CN116611875A - Recommendation method and system for predicting new products based on customer characteristics and behaviors - Google Patents
Recommendation method and system for predicting new products based on customer characteristics and behaviors Download PDFInfo
- Publication number
- CN116611875A CN116611875A CN202310784938.6A CN202310784938A CN116611875A CN 116611875 A CN116611875 A CN 116611875A CN 202310784938 A CN202310784938 A CN 202310784938A CN 116611875 A CN116611875 A CN 116611875A
- Authority
- CN
- China
- Prior art keywords
- customer
- customers
- new
- new product
- new products
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000006399 behavior Effects 0.000 title claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000008921 facial expression Effects 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000001815 facial effect Effects 0.000 abstract description 2
- 239000013598 vector Substances 0.000 description 21
- 238000012360 testing method Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Computer Interaction (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a recommendation method and a recommendation system for predicting new products based on customer characteristics and behaviors, relates to the technical field of consumption data analysis, and solves the technical problems that in the traditional retail consumption field, online physical stores cannot accurately popularize new products for customers and cannot completely know consumption preference of consumption. The method comprises the following steps: 1. and (3) data acquisition: 2. customer behavior prediction: 3. and 4, recommending new products, and updating a history record. The invention classifies the customers by collecting the facial information and wearing of the customers and combining the speaking voice of the customers, judges the receiving degree of the new products for the customers with different classifications, provides the popularization of the new products for the customers, and improves the popularization efficiency of the new products.
Description
Technical Field
The invention relates to the technical field of consumption data analysis, in particular to a recommendation method and a recommendation system for predicting new products based on customer characteristics and behaviors.
Background
The existing selling mode of the off-line physical store basically adopts the traditional selling mode, the commodity is displayed through a counter or a display position mode, and a customer selects the commodity of the core instrument by himself. The selling form of the physical store cannot grasp the consumption information of the customer and analyze the consumption behavior of the customer, so that in the traditional retail consumption field, the off-line physical store cannot accurately popularize new products for the customer and cannot fully understand the consumption preference of the customer. In the popularization process of the product, great obstruction can be caused, and the sales and popularization of the new product on the market are not facilitated.
If the receiving degree of the customer to the new product can be judged through the appearance characteristics and the speaking characteristics of the customer, the new product can be promoted in a targeted manner, and the promotion efficiency of the new product can be improved.
Disclosure of Invention
The invention provides a new technical scheme of a recommending method and a system for predicting new products based on customer characteristics and behaviors, and solves the technical problems that in the traditional retail consumption field, online physical stores cannot accurately popularize new products for customers and cannot completely know consumption preference of consumption.
A recommendation method for predicting new products based on customer characteristics and behaviors, the method comprising the steps of:
step one: collecting one or more characteristics of physical features, facial expressions and dialogue information of a customer, and collecting the geographic position of a retail terminal; meanwhile, judging whether the customer has a purchasing experience or not through the characteristics and the history record of the retail terminal; presenting the commodity, and acquiring patterns, colors and packages focused by customers; reading and writing the body appearance characteristics and/or facial expressions of the customers into a face database, calculating and generating a face recognition matrix, two-dimensionally projecting a feature space of the face recognition matrix, and determining recognized sample types;
step two: predicting the gender, age and occupation of the customer by using an image recognition algorithm according to the characteristic information acquired in the first step; evaluating the consumption preference of the customer and the acceptance degree of the new product according to the prediction result, the historical purchase record and the attention information;
step three: combining brand positioning, price positioning, sales area positioning and target crowd positioning of the new product, matching with consumer preference of customers and acceptance degree of the new product, arranging new product information from high to low according to the matching degree, and displaying on a retail terminal for customers to select;
step four: and updating the history record of the retail terminal to realize a recommendation method for predicting new products based on the characteristics and behaviors of the customers.
Preferably, the first category is whether there is an over-purchase experience.
Preferably, the evaluation method of the second step includes: classifying the receiving degree of the customer on the new product into a plurality of grades through the physical characteristics and the facial expression of the customer; and according to the prediction result, evaluating the consumption preference and the acceptance of the new product of the customer by combining the dialogue information, the historical data and the package, the pattern and the color of the commodity of the customer.
Preferably, the third step includes: classifying the customers according to the calculated customer new product receiving degree index model in the second step, and popularizing different new products for different customers according to the new product receiving degree; and (3) corresponding the new customer receiving degree index model with the new type of the new product, and correspondingly popularizing new products for customers with high customer receiving degree indexes, so as to accurately popularizing new products with different updating degrees for the customers.
A new product recommendation system based on customer identification and behavior prediction, said system comprising:
the intelligent selling terminal is used for commodity popularization and selling;
the data transmission module is used for bidirectionally transmitting the data of the intelligent vending terminal and the data of the background server;
the background server is used for storing the customer data acquired by the intelligent vending terminal and calculating and matching the policy selection model;
the intelligent selling terminal is connected with the background server through the data transmission module.
Preferably, the background server adopts a cloud computing server.
Preferably, the background server includes: a processor and a memory; the memory has stored thereon computer readable instructions which when executed by the processor implement the new product recommendation method based on customer identification and behavior prediction.
The beneficial effects are that: according to the invention, the intelligent vending terminal is used for collecting the information of the customer, and correspondingly processing and calculating the information, so that a set of product popularization method is established, the receiving degree of the new product of the customer can be estimated more accurately, the new product is promoted for the customer, and the win-win purpose of the customer and the new product is achieved.
Other features of the present invention and its advantages will become apparent from the following detailed description of exemplary embodiments of the invention, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flowchart of a recommendation method for predicting new products based on customer characteristics and behavior;
fig. 2 is a flow chart of face recognition according to the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
As shown in fig. 1, a recommendation method for predicting new products based on customer characteristics and behaviors includes the following steps:
step one: collecting one or more characteristics of physical characteristics of a customer, such as hairstyles, wearing, sexes and the like, facial expressions, whether purchase records exist or not and dialogue information through a camera arranged on the intelligent vending terminal, and collecting the geographic position of the retail terminal; meanwhile, judging whether the customer has a purchasing experience or not through the characteristics and the history record of the retail terminal; presenting the commodity, and acquiring patterns, colors and packages focused by customers; reading and writing the body appearance characteristics and/or facial expressions of the customers into a face database, calculating and generating a face recognition matrix, two-dimensionally projecting a feature space of the face recognition matrix, and determining recognized sample types; i.e., determine if the customer has a purchasing experience.
The method comprises the following steps: step one-A: as shown in fig. 2, the face database is a training set, and the set of sample images to be compared, which are read from and written into the face database, is a test set, and the test set is compared with the training set to obtain a result, and the normalized image presents n×n columns, which are connected to form a 2N-dimensional vector value. The 2N-dimensional vector value, which can be regarded as a point in the 2N-dimensional space, can be described by a low-dimensional subspace by a K-L transformation.
The K-L transform generator matrix is computed to obtain the values and vectors of the image itself. It is assumed that the face database contains images X represented by vectors 1 ,X 2 ,...X N (vector dimension is defined as L), then the average facial image is as follows:
the average difference for each image is thus obtained:
X i ′=X i -X ave ,i=1,2,...,N (2);
covariance matrices may be calculated as follows:
calculating eigenvalues lambda of covariance matrix C k And corresponding feature vector mu k . In order to reduce the amount of computation, the average difference of each image is formed into a matrix as follows:
X′=[X 1 ′,X′ 2 ,...,X′ N ] (4);
then formula (3) can be written as formula (5):
to simplify the calculation, phi is calculated j Thereafter, phi' j Can be obtained by the formula (6), wherein Φ j For image vector X 1 ,X 2 ,...X N Covariance matrix of phi' j Is phi j Is a rank matrix of (a).
Step one-B: from the eigenvector mu k Formed intoThe vector space can represent main characteristic information of the face image, and the average difference of all N images in the face image library is projected to the vector space to obtain respective three-dimensional projection vectors Y 1 ,Y 2 ,...,Y N As shown in formulas (7) and (8):
(Y i ) T =[y 1i ,y 2i ,...y Mi ],i=1,2,...,N (7),
y is a two-dimensional projection vector of the mean difference in the face image in the vector space.
y μ =(μ j ) T X j ′,j=1,2,...,M (8),
μ j Is a feature vector of the three-dimensional projection vector y.
For a face image to be identified, calculating projection vectors of the face image and K-order of a covariance matrix C:
p j =(μ j ) T (I i -X ave ),j=1,2,...,M (9)。
through projection vectors p corresponding to N face images in a face database j And comparing, and completing identification according to the distance measurement criterion.
The test image is compared with the training image to determine the class of the sample. Different classifiers may be used herein to classify and select the L1 paradigm.
The addition of the differences between the absolute values of the pixels is also referred to as a summation criterion. The L1 distance formula is:
wherein (x) i ,y i ) Refers to a pixel point of a face image.
Step one-C: training and identifying in a test set of the algorithm; in the first stage, in order to project face information into a feature vector space, an N-dimensional vector Y needs to be obtained i (i=1, 2, N) distance threshold θ c The definition is as follows:
in the face recognition process, the image to be recognized needs to be projected into a vector space of the feature, and the projection vector P and the distance between the projection vector P and each face set can be obtained after projectionFace recognition is carried out by adopting an Euclidean distance method, and classification rules are as follows:
1) If e i >θ c The input image is not a face image; no new popularization is performed.
2) If e i <θ c ,∨k,e i >θ c The input image contains an unknown face; the unknown face image indicates that the customer consumes for the first time, and then the consumer records, the face image and the voice information of the customer are subjected to new customer file data, so that the customer can be conveniently promoted in new products.
3) If e i <θ c ,e i =min{θ c The input image is the face of the kth person in the face database. After the face image is matched with the face image when the previous customer purchases, the previous data of the customer is called, and the commodity data purchased at this time is stored in the previous data file so as to facilitate the subsequent popularization of new products.
Step one-D: the dialogue information between the intelligent selling terminal and the customer is collected through the recording equipment, such as inquiring what cigarettes the opponent wants to buy and the answer of the opponent, and the customer preference is obtained through the voice recognition algorithm; and storing the acquired voice information in one-to-one correspondence with the recognized face images to form a specific database of each customer.
Step one-E: and (3) regularly arranging commodities on the goods shelf to acquire information such as packages, patterns, colors and the like which are focused by customers.
Step two: predicting the sex of the customer according to the characteristic information acquired in the first step by utilizing an image recognition algorithm, wherein the sex of the customer is predicted by combining data such as the length or the length of a hairstyle of the customer, clothes, caps, whether glasses are worn on the face, whether wrinkles, beards, expressions and the like, and the age group is in teenagers, young people, middle-aged people or old people, and the occupation is workers, peasants, students, white collars or elites; the receiving degree of the new products by the customers is divided into 5 grades, and grade 1 represents the old, workers and farmers; class 2 represents middle-aged office workers 40-60 years old; grade 3 represents the young office workers in the age group of 30-40 years old; grade 4 represents the young office workers 20-30 years old; grade 5 represents student population, adolescent population. If the customer is teenager and student, the customer's receiving level is at most 5, indicating that they prefer to receive the new product, and if the customer is elderly, worker, farmer, etc., the customer's receiving level is at least 1, indicating that they are not willing to try the new product. Evaluating the consumption preference of the customer and the acceptance degree of the new product according to the prediction result, the historical purchase record and the attention information; the higher the index of receiving the new product of the customer relative to the ideal state, the higher the achievement of receiving the new product; in addition to the new product receiving degree comprehensive condition being expressed as an index, each level index of the new product receiving degree can be expressed by an index, and the new product receiving degree index model of the customer is obtained as follows:
ccbvix—receiving a degree index for a new customer;
1-the lowest score of the new reception level index;
5-highest score of the new reception degree index;
W bi -the weight of the ith secondary index of the (e=1, 2,3,4,5; i= 4,4,4,3,3);
-means of index measure scores;
b-serial number of the second level index under the xth first level index;
and inputting the calculated receiving degree of the new customer into a system for storage, and taking the receiving degree as the basis of product popularization. And judging whether the customer is a guest or a acquaintance according to the history record, counting the purchase frequency, and acquiring the data of brands, specifications, prices, packages and the like purchased by the customer if the history record exists, so that the similar new products can be recommended conveniently.
Step three: combining brand positioning, price positioning, sales area positioning and target crowd positioning of the new product, matching with consumer preference of customers and acceptance degree of the new product, arranging new product information from high to low according to the matching degree, and displaying on a retail terminal for customers to select; the method comprises the following steps:
step three-A: the data is subjected to level differentiation processing, and the difference between the maximum value and the minimum value of the data series is used for respectively removing the difference between each data and the minimum value in the data series, and the data is classified into a dimensionless data formula of a (0, 1) interval, wherein the dimensionless data formula is as follows:
wherein g t (i) Is dimensionless data, y t (i) Miny is the original data of the ith object t (i) Is the minimum value of the ith object, max (y t (i) I) is the maximum value of the ith object, m is an object element, and t is the number of data objects;
step three-B: the data processed in the step three-A are classified by adopting a K-means clustering algorithm;
step three-C: obtaining a first class of new product receiving degree 4-5, a second class of new product receiving degree 2-3 and a third class of new product receiving degree 1 through k-means clustering of a tool box of MATLAB;
step three-D: and (3) corresponding the new product receiving degree index model of the customer with the new product type, correspondingly popularizing new products by customers with high new product receiving degree index, and analogizing sequentially to accurately popularizing new products with different updating degrees for the customers.
Step four: the history of the retail terminal is updated, and the selection result (information such as brand, specification, price, package, current position, etc.) of the customer is written into the history. Therefore, when the customer purchases next time, the receiving degree of the new product of the customer can be further determined according to the historical purchasing record of the customer, and the recommendation method for predicting the new product based on the characteristics and behaviors of the customer is realized.
A new product recommendation system based on customer identification and behavior prediction, said system comprising:
the intelligent selling terminal is used for commodity popularization and selling;
the data transmission module is used for bidirectionally transmitting the data of the intelligent vending terminal and the data of the background server;
the background server is used for storing the customer data acquired by the intelligent vending terminal and calculating and matching the policy selection model;
the intelligent selling terminal is connected with the background server through the data transmission module.
The background server adopts a cloud computing server. The background server comprises: a processor and a memory; the memory has stored thereon computer readable instructions which when executed by the processor implement the new product recommendation method based on customer identification and behavior prediction.
The intelligent vending terminal is a terminal capable of automatically vending commodities, a customer can purchase the commodities on the terminal, and the intelligent vending terminal records and collects consumption information of the customer during purchase.
The wireless data transmission module adopts a mode that wifi and internet combine, and the terminal is sold to intelligence first through wifi with data transmission to the router, is passing through the router and is transmitting data to the backstage server through the internet. The background server adopts a cloud computing server, and the cloud computing server can store and compute data at the cloud, so that high price and high cost caused by purchasing the entity server are avoided. And can be better for deploying the intelligent selling terminal in different places of the whole country and carry out data communication.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (7)
1. A recommendation method for predicting new products based on customer characteristics and behaviors is characterized by comprising the following steps:
step one: collecting one or more characteristics of physical features, facial expressions and dialogue information of a customer, and collecting the geographic position of a retail terminal; meanwhile, judging whether the customer has a purchasing experience or not through the characteristics and the history record of the retail terminal; presenting the commodity, and acquiring patterns, colors and packages focused by customers; reading and writing the body appearance characteristics and/or facial expressions of the customers into a face database, calculating and generating a face recognition matrix, two-dimensionally projecting a feature space of the face recognition matrix, and determining recognized sample types;
step two: predicting the gender, age and occupation of the customer by using an image recognition algorithm according to the characteristic information acquired in the first step; evaluating the consumption preference of the customer and the acceptance degree of the new product according to the prediction result, the historical purchase record and the attention information;
step three: combining brand positioning, price positioning, sales area positioning and target crowd positioning of the new product, matching with consumer preference of customers and acceptance degree of the new product, arranging new product information from high to low according to the matching degree, and displaying on a retail terminal for customers to select;
step four: and updating the history record of the retail terminal to realize a recommendation method for predicting new products based on the characteristics and behaviors of the customers.
2. The method of claim 1, wherein the category of step one is whether there is a purchase history.
3. The recommendation method for predicting new products based on customer characteristics and behaviors of claim 1, wherein the evaluation method of step two comprises: classifying the receiving degree of the customer on the new product into a plurality of grades through the physical characteristics and the facial expression of the customer; and according to the prediction result, evaluating the consumption preference and the acceptance of the new product of the customer by combining the dialogue information, the historical data and the package, the pattern and the color of the commodity of the customer.
4. The method for recommending new goods based on customer characteristics and behavior prediction according to claim 1, wherein said step three comprises: classifying the customers according to the calculated customer new product receiving degree index model in the second step, and popularizing different new products for different customers according to the new product receiving degree; and (3) corresponding the new customer receiving degree index model with the new type of the new product, and correspondingly popularizing new products for customers with high customer receiving degree indexes, so as to accurately popularizing new products with different updating degrees for the customers.
5. A system for predicting new product recommendation based on customer characteristics and behavior in accordance with any one of claims 1-4, wherein said system comprises:
the intelligent selling terminal is used for commodity popularization and selling;
the data transmission module is used for bidirectionally transmitting the data of the intelligent vending terminal and the data of the background server;
the background server is used for storing the customer data acquired by the intelligent vending terminal and calculating and matching the policy selection model;
the intelligent selling terminal is connected with the background server through the data transmission module.
6. The recommendation system for predicting new products based on customer characteristics and behavior according to claim 5, wherein the background server employs a cloud computing server.
7. The recommendation system for predicting new items based on customer characteristics and behavior in accordance with claim 5, wherein said backend server comprises: a processor and a memory; the memory has stored thereon computer readable instructions which when executed by the processor implement the new product recommendation method based on customer identification and behavior prediction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310784938.6A CN116611875A (en) | 2023-06-29 | 2023-06-29 | Recommendation method and system for predicting new products based on customer characteristics and behaviors |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310784938.6A CN116611875A (en) | 2023-06-29 | 2023-06-29 | Recommendation method and system for predicting new products based on customer characteristics and behaviors |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116611875A true CN116611875A (en) | 2023-08-18 |
Family
ID=87674907
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310784938.6A Pending CN116611875A (en) | 2023-06-29 | 2023-06-29 | Recommendation method and system for predicting new products based on customer characteristics and behaviors |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116611875A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116823337A (en) * | 2023-08-24 | 2023-09-29 | 北京信索咨询股份有限公司 | Product sales prediction system based on big data analysis user habit |
-
2023
- 2023-06-29 CN CN202310784938.6A patent/CN116611875A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116823337A (en) * | 2023-08-24 | 2023-09-29 | 北京信索咨询股份有限公司 | Product sales prediction system based on big data analysis user habit |
CN116823337B (en) * | 2023-08-24 | 2023-11-21 | 北京信索咨询股份有限公司 | Product sales prediction system based on big data analysis user habit |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Roberts et al. | Development and testing of a model of consideration set composition | |
Baesens et al. | Bayesian neural network learning for repeat purchase modelling in direct marketing | |
Prati et al. | A survey on graphical methods for classification predictive performance evaluation | |
US20140279263A1 (en) | Systems and methods for providing product recommendations | |
CN102855268A (en) | Image ranking method and system based on attribute correlation | |
US20120296900A1 (en) | Adaptively learning a similarity model | |
US11676194B2 (en) | Faceted item recommendation system | |
CN112488863B (en) | Dangerous seed recommendation method and related equipment in user cold start scene | |
US20120296776A1 (en) | Adaptive interactive search | |
CN111028029B (en) | Off-line commodity recommendation method and device and electronic equipment | |
CN116611875A (en) | Recommendation method and system for predicting new products based on customer characteristics and behaviors | |
CN112561543A (en) | E-commerce platform false transaction order monitoring method and system based on full-period logistics data analysis and cloud server | |
JP2018169752A (en) | Product recognition system, learned model, and product recognition method | |
CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
CN115526652A (en) | Client loss early warning method and system based on machine learning | |
Holder et al. | Visual siamese clustering for cosmetic product recommendation | |
Aktaş et al. | Comparative unsupervised clustering approaches for customer segmentation | |
CN111340566B (en) | Commodity classification method and device, electronic equipment and storage medium | |
CN115271884A (en) | Multi-source data-based commodity selection method and device and electronic equipment | |
Akshya et al. | Efficient Net-based Expert System for Personalized Facial Skincare Recommendations | |
CN112561596A (en) | Commodity recommendation method and device | |
KR20210112258A (en) | Method and apparatus for providing personalized recommendation service for offline purchase | |
Srikanth et al. | Forecasting the Prices using Machine Learning Techniques: Special Reference to used Mobile Phones | |
CN112488355A (en) | Method and device for predicting user rating based on graph neural network | |
CN111339991A (en) | Human body attribute identification method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |