CN110992097B - Processing method and device for price of revenue product, computer equipment and storage medium - Google Patents
Processing method and device for price of revenue product, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110992097B CN110992097B CN201911220870.9A CN201911220870A CN110992097B CN 110992097 B CN110992097 B CN 110992097B CN 201911220870 A CN201911220870 A CN 201911220870A CN 110992097 B CN110992097 B CN 110992097B
- Authority
- CN
- China
- Prior art keywords
- user
- price
- prices
- revenue
- user data
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 8
- 238000003066 decision tree Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000006399 behavior Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a processing method, a processing device, computer equipment and a storage medium for price of a revenue product, wherein the method is realized by acquiring user history data of shared articles; the user history data includes a user identification; inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price; calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values; and storing the corresponding relation among the recommended price, the user identification and the recommended price into a database. The recommendation price of the revenue product is provided for the user according to the requirement of the user on the shared object, the conversion rate of the revenue product purchased by the user is improved, and the technical problem that the card purchasing conversion rate is low when the electronic ticket is issued to the user is solved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for processing a price of a revenue product, a computer device, and a storage medium.
Background
With the development of internet technology, more and more shared items such as shared bicycles, shared automobiles, shared charging devices, shared umbrellas, etc. are emerging. The current revenue products of shared articles mainly comprise a plurality of forms such as year cards, half year cards, season cards, month cards, secondary cards and the like. For users with relatively rigid requirements, the shared object needs to be frequently used, and products such as moon cards, season cards and the like are relatively economical and practical; for the service side sharing the articles, the viscosity of the user can be increased by selling products such as moon cards, quarter cards and the like.
In general, in order to encourage users to purchase revenue products such as moon cards and quarter cards of shared objects, service parties of the shared objects often issue various electronic coupons to users on a large scale through consumer application programs operated by the service parties, including: cash coupons, vouchers, discount coupons, and red packs, among others.
However, in the conventional art, issuing an electronic ticket to a user has a technical problem of low card purchase conversion rate.
Disclosure of Invention
Based on the above, it is necessary to provide a processing method, device, computer equipment and storage medium for the price of the revenue product, aiming at the technical problem that the conversion rate of purchasing cards is low when issuing electronic coupons to users in the conventional technology.
A method of processing a price for a revenue product, the method comprising:
acquiring user history data of the shared object; the user history data comprises user identifications;
inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price;
calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values;
and storing the recommended price, the user identification and the corresponding relation between the recommended price and the user identification into a database.
In one embodiment, the calculating the expected value according to each price and the purchased probability corresponding to each price, and determining the recommended price of the revenue product according to the calculated expected value includes:
calculating expected values according to the prices and the purchased probabilities corresponding to the prices to obtain the expected values corresponding to the prices;
and selecting the price corresponding to the maximum expected value from expected values corresponding to the prices as the recommended price of the revenue product.
In one embodiment, the method further comprises:
acquiring the configuration price of the revenue product and an operation instruction of a purchase page entering the revenue product; the operation instruction carries the user identification;
searching a corresponding recommended price in the database according to the user identification;
calculating according to the searched recommended price and the configuration price to obtain a preferential amount corresponding to the purchased revenue product;
and generating an electronic ticket corresponding to the purchased revenue product according to the preferential amount, and sending the electronic ticket to a terminal corresponding to the user identifier.
In one embodiment, the generating step of the decision tree forest model includes:
constructing a user data sample set, wherein the user data sample set comprises a user data positive sample and a user data negative sample;
labeling a first class value of purchasing behavior and a recommended price of the revenue product in each positive sample of the user data;
labeling a second class value of the purchasing behavior and the recommended price of the revenue product in each user data negative sample;
training the decision tree forest model according to the positive user data samples, the negative user data samples, the first class values and recommended prices corresponding to the positive user data samples and the second class values and recommended prices corresponding to the negative user data samples.
In one embodiment, the constructing a negative sample of user data includes:
collecting user data samples corresponding to the second class values; the user data sample includes a time to enter the purchase page;
screening the user data samples corresponding to the second class values according to the user identification and the time for entering the purchase page and a preset rule;
and constructing a user data negative sample by using the user data sample corresponding to the second category value obtained by screening.
In one embodiment, the shared item is a shared bicycle; the user data sample also includes at least one of user riding data, data of a user purchasing the revenue product, user attribute data, user registered city, data affecting user riding intent, user behavior data occurring within the purchase page.
In one embodiment, the decision tree forest model is a LightGBM model, and the LightGBM model operates in a distributed computing environment.
A device for processing a price of a revenue product, the device comprising:
the acquisition module is used for acquiring the user history data of the shared object; the user history data comprises user identifications;
The prediction module is used for inputting the user history data into a decision tree forest model to predict, so as to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price;
the calculation module is used for calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values;
and the storage module is used for storing the recommended price, the user identifier and the corresponding relation between the recommended price and the user identifier into a database.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of the method of any of the embodiments described above.
A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of the embodiments described above.
The processing method, the processing device, the computer equipment and the storage medium for the price of the revenue product are realized by acquiring the user history data of the shared object; the user history data includes a user identification; inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price; calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values; and storing the corresponding relation among the recommended price, the user identification and the recommended price into a database. The recommendation price of the revenue product is provided for the user according to the requirement of the user on the shared object, the conversion rate of the revenue product purchased by the user is improved, and the technical problem that the card purchasing conversion rate is low when the electronic ticket is issued to the user is solved.
Drawings
FIG. 1 is an application environment diagram of a method of processing a price of an revenue product in one embodiment;
FIG. 2 is a flow chart of a method of processing a price of an revenue product in one embodiment;
FIG. 3 is a flow chart of a method of processing a price of an revenue product in one embodiment;
FIG. 4 is a flow diagram of generating a decision tree forest model in one embodiment;
FIG. 5 is a flow diagram of constructing a negative sample of user data in one embodiment;
FIG. 6 is a flow chart of a method of processing a price of a revenue product in one embodiment;
FIG. 7 is a block diagram of an embodiment of a processing device for revenue product prices;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
As described in the background art, in order to encourage users to purchase revenue products such as moon cards and quarter cards of shared articles, service parties of the shared articles often issue various electronic coupons to users on a large scale through consumer applications operated by the service parties. These revenue products are pre-paid and the user may use the shared item any number of times during the contracted term after payment. However, the degree of demand of different users for the shared object is different, that is, the number of times of use of the shared object is different, and if the users pay the same fee for the revenue product, this is obviously unfair to the users, and in general, since the electronic coupons are not aimed at the actual demands of the users, some users select to ignore various kinds of electronic coupons issued by the service side of the shared object. This has the technical problem that the conversion rate of purchasing revenue products is low for the service side sharing the goods to issue the electronic coupon to the user.
Based on this, the embodiment of the application calculates the price of the revenue product according to the actual demand of the user for the shared object, and provides a processing method for the price of the revenue product, which can be applied to the application environment shown in fig. 1. Wherein, the terminal 110 performs data interaction with the server 120 through a network. The server 120 obtains user history data of the shared item; the user history data includes a user identification; inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price; calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values; and storing the corresponding relation among the recommended price, the user identification and the recommended price into a database.
The terminal 110 may be configured to display an application page of an application program, where the application page is provided with a button corresponding to purchase a revenue product, and the user triggers the corresponding button to issue an operation instruction to enter the purchase page of the revenue product. The server 120 obtains the configuration price of the revenue product and the operation instruction of the purchase page of the revenue product, wherein the operation instruction carries the user identification, and the corresponding recommended price is searched in the database according to the user identification; calculating according to the searched recommended price and the configuration price to obtain a preferential amount corresponding to purchased the revenue product; and generating an electronic coupon corresponding to the purchased product according to the preferential amount, and sending the electronic coupon to the terminal 110 corresponding to the user identification.
The terminal 110 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 120 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, the present application provides a method for processing a price of a revenue product, which is illustrated by taking a server in an application environment of fig. 1 as an example, and includes the following steps:
s210, acquiring user history data of the shared object.
The service side management of the shared object provides a consumer application program for a user, the user obtains the permission of using the shared object through the application program, the application program can record the behavior data (such as the use times, the use duration and the like) of the user using the shared object, and can record the behavior data (such as the click operation behavior, the access time and the like) of the user using the application program. The user history data is data of various aspects such as shared item information used by a user recorded by a consumer application operated by a service side of the shared item, purchase of a revenue product of the shared item, and user attribute information. The user history data includes a user identification. These user history data may be stored locally on the server or may be stored on a server communicatively connected to the server.
Specifically, in order to promote the user to purchase the revenue product, price strategies of different revenue products are formulated according to different user demands, and interests of both the user and the service side are maintained. In order to estimate the user's need for use of the shared item, it is necessary to analyze the user history data, and therefore, the server obtains the user history data of the shared item locally from the server or obtains the user history data of the shared item from a server communicatively connected to the server.
S220, inputting the user history data into a decision tree forest model for prediction, and obtaining a plurality of prices of the revenue product and the purchase probability corresponding to each price.
The decision tree forest model is an algorithm for integrating multiple tree decisions through the idea of ensemble learning, the basic unit of the algorithm is a decision tree, and the algorithm essentially belongs to an ensemble learning (Ensemble Learning) method of machine learning. The decision tree forest model is a model with prediction capability which is obtained by training in advance. The user history data can reflect the real demands of the users on the shared objects, and the user history data can be used for predicting the price acceptable by the users as the user history data is stored locally in the server or the server in communication connection with the server, so that reasonable and feasible prices are provided for the users according to the real demands of the users. The purchased probability is the probability that the decision tree forest model predicts that the user purchases a certain revenue product. Specifically, the decision tree forest model is deployed in a server, the server acquires user history data, and inputs the user history data into the decision tree forest model for feature division, predicts a plurality of prices of corresponding revenue products, and the probability that the user purchases the revenue products at the prices.
S230, calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values.
Wherein the expected value is the product of the prediction result and the prediction probability. Specifically, a decision tree forest model deployed on a server can be triggered at preset time, multiple prices of a user likely to purchase a revenue product and purchase probabilities corresponding to the prices are predicted according to user history data of the user through the decision tree forest model, so that expected values corresponding to the prices are obtained through calculation by using the predicted multiple prices and the purchase probabilities corresponding to the prices, and recommended prices of the revenue product are determined according to the calculated expected values, and the maximization of benefits of both the user and a server is achieved.
S240, storing the recommended price, the user identification and the corresponding relation between the recommended price and the user identification in a database.
Specifically, recommended prices of the revenue products can be calculated in advance according to requirements of all users, for example, a server automatically triggers operation of a decision tree forest model at a preset time point, historical data of the users are input into the decision data model, and a plurality of prices of the revenue products and the purchased probability corresponding to all the prices are predicted. The server calculates according to the prices and the purchased probabilities corresponding to the prices, and determines the recommended price of the revenue product. And storing the recommended price, the user identification and the corresponding relation between the recommended price and the user identification into a database. When the user purchases the revenue product, the terminal sends an operation instruction comprising the user identifier to the server, and the server searches the database according to the user identifier to quickly obtain the recommended price corresponding to the revenue product purchased by the user. It can be understood that when the user purchases the revenue product, the operation instruction sent to the server by the terminal can trigger the operation of the decision tree forest model to predict the recommended price of the revenue product.
In this embodiment, user history data of the shared object is obtained; the user history data includes a user identification; inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price; calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values; and storing the corresponding relation among the recommended price, the user identification and the recommended price into a database. The recommendation price of the revenue product is provided for the user according to the requirement of the user on the shared object, the conversion rate of the revenue product purchased by the user is improved, and the technical problem that the card purchasing conversion rate is low when the electronic ticket is issued to the user is solved.
In one embodiment, calculating an expected value according to each price and the purchase probability corresponding to each price, and determining a recommended price of the revenue product according to the calculated expected value includes: calculating expected values according to the prices and the purchased probabilities corresponding to the prices to obtain the expected values corresponding to the prices; and selecting the price corresponding to the maximum expected value from expected values corresponding to the prices as the recommended price of the revenue product.
Specifically, the server acquires user history data of the shared object, inputs the acquired user history data into a decision tree forest model for prediction, and obtains a plurality of prices of the revenue product and purchase probabilities corresponding to the prices. And calculating the product of the plurality of prices and the purchased probability corresponding to each price to obtain the expected value corresponding to each price. In order to maximize the interests of both the user and the service party, a price corresponding to the maximum expected value is selected as a recommended price of the revenue product from the expected values corresponding to the prices.
Illustratively, the shared item is a shared bicycle, and the revenue product is a bicycle month card provided by the service party. Inputting the user historical data of the user A into a decision tree forest model for prediction, wherein the price of the obtained bicycle month card can be 40 yuan, 50 yuan and 60 yuan, and the purchase probabilities corresponding to the 40 yuan, the 50 yuan and the 60 yuan are 60%, 50% and 30% respectively; the expected values of the purchase probabilities corresponding to the prices of the bicycle monthly card and the prices are calculated to be 24, 25, and 18, respectively. Therefore, the recommended price for a bicycle moon card should be 50 yuan.
In one embodiment, as shown in fig. 3, the method further comprises the steps of:
S310, acquiring configuration prices of the revenue products and operation instructions of purchasing pages of the revenue products;
s320, searching a corresponding recommended price in a database according to the user identification;
s330, calculating according to the searched recommended price and the configuration price to obtain a preferential amount corresponding to purchased revenue products;
and S340, generating an electronic ticket corresponding to the purchased revenue product according to the preferential amount, and sending the electronic ticket to a terminal corresponding to the user identification.
The configuration price refers to the same unit price formulated by the service side for the revenue product, and the configuration price can be related to factors such as cities, for example, one configuration price corresponds to one city. The purchase webpage is a page for displaying information of purchasing the revenue product to the user in an application program provided by the service party, and can comprise configuration value of the revenue product, product introduction and the like. Specifically, the server locally or a server in communication connection with the server stores the configuration price of the revenue product in advance, and the configuration price of the revenue product is acquired from the server locally or the server in communication connection with the server. The terminal is provided with an application program, other pages of the application program such as a main page are provided with corresponding buttons, the user triggers the buttons, and the terminal displays a purchase page of the revenue product. Namely, the server acquires an operation instruction of entering a purchase page of the revenue product, wherein the operation instruction carries a user identifier. Because the recommended price of the revenue product is predicted in advance according to the historical data of the user and the corresponding relation between the recommended price and the user identifier is stored in the database, the server can search the corresponding recommended price in the database according to the user identifier. In order to determine the preferential amount provided for the user, the server calculates according to the searched recommended price and the configuration price, after calculating to obtain the preferential amount corresponding to the purchased revenue product, the server generates an electronic coupon corresponding to the purchased revenue product according to the preferential amount, and sends the electronic coupon to a terminal corresponding to the user identifier. For example, the server calculates the difference between the recommended price and the configured price, generates coupons with the amount equal to the difference, and sends the coupons to the corresponding terminals; or the server calculates the ratio of the recommended price to the configuration price, generates a discount coupon with the amount equal to the ratio, and sends the discount coupon to the corresponding terminal, etc. It will be appreciated that in this implementation, the database may be deployed locally on the server or may be deployed on a server connected to the server.
In one embodiment, as shown in fig. 4, the generating step of the decision tree forest model includes:
s410, constructing a user data sample set, wherein the user data sample set comprises a user data positive sample and a user data negative sample.
The user data sample set includes a plurality of user data samples, the user data samples can reflect user images, the user data samples include behavior data of a user entering a purchase page, and include data of other aspects, such as: the user uses shared item data, data of the user purchasing the revenue product, user attribute data, user registered city, and the like. The user enters the purchase page to issue a purchase comprising purchasing the revenue product and not purchasing the revenue product. User data entering the purchase page to purchase the revenue product is used as a positive sample of user data, and user data entering the purchase page to not purchase the revenue product is used as a negative sample of user data.
Specifically, the terminal is provided with an application program, a server in communication connection with the terminal collects information such as shared object data, user behavior data, data of a user purchasing a revenue product, user attribute data, a user registration city and the like, and the server stores the collected information to construct a user data sample. And the purchase behavior of the user includes purchasing and not purchasing the revenue product, the user data sample set includes a positive sample of user data and a negative sample of user data.
S420, labeling a first category value of purchasing behavior and recommended price of the revenue product in each user data positive sample.
The positive sample of the user data comprises recommended prices of the revenue products, wherein the recommended prices are the prices of the revenue products displayed to the user by the purchase page when the user enters the purchase page. Specifically, the user data entering the purchase page to purchase the revenue product is used as a positive sample of the user data, the purchase behavior of the revenue product is provided with a corresponding first class value, and the positive sample of the user data is marked by using the first class value. And the recommended price of the revenue product needs to be marked. Namely, the labels corresponding to the positive sample of the user data are the first class value of the purchasing behavior and the recommended price of the revenue product respectively.
S430, labeling the second class value of the purchasing behavior and the recommended price of the revenue product in each user data negative sample.
The user data negative sample comprises recommended prices of the revenue products, wherein the recommended prices are the prices of the revenue products displayed to the user by the purchase page when the user enters the purchase page. Specifically, the user data entering the purchase page and not purchasing the revenue product is used as a negative sample of the user data, the purchase behavior of not purchasing the revenue product is provided with a corresponding second class value, and the positive sample of the user data is marked by using the second class value. And the recommended price of the revenue product needs to be marked. Namely, the labels corresponding to the negative sample of the user data are respectively the second class value of the purchasing behavior and the recommended price of the revenue product.
S440, training a decision tree forest model according to each user data positive sample, each user data negative sample, a first class value and a recommended price corresponding to each user data positive sample, and a second class value and a recommended price corresponding to each user data negative sample.
Specifically, the structure of the decision tree forest model may be set through a server or other computer equipment, the user data sample set includes a positive user data sample and a negative user data sample, the labels corresponding to the positive user data sample are the first category value of the purchasing behavior and the recommended price of the revenue product, and the labels corresponding to the negative user data sample are the second category value of the purchasing behavior and the recommended price of the revenue product. The server trains the decision tree forest model by using each user data positive sample, each user data negative sample, the first class value and the recommended price corresponding to each user data positive sample, and the second class value and the recommended price corresponding to each user data negative sample. And adjusting model parameters of the decision tree forest model according to the difference between the result output by the decision tree forest model and the label value, and continuing training until the training stopping condition is met.
For example, the model may be optimized by setting parameters such as depth of the decision tree, minimum number of samples per leaf node, number of iterations, learning step size, etc. For example, the depth of the decision tree is set to be 10 layers, the minimum sample number of each leaf node can be hundreds of thousands to 2000 thousands, the iteration number is 500, and the learning step size is 0.1.
In this embodiment, a user data sample set is constructed, and the user data sample set includes a positive user data sample and a negative user data sample; labeling a first class value of purchasing behavior and recommended price of the revenue product in each user data positive sample; labeling a second class value of purchasing behavior and recommended price of the revenue product in each user data negative sample; the decision tree forest model is trained by utilizing each user data positive sample, each user data negative sample, the first class value and the recommended price corresponding to each user data positive sample and the second class value and the recommended price corresponding to each user data negative sample, so that the performance of the decision tree forest model is improved, and the accuracy of a prediction result is ensured.
In one embodiment, as shown in FIG. 5, a negative sample of user data is constructed, comprising the steps of:
S510, collecting user data samples corresponding to the second class values; the user data sample includes a time to purchase the page;
s520, screening the user data samples corresponding to the second category value according to the user identification and the time for entering the purchase page and a preset rule;
s530, constructing a user data negative sample by using the user data sample corresponding to the second class value obtained by screening.
In this case, since the user's behavior into the purchase page may include much noise, not all of the user's behavior into the purchase page without purchasing revenue products may be used to train the decision tree forest model. In particular, repeated operation acts frequently issued by the user during a period of time. For example, user a may enter the purchase page many times within a few days before and after purchasing the revenue product, and none of them purchase the revenue product, and these user data entered into the purchase page cannot all be used as negative samples. As another example, user B may enter the purchase page for several consecutive days but eventually not purchase revenue products, and again cannot use all of the user data entered into the purchase page as negative samples, but only one of them. For another example, user C may enter the purchase page many times a few days before purchasing the revenue product, but not purchasing the revenue product, and eventually the user purchases the revenue product at the same recommended price, which may not indicate that the user C cannot receive the recommended price, and therefore, the user data entered into the purchase page cannot all be used as a negative sample. If these noise data frequently entered into the purchase page are all used as negative samples, this will not only be consistent with objective rules, but will also affect the training of the model. Therefore, the user data samples corresponding to the second class value need to be filtered.
Specifically, the server or other computer device collects a user data sample corresponding to the second category value, that is, a user data sample corresponding to the user entering the purchase page without purchasing the revenue product. And the server will collect the time the user entered the purchase page, each user data sample includes the time the user entered the purchase page. In order to reduce the influence of frequently operated user data on user data with low operation frequency, the server screens the user data sample corresponding to the second class value according to a preset rule according to the user identification and the time of entering the purchase page so as to filter out the frequently operated user data or select one from the frequently operated user data for use. And the server constructs a user data negative sample by using the user data sample corresponding to the second class value obtained by screening.
In the embodiment, the user data samples corresponding to the purchase pages, which are not purchased by the user, are screened, so that the influence of noise is reduced, the accuracy of the samples used by the training model is improved, the performance of the decision tree forest model is improved, and the accuracy of the prediction result is ensured.
In one embodiment, the shared item is a shared bicycle. The revenue product may be a bicycle month card and the probability of being purchased of the revenue product may be a card purchase rate. The user data sample also includes at least one of user riding data, data of a user purchasing an revenue product, user attribute data, user registered city, data affecting user riding intent, user behavior data occurring within a purchase page.
In particular, predictions of monthly card purchases and recommended prices for a bicycle require the use of a lot of user data to characterize the user. Such as the following:
1) User riding data such as total number of rides since user history, latest number of rides, number of rides in the validity period after user purchased card historically, user average riding time, etc.
2) The user purchase history, such as the number of times the user historically purchased the card, the price distribution, and the like.
3) The user recharge consumption history, such as the user recharge amount, etc.
4) The user is always at the point. Such as POI (Point of Interest) information of where the user often rides.
5) User basic attributes such as gender, age, etc.
6) The user registers for cities, frequently riding cities.
7) The purchase page presents the recommended price to the user.
8) Weather, holidays, etc., affect the user's willingness to ride.
In one embodiment, the decision tree forest model is a LightGBM model, and the LightGBM model operates in a distributed computing environment.
Illustratively, taking a shared bicycle as an example, first, the algorithm problem needs to be abstracted according to a specific service scenario. The business scenario requires that the probability of purchasing the card for the user under different bicycle month card pricing conditions is calculated, so that a two-class problem can be constructed, namely, whether the user can purchase the bicycle month card at a given price is estimated. The training time tag can be set to 0 and 1 (0 indicates that the bicycle month card is purchased, and 1 indicates that the bicycle month card is not purchased), and meanwhile the model outputs the probability that the user purchases the bicycle month card. A LightGBM (Light Gradient Boosting Machine) model, which is relatively common in the industry at present, can be selected. The LightGBM model is a gradient enhancement framework that uses decision tree based learning algorithms. The LightGBM model is a boosting integrated decision tree forest model, and is optimized on the basis of the XGboost (eXtreme Gradient Boosting) model, so that training learning efficiency can be greatly improved on the premise of keeping XGboost prediction performance.
Further, since the data volume of user data is large, a single machine model cannot quickly predict massive data, and thus a distributed model such as MMLSpark (Microsoft Machine Learning Library for Apache, machine learning library for Apache Spark) needs to be selected for learning and prediction.
In one embodiment, the present application provides a method for processing a price of a revenue product, taking as an example the operation of triggering a decision tree forest model and determining a recommended price of the revenue product when a user enters a purchase page, as shown in fig. 6, the method includes the following steps:
s610, acquiring configuration prices of the revenue products and operation instructions of purchasing pages of the revenue products; the operation instruction carries a user identification.
Specifically, the server stores configuration prices of the revenue products in local data, and the server obtains the configuration prices of the revenue products from a database. The terminal displays an interface of an application program, and the server acquires an operation instruction of entering a purchase page of the revenue product in response to an operation request sent by a user in the application program interface, wherein the operation instruction carries a user identifier.
S620, acquiring user history data of the shared object according to the user identification.
Specifically, the server collects and stores user history data at the server or at a server communicatively coupled to the server. When the server receives an operation instruction for entering a purchase page of the revenue product, the server searches and acquires user history data of the shared object from a corresponding database according to a user identifier carried by the operation instruction.
S630, inputting the user history data into a decision tree forest model for prediction, and obtaining a plurality of prices of the revenue product and the purchase probability corresponding to each price.
Specifically, the decision tree forest model is deployed in the server, when the server receives an operation instruction of entering a purchase page of the revenue product, the operation of the decision tree forest model is automatically triggered, the server inputs the acquired user history data into the decision tree forest model to conduct feature division, a plurality of prices of the corresponding revenue product are predicted, and the probability that the user purchases the revenue product at the price is predicted.
S640, calculating expected values according to the prices and the purchased probabilities corresponding to the prices to obtain the expected values corresponding to the prices;
s650, selecting the price corresponding to the maximum expected value from expected values corresponding to the prices as the recommended price of the revenue product.
Specifically, after obtaining a plurality of prices of the revenue product and the purchased probabilities corresponding to the prices through the decision tree forest model, the server calculates the product of the plurality of prices and the purchased probabilities corresponding to the prices to obtain expected values corresponding to the prices. In order to maximize the interests of both the user and the service party, a price corresponding to the maximum expected value is selected as a recommended price of the revenue product from the expected values corresponding to the prices.
S660, calculating according to the recommended price and the configuration price of the revenue product to obtain the preferential amount corresponding to the purchased revenue product; and S670, generating an electronic ticket corresponding to the purchased product according to the preferential amount, and sending the electronic ticket to a terminal corresponding to the user identification.
Specifically, the server locally or a server in communication connection with the server stores the configuration price of the revenue product in advance, and the configuration price of the revenue product is acquired from the server locally or the server in communication connection with the server. Because the recommended price of the revenue product is predicted in advance according to the historical data of the user, the server calculates according to the searched configuration price and the predicted recommended price, after calculating to obtain the preferential amount corresponding to the purchased revenue product, the server generates the electronic coupon corresponding to the purchased revenue product according to the preferential amount, and sends the electronic coupon to the terminal corresponding to the user identifier.
In one embodiment, the application provides a method for processing a price of a revenue product, wherein the purchase behavior of the revenue product includes a purchase and a non-purchase, corresponding to a first category value and a second category value, respectively. The method comprises the following steps:
s702, constructing a positive sample of user data.
S704, labeling a first category value of purchasing behavior and recommended price of the revenue product in each user data positive sample.
S706, collecting user data samples corresponding to the second class values.
Wherein the user data sample includes a time to purchase the page.
And S708, screening the user data samples corresponding to the second class value according to the user identification and the time for entering the purchase page and a preset rule.
S710, constructing a user data negative sample by using the user data sample corresponding to the second class value obtained by screening.
S712, marking a second class value of the purchasing behavior and a recommended price of the revenue product in each user data negative sample;
s714, training a decision tree forest model according to each user data positive sample, each user data negative sample, a first class value and a recommended price corresponding to each user data positive sample, and a second class value and a recommended price corresponding to each user data negative sample.
S716, acquiring user history data of the shared object;
wherein the user history data comprises a user identification.
S718, inputting the user history data into a decision tree forest model for prediction, and obtaining a plurality of prices of the revenue product and the purchase probability corresponding to each price.
S720, calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and obtaining the expected values corresponding to the prices.
S722, selecting the price corresponding to the maximum expected value from expected values corresponding to the prices as the recommended price of the revenue product.
And S724, saving the recommended price, the user identification and the corresponding relation between the recommended price and the user identification into a database.
S726, acquiring the configuration price of the revenue product and the operation instruction of the purchase page of the revenue product.
The operation instruction carries a user identifier;
s728, searching the corresponding recommended price in the database according to the user identification.
And S730, calculating according to the searched recommended price and the configuration price to obtain the preferential amount corresponding to the purchased revenue product.
S732, generating an electronic ticket corresponding to the purchased revenue product according to the preferential amount, and sending the electronic ticket to a terminal corresponding to the user identification.
It should be understood that, although the steps in the above-described flowcharts are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described above may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, and the order of execution of the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with at least a part of the sub-steps or stages of other steps or other steps.
In one embodiment, as shown in FIG. 7, a processing device for revenue product prices is provided. The processing apparatus 700 includes an acquisition module 710, a prediction module 720, a calculation module 730, and a save module 740.
Wherein:
an acquisition module 710 for acquiring user history data of the shared item; the user history data includes a user identification;
the prediction module 720 is configured to input user history data into a decision tree forest model for prediction, so as to obtain a plurality of prices of the revenue product and purchase probabilities corresponding to the prices;
The calculating module 730 is configured to calculate an expected value according to each price and the purchased probability corresponding to each price, and determine a recommended price of the revenue product according to the calculated expected value;
the storage module 740 is configured to store the recommended price, the user identifier, and a correspondence between the recommended price and the user identifier in the database.
For a specific limitation of the processing device for the price of the revenue product, reference may be made to the limitation of the processing method for the price of the revenue product hereinabove, and the description thereof will not be repeated here. The above-mentioned modules in the processing device for the price of the revenue product may be implemented in whole or in part by software, hardware or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method of processing a price for a revenue product. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method steps of the above embodiments when the computer program is executed.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, implements the method steps of the above embodiments.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A data processing method for transmitting an electronic ticket for a product, the method being executed in a server, the server performing data interaction with a terminal, the method comprising:
acquiring user history data of the shared object recorded by the terminal application program; the user history data comprises user identifications;
inputting the user history data into a decision tree forest model for prediction to obtain a plurality of prices of the revenue product and the purchased probability corresponding to each price, wherein the decision tree forest model is obtained by training by utilizing constructed positive samples of each user data, negative samples of each user data, first class values and recommended prices corresponding to the positive samples of each user data, second class values and recommended prices corresponding to the negative samples of each user data, and the negative samples of each user data at least comprise screening treatment for the samples of the user data corresponding to the revenue product which is not purchased by the user entering a purchase page based on the time of entering the purchase page;
Calculating expected values according to the prices and the purchased probabilities corresponding to the prices, and determining recommended prices of the revenue products according to the calculated expected values, wherein the calculation of the expected values comprises the steps of calculating products of the prices and the purchased probabilities corresponding to the prices to obtain expected values corresponding to the prices;
storing the recommended price, the user identification and the corresponding relation between the recommended price and the user identification into a database;
receiving an operation instruction sent by a terminal and entering a purchase page of an revenue product, and acquiring a configuration price of the revenue product, wherein the operation instruction carries a user identifier;
searching a corresponding recommended price in the database according to the user identification;
calculating according to the searched recommended price and the configuration price to obtain a preferential amount corresponding to the purchased revenue product;
and generating an electronic ticket corresponding to the purchased revenue product according to the preferential amount, and sending the electronic ticket to a terminal corresponding to the user identifier.
2. The method of claim 1, wherein the calculating the expected value according to each price and the purchase probability corresponding to each price, and determining the recommended price of the revenue product according to the calculated expected value comprises:
Calculating expected values according to the prices and the purchased probabilities corresponding to the prices to obtain the expected values corresponding to the prices;
and selecting the price corresponding to the maximum expected value from expected values corresponding to the prices as the recommended price of the revenue product.
3. The method of claim 1, wherein the calculating means of the preference amount includes one of:
calculating the difference between the recommended price and the configured price, wherein correspondingly, generating the electronic coupon corresponding to the purchased revenue product according to the preferential amount comprises generating a coupon with the amount equal to the difference;
and calculating the ratio of the recommended price to the configuration price, wherein correspondingly, generating the electronic coupon corresponding to the purchased revenue product according to the preferential amount comprises generating a discount coupon with the amount equal to the ratio.
4. The method of claim 1, wherein the step of generating the decision tree forest model comprises:
constructing a user data sample set, wherein the user data sample set comprises a user data positive sample and a user data negative sample;
labeling a first class value of purchasing behavior and a recommended price of the revenue product in each positive sample of the user data;
Labeling a second class value of the purchasing behavior and the recommended price of the revenue product in each user data negative sample;
training the decision tree forest model according to the positive user data samples, the negative user data samples, the first class values and recommended prices corresponding to the positive user data samples and the second class values and recommended prices corresponding to the negative user data samples.
5. The method of claim 4, wherein said constructing a negative sample of user data comprises:
collecting user data samples corresponding to the second class values; the user data sample includes a time to enter the purchase page;
screening the user data samples corresponding to the second class values according to the user identification and the time for entering the purchase page and a preset rule;
and constructing a user data negative sample by using the user data sample corresponding to the second category value obtained by screening.
6. The method of claim 5, wherein the shared item is a shared bicycle; the user data sample also includes at least one of user riding data, data of a user purchasing the revenue product, user attribute data, user registered city, data affecting user riding intent, user behavior data occurring within the purchase page.
7. The method of any one of claims 1 to 6, wherein the decision tree forest model is a LightGBM model, and the LightGBM model operates in a distributed computing environment.
8. A data processing apparatus for transmitting electronic coupons for products, said apparatus comprising:
the acquisition module is used for acquiring the user history data of the shared object recorded by the terminal application program; the user history data comprises user identifications; the operation instruction which is sent by the terminal and enters the purchase page of the revenue product is also received, the configuration price of the revenue product is obtained, and the operation instruction carries a user identifier;
the prediction module is used for inputting the user history data into a decision tree forest model to predict, so as to obtain a plurality of prices of the revenue product and the purchase probability corresponding to each price; the decision tree forest model is trained by utilizing constructed positive samples of all user data, negative samples of all user data, first class values and recommended prices corresponding to the positive samples of all user data, second class values and recommended prices corresponding to the negative samples of all user data, wherein the negative samples of all user data at least comprise screening processing of the user data samples corresponding to the fact that the user enters a purchase page and does not purchase revenue products based on time of entering the purchase page;
The calculation module is used for calculating expected values according to the prices and the purchased probabilities corresponding to the prices, determining recommended prices of the revenue products according to the calculated expected values, wherein the calculation of the expected values comprises the steps of calculating products of the prices and the purchased probabilities corresponding to the prices to obtain expected values corresponding to the prices; the electronic coupon corresponding to the purchased revenue product is generated according to the preferential amount and is sent to the terminal corresponding to the user identifier;
and the storage module is used for storing the recommended price, the user identifier and the corresponding relation between the recommended price and the user identifier into a database.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220870.9A CN110992097B (en) | 2019-12-03 | 2019-12-03 | Processing method and device for price of revenue product, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220870.9A CN110992097B (en) | 2019-12-03 | 2019-12-03 | Processing method and device for price of revenue product, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110992097A CN110992097A (en) | 2020-04-10 |
| CN110992097B true CN110992097B (en) | 2024-02-13 |
Family
ID=70089556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911220870.9A Active CN110992097B (en) | 2019-12-03 | 2019-12-03 | Processing method and device for price of revenue product, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110992097B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111556205A (en) * | 2020-04-21 | 2020-08-18 | 北京思特奇信息技术股份有限公司 | Method and system for recommending telecommunication products to target users |
| CN111833094A (en) * | 2020-05-29 | 2020-10-27 | 摩拜(北京)信息技术有限公司 | Data processing method, device, equipment and storage medium |
| CN111768239A (en) * | 2020-06-29 | 2020-10-13 | 腾讯科技（深圳）有限公司 | Property recommendation method, device, system, server and storage medium |
| CN112800329A (en) * | 2021-01-29 | 2021-05-14 | 深圳维创乐科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN116468475A (en) * | 2023-06-19 | 2023-07-21 | 快电动力(北京)新能源科技有限公司 | Charging card recommendation method and device, electronic equipment and readable storage medium |
| CN116542749A (en) * | 2023-07-06 | 2023-08-04 | 深圳依时货拉拉科技有限公司 | Commodity recommendation and pricing method, commodity recommendation and pricing device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
| CN108537382A (en) * | 2018-04-09 | 2018-09-14 | 成都易商商盟数据服务有限公司 | A kind of electric business upward price trend prediction technique and system |
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN108985809A (en) * | 2017-06-02 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Motivate method, apparatus, electronic equipment and the storage medium of push |
| CN109598560A (en) * | 2018-12-29 | 2019-04-09 | 河源弘稼农业科技有限公司 | A kind of processing method and relevant apparatus of favor information |
| CN109711887A (en) * | 2018-12-28 | 2019-05-03 | 拉扎斯网络科技（上海）有限公司 | Generation method and device of mall recommendation list, electronic equipment and computer medium |
| CN109919703A (en) * | 2019-01-16 | 2019-06-21 | 浙江口碑网络技术有限公司 | Store information processing method, device, system, storage medium and computer equipment |
| CN110443649A (en) * | 2019-08-02 | 2019-11-12 | 杭州讯酷科技有限公司 | Intelligent recommendation method, system and vending machine based on matching algorithm |
-
2019
- 2019-12-03 CN CN201911220870.9A patent/CN110992097B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985809A (en) * | 2017-06-02 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Motivate method, apparatus, electronic equipment and the storage medium of push |
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
| CN108537382A (en) * | 2018-04-09 | 2018-09-14 | 成都易商商盟数据服务有限公司 | A kind of electric business upward price trend prediction technique and system |
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN109711887A (en) * | 2018-12-28 | 2019-05-03 | 拉扎斯网络科技（上海）有限公司 | Generation method and device of mall recommendation list, electronic equipment and computer medium |
| CN109598560A (en) * | 2018-12-29 | 2019-04-09 | 河源弘稼农业科技有限公司 | A kind of processing method and relevant apparatus of favor information |
| CN109919703A (en) * | 2019-01-16 | 2019-06-21 | 浙江口碑网络技术有限公司 | Store information processing method, device, system, storage medium and computer equipment |
| CN110443649A (en) * | 2019-08-02 | 2019-11-12 | 杭州讯酷科技有限公司 | Intelligent recommendation method, system and vending machine based on matching algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110992097A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110992097B (en) | Processing method and device for price of revenue product, computer equipment and storage medium | |
| CN109582876B (en) | Tourist industry user portrait construction method and device and computer equipment | |
| US10872298B2 (en) | Machine learning and prediction using graph communities | |
| CN111080398B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| CN108205768B (en) | Database establishing method, data recommending device, equipment and storage medium | |
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN111401777B (en) | Enterprise risk assessment method, enterprise risk assessment device, terminal equipment and storage medium | |
| CN110210882A (en) | Promote position matching process and device, promotion message methods of exhibiting and device | |
| CN112330412B (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN111626832A (en) | Product recommendation method and device and computer equipment | |
| CN116823409B (en) | Intelligent screening method and system based on target search data | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| Viallard et al. | Assessing the evolution of transit user behavior from smart card data | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN110555749B (en) | Credit behavior prediction method and device based on neural network | |
| WO2023070844A1 (en) | Intelligent design method for personalized discount coupon, and electronic apparatus and storage medium | |
| CN113051480A (en) | Resource pushing method and device, electronic equipment and storage medium | |
| CN110674391A (en) | Product data pushing method and system based on big data and computer equipment | |
| US10115125B2 (en) | Determining traffic quality using event-based traffic scoring | |
| CN114116802A (en) | Data processing method, device, equipment and storage medium of Flink computing framework | |
| CN113592605A (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN112579910A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| Cho et al. | Enhancing the accuracy of peak hourly demand in bike-sharing systems using a graph convolutional network with public transit usage data | |
| CN111325614B (en) | Recommendation method and device of electronic object and electronic equipment | |
| CN117273800A (en) | Marketing strategy generation method, device, 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 |