CN117493690A - Data pushing method and device, electronic equipment and storage medium - Google Patents

Data pushing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117493690A
CN117493690A CN202311569735.1A CN202311569735A CN117493690A CN 117493690 A CN117493690 A CN 117493690A CN 202311569735 A CN202311569735 A CN 202311569735A CN 117493690 A CN117493690 A CN 117493690A
Authority
CN
China
Prior art keywords
data
pushing
target
model
push
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
Application number
CN202311569735.1A
Other languages
Chinese (zh)
Inventor
刘舒萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lianren Healthcare Big Data Technology Co Ltd
Original Assignee
Lianren Healthcare Big Data Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Lianren Healthcare Big Data Technology Co Ltd filed Critical Lianren Healthcare Big Data Technology Co Ltd
Priority to CN202311569735.1A priority Critical patent/CN117493690A/en
Publication of CN117493690A publication Critical patent/CN117493690A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services

Abstract

The invention discloses a data pushing method, a data pushing device, electronic equipment and a storage medium. The data pushing method comprises the following steps: determining a target pushing object and data to be pushed corresponding to the target pushing object; carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, and the conversion rate model is determined based on a first conversion model and a second conversion model; and determining target push data based on the target push score, and pushing the target push data to the target push object. Based on the technical scheme of the embodiment of the invention, the pushing matching precision of the fine-discharge pushing model is improved, the accuracy of the determined target pushing score is improved, and the accuracy of data pushing is improved.

Description

Data pushing method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of computer applications, and in particular, to a data pushing method, a data pushing device, an electronic device, and a storage medium.
Background
Due to the introduction of some new technologies such as deep learning, an actual data pushing system generally has four links, which are respectively: recall, coarse and fine rows, and rearrangement. In the fine-ranking link, click rate (CTR) and conversion rate (CVR) models generally score items respectively, and output scores are given to rearrangement to obtain final pushed data, wherein the items generally refer to data to be pushed.
In the related art, a CVR model is usually a single-target modeling based on click data to order data, but due to the characteristic that a decision link between the click data and the order data is too long, the accuracy of the CVR model obtained by training is poor, so that after the score output based on the CVR model is given to rearrangement, the finally output pushing data is not interesting data of a target object, namely, the accuracy of data pushing is poor.
Disclosure of Invention
The invention provides a data pushing method, a data pushing device, electronic equipment and a storage medium, and aims to solve the technical problem of poor accuracy of data pushing.
According to an aspect of the present invention, there is provided a data pushing method, wherein the method includes:
determining a target pushing object and data to be pushed corresponding to the target pushing object;
Carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data;
and determining target push data based on the target push score, and pushing the target push data to the target push object.
According to another aspect of the present invention, there is provided a data pushing apparatus, wherein the apparatus includes:
the data acquisition module is used for determining a target pushing object and data to be pushed corresponding to the target pushing object;
the pushing matching module is used for pushing and matching the input target pushing object and the target pushing data through a fine pushing model to obtain target pushing scores between each target pushing object and each target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the target pushing data to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the target pushing data to real-time order data;
And the data pushing module is used for determining target pushing data based on the target pushing score and pushing the target pushing data to the target pushing object.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the data pushing method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement a data push method according to any one of the embodiments of the present invention when executed.
According to the technical scheme, the target pushing object and the data to be pushed corresponding to the target pushing object are determined; carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data; and determining target push data based on the target push score, and pushing the target push data to the target push object. Meanwhile, conversion prediction among real-time click data, real-time purchase data and real-time order data corresponding to data to be pushed is introduced, so that the fine-ranking pushing model is pushed and matched based on multi-dimensional data, the comprehensiveness and the precision of pushing and matching of the fine-ranking pushing model are improved, the accuracy of the determined target pushing score is improved, and the accuracy of data pushing is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a data pushing method according to a first embodiment of the present invention;
FIG. 2 is a relationship diagram of a data pushing link according to an embodiment of the present invention;
fig. 3 is a flowchart of a data pushing method according to a second embodiment of the present invention;
FIG. 4 is a graph of conversion of push data samples for a full link according to an embodiment of the present invention;
FIG. 5 is an overall flowchart of a training fine-pitch push model provided according to an embodiment of the present invention;
FIG. 6 is an overall flow chart of a data push provided in accordance with an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a data pushing device according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device implementing a data pushing method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a data pushing method according to an embodiment of the present invention, where the method may be applied to the case of data matching, and the method may be performed by a data pushing device, where the data pushing device may be implemented in a form of hardware and/or software, and the data pushing device may be configured in a computer. As shown in fig. 1, the method includes:
s110, determining a target pushing object and data to be pushed corresponding to the target pushing object.
The target push object may be understood as a push object of data. In the embodiment of the present invention, the target push object may be preset according to a scene requirement, which is not specifically limited herein. Alternatively, the target push object may be a terminal or a person, etc.
The data to be pushed can be understood as data to be pushed. In the embodiment of the present invention, the data to be pushed may be preset according to a scene requirement, which is not specifically limited herein. Optionally, the data to be pushed may include an item detail link, network communication data, and the like.
In the embodiment of the invention, the data to be pushed can be one or more.
It should be understood that the overall data pushing link may include a recall link, a coarse-ranking link, a fine-ranking link, and a rearrangement link (refer to fig. 2), where fig. 2 is a relationship diagram of a data pushing link provided according to an embodiment of the present invention. In the embodiment of the invention, the data pushing method may include a fine-ranking link and a rearrangement link.
Optionally, the determining the data to be pushed corresponding to the target push object includes:
determining a coarse-rank database, wherein the coarse-rank database comprises a plurality of candidate push objects, candidate object features corresponding to each candidate push object, a plurality of candidate push data, candidate data features corresponding to each candidate push data and push matching relations between the candidate object features and the candidate data features;
determining the target object characteristics of the target push object and push data characteristics corresponding to the target object characteristics based on the coarse arrangement database;
and determining the data to be pushed corresponding to the target push object based on the push data characteristics.
The coarse row database may be understood as a database determined by a coarse row link, or may be understood as a pushing result output by the coarse row link.
The candidate push object may be understood as an object included in the coarse-rank database. The candidate object feature may be understood as a feature corresponding to the candidate push object.
The candidate push data may be understood as data included in the coarse-rank database. The candidate data feature may be understood as a feature corresponding to the candidate push data.
The push match relationship may be understood as a match relationship between the candidate data feature and the candidate data feature.
S120, pushing and matching the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data.
The fine-ranking pushing model can be understood as a data pushing model of a fine-ranking link. In the embodiment of the invention, the fine-ranking push model has the function of carrying out push matching on the target push object and the data to be pushed, so that the push matching degree between each data to be pushed and the target push object can be determined, and the target push score is higher under the condition that the higher the push matching degree is. The push matching degree can represent the possible interested degree of the target push object to the data to be pushed currently.
The target push score may be understood as a push score between the data to be pushed and the target push object determined based on the fine-ranking push model.
In the embodiment of the invention, the fine-pitch push model comprises a Click-through Rate (CTR) model and a Conversion Rate (CVR) model. It should be understood that the full link conversion path of each data to be pushed may be exposure data- > click data- > purchase data- > order data.
The click rate model may be understood as a model for estimating a conversion rate from real-time exposure data corresponding to the data to be pushed to real-time click data. The conversion rate model may be understood as a model for estimating the conversion rate from the real-time click data corresponding to the data to be pushed to the real-time order data. The first conversion model may be understood as a model for estimating the conversion rate from the real-time click data corresponding to the data to be pushed to the real-time purchase data. The second conversion model may be understood as a model for estimating the conversion rate from the real-time purchasing data corresponding to the data to be pushed to the real-time order data.
The real-time exposure data is understood to be real-time exposure data. The real-time click data may be understood as real-time click data. The real-time purchasing data may be understood as real-time purchasing data. The real-time order data may be understood as real-time order data.
Optionally, the pushing matching of the input target pushing object symbol and the data to be pushed by the fine-ranking pushing model to obtain a target pushing score between each data to be pushed and the target pushing object includes:
respectively carrying out push matching on the input target push object symbol and the data to be pushed through the click rate model and the conversion rate model to obtain a first push score and a second push score between each data to be pushed and the target push object;
the target push score is determined based on the first push score and the second push score.
The first push score may be understood as a push score between the data to be pushed and the target push object, which is determined based on the click rate model.
The second push score may be understood as a push score between the data to be pushed and the target push object determined based on the conversion rate model.
S130, determining target push data based on the target push scores, and pushing the target push data to the target push object.
The target push data may be understood as data pushed to the target push object. Optionally, the target push data may be part or all of the data to be pushed.
Optionally, the determining the target push data based on the target push score includes:
determining a rearrangement rule, and determining a rearranged target push score corresponding to each piece of data to be pushed based on the rearrangement rule and the target push score;
determining the data pushing quantity, and determining the target pushing data in the data to be pushed based on the data pushing quantity and the rearranged target pushing scores.
The rearrangement rule may be understood as a rule of rearrangement links. In the embodiment of the present invention, the rearrangement rules may be preset according to the scene requirement, which is not specifically limited herein.
The data push amount may be understood as the amount of the target push data. In the embodiment of the present invention, the number of data pushing may be preset according to the scene requirement, which is not limited herein, and optionally, the number of data pushing may be 3, 5, 10, or the like.
According to the technical scheme, the target pushing object and the data to be pushed corresponding to the target pushing object are determined; carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data; and determining target push data based on the target push score, and pushing the target push data to the target push object. Meanwhile, conversion prediction among real-time click data, real-time purchase data and real-time order data corresponding to data to be pushed is introduced, so that the fine-ranking pushing model is pushed and matched based on multi-dimensional data, the comprehensiveness and the precision of pushing and matching of the fine-ranking pushing model are improved, the accuracy of the determined target pushing score is improved, and the accuracy of data pushing is improved.
Example two
Fig. 3 is a flowchart of a data pushing method according to a second embodiment of the present invention, where in this embodiment, an addition is performed on the input target pushing object and the data to be pushed by pushing matching through a fine-ranking pushing model in the foregoing embodiment. As shown in fig. 3, the method includes:
s210, determining a target training sample, wherein the target training sample comprises a pushing object sample and a pushing data sample of a full link corresponding to the pushing object sample.
The target training sample can be understood as a sample for training to obtain the fine-discharge pushing model. The push object sample may be understood as an object included in the target training sample. The push data samples of the full link may be understood as push data of the full link included in the target training samples. Wherein, the push data sample of the full link may be an exposure data sample- > click data sample- > add purchase data sample- > order data sample (refer to fig. 4). Fig. 4 is a conversion relationship diagram of a push data sample of a full link according to an embodiment of the present invention.
In the embodiment of the present invention, the pushing object sample may be the same as or different from the target pushing object.
S220, training based on the push data samples of the full link to obtain the click rate model, the first conversion model and the second conversion model.
Optionally, the push data samples of the full link include an exposure data sample, a click data sample, an additional purchase data sample and an order data sample, the click data sample is a positive sample corresponding to the exposure data sample, the additional purchase data sample is a positive sample corresponding to the click data sample, and the order data sample is a positive sample corresponding to the additional purchase data sample.
According to the technical scheme, the precision-discharge pushing model is trained based on the more detailed exposure data sample, click data sample, purchase data sample, order data sample and full-link pushing data sample, the problem of sparse positive samples and sample selection deviation caused by traditional model training based on the link sample data of the exposure data sample, click data sample, order data sample only is solved, the coverage of the positive samples in the precision-discharge pushing model training process is improved, and the suitability and precision of the obtained precision-discharge pushing model are improved.
Optionally, the training based on the push data sample of the full link to obtain the click rate model, the first conversion model, and the second conversion model includes:
Training to obtain the click rate model based on the pushing object sample, the exposure data sample and the click data sample;
training to obtain the first conversion model based on the pushing object sample, the click data sample and the purchasing data sample;
and training to obtain the second conversion model based on the pushing object sample, the purchasing data sample and the order data sample.
According to the technical scheme, sample nodes of the purchased data samples are introduced, the training processes of the first conversion model and the second conversion model are increased, and the accuracy of the conversion rate model determined based on the first conversion model and the second conversion model is improved.
S230, determining the conversion rate model based on the first conversion model and the second conversion model, and determining the fine-discharge pushing model based on the click rate model and the conversion rate model.
According to the technical scheme, the precision of the fine-discharge pushing model determined based on the conversion rate model is improved based on the conversion rate model with higher precision.
S240, determining a target pushing object and data to be pushed corresponding to the target pushing object.
S250, pushing and matching the input target pushing object and the data to be pushed through a fine-ranking pushing model to obtain a target pushing score between each data to be pushed and each target pushing object.
And S260, determining target push data based on the target push score, and pushing the target push data to the target push object.
According to the technical scheme, the target training sample is determined, wherein the target training sample comprises a push object sample and a push data sample of a full link; training to obtain the click rate model, the first conversion model and the second conversion model based on the push data samples of the full link; and determining the conversion rate model based on the first conversion model and the second conversion model, and determining the fine-discharge pushing model based on the click rate model and the conversion rate model. The precision of the fine discharge pushing model obtained through training is improved.
Fig. 5 is an overall flowchart of a training fine-ranking push model according to an embodiment of the present invention.
As shown in fig. 5, the overall flow of training the fine-pitch push model may be:
1. and constructing a target training sample. The target training samples comprise push object samples and push data samples of all links corresponding to the push object samples.
2. Offline training based on a target training sample to obtain a CTR model (click rate model), a CCR model (first conversion model) and a COR model (second conversion model); obtaining a CVR model (conversion rate model) based on the CCR model and the COR model; and obtaining a CTCVR model (fine discharge pushing model) based on the CTR model and the CVR model.
Specifically, three powers of intermediate nodes CTR, CCR (click- > purchase) and COR (purchase- > order) are introduced into the model structure to respectively construct corresponding task towers. On this basis, CTR, CCR, CVR and ctvr four Loss were introduced for model optimization. Where cvr=ccr×cor, ctvr=ctr×cvr.
According to the technical scheme provided by the embodiment of the invention, the modeling is performed on the basis of the push data sample of the full link comprising the exposure data sample, the click data sample, the purchase data sample and the order data sample, so that the problem of sample selection deviation can be solved; in addition, the method solves the problem of sparse positive samples based on the introduced purchased data sample nodes, improves the multidimensional degree of training sample information, ensures the coverage of the positive samples in the training samples, enables the characteristics of the positive samples to be easier to learn in the model training process, and improves the accuracy of model training.
Fig. 6 is an overall flowchart of data pushing provided according to an embodiment of the present invention. As shown in fig. 6, the overall flow of data push may be:
1. when the target push object is accessed, the target object characteristics corresponding to the target push object, the candidate data characteristics corresponding to the candidate push data in the coarse-row database and other context characteristics are obtained from a Feature Server (coarse-row database) to obtain a set of data to be pushed.
2. The data to be pushed is input into the CVR model to be scored to obtain pcvr scores (second push scores).
3. In the rearrangement link, pctr (first push score) and pcvr (second push score) determined based on the rearrangement rule, based on the click rate model, obtain a total score (target push score).
4. And outputting target pushing data of the highest scoring data pushing quantity to the target pushing object.
According to the method and the device for pushing the data, the purchasing node is introduced in the pushing matching process of the data to be pushed corresponding to the target pushing object, so that the accuracy of data pushing is improved.
Example III
Fig. 7 is a schematic structural diagram of a data pushing device according to a third embodiment of the present invention. As shown in fig. 7, the apparatus includes: a data acquisition module 310, a push matching module 320, and a data push module 330. Wherein,
a data acquisition module 310, configured to determine a target push object and data to be pushed corresponding to the target push object; the pushing matching module 320 is configured to perform pushing matching on the input target pushing object and the target pushing data through a fine-ranking pushing model, so as to obtain a target pushing score between each target pushing object and each target pushing object, where the fine-ranking pushing model includes a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating a conversion rate from real-time click data corresponding to the target pushing data to real-time purchase data, and the second conversion model is a model for estimating a conversion rate from real-time purchase data corresponding to the target pushing data to real-time order data; the data pushing module 330 is configured to determine target pushing data based on the target pushing score, and push the target pushing data to the target pushing object.
According to the technical scheme, the target pushing object and the data to be pushed corresponding to the target pushing object are determined; carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data; and determining target push data based on the target push score, and pushing the target push data to the target push object. Meanwhile, conversion prediction among real-time click data, real-time purchase data and real-time order data corresponding to data to be pushed is introduced, so that the fine-ranking pushing model is pushed and matched based on multi-dimensional data, the comprehensiveness and the precision of pushing and matching of the fine-ranking pushing model are improved, the accuracy of the determined target pushing score is improved, and the accuracy of data pushing is improved.
Optionally, the data pushing device further includes: the system comprises a sample acquisition module, a model training module and a model determining module; wherein,
the sample acquisition module is used for determining a target training sample before pushing and matching the input target pushing object symbol and the data to be pushed through a fine-ranking pushing model to obtain a target pushing score between each data to be pushed and the target pushing object, wherein the target training sample comprises a pushing object sample and a pushing data sample of a full link corresponding to the pushing object sample;
the model training module is used for training to obtain the click rate model, the first conversion model and the second conversion model based on the push data sample of the full link;
the model determining module is used for determining the conversion rate model based on the first conversion model and the second conversion model, and determining the fine-discharge pushing model based on the click rate model and the conversion rate model.
Optionally, the push data samples of the full link include an exposure data sample, a click data sample, an additional purchase data sample and an order data sample, the click data sample is a positive sample corresponding to the exposure data sample, the additional purchase data sample is a positive sample corresponding to the click data sample, and the order data sample is a positive sample corresponding to the additional purchase data sample.
Optionally, the model training module is configured to:
training to obtain the click rate model based on the pushing object sample, the exposure data sample and the click data sample;
training to obtain the first conversion model based on the pushing object sample, the click data sample and the purchasing data sample;
and training to obtain the second conversion model based on the pushing object sample, the purchasing data sample and the order data sample.
Optionally, a push matching module 320 is configured to:
respectively carrying out push matching on the input target push object symbol and the data to be pushed through the click rate model and the conversion rate model to obtain a first push score and a second push score between each data to be pushed and the target push object;
the target push score is determined based on the first push score and the second push score.
Optionally, the data pushing module 330 is configured to:
determining a rearrangement rule, and determining a rearranged target push score corresponding to each piece of data to be pushed based on the rearrangement rule and the target push score;
determining the data pushing quantity, and determining the target pushing data in the data to be pushed based on the data pushing quantity and the rearranged target pushing scores.
Optionally, the data acquisition module 310 is configured to:
determining a coarse-rank database, wherein the coarse-rank database comprises a plurality of candidate push objects, candidate object features corresponding to each candidate push object, a plurality of candidate push data, candidate data features corresponding to each candidate push data and push matching relations between the candidate object features and the candidate data features;
determining the target object characteristics of the target push object and push data characteristics corresponding to the target object characteristics based on the coarse arrangement database;
and determining the data to be pushed corresponding to the target push object based on the push data characteristics. The data pushing device provided by the embodiment of the invention can execute the data pushing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 8 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the data push method.
In some embodiments, the data pushing method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data pushing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the data push method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. The data pushing method is characterized by comprising the following steps of:
determining a target pushing object and data to be pushed corresponding to the target pushing object;
carrying out pushing matching on the input target pushing object and the data to be pushed through a fine pushing model to obtain target pushing scores between each data to be pushed and the target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the data to be pushed to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the data to be pushed to real-time order data;
And determining target push data based on the target push score, and pushing the target push data to the target push object.
2. The method of claim 1, wherein before performing push matching on the input target push object symbol and the data to be pushed by the fine push model to obtain a target push score between each data to be pushed and the target push object, further comprises:
determining a target training sample, wherein the target training sample comprises a push object sample and a push data sample of a full link corresponding to the push object sample;
training to obtain the click rate model, the first conversion model and the second conversion model based on the push data samples of the full link;
and determining the conversion rate model based on the first conversion model and the second conversion model, and determining the fine-discharge pushing model based on the click rate model and the conversion rate model.
3. The method of claim 2, wherein the push data samples of the full link include an exposure data sample, a click data sample, a purchase data sample, and an order data sample, the click data sample being a positive sample corresponding to the exposure data sample, the purchase data sample being a positive sample corresponding to the click data sample, the order data sample being a positive sample corresponding to the purchase data sample.
4. The method of claim 3, wherein the training of the push data samples based on the full link to obtain the click rate model, the first conversion model, and the second conversion model comprises:
training to obtain the click rate model based on the pushing object sample, the exposure data sample and the click data sample;
training to obtain the first conversion model based on the pushing object sample, the click data sample and the purchasing data sample;
and training to obtain the second conversion model based on the pushing object sample, the purchasing data sample and the order data sample.
5. The method of claim 1, wherein the performing, by the fine-pitch push model, push matching the input target push object symbol and the data to be pushed to obtain a target push score between each data to be pushed and the target push object, includes:
respectively carrying out push matching on the input target push object symbol and the data to be pushed through the click rate model and the conversion rate model to obtain a first push score and a second push score between each data to be pushed and the target push object;
The target push score is determined based on the first push score and the second push score.
6. The method of claim 1, wherein the determining target push data based on the target push score comprises:
determining a rearrangement rule, and determining a rearranged target push score corresponding to each piece of data to be pushed based on the rearrangement rule and the target push score;
determining the data pushing quantity, and determining the target pushing data in the data to be pushed based on the data pushing quantity and the rearranged target pushing scores.
7. The method of claim 1, wherein the determining the data to be pushed corresponding to the target push object comprises:
determining a coarse-rank database, wherein the coarse-rank database comprises a plurality of candidate push objects, candidate object features corresponding to each candidate push object, a plurality of candidate push data, candidate data features corresponding to each candidate push data and push matching relations between the candidate object features and the candidate data features;
determining the target object characteristics of the target push object and push data characteristics corresponding to the target object characteristics based on the coarse arrangement database;
And determining the data to be pushed corresponding to the target push object based on the push data characteristics.
8. A data pushing apparatus, comprising:
the data acquisition module is used for determining a target pushing object and data to be pushed corresponding to the target pushing object;
the pushing matching module is used for pushing and matching the input target pushing object and the target pushing data through a fine pushing model to obtain target pushing scores between each target pushing object and each target pushing object, wherein the fine pushing model comprises a click rate model and a conversion rate model, the conversion rate model is determined based on a first conversion model and a second conversion model, the first conversion model is a model for estimating the conversion rate from real-time click data corresponding to the target pushing data to real-time purchase data, and the second conversion model is a model for estimating the conversion rate from real-time purchase data corresponding to the target pushing data to real-time order data;
and the data pushing module is used for determining target pushing data based on the target pushing score and pushing the target pushing data to the target pushing object.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the data pushing method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the data push method of any one of claims 1-7 when executed.
CN202311569735.1A 2023-11-22 2023-11-22 Data pushing method and device, electronic equipment and storage medium Pending CN117493690A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311569735.1A CN117493690A (en) 2023-11-22 2023-11-22 Data pushing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311569735.1A CN117493690A (en) 2023-11-22 2023-11-22 Data pushing method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117493690A true CN117493690A (en) 2024-02-02

Family

ID=89679943

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311569735.1A Pending CN117493690A (en) 2023-11-22 2023-11-22 Data pushing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117493690A (en)

Similar Documents

Publication Publication Date Title
CN114580916A (en) Enterprise risk assessment method and device, electronic equipment and storage medium
CN113360711A (en) Model training and executing method, device, equipment and medium for video understanding task
CN114722048B (en) Data processing method and device, electronic equipment and storage medium
CN116228301A (en) Method, device, equipment and medium for determining target user
CN117493690A (en) Data pushing method and device, electronic equipment and storage medium
CN115665783A (en) Abnormal index tracing method and device, electronic equipment and storage medium
CN115599687A (en) Method, device, equipment and medium for determining software test scene
CN115271866A (en) Product recommendation method and device, electronic equipment and readable storage medium
CN115578583B (en) Image processing method, device, electronic equipment and storage medium
CN117667966A (en) Data recall method and device, electronic equipment and storage medium
CN113343090B (en) Method, apparatus, device, medium and product for pushing information
CN116308455A (en) Method and device for identifying hub area in trade network
CN117592618A (en) Active user prediction method, device, server and storage medium
CN115017145A (en) Data expansion method, device and storage medium
CN117331924A (en) Data model matching degree checking method, device, equipment and storage medium
CN116662194A (en) Software quality measurement method, device, equipment and medium
CN117710063A (en) User preference prediction method, device, equipment and medium based on double-layer architecture
CN117911135A (en) Data processing method, device, electronic equipment and storage medium
CN117807384A (en) Prediction method and device, storage medium and electronic equipment
CN116304796A (en) Data classification method, device, equipment and medium
CN114549122A (en) Model training method, commodity recommendation device, equipment and storage medium
CN116823510A (en) Node influence measuring method, device, equipment and storage medium
CN116186411A (en) Method and device for constructing user behavior prediction model based on depth recommendation model
CN116049555A (en) Information recommendation method, device, equipment and storage medium
CN114942996A (en) Triple construction method and device of vertical industry data, electronic equipment and 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