algorithm as an example, a specific process is shown in fig. 3, a speech decoding and searching algorithm is constructed based on a trained acoustic model, a trained language model and a dictionary, and after feature extraction is performed on speech information, the speech decoding and searching algorithm is used for processing to obtain text output information of the speech information.
After the voice information is recognized by the equipment, consumption requirement information is determined, wherein the consumption requirement information comprises consumption requirement keywords which can comprise commodity colors, commodity types and the like, and for example, black, shirts and the like can be used as the consumption requirement information. If the voice message is "want to buy a black, sleek shirt for dad", the consumption requirement information that can be determined at this time can be: "daddy", "black", "build" and "shirt".
S105: and determining recommended commodities based on the customer interest vector, the human body characteristic information and the consumption demand information.
The device determines recommended goods based on the customer interest vector, the human body feature information, and the consumption demand information. In one embodiment, the device may determine a customer interest keyword based on the customer interest vector, and filter the goods in the database based on the customer interest keyword, the body characteristic information, and the consumption demand information.
Further, in another embodiment, in order to more accurately acquire the recommended product, S105 may include S1051 to S1052, and as shown in fig. 3, S1051 to S1052 specifically include the following:
s1051: and acquiring a candidate interest commodity set based on the customer interest vector.
The device obtains items of possible interest to the customer based on the customer interest vector, all items of possible interest to the customer comprising a set of candidate items of interest. Some keywords can be obtained based on the interest vectors of the customers, and the commodities which the customers may be interested in are obtained by screening based on the keywords.
Further, in order to more accurately obtain the candidate interest commodity set, the candidate interest commodity set may also be obtained by presetting a commodity matrix, and S1051 may include: and acquiring a preset commodity matrix corresponding to the commodity name of the interest commodity, and determining a candidate interest commodity set based on the preset commodity matrix. The method comprises the steps that commodity names of interested commodities and corresponding preset commodity matrixes of the interested commodities are preset by equipment, the preset commodity matrixes corresponding to the commodity names of the interested commodities are obtained, similar commodities are found out by inquiring the preset commodity matrixes, and similar commodities of all the interested commodities are aggregated through relevancy to obtain a candidate interested commodity set.
Similar commodities are found by inquiring a preset commodity matrix, and are generally found by depending on a correlation table, wherein each correlation table defines the correlation between the commodities. Let WkIs the k-th correlation table, Wk(i, j) defines the similarity of the item (i, j) on the kth correlation table, Sk(i, M) is the set of M items most similar to item i in the kth relevance table, and the preliminary recommendation result R0The following commercial products were included:
in the above formula, R0Determining all S based on different k and different ik(i, M), where i is of a set of items N (u) in which customer u is interested.
S1052: and determining recommended commodities from the candidate interest commodity set based on the consumption demand information and the human body characteristic information.
And the equipment screens the candidate interest commodity set based on the consumption demand information and the human body characteristic information to determine recommended commodities.
In the embodiment of the invention, the human body image information and the voice information of a customer are acquired; when a preset face matched with face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information; determining a customer interest vector based on the historical consumption information; determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information; and determining recommended commodities based on the customer interest vector, the human body characteristic information and the consumption demand information. According to the method, the human body feature recognition is carried out on the customer, the customer information is utilized to the maximum extent, the customer demand is judged by combining the voice recognition, and the store big data is integrated to carry out targeted recommendation on the customer, so that the commodity recommendation of the store is more targeted.
Referring to fig. 4, fig. 4 is a flowchart illustrating an implementation of another store commodity recommendation method according to an embodiment of the present invention. The store commodity recommendation method in the present embodiment is applied to stores with off-line commodities, and the execution subject of the store commodity recommendation method in the present embodiment is equipment, for example, store commodity recommendation equipment. The difference between the present embodiment and the previous embodiment is that S203 to S204 are further included after S202, where S201 to S202 in the present embodiment are the same as S101 to S102 in the previous embodiment, specifically refer to S101 to S102 in the previous embodiment, where after S202, when the identity information matching with the face image is not acquired or the historical consumption information corresponding to the identity information is not acquired, S203 to S204 may be executed, as shown in fig. 4, S203 to S204 specifically include the following steps:
s203: when the identity information matched with the face image is not acquired or the historical consumption information corresponding to the identity information is not acquired, determining the human body feature information based on the limb image and determining the consumption demand information based on the voice information.
When the identity information matched with the face image is not acquired or the historical consumption information corresponding to the identity information is not acquired, determining the human body feature information based on the limb image and determining the consumption demand information based on the voice information, which is the same as S104, please refer to S104 specifically, and details are not repeated here.
S204: and determining recommended commodities based on the consumption demand information and the human body characteristic information.
The equipment searches in a commodity database based on the consumption demand information and the human body characteristic information, and screens out commodities matched with the consumption demand information and the human body characteristic information. Therefore, when the current customer is a new shop customer or the consumption information is less, the user can identify the demographic characteristics such as age and gender according to the human body, obtain the demand information of the customer and the information related to the body type of the user, recommend commodities according to the information, and realize the differentiated and personalized recommendation.
Referring to fig. 5, fig. 5 is a flowchart illustrating another shop commodity recommendation method according to an embodiment of the present invention. The store commodity recommendation method in the present embodiment is applied to stores with off-line commodities, and the execution subject of the store commodity recommendation method in the present embodiment is equipment, for example, store commodity recommendation equipment. The difference between the present embodiment and the previous embodiment is that S306 is further included after S305, and S301 to S305 in the present embodiment are the same as S101 to S105 in the first embodiment, specifically, refer to S101 to S105 in the previous embodiment, wherein S306 is executed after S301 to S305 is executed, and S306 is specifically as follows:
s306: and when the number of the recommended commodities is not zero, acquiring the commodity information of the recommended commodities and displaying the commodity information.
Due to the fact that stores in different regions are different, current real-time price information may not be uniform, meanwhile, due to climate factors, clothing inventory of each store is not consistent, and placement areas of different types of clothing of each store are different. Therefore, the local database of the current store needs to be queried again to see whether the recommended goods are stored in the local store.
And querying a database, and when the quantity of the recommended commodities is not zero, acquiring commodity information of the recommended commodities, wherein the commodity information can comprise commodity names, commodity pictures, commodity prices and commodity storage position information. And pushing the commodity information to a display to display the commodity information.
Further, in order to facilitate the customer to better view the recommended product, after S306, the following steps may be included: and generating a two-dimensional code associated with the recommended commodity information, and displaying the two-dimensional code. In the specific implementation process, a large screen display is arranged to display recommended commodity information including pictures, size stock conditions, real-time prices and specific direction maps of commodities in stores. Meanwhile, in order to facilitate checking of customers and improve system conversion rate, a two-dimensional code containing recommended commodity information can be generated and also displayed on a screen, the customers can directly check the recommended commodity information on the mobile phone after scanning by the mobile phone, and the shopping guide recommendation system can quickly find commodity information and directions which are interested by the customers and save time and cost. For the merchant, more store new guests can be attracted, and meanwhile, the labor cost of shopping guide is saved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Referring to fig. 6, fig. 6 is a schematic diagram of a store commodity recommendation device according to an embodiment of the present invention. The units included are used to perform the steps in the embodiments corresponding to fig. 1-5. Please refer to the related description of the embodiments in fig. 1 to 5. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 6, the store merchandise recommendation apparatus 6 includes:
a first acquiring unit 610 for acquiring human body image information and voice information of a customer;
a second obtaining unit 620, configured to obtain, when a preset face that matches face information included in the human body image information exists in a preset face database, identity information corresponding to the preset face, and obtain, based on the identity information, historical consumption information corresponding to the identity information;
a first determining unit 630 for determining a customer interest vector based on the historical consumption information;
a second determining unit 640 for determining human body feature information based on the human body image information and determining consumption demand information based on the voice information;
a third determining unit 650 for determining a recommended commodity based on the customer interest vector, the consumption demand information, and the human body feature information.
Further, the first determining unit 630 is specifically configured to:
determining interest goods of the customer based on the historical consumption information;
acquiring the purchase time of the interest commodities, and determining the interest weight of each interest commodity based on the purchase time;
determining a customer interest vector based on the interest weight of each interest commodity and the commodity name of the interest commodity; each element in the interest vector of the customer comprises a commodity name of an interest commodity and an interest weight of the interest commodity.
Further, the third determining unit 650 includes:
a third obtaining unit, configured to obtain a candidate interest commodity set based on the customer interest vector;
and the fourth determining unit is used for determining recommended commodities from the candidate interest commodity set based on the consumption demand information and the human body characteristic information.
Further, the third obtaining unit is specifically configured to:
and acquiring a preset commodity matrix corresponding to the commodity name of the interest commodity, and determining a candidate interest commodity set based on the preset commodity matrix.
Further, the first obtaining unit 610 is specifically configured to:
and when human body information in the preset range is detected, the human body image information and the voice information of the customer are acquired.
Further, the store commodity recommendation apparatus 6 further includes:
and the processing unit is used for acquiring the commodity information of the recommended commodities and displaying the commodity information when the number of the recommended commodities is not zero.
Further, the store commodity recommendation apparatus 6 further includes:
a fifth determining unit, configured to determine, when identity information matching the face image is not obtained or historical consumption information corresponding to the identity information is not obtained, human body feature information based on the limb image and determine consumption demand information based on the voice information;
and the sixth determining unit is used for determining recommended commodities based on the consumption demand information and the human body characteristic information.
Further, the store commodity recommendation apparatus 6 further includes:
and the generating unit is used for generating a two-dimensional code associated with the recommended commodity information and displaying the two-dimensional code.
Fig. 7 is a schematic diagram of a store merchandise recommendation device according to an embodiment of the present invention. As shown in fig. 7, the store merchandise recommendation device 7 of this embodiment includes: a processor 70, a memory 71 and a computer program 72, such as a store merchandise recommendation program, stored in the memory 71 and executable on the processor 70. The processor 70, when executing the computer program 72, implements the steps in the various store merchandise recommendation method embodiments described above, such as the steps 101-105 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of the units in the above-described device embodiments, such as the functions of the modules 610 to 650 shown in fig. 6.
Illustratively, the computer program 72 may be divided into one or more units, which are stored in the memory 7 and executed by the processor 7 to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 72 in the store merchandise recommendation device 7. For example, the computer program 72 may be divided into a first acquiring unit, a second acquiring unit, a first determining unit, a second determining unit, and a third determining unit, and the specific functions of each unit are as follows:
the system comprises a first acquisition unit, a second acquisition unit and a display unit, wherein the first acquisition unit is used for acquiring human body image information and voice information of a customer;
a second obtaining unit, configured to obtain, when a preset face that matches face information included in the human body image information exists in a preset face database, identity information corresponding to the preset face, and obtain, based on the identity information, historical consumption information corresponding to the identity information;
a first determination unit for determining a customer interest vector based on the historical consumption information;
a second determination unit for determining human body feature information based on the human body image information and determining consumption demand information based on the voice information;
and the third determining unit is used for determining recommended commodities based on the customer interest vector, the consumption demand information and the human body characteristic information.
The store merchandise recommendation device may include, but is not limited to, a processor 70, a memory 71. Those skilled in the art will appreciate that fig. 7 is merely an example of the store merchandise recommendation device 7, and does not constitute a limitation of the store merchandise recommendation device 7, and may include more or less components than those shown, or some components in combination, or different components, for example, the store merchandise recommendation device may also include an input-output device, a network access device, a bus, etc.
The Processor 60 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 71 may be an internal storage unit of the store merchandise recommendation device 7, such as a hard disk or a memory of the store merchandise recommendation device 7. The memory 71 may also be an external storage device of the store commodity recommendation device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped on the store commodity recommendation device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the store merchandise recommendation device 7. The memory 71 is used to store the computer program and other programs and data required by the store merchandise recommendation device. The memory 71 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. . Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A store commodity recommendation method, comprising:
acquiring human body image information and voice information of a customer;
when a preset face matched with face information contained in the human body image information exists in a preset face database, acquiring identity information corresponding to the preset face, and acquiring historical consumption information corresponding to the identity information based on the identity information;
determining a customer interest vector based on the historical consumption information;
determining human body feature information based on the human body image information, and determining consumption demand information based on the voice information;
and sorting the store commodities based on the customer interest vector, the human body feature information and the consumption demand information to determine candidate commodities according to a sorting result and recommend the candidate commodities to the customer.
2. The store merchandise recommendation method of claim 1, wherein said determining a customer interest vector based on said historical consumption information comprises:
determining interest goods of the customer based on the historical consumption information;
acquiring the purchase time of the interest commodities, and determining the interest weight of each interest commodity based on the purchase time;
determining a customer interest vector based on the interest weight of each interest commodity and the commodity name of the interest commodity; each element in the interest vector of the customer comprises a commodity name of an interest commodity and an interest weight of the interest commodity.
3. The store commodity recommendation method according to claim 1, wherein the determining a recommended commodity based on the customer interest vector, the human body feature information, and the consumption demand information includes:
acquiring a candidate interest commodity set based on the customer interest vector;
and determining recommended commodities from the candidate interest commodity set based on the consumption demand information and the human body characteristic information.
4. The store commodity recommendation method of claim 3, wherein said obtaining a set of candidate interest commodities based on said customer interest vector comprises:
and acquiring a preset commodity matrix corresponding to the commodity name of the interest commodity, and determining a candidate interest commodity set based on the preset commodity matrix.
5. The store commodity recommendation method according to claim 1, wherein the acquiring of the human body image information and the voice information of the customer comprises:
and when human body information in the preset range is detected, the human body image information and the voice information of the customer are acquired.
6. The store commodity recommendation method according to claims 1-5, further comprising, after said determining recommended commodities based on the customer interest vector, the human body feature information, and the consumption demand information:
and when the number of the recommended commodities is not zero, acquiring the commodity information of the recommended commodities and displaying the commodity information.
7. The store commodity recommendation method according to claim 1, wherein, when there is a preset face matching the face information included in the human body image information in a preset face database, acquiring identity information corresponding to the preset face, and after acquiring historical consumption information corresponding to the identity information based on the identity information, the method further comprises:
when a preset face matched with face information contained in the human body image information is not acquired or historical consumption information corresponding to the identity information is not acquired, determining human body feature information based on the limb image and determining consumption demand information based on the voice information;
and determining recommended commodities based on the consumption demand information and the human body characteristic information.
8. The store commodity recommendation method according to claim 6, wherein, after acquiring the commodity information of the recommended commodity and displaying the commodity information when it is found that the recommended commodity is in stock in the current store, the method further comprises:
and generating a two-dimensional code associated with the recommended commodity information, and displaying the two-dimensional code.
9. A store commodity recommendation apparatus comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of the method according to any one of claims 1 to 8 when executing said computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910266797.2A CN111784372A (en) | 2019-04-03 | 2019-04-03 | Store commodity recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910266797.2A CN111784372A (en) | 2019-04-03 | 2019-04-03 | Store commodity recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111784372A true CN111784372A (en) | 2020-10-16 |
Family
ID=72755691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910266797.2A Pending CN111784372A (en) | 2019-04-03 | 2019-04-03 | Store commodity recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111784372A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270275A (en) * | 2020-11-02 | 2021-01-26 | 上海哔哩哔哩科技有限公司 | Commodity searching method and device based on picture recognition and computer equipment |
| CN113643096A (en) * | 2021-08-06 | 2021-11-12 | 北京远舢智能科技有限公司 | Commodity recommendation method and device based on user portrait, electronic equipment and computer readable storage medium |
| CN113643094A (en) * | 2021-08-06 | 2021-11-12 | 北京远舢智能科技有限公司 | Vending method and device based on user portrait and voice recognition technology, electronic equipment and storage medium |
| CN113674037A (en) * | 2021-10-21 | 2021-11-19 | 西安超嗨网络科技有限公司 | Data acquisition and recommendation method based on shopping behaviors |
| CN114612142A (en) * | 2022-03-09 | 2022-06-10 | 深圳市瑞众科技有限公司 | Multi-mode information fusion commercial content recommendation method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358451A (en) * | 2017-07-17 | 2017-11-17 | 竹间智能科技（上海）有限公司 | A kind of interactive intelligent witch mirror |
| CN108921660A (en) * | 2018-06-29 | 2018-11-30 | 上海小蚁科技有限公司 | Consumption, which is drawn a portrait, determines method and device, storage medium, terminal |
| CN108961005A (en) * | 2018-07-06 | 2018-12-07 | 北京旷视科技有限公司 | Information-pushing method, device, electronic equipment and medium |
| CN109165992A (en) * | 2018-07-16 | 2019-01-08 | 北京旷视科技有限公司 | A kind of intelligent shopping guide method, apparatus, system and computer storage medium |
| CN109472677A (en) * | 2018-12-28 | 2019-03-15 | 出门问问信息科技有限公司 | Information-pushing method, device, electronic equipment and computer readable storage medium |
-
2019
- 2019-04-03 CN CN201910266797.2A patent/CN111784372A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358451A (en) * | 2017-07-17 | 2017-11-17 | 竹间智能科技（上海）有限公司 | A kind of interactive intelligent witch mirror |
| CN108921660A (en) * | 2018-06-29 | 2018-11-30 | 上海小蚁科技有限公司 | Consumption, which is drawn a portrait, determines method and device, storage medium, terminal |
| CN108961005A (en) * | 2018-07-06 | 2018-12-07 | 北京旷视科技有限公司 | Information-pushing method, device, electronic equipment and medium |
| CN109165992A (en) * | 2018-07-16 | 2019-01-08 | 北京旷视科技有限公司 | A kind of intelligent shopping guide method, apparatus, system and computer storage medium |
| CN109472677A (en) * | 2018-12-28 | 2019-03-15 | 出门问问信息科技有限公司 | Information-pushing method, device, electronic equipment and computer readable storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270275A (en) * | 2020-11-02 | 2021-01-26 | 上海哔哩哔哩科技有限公司 | Commodity searching method and device based on picture recognition and computer equipment |
| CN112270275B (en) * | 2020-11-02 | 2023-11-21 | 上海哔哩哔哩科技有限公司 | Commodity searching method and device based on picture identification and computer equipment |
| CN113643096A (en) * | 2021-08-06 | 2021-11-12 | 北京远舢智能科技有限公司 | Commodity recommendation method and device based on user portrait, electronic equipment and computer readable storage medium |
| CN113643094A (en) * | 2021-08-06 | 2021-11-12 | 北京远舢智能科技有限公司 | Vending method and device based on user portrait and voice recognition technology, electronic equipment and storage medium |
| CN113674037A (en) * | 2021-10-21 | 2021-11-19 | 西安超嗨网络科技有限公司 | Data acquisition and recommendation method based on shopping behaviors |
| CN113674037B (en) * | 2021-10-21 | 2022-01-25 | 西安超嗨网络科技有限公司 | Data acquisition and recommendation method based on shopping behaviors |
| CN114612142A (en) * | 2022-03-09 | 2022-06-10 | 深圳市瑞众科技有限公司 | Multi-mode information fusion commercial content recommendation method and device and electronic equipment |
| CN114612142B (en) * | 2022-03-09 | 2023-09-26 | 深圳市瑞众科技有限公司 | Multi-mode information fusion commercial content recommendation method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784372A (en) | Store commodity recommendation method and device | |
| CN107705066B (en) | Information input method and electronic equipment during commodity warehousing | |
| CN106776619B (en) | Method and device for determining attribute information of target object | |
| US10891465B2 (en) | Methods and apparatuses for searching for target person, devices, and media | |
| CN109117777A (en) | The method and apparatus for generating information | |
| CN107833082B (en) | Commodity picture recommendation method and device | |
| Dubey et al. | Species and variety detection of fruits and vegetables from images | |
| CN108171207A (en) | Face identification method and device based on video sequence | |
| CN107305557A (en) | Content recommendation method and device | |
| KR101835333B1 (en) | Method for providing face recognition service in order to find out aging point | |
| CN112085568B (en) | Commodity and rich media aggregation display method and equipment, electronic equipment and medium | |
| CN108197980B (en) | Method/system for generating portrait of personalized shopper, storage medium and terminal | |
| CN110874534A (en) | Data processing method and data processing device | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| CN107203638A (en) | Monitor video processing method, apparatus and system | |
| CN110827797A (en) | Voice response event classification processing method and device | |
| CN113495987A (en) | Data searching method, device, equipment and storage medium | |
| CN114360182A (en) | Intelligent alarm method, device, equipment and storage medium | |
| CN111126049A (en) | Object relation prediction method and device, terminal equipment and readable storage medium | |
| US20220172271A1 (en) | Method, device and system for recommending information, and storage medium | |
| CN110363187A (en) | A kind of face identification method, device, machine readable media and equipment | |
| KR101901645B1 (en) | Method, apparatus, system and computer program for image retrieval | |
| CN112214639A (en) | Video screening method, video screening device and terminal equipment | |
| CN111753852A (en) | Tea leaf identification method, recommendation method, tea leaf identification device, equipment and medium | |
| KR101910825B1 (en) | Method, apparatus, system and computer program for providing aimage retrieval model |
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 |