WO2021042541A1 - Shopping guide method and apparatus in new retail model, device and storage medium - Google Patents

Shopping guide method and apparatus in new retail model, device and storage medium Download PDF

Info

Publication number
WO2021042541A1
WO2021042541A1 PCT/CN2019/117714 CN2019117714W WO2021042541A1 WO 2021042541 A1 WO2021042541 A1 WO 2021042541A1 CN 2019117714 W CN2019117714 W CN 2019117714W WO 2021042541 A1 WO2021042541 A1 WO 2021042541A1
Authority
WO
WIPO (PCT)
Prior art keywords
customer
information
customer information
physical store
terminal
Prior art date
Application number
PCT/CN2019/117714
Other languages
French (fr)
Chinese (zh)
Inventor
乐志能
Original Assignee
平安科技(深圳)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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2021042541A1 publication Critical patent/WO2021042541A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0281Customer communication at a business location, e.g. providing product or service information, consulting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0261Targeted advertisements based on user location
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for shopping guides in a new retail mode.
  • the current sales method in a physical store is generally that the user enters the physical store, and then the sales consultant judges whether the user is a potential buying user based on experience, and if it is judged to be a potential buying customer, follow up the sales guide.
  • This method relies on the empirical judgment of sales consultants, and requires a high level of ability of sales consultants. When there are many customers, the number of sales consultants is limited, which leads to the loss of potential consumer customers because they are not received by sales consultants, or the sales consultants are just new. At the beginning, if you don't understand any hobbies and characteristics of customers, you need to have too many conversations with customers, which arouses customers' disgust and leads to a lower sales success rate.
  • the main purpose of the present invention is to provide a method, device, equipment and storage medium for shopping guide under the new retail mode, aiming to solve the technical problem of low sales success rate in the prior art.
  • the present invention provides a shopping guide method for commodities under a new retail mode, including:
  • the present invention also provides a commodity shopping guide device under the new retail mode, and the commodity shopping guide device under the new retail mode includes:
  • the location judgment module is used to obtain the location information reported by the customer terminal, and determine whether the customer terminal is located in the target physical store according to the location information;
  • a customer information acquisition module configured to acquire customer information reported by the customer terminal if the customer terminal is located in a target physical store
  • the calculation module is used to calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results;
  • the detection module is configured to determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
  • a prediction module configured to input the customer information into a preset prediction model if the maximum similarity calculation result is less than a preset threshold, to obtain a product recommendation result for the customer information;
  • the push module is configured to obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  • the present invention also provides a computer device, the computer device including a memory and a processor;
  • the memory is used to store a computer program
  • the processor is configured to execute the computer program and, when executing the computer program, implement the above-mentioned method for shopping guide under the new retail mode.
  • the present invention also provides a computer-readable storage medium on which is stored a commodity shopping guide program under the new retail mode, and the commodity shopping guide program under the new retail mode is processed When the device is executed, the steps of the commodity shopping guide method under the new retail mode as described above are realized.
  • the product that the customer is interested in is determined according to the customer's information, and the sales staff in the target physical store are notified, so that the sales staff can provide customers with more accurate shopping guide services and increase sales. Efficiency and success rate.
  • FIG. 1 is a schematic diagram of a computer device structure of a hardware operating environment involved in a solution of an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of an embodiment of a merchandise shopping guide method under the new retail mode of the present invention
  • FIG. 3 is a schematic diagram of a scene of an embodiment of a method for shopping guide in a new retail mode according to the present invention
  • FIG. 4 is a schematic diagram of the detailed process of determining that the customer terminal is located in the target physical store in FIG. 2;
  • FIG. 5 is a detailed flowchart of the steps of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store in FIG. 2;
  • Fig. 6 is a schematic diagram of functional modules of an embodiment of a merchandise shopping guide device in a new retail mode of the present invention.
  • Fig. 1 is a schematic structural diagram of a computer device in a hardware operating environment involved in a solution of an embodiment of the present invention.
  • the computer device in the embodiment of the present invention may be a PC, or a terminal device with data processing capabilities, such as a smart phone or a server.
  • the computer device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a magnetic disk memory.
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
  • FIG. 1 does not constitute a limitation on the computer device, and may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements.
  • a memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a network operation control application program.
  • the network interface 1004 is mainly used to connect to the back-end server and communicate with the back-end server;
  • the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client; and the processing
  • the device 1001 can be used to call a computer program stored in the memory 1005 and perform the following operations:
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • the similarity between the customer information and the transaction customer information is calculated by the cosine similarity formula, and multiple similarity calculation results are obtained.
  • the cosine similarity formula is as follows:
  • n(A) represents the number of types of information contained in the customer information
  • n(B) represents the number of types of information contained in the customer information that has been traded
  • n(A ⁇ B) represents that the customer information is the same as that of the customer information that has been traded
  • the amount of information, K is the similarity calculation result.
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • the historical transaction records including the product name and the transaction customer information corresponding to the product name;
  • the prediction function formula is as follows:
  • ⁇ i is the weight value of the transaction customer information i
  • x i is the characteristic value corresponding to the transaction customer information i
  • ⁇ T [ ⁇ 1 , ⁇ 2 ,..., ⁇ n ]
  • x [x 1 ,x 2 ,...,x n ]
  • e is a natural constant.
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • a target output value greater than or equal to a preset probability value is selected, and a product recommendation result for the customer information is obtained based on the target output value.
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • If the product recommendation result exists in the product list execute the acquisition of the face image reported by the customer terminal, and send the face image and the product recommendation result to the target physical store. The steps of the point-of-sale.
  • the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
  • FIG. 2 is a schematic flowchart of an embodiment of a merchandise shopping guide method under the new retail mode of the present invention.
  • the shopping guide methods under the new retail model include:
  • Step S10 Obtain the location information reported by the customer terminal, and determine whether the customer terminal is located in the target physical store according to the location information.
  • the message pushing method is applied to a computer device, and the computer device may specifically be a server.
  • the location information of multiple physical stores is stored on the server.
  • the location information of physical store 1 to physical store 5 are W1, W2, W3, W4, and W5, respectively.
  • the distance between the location information W reported by the customer terminal and W1 to W5 is calculated respectively, and five calculation results are obtained, which are respectively L1 to L5.
  • Step S20 If the customer terminal is located in the target physical store, acquire customer information reported by the customer terminal.
  • the customer needs to pre-register when using the client installed in the customer terminal.
  • some personal information needs to be filled in, such as gender, age, occupation, income status, health status, family medical history, etc. (The type of personal information can be expanded or reduced according to actual needs, and there is no restriction here), and then the customer terminal reports the personal information to the server, and the server stores the personal information in association with the terminal identification of the customer terminal.
  • the personal information that is, customer information
  • the terminal identification of the customer terminal can be obtained from the stored data.
  • Step S30 Calculate the similarity between the customer information and each transaction customer information stored in the historical transaction record to obtain multiple similarity calculation results.
  • step S30 includes:
  • n(A) represents the number of types of information contained in the customer information
  • n(B) represents the number of types of information contained in the customer information that has been traded
  • n(A ⁇ B) represents that the customer information is the same as that of the customer information that has been traded
  • the amount of information, K is the similarity calculation result.
  • Transaction details include: product name, customer information.
  • Table 1 is a data table that stores historical transaction records.
  • Transaction customer information 1 Product name 1
  • Transaction customer information 2 Product name 2
  • Transaction customer information 3 Product name 3
  • Transaction customer information 4 Product name 4
  • the cosine similarity formula is as follows:
  • n(A) represents the type and quantity of information contained in the customer information. If the customer information includes gender, age, occupation, income status, health status, and family medical history, then n(A) is 6; n(B) represents The type and quantity of the information contained in the transaction customer information. If the transaction customer information includes gender, age, occupation, income status, health status, and family medical history, then n(B) is 6; n(A ⁇ B) represents the customer information and The quantity of the same information in the transaction customer information; K represents the calculation result of the similarity between the customer information and the transaction customer information.
  • Step S40 Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold.
  • the transaction customer information includes transaction customer information 1 to transaction customer information 4
  • four similarity calculation results are calculated, namely K1 to K4, and the largest value is selected from K1 to K4
  • K2 it is determined whether K2 is greater than or equal to the preset threshold.
  • the preset threshold is set according to actual needs, for example, set to 0.8.
  • K2 is greater than or equal to the preset threshold, it means that the personal information of the customer is very similar to that of customer 2 who has already traded.
  • the goods purchased by customer 2 who have already traded are likely to be goods of interest to the customer. Therefore, It is possible to directly use the product purchased by the customer 2 who has already traded as the product to be recommended. For example, if the products purchased by customer 2 include: product 1 and product 3, the product recommendation result is product 1 and product 3.
  • Step S50 If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information.
  • the maximum similarity calculation result is less than the preset threshold, it means that the current customer information is not the same as the stored transactional customer information, and it is impossible to predict the products of interest to the current customer information based on historical transaction records.
  • the customer information is input into the predictive model, and the result of product recommendation based on the customer information is obtained.
  • the characteristic values corresponding to the customer information are input into the three prediction models, and three probability values P1, P2, and P3 are obtained.
  • a preset probability value for example, 0.85
  • Step S60 Obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  • the face image reported by the customer terminal is further obtained, and the face image and the product recommendation result are generated to the sales terminal corresponding to the target physical store, so that the sales staff of the sales terminal can follow the person
  • the face image finds the customer, and conducts a shopping guide for the customer according to the product recommendation result.
  • a customer registers to use a customer terminal, he will be required to upload a face image.
  • the customer terminal receives the face image, it will report the face image to the server, and the server will associate the face image with the terminal identifier of the customer terminal. Associated storage.
  • FIG. 3 is a schematic diagram of a scene of an embodiment of a method for shopping guide of goods in a new retail mode of the present invention.
  • the server establishes a communication connection with the customer terminal and the sales terminal respectively.
  • the server determines the target physical store where it is located according to the location information reported by the customer terminal, and determines the product recommendation result according to the customer information corresponding to the customer terminal, so that the product
  • the recommendation result and the facial image reported by the customer terminal are pushed to the sales terminal corresponding to the target physical store.
  • the location information reported by the customer terminal is acquired, and based on the location information, it is determined whether the customer terminal is located in the target physical store; if the customer terminal is located in the target physical store, the customer information reported by the customer terminal is acquired; Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results; determine the maximum similarity calculation result from the multiple similarity calculation results, and determine the Whether the maximum similarity calculation result is less than the preset threshold; if the maximum similarity calculation result is less than the preset threshold, the customer information is input into the preset prediction model to obtain the product recommendation result for the customer information; The face image reported by the customer terminal is sent, and the face image and the product recommendation result are sent to the sales terminal corresponding to the target physical store.
  • the product that the customer is interested in is determined according to the customer's information, and the salesperson is notified, so that the salesperson can provide the customer with more accurate shopping guide services, and improve the sales efficiency and success rate.
  • Fig. 4 is a schematic diagram of the detailed process of determining that the customer terminal is located in the target physical store in Fig. 2.
  • step S10 includes:
  • Step S101 Obtain the location information reported by the customer terminal, calculate the distance between the location information and the location information of each physical store, and obtain multiple distance calculation results.
  • the earth is a nearly standard ellipsoid with an equatorial radius of 6378.140 kilometers, a polar radius of 6356.755 kilometers, and an average radius of 6371.04 kilometers. If we assume that the earth is a perfect sphere, then its radius is the average radius of the earth, denoted as R. If the 0 degree longitude line is used as the reference, then the surface distance between these two points can be calculated based on the latitude and longitude of any two points on the surface of the earth (here, the error caused by the topography of the earth surface to the calculation is ignored, and it is only a theoretical estimate).
  • the longitude and latitude of the first point A is (LonA, LatA)
  • the longitude and latitude of the second point B is (LonB, LatB).
  • the east longitude is taken as the positive value (Longitude)
  • the west longitude is taken as the negative value (-Longitude)
  • the north latitude takes 90-latitude value (90-Latitude)
  • the south latitude takes 90+latitude value (90+Latitude)
  • the two points after the above processing are counted as (MLonA,MLatA) and (MLonB, MLatB).
  • the following formula for calculating the distance between two points can be obtained:
  • the location information (the location information reported by the customer terminal and the location information of each physical store pre-stored in the server) may be latitude and longitude. According to the above formula 1 and formula 2, the distance between the customer terminal and each physical store can be obtained.
  • Step S102 It is determined whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results.
  • multiple distance calculation results can be obtained according to step S101, and then it is further determined whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results.
  • the preset distance is set according to actual needs, for example, set to 50 meters.
  • Step S103 If there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
  • the method before step S10, the method further includes:
  • the historical transaction records including the product name and the transaction customer information corresponding to the product name; calculate the characteristic value corresponding to the transaction customer information, and substitute the characteristic value into the prediction function formula to obtain A prediction function; the multiple prediction functions are iteratively solved to obtain the prediction model corresponding to the product name; the prediction function formula is as follows:
  • ⁇ i is the weight value of the transaction customer information i
  • x i is the characteristic value corresponding to the transaction customer information i
  • ⁇ T [ ⁇ 1 , ⁇ 2 ,..., ⁇ n ]
  • x [x 1 ,x 2 ,...,x n ]
  • e is a natural constant.
  • the transactional customer information corresponding to product 1 in the historical transaction record includes customer information from customer 1 to customer 10; if customer 11 , Customer 12, Customer 13...Customer 20 has purchased product 2, then the transaction customer information corresponding to product 2 in the historical transaction record includes customer information from customer 11 to customer 20; if customer 21, customer 22, customer 23...
  • the customer 30 once purchased the product 3, and the transaction customer information corresponding to the product 3 in the historical transaction record includes the customer information of the customer 21 to the customer 30.
  • customer information includes: gender, age, income, personal health status (the type of information can be expanded or reduced according to actual needs). Calculate the characteristic value corresponding to the customer information according to the preset characteristic value conversion rule.
  • the characteristic value corresponding to the transaction customer information can be obtained. And substitute the eigenvalues into the formula:
  • ⁇ i is the weight value of the transaction customer information i
  • x i is the characteristic value corresponding to the transaction customer information i
  • ⁇ T [ ⁇ 1 , ⁇ 2 ,..., ⁇ n ]
  • x [x 1 ,x 2 ,...,x n ]
  • e is a natural constant.
  • the essence of the prediction model is a specific algorithm.
  • Specific algorithms can include: logistic regression algorithms or neural network algorithms.
  • the prediction model is the LR (Logistic Regression) model.
  • Logistic regression is a classification method, which is mainly used to solve two classification problems (that is, there are only two outputs, representing two classifications respectively).
  • the logistic regression algorithm uses the Logistic function (or called the Sigmoid function), and the curve form of the function is S Type curve, the function form is:
  • ⁇ i is the weight value of the transaction customer information i
  • x i is the characteristic value corresponding to the transaction customer information i
  • ⁇ T [ ⁇ 1 , ⁇ 2 ,..., ⁇ n ]
  • x [x 1 ,x 2 ,...,x n ]
  • e is a natural constant.
  • the prediction model includes: the prediction information is the LR model of product 1, the prediction information is the LR model of product 2, and the prediction information is the LR model of product 3.
  • the way to obtain the prediction information of the LR model of product 1 is: substitute the feature value corresponding to the customer information of customer 1 as sample data 1 into the above formula (3) to obtain the prediction function 1; similarly, the feature corresponding to the customer information of customer 2 The value is substituted into the above formula (3) as the sample data 2 to obtain the prediction function 2, and the characteristic value corresponding to the customer information of the customer 3 to the customer 10 is substituted into the above formula (3) as the sample data 3 to the sample data 10, respectively, to obtain the prediction function 3 To 10, and prediction function 1 to prediction function 10 are all obtained from the information of customers who have purchased product 1, so the output values of prediction function 1 to prediction function 10 are all equal, thereby constructing multiple solution functions, namely prediction function 1.
  • Prediction function 2 Prediction function 2
  • Prediction function 1 Prediction function 3
  • the output value of the LR model is 0 ⁇ 1. The larger the output value, the customer willing The greater the probability of buying product 1.
  • the LR model whose predicted information is product 2 is obtained.
  • the output value of the LR model is 0 to 1. The larger the output value, the greater the probability that the customer corresponding to the input customer information is willing to purchase product 2.
  • the LR model whose prediction information is product 3 the LR model whose prediction information is product 4
  • the LR model whose prediction information is product n can be obtained.
  • the process of quantifying (converting) the transaction customer information (gender, age, income, personal health status) into a numerical value can be based on actual needs and using reasonable rules to convert the transaction customer information (gender, age, Income, personal health status) converted to appropriate values.
  • the characteristic value corresponding to the current customer information is input to the LR model.
  • the output of the LR model is a probability value. The probability value ranges from 0 to 1, and the probability value is higher. Large, indicating that the product corresponding to the LR model is more suitable for the needs of the customer to which the customer information belongs.
  • step S50 includes:
  • the characteristic value corresponding to the customer information is calculated, and the characteristic value is input into the prediction model corresponding to each product to obtain a number of output values; select greater than or equal to the preset probability The value of the target output value is based on the target output value to obtain the product recommendation result for the customer information.
  • multiple training models are obtained by training, for example, the LR model whose prediction information is product 1, the LR model whose prediction information is product 2, and the LR model whose prediction information is product 3. Then, the characteristic values corresponding to the customer information are input into the three prediction models, and three probability values P1, P2, and P3 are obtained. Select a target output value greater than a preset probability value (for example, 0.85) from P1, P2, and P3. If P2 and P3 are greater than or equal to the preset probability value, then P2 and P3 are the target output values, indicating that product 2 and product 3 fit the needs of the customer to whom the current customer information belongs. Therefore, the determined product recommendation result is product 2 and Product 3.
  • a preset probability value for example, 0.85
  • the method before step S60, the method further includes:
  • the product recommendation results are product 2 and product 3. It is necessary to determine whether there is product 2 and product 3 in the target physical store, that is, whether the product recommendation result exists there.
  • step S60 is executed, which avoids waste of sales resources.
  • the out-of-stock reminder can be sent to the customer terminal to remind the customer that the product 2 and product 3 are in the destination physical store. Out of stock status.
  • FIG. 5 is a detailed flowchart of the steps of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store in FIG. 2.
  • the step of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store includes:
  • Step S601 Obtain status information of each sales terminal corresponding to the target physical store.
  • each salesperson is equipped with a sales terminal.
  • the status of the sales terminal is adjusted to busy.
  • the salesperson is idle, the status of the sales terminal is adjusted to idle, and the status of the sales terminal is reported To the server.
  • Step S602 Determine a target sales terminal whose status is idle based on the status information.
  • a target sales terminal whose status is idle can be determined from all sales terminals.
  • Step S603 Send the face image and the product recommendation result to the target sales terminal.
  • the target sales terminal in the idle state is first determined, and the face image and the product recommendation result are sent to the target sales terminal in the idle state, so that the target sales terminal belongs to Sales staff can immediately serve customers, realizing reasonable management of sales resources.
  • FIG. 6 is a schematic diagram of functional modules of an embodiment of a merchandise shopping guide device in a new retail mode of the present invention.
  • the commodity shopping guide device in the new retail mode includes:
  • the location judgment module 10 is configured to obtain location information reported by a customer terminal, and determine whether the customer terminal is located in a target physical store according to the location information;
  • the customer information obtaining module 20 is configured to obtain the customer information reported by the customer terminal if the customer terminal is located in the target physical store;
  • the calculation module 30 is used to calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results;
  • the detection module 40 is configured to determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
  • the prediction module 50 is configured to, if the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
  • the push module 60 is configured to obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  • the specific embodiments of the merchandise shopping guide device in the new retail mode of the present invention are basically the same as the various embodiments of the merchandise shopping guide method in the new retail mode described above, and will not be repeated here.
  • the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a commodity shopping guide program in the new retail mode, and when the commodity shopping guide program in the new retail mode is executed by a processor The steps of each embodiment of the commodity shopping guide method in the above new retail mode are realized.
  • the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present invention.
  • a storage medium such as ROM/RAM
  • a terminal device which can be a mobile phone, a computer, a server, or a network device, etc.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A shopping guide method and apparatus in a new retail model, a device and a storage medium. Said method comprises: acquiring customer information; calculating a similarity between customer information and information about a customer having performed transaction, so as to obtain a plurality of similarities; determining a maximum similarity from the plurality of similarities, and when the maximum similarity is less than a preset threshold, inputting the customer information into a preset prediction model to obtain a product recommendation result; and acquiring a facial image, and sending the facial image and the product recommendation result to a sale terminal.

Description

新零售模式下的商品导购方法、装置、设备及存储介质Commodity shopping guide method, device, equipment and storage medium under new retail mode
本申请要求于2019年9月6日提交中国专利局、申请号为201910844417.9、发明名称为“新零售模式下的商品导购方法、装置、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 201910844417.9, and the invention title is "Methods, devices, equipment, and storage media for shopping guides under the new retail model" on September 6, 2019. All of them The content is incorporated in this application by reference.
技术领域Technical field
本发明涉及人工智能技术领域,尤其涉及新零售模式下的商品导购方法、装置、设备及存储介质。The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and storage medium for shopping guides in a new retail mode.
背景技术Background technique
目前实体店内的销售方式,一般是用户进入实体店,随后销售顾问根据经验判断用户是否是潜在购买用户,若判断为潜在购买客户,则跟进销售导购。这种方式依赖于销售顾问的经验判断,对销售顾问的能力要求较高,且当顾客较多时,由于销售顾问的人数有限,导致潜在消费客户因为没有销售顾问接待而流失,或是销售顾问刚开始不了解客户任何爱好和特征,便需要与顾客进行过多的交谈,引起顾客反感,从而导致销售成功率较低。The current sales method in a physical store is generally that the user enters the physical store, and then the sales consultant judges whether the user is a potential buying user based on experience, and if it is judged to be a potential buying customer, follow up the sales guide. This method relies on the empirical judgment of sales consultants, and requires a high level of ability of sales consultants. When there are many customers, the number of sales consultants is limited, which leads to the loss of potential consumer customers because they are not received by sales consultants, or the sales consultants are just new. At the beginning, if you don't understand any hobbies and characteristics of customers, you need to have too many conversations with customers, which arouses customers' disgust and leads to a lower sales success rate.
发明内容Summary of the invention
本发明的主要目的在于提供一种新零售模式下的商品导购方法、装置、设备及存储介质,旨在解决现有技术中销售成功率不高的技术问题。The main purpose of the present invention is to provide a method, device, equipment and storage medium for shopping guide under the new retail mode, aiming to solve the technical problem of low sales success rate in the prior art.
为实现上述目的,本发明提供一种新零售模式下的商品导购方法,包括:In order to achieve the above objectives, the present invention provides a shopping guide method for commodities under a new retail mode, including:
获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;Acquiring the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information;
若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;If the customer terminal is located in the target physical store, acquiring customer information reported by the customer terminal;
计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results;
从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Acquire the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
此外,为实现上述目的,本发明还提供一种新零售模式下的商品导购装置,所述新零售模式下的商品导购装置包括:In addition, in order to achieve the above object, the present invention also provides a commodity shopping guide device under the new retail mode, and the commodity shopping guide device under the new retail mode includes:
位置判断模块,用于获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;The location judgment module is used to obtain the location information reported by the customer terminal, and determine whether the customer terminal is located in the target physical store according to the location information;
顾客信息获取模块,用于若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;A customer information acquisition module, configured to acquire customer information reported by the customer terminal if the customer terminal is located in a target physical store;
计算模块,用于计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;The calculation module is used to calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results;
检测模块,用于从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;The detection module is configured to determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
预测模块,用于若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;A prediction module, configured to input the customer information into a preset prediction model if the maximum similarity calculation result is less than a preset threshold, to obtain a product recommendation result for the customer information;
推送模块,用于获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。The push module is configured to obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
此外,为实现上述目的,本发明还提供一种计算机设备,所述计算机设备包括存储器和处理器;In addition, in order to achieve the above object, the present invention also provides a computer device, the computer device including a memory and a processor;
所述存储器用于存储计算机程序;The memory is used to store a computer program;
所述处理器,用于执行所述计算机程序并在执行所述计算机程序时实现如上所述的新零售模式下的商品导购方法。The processor is configured to execute the computer program and, when executing the computer program, implement the above-mentioned method for shopping guide under the new retail mode.
此外,为实现上述目的,本发明还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有新零售模式下的商品导购程序,所述新零售模式下的商品导购程序被处理器执行时实现如上所述的新零售模式下的商品导购方法的步骤。In addition, in order to achieve the above-mentioned object, the present invention also provides a computer-readable storage medium on which is stored a commodity shopping guide program under the new retail mode, and the commodity shopping guide program under the new retail mode is processed When the device is executed, the steps of the commodity shopping guide method under the new retail mode as described above are realized.
本发明中,当确定顾客位于目标实体店时,根据顾客的信息确定顾客感兴趣的商品,并告知该目标实体店内的销售人员,使得销售人员能为顾客提供更精准的导购服务,提高了销售效率以及成功率。In the present invention, when it is determined that the customer is located in the target physical store, the product that the customer is interested in is determined according to the customer's information, and the sales staff in the target physical store are notified, so that the sales staff can provide customers with more accurate shopping guide services and increase sales. Efficiency and success rate.
附图说明Description of the drawings
图1为本发明实施例方案涉及的硬件运行环境的计算机设备结构示意图;FIG. 1 is a schematic diagram of a computer device structure of a hardware operating environment involved in a solution of an embodiment of the present invention;
图2为本发明新零售模式下的商品导购方法一实施例的流程示意图;FIG. 2 is a schematic flowchart of an embodiment of a merchandise shopping guide method under the new retail mode of the present invention;
图3为本发明新零售模式下的商品导购方法一实施例的场景示意图;3 is a schematic diagram of a scene of an embodiment of a method for shopping guide in a new retail mode according to the present invention;
图4为图2中确定顾客终端位于目标实体店的细化流程示意图;FIG. 4 is a schematic diagram of the detailed process of determining that the customer terminal is located in the target physical store in FIG. 2;
图5为图2中将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤的细化流程示意图;5 is a detailed flowchart of the steps of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store in FIG. 2;
图6为本发明新零售模式下的商品导购装置一实施例的功能模块示意图。Fig. 6 is a schematic diagram of functional modules of an embodiment of a merchandise shopping guide device in a new retail mode of the present invention.
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。The realization of the objectives, functional characteristics and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings.
具体实施方式detailed description
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention.
附图中所示的流程图仅是示例说明,不是必须包括所有的内容和操作/步骤,也不是必须按所描述的顺序执行。例如,有的操作/步骤还可以分解、组 合或部分合并,因此实际执行的顺序有可能根据实际情况改变。The flowchart shown in the drawings is only an example, and does not necessarily include all contents and operations/steps, nor does it have to be executed in the described order. For example, some operations/steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to actual conditions.
下面结合附图,对本申请的一些实施方式作详细说明。在不冲突的情况下,下述的实施例及实施例中的特征可以相互组合。Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.
如图1所示,图1为本发明实施例方案涉及的硬件运行环境的计算机设备结构示意图。As shown in Fig. 1, Fig. 1 is a schematic structural diagram of a computer device in a hardware operating environment involved in a solution of an embodiment of the present invention.
本发明实施例计算机设备可以是PC,也可以是智能手机、服务器等具有数据处理能力的终端设备。The computer device in the embodiment of the present invention may be a PC, or a terminal device with data processing capabilities, such as a smart phone or a server.
如图1所示,该计算机设备可以包括:处理器1001,例如CPU,网络接口1004,用户接口1003,存储器1005,通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是稳定的存储器(non-volatile memory),例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。As shown in FIG. 1, the computer device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a magnetic disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
本领域技术人员可以理解,图1中示出的计算机设备结构并不构成对计算机设备的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。Those skilled in the art can understand that the structure of the computer device shown in FIG. 1 does not constitute a limitation on the computer device, and may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements.
如图1所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及网络操作控制应用程序。As shown in FIG. 1, a memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a network operation control application program.
在图1所示的计算机设备中,网络接口1004主要用于连接后台服务器,与后台服务器进行数据通信;用户接口1003主要用于连接客户端(用户端),与客户端进行数据通信;而处理器1001可以用于调用存储器1005中存储的计算机程序,并执行以下操作:In the computer device shown in Figure 1, the network interface 1004 is mainly used to connect to the back-end server and communicate with the back-end server; the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client; and the processing The device 1001 can be used to call a computer program stored in the memory 1005 and perform the following operations:
获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;Acquiring the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information;
若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;If the customer terminal is located in the target physical store, acquiring customer information reported by the customer terminal;
计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results;
从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Acquire the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
获取顾客终端上报的位置信息,计算所述位置信息与各个实体店位置信息的距离,得到多个距离计算结果;Acquiring the location information reported by the customer terminal, calculating the distance between the location information and the location information of each physical store, and obtaining multiple distance calculation results;
确定所述多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果;Determine whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results;
若所述多个距离计算结果中存在一个小于或等于预设距离的目标计算结果,则确定所述顾客终端位于所述目标计算结果对应的目标实体店。If there is a target calculation result less than or equal to the preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
获取历史交易记录中存储的各个已交易顾客信息;Obtain each customer's information that has been traded stored in historical transaction records;
通过余弦相似度公式计算所述顾客信息与所述各个已交易顾客信息的相似度,得到多个相似度计算结果,所述余弦相似度公式如下:The similarity between the customer information and the transaction customer information is calculated by the cosine similarity formula, and multiple similarity calculation results are obtained. The cosine similarity formula is as follows:
Figure PCTCN2019117714-appb-000001
Figure PCTCN2019117714-appb-000001
其中,n(A)表示顾客信息中包含的信息的类型数量,n(B)表示已交易顾客信息中包含的信息的类型数量,n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量,K为相似度计算结果。Among them, n(A) represents the number of types of information contained in the customer information, n(B) represents the number of types of information contained in the customer information that has been traded, and n(A∩B) represents that the customer information is the same as that of the customer information that has been traded The amount of information, K is the similarity calculation result.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
获取历史交易记录,所述历史交易记录包括产品名称及所述产品名称对应的已交易顾客信息;Acquiring historical transaction records, the historical transaction records including the product name and the transaction customer information corresponding to the product name;
计算所述已交易顾客信息对应的特征值,并将所述特征值代入预测函数公式,得到多个预测函数;Calculate the feature value corresponding to the transaction customer information, and substitute the feature value into the prediction function formula to obtain multiple prediction functions;
对所述多个预测函数进行迭代求解,得到所述产品名称对应的预测模型;Iteratively solving the multiple prediction functions to obtain a prediction model corresponding to the product name;
所述预测函数公式如下:The prediction function formula is as follows:
Figure PCTCN2019117714-appb-000002
Figure PCTCN2019117714-appb-000002
其中,
Figure PCTCN2019117714-appb-000003
θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
among them,
Figure PCTCN2019117714-appb-000003
θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
若所述最大相识度计算结果小于预设阈值,则计算所述顾客信息对应的特征值,将所述特征值分别输入各个产品对应的预测模型,得到若干输出值;If the calculation result of the maximum acquaintance degree is less than the preset threshold, calculate the characteristic value corresponding to the customer information, and input the characteristic value into the prediction model corresponding to each product to obtain several output values;
选取大于或等于预设概率值的目标输出值,基于所述目标输出值得到针对所述顾客信息的产品推荐结果。A target output value greater than or equal to a preset probability value is selected, and a product recommendation result for the customer information is obtained based on the target output value.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
获取所述目标实体店的产品列表;Obtaining a product list of the target physical store;
检测所述产品推荐结果是否存在于所述产品列表中;Detecting whether the product recommendation result exists in the product list;
若所述产品推荐结果存在于所述产品列表中,则执行所述获取所述顾客 终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤。If the product recommendation result exists in the product list, execute the acquisition of the face image reported by the customer terminal, and send the face image and the product recommendation result to the target physical store. The steps of the point-of-sale.
在一实施例中,处理器1001可以调用存储器1005中存储的计算机程序,还执行以下操作:In an embodiment, the processor 1001 may call a computer program stored in the memory 1005, and also perform the following operations:
获取所述目标实体店对应的各个销售终端的状态信息;Acquiring status information of each sales terminal corresponding to the target physical store;
基于所述状态信息确定状态为空闲的目标销售终端;Determining the target sales terminal whose status is idle based on the status information;
将所述人脸图像以及所述产品推荐结果发送至所述目标销售终端。Sending the face image and the product recommendation result to the target sales terminal.
参照图2,图2为本发明新零售模式下的商品导购方法一实施例的流程示意图。Referring to FIG. 2, FIG. 2 is a schematic flowchart of an embodiment of a merchandise shopping guide method under the new retail mode of the present invention.
如图2所示,新零售模式下的商品导购方法包括:As shown in Figure 2, the shopping guide methods under the new retail model include:
步骤S10、获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店。Step S10: Obtain the location information reported by the customer terminal, and determine whether the customer terminal is located in the target physical store according to the location information.
本实施例中,消息推送方法应用于计算机设备,计算机设备具体可以是服务器。服务器上存储了多个实体店的位置信息,例如,实体店1至实体店5的位置信息,分别为W1、W2、W3、W4、W5。分别计算顾客终端上报的位置信息W与W1至W5的距离,得到五个计算结果,分别为L1至L5。然后进一步判断L1至L5中是否存在小于或等于预设距离的结果,其中,预设距离根据实际情况进行设置,例如设置为50米。由于实体店与实体店之间的具体相距较远,因此一般来说L1至L5中只会存在一个结果小于或等于50米。例如,若L3小于或等于50米,则确定顾客终端当前处于实体店3。In this embodiment, the message pushing method is applied to a computer device, and the computer device may specifically be a server. The location information of multiple physical stores is stored on the server. For example, the location information of physical store 1 to physical store 5 are W1, W2, W3, W4, and W5, respectively. The distance between the location information W reported by the customer terminal and W1 to W5 is calculated respectively, and five calculation results are obtained, which are respectively L1 to L5. Then it is further judged whether there is a result less than or equal to the preset distance in L1 to L5, where the preset distance is set according to the actual situation, for example, set to 50 meters. Due to the specific distance between the physical store and the physical store, generally speaking, only one result from L1 to L5 is less than or equal to 50 meters. For example, if L3 is less than or equal to 50 meters, it is determined that the customer terminal is currently in the physical store 3.
步骤S20、若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息。Step S20: If the customer terminal is located in the target physical store, acquire customer information reported by the customer terminal.
本实施例中,顾客在使用顾客终端中安装的客户端时,需要预先注册,在注册过程中,需要填写一些个人信息,例如,性别、年龄、职业、收入状况、健康状况、家庭病史等信息(个人信息的类型可根据实际需要进行扩充或缩减,在此不做限制),然后由顾客终端将个人信息上报至服务器,服务器将个人信息与该顾客终端的终端标识关联存储。当检测到顾客终端位于目标实体店时,即可从存储的数据中获取该顾客终端的终端标识对应的个人信息(即顾客信息)。In this embodiment, the customer needs to pre-register when using the client installed in the customer terminal. During the registration process, some personal information needs to be filled in, such as gender, age, occupation, income status, health status, family medical history, etc. (The type of personal information can be expanded or reduced according to actual needs, and there is no restriction here), and then the customer terminal reports the personal information to the server, and the server stores the personal information in association with the terminal identification of the customer terminal. When it is detected that the customer terminal is located in the target physical store, the personal information (that is, customer information) corresponding to the terminal identification of the customer terminal can be obtained from the stored data.
步骤S30、计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果。Step S30: Calculate the similarity between the customer information and each transaction customer information stored in the historical transaction record to obtain multiple similarity calculation results.
一可选实施例中,步骤S30包括:In an optional embodiment, step S30 includes:
获取历史交易记录中存储的各个已交易顾客信息;通过余弦相似度公式计算所述顾客信息与所述各个已交易顾客信息的相似度,得到多个相似度计算结果,所述余弦相似度公式如下:Obtain each transaction customer information stored in historical transaction records; calculate the similarity between the customer information and the transaction customer information through a cosine similarity formula, and obtain multiple similarity calculation results, the cosine similarity formula is as follows :
Figure PCTCN2019117714-appb-000004
Figure PCTCN2019117714-appb-000004
其中,n(A)表示顾客信息中包含的信息的类型数量,n(B)表示已交易顾客信息中包含的信息的类型数量,n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量,K为相似度计算结果。Among them, n(A) represents the number of types of information contained in the customer information, n(B) represents the number of types of information contained in the customer information that has been traded, and n(A∩B) represents that the customer information is the same as that of the customer information that has been traded The amount of information, K is the similarity calculation result.
本实施例中,每完成一次销售交易,便将交易详情记录至历史交易记录中。交易详情包括:产品名称、顾客信息。如表1所示,表1为存储历史交易记录的数据表。In this embodiment, every time a sales transaction is completed, the transaction details are recorded in the historical transaction record. Transaction details include: product name, customer information. As shown in Table 1, Table 1 is a data table that stores historical transaction records.
表1Table 1
已交易顾客信息1Transaction customer information 1 产品名称1Product name 1
已交易顾客信息2Transaction customer information 2 产品名称2Product name 2
已交易顾客信息3Transaction customer information 3 产品名称3Product name 3
已交易顾客信息4Transaction customer information 4 产品名称4Product name 4
通过余弦相似度公式分别计算顾客信息与已交易顾客信息1至已交易顾客信息4的相似度。余弦相似度公式如下:Calculate the similarity between customer information and transaction customer information 1 to transaction customer information 4 through the cosine similarity formula. The cosine similarity formula is as follows:
Figure PCTCN2019117714-appb-000005
Figure PCTCN2019117714-appb-000005
其中,n(A)表示顾客信息中包含的信息的类型数量,若顾客信息包括性别、年龄、职业、收入状况、健康状况、家庭病史,则n(A)为6;n(B)表示已交易顾客信息中包含的信息的类型数量,若已交易顾客信息包括性别、年龄、职业、收入状况、健康状况、家庭病史,则n(B)为6;n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量;K表示顾客信息与已交易顾客信息的相似度计算结果。一实施例中,若顾客信息与已交易顾客信息1的年龄、职业、收入状态均相同,则顾客信息与已交易顾客信息1的相似度计算结果K1=0.5。同理,即可计算得到当前的顾客信息与存储的各个已交易顾客信息的相似度,得到多个相似度计算结果。Among them, n(A) represents the type and quantity of information contained in the customer information. If the customer information includes gender, age, occupation, income status, health status, and family medical history, then n(A) is 6; n(B) represents The type and quantity of the information contained in the transaction customer information. If the transaction customer information includes gender, age, occupation, income status, health status, and family medical history, then n(B) is 6; n(A∩B) represents the customer information and The quantity of the same information in the transaction customer information; K represents the calculation result of the similarity between the customer information and the transaction customer information. In one embodiment, if the age, occupation, and income status of the customer information and the transaction customer information 1 are the same, then the similarity calculation result of the customer information and the transaction customer information 1 is K1=0.5. In the same way, the similarity between the current customer information and the stored transactional customer information can be calculated, and multiple similarity calculation results can be obtained.
步骤S40、从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值。Step S40: Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold.
本实施例中,若已交易顾客信息包括已交易顾客信息1至已交易顾客信息4,则计算得到四个相似度计算结果,分别为K1至K4,则从K1至K4中选取最大的一个值,例如最大计算结果为K2,则判断K2是否大于或等于预设阈值。预设阈值的设置根据实际需要进行设置,例如设置为0.8。In this embodiment, if the transaction customer information includes transaction customer information 1 to transaction customer information 4, four similarity calculation results are calculated, namely K1 to K4, and the largest value is selected from K1 to K4 For example, if the maximum calculation result is K2, it is determined whether K2 is greater than or equal to the preset threshold. The preset threshold is set according to actual needs, for example, set to 0.8.
本实施例中,若K2大于或等于预设阈值,则说明该顾客与已交易顾客2的个人信息很相似,已交易顾客2购买过的商品很有可能是该顾客感兴趣的商品,因此,可以直接以已交易顾客2购买过的商品作为待推荐商品。例如,已交易顾客2购买过的商品包括:商品1、商品3,则产品推荐结果即为商品1、商品3。In this embodiment, if K2 is greater than or equal to the preset threshold, it means that the personal information of the customer is very similar to that of customer 2 who has already traded. The goods purchased by customer 2 who have already traded are likely to be goods of interest to the customer. Therefore, It is possible to directly use the product purchased by the customer 2 who has already traded as the product to be recommended. For example, if the products purchased by customer 2 include: product 1 and product 3, the product recommendation result is product 1 and product 3.
步骤S50、若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果。Step S50: If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information.
本实施例中,若最大相似度计算结果小于预设阈值,则说明当前的顾客信息与存储的各个已交易顾客信息均不相同,无法根据历史交易记录预测当前顾客信息感兴趣的产品,则将顾客信息输入预测模型,得到针对顾客信息的产品推荐结果。In this embodiment, if the maximum similarity calculation result is less than the preset threshold, it means that the current customer information is not the same as the stored transactional customer information, and it is impossible to predict the products of interest to the current customer information based on historical transaction records. The customer information is input into the predictive model, and the result of product recommendation based on the customer information is obtained.
本实施例中,预测模型可以是多个,例如预测信息为产品1的LR模型、预测信息为产品2的LR模型以及预测信息为产品3的LR模型。则将顾客信息对应的特征值分别输入这三个预测模型,得到三个概率值P1、P2以及P3。从P1、P2以及P3中选取大于预设概率值(例如0.85)的目标输出值。若P2以及P3大于或等于预设概率值,则P2以及P3为目标输出值,则说明产品2以及产品3贴合当前顾客信息所属的顾客的需求,因此,确定的产品推荐结果为产品2以及产品3。In this embodiment, there may be multiple prediction models, such as an LR model with prediction information of product 1, an LR model with prediction information of product 2, and an LR model with prediction information of product 3. Then, the characteristic values corresponding to the customer information are input into the three prediction models, and three probability values P1, P2, and P3 are obtained. Select a target output value greater than a preset probability value (for example, 0.85) from P1, P2, and P3. If P2 and P3 are greater than or equal to the preset probability value, then P2 and P3 are the target output values, indicating that product 2 and product 3 fit the needs of the customer to whom the current customer information belongs. Therefore, the determined product recommendation result is product 2 and Product 3.
步骤S60、获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Step S60: Obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
本实施例中,得到产品推荐结果后,进一步获取顾客终端上报的人脸图像,并将人脸图像以及产品推荐结果发生至目标实体店对应的销售终端,以供销售终端的所属销售人员根据人脸图像找到顾客,并根据产品推荐结果为该顾客进行导购。本实施例中,顾客在注册使用顾客终端时,会被要求上传人脸图像,顾客终端接收到人脸图像后,将人脸图像上报到服务器,服务器将人脸图像与顾客终端的终端标识符关联存储。In this embodiment, after the product recommendation result is obtained, the face image reported by the customer terminal is further obtained, and the face image and the product recommendation result are generated to the sales terminal corresponding to the target physical store, so that the sales staff of the sales terminal can follow the person The face image finds the customer, and conducts a shopping guide for the customer according to the product recommendation result. In this embodiment, when a customer registers to use a customer terminal, he will be required to upload a face image. After the customer terminal receives the face image, it will report the face image to the server, and the server will associate the face image with the terminal identifier of the customer terminal. Associated storage.
参照图3,图3为本发明新零售模式下的商品导购方法一实施例的场景示意图。如图3所示,服务器分别于顾客终端以及销售终端建立通信连接,服务器根据顾客终端上报的位置信息确定其所在的目标实体店,并根据顾客终端对应的顾客信息确定产品推荐结果,从而将产品推荐结果以及顾客终端上报的人脸图像推送至目标实体店对应的销售终端。Referring to FIG. 3, FIG. 3 is a schematic diagram of a scene of an embodiment of a method for shopping guide of goods in a new retail mode of the present invention. As shown in Figure 3, the server establishes a communication connection with the customer terminal and the sales terminal respectively. The server determines the target physical store where it is located according to the location information reported by the customer terminal, and determines the product recommendation result according to the customer information corresponding to the customer terminal, so that the product The recommendation result and the facial image reported by the customer terminal are pushed to the sales terminal corresponding to the target physical store.
本实施例中,获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。通过本实施例,根据顾客的信息确定顾客感兴趣的商品,并告知销售人员,使得销售人员能为顾客提供更精准的导购服务,提高了销售效率以及成功率。In this embodiment, the location information reported by the customer terminal is acquired, and based on the location information, it is determined whether the customer terminal is located in the target physical store; if the customer terminal is located in the target physical store, the customer information reported by the customer terminal is acquired; Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results; determine the maximum similarity calculation result from the multiple similarity calculation results, and determine the Whether the maximum similarity calculation result is less than the preset threshold; if the maximum similarity calculation result is less than the preset threshold, the customer information is input into the preset prediction model to obtain the product recommendation result for the customer information; The face image reported by the customer terminal is sent, and the face image and the product recommendation result are sent to the sales terminal corresponding to the target physical store. Through this embodiment, the product that the customer is interested in is determined according to the customer's information, and the salesperson is notified, so that the salesperson can provide the customer with more accurate shopping guide services, and improve the sales efficiency and success rate.
参照图4,图4为图2中确定顾客终端位于目标实体店的细化流程示意图。在本发明新零售模式下的商品导购方法一实施例中,步骤S10包括:Referring to Fig. 4, Fig. 4 is a schematic diagram of the detailed process of determining that the customer terminal is located in the target physical store in Fig. 2. In an embodiment of the merchandise shopping guide method under the new retail mode of the present invention, step S10 includes:
步骤S101、获取顾客终端上报的位置信息,计算所述位置信息与各个实体店位置信息的距离,得到多个距离计算结果。Step S101: Obtain the location information reported by the customer terminal, calculate the distance between the location information and the location information of each physical store, and obtain multiple distance calculation results.
地球是一个近乎标准的椭球体,它的赤道半径为6378.140千米,极半径为6356.755千米,平均半径6371.004千米。如果我们假设地球是一个完美的球体,那么它的半径就是地球的平均半径,记为R。如果以0度经线为基准,那么根据地球表面任意两点的经纬度就可以计算出这两点间的地表距离(这里忽略地球表面地形对计算带来的误差,仅仅是理论上的估算值)。设第一点A的经纬度为(LonA,LatA),第二点B的经纬度为(LonB,LatB),按照0度经线的基准,东经取经度的正值(Longitude),西经取经度负值(-Longitude),北纬取90-纬度值(90-Latitude),南纬取90+纬度值(90+Latitude),则经过上述处理过后的两点被计为(MLonA,MLatA)和(MLonB,MLatB)。那么根据三角推导,可以得到计算两点距离的如下公式:The earth is a nearly standard ellipsoid with an equatorial radius of 6378.140 kilometers, a polar radius of 6356.755 kilometers, and an average radius of 6371.04 kilometers. If we assume that the earth is a perfect sphere, then its radius is the average radius of the earth, denoted as R. If the 0 degree longitude line is used as the reference, then the surface distance between these two points can be calculated based on the latitude and longitude of any two points on the surface of the earth (here, the error caused by the topography of the earth surface to the calculation is ignored, and it is only a theoretical estimate). Suppose the longitude and latitude of the first point A is (LonA, LatA), and the longitude and latitude of the second point B is (LonB, LatB). According to the 0 degree longitude, the east longitude is taken as the positive value (Longitude), and the west longitude is taken as the negative value (-Longitude), the north latitude takes 90-latitude value (90-Latitude), the south latitude takes 90+latitude value (90+Latitude), then the two points after the above processing are counted as (MLonA,MLatA) and (MLonB, MLatB). Then according to the trigonometric derivation, the following formula for calculating the distance between two points can be obtained:
公式1:Formula 1:
C=sin(MLatA)*sin(MLatB)*cos(MLonA-MLonB)+cos(MLatA)*cos(MLatB)公式2:C=sin(MLatA)*sin(MLatB)*cos(MLonA-MLonB)+cos(MLatA)*cos(MLatB) Formula 2:
Distance(距离)=R*Arccos(C)*Pi/180Distance=R*Arccos(C)*Pi/180
本实施例中,位置信息(顾客终端上报的位置信息以及服务器预存的各个实体店的位置信息)可以是经纬度,根据上述公式1以及公式2,即可得到顾客终端与各个实体店的距离。In this embodiment, the location information (the location information reported by the customer terminal and the location information of each physical store pre-stored in the server) may be latitude and longitude. According to the above formula 1 and formula 2, the distance between the customer terminal and each physical store can be obtained.
步骤S102。确定所述多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果。Step S102. It is determined whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results.
本实施例中,根据步骤S101即可得到多个距离计算结果,然后进一步确定多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果。其中,预设距离根据实际需要进行设置,例如设置为50米。In this embodiment, multiple distance calculation results can be obtained according to step S101, and then it is further determined whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results. Among them, the preset distance is set according to actual needs, for example, set to 50 meters.
步骤S103、若所述多个距离计算结果中存在一个小于或等于预设距离的目标计算结果,则确定所述顾客终端位于所述目标计算结果对应的目标实体店。Step S103: If there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
本实施例中,若顾客终端与实体店7的距离计算结果小于或等于预设距离,则确定顾客终端位于实体店7。In this embodiment, if the calculated result of the distance between the customer terminal and the physical store 7 is less than or equal to the preset distance, it is determined that the customer terminal is located in the physical store 7.
在一实施例中,本发明新零售模式下的商品导购方法一实施例中,在步骤S10之前,还包括:In an embodiment, in an embodiment of the merchandise shopping guide method in the new retail mode of the present invention, before step S10, the method further includes:
获取历史交易记录,所述历史交易记录包括产品名称及所述产品名称对应的已交易顾客信息;计算所述已交易顾客信息对应的特征值,并将所述特征值代入预测函数公式,得到多个预测函数;对所述多个预测函数进行迭代求解,得到所述产品名称对应的预测模型;所述预测函数公式如下:Obtain historical transaction records, the historical transaction records including the product name and the transaction customer information corresponding to the product name; calculate the characteristic value corresponding to the transaction customer information, and substitute the characteristic value into the prediction function formula to obtain A prediction function; the multiple prediction functions are iteratively solved to obtain the prediction model corresponding to the product name; the prediction function formula is as follows:
Figure PCTCN2019117714-appb-000006
Figure PCTCN2019117714-appb-000006
其中,
Figure PCTCN2019117714-appb-000007
θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
among them,
Figure PCTCN2019117714-appb-000007
θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
本实施例中,若顾客1、顾客2、顾客3……顾客10曾经购买了产品1, 则历史交易记录中产品1对应的已交易顾客信息包括顾客1至顾客10的顾客信息;若顾客11、顾客12、顾客13……顾客20曾经购买了产品2,则历史交易记录中产品2对应的已交易顾客信息包括顾客11至顾客20的顾客信息;若顾客21、顾客22、顾客23……顾客30曾经购买了产品3,则历史交易记录中产品3对应的已交易顾客信息包括顾客21至顾客30的顾客信息。其中,顾客信息包括:性别、年龄、收入、个人健康状况(可根据实际需要对信息类型进行扩充或缩减)。根据预设的特征值转换规则计算顾客信息对应的特征值,例如:若性别为男则取1,为女取0,年龄大于等于50取1,小于50取0,收入大于等于20万取1,小于20万取0,有疾病取1,无疾病取0。基于该转换规则,即可得到已交易顾客信息对应的特征值。并将特征值代入公式:In this embodiment, if customer 1, customer 2, customer 3... customer 10 has purchased product 1, then the transactional customer information corresponding to product 1 in the historical transaction record includes customer information from customer 1 to customer 10; if customer 11 , Customer 12, Customer 13...Customer 20 has purchased product 2, then the transaction customer information corresponding to product 2 in the historical transaction record includes customer information from customer 11 to customer 20; if customer 21, customer 22, customer 23... The customer 30 once purchased the product 3, and the transaction customer information corresponding to the product 3 in the historical transaction record includes the customer information of the customer 21 to the customer 30. Among them, customer information includes: gender, age, income, personal health status (the type of information can be expanded or reduced according to actual needs). Calculate the characteristic value corresponding to the customer information according to the preset characteristic value conversion rule. For example, if the gender is male, take 1; if the female is 0, take 1 if the age is greater than or equal to 50, take 0 if the age is greater than or equal to 50, and take 1 if the income is greater than or equal to 200,000. , If it is less than 200,000, take 0, take 1 if there is a disease, take 0 if there is no disease. Based on the conversion rule, the characteristic value corresponding to the transaction customer information can be obtained. And substitute the eigenvalues into the formula:
Figure PCTCN2019117714-appb-000008
Figure PCTCN2019117714-appb-000008
其中,
Figure PCTCN2019117714-appb-000009
θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
among them,
Figure PCTCN2019117714-appb-000009
θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
本实施例中,预测模型的实质为特定算法。特定算法可以包括:逻辑回归算法或神经网络算法。下面以逻辑回归算法进行说明,相应的,预测模型为LR(Logistic Regression)模型。逻辑回归是一种分类方法,主要用于解决两分类问题(即输出只有两种,分别代表两个分类),逻辑回归算法利用Logistic函数(或称为Sigmoid函数),该函数的曲线形式为S型曲线,函数形式为:In this embodiment, the essence of the prediction model is a specific algorithm. Specific algorithms can include: logistic regression algorithms or neural network algorithms. The following describes the logistic regression algorithm. Correspondingly, the prediction model is the LR (Logistic Regression) model. Logistic regression is a classification method, which is mainly used to solve two classification problems (that is, there are only two outputs, representing two classifications respectively). The logistic regression algorithm uses the Logistic function (or called the Sigmoid function), and the curve form of the function is S Type curve, the function form is:
Figure PCTCN2019117714-appb-000010
Figure PCTCN2019117714-appb-000010
对于线性边界的情况,边界形式如下:For the case of a linear boundary, the boundary form is as follows:
Figure PCTCN2019117714-appb-000011
Figure PCTCN2019117714-appb-000011
利用公式(1)和公式(2)构造预测函数:Use formula (1) and formula (2) to construct the prediction function:
Figure PCTCN2019117714-appb-000012
Figure PCTCN2019117714-appb-000012
θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。 θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
本实施例中,预测模型包括:预测信息为产品1的LR模型,预测信息为产品2的LR模型,预测信息为产品3的LR模型。In this embodiment, the prediction model includes: the prediction information is the LR model of product 1, the prediction information is the LR model of product 2, and the prediction information is the LR model of product 3.
得到预测信息为产品1的LR模型的方式为:将顾客1的顾客信息对应的特征值作为样本数据1代入上述公式(3),得到预测函数1;同理将顾客2的顾客信息对应的特征值作为样本数据2代入上述公式(3),得到预测函数2,将顾客3至顾客10的顾客信息对应的特征值作为样本数据3至样本数据10分别代入上述公式(3),得到预测函数3至10,且预测函数1至预测函数10均是由购买过产品1的顾客的信息得到的,所以预测函数1至预测函数10的输出值均相等,从而构建多个求解函数,即预测函数1=预测函数2,预测函数1=预测函数3,预测函数1=预测函数4……,然后对前述求解函数进行迭代求解,计算得到θ T=[θ 12,...,θ n],将计算得到的θ T代入上述预测函数, 即可得到预测信息为产品1的LR模型,该LR模型的输出值为0~1,输出值越大,说明输入的顾客信息对应的顾客愿意购买产品1的概率越大。 The way to obtain the prediction information of the LR model of product 1 is: substitute the feature value corresponding to the customer information of customer 1 as sample data 1 into the above formula (3) to obtain the prediction function 1; similarly, the feature corresponding to the customer information of customer 2 The value is substituted into the above formula (3) as the sample data 2 to obtain the prediction function 2, and the characteristic value corresponding to the customer information of the customer 3 to the customer 10 is substituted into the above formula (3) as the sample data 3 to the sample data 10, respectively, to obtain the prediction function 3 To 10, and prediction function 1 to prediction function 10 are all obtained from the information of customers who have purchased product 1, so the output values of prediction function 1 to prediction function 10 are all equal, thereby constructing multiple solution functions, namely prediction function 1. = Prediction function 2, Prediction function 1 = Prediction function 3, Prediction function 1 = Prediction function 4..., and then iteratively solve the aforementioned solution function, and calculate θ T =[θ 12 ,...,θ n ], substituting the calculated θ T into the above prediction function, you can get the LR model whose prediction information is product 1. The output value of the LR model is 0~1. The larger the output value, the customer willing The greater the probability of buying product 1.
同理,得到预测信息为产品2的LR模型的方式为:将顾客11的顾客信息对应的特征值作为样本数据11代入上述公式(3),将顾客12的顾客信息对应的特征值作为样本数据12代入上述公式(3),将顾客13至顾客20的顾客信息对应的特征值作为样本数据13至样本数据20分别代入上述公式(3),从而得到10个预测函数,然后根据10个预测函数构建多个求解函数,然后对前述多个求解函数进行迭代求解,计算得到θ T=[θ 12,...,θ n],将计算得到的θ T代入上述预测函数,即可得到预测信息为产品2的LR模型,该LR模型的输出值为0~1,输出值越大,说明输入的顾客信息对应的顾客愿意购买产品2的概率越大。 In the same way, the way to obtain the LR model whose predicted information is product 2 is: substitute the feature value corresponding to customer information of customer 11 as sample data 11 into the above formula (3), and use the feature value corresponding to customer information of customer 12 as sample data 12 is substituted into the above formula (3), and the characteristic values corresponding to the customer information of customers 13 to 20 are substituted into the above formula (3) as sample data 13 to sample data 20 respectively to obtain 10 prediction functions, and then according to the 10 prediction functions Construct multiple solution functions, and then iteratively solve the aforementioned multiple solution functions, and calculate θ T =[θ 12 ,...,θ n ], and substitute the calculated θ T into the above prediction function. The LR model whose predicted information is product 2 is obtained. The output value of the LR model is 0 to 1. The larger the output value, the greater the probability that the customer corresponding to the input customer information is willing to purchase product 2.
根据上述训练过程,即可得到预测信息为产品3的LR模型、预测信息为产品4的LR模型……预测信息为产品n的LR模型。According to the above training process, the LR model whose prediction information is product 3, the LR model whose prediction information is product 4, and the LR model whose prediction information is product n can be obtained.
需要说明的是,将已交易顾客信息(性别、年龄、收入、个人健康状况)量化(转换)为数值的过程,可以根据实际需要,采用合理的规则,将已交易顾客信息(性别、年龄、收入、个人健康状况)转换为合适的数值。此外,得到LR模型后,在使用LR模型时,当前的顾客信息对应的特征值输入到LR模型,LR模型的输出是一个概率值,该概率值的取值范围为0~1,概率值越大,说明该LR模型对应的产品更贴合顾客信息所属的顾客的需求。It should be noted that the process of quantifying (converting) the transaction customer information (gender, age, income, personal health status) into a numerical value can be based on actual needs and using reasonable rules to convert the transaction customer information (gender, age, Income, personal health status) converted to appropriate values. In addition, after the LR model is obtained, when the LR model is used, the characteristic value corresponding to the current customer information is input to the LR model. The output of the LR model is a probability value. The probability value ranges from 0 to 1, and the probability value is higher. Large, indicating that the product corresponding to the LR model is more suitable for the needs of the customer to which the customer information belongs.
进一步地,在本实施例的基础上,步骤S50包括:Further, on the basis of this embodiment, step S50 includes:
若所述最大相识度计算结果小于预设阈值,则计算所述顾客信息对应的特征值,将所述特征值分别输入各个产品对应的预测模型,得到若干输出值;选取大于或等于预设概率值的目标输出值,基于所述目标输出值得到针对所述顾客信息的产品推荐结果。If the calculation result of the maximum acquaintance degree is less than the preset threshold, the characteristic value corresponding to the customer information is calculated, and the characteristic value is input into the prediction model corresponding to each product to obtain a number of output values; select greater than or equal to the preset probability The value of the target output value is based on the target output value to obtain the product recommendation result for the customer information.
本实施例中,如上所述,训练得到了多个训练模型,例如预测信息为产品1的LR模型、预测信息为产品2的LR模型以及预测信息为产品3的LR模型。则将顾客信息对应的特征值分别输入这三个预测模型,得到三个概率值P1、P2以及P3。从P1、P2以及P3中选取大于预设概率值(例如0.85)的目标输出值。若P2以及P3大于或等于预设概率值,则P2以及P3为目标输出值,则说明产品2以及产品3贴合当前顾客信息所属的顾客的需求,因此,确定的产品推荐结果为产品2以及产品3。In this embodiment, as described above, multiple training models are obtained by training, for example, the LR model whose prediction information is product 1, the LR model whose prediction information is product 2, and the LR model whose prediction information is product 3. Then, the characteristic values corresponding to the customer information are input into the three prediction models, and three probability values P1, P2, and P3 are obtained. Select a target output value greater than a preset probability value (for example, 0.85) from P1, P2, and P3. If P2 and P3 are greater than or equal to the preset probability value, then P2 and P3 are the target output values, indicating that product 2 and product 3 fit the needs of the customer to whom the current customer information belongs. Therefore, the determined product recommendation result is product 2 and Product 3.
进一步地,本发明新零售模式下的商品导购方法一实施例中,在步骤S60之前,还包括:Further, in an embodiment of the merchandise shopping guide method in the new retail mode of the present invention, before step S60, the method further includes:
获取所述目标实体店的产品列表;检测所述产品推荐结果是否存在于所述产品列表中;若所述产品推荐结果存在于所述产品列表中,则执行所述获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤。Obtain the product list of the target physical store; detect whether the product recommendation result exists in the product list; if the product recommendation result exists in the product list, execute the acquisition of the report from the customer terminal The step of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
本实施例中,在基于步骤S50得到了产品推荐结果,例如产品推荐结果为产品2以及产品3,需要确定目标实体店内是否有产品2以及产品3正在售 卖,即检测产品推荐结果是否存在于该目标实体店的产品列表中,只有当产品推荐结果存在于产品列表中时,才执行步骤S60,避免了销售资源的浪费。In this embodiment, after the product recommendation results are obtained based on step S50, for example, the product recommendation results are product 2 and product 3. It is necessary to determine whether there is product 2 and product 3 in the target physical store, that is, whether the product recommendation result exists there. In the product list of the target physical store, only when the product recommendation result exists in the product list, step S60 is executed, which avoids waste of sales resources.
本实施例中,若产品推荐结果(例如产品2以及产品3)不存在于产品列表中,则可以将缺货提醒发送至该顾客终端,以提醒顾客在目的实体店中产品2以及产品3处于缺货状态。In this embodiment, if the product recommendation results (such as product 2 and product 3) do not exist in the product list, the out-of-stock reminder can be sent to the customer terminal to remind the customer that the product 2 and product 3 are in the destination physical store. Out of stock status.
参照图5,图5为图2中将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤的细化流程示意图。Referring to FIG. 5, FIG. 5 is a detailed flowchart of the steps of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store in FIG. 2.
本实施例中,将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤包括:In this embodiment, the step of sending the face image and the product recommendation result to the sales terminal corresponding to the target physical store includes:
步骤S601,获取所述目标实体店对应的各个销售终端的状态信息。Step S601: Obtain status information of each sales terminal corresponding to the target physical store.
本实施例中,每个销售人员配置一台销售终端,当销售人员在工作时,将销售终端的状态调整为忙碌,销售人员空闲时,将销售终端的状态调整为空闲,销售终端的状态上报给服务器。In this embodiment, each salesperson is equipped with a sales terminal. When the salesperson is working, the status of the sales terminal is adjusted to busy. When the salesperson is idle, the status of the sales terminal is adjusted to idle, and the status of the sales terminal is reported To the server.
步骤S602,基于所述状态信息确定状态为空闲的目标销售终端。Step S602: Determine a target sales terminal whose status is idle based on the status information.
本实施例中,根据各个销售终端上报的状态信息,即可从所有销售终端中确定状态为空闲的目标销售终端。In this embodiment, according to the status information reported by each sales terminal, a target sales terminal whose status is idle can be determined from all sales terminals.
步骤S603,将所述人脸图像以及所述产品推荐结果发送至所述目标销售终端。Step S603: Send the face image and the product recommendation result to the target sales terminal.
本实施例中,在发送人脸图像以及产品推荐结果时,首先确定处于空闲状态的目标销售终端,将人脸图像以及产品推荐结果发送至处于空闲状态的目标销售终端,使得目标销售终端的所属销售人员能即刻为顾客服务,实现了销售资源的合理管理。In this embodiment, when sending the face image and the product recommendation result, the target sales terminal in the idle state is first determined, and the face image and the product recommendation result are sent to the target sales terminal in the idle state, so that the target sales terminal belongs to Sales staff can immediately serve customers, realizing reasonable management of sales resources.
参照图6,图6为本发明新零售模式下的商品导购装置一实施例的功能模块示意图。Referring to FIG. 6, FIG. 6 is a schematic diagram of functional modules of an embodiment of a merchandise shopping guide device in a new retail mode of the present invention.
本实施例中,新零售模式下的商品导购装置包括:In this embodiment, the commodity shopping guide device in the new retail mode includes:
位置判断模块10,用于获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;The location judgment module 10 is configured to obtain location information reported by a customer terminal, and determine whether the customer terminal is located in a target physical store according to the location information;
顾客信息获取模块20,用于若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;The customer information obtaining module 20 is configured to obtain the customer information reported by the customer terminal if the customer terminal is located in the target physical store;
计算模块30,用于计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;The calculation module 30 is used to calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results;
检测模块40,用于从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;The detection module 40 is configured to determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
预测模块50,用于若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;The prediction module 50 is configured to, if the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
推送模块60,用于获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。The push module 60 is configured to obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
本发明新零售模式下的商品导购装置的具体实施例与上述新零售模式下的商品导购方法的各个实施例基本相同,在此不做赘述。The specific embodiments of the merchandise shopping guide device in the new retail mode of the present invention are basically the same as the various embodiments of the merchandise shopping guide method in the new retail mode described above, and will not be repeated here.
此外,本发明实施例还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有新零售模式下的商品导购程序,所述新零售模式下的商品导购程序被处理器执行时实现如上新零售模式下的商品导购方法各个实施例的步骤。In addition, the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a commodity shopping guide program in the new retail mode, and when the commodity shopping guide program in the new retail mode is executed by a processor The steps of each embodiment of the commodity shopping guide method in the above new retail mode are realized.
本发明计算机可读存储介质的具体实施例与上述新零售模式下的商品导购方法的各个实施例基本相同,在此不做赘述。The specific embodiments of the computer-readable storage medium of the present invention are basically the same as the various embodiments of the commodity shopping guide method under the new retail mode described above, and will not be repeated here.
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。It should be noted that in this article, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, It also includes other elements that are not explicitly listed, or elements inherent to the process, method, article, or system. Without more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or system that includes the element.
上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。The sequence numbers of the foregoing embodiments of the present invention are only for description, and do not represent the superiority or inferiority of the embodiments.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本发明各个实施例所述的方法。Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present invention.
以上仅为本发明的优选实施例,并非因此限制本发明的专利范围,凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本发明的专利保护范围内。The above are only preferred embodiments of the present invention, and do not limit the scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the description and drawings of the present invention, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of the present invention.

Claims (20)

  1. 一种新零售模式下的商品导购方法,所述方法包括:A merchandise shopping guide method under the new retail mode, the method includes:
    获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;Acquiring the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information;
    若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;If the customer terminal is located in the target physical store, acquiring customer information reported by the customer terminal;
    计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results;
    从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
    若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
    获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Acquire the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  2. 如权利要求1所述的新零售模式下的商品导购方法,其中,所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店的步骤包括:The method of shopping guide for goods under the new retail mode according to claim 1, wherein the step of obtaining the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information comprises:
    获取顾客终端上报的位置信息,计算所述位置信息与各个实体店位置信息的距离,得到多个距离计算结果;Acquiring the location information reported by the customer terminal, calculating the distance between the location information and the location information of each physical store, and obtaining multiple distance calculation results;
    确定所述多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果;Determine whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results;
    若所述多个距离计算结果中存在一个小于或等于预设距离的目标计算结果,则确定所述顾客终端位于所述目标计算结果对应的目标实体店。If there is a target calculation result less than or equal to the preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
  3. 如权利要求1所述的新零售模式下的商品导购方法,其中,所述计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果的步骤包括:The method of shopping guide for goods under the new retail mode according to claim 1, wherein the step of calculating the similarity between the customer information and each transaction customer information stored in historical transaction records to obtain multiple similarity calculation results include:
    获取历史交易记录中存储的各个已交易顾客信息;Obtain each customer's information that has been traded stored in historical transaction records;
    通过余弦相似度公式计算所述顾客信息与所述各个已交易顾客信息的相似度,得到多个相似度计算结果,所述余弦相似度公式如下:The similarity between the customer information and the transaction customer information is calculated by the cosine similarity formula, and multiple similarity calculation results are obtained. The cosine similarity formula is as follows:
    Figure PCTCN2019117714-appb-100001
    Figure PCTCN2019117714-appb-100001
    其中,n(A)表示顾客信息中包含的信息的类型数量,n(B)表示已交易顾客信息中包含的信息的类型数量,n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量,K为相似度计算结果。Among them, n(A) represents the number of types of information contained in the customer information, n(B) represents the number of types of information contained in the customer information that has been traded, and n(A∩B) represents that the customer information is the same as that of the customer information that has been traded The amount of information, K is the similarity calculation result.
  4. 如权利要求1所述的新零售模式下的商品导购方法,其中,在所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店的步骤之前,还包括:The method of shopping guide for goods under the new retail mode according to claim 1, wherein, before the step of obtaining the location information reported by the customer terminal and determining whether the customer terminal is located in the target physical store according to the location information, the method further comprises :
    获取历史交易记录,所述历史交易记录包括产品名称及所述产品名称对应的已交易顾客信息;Acquiring historical transaction records, the historical transaction records including the product name and the transaction customer information corresponding to the product name;
    计算所述已交易顾客信息对应的特征值,并将所述特征值代入预测函数公式,得到多个预测函数;Calculate the feature value corresponding to the transaction customer information, and substitute the feature value into the prediction function formula to obtain multiple prediction functions;
    对所述多个预测函数进行迭代求解,得到所述产品名称对应的预测模型;Iteratively solving the multiple prediction functions to obtain a prediction model corresponding to the product name;
    所述预测函数公式如下:The prediction function formula is as follows:
    Figure PCTCN2019117714-appb-100002
    Figure PCTCN2019117714-appb-100002
    其中,
    Figure PCTCN2019117714-appb-100003
    θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
    among them,
    Figure PCTCN2019117714-appb-100003
    θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
  5. 如权利要求4所述的新零售模式下的商品导购方法,其中,所述若所述最大相识度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果的步骤包括:The method of shopping guide for goods under the new retail mode according to claim 4, wherein, if the calculation result of the maximum acquaintance degree is less than a preset threshold, the customer information is input into a preset prediction model to obtain The steps of product recommendation results for customer information include:
    若所述最大相识度计算结果小于预设阈值,则计算所述顾客信息对应的特征值,将所述特征值分别输入各个产品对应的预测模型,得到若干输出值;If the calculation result of the maximum acquaintance degree is less than the preset threshold, calculate the characteristic value corresponding to the customer information, and input the characteristic value into the prediction model corresponding to each product to obtain several output values;
    选取大于或等于预设概率值的目标输出值,基于所述目标输出值得到针对所述顾客信息的产品推荐结果。A target output value greater than or equal to a preset probability value is selected, and a product recommendation result for the customer information is obtained based on the target output value.
  6. 如权利要求1所述的新零售模式下的商品导购方法,其中,在所述获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤之前,还包括:The method of shopping guide for goods under the new retail mode according to claim 1, wherein the face image reported by the customer terminal is acquired, and the face image and the product recommendation result are sent to the target Before the steps of the sales terminal corresponding to the physical store, it also includes:
    获取所述目标实体店的产品列表;Obtaining a product list of the target physical store;
    检测所述产品推荐结果是否存在于所述产品列表中;Detecting whether the product recommendation result exists in the product list;
    若所述产品推荐结果存在于所述产品列表中,则执行所述获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤。If the product recommendation result exists in the product list, execute the acquisition of the face image reported by the customer terminal, and send the face image and the product recommendation result to the target physical store. The steps of the point-of-sale.
  7. 如权利要求1至6中任一项所述的新零售模式下的商品导购方法,其中,所述将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤包括:The merchandise shopping guide method under the new retail mode according to any one of claims 1 to 6, wherein said sending said face image and said product recommendation result to the sales terminal corresponding to said target physical store The steps include:
    获取所述目标实体店对应的各个销售终端的状态信息;Acquiring status information of each sales terminal corresponding to the target physical store;
    基于所述状态信息确定状态为空闲的目标销售终端;Determining the target sales terminal whose status is idle based on the status information;
    将所述人脸图像以及所述产品推荐结果发送至所述目标销售终端。Sending the face image and the product recommendation result to the target sales terminal.
  8. 一种新零售模式下的商品导购装置,所述新零售模式下的商品导购装置包括:A merchandise shopping guide device in a new retail mode. The merchandise shopping guide device in a new retail mode includes:
    位置判断模块,用于获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;The location judgment module is used to obtain the location information reported by the customer terminal, and determine whether the customer terminal is located in the target physical store according to the location information;
    顾客信息获取模块,用于若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;A customer information acquisition module, configured to acquire customer information reported by the customer terminal if the customer terminal is located in a target physical store;
    计算模块,用于计算所述顾客信息与历史交易记录中存储的各个已交易 顾客信息的相似度,得到多个相似度计算结果;The calculation module is used to calculate the similarity between the customer information and the transactional customer information stored in the historical transaction records to obtain multiple similarity calculation results;
    检测模块,用于从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;The detection module is configured to determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
    预测模块,用于若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;A prediction module, configured to input the customer information into a preset prediction model if the maximum similarity calculation result is less than a preset threshold, to obtain a product recommendation result for the customer information;
    推送模块,用于获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。The push module is configured to obtain the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  9. 一种计算机设备,其中,所述计算机设备包括存储器和处理器;A computer device, wherein the computer device includes a memory and a processor;
    所述存储器用于存储计算机程序;The memory is used to store a computer program;
    所述处理器,用于执行所述计算机程序并在执行所述计算机程序时实现如下步骤:The processor is configured to execute the computer program and implement the following steps when the computer program is executed:
    获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;Acquiring the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information;
    若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;If the customer terminal is located in the target physical store, acquiring customer information reported by the customer terminal;
    计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results;
    从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
    若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
    获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Acquire the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  10. 如权利要求9所述的计算机设备,其中,所述处理器在实现所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店时,具体实现:8. The computer device according to claim 9, wherein the processor implements the acquisition of the location information reported by the customer terminal, and determines whether the customer terminal is located in the target physical store according to the location information, and specifically implements:
    获取顾客终端上报的位置信息,计算所述位置信息与各个实体店位置信息的距离,得到多个距离计算结果;Acquiring the location information reported by the customer terminal, calculating the distance between the location information and the location information of each physical store, and obtaining multiple distance calculation results;
    确定所述多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果;Determine whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results;
    若所述多个距离计算结果中存在一个小于或等于预设距离的目标计算结果,则确定所述顾客终端位于所述目标计算结果对应的目标实体店。If there is a target calculation result less than or equal to the preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
  11. 如权利要求9所述的计算机设备,其中,所述处理器在实现所述计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果时,具体实现:9. The computer device according to claim 9, wherein the processor realizes the calculation of the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results, Implementation:
    获取历史交易记录中存储的各个已交易顾客信息;Obtain each customer's information that has been traded stored in historical transaction records;
    通过余弦相似度公式计算所述顾客信息与所述各个已交易顾客信息的相似度,得到多个相似度计算结果,所述余弦相似度公式如下:The similarity between the customer information and the transaction customer information is calculated by the cosine similarity formula, and multiple similarity calculation results are obtained. The cosine similarity formula is as follows:
    Figure PCTCN2019117714-appb-100004
    Figure PCTCN2019117714-appb-100004
    其中,n(A)表示顾客信息中包含的信息的类型数量,n(B)表示已交易顾客信息中包含的信息的类型数量,n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量,K为相似度计算结果。Among them, n(A) represents the number of types of information contained in the customer information, n(B) represents the number of types of information contained in the customer information that has been traded, and n(A∩B) represents that the customer information is the same as that of the customer information that has been traded The amount of information, K is the similarity calculation result.
  12. 如权利要求9所述的计算机设备,其中,所述处理器在实现所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店之前,用于实现:9. The computer device according to claim 9, wherein the processor is configured to implement the acquisition of the location information reported by the customer terminal, and determine whether the customer terminal is located in front of the target physical store according to the location information, to achieve:
    获取历史交易记录,所述历史交易记录包括产品名称及所述产品名称对应的已交易顾客信息;Acquiring historical transaction records, the historical transaction records including the product name and the transaction customer information corresponding to the product name;
    计算所述已交易顾客信息对应的特征值,并将所述特征值代入预测函数公式,得到多个预测函数;Calculate the feature value corresponding to the transaction customer information, and substitute the feature value into the prediction function formula to obtain multiple prediction functions;
    对所述多个预测函数进行迭代求解,得到所述产品名称对应的预测模型;Iteratively solving the multiple prediction functions to obtain a prediction model corresponding to the product name;
    所述预测函数公式如下:The prediction function formula is as follows:
    Figure PCTCN2019117714-appb-100005
    Figure PCTCN2019117714-appb-100005
    其中,
    Figure PCTCN2019117714-appb-100006
    θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
    among them,
    Figure PCTCN2019117714-appb-100006
    θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
  13. 如权利要求12所述的计算机设备,其中,所述处理器在实现所述若所述最大相识度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果时,具体实现:The computer device according to claim 12, wherein the processor realizes that if the calculation result of the maximum acquaintance degree is less than a preset threshold, the customer information is input into a preset prediction model to obtain When the result of product recommendation based on customer information, the specific realization:
    若所述最大相识度计算结果小于预设阈值,则计算所述顾客信息对应的特征值,将所述特征值分别输入各个产品对应的预测模型,得到若干输出值;If the calculation result of the maximum acquaintance degree is less than the preset threshold, calculate the characteristic value corresponding to the customer information, and input the characteristic value into the prediction model corresponding to each product to obtain several output values;
    选取大于或等于预设概率值的目标输出值,基于所述目标输出值得到针对所述顾客信息的产品推荐结果。A target output value greater than or equal to a preset probability value is selected, and a product recommendation result for the customer information is obtained based on the target output value.
  14. 如权利要求9所述的计算机设备,其中,所述处理器在实现所述获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端之前,用于实现:The computer device according to claim 9, wherein the processor implements the acquisition of the face image reported by the customer terminal, and sends the face image and the product recommendation result to the target entity Before the sales terminal corresponding to the store, it is used to realize:
    获取所述目标实体店的产品列表;Obtaining a product list of the target physical store;
    检测所述产品推荐结果是否存在于所述产品列表中;Detecting whether the product recommendation result exists in the product list;
    若所述产品推荐结果存在于所述产品列表中,则执行所述获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端的步骤。If the product recommendation result exists in the product list, execute the acquisition of the face image reported by the customer terminal, and send the face image and the product recommendation result to the target physical store. The steps of the point-of-sale.
  15. 如权利要求9至14任一项所述的计算机设备,其中,所述处理器在实现所述将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端时,具体实现:The computer device according to any one of claims 9 to 14, wherein when the processor realizes the sending of the face image and the product recommendation result to the sales terminal corresponding to the target physical store, Implementation:
    获取所述目标实体店对应的各个销售终端的状态信息;Acquiring status information of each sales terminal corresponding to the target physical store;
    基于所述状态信息确定状态为空闲的目标销售终端;Determining the target sales terminal whose status is idle based on the status information;
    将所述人脸图像以及所述产品推荐结果发送至所述目标销售终端。Sending the face image and the product recommendation result to the target sales terminal.
  16. 一种计算机可读存储介质,其中,所述计算机可读存储介质上存储有新零售模式下的商品导购程序,所述新零售模式下的商品导购程序被处理器执行时实现如下步骤:A computer-readable storage medium, wherein a product shopping guide program in a new retail mode is stored on the computer-readable storage medium, and the following steps are implemented when the product shopping guide program in a new retail mode is executed by a processor:
    获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店;Acquiring the location information reported by the customer terminal, and determining whether the customer terminal is located in the target physical store according to the location information;
    若所述顾客终端位于目标实体店,则获取所述顾客终端上报的顾客信息;If the customer terminal is located in the target physical store, acquiring customer information reported by the customer terminal;
    计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果;Calculate the similarity between the customer information and the transactional customer information stored in the historical transaction record to obtain multiple similarity calculation results;
    从所述多个相似度计算结果中确定最大相似度计算结果,并判断所述最大相似度计算结果是否小于预设阈值;Determine a maximum similarity calculation result from the multiple similarity calculation results, and determine whether the maximum similarity calculation result is less than a preset threshold;
    若所述最大相似度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果;If the maximum similarity calculation result is less than a preset threshold, input the customer information into a preset prediction model to obtain a product recommendation result for the customer information;
    获取所述顾客终端上报的人脸图像,并将所述人脸图像以及所述产品推荐结果发送至所述目标实体店对应的销售终端。Acquire the face image reported by the customer terminal, and send the face image and the product recommendation result to the sales terminal corresponding to the target physical store.
  17. 如权利要求16所述的计算机可读存储介质,其中,所述处理器在实现所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店时,具体实现:The computer-readable storage medium according to claim 16, wherein the processor implements the acquisition of the location information reported by the customer terminal and determines whether the customer terminal is located in the target physical store according to the location information. :
    获取顾客终端上报的位置信息,计算所述位置信息与各个实体店位置信息的距离,得到多个距离计算结果;Acquiring the location information reported by the customer terminal, calculating the distance between the location information and the location information of each physical store, and obtaining multiple distance calculation results;
    确定所述多个距离计算结果中是否存在一个小于或等于预设距离的目标计算结果;Determine whether there is a target calculation result less than or equal to a preset distance among the multiple distance calculation results;
    若所述多个距离计算结果中存在一个小于或等于预设距离的目标计算结果,则确定所述顾客终端位于所述目标计算结果对应的目标实体店。If there is a target calculation result less than or equal to the preset distance among the multiple distance calculation results, it is determined that the customer terminal is located in the target physical store corresponding to the target calculation result.
  18. 如权利要求16所述的计算机可读存储介质,其中,所述处理器在实现所述计算所述顾客信息与历史交易记录中存储的各个已交易顾客信息的相似度,得到多个相似度计算结果时,具体实现:The computer-readable storage medium according to claim 16, wherein the processor obtains a plurality of similarity calculations after calculating the similarity between the customer information and each transaction customer information stored in the historical transaction record. As a result, the specific realization:
    获取历史交易记录中存储的各个已交易顾客信息;Obtain each customer's information that has been traded stored in historical transaction records;
    通过余弦相似度公式计算所述顾客信息与所述各个已交易顾客信息的相似度,得到多个相似度计算结果,所述余弦相似度公式如下:The similarity between the customer information and the transaction customer information is calculated by the cosine similarity formula, and multiple similarity calculation results are obtained. The cosine similarity formula is as follows:
    Figure PCTCN2019117714-appb-100007
    Figure PCTCN2019117714-appb-100007
    其中,n(A)表示顾客信息中包含的信息的类型数量,n(B)表示已交易顾客信息中包含的信息的类型数量,n(A∩B)表示顾客信息与已交易顾客信息中相同信息的数量,K为相似度计算结果。Among them, n(A) represents the number of types of information contained in the customer information, n(B) represents the number of types of information contained in the customer information that has been traded, and n(A∩B) represents that the customer information is the same as that of the customer information that has been traded The amount of information, K is the similarity calculation result.
  19. 如权利要求16所述的计算机可读存储介质,其中,所述处理器在实 现所述获取顾客终端上报的位置信息,根据所述位置信息确定所述顾客终端是否位于目标实体店之前,用于实现:The computer-readable storage medium according to claim 16, wherein the processor is configured to obtain the location information reported by the customer terminal and determine whether the customer terminal is located before the target physical store according to the location information. achieve:
    获取历史交易记录,所述历史交易记录包括产品名称及所述产品名称对应的已交易顾客信息;Acquiring historical transaction records, the historical transaction records including the product name and the transaction customer information corresponding to the product name;
    计算所述已交易顾客信息对应的特征值,并将所述特征值代入预测函数公式,得到多个预测函数;Calculate the feature value corresponding to the transaction customer information, and substitute the feature value into the prediction function formula to obtain multiple prediction functions;
    对所述多个预测函数进行迭代求解,得到所述产品名称对应的预测模型;Iteratively solving the multiple prediction functions to obtain a prediction model corresponding to the product name;
    所述预测函数公式如下:The prediction function formula is as follows:
    Figure PCTCN2019117714-appb-100008
    Figure PCTCN2019117714-appb-100008
    其中,
    Figure PCTCN2019117714-appb-100009
    θ i为已交易顾客信息i的权重值,x i为已交易顾客信息i对应的特征值,θ T=[θ 12,...,θ n],x=[x 1,x 2,...,x n],e为自然常数。
    among them,
    Figure PCTCN2019117714-appb-100009
    θ i is the weight value of the transaction customer information i, x i is the characteristic value corresponding to the transaction customer information i, θ T =[θ 12 ,...,θ n ], x=[x 1 ,x 2 ,...,x n ], e is a natural constant.
  20. 如权利要求19所述的计算机可读存储介质,其中,所述处理器在实现所述若所述最大相识度计算结果小于预设阈值,则将所述顾客信息输入预置的预测模型,得到针对所述顾客信息的产品推荐结果时,具体实现:The computer-readable storage medium according to claim 19, wherein the processor, after realizing that if the calculation result of the maximum acquaintance degree is less than a preset threshold, inputs the customer information into a preset prediction model to obtain When the result of product recommendation based on the customer information, the specific realization is as follows:
    若所述最大相识度计算结果小于预设阈值,则计算所述顾客信息对应的特征值,将所述特征值分别输入各个产品对应的预测模型,得到若干输出值;If the calculation result of the maximum acquaintance degree is less than the preset threshold, calculate the characteristic value corresponding to the customer information, and input the characteristic value into the prediction model corresponding to each product to obtain several output values;
    选取大于或等于预设概率值的目标输出值,基于所述目标输出值得到针对所述顾客信息的产品推荐结果。A target output value greater than or equal to a preset probability value is selected, and a product recommendation result for the customer information is obtained based on the target output value.
PCT/CN2019/117714 2019-09-06 2019-11-12 Shopping guide method and apparatus in new retail model, device and storage medium WO2021042541A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910844417.9A CN110751501B (en) 2019-09-06 2019-09-06 Commodity shopping guide method, device, equipment and storage medium
CN201910844417.9 2019-09-06

Publications (1)

Publication Number Publication Date
WO2021042541A1 true WO2021042541A1 (en) 2021-03-11

Family

ID=69276244

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117714 WO2021042541A1 (en) 2019-09-06 2019-11-12 Shopping guide method and apparatus in new retail model, device and storage medium

Country Status (2)

Country Link
CN (1) CN110751501B (en)
WO (1) WO2021042541A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113411381B (en) * 2021-06-02 2022-10-25 支付宝(杭州)信息技术有限公司 Method and system for pushing information to Internet of things equipment
CN113420677B (en) * 2021-06-25 2024-06-11 联仁健康医疗大数据科技股份有限公司 Method, device, electronic equipment and storage medium for determining reasonable image

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156942A (en) * 2011-04-08 2011-08-17 东华大学 RFID based method for recommending commodities
CN103903161A (en) * 2013-12-02 2014-07-02 奇易科技有限公司 Method and system with detecting, participating, payment processing and client rewarding functions
US20140214614A1 (en) * 2013-01-30 2014-07-31 Sap Ag Consultative online sale of business applications
CN107507017A (en) * 2017-07-07 2017-12-22 阿里巴巴集团控股有限公司 Shopping guide method and device under a kind of line
CN109034973A (en) * 2018-07-25 2018-12-18 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device, system and computer readable storage medium
CN110163666A (en) * 2019-05-06 2019-08-23 北京三快在线科技有限公司 A kind of method and device of commercial product recommending

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933595A (en) * 2015-05-22 2015-09-23 齐鲁工业大学 Collaborative filtering recommendation method based on Markov prediction model
CN109284413A (en) * 2018-09-07 2019-01-29 平安科技(深圳)有限公司 Method of Commodity Recommendation, device, equipment and storage medium based on recognition of face

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156942A (en) * 2011-04-08 2011-08-17 东华大学 RFID based method for recommending commodities
US20140214614A1 (en) * 2013-01-30 2014-07-31 Sap Ag Consultative online sale of business applications
CN103903161A (en) * 2013-12-02 2014-07-02 奇易科技有限公司 Method and system with detecting, participating, payment processing and client rewarding functions
CN107507017A (en) * 2017-07-07 2017-12-22 阿里巴巴集团控股有限公司 Shopping guide method and device under a kind of line
CN109034973A (en) * 2018-07-25 2018-12-18 北京京东尚科信息技术有限公司 Method of Commodity Recommendation, device, system and computer readable storage medium
CN110163666A (en) * 2019-05-06 2019-08-23 北京三快在线科技有限公司 A kind of method and device of commercial product recommending

Also Published As

Publication number Publication date
CN110751501A (en) 2020-02-04
CN110751501B (en) 2023-08-22

Similar Documents

Publication Publication Date Title
US20210073283A1 (en) Machine learning and prediction using graph communities
KR102012676B1 (en) Method, Apparatus and System for Recommending Contents
US10565525B2 (en) Collaborative filtering method, apparatus, server and storage medium in combination with time factor
WO2022100518A1 (en) User profile-based object recommendation method and device
US10402840B2 (en) Systems and methods for setting product prices
AU2014200389B2 (en) Behavior management and expense insight system
US20210150443A1 (en) Parity detection and recommendation system
US20220261591A1 (en) Data processing method and apparatus
US20210256445A1 (en) System and method for matching resource capacity with client resource needs
Gupta et al. Debiasing in-sample policy performance for small-data, large-scale optimization
US20200111027A1 (en) Systems and methods for providing recommendations based on seeded supervised learning
WO2021042541A1 (en) Shopping guide method and apparatus in new retail model, device and storage medium
US20120185476A1 (en) Multi-function searching and search-related tools and techniques for improved search results and enhanced analysis and decision-making
CN111144673A (en) Method, device and equipment for evaluating structure of organization personnel and computer readable medium
JP7318646B2 (en) Information processing device, information processing method, and program
CN110796520A (en) Commodity recommendation method and device, computing equipment and medium
US20210326910A1 (en) System and method for optimizing an observation campaign in response to observed real-world data
JP6970527B2 (en) Content selection method and content selection program
WO2022259512A1 (en) Business assistance device, business assistance method, and program
JP2004258762A (en) Action model creating method and creating device
JP7027606B1 (en) Information processing equipment, information processing methods and information processing programs
US11838170B1 (en) Messaging segmentation based on data flow informatics
CN112948691B (en) Method and device for calculating experience index of entity place
WO2022259511A1 (en) Business assistance device, business assistance method, and program
WO2024103649A1 (en) Image color recognition method and device, and image recommendation method and device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19943944

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19943944

Country of ref document: EP

Kind code of ref document: A1