CN111382346A - Method and system for recommending content - Google Patents
Method and system for recommending content Download PDFInfo
- Publication number
- CN111382346A CN111382346A CN201811621052.5A CN201811621052A CN111382346A CN 111382346 A CN111382346 A CN 111382346A CN 201811621052 A CN201811621052 A CN 201811621052A CN 111382346 A CN111382346 A CN 111382346A
- Authority
- CN
- China
- Prior art keywords
- candidate content
- content
- candidate
- user
- recommended
- 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.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and system for recommending content are provided, the method comprising: generating a prediction sample corresponding to the candidate content aiming at the candidate content; predicting the probability of clicking the candidate content after the candidate content is recommended to the user facing the candidate content according to the prediction sample to serve as the predicted click rate of the candidate content; acquiring optimization index information for measuring the recommended degree of the candidate content value; and determining a recommendation index for recommending the candidate content to the user based on the estimated click through rate together with the optimization index information. By adopting the method and the system for recommending the content according to the exemplary embodiment of the invention, the content can be recommended for the user more accurately, and the method and the system can be helpful for improving the profit of the content provider.
Description
Technical Field
The present invention relates generally to content recommendation and, more particularly, to a method and system for recommending content.
Background
With the development of the internet technology, a large amount of content is generated, and recommending the interested personalized content to the user can help greatly improve the use experience of the user and bring huge benefits to content providers. In general, when recommending a specific content to a user, a content operator may expect to predict the possibility that the specific content is accepted by the user after being recommended, and then perform content recommendation accordingly according to the prediction result. However, the behavior of whether the user last accepted is itself difficult to collect in some cases, and using the click rate as whether the user accepted may result in many inaccurate prediction results.
Disclosure of Invention
An object of exemplary embodiments of the present invention is to provide a method and system for recommending contents to overcome at least one of the disadvantages described above.
According to an aspect of exemplary embodiments of the present invention, there is provided a method for recommending content, including: generating a prediction sample corresponding to the candidate content aiming at the candidate content; predicting the probability of clicking the candidate content after the candidate content is recommended to the user facing the candidate content according to the prediction sample to serve as the predicted click rate of the candidate content; acquiring optimization index information for measuring the recommended degree of the candidate content value; and determining a recommendation index for recommending the candidate content to the user based on the estimated click through rate together with the optimization index information.
Further, the step of generating prediction samples corresponding to the candidate content may comprise: acquiring at least one attribute information corresponding to the candidate content, wherein the at least one attribute information may include attribute information related to the candidate content, a user and/or an environment to which the candidate content is directed; generating a prediction sample corresponding to the candidate content based at least on the acquired at least one attribute information.
Further, the optimization index information may include historical statistical information representing actions of the candidate content after being clicked and/or price information measuring benefits of the candidate content after being recommended to the user.
Further, the historical statistical information may include a power retention rate of the candidate content after being clicked, which is counted within a predetermined time period, wherein the power retention rate may refer to a probability that each user reserves a contact address for the candidate content after clicking the candidate content.
Further, the electricity retention rate may be obtained by: obtaining a power reserve rate of the candidate content from a provider of the candidate content; and/or predicting a power retention rate of the candidate content after being clicked for the candidate content.
Further, the method may further include: normalizing the price information for measuring the profit obtained after the candidate content is recommended to the user, wherein the step of determining the recommendation index for recommending the candidate content to the user based on the estimated click rate and the optimization index information may include: and determining a recommendation index for recommending the candidate content to the user based on the estimated click rate and at least one of the historical statistical information and the normalized price information.
Further, the recommendation index may correspond to a product of the estimated click rate and at least one of the historical statistical information and the normalized price information.
Further, predicting the probability that the candidate content is clicked after being recommended to the user according to the prediction sample as the predicted click rate of the candidate content may include: predicting, by a machine learning model, a probability that the candidate content is clicked after being recommended to the user with respect to the prediction sample as an estimated click rate of the candidate content.
Further, the machine learning model may be trained by: acquiring at least one attribute information corresponding to a real recommended content historically recommended; generating features of training samples corresponding to the real recommended content at least based on the acquired at least one attribute information in a feature processing manner same as that of generating prediction samples; taking the result of whether the real recommended content is clicked or not as a mark of a training sample; and training the machine learning model based on a set of a plurality of training samples.
Further, the method may further include: recommending the candidate content to the user based on the recommendation index by one of: recommending the candidate content with the highest recommendation index in the candidate content set to the user; creating a list of recommended contents, and providing the list for a user, wherein the recommended contents in the list can be candidate contents with recommendation indexes ranked in the top order among the set of candidate contents.
Further, the set of candidate content may include all candidate content or at least a portion of candidate content recalled for a characteristic of the targeted user.
According to an aspect of exemplary embodiments of the present invention, there is provided a system for recommending content, including: a prediction sample generation unit that generates, for candidate content, a prediction sample corresponding to the candidate content; the estimated click rate determining unit is used for predicting the probability that the candidate content is clicked after being recommended to the user facing the candidate content according to the prediction sample to serve as the estimated click rate of the candidate content; an optimization index information acquisition unit that acquires optimization index information for measuring a degree to which the candidate content is worth recommending; and a recommendation index determination unit which determines a recommendation index for recommending the candidate content to the user based on the estimated click rate and the optimization index information.
Further, the prediction sample generation unit may acquire at least one attribute information corresponding to the candidate content, and generate the prediction sample corresponding to the candidate content based on at least the acquired at least one attribute information, wherein the at least one attribute information may include attribute information related to the candidate content, a user and/or an environment to which the candidate content is directed.
Further, the optimization index information may include historical statistical information representing actions of the candidate content after being clicked and/or price information measuring benefits of the candidate content after being recommended to the user.
Further, the historical statistical information may include a power retention rate of the candidate content after being clicked, which is counted within a predetermined time period, wherein the power retention rate may refer to a probability that each user reserves a contact address for the candidate content after clicking the candidate content.
Further, the optimization index information acquisition unit may acquire the electricity retention rate by: obtaining a power reserve rate of the candidate content from a provider of the candidate content; and/or predicting a power retention rate of the candidate content after being clicked for the candidate content.
Further, the recommendation index determining unit may further perform normalization processing on price information for measuring revenue obtained after the candidate content is recommended to the user, and determine a recommendation index for recommending the candidate content to the user based on at least one of the historical statistical information and the price information after the normalization processing and the estimated click rate.
Further, the recommendation index may correspond to a product of the estimated click rate and at least one of the historical statistical information and the normalized price information.
Further, the estimated click rate determination unit may predict, as the estimated click rate of the candidate content, a probability that the candidate content is clicked after being recommended to the user with respect to the prediction sample using a machine learning model.
Further, the system may further comprise a model training unit operable to train the machine learning model by: acquiring at least one attribute information corresponding to a real recommended content historically recommended; generating features of training samples corresponding to the real recommended content at least based on the acquired at least one attribute information in a feature processing manner same as that of generating prediction samples; taking the result of whether the real recommended content is clicked or not as a mark of a training sample; and training the machine learning model based on a set of a plurality of training samples.
Further, the system may further include: a content recommendation unit operable to recommend the candidate content to the user based on the recommendation index by one of: recommending the candidate content with the highest recommendation index in the candidate content set to the user; creating a list of recommended contents, and providing the list for a user, wherein the recommended contents in the list can be candidate contents with recommendation indexes ranked in the top order among the set of candidate contents.
Further, the set of candidate content may include all candidate content or at least a portion of candidate content recalled for a characteristic of the targeted user.
According to another aspect of exemplary embodiments of the present invention, there is provided a system comprising at least one computing device and at least one storage device storing instructions that, when executed by the at least one computing device, cause the at least one computing device to perform any of the above methods.
According to another aspect of exemplary embodiments of the present invention, there is provided a computer-readable storage medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform any of the above methods.
In the method and the system for recommending content according to the exemplary embodiment of the present invention, recommendation can be performed for a user more accurately, and it is also helpful to improve the revenue of a content provider.
Additional aspects and/or advantages of the present general inventive concept will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the general inventive concept.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings which illustrate exemplary embodiments, wherein:
fig. 1 illustrates a flowchart of a method for recommending content according to an exemplary embodiment of the present invention;
FIG. 2 shows a flowchart of the steps of generating prediction samples corresponding to candidate content according to an example embodiment of the present invention;
FIG. 3 shows a flowchart of the steps of training a machine learning model according to an exemplary embodiment of the present invention;
fig. 4 illustrates a block diagram of a system for recommending content according to an exemplary embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. The embodiments are described below in order to explain the present invention by referring to the figures.
Fig. 1 illustrates a flowchart of a method for recommending content according to an exemplary embodiment of the present invention. Here, the method may be performed by a computer program, or may be performed by a system or a computing device dedicated to recommending content, as an example.
Referring to fig. 1, in step S10, a prediction sample corresponding to a candidate content is generated for the candidate content.
Here, the candidate content may refer to content to be recommended by the user, such as music, news, advertisements, videos, information, courses, and the like. The steps of generating prediction samples corresponding to candidate content are described below with reference to fig. 2.
Fig. 2 illustrates a flowchart of the step of generating prediction samples corresponding to candidate contents according to an exemplary embodiment of the present invention.
Referring to fig. 2, in step S101, at least one attribute information corresponding to a candidate content is acquired. Here, the at least one attribute information may include attribute information related to the candidate content, the user and/or the environment to which it is directed.
For example, the attribute information related to the candidate content may include, but is not limited to, at least one of: the ID of the candidate content, the category of the candidate content, the title of the candidate content, the abstract of the candidate content, the keyword of the candidate content, the part of speech of the keyword of the candidate content, and the position where the candidate content is presented to the user.
For example, attribute information relating to a user to which the candidate content is directed may include, but is not limited to, at least one of: the gender of the user, the age of the user, the ID of the user, the set of recommended content clicked by the user, and the set of recommended content publishers clicked by the user.
For example, attribute information relating to an environment may refer to additional feature information relating to the environment in which the candidate content, the user, and/or other parties are located. By way of example, the environment-related attribute information may include, but is not limited to, at least one of: a browser version showing the candidate content, a category of the terminal device showing the candidate content (e.g., desktop, tablet, smartphone), a model of the terminal device, weather, season, recent hot events.
In an example, the candidate content may be a candidate recommended course, which may be presented in association in an article of a blog (blog), in which case, the related information of the blog may include, but is not limited to, at least one of the following: blog ID, blog title, blog content, number of times the blog was clicked, blog publisher information, time of blog publishing candidate content, category of blog, label of blog.
Optionally, at least one attribute information of the candidate content may be periodically or periodically acquired, and may also be acquired at a specific time point or triggered by a specific event. Here, the attribute information of the candidate contents may be obtained in batches, where the attribute information collection is performed for a plurality of candidate contents per batch.
In step S102, a prediction sample corresponding to the candidate content is generated based on at least the acquired at least one attribute information.
For example, the obtained at least one attribute information may be regarded as at least one attribute field of the sample example, and accordingly, the characteristic portion of the prediction sample may be obtained by performing characteristic processing on the at least one attribute field. As an example, other additional information, such as timing statistics, etc., may also be incorporated in the above feature processing.
The characteristic engineering can be carried out in any suitable manner, without the invention being restricted thereto. For example, the feature of the prediction sample can be generated by performing various processes such as operation, combination, discretization, and serialization on the attribute field, and combined operation thereof.
Returning to fig. 1, in step S20, the probability that the candidate content is clicked after being recommended to the user to which the candidate content is facing is predicted according to the prediction sample as the predicted click rate of the candidate content.
Here, exemplary embodiments of the present invention may use any suitable approach to predicting click-through rates, for example, using human rules, data analysis, or machine learning models. By way of example, the estimated click rate of the candidate content may be predicted by tag similarity calculation, statistical methods, and the like.
In an alternative embodiment, the prediction samples may be input to a machine learning model (e.g., logistic regression model, Gradient Boosting Decision Tree (grm) model, neural network model), through which the probability that the candidate content is clicked after being recommended to the corresponding user is predicted.
Here, the machine learning model for predicting the click rate of the candidate content may be a machine learning model that the method executing subject itself has trained in advance, or may be a machine learning model that the subject has trained directly or indirectly acquires from the outside. The steps of training a machine learning model according to an exemplary embodiment of the present invention are described below with reference to fig. 3.
FIG. 3 shows a flowchart of the steps of training a machine learning model according to an exemplary embodiment of the present invention.
Referring to fig. 3, in step S301, at least one attribute information corresponding to a real recommended content that has been historically recommended is acquired.
Here, the acquired at least one attribute information corresponding to the true recommended content is the same as the acquired at least one attribute information corresponding to the candidate content in step S101. In this step, click-through situations after a large amount of real content has historically been recommended to the respective user may be obtained for forming training samples of the machine learning model.
In step S302, the feature of the training sample corresponding to the true recommended content is generated based on at least the acquired at least one attribute information in the same feature processing manner as the feature of the prediction sample is generated.
In step S303, the result of whether the real recommended content is clicked is used as a label of the training sample.
For example, the at least one attribute information corresponding to the real recommended content and the result of whether the real recommended content is clicked may be collected in a random recommendation manner to generate the feature of the training sample and the label of the training sample.
In step S304, a machine learning model is trained based on a set consisting of a plurality of training samples.
Here, any supervised algorithm may be employed to train the model for predicting click-through rate, as the present invention is not limited in this respect.
Optionally, the method for recommending content according to an exemplary embodiment of the present invention may further include: and updating the machine learning model.
For example, the machine learning model may be updated by: recording a real result of whether the candidate content is clicked or not after being recommended to the user facing the candidate content, and forming training samples for model updating based on at least one attribute information corresponding to the candidate content and the real result of whether the candidate content is clicked or not after being recommended to the user facing the candidate content, wherein the training samples can be used for retraining or incrementally training the machine learning model. By continuously updating the machine learning model, the accuracy of content recommendation can be effectively improved, and more accurate personalized recommendation service is provided for users.
Returning to fig. 1, in step S30, optimization index information for measuring the degree to which the candidate content is worth recommending is acquired. Here, the optimization index information may reflect whether the corresponding candidate content is worth being actually recommended from aspects of a true acceptance rate (e.g., information that the user has clicked but not actually browsed, etc.), a profit scenario, and the like.
Alternatively, the optimization index information may refer to a subsequent index directly related to the candidate content being clicked, for example, the optimization index information may include historical statistical information representing actions of the candidate content being further accepted after being clicked and/or price information measuring the profit obtained after the candidate content is recommended to the user.
In an alternative embodiment, the historical statistical information may include the power retention rate of the candidate content after being clicked, which is counted within a predetermined time period. Here, the power retention rate may refer to a probability that a contact address (e.g., a phone number, a mailbox, an account, etc.) is reserved for the candidate content by each user after clicking the candidate content in history. After the candidate recommended course is clicked, whether the user reserves the contact way or not is related to whether the candidate content is further accepted by the user or not, that is, the higher the electricity-staying rate of the candidate content is, the higher the possibility that the candidate content is further accepted can be shown, and the candidate content is more worthy of being recommended to the user.
As an example, the power reserve rate of the candidate content may be obtained from a provider of the candidate content. For the case that the candidate content is a candidate recommended course, the power retention rate counted for each candidate recommended course in a specific time period may be collected from the provider of the candidate recommended course. However, the present invention is not limited thereto, for example, the power retention rate of the candidate content after being clicked may be predicted for the candidate content, that is, a prediction operation mechanism for the power retention rate may be established, however, in a case where it is difficult to collect corresponding data about a real situation of whether a contact is left, an exemplary embodiment of the present invention may use statistical information or the like to obtain the power retention rate. It is also conceivable to combine the two above-mentioned ways to some extent.
In the case that the candidate content is the candidate recommended course, the electricity-reserving rate and the course price of the candidate recommended course are two key factors related to whether the candidate recommended course is worth recommending or not, so that the electricity-reserving rate and the course price can be used as optimization index information when the course is recommended to the user, and the purpose of improving the overall course income is achieved.
In step S40, a recommendation index for recommending the candidate content to the user is determined based on the estimated click rate of the candidate content together with the optimization index information.
Here, the estimated click rate and the optimization index information can be considered at the same time to determine the size of the recommendation index, and here, the degree and the mode of the estimated click rate and the optimization index information influencing the recommendation index can be set according to needs.
Optionally, the method for recommending content according to an exemplary embodiment of the present invention may further include: and carrying out normalization processing on the price information of the income obtained after the candidate content is recommended to the user.
For example, the price information can be z-score normalized, then normalized to between (0-1) using min-max, enabling it to be computed in the same space. However, the present invention is not limited thereto, and the min-max normalization process or the z-score normalization process may be used alone to normalize the price information. Besides, other normalization processing methods can be adopted in the field to normalize the price information.
In this case, a recommendation index for recommending the candidate content to the user may be determined based on the estimated click rate of the candidate content and at least one of historical statistical information and normalized price information representing an action of the candidate content being further accepted after being clicked.
As an example, the recommendation index may correspond to a product of the estimated click-through rate and at least one of historical statistical information and normalized price information.
For example, taking the example that the optimization index information includes the power reserve rate and the price information, the recommendation index may be determined by the following formula:
δi＝μi×ηi×τi(1)
in the formula (1), i represents the ith candidate content, δiA recommendation index, μ, representing the recommendation of the ith candidate content to the useriIndicating the estimated click rate of the ith candidate content (which may be the output of the model directly or a power of a, where a may be an integer between 0 and 10, for example), ηiIndicating the counted ith candidate content within a predetermined time period after being clickedSpecific power, τiAnd price information representing the profit obtained after the normalized candidate content is recommended to the user. Here, 1 ≦ i ≦ n, n being the number of candidate contents. Here, as an example, the set of candidate content may include all of the candidate content or at least a portion of the candidate content recalled for a characteristic of the targeted user.
Optionally, the method for recommending content according to an exemplary embodiment of the present invention may further include: and recommending the candidate content to the user based on the recommendation index.
In one example, the candidate content with the highest recommendation index among the set of candidate contents may be recommended to the user.
For example, for each candidate content in the set of candidate contents, a recommendation index for recommending each candidate content to the user is determined separately, so as to recommend the candidate content with the highest recommendation index to the user.
In another example, a list of recommended content may be created to provide the user with the created list of recommended content. Here, the recommended content in the list may be a candidate content whose recommendation index is ranked top among the set of candidate contents.
For example, for each candidate content in the set of candidate contents, a recommendation index for recommending each candidate content to the user may be determined respectively, and sorted in descending order according to the recommendation index, and a predetermined number of candidate contents with the recommendation indexes sorted in the top order are selected to be recommended to the user in a list form.
Alternatively, the method for recommending content may be performed on a server of a publisher of the candidate content, for example, on a server of a web page publishing the candidate content, or may also be performed on a server of an application publishing the candidate content. In addition, the method for recommending the content may be executed on a third-party server to obtain a recommendation index for recommending the candidate content to the user, and the publisher of the candidate content recommends the candidate content to the user according to the recommendation index.
According to the method for recommending content of the exemplary embodiment of the present invention, the recommendation index is determined in combination with optimization index information such as the power retention rate and/or price information of the candidate content on the basis of predicting the estimated click rate of the candidate content, so that the recommended candidate content is more worthy of being recommended, for example, the candidate content is more likely to be finally accepted/purchased by the user or the profitability is higher, which may bring greater revenue to the provider of the candidate content.
Fig. 4 illustrates a block diagram of a system for recommending content according to an exemplary embodiment of the present invention. Here, as an example, the method shown in FIG. 1 may be performed by the system shown in FIG. 4.
As shown in fig. 4, a system for recommending content according to an exemplary embodiment of the present invention includes: the system comprises a prediction sample generation unit 10, an estimated click rate determination unit 20, an optimization index information acquisition unit 30 and a recommendation index determination unit 40.
Specifically, the prediction sample generation unit 10 generates, for candidate contents, a prediction sample corresponding to the candidate contents.
The prediction sample generation unit 10 may acquire at least one attribute information corresponding to the candidate content and generate a prediction sample corresponding to the candidate content based on at least the acquired at least one attribute information. Here, the at least one attribute information may include attribute information related to the candidate content, the user and/or the environment to which it is directed.
The estimated click rate determining unit 20 predicts, as an estimated click rate of the candidate content, a probability that the candidate content is clicked after being recommended to the user to which it is directed, based on the prediction sample.
In an alternative embodiment, the predicted click rate determining unit 20 may predict, as the predicted click rate of the candidate content, the probability that the candidate content is clicked after being recommended to the user with respect to the prediction sample by using a machine learning model.
Here, the machine learning model for predicting the click rate of the candidate content may be a machine learning model trained in advance by the recommendation system itself, or may be obtained from the outside directly or indirectly by the recommendation system.
In case of training the machine learning model, the system for recommending content according to an exemplary embodiment of the present invention may further include a model training unit (not shown in the drawings) for training the machine learning model.
For example, the model training unit may train the machine learning module by: the method comprises the steps of obtaining at least one piece of attribute information corresponding to real recommended content recommended historically, generating characteristics of training samples corresponding to the real recommended content at least based on the obtained at least one piece of attribute information according to the same characteristic processing mode as characteristics of generated prediction samples, using a result of whether the real recommended content is clicked as a mark of the training samples, and training a machine learning model based on a set consisting of a plurality of training samples.
Optionally, the system for recommending content according to an exemplary embodiment of the present invention may further include: and the model updating unit is used for updating the machine learning model.
For example, the model updating unit may update the machine learning model by: recording a real result of whether the candidate content is clicked or not after being recommended to the user facing the candidate content, and retraining the machine learning model based on at least one attribute information corresponding to the candidate content and the real result of whether the candidate content is clicked or not after being recommended to the user facing the candidate content.
The optimization index information acquisition unit 30 acquires optimization index information for measuring the degree to which the candidate content is worth recommending.
Alternatively, the optimization index information may refer to a subsequent index directly related to the candidate content being clicked, for example, the optimization index information may include historical statistical information representing actions of the candidate content being further accepted after being clicked and/or price information measuring the profit obtained after the candidate content is recommended to the user.
In an alternative embodiment, the historical statistical information may include the power retention rate of the candidate content after being clicked, which is counted within a predetermined time period. Here, the power retention rate may refer to a probability that the user reserves a contact address for the candidate content after clicking the candidate content.
Alternatively, the optimization index information acquisition unit 30 may acquire the power retention rate of the candidate content from the provider of the candidate content, and/or predict the power retention rate of the candidate content after being clicked for the candidate content.
The recommendation index determining unit 40 determines a recommendation index to recommend the candidate content to the user based on the estimated click rate of the candidate content together with the optimization index information.
Alternatively, the recommendation index determining unit 40 may further perform normalization processing on price information that measures the profit obtained after the candidate content is recommended to the user. In this case, the recommendation index determining unit 40 may determine a recommendation index to recommend the candidate content to the user based on the estimated click rate and at least one of the historical statistical information and the normalized price information.
As an example, the recommendation index may correspond to a product of the estimated click-through rate and at least one of historical statistical information and normalized price information.
Optionally, the system for recommending content according to an exemplary embodiment of the present invention may further include: and a content recommending unit (not shown in the figure) for recommending the candidate content to the user based on the recommendation index.
In one example, the content recommending unit may recommend the candidate content having the highest recommendation index among the set of candidate contents to the user.
In another example, the content recommending unit may create a list of recommended contents, and provide the created list of recommended contents to the user. Here, the recommended content in the list may be a candidate content whose recommendation index is ranked top among the set of candidate contents.
As an example, the set of candidate content may include all of the candidate content or at least a portion of the candidate content recalled for a characteristic of the targeted user.
The units included in the system for recommending content according to an exemplary embodiment of the present invention may be respectively configured as software, hardware, firmware, or any combination thereof that performs a specific function. These means may correspond, for example, to a dedicated integrated circuit, to pure software code, or to a module combining software and hardware. Further, one or more functions implemented by these apparatuses may also be collectively performed by components in a physical entity device (e.g., a processor, a client, a server, or the like).
A computing device for recommending content is also presented in an exemplary embodiment of the present invention. The computing devices may be deployed in servers or clients, as well as on node devices in a distributed network environment. Further, the computing device may be a PC computer, tablet device, personal digital assistant, smart phone, web application, or other device capable of executing the set of instructions described above.
The computing device need not be a single computing device, but can be any device or collection of circuits capable of executing the instructions (or sets of instructions) described above, individually or in combination. The computing device may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with local or remote (e.g., via wireless transmission).
In the computing device, the processor may include a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processors may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, and the like.
Some of the operations described in the method for recommending contents according to the exemplary embodiment of the present invention may be implemented by software, some of the operations may be implemented by hardware, and further, the operations may be implemented by a combination of hardware and software.
The processor may execute instructions or code stored in one of the memory components, which may also store data. Instructions and data may also be transmitted and received over a network via a network interface device, which may employ any known transmission protocol.
The memory component may be integral to the processor, e.g., having RAM or flash memory disposed within an integrated circuit microprocessor or the like. Further, the storage component may comprise a stand-alone device, such as an external disk drive, storage array, or any other storage device usable by a database system. The storage component and the processor may be operatively coupled or may communicate with each other, such as through an I/O port, a network connection, etc., so that the processor can read files stored in the storage component.
Further, the computing device may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the computing device may be connected to each other via a bus and/or a network.
Operations involved in methods for recommending content according to exemplary embodiments of the present invention may be described as various interconnected or coupled functional blocks or functional diagrams. However, these functional blocks or functional diagrams may be equally integrated into a single logic device or operated on by non-exact boundaries.
For example, as described above, there is provided a system comprising at least one computing device and at least one storage device storing instructions that, when executed by the at least one computing device, cause the at least one computing device to perform the steps of: generating a prediction sample corresponding to the candidate content aiming at the candidate content; predicting the probability of clicking the candidate content after the candidate content is recommended to the user facing the candidate content according to the prediction sample to serve as the predicted click rate of the candidate content; acquiring optimization index information for measuring the recommended degree of the candidate content value; and determining a recommendation index for recommending the candidate content to the user based on the estimated click through rate together with the optimization index information.
That is, the method for recommending content shown in fig. 1 may be performed by the computing device described above. Since the method for recommending contents has been described in detail in fig. 1 to 3, the contents of this part of the present invention will not be described again.
Alternatively, the above-described system and computing device for recommending content may be integrated in a server of a publisher of the candidate content, for example, may be integrated in a server of a web page publishing the candidate content, or may also be integrated in a server of an application publishing the candidate content. In addition, the recommendation method can also be integrated in a third-party server to obtain a recommendation index for recommending the candidate content to the user, and then the publisher of the candidate content recommends the candidate content to the user according to the recommendation index.
It is to be understood that the method for recommending content according to an exemplary embodiment of the present invention may be implemented by a program recorded on a computer-readable medium, for example, according to an exemplary embodiment of the present invention, there may be provided a computer-readable medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform the following method: generating a prediction sample corresponding to the candidate content aiming at the candidate content; predicting the probability of clicking the candidate content after the candidate content is recommended to the user facing the candidate content according to the prediction sample to serve as the predicted click rate of the candidate content; acquiring optimization index information for measuring the recommended degree of the candidate content value; and determining a recommendation index for recommending the candidate content to the user based on the estimated click through rate together with the optimization index information.
The computer program in the computer-readable medium may be executed in an environment deployed in a computer device such as a client, a host, a proxy device, a server, and the like, and it should be noted that the computer program may also be used to perform additional steps other than the above steps or perform more specific processing when the above steps are performed, and the contents of the additional steps and the further processing are described with reference to fig. 1 to 3, and will not be described again to avoid repetition.
It should be noted that the system for recommending content according to an exemplary embodiment of the present invention may completely rely on the execution of a computer program to implement the corresponding functions, i.e., each device corresponds to each step in the functional architecture of the computer program, so that the entire system is called by a special software package (e.g., a library of libs) to implement the corresponding functions.
On the other hand, the respective units included in the system for recommending content according to an exemplary embodiment of the present invention may also be implemented by hardware, software, firmware, middleware, microcode, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the corresponding operations may be stored in a computer-readable medium such as a storage medium, so that a processor may perform the corresponding operations by reading and executing the corresponding program code or code segments.
While exemplary embodiments of the invention have been described above, it should be understood that the above description is illustrative only and not exhaustive, and that the invention is not limited to the exemplary embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. Therefore, the protection scope of the present invention should be subject to the scope of the claims.
Claims (10)
1. A method for recommending content, comprising:
generating a prediction sample corresponding to the candidate content aiming at the candidate content;
predicting the probability of clicking the candidate content after the candidate content is recommended to the user facing the candidate content according to the prediction sample to serve as the predicted click rate of the candidate content;
acquiring optimization index information for measuring the recommended degree of the candidate content value; and
determining a recommendation index to recommend the candidate content to the user based on the estimated click through rate together with the optimization index information.
2. The method of claim 1, wherein generating prediction samples corresponding to the candidate content comprises:
acquiring at least one attribute information corresponding to the candidate content, wherein the at least one attribute information comprises attribute information related to the candidate content, a user and/or an environment to which the candidate content is directed;
generating a prediction sample corresponding to the candidate content based at least on the acquired at least one attribute information.
3. The method of claim 1 or 2, wherein the optimization index information comprises historical statistical information representing actions of the candidate content after being clicked on and/or price information measuring income obtained after the candidate content is recommended to a user.
4. The method of claim 3, wherein the historical statistical information comprises a power retention rate of the candidate content after being clicked, counted over a predetermined period of time, wherein the power retention rate refers to a probability that a contact address is reserved for the candidate content by each user after clicking the candidate content.
5. The method of claim 4, wherein the electrical retention is obtained by:
obtaining a power reserve rate of the candidate content from a provider of the candidate content; and/or
And predicting the electricity retention rate of the candidate content after being clicked for the candidate content.
6. The method of claim 3, wherein the method further comprises: normalizing the price information for measuring the income obtained after the candidate content is recommended to the user,
wherein determining a recommendation index to recommend the candidate content to the user based on the estimated click through rate together with the optimization index information comprises:
and determining a recommendation index for recommending the candidate content to the user based on the estimated click rate and at least one of the historical statistical information and the normalized price information.
7. The method of claim 6, wherein the recommendation index corresponds to a product of the estimated click-through rate and at least one of the historical statistical information and normalized price information.
8. A system for recommending content, comprising:
a prediction sample generation unit that generates, for candidate content, a prediction sample corresponding to the candidate content;
the estimated click rate determining unit is used for predicting the probability that the candidate content is clicked after being recommended to the user facing the candidate content according to the prediction sample to serve as the estimated click rate of the candidate content;
an optimization index information acquisition unit that acquires optimization index information for measuring a degree to which the candidate content is worth recommending; and
and the recommendation index determining unit is used for determining a recommendation index for recommending the candidate content to the user based on the estimated click rate and the optimization index information.
9. A system comprising at least one computing device and at least one storage device storing instructions that, when executed by the at least one computing device, cause the at least one computing device to perform the method of any of claims 1 to 7.
10. A computer-readable storage medium storing instructions that, when executed by at least one computing device, cause the at least one computing device to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811621052.5A CN111382346B (en) | 2018-12-28 | 2018-12-28 | Method and system for recommending content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811621052.5A CN111382346B (en) | 2018-12-28 | 2018-12-28 | Method and system for recommending content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111382346A true CN111382346A (en) | 2020-07-07 |
| CN111382346B CN111382346B (en) | 2023-09-01 |
Family
ID=71220452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811621052.5A Active CN111382346B (en) | 2018-12-28 | 2018-12-28 | Method and system for recommending content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382346B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598511A (en) * | 2014-10-23 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Method, device and system for recommending search results |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Data recommendation method and device for application program |
| CN108446382A (en) * | 2018-03-20 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108510313A (en) * | 2018-03-07 | 2018-09-07 | 阿里巴巴集团控股有限公司 | A kind of prediction of information transferring rate, information recommendation method and device |
| CN109063104A (en) * | 2018-07-27 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method for refreshing, device, storage medium and the terminal device of recommendation information |
| CN109086439A (en) * | 2018-08-15 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958030B (en) * | 2017-11-17 | 2021-08-24 | 北京奇虎科技有限公司 | Video cover recommendation model optimization method and device |
| CN109062919B (en) * | 2018-05-31 | 2021-06-15 | 腾讯科技（深圳）有限公司 | Content recommendation method and device based on deep reinforcement learning |
| CN108921300A (en) * | 2018-06-21 | 2018-11-30 | 第四范式（北京）技术有限公司 | The method and apparatus for executing automaton study |
-
2018
- 2018-12-28 CN CN201811621052.5A patent/CN111382346B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598511A (en) * | 2014-10-23 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Method, device and system for recommending search results |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Data recommendation method and device for application program |
| CN108510313A (en) * | 2018-03-07 | 2018-09-07 | 阿里巴巴集团控股有限公司 | A kind of prediction of information transferring rate, information recommendation method and device |
| CN108446382A (en) * | 2018-03-20 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109063104A (en) * | 2018-07-27 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method for refreshing, device, storage medium and the terminal device of recommendation information |
| CN109086439A (en) * | 2018-08-15 | 2018-12-25 | 腾讯科技（深圳）有限公司 | Information recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111382346B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11816272B2 (en) | Identifying touchpoint contribution utilizing a touchpoint attribution attention neural network | |
| Karimi et al. | News recommender systems–Survey and roads ahead | |
| US11048530B1 (en) | Predictive action modeling to streamline user interface | |
| US11551239B2 (en) | Characterizing and modifying user experience of computing environments based on behavior logs | |
| US20190012683A1 (en) | Method for predicting purchase probability based on behavior sequence of user and apparatus for the same | |
| US10360631B1 (en) | Utilizing artificial intelligence to make a prediction about an entity based on user sentiment and transaction history | |
| US11109083B2 (en) | Utilizing a deep generative model with task embedding for personalized targeting of digital content through multiple channels across client devices | |
| US20230401122A1 (en) | Detecting, diagnosing, and alerting anomalies in network applications | |
| WO2021135562A1 (en) | Feature validity evaluation method and apparatus, and electronic device and storage medium | |
| US11288709B2 (en) | Training and utilizing multi-phase learning models to provide digital content to client devices in a real-time digital bidding environment | |
| US11275748B2 (en) | Influence score of a social media domain | |
| US20130268457A1 (en) | System and Method for Extracting Aspect-Based Ratings from Product and Service Reviews | |
| WO2016107354A1 (en) | Method and apparatus for providing user personalised resource message pushing | |
| US11809505B2 (en) | Method for pushing information, electronic device | |
| JP2023533475A (en) | Artificial intelligence for keyword recommendation | |
| CN105069036A (en) | Information recommendation method and apparatus | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| US20210192549A1 (en) | Generating analytics tools using a personalized market share | |
| CN111723260A (en) | Method and device for acquiring recommended content, electronic equipment and readable storage medium | |
| CN113076416A (en) | Information heat evaluation method and device and electronic equipment | |
| CN115935185A (en) | Training method and device for recommendation model | |
| CN116883181B (en) | Financial service pushing method based on user portrait, storage medium and server | |
| CN107644042B (en) | Software program click rate pre-estimation sorting method and server | |
| CN111414455A (en) | Public opinion analysis method, device, electronic equipment and readable storage medium | |
| CN111382346B (en) | Method and system for recommending content |
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 |