CN117934088A

CN117934088A - Commodity recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN117934088A
Application number: CN202211250967.6A
Authority: CN
Inventors: 周浩
Original assignee: SF Technology Co Ltd
Current assignee: SF Technology Co Ltd
Priority date: 2022-10-12
Filing date: 2022-10-12
Publication date: 2024-04-26

Abstract

The application discloses a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium, wherein the commodity recommendation method comprises the following steps: acquiring shopping monitoring images of users to be recommended; determining a commodity area corresponding to the shopping monitoring image according to the position information of the shooting device associated with the shopping monitoring image; generating a shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image; determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track; and screening and obtaining commodities to be recommended corresponding to the users to be recommended according to the commodity attributes corresponding to the preference areas. The commodity to be recommended determined by the method is more accurate. In addition, the method can determine the commodity to be recommended only according to the data of the shopping monitoring image and the position information of the shooting device, and is low in cost and convenient to deploy.

Description

Commodity recommendation method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of article recommendation, in particular to a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium.

Background

In order to increase sales volume of goods, at present, merchants recommend goods to users through short messages, mails, settlement counters in shops or the like.

The current recommendation method generally predicts the types of goods favored by the user according to the user attribute information such as age, income and the like of the user so as to recommend the goods. However, this recommendation method predicts the type of goods preferred by the user only from a global point of view, and does not take individual differences of the users into consideration, so that the recommended goods are not accurate enough.

Disclosure of Invention

The application provides a commodity recommending method, a commodity recommending device, electronic equipment and a storage medium, and aims to solve the problem that the existing commodity recommending method is inaccurate.

In a first aspect, the present application provides a commodity recommendation method, including:

acquiring shopping monitoring images of users to be recommended;

Determining a commodity area corresponding to the shopping monitoring image according to the position information of the shooting device associated with the shopping monitoring image;

Generating a shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image;

determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track;

And screening and obtaining commodities to be recommended corresponding to the users to be recommended according to the commodity attributes corresponding to the preference areas.

In one possible implementation manner of the present application, the determining the preference area of the user to be recommended according to the residence time of the user to be recommended in the commodity area and the shopping track includes:

counting to obtain the stay time of the user to be recommended in the commodity area according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image;

and sequencing the commodity areas according to the stay time in the commodity areas and the sequence information among the commodity areas in the shopping track to obtain the highest-sequencing preference area.

In one possible implementation manner of the present application, the acquiring a shopping monitoring image of a user to be recommended includes:

receiving a recommendation triggering request, and determining a user to be recommended corresponding to the recommendation triggering request;

acquiring a reference image of the user to be recommended;

and matching the user posture information contained in the reference image with the user posture information contained in the monitoring image in the preset database to obtain the shopping monitoring image of the user to be recommended.

In one possible implementation manner of the present application, the preset database includes a plurality of preset storage spaces, each of the preset storage spaces is used for storing the monitoring images acquired in different time periods and corresponding to different commodity areas,

The step of matching the user posture information contained in the reference image with the user posture information contained in the monitoring image in the preset database to obtain the shopping monitoring image of the user to be recommended comprises the following steps:

Calculating the similarity between the user posture information contained in the reference image and the user posture information in each preset storage space;

screening to obtain candidate images with similarity larger than a preset similarity threshold value in each preset storage space, and selecting the candidate image with highest similarity from each preset storage space as a shopping monitoring image of the user to be recommended.

In one possible implementation manner of the present application, before the obtaining the reference image of the user to be recommended, the method further includes:

acquiring historical recommended commodities of the user to be recommended and recommendation feedback information of the historical recommended commodities;

and if the commodity purchase times in the recommendation feedback information are greater than a preset time threshold, executing the step of acquiring the reference image of the user to be recommended.

In one possible implementation of the present application, the merchandise attribute includes a first merchandise category,

And screening to obtain the commodity to be recommended corresponding to the user to be recommended according to the commodity attribute corresponding to the preference area, wherein the commodity to be recommended comprises the following components:

Inquiring a preset commodity sales record to obtain a second commodity category associated with the first commodity category corresponding to the preference area;

And screening and obtaining the commodity to be recommended corresponding to the user to be recommended from preset candidate commodities according to the first commodity category and the second commodity category.

In one possible implementation manner of the present application, before the selecting, according to the first commodity category and the second commodity category, the commodity to be recommended corresponding to the user to be recommended from preset candidate commodities, the method further includes:

carrying out statistical processing on the historical consumption amount in the commodity sales records to obtain consumption amount distribution information;

obtaining a target amount with the maximum probability in the consumption amount distribution information;

And comparing the preset commodity sales amount of the commodity sold with the target amount to obtain candidate commodities of which commodity sales amount is smaller than the target amount.

In a second aspect, the present application provides a commodity recommendation device, comprising:

The acquisition unit is used for acquiring shopping monitoring images of users to be recommended;

a first determining unit, configured to determine a commodity area corresponding to the shopping monitoring image according to position information of a shooting device associated with the shopping monitoring image;

The generation unit is used for generating the shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image;

The second determining unit is used for determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track;

And the screening unit is used for screening and obtaining the commodity to be recommended corresponding to the user to be recommended according to the commodity attribute corresponding to the preference area.

In a possible implementation of the application, the second determining unit is further configured to:

In a possible implementation of the application, the obtaining unit is further configured to:

acquiring a reference image of the user to be recommended;

In one possible implementation manner of the present application, the preset database includes a plurality of preset storage spaces, each of the preset storage spaces is used for storing the monitoring images acquired in different time periods and corresponding to different commodity areas, and the acquiring unit is further used for:

In a possible implementation of the application, the screening unit is further configured to:

In a third aspect, the present application also provides an electronic device, the electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor executing the steps of any of the commodity recommendation methods provided by the present application when calling the computer program in the memory.

In a fourth aspect, the present application also provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the merchandise recommendation methods provided by the present application.

In summary, the commodity recommendation method provided by the embodiment of the application includes: acquiring shopping monitoring images of users to be recommended; determining a commodity area corresponding to the shopping monitoring image according to the position information of the shooting device associated with the shopping monitoring image; generating a shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image; determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track; and screening and obtaining commodities to be recommended corresponding to the users to be recommended according to the commodity attributes corresponding to the preference areas.

Therefore, when the commodity recommending method provided by the embodiment of the application acquires the favorite area, the commodity recommending method is more accurate according to the personal shopping habit of the user to be recommended, so that the determined commodity to be recommended better accords with the preference of the user to be recommended. In addition, the method can obtain the favorite area and the commodity to be recommended only according to the data of the shopping monitoring image and the position information of the shooting device, and has low cost and convenient deployment.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is an application scenario schematic diagram of a commodity recommendation method provided by an embodiment of the present application;

FIG. 2 is a schematic flow chart of a commodity recommendation method according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of acquiring shopping monitoring images provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a configuration of a preset database according to an embodiment of the present application;

FIG. 5 is a schematic flow chart of another method for recommending commodities according to an embodiment of the present application;

FIG. 6 is a schematic flow chart of acquiring goods to be recommended according to an embodiment of the present application;

FIG. 7 is a schematic structural view of an embodiment of a commodity recommendation device according to the present application;

Fig. 8 is a schematic structural diagram of an embodiment of an electronic device provided in an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.

In describing embodiments of the present application, it should be understood that the terms "first," "second," and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless explicitly defined otherwise.

The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known processes have not been described in detail in order to avoid unnecessarily obscuring the description of the embodiments of the application. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

The embodiment of the application provides a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium. The commodity recommending device can be integrated in electronic equipment, and the electronic equipment can be a server, a terminal and other equipment.

The execution main body of the commodity recommendation method in the embodiment of the present application may be a commodity recommendation device provided in the embodiment of the present application, or different types of electronic devices such as a server device, a physical host, or a User Equipment (UE) integrated with the commodity recommendation device, where the commodity recommendation device may be implemented in a hardware or software manner, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a notebook computer, a palm computer, a desktop computer, or a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA).

The electronic device may be operated in a single operation mode, or may also be operated in a device cluster mode.

Referring to fig. 1, fig. 1 is a schematic view of a commodity recommendation system according to an embodiment of the present application. The commodity recommendation system may include an electronic device 101, and a commodity recommendation device is integrated in the electronic device 101.

In addition, as shown in FIG. 1, the merchandise recommendation system may also include a memory 102 for storing data, such as text data.

It should be noted that, the schematic view of the scenario of the commodity recommendation system shown in fig. 1 is only an example, and the commodity recommendation system and scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided by the embodiments of the present application, and those skilled in the art can know that, along with the evolution of the commodity recommendation system and the appearance of a new service scenario, the technical solution provided by the embodiments of the present application is equally applicable to similar technical problems.

In the embodiment of the present application, an electronic device is used as an execution body, and for simplicity and convenience of description, in the subsequent method embodiment, the execution body is omitted, and the commodity recommendation method includes: acquiring shopping monitoring images of users to be recommended; determining a commodity area corresponding to the shopping monitoring image according to the position information of the shooting device associated with the shopping monitoring image; generating a shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image; determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track; and screening and obtaining commodities to be recommended corresponding to the users to be recommended according to the commodity attributes corresponding to the preference areas.

Referring to fig. 2, fig. 2 is a schematic flow chart of a commodity recommendation method according to an embodiment of the present application. It should be noted that although a logical order is depicted in the flowchart, in some cases the steps depicted or described may be performed in a different order than presented herein. The commodity recommendation method specifically may include the following steps 201 to 205, in which:

201. and acquiring shopping monitoring images of the users to be recommended.

The user to be recommended refers to a user of the commodity to be recommended. In order to facilitate understanding of users to be recommended, first, a practical application scenario of the embodiment of the present application is provided: the commodity recommending method provided by the embodiment of the application can be used in the entity shops, after personal information is acquired through user authorization, when user shopping is completed and the automatic checkout counter carries out payment checkout, the commodity recommended to the current payment user can be displayed in the automatic checkout counter, and the current payment user is the user to be recommended. In this application scenario, the electronic device may determine a current payment user through a user account currently logged in by the automated checkout counter, and take the current payment user as a user to be recommended. In order to facilitate understanding of the present method, the following description is based on the above application scenario, but should not be construed as limiting the embodiments of the present application.

The shopping monitoring image is an image shot by an image acquisition device in the physical store after the user is authorized, so that the shopping monitoring image of the user to be recommended is an image containing the user to be recommended shot by the image acquisition device in the physical store after the user to be recommended is authorized. The shopping monitoring image may be an image captured during the shopping process, or may be an image captured during the historical shopping process. For example, when a user to be recommended enters an entity shop, the electronic device may obtain a face image of the user to be recommended by shooting through a camera at an entrance of the entity shop after authorization, and then compare the face image of the user to be recommended with a monitoring image obtained by shooting in the entity shop in real time to determine an image containing the user to be recommended, that is, a shopping monitoring image of the user to be recommended.

In some embodiments, when the electronic device may receive the recommendation trigger request of the user to be recommended, step 201 is executed, and before receiving the recommendation trigger request of the user to be recommended, the electronic device may continuously determine a shopping monitoring image of the user to be recommended from the real-time monitoring image, and store the shopping monitoring image of the user to be recommended in a background database of the physical store, and when step 201 is executed, the electronic device may read the shopping monitoring image of the user to be recommended from the background database. It will be appreciated that the recommended trigger request may refer to a user entering a payment instruction in an automated checkout counter.

In other embodiments, the electronic device may execute step 201 when receiving a recommendation trigger request of the user to be recommended, and read a preset monitoring image from a background database of the physical store, obtain a historical monitoring image in a preset historical time period from the preset monitoring image, and determine a shopping monitoring image of the user to be recommended from the historical monitoring image. The length of the historical time period can be set according to actual scene requirements, for example, the historical time period can be set to 8 hours.

202. And determining a commodity area corresponding to the shopping monitoring image according to the position information of the shooting device associated with the shopping monitoring image.

The photographing device associated with the shopping monitoring image is a photographing device that photographs the shopping monitoring image. The position information of the photographing device includes the installation position of the photographing device.

In the embodiment of the application, the commodity area refers to an area placed in a commodity selling area in a physical store.

The commodity area corresponding to the shopping monitoring image is the commodity area shot in the shopping monitoring image. Because the shooting performance of the shooting device in the physical store is limited, in the embodiment of the application, the commodity area where the shooting device related to the shopping monitoring image is located can be determined according to the position information of the shooting device related to the shopping monitoring image, and the commodity area where the shooting device is located is taken as the commodity area corresponding to the shopping monitoring image.

In some embodiments, the installation location of the photographing device has been previously associated with a pre-divided commodity area within the physical store, and the photographing device is installed in the associated commodity area and is used to photograph the associated commodity area. In this case, the location information of the photographing device may be information of a region associated with the photographing device, and the determined commodity region corresponding to the shopping monitoring image is the commodity region associated with the photographing device.

In other embodiments, where the installation locations of the cameras are not associated with the commodity area within the physical store, a store coordinate system may be previously established within the physical store, and the device coordinates of each camera within the store coordinate system may be previously determined. When executing step 202, the electronic device may acquire the device coordinates of the photographing device associated with the shopping monitoring image, match the device coordinates with the pre-divided commodity areas in the physical store, determine the commodity area where the device coordinates are located, and use the commodity area where the device coordinates are located as the commodity area corresponding to the shopping monitoring image.

The purpose of acquiring the commodity area corresponding to the shopping monitoring image is to determine a target area visited by the user to be recommended, and take information such as the category, price and the like of the commodity in the target area as reference information of the recommended commodity.

203. And generating the shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image.

The acquisition time information of the shopping monitoring image refers to the time information of the shopping monitoring image obtained by shooting by the shooting device. The electronic device can obtain the acquisition time information of the shopping monitoring image according to the time stamp of the shopping monitoring image.

The shopping track may refer to a track of actions of a user accessing each commodity area. According to the acquisition time information of the shopping monitoring image, the time of accessing the commodity area corresponding to the shopping monitoring image by the user to be recommended can be determined, and according to the access time of the user to be recommended to the commodity area corresponding to the shopping monitoring image, the shopping track of the user to be recommended can be generated, wherein the shopping track of the user to be recommended comprises the time sequence of accessing the commodity area corresponding to the shopping monitoring image by the user to be recommended.

The purpose of generating the shopping track is to determine the access priority of the user to be recommended for the commodity area corresponding to the shopping monitoring image, and the higher the access priority of the commodity area is, the higher the preference degree of the user to be recommended for the commodity area is, so that the time sequence information of the commodity area in the shopping track can be used as the reference information of the recommended commodity.

204. And determining a preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track.

In some embodiments, the electronic device may sort the commodity areas corresponding to the shopping monitoring images according to the stay time of the user to be recommended in the commodity areas and the time sequence between the commodity areas in the shopping track, so as to obtain the preference area of the user to be recommended. At this time, the step of determining the preference area of the user to be recommended according to the stay time of the user to be recommended in the commodity area and the shopping track includes:

and (1.1) counting to obtain the stay time of the user to be recommended in the commodity area according to the acquisition time information of the shopping monitoring image and the commodity area corresponding to the shopping monitoring image.

The electronic device may classify the shopping monitoring images according to the commodity areas corresponding to the shopping monitoring images to obtain target monitoring images corresponding to the same commodity areas, and calculate the stay time of the user to be recommended in the commodity areas corresponding to the target monitoring images according to the acquisition time of the monitoring image with the earliest acquisition time in the target monitoring images and the acquisition time of the monitoring image with the latest acquisition time in the target monitoring images.

And (1.2) sequencing the commodity areas according to the stay time in the commodity areas and the sequence information among the commodity areas in the shopping track, so as to obtain the highest-sequencing preference area.

The order information between commodity areas may refer to access time order information between commodity areas.

In some embodiments, the electronic device may sort the commodity areas corresponding to the shopping monitoring images according to the order information between the commodity areas, screen to obtain the commodity area with the top sorting, sort the commodity area with the top sorting again according to the stay time, and use the commodity area with the highest sorting as the favorite area. The electronic device may use the commodity area ordered before the preset order as the commodity area ordered before, and the preset order may be set according to the actual scene requirement, for example, the preset order may be the fourth, that is, the electronic device uses the commodity area ordered before three as the commodity area ordered before.

In other embodiments, the electronic device may screen the product areas with stay time longer than the preset time, and then sort the product areas according to the order information between the product areas in the shopping track, and use the product area with the highest sorting as the favorite area. The sorting method in this embodiment can avoid the influence of the position of the commodity area in the physical store on the sorting, for example, the time sequence of most users accessing the commodity area is related to the distance between the commodity area and the store entrance, the closer the distance between the commodity area and the store entrance is, the earlier the users accessing the commodity area is, if the sorting is not accurate enough by the method in the previous embodiment, the method in this embodiment firstly performs screening according to the stay time, and can effectively avoid the influence of the position of the commodity area in the physical store on the sorting.

Therefore, through the methods of the steps (1.1) - (1.2), the access time sequence among commodity areas and the stay time of the user to be recommended in the commodity areas can be comprehensively considered when the favorite areas are acquired, and the accuracy in determining the favorite areas is improved.

205. And screening and obtaining commodities to be recommended corresponding to the users to be recommended according to the commodity attributes corresponding to the preference areas.

The commodity attribute corresponding to the preference area refers to the commodity attribute of the commodity in the preference area. The commodity attributes may include information such as category, value, sales, etc. of the commodity. In some embodiments, the commodity area may be associated with the commodity in the commodity area in advance, and stored in a background database of the physical store, and when executing step 205, the electronic device may query the background database of the physical store to obtain the commodity associated with the preference area and the commodity attribute corresponding to the preference area.

In some embodiments, the electronic device may screen, according to the commodity attribute corresponding to the preference area, a commodity to be recommended corresponding to the user to be recommended from the commodity sold in the physical store. For example, the electronic device may obtain the commodity attribute corresponding to the preference area, and screen the commodity of the same category from the sold commodities in the physical store according to the commodity category in the commodity attribute, and then select the commodity to be recommended with higher sales volume from the commodity of the same category. It should be noted that the screening method provided in the embodiment of the present application is only exemplary, and should not be construed as limiting the present application.

The method of obtaining a shopping monitoring image by face image matching is described above. However, due to the limitation of the shooting capability of the shooting device, the face features in the monitored image are generally poor, and a better effect is sometimes difficult to achieve by a face image matching method. Accordingly, an embodiment of the present application provides a method for acquiring a shopping monitoring image through physical information, referring to fig. 3, at this time, the step of acquiring a shopping monitoring image of a user to be recommended includes:

301. And receiving a recommendation triggering request, and determining a user to be recommended corresponding to the recommendation triggering request.

The description of the recommended triggering request may refer to the above, and details are not repeated.

302. And acquiring the reference image of the user to be recommended.

The reference image may refer to an image of a user to be recommended, which is obtained by shooting in real time when a recommendation trigger request is received, and is used for comparing with a monitoring image.

The electronic device may obtain the reference image by capturing a whole body image of the user to be recommended through a camera set on the automatic checkout counter after inquiring a payment instruction input to the automatic checkout counter by the user to be recommended, through authorization of the user to be recommended.

303. And matching the user posture information contained in the reference image with the user posture information contained in the monitoring image in the preset database to obtain the shopping monitoring image of the user to be recommended.

The user posture information may refer to posture information of the user. Illustratively, the pifPaf model may be used to process the reference image to obtain the user posture information contained in the reference image.

The pifPaf model is a bottom-up multi-person 2D human body posture estimation method, and human body posture information can be obtained by identifying key points of a human body structure.

The preset database may refer to the background database of the physical store above. When the photographing device in the physical store monitors the physical store in real time, the photographed monitoring image is uploaded to the preset database, and when step 303 is executed, the electronic device may directly read the monitoring image from the preset database. Likewise, the electronic device may read the monitoring image from the preset database according to a preset historical time period, and the description in the historical time period may refer to the above, which is not described in detail.

Likewise, the user posture information of the monitoring image can also be obtained through the pifPaf model, which is not described in detail.

In the embodiment of the application, the similarity between the user posture information contained in the reference image and the user posture information contained in the monitoring image in the preset database can be calculated, and the monitoring image with the similarity larger than the preset similarity threshold value is used as the shopping monitoring image. The specific value of the preset similarity threshold can be set according to actual scene requirements.

In some embodiments, a plurality of storage spaces may be divided in the preset database, where each storage space is used for storing the monitoring images corresponding to the same commodity area and the time is collected in different time periods, and when step 303 is executed, only one monitoring image is obtained from each storage space as a shopping monitoring image, so as to reduce the number of shopping monitoring images and improve the efficiency of commodity recommendation. At this time, the step of matching the user posture information contained in the reference image with the user posture information contained in the monitoring image in the preset database to obtain the shopping monitoring image of the user to be recommended includes:

and (2.1) calculating the similarity between the user posture information contained in the reference image and the user posture information in each preset storage space.

And (2.2) screening to obtain candidate images with the similarity larger than a preset similarity threshold value in each preset storage space, and selecting the candidate image with the highest similarity from each preset storage space as a shopping monitoring image of the user to be recommended.

For convenience of understanding, the configuration of the preset database may be referred to fig. 4, and the preset database 400 in fig. 4 includes a plurality of preset storage spaces 401 and 402 … …, as can be seen from fig. 4, the preset storage space 401 is used for storing the monitoring image corresponding to the commodity area 1 and collected in the period t1, the preset storage space 402 is used for storing the monitoring image corresponding to the commodity area 2, and when the monitoring image … … collected in the period t2 is executed in the step (2.2), candidate images with the similarity greater than the preset similarity threshold value are obtained from each preset storage space, and the candidate image with the highest similarity is used as the shopping monitoring image of the user to be recommended. Therefore, the quantity of shopping monitoring images can be effectively reduced as long as reasonable planning is performed on the time periods t1, t2 … … and the like, behavior data of the user to be recommended in each commodity area and each time period can be obtained, and omission can not occur.

The shopping monitoring images can be obtained by comparing the user posture information through the method of the steps 301-303, the obtained shopping monitoring images are more accurate because the user posture information is richer than the human face information in the monitoring images, and the quantity of the shopping monitoring images can be reduced and the commodity recommending efficiency can be improved through the preset databases constructed through the steps (2.1) -2.2.

In some embodiments, the effect of recommending the commodity to the user to be recommended may be determined first, and when the effect is good, step 302 is executed again, so that the problem that the commodity is recommended to the user to be recommended with poor effect, the scheme of the user to be recommended is caused, and the commodity recommendation efficiency is reduced is avoided. Referring to fig. 5, at this time, before the step of "obtaining the reference image of the user to be recommended", the method further includes:

501. And acquiring historical recommended commodities of the user to be recommended and recommendation feedback information of the historical recommended commodities.

The historical recommended commodities of the user to be recommended refer to commodities which are recommended by the user to be recommended once.

The recommendation feedback information of the historical recommended commodity refers to feedback information of the user to be recommended on the historical recommended commodity after the user to be recommended recommends the historical recommended commodity. The recommendation feedback information of the history recommended goods may include purchasing the history recommended goods, viewing goods details of the history recommended goods, and the like.

The electronic device may query, from a background database of the entity store, historical recommended products of the user to be recommended and recommendation feedback information of the historical recommended products according to a user account number adopted when the user to be recommended logs in the automatic checkout counter.

502. And if the commodity purchase times in the recommendation feedback information are greater than a preset time threshold, executing the step of acquiring the reference image of the user to be recommended.

The preset frequency threshold is used for evaluating the commodity purchase frequency, if the commodity purchase frequency is larger than the preset frequency threshold, the effect of commodity recommendation of the user to be recommended is good, and therefore the step of acquiring the reference image of the user to be recommended can be executed. If the commodity purchase times are smaller than or equal to the preset times threshold, the effect of recommending the commodity to the user to be recommended is poor, and payment settlement can be directly carried out at the moment, so that the commodity is not recommended.

In some embodiments, in order to increase the number of the articles to be recommended, the selection space of the user to be recommended is enlarged, the associated article category associated with the article category in the preference area may be queried, and the articles to be recommended may be selected according to the article category in the preference area and the associated article category. Referring to fig. 6, at this time, the step of "filtering to obtain the to-be-recommended merchandise corresponding to the to-be-recommended user according to the merchandise attribute corresponding to the preference area" includes:

601. and inquiring a preset commodity sales record to obtain a second commodity category associated with the first commodity category corresponding to the preference area.

The commodity sales record comprises historical sales information of commodities in the physical store. For example, the commodity sales record may include historical sales information of commodities in each historical transaction, and may include association relationships between commodity categories of commodities in each transaction, in addition to sales amounts of commodities in each transaction and transaction amounts of each transaction. In the embodiment of the present application, the association may refer to simultaneous sales, and the following is exemplified as an example: for a first commodity with a commodity category of "detergent", if it is associated with a second commodity with a commodity category of "wipe", it is stated that the user purchases the first commodity and also purchases the second commodity at the same time. The electronic equipment can collect shopping records of the user after the user authorization, count and obtain association relations among all commodity categories and historical sales of all commodities to obtain commodity sales records, and store the commodity sales records in a background database of the physical store.

602. And screening and obtaining the commodity to be recommended corresponding to the user to be recommended from preset candidate commodities according to the first commodity category and the second commodity category.

Besides screening according to the commodity category only, information such as sales volume of the commodity can be combined, and detailed description is omitted.

In some embodiments, the candidate good may refer to all of the on-sale goods of the physical store.

In other embodiments, the candidate good may be a portion of the good selected from all of the goods sold. For example, the average purchasing power of the user may be determined based on the big data, and the candidate commodity may be selected based on the average purchasing power and the commodity sales amount of the commodity being sold. At this time, before the step of "inquiring the preset commodity sales record to obtain the second commodity category associated with the first commodity category corresponding to the preference area", the method further includes:

And (3.1) carrying out statistical processing on the historical consumption amount in the commodity sales record to obtain consumption amount distribution information.

The historical consumption amount refers to an amount consumed by the user when shopping in the physical store, which may include a transaction amount corresponding to each transaction.

The consumption amount distribution information contains probability information of the consumption amount, and the probability is higher, so that the probability of the user to conduct transaction with the consumption amount is higher when shopping.

And (3.2) obtaining the target amount with the highest probability in the consumption amount distribution information.

The goal of obtaining the target amount is to determine the average purchasing power of the user, and it is understood that the higher the target amount, the stronger the average purchasing power of the user.

And (3.3) comparing the preset commodity sales amount of the on-sale commodity with the target amount to obtain candidate commodities with commodity sales amount smaller than the target amount.

The commodity sales amount for the commodity on sale may refer to the sales price of the commodity on sale.

Through the steps (3.1) - (3.3), the electronic equipment can screen the on-sale goods according to the average purchase and commodity sales amount of the user, and the recommending efficiency of the goods is improved.

In order to better implement the commodity recommendation method according to the embodiment of the present application, on the basis of the commodity recommendation method, a commodity recommendation device is further provided in the embodiment of the present application, as shown in fig. 7, which is a schematic structural diagram of an embodiment of the commodity recommendation device in the embodiment of the present application, where the commodity recommendation device 700 includes:

an acquisition unit 701, configured to acquire a shopping monitoring image of a user to be recommended;

A first determining unit 702, configured to determine a commodity area corresponding to the shopping monitoring image according to location information of a shooting device associated with the shopping monitoring image;

A generating unit 703, configured to generate a shopping track of the user to be recommended according to the acquisition time information of the shopping monitoring image and a commodity area corresponding to the shopping monitoring image;

a second determining unit 704, configured to determine a preference area of the user to be recommended according to a residence time of the user to be recommended in the commodity area and the shopping track;

And the screening unit 705 is configured to screen and obtain the commodity to be recommended corresponding to the user to be recommended according to the commodity attribute corresponding to the preference area.

In a possible implementation manner of the present application, the second determining unit 704 is further configured to:

In one possible implementation of the present application, the obtaining unit 701 is further configured to:

acquiring a reference image of the user to be recommended;

In one possible implementation manner of the present application, the preset database includes a plurality of preset storage spaces, each of the preset storage spaces is used for storing the monitoring images acquired in different time periods and corresponding to different commodity areas, and the acquiring unit 701 is further configured to:

In a possible implementation of the present application, the screening unit 705 is further configured to:

In the implementation, each unit may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.

The method for recommending the commodity according to any embodiment of the present application can achieve the beneficial effects of the method for recommending the commodity according to any embodiment of the present application, and the detailed description is omitted herein.

In addition, in order to better implement the commodity recommendation method in the embodiment of the present application, the commodity recommendation method is

On the basis, the embodiment of the present application further provides an electronic device, referring to fig. 8, fig. 8 shows a schematic structural diagram of the electronic device according to the embodiment of the present application, and specifically, the electronic device according to the embodiment of the present application includes a processor 801, where the processor 801 is configured to implement steps of the commodity recommendation method in any embodiment when executing a computer program stored in a memory 802; or the processor 801 when executing a computer program stored in the memory 802 performs the functions of the units in the corresponding embodiment as in fig. 7.

By way of example, a computer program may be partitioned into one or more modules/units that are stored in memory 802 and executed by processor 801 to accomplish an embodiment of the application. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions to describe the execution of the computer program in a computer device.

Electronic devices may include, but are not limited to, processor 801, memory 802. It will be appreciated by those skilled in the art that the illustrations are merely examples of electronic devices and are not limiting of electronic devices, and may include more or fewer components than illustrated, or may combine certain components, or different components.

The Processor 801 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center for an electronic device, with various interfaces and lines connecting various parts of the overall electronic device.

The memory 802 may be used to store computer programs and/or modules, and the processor 801 implements various functions of the computer device by running or executing the computer programs and/or modules stored in the memory 802 and invoking data stored in the memory 802. The memory 802 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the electronic device, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the above-described commodity recommendation apparatus, electronic device and corresponding units may refer to the description of the commodity recommendation method in any embodiment, and the detailed description is omitted herein.

Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions or by controlling associated hardware, which may be stored in a storage medium and loaded and executed by a processor.

Therefore, the embodiment of the present application provides a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the commodity recommendation method in any embodiment of the present application, and specific operations may refer to the description of the commodity recommendation method in any embodiment, which is not described herein.

Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.

The steps in the commodity recommendation method in any embodiment of the present application can be executed by the instructions stored in the storage medium, so that the beneficial effects that can be achieved by the commodity recommendation method in any embodiment of the present application can be achieved, and detailed descriptions are omitted here.

The above description of the commodity recommendation method, the device, the storage medium and the electronic equipment provided by the embodiment of the present application applies specific examples to describe the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.

Claims

1. A commodity recommendation method, comprising:

acquiring shopping monitoring images of users to be recommended;

2. The commodity recommending method according to claim 1, wherein said determining a preference area of the user to be recommended based on a stay time of the user to be recommended in the commodity area and the shopping trail includes:

3. The merchandise recommendation method according to claim 1, wherein the acquiring a shopping monitor image of a user to be recommended comprises:

acquiring a reference image of the user to be recommended;

4. The commodity recommending method according to claim 3, wherein said preset database comprises a plurality of preset storage spaces, each of said preset storage spaces being used for storing monitoring images acquired in different time periods and corresponding to different commodity areas,

5. The merchandise recommendation method according to claim 3, wherein before said obtaining the reference image of the user to be recommended, further comprising:

6. The merchandise recommendation method according to any one of claims 1-5, wherein the merchandise attribute comprises a first merchandise category,

7. The method for recommending commodities according to claim 6, wherein before screening the commodities to be recommended corresponding to the user to be recommended from preset candidate commodities according to the first commodity category and the second commodity category, further comprises:

8. A commodity recommendation device, comprising:

9. An electronic device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the merchandise recommendation method according to any one of claims 1 to 7 when the computer program is executed by the processor.

10. A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the merchandise recommendation method of any one of claims 1 to 7.