CN112837079B - Commodity sales predicting method, commodity sales predicting device and computer equipment - Google Patents
Commodity sales predicting method, commodity sales predicting device and computer equipment Download PDFInfo
- Publication number
- CN112837079B CN112837079B CN201911153294.0A CN201911153294A CN112837079B CN 112837079 B CN112837079 B CN 112837079B CN 201911153294 A CN201911153294 A CN 201911153294A CN 112837079 B CN112837079 B CN 112837079B
- Authority
- CN
- China
- Prior art keywords
- video
- target user
- peripheral
- user
- purchasing
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a commodity sales prediction method, a commodity sales prediction device, computer equipment and a readable storage medium, and belongs to the technical field of data prediction. The commodity sales predicting method comprises the following steps: the method comprises the steps of obtaining behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video; acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information; and calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video. The method and the device can improve the accuracy of commodity sales estimation.
Description
Technical Field
The present invention relates to the field of data prediction technologies, and in particular, to a method, an apparatus, and a computer device for predicting sales of a commodity.
Background
In the prior art, a merchant usually performs goods feeding, goods replenishment and the like on goods in a manner of manually predicting goods sales, for example, a store length predicts goods sales for a period of time in the future according to recent goods sales, and supplements goods on inventory of goods according to the goods sales, however, the manner of manually predicting is blind.
Thus, to get rid of this blindness, some merchants have adopted a more intelligent way to conduct sales predictions. For example, when a merchant estimates sales of a commodity around a certain work, the sales of the periphery of the work is usually estimated by calculating overall indexes such as the play amount, the number of viewers, and the number of attention of the certain work. For example, the play amount, the number of viewers, the number of attention are weighted and summed to be the popularity of the senna, and then sales around the work are estimated according to the popularity, etc.
However, the overall index of the works, such as the playing quantity, has positive correlation with the sales of the works, but the correlation coefficient is not fixed due to different types of the works, and the estimated accuracy can be influenced only by estimating the correlation coefficient through an empirical value.
Disclosure of Invention
In view of the above, a method, a device, a computer device and a computer readable storage medium for predicting sales of commodity are provided, so as to solve the problem that the estimated sales are inaccurate when the existing method is used for estimating the sales of commodity.
The invention provides a commodity sales predicting method, which comprises the following steps:
acquiring behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video;
acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information;
and calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video.
Optionally, the calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video comprises:
and taking the sum of probability values of all target users purchasing the peripheral products as sales of the peripheral products.
Optionally, the commodity sales predicting method further includes:
acquiring a training sample data set, wherein each training sample data set comprises behavior data of a user when watching a video, basic information of the user, basic information of the video and consumption information of the user on related peripheral products of the video;
and inputting the training sample data set into a preset machine learning model for training until the loss function of the machine learning model is converged, ending the training, and obtaining the commodity sales prediction model.
Optionally, the calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video further comprises:
dividing the probability value of the target user purchasing the peripheral product into preset interval sections;
counting the number of target users contained in each interval;
obtaining a mapping relation between each interval and the real purchase rate;
and calculating sales of the peripheral products according to the mapping relation and the number of target users contained in each interval.
Optionally, dividing the probability value of the target user purchasing the peripheral product into a preset interval section includes: :
Dividing the probability value of purchasing the peripheral products by the target user into five interval sections of 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8 and 0.8-1.0.
Optionally, the obtaining the mapping relationship between each interval and the real purchase rate includes:
inputting a test sample data set into the commodity sales prediction model to obtain a probability value of a user purchasing the peripheral product, wherein each test sample data in the test sample data set comprises behavior data of the user watching a video, basic information of the user, basic information of the video and consumption information of the user on the peripheral product related to the video;
counting the number of the obtained probability values in each interval section;
counting the real purchase quantity of each interval section in the test sample data set;
and determining the mapping relation between each interval section and the real purchase rate according to the number of each interval section and the real purchase number of each interval section.
Optionally, the basic information of the target user includes: user identification, gender, age, consumption level, and usual address;
the basic information of the video comprises play quantity, attention number, score and video type.
The invention also provides a commodity sales predicting device, which comprises:
the first acquisition module is used for acquiring behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video;
the second acquisition module is used for acquiring the probability value of the target user purchasing the peripheral product by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information;
and the calculating module is used for calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The beneficial effects of the technical scheme are that:
in the embodiment of the invention, the behavior data of a target user when watching a video, the basic information of the target user, the basic information of the video and the consumption information of the target user on the related peripheral products of the video are obtained; acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information; and calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video. Compared with the existing commodity sales predicting method, the commodity sales predicting method in the embodiment of the invention not only considers the playing amount of videos and the number of people concerned in the calculating process, but also considers the consumption capacity of audiences, the population distribution of the audiences and various interactive behaviors of the audiences, thereby realizing the purpose of predicting the peripheral sales of the works by taking the user as the center from each audience and improving the accuracy of commodity sales prediction.
Drawings
FIG. 1 is a block diagram of one embodiment of a system block diagram for commodity sales prediction according to the present invention;
FIG. 2 is a flow chart of one embodiment of a method for predicting sales of a commodity according to the present invention;
FIG. 3 is a detailed flowchart of the step of calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video according to an embodiment of the present invention;
FIG. 4 is a detailed flowchart of the step of obtaining the mapping relationship between each interval and the real purchase rate according to an embodiment of the present invention;
FIG. 5 is a flow chart of another embodiment of a method for predicting sales of a commodity according to the present invention;
FIG. 6 is a block diagram of one embodiment of a merchandise sales predicting device according to the present invention;
fig. 7 is a schematic hardware structure of a computer device for executing the commodity sales predicting method according to an embodiment of the present invention.
Detailed Description
Advantages of the invention are further illustrated in the following description, taken in conjunction with the accompanying drawings and detailed description.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In the description of the present invention, it should be understood that the numerical references before the steps do not identify the order in which the steps are performed, but are merely used to facilitate description of the present invention and to distinguish between each step, and thus should not be construed as limiting the present invention.
Fig. 1 schematically shows an application environment schematic of a commodity sales predicting method according to an embodiment of the present application. In an exemplary embodiment, the system of the application environment may include a user terminal 10, a background server 20. The user terminal 10 and the background server 20 form a wireless or wired connection, and the user terminal 10 has a corresponding application client or web client, through which a user can watch video or purchase goods. The user terminal 10 may be a PC, a mobile phone, an iPAD, a tablet computer, a notebook computer, a personal digital assistant, etc. The backend server 20 may be a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster formed by a plurality of servers), etc.
Referring to fig. 2, a flow chart of a commodity sales predicting method according to an embodiment of the present invention is shown. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. As can be seen from the following description with the server as the execution body, the commodity sales predicting method provided in the present embodiment includes:
Step S20, behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video are obtained.
Specifically, the video watched by the target user may be a sitcoms video, an animation video, a movie video, or the like. In the embodiment of the invention, the video watched by the user is exemplified by the senna video.
Accordingly, the behavior data comprise the searching, watching and watching time length of the target user on the senna, and the behavior information of coin-in, comment, barrage, sharing and the like on the senna. The basic information of the target user comprises user identification, gender, age, consumption level, usual living address and the like, wherein the user identification is identification information for distinguishing each user identity, the consumption level is information for indicating the consumption level of the user, the consumption levels corresponding to the consumption level intervals of different sections are different, and the usual living address is the address where the user is frequently located. The basic information of the video comprises information such as play quantity, attention number, score, video type and the like. The peripheral products are goods which are made by using figures or animal models in the sitcom after authorization. The peripheral products are very rich in variety, and include toys, stationery, food, clothes, electrical appliances, various articles for daily use and the like. The consumption information of the peripheral products includes which peripheral products of the senna are purchased by the target user, which peripheral products of the senna are browsed by the target user, which peripheral products of the senna are added to the shopping cart by the target user, and the like.
It should be noted that, the target user refers to a user who purchases a peripheral product to be predicted currently.
And S21, acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information.
Specifically, the commodity sales prediction model is obtained by training a machine learning model through a training sample data set in advance, wherein each training sample data in the training sample data set comprises behavior data of a user when watching a video, basic information of the user, basic information of the video and consumption information of the user on related peripheral products of the video. The sales prediction model obtained through training can predict and obtain the probability value of the target user purchasing the surrounding commodity of the senna, for example, the probability value of the target user purchasing the surrounding commodity is predicted and obtained to be 0.8.
It should be noted that the peripheral product does not refer to a certain product, but refers to all the peripheral products related to the sitcom.
And S22, calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video.
Specifically, each target user refers to all users who have watched the senna. In this embodiment, it is necessary to predict the probability value of all the users who have watched the senna purchasing the surrounding products by the commodity sales prediction model. Assuming that the users who have watched the senna have 10 persons in total, the probability value of purchasing the surrounding products predicted by the commodity sales predicting model is: 1.0, 0.9, 0.2, 0.7, 0.3, 0.5, 0.4, 0.8, 0.6, 0.5.
After obtaining the probability value of each target user purchasing the peripheral product, the sales volume of the peripheral product can be calculated according to the obtained probability value of each target user purchasing the peripheral product and the total number of people watching the video.
According to the embodiment of the invention, the behavior data of the target user when watching the video, the basic information of the target user, the basic information of the video and the consumption information of the target user on the related peripheral products of the video are obtained; acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information; and calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video. Compared with the existing commodity sales predicting method, the commodity sales predicting method in the embodiment of the invention not only considers the playing amount of videos and the number of people in attention in the calculating process, but also considers the consumption capacity of audiences, the population distribution of the audiences and various interactive behaviors of the audiences, thereby realizing the purpose of predicting the peripheral sales of the works by taking the user as the center from each audience, improving the accuracy of commodity sales prediction and providing references for commodity intake, commodity replenishment or production by merchants.
In one embodiment, when calculating sales of the peripheral product, the probability values of all target users purchasing the peripheral product can be directly added, and the sum value is used as the sales of the peripheral product. Taking the above numerical value as an example, the probability value of purchasing the peripheral product by all target users is taken as the example, and the sales of the peripheral product=1.0+0.9+0.2+0.7+0.3+0.5+0.4+0.8+0.6+0.5=5.9, and when the calculated sales value is a decimal value, the final sales can be obtained by rounding or can be obtained by rounding off decimal values.
According to the embodiment of the invention, the probability values of all target users purchasing the peripheral products are directly added, and the sum value is used as the sales quantity of the peripheral products.
In another embodiment, referring to fig. 3, the calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video includes:
and step S30, dividing the probability value of purchasing the peripheral products by the target user into preset interval sections.
Specifically, since the probability value of purchasing the peripheral product by the user obtained by the commodity sales model is an error value, the peripheral product is not necessarily purchased by the user whose estimated purchasing probability is 0.8, and the peripheral product is not necessarily purchased by the user whose estimated purchasing probability is 0.2, which is expressed on the big data set: the estimated user population of 0.8 is higher than the estimated actual purchase probability of the user population of 0.2. Therefore, in order to improve the accuracy of the sales amount obtained by calculation, the probability value of purchasing the peripheral product by the user may be divided into preset intervals, the number of the intervals and the range of each interval are preset according to practical situations, for example, the intervals are divided into 5 intervals, the ranges of each interval are divided into 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8 and 0.8-1.0, wherein each interval contains the maximum value thereof and does not contain the minimum value thereof, for example, the intervals 0.4-0.6 represent: 0.4< probability value of user purchasing the peripheral product < = 0.6. In other embodiments, each section may not include the maximum value, and may include the minimum value, which is not limited in this example.
Step S31, counting the number of target users contained in each interval.
Specifically, after obtaining probability values of purchasing peripheral products by each target user through the commodity sales prediction model, counting the target users in each section, thereby obtaining the number of target users contained in each section. For example, the probability value of purchasing the peripheral product predicted by the commodity sales predicting model is: 1.0, 0.9, 0.2, 0.7, 0.3, 0.5, 0.4, 0.8, 0.6, 0.5, the divided interval is 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8, 0.8-1.0, 1 target user in 0-0.2 interval can be counted; 2 target users in the interval of 0.2-0.4; 3 target users in the interval of 0.4-0.6; 2 target users in the interval of 0.6-0.8; there are 2 target users in the interval 0.8-1.0.
Step S32, the mapping relation between each interval and the real purchase rate is obtained.
Specifically, the mapping relationship between each interval and the real purchase rate may be preset, and the real purchase rate may be obtained by counting the real purchase rates of all training sample data sets or test sample data sets in each interval.
Specifically, referring to fig. 4, the obtaining the mapping relationship between each interval and the real purchase rate includes:
and S40, inputting a test sample data set into the commodity sales prediction model to obtain a probability value of purchasing the peripheral products by a user, wherein each test sample data in the test sample data set comprises behavior data of the user when watching the video, basic information of the user, basic information of the video and consumption information of the user on the peripheral products related to the video.
Specifically, the test sample data set is input to the commodity sales volume prediction model, so that the probability value of purchasing the peripheral products by each user contained in the test sample data set is obtained through the commodity sales volume test model.
Step S41, counting the number of the obtained probability values in each interval section.
Specifically, after obtaining probability values of purchasing the peripheral products corresponding to each user contained in the test sample data set through the commodity sales volume prediction model, the number of the obtained probability values in each interval section can be counted according to the obtained probability values.
Step S42, counting the actual purchase quantity of each interval section in the test sample data set.
Specifically, after obtaining the probability value of purchasing the peripheral product corresponding to each user included in the test sample data set, the real purchasing quantity of each section may be further counted according to the information of purchasing the peripheral product by each user included in the test sample data, for example, when the probability value corresponding to the target user a is 0.7, the target user a may be regarded as a real purchasing user of the 0.6-0.8 section after purchasing the peripheral product; similarly, if the probability value corresponding to the target user B is 0.1, and the target user B also purchases the peripheral commodity, the target user B can be used as a real purchasing user in the interval of 0-0.2; if the probability value corresponding to the target user C is 0.9, and the target user C also purchases the surrounding commodity, the target user C can be used as a real purchasing user in the interval of 0.8-1.0.
Step S43, determining the mapping relation between each section and the real purchase rate according to the number of each section and the real purchase number of each section.
Specifically, after the number of each interval and the actual purchase number of each interval of the probability that the target user purchases the peripheral product are obtained, the mapping relationship between each interval and the actual purchase rate can be determined according to the ratio of the number of each interval and the actual purchase rate. For example, when the number of the probability values obtained by statistics in the interval section 0-0.2 is 100 ten thousand, and the number of the actual purchases obtained by statistics in the interval section is 15 ten thousand, the actual purchase rate corresponding to the interval section is 15 ten thousand/100 ten thousand=15%; the number of the probability values obtained by statistics in the interval section 0.2-0.4 is 50 ten thousand, the real purchase number obtained by statistics in the interval section is 12 ten thousand, and the real purchase rate corresponding to the interval section is 12 ten thousand/50 ten thousand=24%; the number of the probability values obtained by statistics is 40 ten thousand in the interval section 0.4-0.6, and the real purchase number obtained by statistics in the interval section is 20 ten thousand, so that the real purchase rate corresponding to the interval section is 20 ten thousand/40 ten thousand=50%; the number of the probability values obtained by statistics is 20 ten thousand in the interval section 0.6-0.8, and the real purchase number obtained by statistics in the interval section is 15 ten thousand, so that the real purchase rate corresponding to the interval section is 15 ten thousand/20 ten thousand=75%; the probability value obtained by statistics is 50 ten thousand in the interval section 0.8-1.0, and the real purchase quantity obtained by statistics is 46 ten thousand in the interval section, so that the real purchase rate corresponding to the interval section is 46 ten thousand/50 ten thousand=92%.
According to the embodiment of the invention, the number of the obtained probability values in each interval section and the real purchase number of each interval section in the test sample data set are counted, and then the mapping relation between each interval section and the real purchase rate is obtained through calculation according to the obtained two groups of number values, so that the calculated mapping relation between each interval section and the real purchase rate is more accurate.
And step S33, calculating sales of the peripheral products according to the mapping relation and the number of target users contained in each interval section.
Specifically, after the mapping relationship and the number of target users included in each section are obtained, the sales corresponding to the target users of each section can be obtained by multiplying the number of target users of each section by the corresponding real purchase rate, and then the sales corresponding to the target users of each section are added to obtain the total sales of the peripheral products. For example, taking the number of target users and the mapping relationship included in each section as an example, the data in step S43 may be taken as the sales of the peripheral products=100×15×50×24+40×50+20×75+50×92=108.
In the embodiment of the invention, the probability value of each target user purchasing the peripheral commodity obtained by the commodity sales volume prediction model is mapped with the real purchasing rate, instead of directly taking the probability value of the target user purchasing the peripheral commodity obtained by the commodity sales volume prediction model as the real purchasing rate of the target user, so that the accuracy of the obtained peripheral commodity sales volume can be improved.
Further, referring to fig. 5, which is a flow chart of a commodity sales predicting method according to another embodiment of the present invention, it can be seen from the drawing that the commodity sales predicting method provided in the present embodiment includes:
step S50, a training sample data set is obtained, wherein each training sample data set comprises behavior data of a user when the user watches the video, basic information of the user, basic information of the video and consumption information of the user on peripheral products related to the video.
Specifically, the training sample data set may be obtained from a server owned by the merchant, and if the merchant's server is provided to the customer, may be obtained from the customer's server. For example, the sample training data set is derived from the sitcom watching information and commodity sales information of the station B, and because the station B has two services of sitcom and member purchase, the watching behavior (duration, coin, barrage, comment and the like) of the user on one sitcom can be directly obtained from the server corresponding to the two services of sitcom and member purchase of the station B, and the information of whether the user purchases related commodities of the sitcom or not and the basic information of the user and the basic information of video (sitcom) can also be obtained.
And step S51, inputting the training sample data set into a preset machine learning model for training until the loss function of the machine learning model is converged, ending the training, and obtaining the commodity sales prediction model.
Specifically, the machine learning model may be a neural network model, such as a DNN (Deep Neural Networks, deep neural network) model, or may be another model, such as a logistic regression model, which is not limited in the embodiment of the present invention.
After the training sample data set is obtained, training sample data in the training sample data set is input into the machine learning model, so that the machine learning model can continuously adjust a loss function in the model according to the input training sample data until the loss function converges, training of the machine learning model can be completed, a commodity sales predicting model is obtained, and probability values of purchasing peripheral products of all target users can be predicted and obtained through the commodity sales model.
Step S52, behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video are obtained.
And step S53, acquiring the probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information.
Step S54, calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video.
Specifically, the steps S52 to S54 are the same as the steps S20 to S22 in the above embodiment, and will not be described in detail in this embodiment.
According to the embodiment of the invention, the preset machine learning model is trained through the training sample data set so as to obtain the commodity sales predicting model through training, so that the probability of purchasing peripheral products by a user is estimated through the commodity sales predicting model, manual prediction by a merchant is not needed, and the accuracy of commodity sales predicting can be improved.
Referring to FIG. 6, a block diagram of a merchandise sales predicting device 600 according to an embodiment of the present invention is shown.
In this embodiment, the commodity sales predicting apparatus 600 includes a series of computer program instructions stored in a memory, which when executed by a processor, can implement the commodity sales predicting function of the embodiments of the present invention. In some embodiments, the merchandise sales prediction apparatus 600 may be divided into one or more modules based on the particular operations implemented by portions of the computer program instructions. For example, in fig. 6, the commodity sales predicting apparatus 600 may be divided into a first obtaining module 601, a second obtaining module 602, and a calculating module 603. Wherein:
The first obtaining module 601 is configured to obtain behavior data of a target user when watching a video, basic information of the target user, basic information of the video, and consumption information of the target user on peripheral products related to the video.
Specifically, the video watched by the target user may be a sitcoms video, an animation video, a movie video, or the like. In the embodiment of the invention, the video watched by the user is exemplified by the senna video.
Accordingly, the behavior data comprise the searching, watching and watching time length of the target user on the senna, and the behavior information of coin-in, comment, barrage, sharing and the like on the senna. The basic information of the target user comprises user identification, gender, age, consumption level, usual living address and the like, wherein the user identification is identification information for distinguishing each user identity, the consumption level is information for indicating the consumption level of the user, the consumption levels corresponding to the consumption level intervals of different sections are different, and the usual living address is the address where the user is frequently located. The basic information of the video comprises information such as play quantity, attention number, score, video type and the like. The peripheral products are goods which are made by using figures or animal models in the sitcom after authorization. The peripheral products are very rich in variety, and include toys, stationery, food, clothes, electrical appliances, various articles for daily use and the like. The consumption information of the peripheral products includes which peripheral products of the senna are purchased by the target user, which peripheral products of the senna are browsed by the target user, which peripheral products of the senna are added to the shopping cart by the target user, and the like.
It should be noted that, the target user refers to a user who purchases a peripheral product to be predicted currently.
The second obtaining module 602 is configured to obtain, according to the behavior data, the basic information of the target user, the basic information of the video, and the consumption information, a probability value of the target user purchasing the peripheral product by using a pre-trained commodity sales prediction model.
Specifically, the commodity sales prediction model is obtained by training a machine learning model through a training sample data set in advance, wherein each training sample data in the training sample data set comprises behavior data of a user when watching a video, basic information of the user, basic information of the video and consumption information of the user on related peripheral products of the video. The sales prediction model obtained through training can predict and obtain the probability value of the target user purchasing the surrounding commodity of the senna, for example, the probability value of the target user purchasing the surrounding commodity is predicted and obtained to be 0.8.
It should be noted that the peripheral product does not refer to a certain product, but refers to all the peripheral products related to the sitcom.
A calculating module 603, configured to calculate sales of the peripheral products according to the probability value of each target user purchasing the peripheral products and the total number of people watching the video.
Specifically, each target user refers to all users who have watched the senna. In this embodiment, it is necessary to predict the probability value of all the users who have watched the senna purchasing the surrounding products by the commodity sales prediction model. Assuming that the users who have watched the senna have 10 persons in total, the probability value of purchasing the surrounding products predicted by the commodity sales predicting model is: 1.0, 0.9, 0.2, 0.7, 0.3, 0.5, 0.4, 0.8, 0.6, 0.5.
After obtaining the probability value of each target user purchasing the peripheral product, the sales volume of the peripheral product can be calculated according to the obtained probability value of each target user purchasing the peripheral product and the total number of people watching the video.
According to the embodiment of the invention, the behavior data of the target user when watching the video, the basic information of the target user, the basic information of the video and the consumption information of the target user on the related peripheral products of the video are obtained; acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information; and calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video. Compared with the existing commodity sales predicting method, the commodity sales predicting method in the embodiment of the invention not only considers the playing amount of videos and the number of people in attention in the calculating process, but also considers the consumption capacity of audiences, the population distribution of the audiences and various interactive behaviors of the audiences, thereby realizing the purpose of predicting the peripheral sales of the works by taking the user as the center from each audience, improving the accuracy of commodity sales prediction and providing references for commodity intake, commodity replenishment or production by merchants.
In one embodiment, when calculating sales of the peripheral product, the calculating module 603 may directly add the probability values of all target users purchasing the peripheral product, and use the sum value as the sales of the peripheral product. Taking the above-mentioned numerical values as examples, the probability value of purchasing the peripheral product by all target users is taken as an example, and the sales of the peripheral product=1.0+0.9+0.2+0.7+0.3+0.5+0.4+0.8+0.6+0.5=5.9, and when the calculated sales value is a decimal value, the final sales may be obtained by rounding or may be obtained by rounding off decimal values.
According to the embodiment of the invention, the probability values of all target users purchasing the peripheral products are directly added, and the sum value is used as the sales quantity of the peripheral products.
In another embodiment, the calculating module 603 is further configured to divide the probability value of the target user purchasing the peripheral product into a preset interval.
Specifically, since the probability value of purchasing the peripheral product by the user obtained by the commodity sales model is an error value, the peripheral product is not necessarily purchased by the user whose estimated purchasing probability is 0.8, and the peripheral product is not necessarily purchased by the user whose estimated purchasing probability is 0.2, which is expressed on the big data set: the estimated user population of 0.8 is higher than the estimated actual purchase probability of the user population of 0.2. Therefore, in order to improve the accuracy of the sales amount obtained by calculation, the probability value of purchasing the peripheral product by the user may be divided into preset intervals, the number of the intervals and the range of each interval are preset according to practical situations, for example, the intervals are divided into 5 intervals, the ranges of each interval are divided into 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8 and 0.8-1.0, wherein each interval contains the maximum value thereof and does not contain the minimum value thereof, for example, the intervals 0.4-0.6 represent: 0.4< probability value of user purchasing the peripheral product < = 0.6. In other embodiments, each section may not include the maximum value, and may include the minimum value, which is not limited in this example.
The calculating module 603 is further configured to count the number of target users included in each interval.
Specifically, after obtaining probability values of purchasing peripheral products by each target user through the commodity sales prediction model, counting the target users in each section, thereby obtaining the number of target users contained in each section. For example, the probability value of purchasing the peripheral product predicted by the commodity sales predicting model is: 1.0, 0.9, 0.2, 0.7, 0.3, 0.5, 0.4, 0.8, 0.6, 0.5, the divided interval is 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8, 0.8-1.0, 1 target user in 0-0.2 interval can be counted; 2 target users in the interval of 0.2-0.4; 3 target users in the interval of 0.4-0.6; 2 target users in the interval of 0.6-0.8; there are 2 target users in the interval 0.8-1.0.
The calculating module 603 is further configured to obtain a mapping relationship between each interval and the real purchase rate.
Specifically, the mapping relationship between each interval and the real purchase rate may be preset, and the real purchase rate may be obtained by counting the real purchase rates of all training sample data sets or test sample data sets in each interval.
Illustratively, in an embodiment, the calculating module 603 is further configured to input a test sample data set to the sales volume prediction model to obtain a probability value of the user purchasing the peripheral product, where each test sample data in the test sample data set includes behavior data of the user when watching the video, basic information of the user, basic information of the video, and consumption information of the video related peripheral product by the user.
Specifically, the test sample data set is input to the commodity sales volume prediction model, so that the probability value of purchasing the peripheral products by each user contained in the test sample data set is obtained through the commodity sales volume test model.
The calculating module 603 is further configured to count the number of the obtained probability values in each interval.
Specifically, after obtaining probability values of purchasing the peripheral products corresponding to each user contained in the test sample data set through the commodity sales volume prediction model, the number of the obtained probability values in each interval section can be counted according to the obtained probability values.
The calculating module 603 is further configured to count the actual purchase amount of each interval in the test sample data set.
Specifically, after obtaining the probability value of purchasing the peripheral product corresponding to each user included in the test sample data set, the real purchasing quantity of each section may be further counted according to the information of purchasing the peripheral product by each user included in the test sample data, for example, when the probability value corresponding to the target user a is 0.7, the target user a may be regarded as a real purchasing user of the 0.6-0.8 section after purchasing the peripheral product; similarly, if the probability value corresponding to the target user B is 0.1, and the target user B also purchases the peripheral commodity, the target user B can be used as a real purchasing user in the interval of 0-0.2; if the probability value corresponding to the target user C is 0.9, and the target user C also purchases the surrounding commodity, the target user C can be used as a real purchasing user in the interval of 0.8-1.0.
The calculating module 603 is further configured to determine a mapping relationship between the respective interval sections and the real purchase rate according to the number of the respective interval sections and the real purchase number of the respective interval sections.
Specifically, after the number of each interval and the actual purchase number of each interval of the probability that the target user purchases the peripheral product are obtained, the mapping relationship between each interval and the actual purchase rate can be determined according to the ratio of the number of each interval and the actual purchase rate. For example, when the number of the probability values obtained by statistics in the interval section 0-0.2 is 100 ten thousand, and the number of the actual purchases obtained by statistics in the interval section is 15 ten thousand, the actual purchase rate corresponding to the interval section is 15 ten thousand/100 ten thousand=15%; the number of the probability values obtained by statistics in the interval section 0.2-0.4 is 50 ten thousand, the real purchase number obtained by statistics in the interval section is 12 ten thousand, and the real purchase rate corresponding to the interval section is 12 ten thousand/50 ten thousand=24%; the number of the probability values obtained by statistics is 40 ten thousand in the interval section 0.4-0.6, and the real purchase number obtained by statistics in the interval section is 20 ten thousand, so that the real purchase rate corresponding to the interval section is 20 ten thousand/40 ten thousand=50%; the number of the probability values obtained by statistics is 20 ten thousand in the interval section 0.6-0.8, and the real purchase number obtained by statistics in the interval section is 15 ten thousand, so that the real purchase rate corresponding to the interval section is 15 ten thousand/20 ten thousand=75%; the probability value obtained by statistics is 50 ten thousand in the interval section 0.8-1.0, and the real purchase quantity obtained by statistics is 46 ten thousand in the interval section, so that the real purchase rate corresponding to the interval section is 46 ten thousand/50 ten thousand=92%.
According to the embodiment of the invention, the number of the obtained probability values in each interval section and the real purchase number of each interval section in the test sample data set are counted, and then the mapping relation between each interval section and the real purchase rate is obtained through calculation according to the obtained two groups of number values, so that the calculated mapping relation between each interval section and the real purchase rate is more accurate.
The calculating module 603 is further configured to calculate sales of the peripheral product according to the mapping relationship and the number of target users included in each interval.
Specifically, after the mapping relationship and the number of target users included in each section are obtained, the sales corresponding to the target users of each section can be obtained by multiplying the number of target users of each section by the corresponding real purchase rate, and then the sales corresponding to the target users of each section are added to obtain the total sales of the peripheral products. For example, taking the above-mentioned data as an example, the number of target users and the mapping relationship included in each section may be obtained by the method that the sales of the peripheral product=100×15×50×24+40×50+20×75+50×92=108.
In the embodiment of the invention, the probability value of each target user purchasing the peripheral commodity obtained by the commodity sales volume prediction model is mapped with the real purchasing rate, instead of directly taking the probability value of the target user purchasing the peripheral commodity obtained by the commodity sales volume prediction model as the real purchasing rate of the target user, so that the accuracy of the obtained peripheral commodity sales volume can be improved.
Further, in an embodiment, the commodity sales predicting apparatus 600 further includes a third obtaining module and an input module.
The third obtaining module is configured to obtain a training sample data set, where each training sample data in the training sample data set includes behavior data of a user when the user views a video, basic information of the user, basic information of the video, and consumption information of the user on peripheral products related to the video.
Specifically, the training sample data set may be obtained from a server owned by the merchant, and if the merchant's server is provided to the customer, may be obtained from the customer's server. For example, the sample training data set is derived from the sitcom watching information and commodity sales information of the station B, and because the station B has two services of sitcom and member purchase, the watching behavior (duration, coin, barrage, comment and the like) of the user on one sitcom can be directly obtained from the server corresponding to the two services of sitcom and member purchase of the station B, and the information of whether the user purchases related commodities of the sitcom or not and the basic information of the user and the basic information of video (sitcom) can also be obtained.
The input module is used for inputting the training sample data set into a preset machine learning model for training until the loss function of the machine learning model is converged, and ending the training to obtain the commodity sales prediction model.
Specifically, the machine learning model may be a neural network model, such as a DNN (Deep Neural Networks, deep neural network) model, or may be another model, such as a logistic regression model, which is not limited in the embodiment of the present invention.
After the training sample data set is obtained, training sample data in the training sample data set is input into the machine learning model, so that the machine learning model can continuously adjust a loss function in the model according to the input training sample data until the loss function converges, training of the machine learning model can be completed, a commodity sales predicting model is obtained, and probability values of purchasing peripheral products of all target users can be predicted and obtained through the commodity sales model.
According to the embodiment of the invention, the preset machine learning model is trained through the training sample data set so as to obtain the commodity sales predicting model through training, so that the probability of purchasing peripheral products by a user is estimated through the commodity sales predicting model, manual prediction by a merchant is not needed, and the accuracy of commodity sales predicting can be improved.
Fig. 7 schematically shows a hardware architecture diagram of a computer device 2 adapted to implement the sales volume prediction method according to an embodiment of the present application. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with instructions set or stored in advance. For example, the server may be a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack server (including a stand-alone server or a server cluster formed by a plurality of servers), etc. As shown in fig. 7, the computer device 2 includes at least, but is not limited to: the memory 701, the processor 702, and the network interface 703 may be communicatively linked to each other via a system bus. Wherein:
the memory 701 includes at least one type of computer-readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 701 may be an internal storage module of the computer device 2, such as a hard disk or memory of the computer device 2. In other embodiments, the memory 701 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 2. Of course, the memory 701 may also include both the internal memory module of the computer device 2 and its external memory device. In the present embodiment, the memory 701 is typically used to store an operating system installed on the computer device 2 and various types of application software, such as program codes of a commodity sales prediction method. In addition, the memory 701 can also be used to temporarily store various types of data that have been output or are to be output.
The processor 702 may be a central processing unit (Central Processing Unit, simply CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 702 is generally configured to control overall operation of the computer device 2, such as performing control and processing related to data interaction or communication with the computer device 2, and the like. In this embodiment, a processor 702 is used to execute program code or process data stored in a memory 701.
The network interface 703 may comprise a wireless network interface or a wired network interface, which network interface 703 is typically used to establish a communication link between the computer device 2 and other computer devices. For example, the network interface 703 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication link between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, abbreviated as GSM), wideband code division multiple access (Wideband Code Division Multiple Access, abbreviated as WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, etc.
It should be noted that fig. 7 only shows a computer device having components 701-703, but it is to be understood that not all of the illustrated components are required to be implemented, and that more or fewer components may be implemented instead.
In this embodiment, the commodity sales prediction method stored in the memory 701 may also be divided into one or more program modules and executed by one or more processors (the processor 702 in this embodiment) to complete the present invention.
The present embodiments provide a non-transitory computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the commodity sales prediction method of the embodiments.
In this embodiment, the computer-readable storage medium includes a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the computer readable storage medium may be an internal storage unit of a computer device, such as a hard disk or a memory of the computer device. In other embodiments, the computer readable storage medium may also be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), etc. that are provided on the computer device. Of course, the computer-readable storage medium may also include both internal storage units of a computer device and external storage devices. In this embodiment, the computer-readable storage medium is typically used to store an operating system installed on a computer device and various types of application software, such as program codes of the commodity sales prediction method in the embodiment, and the like. Furthermore, the computer-readable storage medium may also be used to temporarily store various types of data that have been output or are to be output.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over at least two network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the embodiments of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus a general purpose hardware platform, or may be implemented by hardware. Those skilled in the art will appreciate that all or part of the processes implementing the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and where the program may include processes implementing the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), or the like.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.
Claims (9)
1. A commodity sales prediction method, comprising:
acquiring behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video, wherein the behavior data comprises search, watching and watching time of the target user on a senna, coin-in of the senna, comment, barrage and sharing behavior information;
acquiring a probability value of purchasing the peripheral product by the target user by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information;
Calculating sales of the peripheral products according to probability values of purchasing the peripheral products by each target user and the total number of watching the video;
the calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video comprises the following steps:
dividing the probability value of the target user purchasing the peripheral product into preset interval sections;
counting the number of target users contained in each interval;
obtaining a mapping relation between each interval section and a real purchase rate, wherein the real purchase rate is obtained by counting the real purchase rates of all training sample data sets or test sample data sets in each interval section;
and calculating sales of the peripheral products according to the mapping relation and the number of target users contained in each interval.
2. The merchandise sales predicting method according to claim 1, wherein said calculating sales of said peripheral products according to a probability value of each target user purchasing said peripheral products and a total number of people watching said video comprises:
and taking the sum of probability values of all target users purchasing the peripheral products as sales of the peripheral products.
3. The commodity sales prediction method according to claim 1, further comprising:
acquiring a training sample data set, wherein each training sample data set comprises behavior data of a user when watching a video, basic information of the user, basic information of the video and consumption information of the user on related peripheral products of the video;
and inputting the training sample data set into a preset machine learning model for training until the loss function of the machine learning model is converged, ending the training, and obtaining the commodity sales prediction model.
4. The commodity sales prediction method according to claim 1, wherein dividing the probability value of the target user purchasing the peripheral product into preset interval segments comprises:
dividing the probability value of purchasing the peripheral product by a target user into five interval sections of 0-0.2, 0.2-0.4, 0.4-0.6, 0.6-0.8 and 0.8-1.0, wherein each interval section contains the maximum value and the minimum value.
5. The commodity sales predicting method according to claim 1, wherein said obtaining a mapping relationship between each section and a true purchase rate comprises:
Inputting a test sample data set into the commodity sales prediction model to obtain a probability value of a user purchasing the peripheral product, wherein each test sample data in the test sample data set comprises behavior data of the user watching a video, basic information of the user, basic information of the video and consumption information of the user on the peripheral product related to the video;
counting the number of the obtained probability values in each interval section;
counting the real purchase quantity of each interval section in the test sample data set;
and determining the mapping relation between each interval section and the real purchase rate according to the number of each interval section and the real purchase number of each interval section.
6. The commodity sales prediction method according to any one of claims 1 to 5, wherein the basic information of the target user includes: user identification, gender, age, consumption level, and usual address;
the basic information of the video comprises play quantity, attention number, score and video type.
7. A commodity sales predicting apparatus, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring behavior data of a target user when watching a video, basic information of the target user, basic information of the video and consumption information of the target user on peripheral products related to the video, and the behavior data comprise search, watching and watching time of the target user on a senna, coin-feed, comment, barrage and sharing behavior information of the senna;
The second acquisition module is used for acquiring the probability value of the target user purchasing the peripheral product by adopting a pre-trained commodity sales prediction model according to the behavior data, the basic information of the target user, the basic information of the video and the consumption information;
the calculation module is used for calculating sales of the peripheral products according to the probability value of purchasing the peripheral products by each target user and the total number of watching the video;
the computing module is also used for dividing the probability value of the target user purchasing the peripheral product into preset interval sections; counting the number of target users contained in each interval; obtaining a mapping relation between each interval and the real purchase rate; and calculating sales of the peripheral products according to the mapping relation and the number of target users contained in each interval, wherein the real purchase rate is obtained by counting the real purchase rate of all training sample data sets or test sample data sets in each interval.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the commodity sales prediction method of any one of claims 1 to 6 when the computer program is executed.
9. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program when executed by a processor implements the steps of the commodity sales prediction method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911153294.0A CN112837079B (en) | 2019-11-22 | 2019-11-22 | Commodity sales predicting method, commodity sales predicting device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911153294.0A CN112837079B (en) | 2019-11-22 | 2019-11-22 | Commodity sales predicting method, commodity sales predicting device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112837079A CN112837079A (en) | 2021-05-25 |
| CN112837079B true CN112837079B (en) | 2023-06-09 |
Family
ID=75921548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911153294.0A Active CN112837079B (en) | 2019-11-22 | 2019-11-22 | Commodity sales predicting method, commodity sales predicting device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112837079B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426640A (en) * | 2010-11-19 | 2012-04-25 | 微软公司 | Secure software product identifier for product validation and activation |
| CN107330744A (en) * | 2017-07-21 | 2017-11-07 | 携程旅游网络技术（上海）有限公司 | The recommendation method and system of air ticket derived product |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN109509030A (en) * | 2018-11-15 | 2019-03-22 | 北京旷视科技有限公司 | Method for Sales Forecast method and its training method of model, device and electronic system |
-
2019
- 2019-11-22 CN CN201911153294.0A patent/CN112837079B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426640A (en) * | 2010-11-19 | 2012-04-25 | 微软公司 | Secure software product identifier for product validation and activation |
| CN107330744A (en) * | 2017-07-21 | 2017-11-07 | 携程旅游网络技术（上海）有限公司 | The recommendation method and system of air ticket derived product |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN109509030A (en) * | 2018-11-15 | 2019-03-22 | 北京旷视科技有限公司 | Method for Sales Forecast method and its training method of model, device and electronic system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112837079A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190012683A1 (en) | Method for predicting purchase probability based on behavior sequence of user and apparatus for the same | |
| US10210548B1 (en) | Predictive recommendation system using absolute relevance | |
| CN111080413A (en) | E-commerce platform commodity recommendation method and device, server and storage medium | |
| CN112837106A (en) | Commodity recommendation method and device and computer equipment | |
| CN109460514A (en) | Method and apparatus for pushed information | |
| CN110008397B (en) | Recommendation model training method and device | |
| EP4181026A1 (en) | Recommendation model training method and apparatus, recommendation method and apparatus, and computer-readable medium | |
| CN109299356B (en) | Activity recommendation method and device based on big data, electronic equipment and storage medium | |
| US10699198B2 (en) | Method and system for cold-start item recommendation | |
| CN109993627B (en) | Recommendation method, recommendation model training device and storage medium | |
| US11423324B2 (en) | Training and estimation of selection behavior of target | |
| KR102049777B1 (en) | Item recommendation method and apparatus based on user behavior | |
| CN112613938B (en) | Model training method and device and computer equipment | |
| CN116541610B (en) | Training method and device for recommendation model | |
| CN112380449B (en) | Information recommendation method, model training method and related device | |
| CN108133390A (en) | For predicting the method and apparatus of user behavior and computing device | |
| CN111861605A (en) | Business object recommendation method | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN111080417A (en) | Processing method for improving booking smoothness rate, model training method and system | |
| CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
| CN110019940A (en) | A kind of video display method for pushing and device | |
| CN111340540B (en) | Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device | |
| CN112837079B (en) | Commodity sales predicting method, commodity sales predicting device and computer equipment | |
| CN109460778B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN116977019A (en) | Merchant recommendation method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |