CN106339510B - Click estimation method and device based on artificial intelligence - Google Patents
Click estimation method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN106339510B CN106339510B CN201610972619.8A CN201610972619A CN106339510B CN 106339510 B CN106339510 B CN 106339510B CN 201610972619 A CN201610972619 A CN 201610972619A CN 106339510 B CN106339510 B CN 106339510B
- Authority
- CN
- China
- Prior art keywords
- entity
- recommended
- determining
- click
- query statement
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a click prediction method and device based on artificial intelligence, wherein the method comprises the following steps: acquiring attribute information of an entity to be recommended according to a query statement input by a user; performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively, and determining the characteristics of the query statement and the entity to be recommended; and determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset deep neural network model. Therefore, the method can be used for predicting the click rate of the entity to be recommended by fusing the extracted features into the deep neural network model, so that the accuracy of click rate prediction is improved, the recommendation system can accurately provide services for users, the service quality of the recommendation system is improved, and the user experience is improved.
Description
Technical Field
the application relates to the technical field of networks, in particular to a click estimation method and device based on artificial intelligence.
Background
Artificial Intelligence (Artificial Intelligence), abbreviated in english as AI. The method is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence, a field of research that includes robotics, language recognition, image recognition, natural language processing, and expert systems, among others.
Click Through Rate (CTR) prediction is one of the classic problems in big data technology applications. One of the important points of the click through rate forecast is to find the most appropriate advertisement or recommended product to present to the user. Currently, in the field of recommendation of advertisement, finance and the like, a Logical Regression (LR) model is generally used to estimate the click rate of a product to be recommended, and linear weighting and nonlinear operation are performed on a query statement input by a user and an acquired feature value of a recommended entity, so that the click rate of the entity to be recommended can be determined.
however, the click rate of the entity to be recommended is determined by using the LR model, and the click rate accuracy of the entity to be recommended is low due to the limitation of the LR model.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
therefore, the first objective of the present application is to provide a click prediction method based on artificial intelligence, which includes fusing the extracted features into a deep neural network model to predict the click rate of an entity to be recommended, so as to improve the accuracy of click rate prediction, enable a recommendation system to accurately provide services for users, improve the quality of service of the recommendation system, and improve user experience.
The second objective of the present application is to provide a click estimation device based on artificial intelligence.
The third purpose of the application is to provide a click prediction device based on artificial intelligence.
a fourth object of the present application is to propose a non-transitory computer-readable storage medium.
a fifth object of the present application is to propose a computer program product.
in order to achieve the above object, an embodiment of a first aspect of the present application provides a click prediction method based on artificial intelligence, including: acquiring attribute information of an entity to be recommended according to a query statement input by a user; performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively, and determining the characteristics of the query statement and the entity to be recommended; and determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset deep neural network model.
according to the click estimation method based on the artificial intelligence, after the attribute information of the entity to be recommended is obtained according to the query sentence input by the user, word segmentation processing can be respectively carried out on the query sentence and the attribute information of the entity to be recommended, the characteristics of the query sentence and the entity to be recommended are determined, and then the click rate of the entity to be recommended is determined according to the characteristics of the query sentence and the entity to be recommended by using a preset deep neural network model. Therefore, the extracted features are merged into the deep neural network model, the click rate of the entity to be recommended is estimated, the accuracy of estimation of the click rate is improved, the recommendation system can accurately provide services for users, the service quality of the recommendation system is improved, and the user experience is improved.
in order to achieve the above object, a second aspect of the present application provides an artificial intelligence-based click estimation apparatus, including: the acquisition module is used for acquiring attribute information of the entity to be recommended according to the query statement input by the user; the word segmentation module is used for respectively carrying out word segmentation on the attribute information of the query statement and the entity to be recommended and determining the characteristics of the query statement and the entity to be recommended; and the processing module is used for determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by utilizing a preset deep neural network model.
According to the click pre-estimation device based on artificial intelligence, after the attribute information of the entity to be recommended is obtained according to the query sentence input by the user, word segmentation processing can be respectively carried out on the query sentence and the attribute information of the entity to be recommended, the characteristics of the query sentence and the entity to be recommended are determined, and then the click rate of the entity to be recommended is determined according to the characteristics of the query sentence and the entity to be recommended by utilizing a preset deep neural network model. Therefore, the extracted features are merged into the deep neural network model, the click rate of the entity to be recommended is estimated, the accuracy of estimation of the click rate is improved, the recommendation system can accurately provide services for users, the service quality of the recommendation system is improved, and the user experience is improved.
in order to achieve the above object, a third aspect of the present application provides an artificial intelligence based click prediction device, including:
a processor;
A memory for storing processor-executable instructions;
wherein the processor is configured to perform the artificial intelligence based click prediction method as in the first aspect above.
To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium, wherein instructions, when executed by a processor of a mobile terminal, enable the mobile terminal to perform an artificial intelligence based click prediction method as in the first aspect.
To achieve the above object, a fifth aspect of the present application provides a computer program product, wherein when being executed by an instruction processor of the computer program product, the computer program product performs an artificial intelligence based click prediction method as in the first aspect.
Drawings
the foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow diagram of an artificial intelligence based click prediction method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a process of estimating a click rate by using a deep neural network model according to an embodiment of the present disclosure;
Fig. 3 is a schematic diagram of a process of determining a vector corresponding to a query statement according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a process for determining click through rates according to query statements and vectors of entities to be recommended;
FIG. 5 is a flow diagram of an artificial intelligence based click prediction method according to another embodiment of the present application;
FIG. 6 is a schematic diagram of a click tag estimation process provided in the embodiment of the present application;
FIG. 7 is a schematic structural diagram of an artificial intelligence based click prediction device according to an embodiment of the present application;
FIG. 8 is a schematic structural diagram of an artificial intelligence based click estimation device according to another embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The click estimation method and device based on artificial intelligence according to the embodiment of the present application are described below with reference to the accompanying drawings.
FIG. 1 is a flowchart of an artificial intelligence based click prediction method according to an embodiment of the present application.
As shown in fig. 1, the artificial intelligence based click prediction method includes:
Step 101, obtaining attribute information of an entity to be recommended according to a query statement input by a user.
Specifically, an execution main body of the artificial intelligence based click estimation method provided by the embodiment of the invention is an artificial intelligence based click estimation device provided by the application, and the device can be configured in any search and recommendation service system so as to estimate the click rate of an entity to be recommended when a user searches.
The attribute information of the entity to be recommended comprises at least one of the following information: the name of the entity to be recommended, the recommendation reason and the identification of the entity to be recommended. For example, if the query sentence input by the user is "what playful place is near shaxi", the click estimation device determines one of the entities to be recommended as "shanxi xiangshan" by querying the search database, and meanwhile, in the entity library, the unique identifier "sxxs" corresponding to "shanxi xiangshan" and the corresponding recommended utilization "province-level scenic spot" are further included. The attribute information of the entity to be recommended "shanxi xiangshan" corresponding to the query sentence "what playful place is near shanxi", may be "shanxi xiangshan", "sxxs", and "province-level scenic spot of interest".
it can be understood that the more contents are included in the attribute information of the entity to be recommended, that is, the more accurate the representation of the entity to be recommended is, the more accurate the click rate estimation of the entity to be recommended is.
And 102, performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively, and determining the characteristics of the query statement and the entity to be recommended.
in the concrete implementation, in order to make the obtained characteristics of the query sentence and the entity to be recommended as accurate as possible, the click estimation device can adopt various word segmentation modes to perform word segmentation processing on the attribute information of the query sentence and the entity to be recommended. For example, according to different word segmentation granularities, word segmentation processing is performed on the attribute information of the query statement and the entity to be recommended respectively, and word segmentation with different granularities included in the query statement and the entity to be recommended respectively is determined.
For example, for the query sentence "what playful place is near shaan", the result obtained by fine-grained word segmentation (basic word segment) is the | place of | what playful | near shaan | and the result obtained by coarse-grained word segmentation (phrase word segment) is the | what playful place near shaan | near shaan. For a given entity entry, we also perform two granularity word cuts on it, resulting in both: shanxi | xiangshan. Meanwhile, the unique identification id of the entity in the entity library and a recommendation reason of the entity are obtained, namely, provincial-level scenic spot. Therefore, two granularity word cuts for which we can get the reason for the recommendation are: a provincial | scenic | region, and a provincial | scenic | region. Therefore, in the context of search recommendation, the features of the query can be selected to include a query fine-grained word segmentation result and a coarse-grained word segmentation result; the characteristics of the entity include the coarse-and-fine-grained word segmentation result of the entity itself, id, and the coarse-and-fine-grained word segmentation result of the reason for recommendation.
And 103, determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset Deep Neural Network (DNN) model.
specifically, the click estimation device can train a preset deep neural network model by combining a deep neural network for a large number of query sentences and corresponding entities to be recommended, and is used for estimating the click rate of the entities to be recommended according to the characteristics of the query sentences and the entities to be recommended.
In the specific implementation, the click rate of the entity to be recommended is estimated by using the preset deep neural network model, and the estimation can be mainly implemented through the steps shown in fig. 2. Fig. 2 is a schematic flow chart illustrating a process of estimating a click rate by using a deep neural network model according to an embodiment of the present application.
step 201, determining vectors corresponding to the query statement and the entity to be recommended respectively by using a preset mapping relationship between the participles and the vectors according to the participles with different granularities included in the query statement and the entity to be recommended respectively.
Specifically, first, each participle of the query and the entry is mapped to an embedding (embedding) layer in the DNN model in a vector mapping mode, and each participle corresponds to one embedding representation. Wherein, for the same word, the corresponding embedding representation is unique. Then adding the embedding vectors of each participle in the fine-grained participle to obtain an embedding representation of the query in the fine-grained participle segmentation, as shown in fig. 3, fig. 3 is a schematic diagram of a process for determining a vector corresponding to a query statement provided by the embodiment of the present application.
In addition to the vector addition method, an embedding representation of a feature may be obtained by a vector convolution method or the like. For other query and entry features, we also use the same method to obtain embedding representations of different features. For the entity id, we also map each id to a separate embedding, resulting in an embedding representation of the entity id.
it can be understood that after embedding mapping, the vector quantity corresponding to the query and the entry respectively relates to whether the word segmentation granularity types of the query and the entry and the participles corresponding to different word segmentation granularities are the same. For example, if two kinds of particle size word segmentation are respectively adopted for the query and the entry, and the word segmentation structures obtained after the two kinds of particle size word segmentation are different, after the embedding mapping, the number of vectors corresponding to the query is 2, and the word segmentation structures obtained after the entry name and the recommendation reason are the same, then the number of vectors corresponding to the entry is 3, the entry name corresponds to 1 vector, the entry id corresponds to one vector, and the recommendation reason of the entry corresponds to 1 vector.
step 202, utilizing a first preset operation rule to operate the vectors corresponding to the query statement and the entity to be recommended respectively, and determining the click rate of the entity to be recommended.
specifically, after determining the vectors corresponding to the query and the entry, the click estimation device may determine the click rate of the entry through a certain operation.
Generally, in the DNN model, the final embedding vector representation of the query and the entity may be determined by linear transformation and nonlinear transformation, that is, the step 202 is specifically:
Carrying out linear transformation and nonlinear transformation on vectors respectively corresponding to the query statement and the entity to be recommended, and determining new vectors respectively corresponding to the query statement and the entity to be recommended;
And determining the click rate of the entity to be recommended according to the inner products of the new vectors respectively corresponding to the query statement and the entity to be recommended.
for example, FIG. 4 is a schematic diagram illustrating a process of determining a click-through rate according to a query statement and a vector of an entity to be recommended. After acquiring the embedding representations of various features, we add the embedding vectors of all features of the query to acquire a unique embedding representation of the query, and add the embedding vectors of all features of the entry to acquire a unique embedding representation of the entry, as shown in fig. 4. Then after linear transformation and a non-linear transformation, new vector representations of query and entity are obtained. Then we do this by taking the inner product of the two vectors and mapping it to a value between 0 and 1, i.e. the CTR value.
the nonlinear transformation is performed by any nonlinear operation, such as cosine operation, sine operation, tangent operation, and cotangent operation, and the present embodiment is not limited thereto.
the click estimation device can estimate the click rate of each entity to be recommended corresponding to the query statement input by the user in the above manner, so that the user can be recommended according to the click rate of each entity to be recommended.
according to the click estimation method based on the artificial intelligence, after the attribute information of the entity to be recommended is obtained according to the query sentence input by the user, word segmentation processing can be respectively carried out on the query sentence and the attribute information of the entity to be recommended, the characteristics of the query sentence and the entity to be recommended are determined, and then the click rate of the entity to be recommended is determined according to the characteristics of the query sentence and the entity to be recommended by using a preset deep neural network model. Therefore, the extracted features are merged into the deep neural network model, the click rate of the entity to be recommended is estimated, the accuracy of estimation of the click rate is improved, the recommendation system can accurately provide services for users, the service quality of the recommendation system is improved, and the user experience is improved.
Through the analysis, the click pre-estimation device can pre-estimate the click rate of the entity to be recommended by utilizing a preset DNN model according to the query statement and the characteristics of the entity to be recommended. In actual implementation, since the click rate of the entity to be recommended is related to the displayed position, after the click rate of the entity to be recommended is determined, whether the user clicks the recommended entity can be estimated by combining the displayed position of the recommended entity, and the click estimation method based on artificial intelligence provided by the embodiment of the present application is further described by combining fig. 5.
FIG. 5 is a flow chart of a method for artificial intelligence based click prediction in accordance with another embodiment of the present application.
As shown in fig. 5, the artificial intelligence based click prediction method includes the following steps:
step 501, obtaining attribute information of an entity to be recommended according to a query statement input by a user.
step 502, performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively according to different word segmentation granularities, and determining word segmentations with different granularities respectively included in the query statement and the entity to be recommended.
Step 503, determining vectors corresponding to the query statement and the entity to be recommended respectively by using a preset mapping relationship between the participles and the vectors according to the participles with different granularities included in the query statement and the entity to be recommended respectively.
Step 504, performing linear transformation and nonlinear transformation on the vectors corresponding to the query statement and the entity to be recommended respectively, and determining new vectors corresponding to the query statement and the entity to be recommended respectively.
And 505, determining the click rate of the entity to be recommended according to the inner products of the new vectors respectively corresponding to the query statement and the entity to be recommended.
Step 506, determining the display position of the entity to be recommended.
Specifically, the click estimation device may determine a presentation position (entity display position) of the entity to be recommended in a plurality of ways. For example, determining the display position of the entity to be recommended according to the historical behavior log of the user; or determining the display position of the entity to be recommended according to the click rate of the entity to be recommended; or, a random distribution mode is adopted to distribute the display position for the entity to be recommended, and the like.
and 507, determining a click label of the entity to be recommended according to the click rate and the display position of the entity to be recommended.
Specifically, the click estimation device may still use the DNN model to determine the click label of the entity to be recommended according to the click rate and the display position of the entity to be recommended. Namely, step 507 includes:
Determining a correction vector corresponding to the entity to be recommended according to the click rate and the display position of the entity to be recommended;
And calculating the correction vector by using a second preset operation rule to determine a click label corresponding to the entity to be recommended.
the operation manner included in the second preset operation rule may be different from or different from the operation manner included in the first preset operation rule, and this embodiment does not limit this.
for example, fig. 6 is a schematic diagram of a click tag estimation process provided in the embodiment of the present application. As shown in fig. 6, vector representations corresponding to the CTR score and the entity display position are determined through a vector mapping form, then the vectors of the CTR score and the entity display position are connected in series to serve as correction vectors of an entity to be recommended, and then the correction vectors are subjected to linear transformation and nonlinear transformation to determine a click label corresponding to the entity to be recommended.
It should be noted that, the click pre-estimation device may determine the click label corresponding to the entity to be recommended according to the obtained vector value after processing the modified vector of the entity to be recommended through linear transformation and branching linear transformation, for example, if the obtained vector value is finally a value greater than 0.5, the corresponding click label is "easy to click"; if the obtained vector value is a value smaller than 0.2, the corresponding click label is 'click difficult'; if the obtained vector value is a value smaller than 0.5 and larger than 0.2, the corresponding click label is "click probability low", and the like.
according to the click estimation method based on the artificial intelligence, after the attribute information of an entity to be recommended corresponding to a query sentence input by a user is obtained, word segmentation processing is performed on the query sentence and the attribute information of the recommended entity by adopting different word segmentation granularity, word segmentation of different granularities included in the query sentence and the entity to be recommended is determined, vector representation corresponding to the word segmentation of the query sentence and the word segmentation of the entity to be recommended is determined through vector mapping, the click rate of the entity to be recommended is determined through linear transformation and nonlinear transformation, and then whether the entity to be recommended is clicked or not is estimated according to the display position of the entity to be recommended. Therefore, the click rate and the click label of the entity to be recommended are predicted by using the DNN model, the accuracy of the click rate prediction of the entity to be recommended is improved, the service quality of a recommendation system is improved, and the user experience is improved.
in order to realize the embodiment, the application further provides a click estimation device based on artificial intelligence.
FIG. 7 is a schematic structural diagram of an artificial intelligence based click estimation device according to an embodiment of the present application.
As shown in fig. 7, the artificial intelligence based click prediction apparatus includes:
The obtaining module 71 is configured to obtain attribute information of an entity to be recommended according to a query statement input by a user;
The word segmentation module 72 is configured to perform word segmentation processing on the attribute information of the query statement and the entity to be recommended, and determine characteristics of the query statement and the entity to be recommended;
And the processing module 73 is configured to determine, by using a preset deep neural network model, a click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended.
Wherein the attribute information of the entity to be recommended comprises at least one of the following information: the name of the entity to be recommended, the recommendation reason and the identification of the entity to be recommended.
In a possible implementation form of this embodiment, the word segmentation module 72 is specifically configured to:
and according to different word cutting particle sizes, performing word segmentation processing on the attribute information of the query sentence and the entity to be recommended respectively, and determining word segments with different particle sizes, which are respectively included by the query sentence and the entity to be recommended.
Accordingly, the processing module 73 includes:
the determining unit is used for determining vectors corresponding to the query statement and the entity to be recommended respectively according to the participles with different granularities respectively included by the query statement and the entity to be recommended by utilizing a preset mapping relation between the participles and the vectors;
and the operation unit is used for operating the vectors corresponding to the query statement and the entity to be recommended respectively by utilizing a first preset operation rule, and determining the click rate of the entity to be recommended.
in a possible implementation form of this embodiment, the operation unit is specifically configured to:
Carrying out linear transformation and nonlinear transformation on vectors respectively corresponding to the query statement and the entity to be recommended, and determining new vectors respectively corresponding to the query statement and the entity to be recommended;
And determining the click rate of the entity to be recommended according to the inner products of the new vectors respectively corresponding to the query statement and the entity to be recommended.
it should be noted that the above explanation of the embodiment of the click prediction method based on artificial intelligence is also applicable to the click prediction device based on artificial intelligence of this embodiment, and is not repeated here.
According to the click pre-estimation device based on artificial intelligence, after the attribute information of the entity to be recommended is obtained according to the query sentence input by the user, word segmentation processing can be respectively carried out on the query sentence and the attribute information of the entity to be recommended, the characteristics of the query sentence and the entity to be recommended are determined, and then the click rate of the entity to be recommended is determined according to the characteristics of the query sentence and the entity to be recommended by utilizing a preset deep neural network model. Therefore, the extracted features are merged into the deep neural network model, the click rate of the entity to be recommended is estimated, the accuracy of estimation of the click rate is improved, the recommendation system can accurately provide services for users, the service quality of the recommendation system is improved, and the user experience is improved.
FIG. 8 is a schematic structural diagram of an artificial intelligence based click estimation device according to another embodiment of the present application.
As shown in fig. 8, the artificial intelligence based click estimation device further includes, in addition to the device shown in fig. 7:
A first determining module 81, configured to determine a display position of the entity to be recommended;
And the second determining module 82 is configured to determine a click label of the entity to be recommended according to the click rate and the display position of the entity to be recommended.
Specifically, the first determining module 81 is specifically configured to:
and determining the display position of the entity to be recommended according to the historical behavior log of the user.
Correspondingly, the second determining module 82 is specifically configured to:
determining a correction vector corresponding to the entity to be recommended according to the click rate and the display position of the entity to be recommended;
And calculating the correction vector by using a second preset operation rule to determine a click label corresponding to the entity to be recommended.
It should be noted that the above explanation of the embodiment of the click prediction method based on artificial intelligence is also applicable to the click prediction device based on artificial intelligence of this embodiment, and is not repeated here.
According to the click estimation device based on artificial intelligence, after the attribute information of an entity to be recommended corresponding to a query sentence input by a user is obtained, word segmentation processing is performed on the query sentence and the attribute information of the recommended entity by adopting different word segmentation granularity, word segmentation of different granularities included in the query sentence and the entity to be recommended is determined, vector representation corresponding to the word segmentation of the query sentence and the word segmentation of the entity to be recommended is determined through vector mapping, the click rate of the entity to be recommended is determined through linear transformation and nonlinear transformation, and then whether the entity to be recommended is clicked or not is estimated according to the display position of the entity to be recommended. Therefore, the click rate and the click label of the entity to be recommended are predicted by using the DNN model, the accuracy of the click rate prediction of the entity to be recommended is improved, the service quality of a recommendation system is improved, and the user experience is improved.
Based on the foregoing embodiments, another embodiment of the present application provides a click prediction device based on artificial intelligence, including:
A processor;
A memory for storing processor-executable instructions;
Wherein the processor is configured to perform the following operations: acquiring attribute information of an entity to be recommended according to a query statement input by a user;
Performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively, and determining the characteristics of the query statement and the entity to be recommended;
And determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset deep neural network model.
Further, the present application also provides a non-transitory computer-readable storage medium, wherein instructions of the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the artificial intelligence based click prediction method as in the above embodiments.
further, the present application provides a computer program product, wherein when being executed by an instruction processor of the computer program product, the computer program product executes an artificial intelligence based click estimation method as described in the foregoing embodiments.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
it will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
in addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
the storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (12)
1. A click pre-estimation method based on artificial intelligence is characterized by comprising the following steps:
acquiring attribute information of an entity to be recommended according to a query statement input by a user;
performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively, and determining the characteristics of the query statement and the entity to be recommended;
determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset deep neural network model;
determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by using a preset deep neural network model, wherein the determining comprises the following steps:
Determining vectors corresponding to the query statement and the entity to be recommended respectively by utilizing a preset mapping relation between the participles and the vectors according to the participles with different granularities respectively included by the query statement and the entity to be recommended;
calculating vectors corresponding to the query statement and the entity to be recommended respectively by using a first preset operation rule, and determining the click rate of the entity to be recommended;
the method for calculating the vectors corresponding to the query statement and the entity to be recommended respectively by using the first preset operation rule comprises the following steps:
carrying out linear transformation and nonlinear transformation on vectors respectively corresponding to the query statement and the entity to be recommended, and determining new vectors respectively corresponding to the query statement and the entity to be recommended;
and determining the click rate of the entity to be recommended according to the inner products of the new vectors respectively corresponding to the query statement and the entity to be recommended.
2. the method of claim 1, wherein the performing word segmentation processing on the attribute information of the query statement and the entity to be recommended respectively to determine the feature values of the query statement and the entity to be recommended comprises:
And according to different word cutting particle sizes, performing word segmentation processing on the attribute information of the query sentence and the entity to be recommended respectively, and determining word segments with different particle sizes, which are respectively included by the query sentence and the entity to be recommended.
3. the method of claim 1, wherein after determining the click-through rate of the entity to be recommended, further comprising:
Determining the display position of the entity to be recommended;
And determining the click label of the entity to be recommended according to the click rate and the display position of the entity to be recommended.
4. the method of claim 3, wherein the determining the presentation location of the entity to be recommended comprises:
And determining the display position of the entity to be recommended according to the historical behavior log of the user.
5. The method of claim 3, wherein the determining the click label of the entity to be recommended according to the click rate and the presentation position of the entity to be recommended comprises:
Determining a correction vector corresponding to the entity to be recommended according to the click rate and the display position of the entity to be recommended;
Calculating the correction vector by using a second preset calculation rule, and determining a click label corresponding to the entity to be recommended;
the calculating the correction vector by using a second preset calculation rule, and determining the click label corresponding to the entity to be recommended includes:
and performing linear transformation and nonlinear transformation on the correction vector, and determining a click label corresponding to the entity to be recommended.
6. The method according to any of claims 1-5, wherein the attribute information of the entity to be recommended comprises at least one of the following information: the name of the entity to be recommended, the recommendation reason and the identification of the entity to be recommended.
7. the utility model provides a click and predict device based on artificial intelligence which characterized in that includes:
the acquisition module is used for acquiring attribute information of the entity to be recommended according to the query statement input by the user;
The word segmentation module is used for respectively carrying out word segmentation on the attribute information of the query statement and the entity to be recommended and determining the characteristics of the query statement and the entity to be recommended;
the processing module is used for determining the click rate of the entity to be recommended according to the query statement and the characteristics of the entity to be recommended by utilizing a preset deep neural network model;
Wherein the processing module comprises:
The determining unit is used for determining vectors corresponding to the query statement and the entity to be recommended respectively according to the participles with different granularities respectively included by the query statement and the entity to be recommended by utilizing a preset mapping relation between the participles and the vectors;
The operation unit is used for operating the vectors corresponding to the query statement and the entity to be recommended respectively by utilizing a first preset operation rule, and determining the click rate of the entity to be recommended;
Wherein, the arithmetic unit is specifically configured to:
Carrying out linear transformation and nonlinear transformation on vectors respectively corresponding to the query statement and the entity to be recommended, and determining new vectors respectively corresponding to the query statement and the entity to be recommended;
and determining the click rate of the entity to be recommended according to the inner products of the new vectors respectively corresponding to the query statement and the entity to be recommended.
8. The apparatus of claim 7, wherein the word segmentation module is specifically configured to:
And according to different word cutting particle sizes, performing word segmentation processing on the attribute information of the query sentence and the entity to be recommended respectively, and determining word segments with different particle sizes, which are respectively included by the query sentence and the entity to be recommended.
9. The apparatus of claim 7, further comprising:
The first determination module is used for determining the display position of the entity to be recommended;
and the second determining module is used for determining the click label of the entity to be recommended according to the click rate and the display position of the entity to be recommended.
10. the apparatus of claim 9, wherein the first determining module is specifically configured to:
And determining the display position of the entity to be recommended according to the historical behavior log of the user.
11. The apparatus of claim 10, wherein the second determining module is specifically configured to:
determining a correction vector corresponding to the entity to be recommended according to the click rate and the display position of the entity to be recommended;
Calculating the correction vector by using a second preset calculation rule, and determining a click label corresponding to the entity to be recommended;
the calculating the correction vector by using a second preset calculation rule, and determining the click label corresponding to the entity to be recommended includes:
And performing linear transformation and nonlinear transformation on the correction vector, and determining a click label corresponding to the entity to be recommended.
12. The apparatus according to any of claims 7-10, wherein the attribute information of the entity to be recommended includes at least one of the following information: the name of the entity to be recommended, the recommendation reason and the identification of the entity to be recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610972619.8A CN106339510B (en) | 2016-10-28 | 2016-10-28 | Click estimation method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610972619.8A CN106339510B (en) | 2016-10-28 | 2016-10-28 | Click estimation method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106339510A CN106339510A (en) | 2017-01-18 |
| CN106339510B true CN106339510B (en) | 2019-12-06 |
Family
ID=57841712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610972619.8A Active CN106339510B (en) | 2016-10-28 | 2016-10-28 | Click estimation method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106339510B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463704B (en) * | 2017-08-16 | 2021-05-07 | 北京百度网讯科技有限公司 | Search method and device based on artificial intelligence |
| CN108255954A (en) * | 2017-12-20 | 2018-07-06 | 广州优视网络科技有限公司 | Using search method, device, storage medium and terminal |
| CN110415006B (en) * | 2018-04-28 | 2022-03-08 | 阿里巴巴（中国）有限公司 | Advertisement click rate estimation method and device |
| CN108875022B (en) * | 2018-06-20 | 2021-03-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device |
| CN109255070B (en) * | 2018-08-01 | 2022-04-12 | 百度在线网络技术（北京）有限公司 | Recommendation information processing method and device, computer equipment and storage medium |
| CN109359247B (en) * | 2018-12-07 | 2021-07-06 | 广州市百果园信息技术有限公司 | Content pushing method, storage medium and computer equipment |
| CN109784537B (en) * | 2018-12-14 | 2019-12-06 | 北京达佳互联信息技术有限公司 | advertisement click rate estimation method and device, server and storage medium |
| CN109829116B (en) * | 2019-02-14 | 2021-07-30 | 北京达佳互联信息技术有限公司 | Content recommendation method and device, server and computer readable storage medium |
| CN110399979B (en) * | 2019-06-17 | 2022-05-13 | 深圳大学 | Click rate pre-estimation system and method based on field programmable gate array |
| CN110390052B (en) * | 2019-07-25 | 2022-10-28 | 腾讯科技（深圳）有限公司 | Search recommendation method, training method, device and equipment of CTR (China train redundancy report) estimation model |
| CN110909182B (en) * | 2019-11-29 | 2023-05-09 | 北京达佳互联信息技术有限公司 | Multimedia resource searching method, device, computer equipment and storage medium |
| CN111445283B (en) * | 2020-03-25 | 2023-09-01 | 北京百度网讯科技有限公司 | Digital person processing method, device and storage medium based on interaction device |
| CN112559892A (en) * | 2020-08-03 | 2021-03-26 | 广州知弘科技有限公司 | Terminal information recommendation system based on big data |
| CN111967599B (en) * | 2020-08-25 | 2023-07-28 | 百度在线网络技术（北京）有限公司 | Method, apparatus, electronic device and readable storage medium for training model |
| CN113435523B (en) * | 2021-06-29 | 2023-09-26 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and storage medium for predicting content click rate |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425691A (en) * | 2012-05-22 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Search method and search system |
| CN104750713A (en) * | 2013-12-27 | 2015-07-01 | 阿里巴巴集团控股有限公司 | Method and device for sorting search results |
| CN105045906A (en) * | 2015-08-07 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Estimation method and device of click rate of delivery information |
| CN105046515A (en) * | 2015-06-26 | 2015-11-11 | 深圳市腾讯计算机系统有限公司 | Advertisement ordering method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346745B (en) * | 2010-08-02 | 2014-04-02 | 阿里巴巴集团控股有限公司 | Method and device for predicting user behavior number for words |
| CN104572734B (en) * | 2013-10-23 | 2019-04-30 | 腾讯科技（深圳）有限公司 | Method for recommending problem, apparatus and system |
-
2016
- 2016-10-28 CN CN201610972619.8A patent/CN106339510B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425691A (en) * | 2012-05-22 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Search method and search system |
| CN104750713A (en) * | 2013-12-27 | 2015-07-01 | 阿里巴巴集团控股有限公司 | Method and device for sorting search results |
| CN105046515A (en) * | 2015-06-26 | 2015-11-11 | 深圳市腾讯计算机系统有限公司 | Advertisement ordering method and device |
| CN105045906A (en) * | 2015-08-07 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Estimation method and device of click rate of delivery information |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的搜索广告点击率预测方法研究;李思琴;《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》;20160215;第2016年卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106339510A (en) | 2017-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106339510B (en) | Click estimation method and device based on artificial intelligence | |
| CN107330023B (en) | Text content recommendation method and device based on attention points | |
| CN106557563B (en) | Query statement recommendation method and device based on artificial intelligence | |
| CN110674408B (en) | Service platform, and real-time generation method and device of training sample | |
| CN113361578B (en) | Training method and device for image processing model, electronic equipment and storage medium | |
| CN114298417A (en) | Anti-fraud risk assessment method, anti-fraud risk training method, anti-fraud risk assessment device, anti-fraud risk training device and readable storage medium | |
| CN111460290B (en) | Information recommendation method, device, equipment and storage medium | |
| CN110110092B (en) | Knowledge graph construction method and related equipment | |
| CN111105786B (en) | Multi-sampling-rate voice recognition method, device, system and storage medium | |
| CN111104599B (en) | Method and device for outputting information | |
| CN111046188A (en) | User preference degree determining method and device, electronic equipment and readable storage medium | |
| CN111611390B (en) | Data processing method and device | |
| CN111291936B (en) | Product life cycle prediction model generation method and device and electronic equipment | |
| EP3336778A1 (en) | Policy introduced effect prediction apparatus, policy introduced effect prediction program, and policy introduced effect prediction method | |
| CN111782946A (en) | Book friend recommendation method, calculation device and computer storage medium | |
| CN111144109A (en) | Text similarity determination method and device | |
| CN107577660B (en) | Category information identification method and device and server | |
| CN110866122B (en) | Method and device for mapping entity words based on knowledge graph | |
| CN112906896A (en) | Information processing method and device and computing equipment | |
| CN112163132A (en) | Data labeling method and device, storage medium and electronic equipment | |
| CN111489196A (en) | Prediction method and device based on deep learning network, electronic equipment and medium | |
| Liao et al. | Location prediction through activity purpose: integrating temporal and sequential models | |
| CN111125272B (en) | Regional characteristic acquisition method, regional characteristic acquisition device, computer equipment and medium | |
| CN112417260B (en) | Localized recommendation method, device and storage medium | |
| CN114297235A (en) | Risk address identification method and system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |