CN107590691B - Information publishing method and device, storage medium and terminal - Google Patents
Information publishing method and device, storage medium and terminal Download PDFInfo
- Publication number
- CN107590691B CN107590691B CN201710798258.4A CN201710798258A CN107590691B CN 107590691 B CN107590691 B CN 107590691B CN 201710798258 A CN201710798258 A CN 201710798258A CN 107590691 B CN107590691 B CN 107590691B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- time interval
- determining
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
An information issuing method and device, a storage medium and a terminal are provided, and the method comprises the following steps: judging whether a user is a target audience of information to be released or not according to flow data, wherein the flow data are generated based on the internet surfing behavior of the user; when the judgment result shows that the user is the target audience of the information to be published, determining publishing time according to the information publishing cost of the information to be published; and issuing the information to be issued to the user at the issuing time. According to the scheme provided by the invention, the target audience can be searched based on intelligent flow screening of big data, and the identification accuracy of the target audience is greatly improved, so that the CTR is better improved.
Description
Technical Field
The invention relates to the field of internet information publishing, in particular to an information publishing method and device, a storage medium and a terminal.
Background
In the internet information distribution industry, Real Time Bidding (RTB) is an information purchasing method that has become popular in recent years. Unlike traditional contractual information distribution models, RTBs allow information distributors to bid on every information presentation opportunity, replacing information presentation place purchases with crowd purchases.
On this basis, a Demand Side Platform (DSP) is used as a proxy of the information publisher, and in order to assist the information publisher to complete the RTB operation, a decision needs to be made for each information publication request within 100ms to determine whether to participate in bidding or not and how much to bid if participating in bidding. The information publisher usually examines the proxy delivery performance of the DSP by using Click Through Rate (CTR) as an index. Therefore, how to obtain better information delivery effect with less cost is one of the focus points of DSP.
When the current DSP executes the RTB operation, in order to achieve a better information delivery effect, after analyzing characteristics of the information to be published, a rule is manually set according to experience, and a flow crowd (also referred to as a target audience) suitable for the information to be published is defined based on the set rule, for example, the target audience can be defined as a working place such as beijing, shanghai, guangzhou, and shenzhen; the mobile phone is as follows: and the iPhone puts the information to be released aiming at the target audiences in a repeated mode, so that the information putting cost of the information releasing party is saved, and the click through rate of the information to be released is improved.
However, the existing rules determined based on manual experience are often relatively comprehensive, the accuracy of searching for the target audience is limited, the deep identification of the target audience is not facilitated, and the information delivery success rate of an information publisher is also seriously influenced.
Disclosure of Invention
The technical problem solved by the invention is how to more efficiently and accurately find the target audience suitable for the information to be released.
In order to solve the above technical problem, an embodiment of the present invention provides an information publishing method, including: judging whether a user is a target audience of information to be released or not according to flow data, wherein the flow data are generated based on the internet surfing behavior of the user; when the judgment result shows that the user is the target audience of the information to be published, determining publishing time according to the information publishing cost of the information to be published; and issuing the information to be issued to the user at the issuing time.
Optionally, the determining, according to the traffic data, whether the user is a target audience of the information to be published includes: determining the similarity between the user and a target audience of the information to be published according to the flow data; and judging whether the user is the target audience of the information to be released or not according to the similarity.
Optionally, the determining, according to the similarity, whether the user is the target audience of the information to be published includes: judging whether the similarity exceeds a preset threshold value or not; and when the judgment result shows that the similarity exceeds the preset threshold value, determining the user as the target audience.
Optionally, the determining, according to the traffic data, the similarity between the user and the target audience of the information to be published includes: determining the deviation degree of the flow data and preset standard information based on a preset prediction model, wherein the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published; and determining the similarity according to the deviation.
Optionally, the preset prediction model is obtained by training based on a positive sample and a negative sample which are historically associated with an information publisher providing the information to be published, where the positive sample is traffic data of a user who historically realizes a preset target, and the negative sample is traffic data of a user who historically does not realize the preset target.
Optionally, the determining the publishing time according to the information publishing cost of the information to be published includes: and determining the issuing time of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval.
Optionally, the determining, according to a comparison result between the information distribution cost of the information to be distributed in the current time interval and the information distribution cost of the information to be distributed in a preset time interval, a distribution time of the information to be distributed includes: when the information publishing cost of the information to be published in the current time interval is greater than the information publishing cost of the information to be published in a preset time interval, passing the flow data with a first probability, wherein the preset time interval is greater than the current time interval; and for the passing flow data, determining the issuing time of the information to be issued as immediate sending.
Optionally, the determining, according to a comparison result between the information distribution cost of the information to be distributed in the current time interval and the information distribution cost of the information to be distributed in a preset time interval, the distribution time of the information to be distributed further includes: when the information issuing cost of the information to be issued in the current time interval is less than or equal to the information issuing cost of the information to be issued in the preset time interval, passing through the flow data at a second probability; and for the passing flow data, determining the issuing time of the information to be issued as immediate sending.
Optionally, the first probability is a ratio of an information issuing cost of the information to be issued in a preset time interval to an information issuing cost of the information to be issued in a current time interval; the second probability is greater than the first probability.
Optionally, the information publishing method further includes: when the judgment result shows that the user is not the target audience of the information to be released, the flow data is passed through according to a third probability; and for the passing traffic data, sending the information to be issued to the user associated with the traffic data.
An embodiment of the present invention further provides an information issuing apparatus, including: the judging module is used for judging whether a user is a target audience of information to be released or not according to flow data, and the flow data are generated based on the internet surfing behavior of the user; the determining module is used for determining the releasing time according to the information releasing cost of the information to be released when the judging result shows that the user is the target audience of the information to be released; and the issuing module is used for issuing the information to be issued to the user at the issuing time.
Optionally, the determining module includes: the first determining submodule is used for determining the similarity between the user and a target audience of the information to be published according to the flow data; and the judging submodule is used for judging whether the user is the target audience of the information to be released according to the similarity.
Optionally, the determining sub-module includes: the judging unit is used for judging whether the similarity exceeds a preset threshold value or not; and the first determining unit is used for determining the user as the target audience when the judgment result shows that the similarity exceeds the preset threshold.
Optionally, the first determining sub-module includes: a second determining unit, configured to determine, based on a preset prediction model, a deviation degree of the traffic data from preset standard information, where the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published; and the third determining unit is used for determining the similarity according to the deviation degree.
Optionally, the preset prediction model is obtained by training based on a positive sample and a negative sample which are historically associated with an information publisher providing the information to be published, where the positive sample is traffic data of a user who historically realizes a preset target, and the negative sample is traffic data of a user who historically does not realize the preset target.
Optionally, the determining module includes: and the second determining submodule is used for determining the issuing time of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval.
Optionally, the second determining sub-module includes: a first processing unit, configured to pass through the traffic data with a first probability when an information distribution cost of the information to be distributed in a current time interval is greater than an information distribution cost of the information to be distributed in a preset time interval, where the preset time interval is greater than the current time interval; and the fourth determining unit is used for determining the distribution time of the information to be distributed as immediate transmission for the passing flow data.
Optionally, the second determining sub-module further includes: the second processing unit passes through the flow data according to a second probability when the information issuing cost of the information to be issued in the current time interval is less than or equal to the information issuing cost of the information to be issued in a preset time interval; and the fifth determining unit is used for determining the distribution time of the information to be distributed as immediate transmission for the passing flow data.
Optionally, the first probability is a ratio of an information issuing cost of the information to be issued in a preset time interval to an information issuing cost of the information to be issued in a current time interval; the second probability is greater than the first probability.
Optionally, the information issuing apparatus further includes: the processing module passes through the flow data according to a third probability when the judgment result shows that the user is not the target audience of the information to be published; and the sending module is used for sending the information to be issued to the user associated with the traffic data for the passing traffic data.
The embodiment of the invention also provides a storage medium, wherein computer instructions are stored on the storage medium, and the computer instructions execute the steps of the method when running.
The embodiment of the present invention further provides a terminal, which includes a memory and a processor, where the memory stores computer instructions capable of running on the processor, and the processor executes the steps of the method when executing the computer instructions.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
judging whether a user is a target audience of information to be released or not according to flow data, wherein the flow data are generated based on the internet surfing behavior of the user; when the judgment result shows that the user is the target audience of the information to be published, determining publishing time according to the information publishing cost of the information to be published; and issuing the information to be issued to the user at the issuing time. Compared with the existing scheme for searching for the target audience formulated based on manual experience, the technical scheme of the embodiment of the invention can judge whether the user is the target audience of the information to be published according to the flow data generated when the user surfs the internet, and determine the publishing time for sending the information to be published to the user according to the judgment result, so that the information to be published is published to the user at the most appropriate time, and the CTR of the information to be published is improved. Furthermore, the technical scheme of the embodiment of the invention can search the target audience based on the intelligent flow screening of the big data, thereby greatly improving the identification accuracy of the target audience and further improving the CTR (program traffic rating) better.
Further, the flow data comprises basic information of the user, and based on the technical scheme of the embodiment of the invention, the similarity between the user and the target audience of the information to be published can be determined according to the basic information, and then whether the user is the target audience of the information to be published is judged according to the similarity, so that the target audience is accurately found from massive data, and the problem that a search result is too extensive when a rule is artificially established for screening the target audience is solved.
Drawings
Fig. 1 is a flowchart of an information distribution method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a specific implementation of step S101 in the first embodiment;
FIG. 3 is a flowchart of one embodiment of step S102 in the first embodiment;
fig. 4 is a schematic structural diagram of an information distribution apparatus according to a second embodiment of the present invention;
FIG. 5 is a schematic diagram of an exemplary application scenario in which an embodiment of the present invention may be employed;
FIG. 6 is a schematic diagram of a training of a predictive model used in an embodiment of the invention.
Detailed Description
As will be understood by those skilled in the art, as indicated in the background art, in order to obtain a better information delivery effect, an existing Demand Side Platform (DSP) manually analyzes target audiences suitable for information publishers and delivers information to be published of the information publishers to the target audiences.
However, in the existing technical scheme of manually formulating rules according to experience and searching for target audiences in mass data according to the rules, the search result is too comprehensive due to unreasonable formulation of the rules, and the target audiences suitable for the information to be published cannot be effectively and accurately found.
In order to solve the technical problem, the technical scheme of the embodiment of the invention judges whether the user is the target audience of the information to be released according to the flow data, wherein the flow data is generated based on the internet surfing behavior of the user; when the judgment result shows that the user is the target audience of the information to be published, determining publishing time according to the information publishing cost of the information to be published; and issuing the information to be issued to the user at the issuing time.
The technical scheme of the embodiment of the invention can judge whether the user is the target audience of the information to be released or not according to the flow data generated when the user surfs the internet, and determine the releasing time of the information to be released to be sent to the user according to the judging result, so that the information to be released is released to the user at the most appropriate time to improve the CTR of the information to be released.
Furthermore, the technical scheme of the embodiment of the invention can search the target audience based on the intelligent flow screening of the big data, thereby greatly improving the identification accuracy of the target audience and further improving the CTR (program traffic rating) better.
Further, the flow data comprises basic information of the user, and based on the technical scheme of the embodiment of the invention, the similarity between the user and the target audience of the information to be published can be determined according to the basic information, and then whether the user is the target audience of the information to be published is judged according to the similarity, so that the target audience is more accurately found from massive data, and the problem that a search result is not accurate enough when a rule is artificially established for screening the target audience is solved.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a flowchart of an information distribution method according to a first embodiment of the present invention. Specifically, by adopting the scheme of the embodiment, the information to be released can be released to the target audience of the information releasing party in a targeted manner at the most appropriate time.
The target audience can be associated with the information to be published, namely, a potential target audience is accurately searched in the mass data aiming at the information to be published, and after the target audience is found, the information to be published is released to the target audience at the most appropriate time.
Or, the target audience may also be associated with an information publisher that provides the information to be published, that is, the information publisher accurately searches for a potential target audience in mass data, and delivers the information to be published of the information publisher to the target audience at a most appropriate time after finding the target audience. The information to be published can be any information to be published provided by the information publisher, and can also be specific information to be published provided by the information publisher determined by further analyzing the historical network browsing habits of the found target audience.
More specifically, in this embodiment, the information issuing method may include the following steps:
step S101, judging whether a user is a target audience of information to be released or not according to flow data, wherein the flow data is generated based on the internet surfing behavior of the user.
And step S102, when the judgment result shows that the user is the target audience of the information to be released, determining the releasing time according to the information releasing cost of the information to be released.
Step S103, the information to be issued is issued to the user at the issuing time.
Further, the traffic data may include Identification Information (ID) of the device, which is hereinafter referred to as device ID. As a non-limiting example, the user and the internet access trace generated by the internet behavior thereof may be associated by the device ID. Alternatively, for a user's internet trace generated by a Personal Computer (PC), the user may be associated with the user according to an ID of a browser installed on the PC.
Preferably, the internet access footprint associated with the user may include a record of the user's browsing on a website of the information publisher and/or the information presentation platform. The information publisher refers to a provider of the information to be published; the information display platform is a platform for providing information display positions for the information to be displayed. For example, the browsing history may include browsing duration, details of the specific web page browsed, and the like.
Further, based on an internet access trace generated by the internet behavior of the user, the basic information of the user can be acquired. Specifically, the basic information of the user may include information of age, sex, purchasing power, and the like of the user. Preferably, the basic information of the user can be collected from the information publisher (and/or information display platform, such as website, webpage, etc.), and can also be directly collected from the historical internet access data of the user.
For example, the basic information of the user can be directly obtained based on the data provided by the user to the information publisher and/or the information presentation platform; for another example, the basic information of the user may be speculatively obtained based on internet access traces of the user at the information distributor and/or the information presentation platform. The operation of inference can be executed by the information publisher and/or the information display platform, or can be executed by a terminal (such as a DSP) executing the solution of this embodiment.
In a non-limiting embodiment, the DSP may pre-record basic information of at least one user and an associated device ID, and when receiving the traffic data, look up corresponding basic information from a pre-stored record based on the device ID included in the traffic data.
In another non-limiting embodiment, the traffic data may also directly include basic information of the user. For example, the information presentation platform may directly include the device ID and basic information of the user in the traffic data sent to the DSP. Further, the traffic data may be generated based on internet access behavior of the user. For example, when a user accesses an information display platform (such as a blog), if the blog has an information display position, a site (i.e., a background server) of the blog may notify the DSP that someone is browsing the blog and ask the DSP whether the DSP needs to bid on the information display position, the DSP may adopt the technical scheme of this embodiment to determine whether the user is a target audience of information to be released that the DSP is ready to display, and execute corresponding operation according to the determination result. In other words, when a user browses an information display platform such as a webpage where an information display position is located, the owner of the information display platform sends the device ID of the user browsing the information display platform to the DSP, and the DSP determines, by using the technical scheme of this embodiment, the basic information of the user (or other internet access information capable of describing the user characteristics of the user) through the device ID to determine whether the user meets the target audience requirement of the information to be displayed that the DSP wishes to release.
It should be noted that the terminal adopting the scheme of this embodiment may also determine the similarity between the user and the target audience of the information to be released based on other information besides the basic information, where the other data may be any information that can describe the user characteristics and is obtained based on the user internet behavior. Wherein the user characteristics may include purchasing preferences, information browsing preferences, etc. of the user. For example, the DSP adopting the scheme of this embodiment may train the preset prediction model according to all or part of the content of the data generated by the user accessing the internet, and then determine, according to the preset prediction model obtained by the training, all or part of the content of the data generated by the user accessing the internet, which is obtained this time, to determine the similarity between the user and the target audience of the information to be published.
For simplicity, the basic information of the user is set forth as a judgment criterion.
In one non-limiting embodiment, referring to fig. 2, the step S101 may include: step S1011, determining the similarity between the user and the target audience of the information to be released according to the basic information; step S1012, determining whether the user is a target audience of the information to be published according to the similarity.
The target audience of the information to be published may include users who historically achieve a preset target, and the preset target may be associated with the information to be published. For example, the preset target may include clicking information to be published, and when a user historically clicks the information to be published, it may be determined that the user realizes the preset target; for another example, the preset target may further include purchasing a commodity associated with the information to be released, and when a user completes a purchasing behavior of the commodity historically, it may be determined that the user achieves the preset target. Preferably, the preset target may be determined by an information issuer.
Specifically, in the present non-limiting embodiment, the step S1011 may include the steps of: determining the deviation degree of the basic information and preset standard information based on a preset prediction model, wherein the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published; and determining the similarity according to the deviation. The preset prediction model may be obtained based on training of positive samples and negative samples historically associated with an information publisher providing the information to be published, where the positive samples are traffic data of users historically realizing a preset target, and the negative samples are traffic data of users historically not realizing the preset target.
For example, the deviation degree may be taken from an interval range of [0,1], where a deviation degree of 0 indicates that the similarity between the user and the target audience of the information to be published is the highest; and when the deviation degree is 1, the similarity between the user and the target audience of the information to be released is the lowest.
Further, the preset standard information may be used to describe a standard target audience of the information to be published, and the standard target audience may refer to users who theoretically achieve the preset target in hundreds of cents. Preferably, the preset standard information may include basic information of the standard target audience. Taking the information to be released as loving heart promoting information as an example, according to the training of the preset prediction model (the preset prediction model only takes age and gender as training dimensions), the preset standard information may include female users aged 20-50 years. Further, the preset prediction model can also perform model training in more dimensions to obtain the weight value of each dimension corresponding to the standard target audience of the information to be published, and further determine the preset standard information by weighted summation of all dimensions.
Further, in this non-limiting embodiment, the preset prediction model may be trained according to the positive sample and the negative sample, so as to obtain the preset standard information through the preset prediction model, and then determine the similarity between the user and the target audience of the information to be published according to the difference (i.e., the deviation) between the preset standard information and the basic information of the user, thereby determining the possibility that the user is the target audience of the information to be published.
Preferably, the positive and negative examples can be provided by the information publisher, or can be obtained through other channels (such as self-collection).
Preferably, a Logistic Regression (LR) algorithm may be used to train the preset prediction model. Those skilled in the art can also change the embodiments according to actual needs, and details are not described herein.
More specifically, in the present non-limiting embodiment, the step S1012 may include the steps of: judging whether the similarity exceeds a preset threshold value or not; and when the judgment result shows that the similarity exceeds the preset threshold value, determining the user as the target audience. Preferably, the preset threshold may be determined by a processing party such as an information issuing party or a DSP adopting the scheme of the embodiment.
In a non-limiting embodiment, when the similarity between the user and the target audience of the information to be published exceeds the preset threshold, the determination result of step S101 is affirmative; otherwise, the determination result of the step S101 is negative. Further, when the determination result of the step S101 is affirmative, the steps S102 and S103 are performed; otherwise, namely when the similarity between the user and the target audience of the information to be published does not exceed the preset threshold value, executing the step S104, and passing through the flow data according to a third probability; operation S105 is performed, and for the passing traffic data, the information to be published is sent (also referred to as publishing) to the user associated with the traffic data. Preferably, the exceeding can mean greater than or equal to, and the not exceeding can mean less than; alternatively, the excess may mean greater than, and the non-excess may mean equal to or less than. The definitions of exceeding and not exceeding can be adjusted by the person skilled in the art according to the actual need.
Further, the information publishing Cost can be characterized based on a Cost Per Action (CPA). For example, the time at which the cost per action of publishing the information to be published within the future period of time is the lowest can be determined as the publishing opportunity.
Further, the third probability may be a random number; or, the third probability may also be a ratio of a sum of Click rates (Click) of the information to be published to a sum of Page Views (PV) of an information presentation platform that presents the information to be published within the same time, that is, the third probability may be a Click Through Rate (Click Through Rate, abbreviated as CTR) of the information to be published within a preset time interval.
Those skilled in the art understand that when the similarity between the user and the target audience of the information to be published does not exceed the preset threshold, it may be determined that the user is not the target audience of the information to be published, but based on the scheme of this embodiment, the users are not directly discarded at this time, but the target audience can be deeply detected through traffic with a certain probability, so as to mine more potential target audiences, and thus more positive samples and negative samples are provided for the preset prediction model, so that the preset prediction model obtained through training can be more comprehensive and more accurate.
In one non-limiting embodiment, the step S102 may include the steps of: and determining the issuing time of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval. Preferably, the preset time interval may be divided into a plurality of time intervals, and the current time interval may belong to the divided plurality of time intervals. For example, the preset time interval may be in units of natural days (24 hours), and the issuing timing of the information to be issued may be determined according to a comparison result between an information issuing cost (such as the cost per action) of the information to be issued in the current 1 hour and an information issuing cost (such as the cost per action) of the information to be issued in the 24 hours. Those skilled in the art can also adjust the lengths of the preset time interval and the current time interval according to actual needs, which is not described herein.
In a preferred example, the step S102 may further include: step S1021, judging whether the information release cost of the information to be released in the current time interval is greater than the information release cost of the information to be released in a preset time interval; step S1022, when the information distribution cost of the information to be distributed in the current time interval is greater than the information distribution cost of the information to be distributed in a preset time interval, the flow data may be passed through with a first probability, where the preset time interval is greater than the current time interval; step S1023, for the passing traffic data, determining that the distribution timing of the information to be distributed is immediate transmission.
Preferably, the first probability may be a ratio of an information distribution cost of the information to be distributed in a preset time interval to an information distribution cost of the information to be distributed in a current time interval.
The technical personnel in the field understand that, when the information publishing cost of the information to be published in the current time interval is greater than the information publishing cost of the information to be published in the preset time interval, it indicates that the current time interval may not be the most appropriate time for publishing the information to be published to the user, for example, the information to be published is merchandise push information, the corresponding target audience is white-collar people, and the current time interval is 9 to 10 am. Therefore, at this time, the information to be released can be released with a small probability, so as to obtain a high CTR as much as possible on the premise of ensuring that the CPA is not too high. The most suitable time may be that the highest CTR and the lowest CPA can be obtained after the information to be issued is issued to the user at that time.
Further, for the traffic data screened with the first probability (i.e., the traffic data that does not pass), the basic information of the user may be temporarily stored, and when the basic information of the user is received again next time, the pre-stored data may be directly searched to determine that the user is the target audience of the information to be published, and whether to immediately publish the information to be published to the user is determined according to a comparison result between the information publishing cost of the current time interval in which the next receiving period is located and the information publishing cost of the preset time interval.
As a variation, when the determination result of the step S1021 is negative, that is, when the information distribution cost of the information to be distributed in the current time interval is less than or equal to the information distribution cost of the information to be distributed in the preset time interval, step S1024 may be performed to pass through the traffic data with a second probability; then, the step S1023 may also be executed, and for the passing traffic data, it is determined that the distribution timing of the information to be distributed is immediate transmission. Preferably, the second probability may be greater than the first probability.
Those skilled in the art understand that when the information publishing cost of the information to be published in the current time interval is less than or equal to the information publishing cost of the information to be published in the preset time interval, it may be determined that the current time interval may be a more appropriate publishing opportunity, and thus traffic may be passed with a greater probability (at least a probability greater than the first probability) to publish the information to be published to more users determined as the target audience.
Preferably, the second probability may be 1, that is, the information to be published is published to all users determined as the target audience in the current time interval. Further, for the traffic which does not pass through the first probability, the information to be distributed may be distributed to the users corresponding to the traffic which does not pass through the current time interval.
Preferably, the second probability may be greater than the first probability, and the first probability may be greater than the third probability.
Therefore, by adopting the scheme of the first embodiment, when the traffic data of the user is received, the basic information of the user can be obtained, and the similarity between the user and the target audience of the information to be published is determined according to the basic information. When the similarity exceeds a preset threshold, the user can be determined as a target audience of the information to be published. But at this time, the information to be sent is not necessarily immediately issued to the user, but the size relationship between the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval is further judged, and when the information issuing cost of the information to be issued in the current time interval is greater than the information issuing cost of the information to be issued in the preset time interval, the flow data can be passed through at a first probability; otherwise, the information to be issued is issued to the user at the most appropriate time through the flow data according to the second probability so as to improve the CTR of the information to be issued. Wherein the similarity may be determined according to a preset prediction model.
Furthermore, users determined as target audiences of information to be released because the similarity is lower than a preset threshold value are not discarded completely, and the flow data of the users are passed through by a third probability to detect potential target audiences so as to make up the flow data which cannot be captured by a preset prediction model, so that the preset prediction model is expanded and perfected.
Fig. 4 is a schematic structural diagram of an information distribution apparatus according to a second embodiment of the present invention. Those skilled in the art understand that the information distribution apparatus 4 according to this embodiment may be used to implement the method technical solutions described in the embodiments shown in fig. 1 to fig. 3.
Specifically, in this embodiment, the information distribution apparatus 4 may include a determining module 41, configured to determine whether a user is a target audience of information to be distributed according to traffic data, where the traffic data is generated based on internet access behavior of the user; the determining module 42 is configured to determine a publishing time according to the information publishing cost of the information to be published when the determination result indicates that the user is the target audience of the information to be published; the issuing module 43 is configured to issue the information to be issued to the user at the issuing time.
Further, the determining module 41 may include a first determining sub-module 411, configured to determine, according to the traffic data, a similarity between the user and a target audience of the information to be published; and the judging submodule 412 is configured to judge whether the user is a target audience of the information to be published according to the similarity.
Further, the determining sub-module 412 may include a determining unit 4121 configured to determine whether the similarity exceeds a preset threshold; the first determining unit 4122 determines that the user is the target audience when the determination result indicates that the similarity exceeds the preset threshold.
Further, the first determining sub-module 411 may include a second determining unit 4111, configured to determine, based on a preset prediction model, a deviation degree of the traffic data from preset standard information, where the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published; a third determining unit 4112, configured to determine the similarity according to the deviation degree.
Preferably, the preset prediction model may be obtained by training based on a positive sample and a negative sample historically associated with an information publisher providing the information to be published, where the positive sample is traffic data of a user who historically achieves a preset target, and the negative sample is traffic data of a user who historically does not achieve the preset target.
Further, the determining module 42 may include a second determining submodule 421, configured to determine the issuing timing of the information to be issued according to a comparison result between the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in a preset time interval.
In a preferred example, the second determining submodule 421 may include a first processing unit 4211, configured to pass through the traffic data with a first probability when an information distribution cost of the information to be distributed in a current time interval is greater than an information distribution cost of the information to be distributed in a preset time interval, where the preset time interval is greater than the current time interval; a fourth determining unit 4212 determines that the distribution timing of the information to be distributed is immediate transmission for the passing traffic data.
As a variation, the second determining submodule 421 may further include a second processing unit 4213, where when the information distribution cost of the information to be distributed in the current time interval is less than or equal to the information distribution cost of the information to be distributed in a preset time interval, the traffic data is passed through with a second probability; a fifth determining unit 4214 determines, for the passing traffic data, that the distribution timing of the information to be distributed is immediate transmission.
Preferably, the first probability may be a ratio of an information publishing cost of the information to be published in a preset time interval to an information publishing cost of the information to be published in a current time interval; the second probability may be greater than the first probability.
Further, the information distribution apparatus 4 may further include a processing module 44, when the determination result indicates that the user is not the target audience of the information to be distributed, passing through the traffic data according to a third probability; the sending module 45 sends the information to be published to the user associated with the traffic data for the passing traffic data.
Preferably, the issuing module 43 and the sending module 45 may be integrated into the same module; alternatively, the publishing module 43 and the sending module 45 may be integrated into different modules, and both of them may be used to publish the information to be published.
It should be noted that each module included in the information distribution apparatus 4 according to this embodiment may operate independently, and the technical solutions of the methods in fig. 1 to fig. 3 are executed through interaction between the modules; or, in practical applications, one or more modules included in the information distribution apparatus 4 according to this embodiment may also be integrated together, so as to perform the technical solutions of the methods in fig. 1 to fig. 3 as a whole.
For more details of the operation principle and the operation mode of the information distribution apparatus 4, reference may be made to the relevant descriptions in fig. 1 to fig. 3, which are not described herein again.
Fig. 5 is a schematic diagram of an exemplary application scenario in which an embodiment of the present invention is employed. The target audience prediction module 52 shown in fig. 5 may be integrated with the determination module 41 and its sub-modules and units described in the embodiment shown in fig. 4; the real-time feedback module 53 shown in fig. 5 may be integrated with the determination module 42 and its sub-modules and units, and the publishing module 43 described in the above-described embodiment shown in fig. 4; the intelligent discovery module 54 shown in fig. 5 may be integrated with the processing module 44 and the transmission module 45 described in the above-described embodiment shown in fig. 4.
Specifically, for the received traffic data 51 of the user, the target audience prediction module 52, the real-time feedback module 53 and the intelligent exploration module 54 may execute the method technical solution in the embodiments shown in fig. 1 to 3 to determine whether the user is the target audience of the information to be published, and publish the information to be published to the user at the most appropriate publishing time based on the determination result.
More specifically, in the application scenario, the traffic data 51 of the user may first pass through the target audience prediction module 52 to determine the similarity between the traffic data 51 and the target audience of the information to be published, where the similarity may be determined by a preset prediction model; then, according to the similarity predicted by the preset prediction model, the real-time feedback module 53 or the intelligent exploration module 54 may be called to publish the information to be published to the user at a suitable publishing time.
For example, for the traffic data 51 with the similarity greater than the preset threshold, the real-time feedback module 53 may be called, and the real-time feedback module 53 may determine the information distribution cost of the information to be distributed according to an information presentation platform (vendor) and a current time interval, and further pass through the traffic data 51 with a certain probability (i.e., the first probability or the second probability).
For another example, for the traffic data 51 with the similarity smaller than or equal to the preset threshold, the intelligent exploration module 54 may be called to pass through the traffic data 51 with a certain probability (i.e., the third probability). Those skilled in the art will appreciate that the intelligent exploration module 54 can be used to compensate for the traffic data that the preset prediction model fails to capture, and the target audience prediction module 52, the real-time feedback module 53 and the intelligent exploration module 54 can be combined to comprehensively and accurately find the target audience of the information to be published.
Preferably, the specific value of the preset threshold may be dynamically adjusted according to the final effect obtained by implementing the embodiment of the present invention. Specifically, the larger the preset threshold is, the less the flow data enters the real-time feedback module 53, and the more the flow data enters the intelligent exploration module 54.
Further, referring to fig. 6, the information publisher target audience 61 may be used as a positive sample, the non-information publisher target audience 62 may be used as a negative sample, and a logistic regression algorithm (LR for short) is used to train the preset prediction model adopted in the technical solution of the embodiment of the present invention. Wherein, the information distributor target audience 61 and the non-information distributor target audience 62 can be provided by the information distributor.
Next, table 1 is taken as an example for comparison to show the releasing effect of releasing the same information to be released before and after the scheme described in the embodiment of the present invention is adopted. Table 1 is split into tables 1-1 and tables 1-2 below for presentation, subject to page scale limitations.
Table 1-1 comparison table of information display effect before and after the scheme of the embodiment of the present invention is adopted
Tables 1-2 information presentation effect comparison tables before and after the scheme of the embodiment of the present invention is adopted (continue the above table)
Tables 1-1 and 1-2 show an effect comparison table of the same information to be released before and after the scheme of the embodiment of the invention is adopted. Wherein, the date 1 is a non-experimental group, that is, a result obtained by not adopting the scheme of the embodiment of the invention to issue information; dates 2, 3 and 4 are experimental groups, i.e., results obtained by issuing information using the scheme described in the embodiments of the present invention. It is readily seen that the CTR and CPC of each experimental group are superior to those of the non-experimental group.
The CAPTURE is the CAPTURE number of the traffic data, for example, the CAPTURE number may be the traffic sent to a DSP by an information transaction platform (AdExchange); the BID is the number of participating BIDs; the imp (impression) is a display number (i.e. a putting success number) of the information to be published; the CLK (click) is the click number of the information to be issued; the CTR is the click through rate of the information to be issued; the CPC is the average price of the information to be issued in single display (IMP); the CPA (click Per action) is the average price of the information to be issued in a single Click (CLK). Wherein, CPA is CPC × IMP/Action; the Action is an Action, which in this example corresponds to the CLK listed in table 1-2, i.e., the CLK is used as the target audience (the user who completed the clicking Action will be determined as the target audience of the clicked information to be published).
Further, the specific meaning of the action may be determined by the information publisher, and the definition of the action may be consistent with the definition of the target audience.
For example, when the information publisher defines a user who has performed a Click (CLK) action as a target audience, the CPA may represent an average price of clicks (which may be referred to as an average price).
For another example, when the information publisher defines the user who performed the ordering action as the target audience, after clicking the released information to be published, only a part of the users may actually perform the ordering action, and the CPA may represent the average price of the ordering person (i.e., the target audience).
Further, the embodiment of the present invention further discloses a storage medium, on which computer instructions are stored, and when the computer instructions are executed, the method technical solution described in the embodiments shown in fig. 1 to fig. 3 is executed. Preferably, the storage medium may include a computer-readable storage medium. The storage medium may include ROM, RAM, magnetic or optical disks, etc.
Further, an embodiment of the present invention further discloses a terminal, which includes a memory and a processor, where the memory stores a computer instruction capable of running on the processor, and the processor executes the method technical solution described in the embodiments shown in fig. 1 to fig. 3 when running the computer instruction.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (16)
1. An information distribution method, comprising:
judging whether a user is a target audience of information to be released or not according to flow data, wherein the flow data are generated based on the internet surfing behavior of the user;
when the judgment result shows that the user is the target audience of the information to be published, determining publishing time according to the information publishing cost of the information to be published;
issuing the information to be issued to the user at the issuing occasion;
wherein, the determining the publishing time according to the information publishing cost of the information to be published comprises:
determining the issuing time of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval;
wherein, the determining the publishing time of the information to be published according to the comparison result of the information publishing cost of the information to be published in the current time interval and the information publishing cost of the information to be published in the preset time interval comprises:
when the information publishing cost of the information to be published in the current time interval is greater than the information publishing cost of the information to be published in a preset time interval, passing the flow data with a first probability, wherein the preset time interval is greater than the current time interval;
for the passing flow data, determining the issuing time of the information to be issued as immediate sending;
the determining the issuing timing of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval further includes:
when the information issuing cost of the information to be issued in the current time interval is less than or equal to the information issuing cost of the information to be issued in the preset time interval, passing through the flow data at a second probability;
and for the passing traffic data, determining that the distribution time of the information to be distributed is immediate transmission, and for the traffic data which does not pass through the first probability, distributing the information to be distributed to the user corresponding to the traffic data which does not pass through the first probability in the current time interval.
2. The information distribution method of claim 1, wherein the determining whether the user is a target audience of the information to be distributed according to the traffic data comprises:
determining the similarity between the user and a target audience of the information to be published according to the flow data;
and judging whether the user is the target audience of the information to be released or not according to the similarity.
3. The information distribution method according to claim 2, wherein the determining whether the user is a target audience of the information to be distributed according to the similarity includes:
judging whether the similarity exceeds a preset threshold value or not;
and when the judgment result shows that the similarity exceeds the preset threshold value, determining the user as the target audience.
4. The information distribution method according to claim 2, wherein the determining the similarity between the user and the target audience of the information to be distributed according to the traffic data includes:
determining the deviation degree of the flow data and preset standard information based on a preset prediction model, wherein the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published;
and determining the similarity according to the deviation.
5. The information distribution method according to claim 4, wherein the preset prediction model is obtained by training based on a positive sample and a negative sample historically associated with an information distributor providing the information to be distributed, wherein the positive sample is traffic data of a user who has historically achieved a preset target, and the negative sample is traffic data of a user who has not historically achieved the preset target.
6. The information distribution method according to claim 1, wherein the first probability is a ratio of an information distribution cost of the information to be distributed in a preset time interval to an information distribution cost of the information to be distributed in a current time interval; the second probability is greater than the first probability.
7. The information distribution method according to any one of claims 1 to 6, further comprising:
when the judgment result shows that the user is not the target audience of the information to be released, the flow data is passed through according to a third probability;
and for the passing traffic data, sending the information to be issued to the user associated with the traffic data.
8. An information distribution apparatus, comprising:
the judging module is used for judging whether a user is a target audience of information to be released or not according to flow data, and the flow data are generated based on the internet surfing behavior of the user;
the determining module is used for determining the releasing time according to the information releasing cost of the information to be released when the judging result shows that the user is the target audience of the information to be released;
the release module is used for releasing the information to be released to the user at the release time;
wherein the determining module comprises: the second determining submodule is used for determining the issuing time of the information to be issued according to the comparison result of the information issuing cost of the information to be issued in the current time interval and the information issuing cost of the information to be issued in the preset time interval;
the second determination submodule includes: a first processing unit, configured to pass through the traffic data with a first probability when an information distribution cost of the information to be distributed in a current time interval is greater than an information distribution cost of the information to be distributed in a preset time interval, where the preset time interval is greater than the current time interval; the fourth determining unit is used for determining the issuing time of the information to be issued as immediate sending for the passing flow data;
the second determination sub-module further includes: the second processing unit passes through the flow data according to a second probability when the information issuing cost of the information to be issued in the current time interval is less than or equal to the information issuing cost of the information to be issued in a preset time interval; and a fifth determining unit, configured to determine, for the passing traffic data, that the distribution timing of the information to be distributed is immediate transmission, and for the traffic data that does not pass through the first probability, distribute the information to be distributed to the user corresponding to the traffic data that does not pass through the first probability within the current time interval.
9. The information distribution apparatus according to claim 8, wherein the judgment module includes:
the first determining submodule is used for determining the similarity between the user and a target audience of the information to be published according to the flow data;
and the judging submodule is used for judging whether the user is the target audience of the information to be released according to the similarity.
10. The information distribution apparatus according to claim 9, wherein the judgment sub-module includes:
the judging unit is used for judging whether the similarity exceeds a preset threshold value or not;
and the first determining unit is used for determining the user as the target audience when the judgment result shows that the similarity exceeds the preset threshold.
11. The information distribution apparatus according to claim 9, wherein the first determination sub-module includes:
a second determining unit, configured to determine, based on a preset prediction model, a deviation degree of the traffic data from preset standard information, where the preset standard information corresponds to the preset prediction model, and the preset prediction model is associated with a target audience of the information to be published;
and the third determining unit is used for determining the similarity according to the deviation degree.
12. The information distribution apparatus according to claim 11, wherein the preset prediction model is obtained by training based on a positive sample and a negative sample historically associated with an information distributor that provides the information to be distributed, wherein the positive sample is traffic data of a user who has historically achieved a preset target, and the negative sample is traffic data of a user who has not historically achieved the preset target.
13. The information distribution apparatus according to claim 8, wherein the first probability is a ratio of an information distribution cost of the information to be distributed in a preset time interval to an information distribution cost of the information to be distributed in a current time interval; the second probability is greater than the first probability.
14. The information distribution apparatus according to any one of claims 8 to 13, characterized by further comprising:
the processing module passes through the flow data according to a third probability when the judgment result shows that the user is not the target audience of the information to be published;
and the sending module is used for sending the information to be issued to the user associated with the traffic data for the passing traffic data.
15. A storage medium having stored thereon computer instructions, wherein said computer instructions when executed perform the steps of the method of any of claims 1 to 7.
16. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710798258.4A CN107590691B (en) | 2017-09-06 | 2017-09-06 | Information publishing method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710798258.4A CN107590691B (en) | 2017-09-06 | 2017-09-06 | Information publishing method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107590691A CN107590691A (en) | 2018-01-16 |
| CN107590691B true CN107590691B (en) | 2021-01-15 |
Family
ID=61050855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710798258.4A Active CN107590691B (en) | 2017-09-06 | 2017-09-06 | Information publishing method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590691B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629014A (en) * | 2018-05-07 | 2018-10-09 | 中国平安人寿保险股份有限公司 | A kind of data processing method, device, computer equipment and storage medium |
| CN109816445B (en) * | 2019-01-22 | 2020-12-15 | 腾讯科技（北京）有限公司 | Information delivery method and device |
| CN110147503B (en) * | 2019-05-20 | 2021-08-17 | 北京达佳互联信息技术有限公司 | Information issuing method and device, computer equipment and storage medium |
| CN110322169B (en) * | 2019-07-12 | 2020-11-10 | 河北冀联人力资源服务集团有限公司 | Task issuing method and device |
| CN111666488A (en) * | 2020-04-21 | 2020-09-15 | 上海晶赞融宣科技有限公司 | Information issuing method and device, storage medium and terminal |
| CN112800234B (en) * | 2021-04-15 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Information processing method, device, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321350A (en) * | 2008-07-24 | 2008-12-10 | 北京立通无限科技有限公司 | Method ,device and system for automatically updating application software of mobile terminal |
| CN103150663A (en) * | 2013-02-18 | 2013-06-12 | 亿赞普(北京)科技有限公司 | Method and device for placing network placement data |
| CN103164450A (en) * | 2011-12-15 | 2013-06-19 | 腾讯科技（深圳）有限公司 | Method and device for pushing information to target user |
| CN103489117A (en) * | 2012-06-12 | 2014-01-01 | 深圳市腾讯计算机系统有限公司 | Method and system for information releasing |
| CN103927376A (en) * | 2014-04-25 | 2014-07-16 | 广州壹网网络技术有限公司 | System and method for conducting information spreading through third party social account |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| CN103955381A (en) * | 2014-04-04 | 2014-07-30 | 京信通信系统（中国）有限公司 | Method and system for management server to perform batch software update on terminal equipment |
| CN105279204A (en) * | 2014-07-25 | 2016-01-27 | 阿里巴巴集团控股有限公司 | Information push method and apparatus |
| CN105447730A (en) * | 2015-12-25 | 2016-03-30 | 腾讯科技（深圳）有限公司 | Target user orientation method and device |
| CN105550903A (en) * | 2015-12-25 | 2016-05-04 | 腾讯科技（深圳）有限公司 | Target user determination method and apparatus |
| CN105989004A (en) * | 2015-01-27 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Information releasing pretreatment method and device |
| CN107123057A (en) * | 2017-03-22 | 2017-09-01 | 阿里巴巴集团控股有限公司 | User recommends method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101022636A (en) * | 2007-03-16 | 2007-08-22 | 上海华为技术有限公司 | Device updating method and hardware device |
| CN201383709Y (en) * | 2009-03-02 | 2010-01-13 | 广西电力试验研究院有限公司 | Remote software automatic upgrading device for intelligent electric device |
| CN103684969A (en) * | 2012-08-31 | 2014-03-26 | 国际商业机器公司 | Message handling method and message handling system |
| KR20140098947A (en) * | 2013-01-31 | 2014-08-11 | 삼성전자주식회사 | User terminal, advertisement providing system and method thereof |
| CN104883324A (en) * | 2015-05-28 | 2015-09-02 | 北京交通大学 | Network flow control method and control apparatus |
-
2017
- 2017-09-06 CN CN201710798258.4A patent/CN107590691B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321350A (en) * | 2008-07-24 | 2008-12-10 | 北京立通无限科技有限公司 | Method ,device and system for automatically updating application software of mobile terminal |
| CN103164450A (en) * | 2011-12-15 | 2013-06-19 | 腾讯科技（深圳）有限公司 | Method and device for pushing information to target user |
| CN103489117A (en) * | 2012-06-12 | 2014-01-01 | 深圳市腾讯计算机系统有限公司 | Method and system for information releasing |
| CN103150663A (en) * | 2013-02-18 | 2013-06-12 | 亿赞普(北京)科技有限公司 | Method and device for placing network placement data |
| CN103955381A (en) * | 2014-04-04 | 2014-07-30 | 京信通信系统（中国）有限公司 | Method and system for management server to perform batch software update on terminal equipment |
| CN103927376A (en) * | 2014-04-25 | 2014-07-16 | 广州壹网网络技术有限公司 | System and method for conducting information spreading through third party social account |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| CN105279204A (en) * | 2014-07-25 | 2016-01-27 | 阿里巴巴集团控股有限公司 | Information push method and apparatus |
| CN105989004A (en) * | 2015-01-27 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Information releasing pretreatment method and device |
| CN105447730A (en) * | 2015-12-25 | 2016-03-30 | 腾讯科技（深圳）有限公司 | Target user orientation method and device |
| CN105550903A (en) * | 2015-12-25 | 2016-05-04 | 腾讯科技（深圳）有限公司 | Target user determination method and apparatus |
| CN107123057A (en) * | 2017-03-22 | 2017-09-01 | 阿里巴巴集团控股有限公司 | User recommends method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107590691A (en) | 2018-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590691B (en) | Information publishing method and device, storage medium and terminal | |
| CN103914468B (en) | A kind of method and apparatus of impression information search | |
| TWI512508B (en) | Recommended methods and systems for recommending information | |
| US10025807B2 (en) | Dynamic data acquisition method and system | |
| US10262339B2 (en) | Externality-based advertisement bid and budget allocation adjustment | |
| US20140149418A1 (en) | Method and system for measuring social influence and receptivity of users | |
| TW200925909A (en) | Traffic predictor for network-accessible informaton modules | |
| WO2013060015A1 (en) | Advertisement determination system and method for clustered search results | |
| CN102037464A (en) | Search results with most clicked next objects | |
| JP2014182437A (en) | Advertisement extraction apparatus, advertisement extraction method and advertisement extraction program | |
| CN106445954B (en) | Business object display method and device | |
| CN111210258A (en) | Advertisement putting method and device, electronic equipment and readable storage medium | |
| US20100318427A1 (en) | Enhancing database management by search, personal search, advertising, and databases analysis efficiently using core-set implementations | |
| US20130254014A1 (en) | Automatic Information Placement | |
| CN103795697A (en) | Network medium information release effect simulation method and system | |
| US20130066708A1 (en) | Online advertising system and a method of operating the same | |
| CN108229990B (en) | Advertisement title generation method, device and equipment | |
| US20110016206A1 (en) | Systems and methods for creating user interest profiles | |
| US9292515B1 (en) | Using follow-on search behavior to measure the effectiveness of online video ads | |
| US9159083B1 (en) | Content evaluation based on user's browsing history | |
| US8589234B1 (en) | Companion ad auctions | |
| CN109075987A (en) | Optimize digital assembly analysis system | |
| US10013699B1 (en) | Reverse associate website discovery | |
| US20110184802A1 (en) | Auction format selection using historical data | |
| CN111582901B (en) | Quantification method, device and system for showing link effect and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |