CN111782926B - Method and device for data interaction, storage medium and electronic equipment - Google Patents

Method and device for data interaction, storage medium and electronic equipment Download PDF

Info

Publication number
CN111782926B
CN111782926B CN201910273138.1A CN201910273138A CN111782926B CN 111782926 B CN111782926 B CN 111782926B CN 201910273138 A CN201910273138 A CN 201910273138A CN 111782926 B CN111782926 B CN 111782926B
Authority
CN
China
Prior art keywords
data
display
keywords
click
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910273138.1A
Other languages
Chinese (zh)
Other versions
CN111782926A (en
Inventor
张育浩
朱鑫
徐夙龙
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.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information 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 Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Priority to CN201910273138.1A priority Critical patent/CN111782926B/en
Publication of CN111782926A publication Critical patent/CN111782926A/en
Application granted granted Critical
Publication of CN111782926B publication Critical patent/CN111782926B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G06F16/9538—Presentation of query results
    • 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
    • G06F16/957—Browsing optimisation, e.g. caching or content distillation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0273—Determination of fees for advertising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Abstract

The embodiment of the invention provides a method, a device, a storage medium and electronic equipment for data interaction, wherein the method comprises the following steps: acquiring keywords from a client, and acquiring click weights of display links corresponding to the keywords to acquire click weights of the display links corresponding to the keywords displayed by the client; obtaining conversion data of each display link according to a first model; acquiring resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; the display links corresponding to the keywords are ordered based on the index threshold value, and the ordered display links are sent to the client for display, so that display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold value of the keywords, waste of the display link positions and overlarge data processing pressure of a display link platform side are avoided, and meanwhile the problems of cyclic feedback and confidence in the index threshold value of the long-tail keywords are solved.

Description

Method and device for data interaction, storage medium and electronic equipment
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a storage medium, and an electronic device for data interaction.
Background
In the display link publishing system, the index threshold is an index of display link bits which are determined to be distributed for the display links by the display link platform side, and is one of important influencing factors influencing the ecology of the display links. The index threshold can be regarded as an admission threshold of the display link issuing system, if the index threshold is set too high, participation of a display link owner is limited, waste of display link bits is caused, if the index threshold is set low, the display link bits required to be set by a display link platform side are too many, and data processing pressure of the display link platform side is increased.
Therefore, a new method, device, storage medium and electronic equipment for data interaction are needed, which can integrate a plurality of factors to determine the index threshold of the keyword, avoid the waste of the display link bit and reduce the data processing pressure of the display link platform side.
The above information disclosed in the background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the foregoing, the present invention provides a new method, apparatus, storage medium and electronic device for data interaction, which can synthesize a plurality of factors to determine an index threshold of a keyword, improve the use efficiency of a display link bit, and reduce the data processing pressure of a display link platform side.
Other features and advantages of the invention will be apparent from the following detailed description, or may be learned by the practice of the invention.
According to a first aspect of the present invention there is provided a method for data interaction, wherein the method comprises: acquiring keywords from a client, and acquiring click weights of each display link corresponding to the keywords; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; and determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data.
According to some embodiments, the method further comprises: acquiring the first model;
acquiring the first model, including: taking the characteristic information of keywords and corresponding display links in the historical conversion data and the conversion results of the corresponding display links as samples, and generating a first data set comprising a first training set and a first test set; training a first model based on samples in the first training set; and testing the initially selected first model based on the samples in the first test set to obtain a first model.
According to some embodiments, the method further comprises: acquiring the second model;
obtaining the second model includes: screening display links with conversion number larger than a threshold value from historical resource occupation data, taking characteristic information of the display links and rate data corresponding to the display links as samples, and generating a second data set comprising a second training set and a second test set; based on the second of training sets training a first model by a sample; and testing the initially selected second model based on the samples in the second test set to obtain a second model.
According to some embodiments, obtaining a click weight of each display link corresponding to a keyword input by a user includes: the click weight of each display link is calculated by the following formula:
ad_weight(query i ，ad j )＝click(query i ，ad j )/∑ j click(query i ，ad j )
wherein the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Weights of (click) (query) i ，ad j ) Representing keyword query i Corresponding presentation link ad j Number of clicks.
According to some embodiments, the determining the index threshold of the keyword based on the click weight, the conversion data, and the resource occupancy data includes: determining click resource data of the keyword based on the click weight, the conversion data and the resource occupation data; and determining an index threshold value of the keyword based on the click resource data and a preset index coefficient.
According to some embodiments, the determining click resource data of the keyword based on the click weight, the conversion data, and the resource occupancy data includes: calculating click resource data of the keywords through the following formula:
value(query i )＝∑ j ad_weight(query i ，ad j )×cvr(query i ，ad j )×cpa(ad j )
wherein the value (query i ) Representing keyword query i Is the click resource data of the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Is the click weight of the cvr (query i ，ad j ) Representing the keyword query i Corresponding presentation link ad j Is converted into data of the cpa (ad) j ) Representing the keyword query i Corresponding presentation link ad j Is a resource occupancy data of (1).
According to some embodiments, determining the index threshold of the keyword based on the click resource data and a preset index coefficient includes: calculating an index threshold of the keyword through the following formula:
reserve_price(query i )＝reserve_price_ratio×value(query i )
wherein the reserve_price (query i ) Representing the keyword query i The reserve_price_ratio represents a preset index coefficient, the value (query i ) Representing the keyword query i Is provided with click resource data.
According to some embodiments, sorting the presentation links corresponding to the keywords based on the indicator threshold includes: filtering out display links with index data lower than the index threshold value from the display links corresponding to the keywords; and calculating the click rate of the filtered display links based on the CTR model, and sequencing the filtered display links based on the click rate of the display links and index data.
According to a second aspect of the present invention, there is provided an apparatus for data interaction, wherein the apparatus comprises:
the first acquisition module is used for acquiring keywords from the client and acquiring click weights of each display link corresponding to the keywords; the second acquisition module is used for acquiring the conversion data of each display link according to the first model; the third acquisition module is used for acquiring the resource occupation data of each display link according to the second model; the determining module is used for determining an index threshold value of the keyword based on the click weight, the conversion data and the resource occupation data; and the ordering module is used for ordering the display links corresponding to the keywords based on the index threshold value and sending the ordered display links to the client for display.
According to some embodiments, the apparatus further comprises: the first model acquisition module is used for acquiring the first model;
the first model acquisition module includes:
the first generation unit is used for taking the key words in the history conversion data, the characteristic information of the corresponding display links and the conversion results of the corresponding display links as samples, and generating a first data set comprising a first training set and a first test set; a first training unit for training a first model based on samples in the first training set; and the first testing unit is used for testing the initially selected first model based on the samples in the first testing set so as to obtain a first model.
According to some embodiments, the apparatus further comprises: the second model acquisition module is used for acquiring the second model; the second model acquisition module includes:
the second generation unit is used for screening display links with the conversion number larger than a threshold value from the historical resource occupation data, taking characteristic information of the display links and rate data corresponding to the display links as samples, and generating a second data set comprising a second training set and a second test set; a second training unit for training a first selected second model based on the samples in the second training set; and the second testing unit is used for testing the initially selected second model based on the samples in the second testing set so as to obtain a second model.
According to some embodiments, the first obtaining module is configured to calculate the click weight of each display link by the following formula:
ad_weight(query i ，ad j )＝click(query i ，ad j )/∑ j click(query i ，ad j )
wherein the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Weights of (click) (query) i ，ad j ) Representing keyword query i Corresponding presentation link ad j Number of clicks.
According to some embodiments, the determining module comprises: the first determining unit is used for determining click resource data of the keyword based on the click weight, the conversion data and the resource occupation data; and the second determining unit is used for determining the index threshold value of the keyword based on the click resource data and the preset index coefficient.
According to some embodiments, the first determining unit is configured to calculate click resource data of the keyword by the following formula:
value(query i )＝∑ j ad_weight(query i ，ad j )×cvr(query i ，ad j )×cpa(ad j )
wherein the value (query i ) Representing keyword query i Is the click resource data of the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Is the click weight of the cvr (query i ，ad j ) Representing the keyword query i Corresponding presentation link ad j Is converted into data of the cpa (ad) j ) Representing the keyword query i Corresponding presentation link ad j Is a resource occupancy data of (1).
According to some embodiments, the second determining unit is configured to calculate the index threshold of the keyword by the following formula:
reserve_price(query i )＝reserve_price_ratio×value(query i )
wherein the reserve_price (query i ) Representing the keyword query i The reserve_price_ratio represents a preset index coefficient, the value (query i ) Representing the keyword query i Is provided with click resource data.
According to some embodiments, the ranking module comprises: the filtering unit is configured to filter out display links with index data of the display links lower than the index threshold value from the display links corresponding to the keywords; and the sorting unit is configured to calculate the click rate of the filtered display links based on the CTR model and sort the filtered display links based on the click rate of the display links and index data.
According to a third aspect of the present invention, there is provided a data interaction system comprising:
the client is used for displaying the keywords and displaying the keywords after receiving the display links sent by the server;
the server is used for acquiring keywords from the client, acquiring click weight of each display link corresponding to the keywords, acquiring conversion data of each display link according to a first model, acquiring resource occupation data of each display link according to a second model, determining index threshold values of the keywords based on the click weight, the conversion data and the resource occupation data, sorting the display links corresponding to the keywords based on the index threshold values, and sending the sorted display links to the client.
According to a fourth aspect of the present invention there is provided a computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the method steps according to the first aspect.
According to a fifth aspect of the present invention, there is provided an electronic apparatus, comprising: one or more processors; storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to carry out the method steps as described in the first aspect.
In the embodiment of the invention, the click weight of each keyword displayed by the client is obtained by obtaining the keyword from the client and the click weight of each display link corresponding to the keyword; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and ordering the display links corresponding to the keywords based on the index threshold, and sending the ordered display links to the client for display, so that the display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold of the keywords, the waste of the display link positions and the overlarge data processing pressure of a display link platform side are avoided, and the problems of cyclic feedback and confidence of the index threshold of the long-tail keywords are solved.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
FIG. 1 is a flow chart illustrating a method for data interaction according to an example embodiment;
FIG. 2 is a flowchart illustrating a method of acquiring a first model, according to an example embodiment;
FIG. 3 is a flowchart illustrating a method of acquiring a second model, according to an example embodiment;
FIG. 4 is a diagram of a search advertisement system architecture, shown according to an example embodiment;
FIG. 5 is a signaling diagram illustrating a data interaction between a client and a server according to an example embodiment;
FIG. 6 is a schematic diagram illustrating an apparatus for data interaction, according to an example embodiment;
FIG. 7 is a schematic diagram of a system for data interaction, according to an example embodiment;
fig. 8 is a schematic diagram of an electronic device according to an exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
In the related art, index thresholds of different keywords are set based on a history index threshold distribution corresponding to the keywords, for example, the following two index threshold setting methods:
1. offline index threshold setting: the offline indicator threshold setting is typically set based on bid information that reveals link bit/keyword correspondence over a period of time. For the exhibition link, the bid resource occupation data distribution corresponding to the exhibition link bit is usually generated, and then the index threshold corresponding to the exhibition link bit is calculated based on the relevant statistical information (such as quantiles, bid probability density distribution, bid accumulation distribution and the like) of the bid distribution of the resource occupation data. For search demonstration links, the demonstration link owner sets an index threshold value based on search keyword bid, so that the bid resource occupation data distribution based on keywords is generally generated, and then the index threshold value of each keyword is set according to the bid resource occupation data distribution.
2. Setting a real-time index threshold value: the real-time index threshold setting can set different index thresholds for each auction, and the index threshold estimation is usually performed by using a machine learning method.
The application of the two index thresholds is different. However, the method of the index threshold has the following problems:
1. And (3) cyclic feedback: the display link owner can promote resource occupation data for obtaining more display link bits of the platform, so that resource occupation data distribution changes, index threshold values are improved, the display link owner can be further lifted due to the influence of the resource occupation data distribution, the index threshold values obtained based on statistics can be correspondingly lifted, the circulation is performed, deviation between the index threshold values and actual indexes of keywords is continuously enlarged, and further the calculated index threshold values have differences and even have larger differences, so that ecology of the display link is influenced.
2. Threshold confidence of long tail keyword index: the long-tail keyword data are sparse, so that the obtained resource occupation data distribution and index threshold value are not confidence, and a default index threshold value is generally adopted.
Based on the above problems, the embodiment of the invention provides a method for data interaction, which realizes the determination of the display link bit allocated for the display link and the ordering of the display link according to the index threshold of the keyword, avoids the waste of the display link bit and the overlarge data processing pressure of the display link platform side, and solves the problems of cyclic feedback and confidence of the index threshold of the long-tail keyword.
The method for data interaction according to the embodiment of the present invention is described in detail below with reference to specific embodiments. It should be noted that, the data interaction method provided in the embodiment of the present invention may be executed by any device having a computing processing capability, for example, a server and/or a terminal device, which is not limited in this aspect of the present invention. The present embodiment is described by taking a server as an example.
FIG. 1 is a flow chart illustrating a method for data interaction according to an example embodiment.
As shown in fig. 1, in S110, a keyword is acquired from a client, and a click weight of each presentation link corresponding to the keyword is acquired.
According to the embodiment of the invention, the client can display an input box for inputting the keyword by the user, the client sends the keyword input by the user to the server, the server acquires the keyword, and the click weight of each display link corresponding to the keyword is acquired based on the click data of all display links (such as advertisements) corresponding to the keyword in a period of time. It should be noted that, the keyword input by the user and obtained by the server from the client may be a sentence containing the keyword, and if the keyword is a sentence containing the keyword, the keyword is first extracted by identifying the keyword of the sentence. Note that the keyword may be plural.
According to the embodiment of the invention, the server side stores the display links matched with the keywords, and after the keywords are acquired, the display links corresponding to the keywords are acquired through matching. It should be noted that one keyword may be matched to a plurality of presentation links, and a plurality of keywords may be matched to a plurality of presentation links in common.
According to the embodiment of the invention, the click weight of each display link corresponding to the keyword input by the user can be calculated through the following formula:
ad_weight(query i ，ad j )＝click(query i ，ad j )/∑ j click(query i ，ad j )
wherein the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Weights of (click) (query) i ，ad j ) Representing keyword query i Corresponding presentation link ad j Number of clicks.
In S120, conversion data of each presentation link is acquired according to the first model.
In the embodiment of the invention, the first model is preset, and the conversion data of each display link corresponding to the keyword can be obtained by inputting the characteristic information of each display link corresponding to the keyword into the first model, so that the results are stored. In the embodiment of the present invention, the conversion data may include: conversion, i.e., the ratio of the number of times a conversion activity is completed to the total number of clicks that a link is presented within a statistical period.
It should be noted that, the feature information of the keyword and the corresponding display link may include, but is not limited to: keyword text, display link brands, categories, prices, sales, and user scores.
In S130, resource occupancy data for each display link is obtained according to a second model.
In the embodiment of the invention, a second model is preset, and the resource occupation data of each display link can be obtained by inputting the characteristic information of each display link into the second model. In the embodiment of the present invention, the resource occupation data may include: conversion cost data, i.e., the cost of completing the conversion activity.
It should be noted that, the feature information of the presentation link may include, but is not limited to: the brand, category, price, sales, and user scores of the links are presented.
In S140, an index threshold for the keyword is determined based on the click weight, the conversion data, and the resource occupation data.
According to the embodiment of the invention, the click resource data of the keyword can be determined firstly based on the click weight, the conversion data and the resource occupation data, and then the index threshold of the keyword can be determined based on the click resource data and the preset index coefficient. In the embodiment of the present invention, the index threshold may include: reserve price, i.e., the minimum price that a display link (e.g., advertisement) place auctions to reach. Click resource data may include: clicking on the fee data, i.e., the fee data resulting from clicking on a presentation link (e.g., advertisement).
It should be noted that click resource data can be calculated by the following formula:
value(query i )＝∑ j ad_weight(query i ，ad j )×cvr(query i ，ad j )×cpa(ad j ) Wherein the value (query i ) Representing keyword query i Is the click resource data of the ad_weight (query i ，ad j ) Representing keyword query i Corresponding presentation link ad j Is the click weight of the cvr (query i ，ad j ) Representing the keyword query i Corresponding presentation link ad j Is converted into data of the cpa (ad) j ) Representing the keyword query i Corresponding presentation link ad j Is a resource occupancy data of (1).
According to the embodiment of the invention, the index threshold value of the keyword can be calculated through the following formula:
reserve_price(query i )＝reserve_price_ratio×value(query i )
wherein the reserve_price (query i ) Representing the keyword query i The reserve_price_ratio represents a preset index coefficient, the value (query i ) Representing the keyword query i Is provided with click resource data.
It should be noted that the index coefficient is an adjustable coefficient.
In S150, sorting the presentation links corresponding to the keywords based on the index threshold, and sending the sorted presentation links to the client for display.
In the embodiment of the invention, after the index threshold is determined, the display links with index data lower than the index threshold of the display links can be filtered from the display links corresponding to the keywords, the click rate of the filtered display links is calculated based on a CTR model, and the filtered display links are ordered based on the click rate of the display links and the index data.
It should be noted that the index data of the show link may be a bid of an advertiser for an advertisement, and the show link below the index threshold is filtered out, that is, the advertisement with the bid below the reserve price is filtered out. And then, performing CTR (Click Through Rate, click rate) estimation on the display links by a pre-trained click rate model, calculating the thousand display cost eCPM=display link index data multiplied by the click rate multiplied by 1000 of the remaining display links after filtering according to the following formula, sequencing the filtered display links according to the order of eCPM from high to low, and returning the sequenced display links to the client for display.
According to the embodiment, the display links are ranked together according to the index data of the display links and the click rate, so that the display links with high click rate and the display links with high index data of the display links are ranked, the probability of clicking the display links is improved, and the income of a display link platform is increased.
In the embodiment of the invention, the click weight of each keyword displayed by the client is obtained by obtaining the keyword from the client and the click weight of each display link corresponding to the keyword; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and ordering the display links corresponding to the keywords based on the index threshold, and sending the ordered display links to the client for display, so that the display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold of the keywords, the waste of the display link positions and the overlarge data processing pressure of a display link platform side are avoided, and the problems of cyclic feedback and confidence of the index threshold of the long-tail keywords are solved.
The method of acquiring the first model is described in detail below. FIG. 2 is a flowchart illustrating a method of acquiring a first model, according to an example embodiment. It should be noted that, the first model may be a CVR (Click Value Rate) model, and as shown in fig. 2, the method may include the following steps:
in S210, a first data set including a first training set and a first test set is generated using, as samples, feature information of keywords in the history conversion data and corresponding presentation links and conversion results of the corresponding presentation links.
According to the embodiment of the invention, a period of time t1 can be intercepted, and the keyword query contained in t1 can be intercepted x And taking the characteristic information linked with the corresponding presentation and the historical conversion data of the conversion result as samples to generate a first data set.
It should be noted that the first data set includes: a first training set and a first test set. The number of samples in the first training set and the first test set may be set manually, for example, the ratio of the number of samples in the first training set to the number of samples in the first test set is set to be 6:4.
It should be noted that, the feature information of the keyword and the corresponding display link may include, but is not limited to: keyword text, display link brands, categories, prices, sales, and user scores.
In S220, a first model is initially selected based on the samples in the first training set.
According to the embodiment of the invention, the first model structure is not particularly limited, and the first model modeling can be performed by selecting a shallow model (such as a linear model and the like) or a depth model (such as a deep and wide and the like) based on a specific scene. In addition, as the number of pairs of the data of the keywords and the corresponding display links is small, the representation and generalization capability of the model can be enhanced by adopting transfer learning and other technologies, and the estimation effect is improved. After modeling, the initial first model is trained using the samples in the first training set.
In S230, the first model is tested based on the samples in the first test set to obtain a first model.
According to the embodiment of the invention, after the primary first model is obtained, the primary model can be tested based on the samples in the first test set, and the primary model is corrected according to the test result and the actual result of the samples so as to obtain the final first model.
The method of acquiring the second model is described in detail below. FIG. 3 is a flowchart illustrating a method of acquiring a second model, according to an example embodiment. It should be noted that, the second model may be a CPA (Cost Per Action, accounting by fruit number) model, and as shown in fig. 3, the method may include the following steps:
In S310, display links with a number of transitions greater than a threshold are screened from the historical resource occupancy data, and feature information of the display links and corresponding rates are used as samples to generate a second data set including a second training set and a second test set.
According to the embodiment of the invention, a period of time t2 can be intercepted, and a keyword query in t2 can be obtained x Corresponding display links from which the number of transitions is selected to be greater than a threshold cpa And taking the characteristic information of the screened display links and the corresponding conversion rates as samples to generate a second data set.
It should be noted that the second data set includes: a second training set and a second test set. The number of samples in the second training set and the second test set may be considered as a set, for example, the ratio of the number of samples in the second training set to the number of samples in the second test set is set to be 7:3.
It should be noted that, the feature information of the presentation link may include, but is not limited to: the brand, category, price, sales, and user scores of the links are presented.
In S320, a first selected second model is trained based on the samples in the second training set.
According to the embodiment of the invention, the second model structure is not particularly limited, and the second model modeling can be performed by selecting a shallow model (such as a linear model and the like) or a depth model (such as a deep and wide and the like) based on a specific scene. In addition, as the number of pairs of the data of the keywords and the corresponding display links is small, the representation and generalization capability of the model can be enhanced by adopting transfer learning and other technologies, and the estimation effect is improved. After modeling, the initial second model is trained using the samples in the second training set.
In S330, the preliminary second model is tested based on the samples in the second test set, to obtain a second model.
According to the embodiment of the invention, after the primary second model is obtained, the primary model can be tested based on the samples in the second test set, and the primary model is corrected according to the test result and the actual result of the samples so as to obtain the final second model.
The following is an application scenario of a method for data interaction according to an embodiment of the present invention, in which a display link is illustrated by using an advertisement as an example, and an index threshold is illustrated by using a reserve price as an example, and fig. 4 is a diagram illustrating a search advertisement system architecture according to an exemplary embodiment.
As shown in fig. 4, a user inputs a search advertisement request containing a certain keyword in a client display system, the request is sent from the client display system to an advertisement delivery system, the advertisement delivery system firstly carries out analysis such as expansion and rewriting on the keyword, then combines the keyword, the user and advertisement information to trigger to obtain a candidate advertisement queue, the advertisement delivery system determines the reserve price of the keyword through the method for data interaction provided by the invention, filters the candidate advertisement according to the reserve price, filters advertisements with advertisement bids lower than the reserve price, sorts the rest part of advertisements, carries out CTR (Click Through Rate, click rate) estimation on the advertisements by a pre-trained click rate model, and then combines the advertisement bids to obtain the advertisement queue which is sorted according to eCPM (eCPM is thousands of display charges, eCPM=advertisement unit price×click rate×1000), and returns the advertisement queue to the client.
It should be noted that, the method for evaluating click resource data according to search keywords provided by the invention can be used for determining the index threshold value, and can also be applied to setting the index threshold value of buying words by advertisers, thereby having certain reference significance for pricing crowd packages in audience orientation.
FIG. 5 is a diagram illustrating a client according to an exemplary embodiment signaling diagram of data interaction between terminal and server. As shown in fig. 5, includes:
s501, the client acquires the keywords.
S502, the client sends the keywords to the server.
S503, the server acquires the click weight of each display link corresponding to the keyword.
S504, the server acquires conversion data of each display link according to the first model.
S505, the server acquires the resource occupation data of each display link according to the second model.
S506, the server determines the index threshold of the keyword based on the click weight, the conversion data and the resource occupation data.
S507, the server sorts the display links corresponding to the keywords based on the index threshold.
And S508, the server sends the ordered display links to the client.
And S509, the client displays the ordered display links.
In the embodiment of the invention, the click weight of each keyword displayed by the client is obtained by obtaining the keyword from the client and the click weight of each display link corresponding to the keyword; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and ordering the display links corresponding to the keywords based on the index threshold, and sending the ordered display links to the client for display, so that the display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold of the keywords, the waste of the display link positions and the overlarge data processing pressure of a display link platform side are avoided, and the problems of cyclic feedback and confidence of the index threshold of the long-tail keywords are solved.
It should be clearly understood that the present invention describes how to make and use specific examples, but the principles of the present invention are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
The following are examples of the apparatus of the present invention that may be used to perform the method embodiments of the present invention. In the following description of the device, the same parts as those of the previous method will not be repeated.
Fig. 6 is a schematic structural diagram of an apparatus for data interaction, according to an exemplary embodiment, wherein the apparatus includes:
the first obtaining module 610 is configured to obtain a keyword from a client, and obtain a click weight of each display link corresponding to the keyword.
A second obtaining module 620, configured to obtain the conversion data of each display link according to the first model.
And a third obtaining module 630, configured to obtain the resource occupation data of each display link according to the second model.
A determining module 640, configured to determine an index threshold of the keyword based on the click weight, the conversion data, and the resource occupation data.
And the sorting module 650 is configured to sort the display links corresponding to the keywords based on the index threshold, and send the sorted display links to the client for display.
In the embodiment of the invention, the click weight of each keyword displayed by the client is obtained by obtaining the keyword from the client and the click weight of each display link corresponding to the keyword; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and ordering the display links corresponding to the keywords based on the index threshold, and sending the ordered display links to the client for display, so that the display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold of the keywords, the waste of the display link positions and the overlarge data processing pressure of a display link platform side are avoided, and the problems of cyclic feedback and confidence of the index threshold of the long-tail keywords are solved.
Further, in an embodiment of the present invention, a data interaction system is provided, and fig. 7 is a schematic structural diagram of a system for data interaction according to an exemplary embodiment, where the data interaction system 700 may include a client 710 and a server 720.
The client 710 is configured to display the keyword, and display the keyword after receiving the display link sent by the server. The server 720 is configured to obtain a keyword from a client, obtain a click weight of each display link corresponding to the keyword, obtain conversion data of each display link according to a first model, obtain resource occupation data of each display link according to a second model, determine an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data, sort display links corresponding to the keyword based on the index threshold, and send the sorted display links to the client. With continued reference to fig. 7, in an embodiment of the present invention, the data interaction system may further include: the memory 730 is configured to store a matching relationship between the keyword and the presentation link, click data of the presentation link, history conversion data, a first data set, history resource occupation data, and a second data set.
In the embodiment of the invention, the click weight of each keyword displayed by the client is obtained by obtaining the keyword from the client and the click weight of each display link corresponding to the keyword; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and ordering the display links corresponding to the keywords based on the index threshold, and sending the ordered display links to the client for display, so that the display link positions distributed for the display links and the ordering of the display links are determined according to the index threshold of the keywords, the waste of the display link positions and the overlarge data processing pressure of a display link platform side are avoided, and the problems of cyclic feedback and confidence of the index threshold of the long-tail keywords are solved.
As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer-readable medium carries one or more programs which, when executed by one of the devices, cause the device to perform: acquiring keywords from a client, and acquiring click weights of each display link corresponding to the keywords; obtaining conversion data of each display link according to a first model; acquiring the resource occupation data of each display link according to a second model; determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data; and sorting the display links corresponding to the keywords based on the index threshold, and sending the sorted display links to the client for display.
Fig. 8 is a schematic diagram of an electronic device according to an exemplary embodiment. It should be noted that the electronic device shown in fig. 8 is only an example, and should not impose any limitation on the functions and application scope of the embodiments of the present application.
As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU) 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. CPU 801 ROM 802 and RAM 803 are connected to each other by bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; comprising hard disks or the like a storage section 808; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. When executed by a Central Processing Unit (CPU) 801, the computer program performs the above-described functions defined in the terminal of the present application.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware. The described units may also be provided in a processor, for example, described as: a processor includes a first acquisition module, a second acquisition module, a third acquisition module, and a determination module. The names of these modules do not constitute a limitation on the module itself in some cases.
Exemplary embodiments of the present invention are specifically illustrated and described above. It is to be understood that this invention is not limited to the precise arrangements, instrumentalities and instrumentalities described herein; on the contrary, the invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (10)

1. A method for data interaction, the method comprising:
acquiring keywords from a client, and acquiring click weights of each display link corresponding to the keywords;
obtaining conversion data of each display link according to a first model, wherein the conversion data comprises conversion rate;
acquiring resource occupation data of each display link according to a second model, wherein the resource occupation data comprises conversion cost data;
determining an index threshold of the keyword based on the click weight, the conversion data and the resource occupation data;
sorting the display links corresponding to the keywords based on the index threshold, and sending the sorted display links to the client for display;
the click weight of each display link is calculated by the following formula:
;
wherein the said Representing keywords +.>Corresponding show link->Is used to determine the click weight of (1),representing keywords +.>Corresponding show link->The number of times clicked;
the ranking the display links corresponding to the keywords based on the index threshold includes:
filtering out display links with index data lower than the index threshold value from the display links corresponding to the keywords;
and calculating the click rate of the filtered display links based on the CTR model, and sequencing the filtered display links based on the click rate of the display links and index data.
2. The method of claim 1, wherein the method further comprises: acquiring the first model;
acquiring the first model, including:
taking the characteristic information of keywords and corresponding display links in the historical conversion data and the conversion results of the corresponding display links as samples, and generating a first data set comprising a first training set and a first test set;
training a first model based on samples in the first training set;
and testing the initially selected first model based on the samples in the first test set to obtain a first model.
3. The method of claim 1, wherein the method further comprises: acquiring the second model;
Obtaining the second model includes:
screening display links with the conversion number larger than a threshold value from historical resource occupation data, taking characteristic information of the display links and rate data corresponding to the display links as samples, and generating a second data set comprising a second training set and a second test set;
training a first selected second model based on the samples in the second training set;
and testing the initially selected second model based on the samples in the second test set to obtain a second model.
4. The method of claim 1, wherein the determining the index threshold for the keyword based on the click weight, the conversion data, and the resource occupancy data comprises:
determining click resource data of the keyword based on the click weight, the conversion data and the resource occupation data;
and determining an index threshold value of the keyword based on the click resource data and a preset index coefficient.
5. The method of claim 4, wherein the determining click resource data for the keyword based on the click weight, the conversion data, and the resource occupancy data comprises:
Calculating click resource data of the keywords through the following formula:
;
wherein the saidRepresenting keywords +.>Click resource data of said +.>Representing keywords +.>Corresponding show link->Click weight of said +.>Representing the keywordsCorresponding show link->Is described>Representing the keyword->Corresponding show link->Is a resource occupancy data of (1).
6. The method of claim 5, wherein determining the index threshold for the keyword based on the click resource data and a preset index coefficient comprises:
calculating an index threshold of the keyword through the following formula:
;
wherein the saidRepresenting the keyword->Index threshold of (2), saidRepresenting a preset index coefficient, said +.>Representing the keyword->Is provided with click resource data.
7. An apparatus for data interaction, the apparatus comprising:
the first acquisition module is used for acquiring keywords from the client and acquiring click weights of each display link corresponding to the keywords; the click weight of each display link is calculated by the following formula:
;
wherein the saidRepresenting keywords +. >Corresponding show link->Is used to determine the click weight of (1),representing keywords +.>Corresponding show link->The number of times clicked;
the second acquisition module is used for acquiring conversion data of each display link according to the first model, wherein the conversion data comprises conversion rate;
the third acquisition module is used for acquiring the resource occupation data of each display link according to the second model, wherein the resource occupation data comprises conversion cost data;
the determining module is used for determining an index threshold value of the keyword based on the click weight, the conversion data and the resource occupation data;
the ranking module is configured to rank the display links corresponding to the keywords based on the indicator threshold, and send the ranked display links to the client for display, where the ranking the display links corresponding to the keywords based on the indicator threshold includes: filtering out display links with index data lower than the index threshold value from the display links corresponding to the keywords; and calculating the click rate of the filtered display links based on the CTR model, and sequencing the filtered display links based on the click rate of the display links and index data.
8. A data interaction system, comprising:
the client is used for displaying the keywords and displaying the keywords after receiving the display links sent by the server;
the server is used for acquiring the keywords from the client and acquiring the click weights of the display links corresponding to the keywords, wherein the click weights of the display links are calculated by the following formula:
;
wherein the saidRepresenting keywords +.>Corresponding show link->According to a first model, obtaining conversion data of each display link, wherein the conversion data comprises conversion rate, obtaining resource occupation data of each display link according to a second model, wherein the resource occupation data comprises conversion cost data, determining an index threshold value of the keyword based on the click weight, the conversion data and the resource occupation data, sorting display links corresponding to the keyword based on the index threshold value, and sending the sorted display links to the client, wherein display links with index data of the display links lower than the index threshold value are filtered from the display links corresponding to the keyword; and calculating the click rate of the filtered display links based on the CTR model, and sequencing the filtered display links based on the click rate of the display links and index data.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method steps of any of claims 1-6.
10. An electronic device, comprising: one or more processors;
storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method steps of any of claims 1-6.
CN201910273138.1A 2019-04-04 2019-04-04 Method and device for data interaction, storage medium and electronic equipment Active CN111782926B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910273138.1A CN111782926B (en) 2019-04-04 2019-04-04 Method and device for data interaction, storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910273138.1A CN111782926B (en) 2019-04-04 2019-04-04 Method and device for data interaction, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN111782926A CN111782926A (en) 2020-10-16
CN111782926B true CN111782926B (en) 2024-04-09

Family

ID=72755472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910273138.1A Active CN111782926B (en) 2019-04-04 2019-04-04 Method and device for data interaction, storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN111782926B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113744015A (en) * 2020-10-20 2021-12-03 北京沃东天骏信息技术有限公司 Sorting method, device, equipment and computer storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116582A (en) * 2011-11-16 2013-05-22 阿里巴巴集团控股有限公司 Information retrieval method and relevant system and device
CN106504011A (en) * 2015-09-06 2017-03-15 阿里巴巴集团控股有限公司 A kind of methods of exhibiting of business object and device
CN107977859A (en) * 2017-11-14 2018-05-01 广州优视网络科技有限公司 Advertisement placement method, device, computing device and storage medium
CN108062680A (en) * 2017-11-15 2018-05-22 深圳市金立通信设备有限公司 It estimates conversion ratio and determines method, want advertisement side's platform and computer-readable medium
CN109064221A (en) * 2018-07-20 2018-12-21 广州市丰申网络科技有限公司 AdWords intelligence put-on method and equipment based on big data technology

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090043649A1 (en) * 2007-08-08 2009-02-12 Google Inc. Content Item Pricing
US20170262899A1 (en) * 2016-02-11 2017-09-14 360I Llc Computing Mathematically-Optimized Properties for Paid Search

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116582A (en) * 2011-11-16 2013-05-22 阿里巴巴集团控股有限公司 Information retrieval method and relevant system and device
CN106504011A (en) * 2015-09-06 2017-03-15 阿里巴巴集团控股有限公司 A kind of methods of exhibiting of business object and device
CN107977859A (en) * 2017-11-14 2018-05-01 广州优视网络科技有限公司 Advertisement placement method, device, computing device and storage medium
CN108062680A (en) * 2017-11-15 2018-05-22 深圳市金立通信设备有限公司 It estimates conversion ratio and determines method, want advertisement side's platform and computer-readable medium
CN109064221A (en) * 2018-07-20 2018-12-21 广州市丰申网络科技有限公司 AdWords intelligence put-on method and equipment based on big data technology

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机器学习混合算法的APP广告转化率预测研究;赵杨;袁析妮;陈亚文;武立强;;数据分析与知识发现(11);全文 *

Also Published As

Publication number Publication date
CN111782926A (en) 2020-10-16

Similar Documents

Publication Publication Date Title
US7827128B1 (en) System identification, estimation, and prediction of advertising-related data
US10037543B2 (en) Estimating conversion rate in display advertising from past performance data
Miralles-Pechuán et al. A novel methodology for optimizing display advertising campaigns using genetic algorithms
US8732015B1 (en) Social media pricing engine
US20140244345A1 (en) Measuring Effectiveness Of Marketing Campaigns Across Multiple Channels
US20160132935A1 (en) Systems, methods, and apparatus for flexible extension of an audience segment
CN109299356B (en) Activity recommendation method and device based on big data, electronic equipment and storage medium
CN111125574A (en) Method and apparatus for generating information
US20120259867A1 (en) Data classification tool using dynamic allocation of attribute weights
CN113947336A (en) Method, device, storage medium and computer equipment for evaluating risks of bidding enterprises
CN109543940B (en) Activity evaluation method, activity evaluation device, electronic equipment and storage medium
CN112446764A (en) Game commodity recommendation method and device and electronic equipment
US20140257972A1 (en) Method, computer readable medium and system for determining true scores for a plurality of touchpoint encounters
CN113761348A (en) Information recommendation method and device, electronic equipment and storage medium
US20140257966A1 (en) Method , computer readable medium and system for determining weights for attributes and attribute values for a plurality of touchpoint encounters
CN109344347B (en) Display control method, display control device, electronic equipment and computer-readable storage medium
CN111782926B (en) Method and device for data interaction, storage medium and electronic equipment
CN110197317B (en) Target user determination method and device, electronic equipment and storage medium
CN112884529B (en) Advertisement bidding method, device, equipment and medium
US20230316106A1 (en) Method and apparatus for training content recommendation model, device, and storage medium
CN113763004A (en) Information matching method and device
CN113778979A (en) Method and device for determining live broadcast click rate
CN111199454A (en) Real-time user transformation evaluation method and device and electronic equipment
CN111401935B (en) Resource allocation method, device and storage medium
CN115344774A (en) User account screening method and device and server

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant