TWI715151B - Product promotion device based on image recognition and method thererof - Google Patents

Product promotion device based on image recognition and method thererof Download PDF

Info

Publication number
TWI715151B
TWI715151B TW108128932A TW108128932A TWI715151B TW I715151 B TWI715151 B TW I715151B TW 108128932 A TW108128932 A TW 108128932A TW 108128932 A TW108128932 A TW 108128932A TW I715151 B TWI715151 B TW I715151B
Authority
TW
Taiwan
Prior art keywords
accessory
image
information
processing module
camera
Prior art date
Application number
TW108128932A
Other languages
Chinese (zh)
Other versions
TW202107369A (en
Inventor
張芷瑜
Original Assignee
華南商業銀行股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 華南商業銀行股份有限公司 filed Critical 華南商業銀行股份有限公司
Priority to TW108128932A priority Critical patent/TWI715151B/en
Application granted granted Critical
Publication of TWI715151B publication Critical patent/TWI715151B/en
Publication of TW202107369A publication Critical patent/TW202107369A/en

Links

Images

Landscapes

  • Image Analysis (AREA)

Abstract

A product promotion device based on image recognition includes a camera, a database and a processing module. The camera is configured to capture a target image. The database is configured to store a plurality of sets of financial product information and a plurality of sets of accessory information. The processing module is connected to the camera and the database, and configured to obtain a set of biological characteristics. The processing module generates a set of information of potential finance demand according to the set of biological characteristics. The processing module further captures an image of an accessory from the target image, and estimates a value of the accessory according to one or more accessory characteristics in the image of the accessory and a plurality of sets of information of accessory images so as to generate a set of information of estimated income interval. The processing module searches in the database according to the set of information of potential finance demand as well as the set of information of estimated income interval and further outputs one or more of the sets of financial product information.

Description

基於影像辨識的商品推銷輔助裝置及方法Auxiliary device and method for product promotion based on image recognition

本發明係關於一種基於影像辨識的商品推銷輔助裝置，特別是一種應用生物與配件影像辨識的商品推銷輔助裝置。The present invention relates to an auxiliary device for product promotion based on image recognition, in particular to an auxiliary device for product promotion using biological and accessory image recognition.

隨著金融業市場競爭越趨激烈，各家銀行總希望旗下員工可以大力向客戶推銷金融商品，例如***、現金卡、存放款、期貨、基金等，以期擴展自家公司的業務並提升營運狀況。With the increasingly fierce competition in the financial market, banks always hope that their employees can vigorously promote financial products to customers, such as credit cards, cash cards, deposits, futures, funds, etc., in order to expand their company's business and improve operating conditions.

然而，一般來說，當銀行櫃員服務陌生客戶時，往往僅能依賴個人經驗初步判斷該名陌生客戶的收入能力與需求，並無法在短暫的櫃位服務時間內透過多元影像分析正確地掌握該名陌生客戶的屬性，進而導致失去推銷自家金融商品的機會。因此，在此領域中，係需要一種高準度的多元影像分析可以輔助櫃員快速了解客戶屬性並對應地推薦適合的金融商品的裝置。However, generally speaking, when a bank teller serves an unfamiliar customer, he can often only rely on personal experience to make a preliminary judgment on the income ability and needs of the unfamiliar customer, and cannot correctly grasp the income through multiple image analysis during the short counter service time. The attributes of unfamiliar customers, which in turn led to the loss of opportunities to promote their own financial products. Therefore, in this field, there is a need for a high-precision multiple image analysis device that can assist tellers to quickly understand customer attributes and recommend appropriate financial products accordingly.

本發明提出一種基於影像辨識的商品推銷輔助裝置及方法，透過人物的生物特徵影像辨識及其所配帶之配件影像辨識，綜合判斷該名人物的屬性，進而及時地推薦適合的商品。The present invention provides an auxiliary device and method for product promotion based on image recognition. Through the image recognition of a person's biological characteristics and the image recognition of its accessories, the attributes of the person are comprehensively judged, and suitable products can be recommended in time.

依據本發明之一實施例揭露一種基於影像辨識的商品推銷輔助裝置，包含攝像機、資料庫及處理模組。攝像機用以取得目標影像。資料庫用於儲存多個金融商品資訊及多個配件圖像資訊。處理模組連接攝像機與資料庫，處理模組用以從目標影像取得一組生物特徵，且根據該組生物特徵產生潛在金融需求資訊，處理模組更用以從目標影像中擷取配件的影像，且根據配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估該配件的價值，據以產生預估收入區間資訊，處理模組根據潛在金融需求資訊及預估收入區間資訊在資料庫搜尋並輸出該些金融商品資訊中的一或多個金融商品資訊。According to an embodiment of the present invention, a product promotion auxiliary device based on image recognition is disclosed, which includes a camera, a database, and a processing module. The camera is used to obtain the target image. The database is used to store multiple financial product information and multiple accessory image information. The processing module is connected to the camera and the database. The processing module is used to obtain a set of biological characteristics from the target image, and generate potential financial demand information based on the set of biological characteristics, and the processing module is further used to capture the image of the accessory from the target image , And estimate the value of the accessory based on one or more accessory features of the accessory’s image and the accessory image information, and generate estimated income range information based on it, and the processing module based on the potential financial demand information and estimated income The interval information searches the database for and outputs one or more financial product information in the financial product information.

依據本發明之一實施例揭露一種基於影像辨識的商品推銷輔助方法，包含以下步驟：以攝像機取得目標影像；以處理模組從目標影像取得一組生物特徵，且根據該組生物特徵產生一潛在金融需求資訊；以處理模組從目標影像中擷取配件的影像，且根據配件的影像所具有的一或多個配件特徵預估配件的價值，據以產生預估收入區間資訊；以及以處理模組根據潛在金融需求資訊及預估收入區間資訊在資料庫搜尋並輸出多個金融商品資訊中的一或多個金融商品資訊。According to an embodiment of the present invention, a method for assisting product promotion based on image recognition is disclosed, including the following steps: obtaining a target image with a camera; obtaining a set of biological characteristics from the target image by a processing module, and generating a potential based on the set of biological characteristics Financial demand information; use the processing module to extract the image of the accessory from the target image, and estimate the value of the accessory based on one or more accessory features in the image of the accessory, and generate estimated income interval information based on it; and to process The module searches and outputs one or more financial product information among multiple financial product information in the database based on potential financial demand information and estimated income range information.

綜上所述，在本發明提出的基於影像辨識的商品推銷輔助裝置及方法中，係先透過人物的臉部影像辨識取得生物特徵，並根據生物特徵分析客戶的潛在金融需求，再藉由配件影像的辨識取得配件特徵，並根據配件特徵評估客戶所配戴的配件價值判斷客戶的收入區間，進而綜合以上兩者條件來判斷客戶屬性，以利櫃員可及時地在有限的櫃位服務時間內推薦適合該名客戶的金融商品，如此可有效地提升金融商品推薦成功的機率。To sum up, in the image recognition-based merchandising aid device and method proposed in the present invention, the biological characteristics are first obtained through facial image recognition of people, and the potential financial needs of customers are analyzed based on the biological characteristics, and then the accessories The image recognition obtains the characteristics of the accessories, and evaluates the value of the accessories worn by the customer according to the characteristics of the accessories to determine the customer's income range, and then combines the above two conditions to determine the customer's attributes, so that the teller can timely in the limited counter service time Recommend financial products suitable for the customer, which can effectively increase the probability of successful financial product recommendation.

以上之關於本揭露內容之說明及以下之實施方式之說明係用以示範與解釋本發明之精神與原理，並且提供本發明之專利申請範圍更進一步之解釋。The above description of the content of the disclosure and the description of the following embodiments are used to demonstrate and explain the spirit and principle of the present invention, and to provide a further explanation of the patent application scope of the present invention.

以下在實施方式中詳細敘述本發明之詳細特徵以及優點，其內容足以使任何熟習相關技藝者了解本發明之技術內容並據以實施，且根據本說明書所揭露之內容、申請專利範圍及圖式，任何熟習相關技藝者可輕易地理解本發明相關之目的及優點。以下之實施例係進一步詳細說明本發明之觀點，但非以任何觀點限制本發明之範疇。The detailed features and advantages of the present invention are described in detail in the following embodiments, and the content is sufficient to enable anyone familiar with the relevant art to understand the technical content of the present invention and implement it accordingly, and according to the content disclosed in this specification, the scope of patent application and the drawings Anyone who is familiar with the relevant art can easily understand the related purpose and advantages of the present invention. The following examples further illustrate the viewpoints of the present invention in detail, but do not limit the scope of the present invention by any viewpoint.

請參照圖1，圖1係依據本發明之一實施例所繪示的基於影像辨識的商品推銷輔助裝置的功能方塊圖。如圖1所示，商品推銷輔助裝置1包含攝像機10、資料庫11及處理模組12。攝像機10具有攝像主機且外接有一或多個攝像鏡頭(圖中未示)供用以拍攝一人物取得目標影像，且此目標影像會被回傳到攝像機10內的主機，其中所述的目標影像例如係銀行客戶的影像。資料庫11用於儲存多個金融商品資訊。實務上，資料庫11係被建立在本裝置的記憶體或儲存單元中，資料庫11可儲存各種類的金融商品資訊，例如***、現金卡、存放款、期貨、基金、股票、債券等資訊。Please refer to FIG. 1. FIG. 1 is a functional block diagram of a product promotion aid based on image recognition according to an embodiment of the present invention. As shown in FIG. 1, the product promotion auxiliary device 1 includes a camera 10, a database 11 and a processing module 12. The camera 10 has a camera host and is connected with one or more camera lenses (not shown) for shooting a person to obtain a target image, and the target image will be returned to the host in the camera 10, where the target image is, for example It is an image of bank customers. The database 11 is used to store multiple financial product information. In practice, the database 11 is established in the memory or storage unit of the device. The database 11 can store various types of financial product information, such as credit cards, cash cards, deposits, futures, funds, stocks, bonds, etc. .

處理模組12連接攝像機10與資料庫11，處理模組12用以從攝像機10所拍攝的目標影像(例如銀行客戶)中取得一組生物特徵，所述的生物特徵包含客戶的頭髮狀態、皮膚狀態、臉部五官狀態、體態或肢體語言特徵等至少一者。於一實際範例中，當處理模組12收到來自攝像機10的目標影像後，處理模組12內部的影像處理器121會先在這個目標影像中捕捉一人臉影像，並將此目標影像中不屬於該人臉影像的區域視為背景而將其濾除。接著，處理模組12的影像處理器121取得人臉影像中的多個特徵點以得到由該些特徵點所構成的一子影像。The processing module 12 is connected to the camera 10 and the database 11. The processing module 12 is used to obtain a set of biological characteristics from a target image (such as a bank customer) captured by the camera 10. The biological characteristics include the customer's hair condition and skin At least one of state, facial features, body posture or body language characteristics. In a practical example, after the processing module 12 receives the target image from the camera 10, the image processor 121 inside the processing module 12 will first capture a face image in the target image, and remove the target image from the target image. The area belonging to the face image is regarded as the background and filtered out. Then, the image processor 121 of the processing module 12 obtains a plurality of feature points in the face image to obtain a sub-image composed of the feature points.

更具體來說，在人臉影像當中透過該些特徵點連線所圍成的區域便是所述的子影像，其中所述的子影像包含有該名人員的五官之一及其周邊皮膚的影像，其即為該名人員的生物特徵的資訊。此實施例中，處理模組12的影像處理器121可以透過取得人臉影像中的更多的特徵點以得到更多的子影像，例如得到該名人員的所有五官及其對應的周邊皮膚的影像作為該名人員的生物特徵的資訊。More specifically, in the face image, the area enclosed by the connection of these feature points is the sub-image, wherein the sub-image includes one of the facial features of the person and the surrounding skin Image, which is the biometric information of the person. In this embodiment, the image processor 121 of the processing module 12 can obtain more sub-images by obtaining more feature points in the face image, for example, obtaining information about all facial features of the person and their corresponding peripheral skin. The image serves as the biological information of the person.

當處理模組12的運算器122取得來自影像處理器121的所有五官及其對應的周邊皮膚的影像時，便可透過五官的態樣與其周邊的皮膚狀態(即生物特徵)推估該名人員的年齡及/或性別。詳細來說，五官的態樣例如包含眼睛形狀、雙眼間距、眉毛長度與粗細程度、鼻翼寬度、鼻梁長度、雙唇厚度或耳朵形狀等，皮膚狀態例如包含皺紋粗細與數量、毛孔粗細程度與數量或皮膚斑紋的顏色及數量等。When the arithmetic unit 122 of the processing module 12 obtains the images of all the five sense organs and their corresponding peripheral skin from the image processor 121, it can estimate the person through the appearance of the five sense organs and the state of the surrounding skin (ie, biological characteristics) Age and/or gender. In detail, the facial features include the shape of the eyes, the distance between the eyes, the length and thickness of the eyebrows, the width of the nose, the length of the bridge of the nose, the thickness of the lips or the shape of the ears, etc. The state of the skin includes the thickness and number of wrinkles, and the thickness and thickness of the pores. Number or color and number of skin markings, etc.

處理模組12的運算器122進一步根據該組生物特徵對應的年齡及/或性別產生潛在金融需求資訊。在實作上，運算器122可例如是包含處理器、微處理器、控制器、微控制器等具有運算功能的元件。資料庫11的各種類金融商品資訊可例如預先歸類為高風險短期投資類商品(例如股票或期貨)、低風險長期投資類商品(例如定期存款)及一般類商品(例如***或現金卡)。進一步地，處理模組12的運算器122可蒐集並統計分析銀行內部的客戶資訊，據此設定不同性別在各年齡層的客戶傾向需要的金融商品為何，以作為產生潛在金融需求資訊的依據。The arithmetic unit 122 of the processing module 12 further generates potential financial demand information according to the age and/or gender corresponding to the set of biological characteristics. In practice, the arithmetic unit 122 may, for example, include components with arithmetic functions such as a processor, a microprocessor, a controller, and a microcontroller. The information of various types of financial products in the database 11 can be pre-classified, for example, into high-risk short-term investment products (such as stocks or futures), low-risk long-term investment products (such as time deposits), and general products (such as credit cards or cash cards). . Further, the arithmetic unit 122 of the processing module 12 can collect and statistically analyze customer information within the bank, and accordingly set the financial products that customers of different genders and age groups tend to need, as a basis for generating potential financial demand information.

更詳細來說，處理模組12的運算器122可基於生物特徵分析出客戶的性別及/或年齡以決定其潛在金融需求資訊，而實際上不同性別及/或年齡的客戶對於金融產品的需求都可能有所差異，例如男性的投資觀念較女性的投資觀念積極，老年年齡層的人相較於壯年年齡層的人的理財方式更加保守，而青少年年齡層的人可能根本不具有投資理財的想法。於一實施例中，資料庫11儲存一金融需求清單，不同性別及/或年齡的條件下對應不同類別需求資訊，所述的不同類別需求資訊可包含第一類需求資訊、第二類需求資訊及第三類需求資訊，分別對應前述的高風險短期投資類商品、低風險長期投資類商品及一般類商品。處理模組12的運算器122可根據生物特徵分析出客戶的性別及/或年齡，依據此性別及/或年齡在此金融需求清單選取第一類需求資訊、第二類需求資訊及第三類需求資訊其中之一作為潛在金融需求資訊。In more detail, the arithmetic unit 122 of the processing module 12 can analyze the gender and/or age of the customer based on the biological characteristics to determine the potential financial demand information. In fact, the demand for financial products by customers of different gender and/or age There may be differences. For example, men’s investment attitudes are more positive than women’s investment attitudes. Older people have more conservative financial management methods than those of middle-aged people, while teenagers may not have the investment and financial management skills at all. idea. In one embodiment, the database 11 stores a list of financial needs corresponding to different types of demand information under conditions of different genders and/or ages. The different types of demand information may include the first type of demand information and the second type of demand information. And the third type of demand information corresponds to the aforementioned high-risk short-term investment products, low-risk long-term investment products, and general products, respectively. The arithmetic unit 122 of the processing module 12 can analyze the gender and/or age of the customer based on the biological characteristics, and select the first type of demand information, the second type of demand information, and the third type in this financial demand list based on the gender and/or age One of the demand information serves as potential financial demand information.

以上述概念為基準，舉實際範例來說明，若客戶係為女性且年齡約55歲(例如家庭主婦)，評估其投資觀念較為保守，比較能接受低風險且長期投資才能獲利的金融商品，因此處理模組12的運算器122可判斷該客戶的潛在金融需求資訊係為第二類需求資訊。若客戶係為男性且年齡約38歲(例如中小企業主管)，評估其投資觀念較為開放，比較能接受高風險且短期投資就能獲利的金融商品，因此處理模組12的運算器122可判斷該客戶的潛在金融需求資訊係為第一類需求資訊。若客戶係為男性(或女性)且年齡約23歲(例如職場新鮮人)，評估其對投資理財興趣不高或無想法，較適用一般類金融商品(***或現金卡)，因此處理模組12的運算器122可判斷該客戶的潛在金融需求資訊係為第三類需求資訊。處理模組12的運算器122透過分析客戶的性別及年齡可推估客戶可能需要的金融商品種類需求。Taking the above concepts as a benchmark, and taking a practical example to illustrate, if the client is a female and is about 55 years old (such as a housewife), the assessment of her investment concept is more conservative, and it is more acceptable to accept low-risk financial products that can only be profitable by long-term investment. Therefore, the arithmetic unit 122 of the processing module 12 can determine that the customer's potential financial demand information is the second type of demand information. If the client is a male and is about 38 years old (for example, a manager of a small and medium-sized enterprise), his investment concept is more open, and he is more able to accept high-risk financial products that can be profitable from short-term investment. Therefore, the processor 122 of the processing module 12 It is determined that the customer’s potential financial demand information is the first type of demand information. If the client is male (or female) and is about 23 years old (for example, a newcomer in the workplace), assess that he is not interested in investment and financial management or has no ideas, and it is more suitable for general financial products (credit or cash cards), so the processing module The calculator 122 of 12 can determine that the customer's potential financial demand information is the third type of demand information. The arithmetic unit 122 of the processing module 12 can estimate the type of financial products that the customer may need by analyzing the gender and age of the customer.

然而，根據性別及年齡僅能夠推估客戶的金融商品潛在需求係屬於哪個類別需求，尚不足以確定客戶的財務能力與該類別的金融商品的投資單價是否相符。舉例來說，假設根據客戶性別及年齡推測該名客戶適合第二類需求資訊(適合投資高風險產品)，例如股票。然而不同上市公司的股票單價不盡相同，部分上市公司的股票單價可能達上百萬，若是客戶的收入能力無法負擔，推薦此類股票給該名客戶顯然不恰當。因此，有必要進一步評估客戶的收入多寡，才可在對應類別的多個金融商品資訊中挑選並輸出真正合適的金融商品資訊推薦給客戶。However, based on gender and age, it is only possible to estimate which category the customer’s potential demand for financial products belongs to, and it is not yet sufficient to determine whether the customer’s financial capability matches the investment unit price of that category of financial products. For example, suppose that based on the customer’s gender and age, it is assumed that the customer is suitable for the second type of demand information (suitable for investing in high-risk products), such as stocks. However, the unit price of stocks of different listed companies is not the same, and the unit price of some listed companies may reach millions. If the customer's income cannot afford it, it is obviously inappropriate to recommend such stocks to the customer. Therefore, it is necessary to further evaluate the amount of income of the customer, so as to select and output the truly suitable financial product information to recommend to the customer from the multiple financial product information of the corresponding category.

有鑑於此，處理模組12更從目標影像中擷取配件的影像，且處理模組12再進一步根據配件的影像所具有的一或多個配件特徵及資料庫11中的配件圖像資訊預估該配件的價值，據以產生預估收入區間資訊，以評估客戶的收入多寡。接著，處理模組12再根據潛在金融需求資訊及預估收入區間資訊在資料庫11搜尋並輸出該些金融商品資訊中的一或多個金融商品資訊。在實務上，所述的配件例如是客戶身上所配戴或攜帶的手錶、皮夾、領帶/絲巾、項鍊、耳環等物件。於一實施例中，所述的配件特徵包含外緣輪廓、品牌商標或紋路圖樣。更具體來說，外緣輪廓例如是某個特殊外形的項鍊或飾品，品牌商標例如是某個手錶或皮夾上的品牌標誌，而紋路圖樣例如是某個領帶或絲巾上的花紋型態。In view of this, the processing module 12 further captures the image of the accessory from the target image, and the processing module 12 further predicts the accessory image information based on one or more accessory features of the accessory image and the accessory image information in the database 11. Estimate the value of the accessory and generate estimated income range information to evaluate the customer’s income. Then, the processing module 12 searches and outputs one or more financial product information in the financial product information in the database 11 based on the potential financial demand information and the estimated income interval information. In practice, the accessories mentioned are, for example, watches, wallets, ties/scarves, necklaces, earrings, etc. worn or carried by the customer. In one embodiment, the accessory features include outer edge contours, brand trademarks or texture patterns. More specifically, the outer contour is, for example, a necklace or jewelry with a special shape, a brand trademark is, for example, a brand logo on a watch or wallet, and a pattern is a pattern on a tie or silk scarf, for example. .

在一實施例中，處理模組12的影像處理器121會先在這個目標影像中搜尋並捕捉一配件影像，並將此配件影像中不屬於該配件影像的區域視為背景而將其濾除。接著，處理模組12的影像處理器121取得配件影像中的多個特徵點以得到由該些特徵點所構成的一子影像。具體來說，該些特徵點在此配件影像中連線所圍成的區域便是所述的子影像，例如依據該些特徵點連線圍出一矩形區域或其他形狀的區域作為子影像。其中，所述的子影像將包含有此配件的商品標誌及其周邊的特殊花紋圖樣的影像，也就是所述的配件特徵的資訊。In one embodiment, the image processor 121 of the processing module 12 first searches for and captures an accessory image in the target image, and regards the area of the accessory image that does not belong to the accessory image as the background and filters it out . Then, the image processor 121 of the processing module 12 obtains a plurality of feature points in the accessory image to obtain a sub-image composed of the feature points. Specifically, the area enclosed by the connection of the characteristic points in the accessory image is the sub-image, for example, a rectangular area or an area of other shapes is enclosed as the sub-image according to the connection of the characteristic points. Wherein, the sub-image will include the image of the product mark of the accessory and the special pattern around it, that is, the information of the accessory feature.

以手錶作為配件舉例說明，處理模組12的影像處理器121取得手錶影像中的該手錶本體輪廓的多個特徵點，並以該些特徵點圍出一矩形區域或其他形狀的區域作為子影像。在此情況下，所述的子影像包含鑲嵌於該手錶本體錶面上的商品標誌及特殊花紋圖樣。因此，處理模組12的影像處理器121可提取該商品標誌及特殊花紋圖樣作為配件特徵。Taking a watch as an example, the image processor 121 of the processing module 12 obtains a plurality of feature points of the outline of the watch body in the watch image, and uses the feature points to enclose a rectangular area or an area of other shapes as a sub-image . In this case, the sub-image includes a product logo and a special pattern inlaid on the surface of the watch body. Therefore, the image processor 121 of the processing module 12 can extract the product logo and the special pattern as accessory features.

在此實施例中，資料庫11儲存各種類的配件圖像資訊，其包含市場上各大品牌產品上的商標圖案、花紋圖樣或外緣輪廓，該些配件圖像資訊根據其對應的品牌在市面上公認之價值/價格由低至高而預先歸類為初階配件圖像、中階配件圖像與高階配件圖像，以作為配件價值的判斷依據。也就是說，處理模組12的運算器122會將來自影像處理器121的配件特徵逐一比對到初階配件圖像、中階配件圖像與高階配件圖像，以判斷此配件特徵係符合初階、中階或高階配件圖像中的哪一個，據以判斷配件的價值係屬初階、中階或高階等級。接著，處理模組12的運算器122根據判斷的結果選取多個收入區間之一作為預估收入區間資訊。於實作上，可例如設定處理模組12的運算器122使其判斷準則為初階等級對應年收入區間約為六十萬元以下，中階等級對應年收入區間約為六十萬至一百萬元之間，而高階等級對應年收入區間約為一百萬元至數百萬元之間。In this embodiment, the database 11 stores various types of accessory image information, which includes trademark patterns, patterns, or outer contours on major brand products on the market. The accessory image information is based on the corresponding brands. The recognized values/prices on the market are pre-classified into primary accessory images, mid-level accessory images, and high-level accessory images, from low to high, as the basis for judging the value of accessories. That is to say, the arithmetic unit 122 of the processing module 12 compares the accessory features from the image processor 121 to the primary accessory image, the intermediate accessory image, and the high-level accessory image one by one to determine whether the accessory feature matches Which one of the elementary, intermediate, or high-level accessory images is based on determining whether the value of the accessory is elementary, intermediate, or high-level. Then, the arithmetic unit 122 of the processing module 12 selects one of a plurality of income intervals as the estimated income interval information according to the judgment result. In practice, for example, the arithmetic unit 122 of the processing module 12 can be set to make its judgment criterion such that the initial level corresponds to an annual income range of approximately 600,000 yuan or less, and the intermediate level corresponds to an annual income range of approximately 600,000 to one. Between one million yuan, and the corresponding annual income range of high-level grades is about one million yuan to several million yuan.

請進一步參照圖2，圖2係依據本發明之一實施例所繪示的目標影像的示意圖。以下以圖2實施例搭配圖1作為實際範例進行說明，如圖2所示，假設攝像機10透過拍攝而取得之目標影像A0，具有影像處理器121與運算器122的處理模組12透過生物特徵擷取及分析判斷該名客戶的性別為男性且年齡約為35歲到40歲之間，進一步評估其潛在金融需求可能係為第一類需求資訊，如股票或期貨等高風險的金融產品。另外，由於該名客戶配帶某品牌的手錶作為配件，處理模組12進一步根據此配件的影像A1中該只手錶上的品牌商標與預存的配件圖像資訊的比對結果，辨識出該只手錶的品牌商標符合資料庫內11的某一高階配件圖像，故判斷該只手錶的價值相當昂貴(屬高階等級配件)。據此，處理模組12可推斷該名客戶的預估收入區間相當高，大約落在年收入一百萬至數百萬元之間，因此對應將年收入一百萬至數百萬元作為預估收入區間資訊。綜合以上兩者預估條件(即潛在金融需求與預估收入區間資訊)，處理模組12便可在資料庫11中搜尋相對高單價的股票或期貨等高風險金融商品推薦給該名客戶。Please further refer to FIG. 2. FIG. 2 is a schematic diagram of a target image drawn according to an embodiment of the present invention. The embodiment of FIG. 2 and FIG. 1 are used as a practical example for description. As shown in FIG. 2, it is assumed that the target image A0 obtained by the camera 10 through shooting, and the processing module 12 with the image processor 121 and the arithmetic unit 122 transmits the biological features. Extracting and analyzing to determine that the customer's gender is male and the age is between 35 and 40 years old, further assessing its potential financial needs may be the first type of demand information, such as high-risk financial products such as stocks or futures. In addition, since the customer wears a watch of a certain brand as an accessory, the processing module 12 further identifies the watch based on the comparison result of the brand trademark on the watch in the accessory image A1 and the pre-stored accessory image information. The brand trademark of the watch matches a certain high-end accessory image in the database, so it is judged that the value of the watch is quite expensive (a high-end accessory). Based on this, the processing module 12 can infer that the estimated income range of the customer is quite high, about falling between one million and several million yuan in annual income, so the corresponding annual income is one million to several million yuan. Estimated income range information. Combining the above two estimation conditions (ie, potential financial demand and estimated income interval information), the processing module 12 can search the database 11 for high-risk financial products such as stocks or futures with relatively high unit prices and recommend it to the customer.

在實作上，考量到僅以客戶身上單一配件的價值評估其預估收入區間資訊可能不夠精準，因此在本發明之一實施例中，商品推銷輔助裝置1的處理模組12可基於上述相同方法進一步地從目標影像中擷取另一配件的影像，且處理模組12根據此另一配件的影像所具有的一或多個配件特徵，據以預估此另一配件的價值，進一步地處理模組12的運算器122根據另一配件的價值及該配件的價值調整預估收入區間資訊，接著處理模組12的運算器122可根據潛在金融需求資訊以及調整後的預估收入區間資訊，在資料庫11搜尋並輸出適合的金融商品資訊。在實務上，處理模組12調整預估收入區間資訊可以係為調升或調降預估收入區間。以圖2的實施例來說，客戶的另一配件係為皮夾，處理模組12根據此皮夾配件的影像A2所具有的一或多個配件特徵比對資料庫11內的配件圖像資訊，例如皮夾上的紋路圖樣符合某一初階配件圖像，則處理模組12可預估此皮夾僅為平價商品(屬初階等級配件)，其價值並非特別昂貴。因此，處理模組12根據初階平價皮夾的價值及前述高階高檔手錶的價值進行綜合判斷，將原本的預估收入區間調降至約為年收入六十萬至一百萬元之間。也就是說，於此實施例中，處理模組12根據另一配件的價值判斷該名客戶年收並非當初預估的那麼高，因此在預估收入區間調降後，處理模組12將在資料庫11中搜尋中間單價的股票或期貨等高風險金融商品推薦給該名客戶。In practice, considering that only the value of a single accessory on the customer’s estimated income range information may not be accurate enough, in one embodiment of the present invention, the processing module 12 of the product promotion assistance device 1 can be based on the same The method further extracts an image of another accessory from the target image, and the processing module 12 estimates the value of the other accessory based on one or more accessory characteristics of the image of the other accessory, and further The arithmetic unit 122 of the processing module 12 adjusts the estimated income interval information according to the value of another accessory and the value of the accessory, and then the arithmetic unit 122 of the processing module 12 can adjust the estimated income interval information according to the potential financial demand information and the adjusted estimated income interval information , Search and output suitable financial product information in the database 11. In practice, the processing module 12 adjusting the estimated income range information can be an increase or decrease in the estimated income range. Taking the embodiment of FIG. 2 as an example, another accessory of the customer is a wallet, and the processing module 12 compares the accessory image in the database 11 according to one or more accessory features of the image A2 of this wallet accessory Information, for example, if the pattern on the wallet matches a certain elementary accessory image, the processing module 12 can estimate that the wallet is only a cheap commodity (belonging to an elementary level accessory), and its value is not particularly expensive. Therefore, the processing module 12 makes a comprehensive judgment based on the value of the primary parity wallet and the value of the aforementioned high-end high-end watches, and reduces the original estimated income range to approximately between 600,000 and 1 million yuan per year. That is, in this embodiment, the processing module 12 judges that the customer’s annual income is not as high as originally estimated based on the value of another accessory. Therefore, after the estimated income range is reduced, the processing module 12 will The database 11 searches for high-risk financial products such as stocks or futures with an intermediate unit price and recommends it to the customer.

請參照圖1，如圖1所示的商品推銷輔助裝置1更包含叫號機13，其電性連接處理模組12。在此實施例中，叫號機13電性連接各個櫃台端裝置21~23，供各銀行櫃員使用以通知下一位客戶到指定櫃位辦理業務。叫號器13用以在被觸發時產生對應一櫃台端裝置的服務序號，處理模組12的運算器122可依據此服務序號將一或多個金融商品資訊傳送到對應的櫃台端裝置。以圖1實施例來說，各個櫃台端裝置21、22及23分別裝設攝像鏡頭連接到攝像機並且各個櫃台端裝置21、22及23分配有服務序號001、002及003。在一實施情境中，假設櫃台端裝置22的櫃員欲服務下一名客戶，便可操作櫃台端裝置22發送一觸發訊號到叫號器13，此時叫號器13執行叫號，且產生對應的服務序號002並將此服務序號002傳送到處理模組12的運算器122。Please refer to FIG. 1, the product promotion auxiliary device 1 shown in FIG. 1 further includes a number calling machine 13, which is electrically connected to the processing module 12. In this embodiment, the number calling machine 13 is electrically connected to each counter-end device 21 to 23 for use by the tellers of each bank to notify the next customer to go to the designated counter to handle business. The caller 13 is used to generate a service serial number corresponding to a counter-end device when triggered, and the arithmetic unit 122 of the processing module 12 can transmit one or more financial product information to the corresponding counter-end device according to the service serial number. Taking the embodiment of FIG. 1 as an example, each counter-end device 21, 22, and 23 are respectively equipped with a camera lens connected to the camera, and each counter-end device 21, 22, and 23 are assigned service numbers 001, 002, and 003. In an implementation scenario, assuming that the teller of the counter-end device 22 wants to serve the next customer, he can operate the counter-end device 22 to send a trigger signal to the caller 13, and then the caller 13 executes the call and generates a corresponding The service serial number 002 is sent to the arithmetic unit 122 of the processing module 12.

在叫號器13執行叫號之後，該名客戶便會移動到對應的櫃台端裝置22前，由攝像機10透過對應的攝像鏡頭取得該名客戶的影像作為目標影像，且處理模組12的運算器122根據此目標影像透過前述生物分析及配件價值評估判斷客戶的潛在金融需求及預估收入區間，綜合兩者的預估條件，在資料庫中搜尋到一或多個合適金融商品資訊進行推銷。接著，處理模組12的運算器122可依據此服務序號002將所建議推銷的一或多個金融商品資訊傳送到對應的櫃台端裝置22。因此，櫃員可即時地透過櫃台端裝置22的螢幕所顯示的該些金融商品資訊，向該名客戶進行推銷，如此一來可以大大提升推銷成功的機率。After the caller 13 executes the call, the customer will move to the corresponding counter-end device 22, and the camera 10 will obtain the image of the customer through the corresponding camera lens as the target image, and process the calculation of the module 12 Based on the target image, the device 122 judges the customer’s potential financial needs and estimated income range through the aforementioned biological analysis and accessory value evaluation, and combines the estimated conditions of the two to search for one or more suitable financial product information in the database for promotion . Then, the arithmetic unit 122 of the processing module 12 can transmit the information of one or more financial products recommended to be promoted to the corresponding counter device 22 according to the service serial number 002. Therefore, the teller can instantly promote to the customer through the financial product information displayed on the screen of the counter device 22, which can greatly increase the probability of successful sales.

請進一步參照圖3，圖3係依據本發明之一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。此方法適用於圖1的商品推銷輔助裝置。如圖3所示，在步驟S1中，以攝像機10取得目標影像。在步驟S2中，以處理模組12從目標影像取得一組生物特徵，且根據該組生物特徵產生潛在金融需求資訊。在步驟S3，以處理模組12從目標影像中擷取配件的影像，且根據配件的影像所具有的一或多個配件特徵及多個配件圖像資訊預估配件的價值，據以產生預估收入區間資訊。在步驟S4中，以處理模組12根據潛在金融需求資訊及預估收入區間資訊在資料庫搜尋並輸出多個金融商品資訊中的一或多個金融商品資訊。Please further refer to FIG. 3, which is a flowchart of a method for assisting product promotion based on image recognition according to an embodiment of the present invention. This method is suitable for the merchandise promotion aid of Figure 1. As shown in FIG. 3, in step S1, the camera 10 obtains a target image. In step S2, the processing module 12 obtains a set of biological characteristics from the target image, and generates potential financial demand information based on the set of biological characteristics. In step S3, the processing module 12 captures the image of the accessory from the target image, and estimates the value of the accessory according to the one or more accessory features and multiple accessory image information of the accessory image, and then generates a prediction Estimate income range information. In step S4, the processing module 12 searches the database according to the potential financial demand information and the estimated income interval information and outputs one or more financial product information among the multiple financial product information.

請參照圖4，圖4係依據本發明之另一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。圖4實施例的步驟S11~S13及S16相仿於圖3實施例的步驟S1~S3及S4，惟差異在於圖4實施例更包含步驟S14及S15。在步驟S14中，以處理模組12從目標影像中擷取另一配件的影像，且根據此另一配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估此另一配件的價值。在步驟S15中，以處理模組12依據配件的價值及此另一配件的價值調整預估收入區間資訊。Please refer to FIG. 4. FIG. 4 is a flowchart of a method for assisting product promotion based on image recognition according to another embodiment of the present invention. Steps S11 to S13 and S16 in the embodiment in FIG. 4 are similar to steps S1 to S3 and S4 in the embodiment in FIG. 3, but the difference is that the embodiment in FIG. 4 further includes steps S14 and S15. In step S14, the processing module 12 captures an image of another accessory from the target image, and predicts the other accessory based on one or more accessory features of the image of the other accessory and the accessory image information. The value of an accessory. In step S15, the processing module 12 adjusts the estimated income interval information according to the value of the accessory and the value of this other accessory.

請參照圖5，圖5係依據本發明之另一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。圖5實施例的步驟S111~S114相仿於圖3實施例的步驟S1~S4。惟差異在於圖5更包含在以攝像機10取得目標影像之前，在步驟S110中，當叫號器13被觸發時，以叫號器13產生並傳送服務序號至處理模組12。在處理模組12輸出該一或多個金融商品資訊後，在步驟S115中，以處理模組12依據服務序號將所輸出的一或多個金融商品資訊傳送到服務序號所對應的櫃台端裝置。Please refer to FIG. 5. FIG. 5 is a flowchart of a method for assisting product promotion based on image recognition according to another embodiment of the present invention. Steps S111 to S114 in the embodiment in FIG. 5 are similar to steps S1 to S4 in the embodiment in FIG. 3. The only difference is that FIG. 5 further includes that before the camera 10 obtains the target image, in step S110, when the caller 13 is triggered, the caller 13 generates and transmits the service serial number to the processing module 12. After the processing module 12 outputs the one or more financial product information, in step S115, the processing module 12 transmits the output one or more financial product information to the counter-side device corresponding to the service serial number according to the service serial number. .

在一實施例中，以處理模組12根據配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估該配件的價值，據以產生預估收入區間資訊包含以處理模組12取得配件的影像的外緣輪廓、品牌商標或紋路圖樣作為此一或多個配件特徵且將每個配件特徵個別比對至該些配件圖像資訊，以選取多個收入區間之一作為預估收入區間資訊。In one embodiment, the processing module 12 estimates the value of the accessory according to one or more accessory features of the accessory image and the accessory image information, and generates estimated income interval information based on the processing model. Group 12 obtains the outer edge contour, brand trademark or texture pattern of the image of the accessory as the one or more accessory features and compares each accessory feature to the accessory image information individually to select one of the multiple income ranges as Estimated income range information.

綜上所述，在本發明提出的基於影像辨識的商品推銷輔助裝置及方法中，係先透過人物的臉部影像辨識取得生物特徵，並根據生物特徵分析客戶的潛在金融需求，再藉由配件影像的辨識取得配件特徵，並根據配件特徵評估客戶所配戴的配件價值判斷客戶的收入區間，進而綜合以上兩者條件來判斷客戶屬性，以幫助櫃員在有限的櫃位服務時間內推薦適合該名客戶的金融商品，如此可有效地提升金融商品推薦成功的機率。To sum up, in the image recognition-based merchandising aid device and method proposed in the present invention, the biological characteristics are first obtained through facial image recognition of people, and the potential financial needs of customers are analyzed based on the biological characteristics, and then the accessories The image recognition obtains the characteristics of the accessories, and evaluates the value of the accessories worn by the customer according to the characteristics of the accessories to determine the customer’s income range, and then combines the above two conditions to determine the customer’s attributes, so as to help tellers recommend suitable for the counter within the limited counter service time. This can effectively increase the probability of successful financial product recommendation.

雖然本發明以前述之實施例揭露如上，然其並非用以限定本發明。在不脫離本發明之精神和範圍內，所為之更動與潤飾，均屬本發明之專利保護範圍。關於本發明所界定之保護範圍請參考所附之申請專利範圍。Although the present invention is disclosed in the foregoing embodiments, it is not intended to limit the present invention. All changes and modifications made without departing from the spirit and scope of the present invention fall within the scope of patent protection of the present invention. For the scope of protection defined by the present invention, please refer to the attached patent scope.

1:商品推銷輔助裝置 10:攝像機 11:資料庫 12:處理模組 121:影像處理器 122:運算器 13:叫號器 21~23:櫃台端裝置 A0:目標影像 A1、A2:配件的影像 1: Auxiliary device for product promotion 10: Camera 11: Database 12: Processing module 121: image processor 122: Calculator 13: Caller 21~23: Counter device A0: Target image A1, A2: Images of accessories

圖1係依據本發明之一實施例所繪示的基於影像辨識的商品推銷輔助裝置的功能方塊圖。 圖2係依據本發明之一實施例所繪示的目標影像的示意圖。 圖3係依據本發明之一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。 圖4係依據本發明之另一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。 圖5係依據本發明之另一實施例所繪示的基於影像辨識的商品推銷輔助方法的方法流程圖。 FIG. 1 is a functional block diagram of an auxiliary device for promoting merchandise based on image recognition according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a target image drawn according to an embodiment of the invention. FIG. 3 is a flowchart of a method for assisting product promotion based on image recognition according to an embodiment of the present invention. FIG. 4 is a flowchart of a method for assisting product promotion based on image recognition according to another embodiment of the present invention. FIG. 5 is a flowchart of a method for assisting merchandise promotion based on image recognition according to another embodiment of the present invention.

1:商品推銷輔助裝置 1: Auxiliary device for product promotion

10:攝像機 10: Camera

11:資料庫 11: Database

12:處理模組 12: Processing module

121:影像處理器 121: image processor

122:運算器 122: Calculator

13:叫號器 13: Caller

21~23:櫃台端裝置 21~23: Counter device

Claims (6)

一種基於影像辨識的商品推銷輔助裝置，包含：一攝像機，用以取得一目標影像，其中該攝像機具有一攝像主機且外接有一或多個攝像鏡頭；一資料庫，用於儲存多個金融商品資訊及多個配件圖像資訊；一處理模組，連接該攝像機與該資料庫，該處理模組用以從該目標影像取得一組生物特徵，且根據該組生物特徵產生一潛在金融需求資訊，該處理模組更用以從該目標影像中擷取一配件的影像，且根據該配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估該配件的價值，據以產生一預估收入區間資訊，該處理模組根據該潛在金融需求資訊及該預估收入區間資訊在該資料庫搜尋並輸出該些金融商品資訊中的一或多個金融商品資訊；以及一叫號器，電性連接該處理模組，該叫號器用以在被觸發時產生對應一櫃台端裝置的一服務序號，該處理模組依據該服務序號將該一或多個金融商品資訊傳送到對應的該櫃台端裝置。 An auxiliary device for product promotion based on image recognition, comprising: a camera for obtaining a target image, wherein the camera has a camera host and one or more camera lenses externally connected; a database for storing multiple financial product information And a plurality of accessory image information; a processing module connected to the camera and the database, the processing module is used to obtain a set of biological characteristics from the target image, and generate a potential financial demand information according to the set of biological characteristics, The processing module is further used to extract an image of an accessory from the target image, and estimate the value of the accessory according to one or more accessory characteristics of the image of the accessory and the accessory image information. Generate an estimated income interval information, the processing module searches the database based on the potential financial demand information and the estimated income interval information and outputs one or more financial product information among the financial product information; and The number device is electrically connected to the processing module, the number calling device is used to generate a service serial number corresponding to a counter-side device when triggered, and the processing module transmits the one or more financial product information to The corresponding counter-side device. 如請求項1所述的基於影像辨識的商品推銷輔助裝置，其中該處理模組更從該目標影像中擷取另一配件的影像且根據該另一配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估該另一配件的價值，且該處理模組根據該另一配件的價值及該配件的價值，以調整該預估收入區間資訊。 The product promotion assistance device based on image recognition according to claim 1, wherein the processing module further extracts an image of another accessory from the target image and based on one or more accessories of the image of the other accessory The feature and the accessory image information estimate the value of the other accessory, and the processing module adjusts the estimated income interval information according to the value of the other accessory and the value of the accessory. 如請求項1所述的基於影像辨識的商品推銷輔助裝置，其中該一或多個配件特徵包含一外緣輪廓、一品牌商標或一紋路圖樣。 The product promotion assistance device based on image recognition according to claim 1, wherein the one or more accessory features include an outer contour, a brand trademark, or a texture pattern. 一種基於影像辨識的商品推銷輔助方法，包含：當一叫號器被觸發時，以該叫號器產生並傳送一服務序號至一處理模組；以一攝像機取得一目標影像，其中該攝像機具有一攝像主機且外接有一或多個攝像鏡頭；以該處理模組從該目標影像取得一組生物特徵，且根據該組生物特徵產生一潛在金融需求資訊；以該處理模組從該目標影像中擷取一配件的影像，且根據該配件的影像所具有的一或多個配件特徵及多個配件圖像資訊預估該配件的價值，據以產生一預估收入區間資訊；以該處理模組根據該潛在金融需求資訊及該預估收入區間資訊在一資料庫搜尋並輸出多個金融商品資訊中的一或多個金融商品資訊；以及以該處理模組依據該服務序號將所輸出的該一或多個金融商品資訊傳送到該服務序號所對應的一櫃台端裝置。 An auxiliary method for product promotion based on image recognition includes: when a caller is triggered, the caller generates and transmits a service serial number to a processing module; a camera obtains a target image, wherein the camera has A camera host is connected with one or more camera lenses; the processing module is used to obtain a set of biological characteristics from the target image, and a potential financial demand information is generated according to the set of biological characteristics; the processing module is used to obtain information from the target image Capture an image of an accessory, and estimate the value of the accessory based on one or more accessory features and multiple accessory image information in the image of the accessory, and generate an estimated income interval information based on the processing model; The group searches for and outputs one or more financial product information among multiple financial product information in a database based on the potential financial demand information and the estimated income interval information; and uses the processing module to output the information based on the service serial number The one or more financial product information is transmitted to a counter terminal device corresponding to the service serial number. 如請求項4所述的基於影像辨識的商品推銷輔助方法，更包含：以該處理模組從該目標影像中擷取另一配件的影像，且根據該另一配件的影像所具有的一或多個配件特徵及該些配件圖像資訊預估該另一配件的價值；以及以該處理模組依據該配件的價值及該另一配件的價值調整該預估收入區間資訊。 The auxiliary method for product promotion based on image recognition as described in claim 4, further comprising: using the processing module to extract an image of another accessory from the target image, and according to one or more of the image of the other accessory A plurality of accessory features and the accessory image information estimate the value of the other accessory; and the processing module is used to adjust the estimated income interval information according to the value of the accessory and the value of the other accessory. 如請求項4所述的基於影像辨識的商品推銷輔助方法，其中以該處理模組根據該配件的影像所具有的該一或多個配件特徵及該些配件圖像資訊預估該配件的價值，據以產生該預估收入區間資訊包含：以該處理模組取得該配件的影像的一外緣輪廓、一品牌商標或一紋路圖樣作為該一或多個配件特徵且將每一該配件特徵個別比對至該些配件圖像資訊，以選取多個收入區間之一作為該預估收入區間資訊。 The auxiliary method for product promotion based on image recognition according to claim 4, wherein the processing module is used to estimate the value of the accessory based on the one or more accessory characteristics of the accessory image and the accessory image information , According to which the estimated income interval information is generated includes: using the processing module to obtain an outer contour, a brand trademark or a pattern pattern of the image of the accessory as the one or more accessory features and assigning each accessory feature Individually compare the accessory image information to select one of multiple income ranges as the estimated income range information.
TW108128932A 2019-08-14 2019-08-14 Product promotion device based on image recognition and method thererof TWI715151B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW108128932A TWI715151B (en) 2019-08-14 2019-08-14 Product promotion device based on image recognition and method thererof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW108128932A TWI715151B (en) 2019-08-14 2019-08-14 Product promotion device based on image recognition and method thererof

Publications (2)

Publication Number Publication Date
TWI715151B true TWI715151B (en) 2021-01-01
TW202107369A TW202107369A (en) 2021-02-16

Family

ID=75237251

Family Applications (1)

Application Number Title Priority Date Filing Date
TW108128932A TWI715151B (en) 2019-08-14 2019-08-14 Product promotion device based on image recognition and method thererof

Country Status (1)

Country Link
TW (1) TWI715151B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWM443899U (en) * 2012-02-29 2012-12-21 Bethel Comp Consultant Co Ltd An intelligent point-of-sales system with active identification of customer group
CN104036404A (en) * 2013-03-06 2014-09-10 承玉琴 Interactive advertising method and equipment
CN108073671A (en) * 2017-04-12 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus and electronic equipment
TWM575154U (en) * 2018-07-03 2019-03-01 中光電智能雲服股份有限公司 Product recommendation display system
CN109447714A (en) * 2018-11-06 2019-03-08 北京极睿科技有限责任公司 Advertisement recommended method, device, equipment, system and server

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWM443899U (en) * 2012-02-29 2012-12-21 Bethel Comp Consultant Co Ltd An intelligent point-of-sales system with active identification of customer group
CN104036404A (en) * 2013-03-06 2014-09-10 承玉琴 Interactive advertising method and equipment
CN108073671A (en) * 2017-04-12 2018-05-25 北京市商汤科技开发有限公司 Business object recommends method, apparatus and electronic equipment
TWM575154U (en) * 2018-07-03 2019-03-01 中光電智能雲服股份有限公司 Product recommendation display system
CN109447714A (en) * 2018-11-06 2019-03-08 北京极睿科技有限责任公司 Advertisement recommended method, device, equipment, system and server

Also Published As

Publication number Publication date
TW202107369A (en) 2021-02-16

Similar Documents

Publication Publication Date Title
JP5650499B2 (en) Computer-implemented method for collecting consumer purchase preferences for goods
US9460342B1 (en) Determining body measurements
JP2019102068A (en) Recommendation system based on user's physical features
EP3182362A1 (en) Method and sytem for evaluating fitness between eyeglasses wearer and eyeglasses worn thereby
CN109993595A (en) Method, system and the equipment of personalized recommendation goods and services
US11157988B2 (en) System and method for fashion recommendations
CN108876430A (en) A kind of advertisement sending method based on crowd characteristic, electronic equipment and storage medium
JP2022099130A (en) Determination method, determination apparatus, and determination program
WO2020168134A1 (en) Systems and methods for accurate image characteristic detection
US11544768B2 (en) System and method for fashion recommendations
US20150199571A1 (en) Pos terminal apparatus and customer information acquisition method
WO2022142899A1 (en) Store sales data analysis method, apparatus, electronic device, and storage medium
CN111311379A (en) Information interaction method and device for intelligent goods shelf, intelligent goods shelf and storage medium
TWM592541U (en) Image recognition system
TWI715151B (en) Product promotion device based on image recognition and method thererof
CN113033413A (en) Glasses recommendation method and device, storage medium and terminal
TWI745089B (en) Product promotion device based on image of accessory and method thererof
TWM591213U (en) Auxiliary device for merchandising based on image recognition
US20220343393A1 (en) System and Method for Fashion Recommendations
CN115601877A (en) Automatic vending machine identification system based on image processing and identification method thereof
CN106462726A (en) Frame recognition system and method
CN116226817A (en) Identity recognition method, identity recognition device, computer equipment and storage medium
KR20220166063A (en) Method and apparatus for identifying genuine article of seized movable property, and electronic auction system using the same
Lin et al. Face detection based on the use of eyes tracking
KR20210140917A (en) Method for Supporting Custom Glasses Purchase Using Application Program, and Managing Server Used Therein