CN111242713A - Information pushing method and device - Google Patents
Information pushing method and device Download PDFInfo
- Publication number
- CN111242713A CN111242713A CN201811444018.5A CN201811444018A CN111242713A CN 111242713 A CN111242713 A CN 111242713A CN 201811444018 A CN201811444018 A CN 201811444018A CN 111242713 A CN111242713 A CN 111242713A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- information
- time period
- shopping cart
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000010801 machine learning Methods 0.000 claims abstract description 33
- 238000009826 distribution Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005304 joining Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Cash Registers Or Receiving Machines (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an information pushing method and device, comprising the following steps: generating corresponding product data and state identification of the product data according to product information of a user in a shopping cart in a preset historical time period and order data generated in the historical time period; training a preset machine learning model according to the product data and the state identification of the product data; for each product which is added into the shopping cart by the user within the latest preset first time period, predicting whether the product will be placed by the user by using the machine learning model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user. By adopting the invention, the accuracy of information push can be improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an information push method and apparatus.
Background
At present, in a scheme of data mining by an e-commerce platform based on commodity data of a user shopping cart, commodity data of the user shopping cart is usually directly extracted, and personalized recommendation of information, analysis and positioning of commodities favored by the user, portrait analysis of the user and the like are performed based on the data.
In the process of implementing the present invention, the inventor finds that the existing data mining scheme based on shopping cart data at least has the following problems:
firstly, the commodity which the user adds into the shopping cart in a certain time period cannot be equal to the commodity which the user really is interested in to a certain extent, the commodity is possibly in a to-be-selected state, and the shopping cart is possibly not cleaned in time after the commodity is purchased in other channels. Therefore, the above-described data mining for personalized recommendation directly based on user shopping cart data is of limited accuracy.
Secondly, the goods which the user is interested in are not invariable and often change along with the time, and the existing data mining scheme based on the shopping cart does not consider the potential rule of certain goods required by the user in a certain time period according to the time dimension, so that the accuracy of data mining is also influenced.
Therefore, the existing data mining scheme based on shopping cart data has the problem of low accuracy, and accurate information matching and pushing based on data mining results cannot be carried out.
Disclosure of Invention
In view of the above, the present invention provides an information pushing method and apparatus, which can improve the accuracy of information pushing.
In order to achieve the above purpose, the embodiment of the present invention provides a technical solution:
an information push method, comprising:
generating corresponding product data and state identification of the product data according to product information of a user in a shopping cart in a preset historical time period and order data generated in the historical time period;
training a preset machine learning model according to the product data and the state identification of the product data;
for each product which is added into the shopping cart by the user within the latest preset first time period, predicting whether the product will be placed by the user by using the machine learning model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
Preferably, the generating the corresponding product data and the state identifier of the product data according to the product information that the user joins the shopping cart in the preset historical time period and the order data generated in the historical time period includes:
generating corresponding product data according to the product information of the shopping cart added by the user in the historical time period;
judging whether each product placed in a shopping cart in the historical time period is placed by the user according to order data generated by the user in the historical time period;
and identifying the state of the corresponding product data according to the judgment result.
Preferably, the generating corresponding product data according to the product information that the user joins the shopping cart in the historical time period includes:
and for each product added into the shopping cart by the user in the historical time period, connecting the time information of the product added into the shopping cart by the user with the class identification information of the product at the preset level in series to obtain the product data corresponding to the product.
Preferably, the time information is month information, and the category identification information at the preset level is third-level category identification information.
Preferably, the historical time period is a latest preset second time period, and the duration of the second time period is greater than the duration of the first time period.
Preferably, the first period of time is one week and the second period of time is one month.
Preferably, according to the predicted result, matching corresponding product push information for the user includes:
when the predicted result is that the user can order, the matched product push information is related product information matched with a corresponding product for use;
and when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
Preferably, the machine learning model is a hidden markov model.
An information pushing apparatus comprising:
the system comprises a sample data acquisition unit, a state identification generation unit and a display unit, wherein the sample data acquisition unit is used for generating corresponding product data and state identification of the product data according to product information of a shopping cart added by a user within a preset historical time period and order data generated within the historical time period;
the model training unit is used for training a preset machine learning model according to the product data and the state identification of the product data;
the predicting and pushing unit is used for predicting whether each product which is added into the shopping cart by the user in the latest preset first time period is ordered by the user by utilizing the machine learning model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
Preferably, the sample data obtaining unit is configured to generate corresponding product data according to product information that the user joins the shopping cart in the historical time period; judging whether each product placed in a shopping cart in the historical time period is placed by the user according to order data generated by the user in the historical time period; and identifying the state of the corresponding product data according to the judgment result.
Preferably, the sample data obtaining unit is configured to, for each product that the user adds to the shopping cart within the historical time period, concatenate time information of the product that the user adds to the shopping cart with the product identification information of the preset level, and obtain the product data corresponding to the product.
Preferably, the time information is month information, and the category identification information at the preset level is third-level category identification information.
Preferably, the historical time period is a latest preset second time period, and the duration of the second time period is greater than the duration of the first time period.
Preferably, the first period of time is one week and the second period of time is one month.
Preferably, the predicting and pushing unit is configured to, when the predicted result is that the order will be placed by the user, obtain the matched product pushing information as related product information for matching use with the corresponding product; and when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
Preferably, the machine learning model is a hidden markov model.
An information pushing apparatus comprising:
a memory; and a processor coupled to the memory, the processor configured to execute the information pushing method as described above based on instructions stored in the memory.
A computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the information pushing method described above.
In summary, the information pushing method and the information pushing device provided by the invention utilize the machine learning model to perform data mining on products of a user who puts in a shopping cart in a historical time period and the actual ordering situation of the user, so as to obtain the machine learning model matched with the actual demand of the user, predict whether the products of the user who puts in the shopping cart in the recent time period will be ordered based on the model, and finally push the matched product information for the user based on the prediction result, so that the product pushing information is matched with the actual demand of the user, the accuracy of information pushing is improved, the user demand is met to the greatest extent, and the order conversion rate of the products can be effectively improved.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of step 101 in FIG. 1;
fig. 3 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a schematic flow chart of a method according to an embodiment of the present invention, and as shown in fig. 1, the information push method implemented in the embodiment mainly includes:
In this step, corresponding product data and state identifiers of the product data are generated for the user according to the product information of the user entering the shopping cart in a certain historical time period and the order data generated by the user in the time period, so that the machine learning model can be trained in the subsequent steps based on the data and the state identifiers, and whether the product placed in the shopping cart by the user can be purchased or not can be estimated based on the trained machine learning model.
It should be noted that, in this step, data for performing machine learning model training is generated based on the information of the products placed in the shopping cart by the user within a certain historical time period and the information of whether the products are finally placed for purchase, so that the machine learning model obtained by training can be matched with the actual shopping preference of the user, and the accuracy of predicting whether the products are placed for purchase based on the model in the following step can be further increased.
Preferably, as shown in fig. 2, step 101 can be implemented by:
and step 1011, generating corresponding product data according to the product information of the shopping cart added by the user in the historical time period.
Preferably, in order to generate data favorable for training the machine learning model quickly and accurately, step 1011 can be implemented by the following method:
and for each product added into the shopping cart by the user in the historical time period, connecting the time information of the product added into the shopping cart by the user with the class identification information of the product at the preset level in series to obtain the product data corresponding to the product.
By adopting the method, the corresponding product data can be generated directly based on the attribute information of the product, so that the data for model training can be directly generated without manual participation, and manpower and material resources are effectively saved.
In the method, the product data is obtained by combining the time information and the category identification information.
Preferably, the time information may be month information, but is not limited thereto.
Preferably, the category identification information of the preset level may be three-level category identification information, but is not limited thereto.
For example, for a product that is added to a shopping cart, the corresponding product data is 0112313, indicating that month 01 has added a product with a tertiary item identification of 12313.
Preferably, the historical time period is used for limiting a time range corresponding to the acquisition of the product data used for the machine learning model training. Specifically, a suitable time length may be selected by a person skilled in the art according to actual needs, for example, the second time period may be the latest preset time period. The second period of time may be one month and correspondingly, the historical period of time will be the last month. Namely, based on the product data put into the shopping cart by the user in the last month and the order data generated by the user in the last month, the corresponding product data and the state identifier of the product data are generated.
And 1013, identifying the state of the corresponding product data according to the judgment result.
The method comprises the following steps of identifying whether each product placed into the shopping cart by the user in the historical time period is purchased by the user, namely generating a corresponding label for product data used for training a machine learning model so as to train the model.
And 102, training a preset machine learning model according to the product data and the state identification of the product data.
The specific implementation method of this step is known to those skilled in the art and will not be described herein.
Preferably, the machine learning model may be a hidden markov model.
For ease of understanding, the hidden markov model is described below.
The hidden Markov model is represented by an initial state probability sequence pi, a state transition matrix A and an observation probability matrix B. In addition, a hidden state and a displayed state exist, the hidden state cannot be directly observed, and the displayed state can be directly observed. The formal definition of the hidden markov model can be represented by the triplet λ ═ (pi, a, B):
wherein:
π={πi},πi=P(q1=si): initial state distribution, representing state s at time t-1iThe probability of (c).
A={aij},aij=P(qt+1=sj|qt=si): a state transition probability matrix wherein aijIndicating that time t is in state siAt time t +1 is in state sjThe probability of (c).
B={bik},bik=P(ot=vk|qt=si): observation probability matrix representing state s at time tiProduction under conditions of (v)kThe probability of (c).
The hidden Markov model has the following basic characteristics: the method comprises the steps that a hidden state and an explicit state exist, and the hidden state and the explicit state respectively correspond to data of a user actually placing an order and data of products of the user entering the shopping cart in the embodiment of the invention, namely the products of the user entering the shopping cart are observable, and the products of the actually placing the order are not observable before the actual placing of the order. The most probable hidden states in some display states are predicted through observation and statistics of the display states, namely whether the products added into the shopping cart by the user are finally ordered or not is predicted through statistics of product data of the user added into the shopping cart. The historical display state data in this embodiment may be formed by combining the month of joining the shopping cart with the item class id of level 3, such as 0112313 indicating that the class id of level 3 of the item joined to the shopping cart in month 3 is 12313. The data of the history hidden state is information of whether data such as 0112313 in a certain shopping cart is finally ordered, 0 is used for not ordering, and 1 is used for ordering.
In practical applications, a person skilled in the art may also choose to implement the embodiments of the present invention by using other machine learning models, and is not limited to the hidden markov model.
103, predicting whether each product added into the shopping cart by the user in a first time period preset recently is predicted by using the machine learning model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
In this step, it is predicted whether each product that the user has entered the shopping cart in the last period of time will be placed an order by the user based on the machine learning model obtained in step 102.
In the specific implementation, for each product that the user joins the shopping cart in the first time period preset recently, corresponding product data needs to be generated first, and then the product data is input into the model, so that the prediction result of whether the product will be placed by the user can be obtained. In the same step 1011, the product data generating method may be used to construct the product data by combining the time information of the product entering the shopping cart with the category identification information of the preset level of the product. For example, a 3-grade item identified as 46474 was added at 04 months, and the corresponding product data may be 0446474.
The first time period is used for limiting the product range of the single probability under prediction, and can be set by a person skilled in the art according to actual needs. For example, the last day, several days, or a week may be mentioned.
In order to match the actual need, the duration of the first time period may not be too long, preferably, for example, the first time period is not greater than the duration of the second time period.
Preferably, in step 103, according to the predicted result, matching corresponding product push information for the user:
and when the predicted result is that the order can be placed by the user, the matched product push information is related product information matched with the corresponding product for use.
And when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
By adopting the method, the corresponding product pushing information is matched for the user according to the predicted result, so that the product pushing information is matched with the actual demand of the user, and the order conversion rate of the product can be effectively improved, specifically:
when the product is predicted to be ordered by the user, the corresponding product push information is related product information matched with the corresponding product for use, for example, when the user is predicted to buy a mobile phone, a mobile phone shell can be recommended for the user, and when the user is predicted to buy a jacket, trousers and the like can be recommended for the user.
And when the product is predicted not to be placed by the user, the matched product push information is the coupon distribution information of the corresponding product, so that the product is placed by the user.
According to the method and the device, the machine learning model is used for data mining of products placed in the shopping cart by the user in the recent historical time period and the actual ordering situation of the user, the machine learning model matched with the current actual demand of the user is obtained, whether the products placed in the shopping cart by the user in the recent time period are ordered or not is predicted based on the machine learning model, and finally matched product information is pushed to the user based on the prediction result, so that the product pushing information is matched with the actual demand of the user, the user demand is met to the greatest extent, and the order conversion rate of the products can be effectively improved.
Fig. 3 is a schematic structural diagram of an embodiment of an information pushing apparatus corresponding to the above method embodiment, and as shown in fig. 3, the apparatus includes:
the sample data acquiring unit 301 is configured to generate corresponding product data and a status identifier of the product data according to product information that a user joins the shopping cart in a preset historical time period and order data generated in the historical time period.
A model training unit 302, configured to train a preset machine learning model according to the product data and the state identifier of the product data.
The predicting and pushing unit 303 is configured to predict, by using the machine learning model obtained through the training, whether each product that the user joins in the shopping cart in a first time period that is preset recently will be ordered by the user; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
Preferably, the sample data obtaining unit 301 is configured to generate corresponding product data according to product information that the user joins the shopping cart in the historical time period; judging whether each product placed in a shopping cart in the historical time period is placed by the user according to order data generated by the user in the historical time period; and identifying the state of the corresponding product data according to the judgment result.
Preferably, the sample data obtaining unit 301 is configured to, for each product that the user adds to the shopping cart in the historical time period, concatenate time information of the product that the user adds to the shopping cart with the product identification information at the preset level of the product, and obtain the product data corresponding to the product.
Preferably, the time information is month information, and the category identification information at the preset level is third-level category identification information.
Preferably, the historical time period is a latest preset second time period, and the duration of the second time period is greater than the duration of the first time period.
Preferably, the first period of time is one week and the second period of time is one month.
Preferably, the predicting and pushing unit 303 is configured to, when the predicted result is that the user will order, obtain the matched product pushing information as related product information for matching use with the corresponding product; and when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
Preferably, the machine learning model is a hidden markov model.
An embodiment of the present invention further provides an information pushing apparatus, including:
a memory; and a processor coupled to the memory, the processor configured to execute the information pushing method according to the above embodiment based on the instructions stored in the memory.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the information push method of the embodiment is realized.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (18)
1. An information pushing method, comprising:
generating corresponding product data and state identification of the product data according to product information of a user in a shopping cart in a preset historical time period and order data generated in the historical time period;
training a preset machine learning model according to the product data and the state identification of the product data;
for each product which is added into the shopping cart by the user in a first time period which is preset recently, predicting whether the product will be placed by the user by using the hidden Markov model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
2. The method of claim 1, wherein generating the corresponding product data and the status identifier of the product data according to the product information of the shopping cart entered by the user within the preset historical time period and the order data generated within the historical time period comprises:
generating corresponding product data according to the product information of the shopping cart added by the user in the historical time period;
judging whether each product placed in a shopping cart in the historical time period is placed by the user according to order data generated by the user in the historical time period;
and identifying the state of the corresponding product data according to the judgment result.
3. The method of claim 2, wherein generating corresponding product data based on product information of the user joining the shopping cart during the historical time period comprises:
and for each product added into the shopping cart by the user in the historical time period, connecting the time information of the product added into the shopping cart by the user with the class identification information of the product at the preset level in series to obtain the product data corresponding to the product.
4. The method of claim 3, wherein the time information is month information, and the preset-level class identification information is third-level class identification information.
5. The method of claim 1, wherein the historical period of time is a last predetermined second period of time, the second period of time having a duration greater than the duration of the first period of time.
6. The method of claim 5, wherein the first period of time is one week and the second period of time is one month.
7. The method of claim 1, wherein matching the corresponding product push information for the user according to the predicted result comprises:
when the predicted result is that the user can order, the matched product push information is related product information matched with a corresponding product for use;
and when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
8. The method of claim 1, wherein the machine learning model is a hidden markov model.
9. An information pushing apparatus, comprising:
the system comprises a sample data acquisition unit, a state identification generation unit and a display unit, wherein the sample data acquisition unit is used for generating corresponding product data and state identification of the product data according to product information of a shopping cart added by a user within a preset historical time period and order data generated within the historical time period;
the model training unit is used for training a preset machine learning model according to the product data and the state identification of the product data;
the predicting and pushing unit is used for predicting whether each product which is added into the shopping cart by the user in the latest preset first time period is ordered by the user by utilizing the machine learning model obtained through training; and matching corresponding product pushing information for the user according to the prediction result, and sending the product pushing information to the user.
10. The apparatus according to claim 9, wherein the sample data obtaining unit is configured to generate corresponding product data according to product information that the user joins the shopping cart in the historical time period; judging whether each product placed in a shopping cart in the historical time period is placed by the user according to order data generated by the user in the historical time period; and identifying the state of the corresponding product data according to the judgment result.
11. The apparatus according to claim 10, wherein the sample data obtaining unit is configured to, for each product that the user joins the shopping cart in the historical time period, concatenate time information of joining the product to the shopping cart by the user and class identification information of a preset level of the product, and obtain the product data corresponding to the product.
12. The apparatus of claim 11, wherein the time information is month information, and the category identification information of the preset level is third-level category identification information.
13. The apparatus of claim 9, wherein the historical period of time is a last predetermined second period of time, and wherein the second period of time is greater in duration than the first period of time.
14. The device of claim 13, wherein the first period of time is one week and the second period of time is one month.
15. The apparatus according to claim 9, wherein the predicting and pushing unit is configured to, when the predicted result is that the user will order the product, obtain the matched product pushing information as related product information for matching use with the corresponding product; and when the predicted result is that the order cannot be placed by the user, the matched product push information is the coupon distribution information of the corresponding product.
16. The apparatus of claim 9, wherein the machine learning model is a hidden markov model.
17. An information pushing apparatus, comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of any of claims 1-7 based on instructions stored in the memory.
18. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811444018.5A CN111242713A (en) | 2018-11-29 | 2018-11-29 | Information pushing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811444018.5A CN111242713A (en) | 2018-11-29 | 2018-11-29 | Information pushing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111242713A true CN111242713A (en) | 2020-06-05 |
Family
ID=70879223
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811444018.5A Pending CN111242713A (en) | 2018-11-29 | 2018-11-29 | Information pushing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111242713A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200610A (en) * | 2020-10-10 | 2021-01-08 | 苏州创旅天下信息技术有限公司 | Marketing information delivery method, system and storage medium |
CN112380449A (en) * | 2020-12-03 | 2021-02-19 | 腾讯科技(深圳)有限公司 | Information recommendation method, model training method and related device |
CN113763112A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103824192A (en) * | 2012-08-31 | 2014-05-28 | 埃森哲环球服务有限公司 | Hybrid recommendation system |
US20140351179A1 (en) * | 2013-05-27 | 2014-11-27 | Huawei Technologies Co., Ltd. | Information push method and apparatus |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
CN108805594A (en) * | 2017-04-27 | 2018-11-13 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
-
2018
- 2018-11-29 CN CN201811444018.5A patent/CN111242713A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103824192A (en) * | 2012-08-31 | 2014-05-28 | 埃森哲环球服务有限公司 | Hybrid recommendation system |
US20140351179A1 (en) * | 2013-05-27 | 2014-11-27 | Huawei Technologies Co., Ltd. | Information push method and apparatus |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
CN108805594A (en) * | 2017-04-27 | 2018-11-13 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200610A (en) * | 2020-10-10 | 2021-01-08 | 苏州创旅天下信息技术有限公司 | Marketing information delivery method, system and storage medium |
CN112380449A (en) * | 2020-12-03 | 2021-02-19 | 腾讯科技(深圳)有限公司 | Information recommendation method, model training method and related device |
CN112380449B (en) * | 2020-12-03 | 2021-11-23 | 腾讯科技(深圳)有限公司 | Information recommendation method, model training method and related device |
CN113763112A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222272B (en) | Potential customer mining and recommending method | |
EP3407285B1 (en) | Target user orientation method and device, and computer storage medium | |
CN111080398B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
CN111242713A (en) | Information pushing method and device | |
CN104933084A (en) | Method, apparatus and device for acquiring answer information | |
CN104615721B (en) | For the method and system based on return of goods related information Recommendations | |
CN109582876A (en) | Tourism industry user portrait building method, device and computer equipment | |
CN110322093B (en) | Information processing method, information display method, information processing device and computing equipment | |
US11928709B2 (en) | Method and apparatus for automatically providing advertisements | |
CN112365283B (en) | Coupon issuing method and device, terminal equipment and storage medium | |
CN104951456A (en) | Method, device and equipment used for obtaining answer information | |
CN108932625B (en) | User behavior data analysis method, device, medium and electronic equipment | |
CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
CN111681085A (en) | Commodity pushing method and device, server and readable storage medium | |
CN107908742A (en) | Method and apparatus for output information | |
CN111680213B (en) | Information recommendation method, data processing method and device | |
JP5814303B2 (en) | Revenue index value generation system and revenue index value generation method | |
CN109146606B (en) | Brand recommendation method, electronic equipment, storage medium and system | |
CN114186024A (en) | Recommendation method and device | |
CN111967970B (en) | Bank product recommendation method and device based on spark platform | |
CN111523315A (en) | Data processing method, text recognition device and computer equipment | |
CN111787042B (en) | Method and device for pushing information | |
CN110825960A (en) | Learning content recommendation method and device | |
JP6062514B2 (en) | Revenue index value generation system and revenue index value generation method | |
CN111784091B (en) | Method and device for processing information |
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 |