CN111159563B - Method, device, equipment and storage medium for determining user interest point information - Google Patents
Method, device, equipment and storage medium for determining user interest point information Download PDFInfo
- Publication number
- CN111159563B CN111159563B CN201911418383.3A CN201911418383A CN111159563B CN 111159563 B CN111159563 B CN 111159563B CN 201911418383 A CN201911418383 A CN 201911418383A CN 111159563 B CN111159563 B CN 111159563B
- Authority
- CN
- China
- Prior art keywords
- vector
- item
- determining
- information
- target user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000013598 vector Substances 0.000 claims abstract description 264
- 238000012545 processing Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims description 39
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000010365 information processing Effects 0.000 abstract description 5
- 230000006399 behavior Effects 0.000 description 88
- 230000006870 function Effects 0.000 description 7
- 230000009467 reduction Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000000280 densification Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241001632422 Radiola linoides Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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 embodiment of the invention provides a method, a device, equipment and a storage medium for determining user interest point information, wherein the method comprises the following steps: acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item; determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector; and determining each interest point vector as interest point information of the target user. According to the technical scheme, the degree of interest of the user on each seed item is effectively determined on the premise of not increasing the processing time by combining the behavior feedback information of the user on different seed items through information processing, so that the high-accuracy user interest point information is obtained, and further, in the product recommendation based on the high-accuracy user interest point information, the viscosity of the product and the user is effectively improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining user interest point information.
Background
With the rapid development of the internet field, the explosion-type growing information makes it more and more difficult for users to acquire interesting effective contents, so that personalized recommendation for users has become an unobtainable basic technology in the internet field, and plays an increasingly important role in recommending products such as news, short videos, music and the like.
Generally, personalized recommendation for a user often requires determining points of interest of the user according to historical behaviors of the user, so as to effectively recommend products of interest of the user. In the conventional determination of the user interest point information, interest determination is mainly performed based on items browsed or purchased by a user, so that similar items can be searched for and recommended to the user according to the determined interest points.
However, in the conventional determination of the user interest point information, the determination is mainly performed by considering the basic attribute information of the items purchased or browsed by the user, but the interest point determined only according to the characteristic information has a certain deviation from the actual interest preference of the user, and the information recommendation performed based on the user interest point with lower accuracy often has lower recommendation accuracy, so that the viscosity between the product and the user is reduced.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for determining user interest point information, which improve the effective determination of the user interest point information.
In a first aspect, an embodiment of the present invention provides a method for determining information about a user point of interest, including:
acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item;
determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector;
and determining each interest point vector as interest point information of the target user.
In a second aspect, an embodiment of the present invention provides a device for determining information about a point of interest of a user, including:
the basic information determining module is used for obtaining at least one seed item corresponding to a target user and determining a behavior feedback vector of the target user relative to each seed item;
the interest point vector determining module is used for determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector;
And the target information determining module is used for determining each interest point vector as the interest point information of the target user.
In a third aspect, an embodiment of the present invention provides a device for determining user interest point information, including:
one or more processors;
a storage means for storing one or more programs;
the one or more programs are executed by the one or more processors to cause the one or more processors to implement the methods provided by the above-described embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method provided by the above embodiment of the present invention.
The embodiment of the invention provides a method, a device, equipment and a storage medium for determining user interest point information, wherein the method comprises the following steps: acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item; determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector; and determining each interest point vector as interest point information of the target user. According to the technical scheme, the degree of interest of the user on each seed item is effectively determined on the premise of not increasing the processing time by combining the behavior feedback information of the user on different seed items through information processing, so that the high-accuracy user interest point information is obtained, and further, in the product recommendation based on the high-accuracy user interest point information, the viscosity of the product and the user is effectively improved.
Drawings
Fig. 1 is a flowchart of a method for determining user interest point information according to a first embodiment of the present invention;
fig. 2 is a flow chart of a method for determining user interest point information according to a second embodiment of the present invention;
FIG. 3 is a flowchart illustrating an example of user interest point vector determination in a second embodiment of the present invention;
FIG. 4 is a schematic flow chart of candidate item determination and recommendation in a second embodiment of the present invention;
FIG. 5 is a flow chart of determining a recommendation score according to a second alternative embodiment of the present invention;
fig. 6 is a block diagram of a device for determining user interest point information according to a third embodiment of the present invention;
fig. 7 is a schematic hardware structure of a device for determining user interest point information according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following detailed description of the embodiments of the present invention will be given with reference to the accompanying drawings. It should be understood that the described embodiments are merely some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the embodiments of the present invention and features of the embodiments may be combined with each other without conflict, and the embodiments may be referred to and cited with each other.
It should be noted that, the application scenario of the embodiment of the present invention is various information recommendation fields with resource recommendation requirements, and is applicable to recommendation scenarios of resource items such as news, consultation, music, and short video, for example. In the existing recommendation by determining the information of the user interest points, the user interest is often determined by only considering the basic characteristics of the resource items accessed or browsed by the user, so that the determined user interest points are low in accuracy, and the recommendation accuracy of the resource item recommendation is affected.
According to the method for determining the user interest point information, provided by the embodiment of the invention, the basic characteristic information of the resource items accessed by the user is considered, and the behavior feedback vector of the user relative to the resource items is further added, so that the determined user interest point information can reflect the preference degree difference of the user and express the user intention more accurately, and the accuracy of the resource recommendation by adopting the user interest point information is higher.
Example 1
Fig. 1 is a flow chart of a method for determining user interest point information according to an embodiment of the present invention, where the method may be implemented by a device for determining user interest point information, where the device may be implemented by software and/or hardware and may be generally integrated in a device for determining user interest point information, where the device for determining user interest point information is equivalent to an execution carrier device of the method for determining user interest point information, and may specifically be a background server with a data processing function for performing service support.
As shown in fig. 1, a method for determining user interest point information according to an embodiment of the present invention specifically includes the following operations:
s101, obtaining at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item.
In this embodiment, any object (or audience) to be pushed in the information recommendation field with the resource recommendation requirement is taken as the target user in the embodiment of the present invention. The seed item can be understood as a resource item accessed by the target user in any information release platform supporting an information recommendation function. The step may obtain at least one seed entry accessed by the target user.
In addition, the step can also obtain the behavior feedback information generated by performing various operations on the seed entries when the target user accesses each seed entry. For example, the behavior feedback information may be user behavior information such as whether to click, whether to approve, whether to share, whether to comment, whether to collect, and the like. It can be understood that the common information publishing platform generally has a function of acquiring or recording user behavior data, so that the user behavior data can be acquired, for example, the user behavior data can be acquired through page tracking and event tracking at a web page end, the user behavior data can be acquired through a mode of implanting corresponding codes to count key behaviors of a user at a mobile end, the specific mode of acquiring the user behavior data is not limited, and behavior feedback information generated when a target user accesses the seed item can be extracted from the user behavior data.
In this embodiment, the behavior feedback vector may be specifically understood as a vector obtained through behavior feedback information generated when the target user accesses the seed entry, and may be specifically used to characterize the user behavior of the target user with respect to the seed entry. Illustratively, this step may determine the behavioral feedback vector by encoding the behavioral feedback information and by vectorizing the encoded information.
Optionally, the coding information corresponding to the behavior feedback information may be obtained by searching a given behavior feedback coding table, where the behavior feedback coding table includes each behavior feedback information and the corresponding coding information. Alternatively, the coding information corresponding to the behavior feedback information may also be obtained by a one-hot (one-hot) coding method, and may be selected.
S102, determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector.
In this embodiment, the basic feature information may be understood as information for characterizing the basic feature attribute of the seed item itself. Illustratively, taking a seed item as an example of a video, the basic feature information of the video may include: the video item number, the video poster number, the access user tag, the access user attribution and other information of the video. The interest point vector can be understood as a vector which is extracted from the basic characteristic information and the behavior feedback vector corresponding to each seed item and reflects the interest point information of the target user.
In this embodiment, the basic feature information based on the seed entry may be represented in the form of a basic feature vector, and in this step, the basic feature vector representing the basic feature information may be spliced with a behavioral feedback vector of the user with respect to the seed entry, and the spliced vector is used to determine the target user interest point vector.
Illustratively, the interest point vector for the target can be obtained through processing the vector formed after the stitching, specifically, the internal correlation between the basic feature vector and the behavior feedback vector in the vector formed after the stitching can be captured through a self-attention network model, so that an attention matrix output by the attention network model is obtained, and the attention moment matrix characterizes the mutual relation between the attention of the user and the seed item. And finally, summarizing the interest point vectors of all the seed items by the interest points corresponding to the various seed items of the user so as to characterize the interest points of the user by the interest point vectors.
It should be noted that, in this step, at least one interest point vector may be determined, and the number of interest point vectors determined may be specifically related to the number of parameter sets of analysis parameters used in analyzing the attention matrix, where if only one set of analysis parameters is used for analysis, an interest point vector representing the interest point of the user may be obtained, and if multiple sets of analysis parameters are used, an interest point vector having the same number as the number of sets may be obtained. Wherein, each interest point vector obtained in this step can be understood as a representation of the interest point of the user, and only because the vector value in each interest point vector is different, the preference of the represented interest point is different.
Compared with the existing method for determining the interest point information of the target user simply according to the basic characteristic information of the seed item accessed by the target user, the method provided by the embodiment further takes the behavior feedback information generated when the target user accesses the seed item as the basis for determining the interest point information of the target user on the basis of the prior art scheme, so that the determined interest point information of the user is more accurate, and further the accuracy is higher when the corresponding target user is recommended for resources according to the interest point information of the user.
S103, determining each interest point vector as interest point information of the target user.
In this embodiment, all the determined interest point vectors are taken as the interest point information of the target user, and in this embodiment, a plurality of interest point vectors are considered as the interest point information, which is equivalent to obtaining a plurality of interest point preference features of the target user, so that the determined interest point information can be ensured to more comprehensively represent the interest range of the target user.
According to the method for determining the user interest points, provided by the embodiment of the invention, the interest degree of the user on each seed item is effectively determined on the premise of not increasing the processing time by combining the behavior feedback information of the user on different seed items through information processing, so that the user interest point information with high accuracy is obtained, and further, in the product recommendation based on the user interest point information with high accuracy, the viscosity between the product and the user is effectively improved.
Example two
Fig. 2 is a flow chart of a method for determining user interest point information according to a second embodiment of the present invention, where optimization is performed based on the second embodiment, and in this embodiment, the determining of the behavior feedback vector of the target user with respect to each seed entry is further optimized as follows: for each seed item, acquiring all behavior feedback information of the target user relative to the seed item; searching the coding information corresponding to each piece of behavior feedback information, and processing each piece of coding information by adopting a dense vector determination mechanism to obtain a behavior feedback vector with a set dimension.
Meanwhile, at least one interest point vector corresponding to the target user determined according to each attention matrix is further specifically optimized as follows: taking the whole attention moment array as input data, inputting at least one given first fully-connected network model, and obtaining interest point weight vectors and interest point projection matrixes which are correspondingly output by the first fully-connected network models; determining the product vector of the interest point weight vector and the interest point projection matrix in each first fully-connected network, and determining each product vector as the interest point vector corresponding to the target user under each first fully-connected network; wherein, each first full-connection network model is a network model with the same network structure but different full-connection parameters; the total number of the interest point vectors of the target user is the same as the number of the models of the first fully-connected network model.
As shown in fig. 2, a method for determining user interest point information provided in the second embodiment of the present invention specifically includes the following steps:
s201, at least one seed item corresponding to the target user is obtained.
Illustratively, at least one seed entry accessed by the target user may be obtained from the associated data resource wing.
S202, acquiring all behavior feedback information of the target user relative to each seed item according to each seed item.
Illustratively, this step may also obtain all behavioral feedback information generated by the target user when accessing each seed entry from the associated data monitoring platform.
Wherein the behavior feedback information of the target user relative to various sub-items comprises at least one of the following: praise behavior feedback, share behavior feedback, comment behavior feedback and collection behavior feedback.
In this embodiment, the praise action feedback is feedback information of whether the target user performs the praise operation on each seed item; the sharing behavior feedback is feedback information of whether the target user performs sharing operation on each seed item or not; the comment behavior feedback is feedback information of whether the target user comment operation is performed on each seed item or not; and the collection behavior feedback is feedback information of whether the target user performs collection operation on each seed item.
It can be understood that when the target user accesses or browses a seed item, if a praise operation is performed, the target user can be understood to have a certain interest preference on the seed item; if the sharing operation is performed, the target user can be understood to have stronger interest preference on the seed item; if comment operation is performed, whether the target user is interested in the seed item or not can be further obtained through comment content classification, for example, the preference degree of the target user on the seed item is obtained according to whether the comment content given by the target user is good, bad or medium; if a collection operation is performed, it may be understood that the target user desires to revisit or browse the seed item, even with long-term attention, i.e., the target user is very interested in the seed item.
S203, searching the coding information corresponding to each piece of behavior feedback information, and processing each piece of coding information by adopting a dense vector determination mechanism to obtain a behavior feedback vector with a set dimension.
In this embodiment, behavior feedback information generated when the target user accesses the seed entry, for example, whether to approve, forward, and collect the behavior information may be displayed in a coded form, and this embodiment may suggest a coding table of the behavior feedback information in advance, and this step may determine the coding information corresponding to different behavior feedback information by searching the coding table. If the corresponding code of praise in the behavior feedback information can be determined to be 000, and if the corresponding code of collection is 100, etc.
In this embodiment, after the codes of the behavior feedback information are obtained, a dense vector determination mechanism may be used to process each piece of the code information to obtain a behavior feedback vector with a set dimension; wherein the dense vector is understood to be a form of vector in which each dimension element of the vector is represented by a double-precision floating-point array. The dense vector is a vector representation relative to the sparse vector, illustratively, for vector (1.0,0.0,3.0), represented in dense vector form as [1.0,0.0,3.0], and represented in sparse vector form as (3, [0,2], [1.0,3.0 ]), where 3 is the length of the vector, [0,2] is the index value of the vector in the non-0 dimension, two elements representing positions 0,2 are non-zero values, and [1.0,3.0] is the array element value arranged by index; the difference between the two is that the dense vector stores all values, including zero values, while the sparse vector stores index positions and corresponding non-zero values.
It should be noted that, the dense vector is only a vector representation, in this embodiment, after obtaining the encoded information corresponding to the feedback information of each behavior of the target user for the seed entry, the corresponding encoded information is generally in a sparse matrix form, and when the amount of encoded information is large, the order of the corresponding sparse matrix will be high, which will cause a very occupied resource during data processing. In this regard, an effective solution is to perform dimension reduction processing on the entire sparse matrix through an embedding (embedding) layer, so as to achieve densification of the encoded information. The dimension reduction principle of the embedded layer multiplies the sparse matrix with a set mapping matrix, so that dimension reduction and densification of the sparse matrix are realized.
Meanwhile, in this embodiment, the set dimension may be determined according to a set behavior feedback information type, that is, one dimension corresponds to one behavior feedback information, and one behavior feedback information may represent one feature of the behavior fed back by the target user to the seed item.
The following S204 to S207 in this embodiment show a process of determining the interest point vector based on the basic feature information of the seed entry in combination with the behavior feedback vector of the target user.
S204, constructing a basic feature vector according to the basic feature information of each seed item.
In this embodiment, for each seed entry, the process of converting the basic feature information of the seed entry into a basic feature vector may be implemented by a similar method for obtaining a corresponding behavior feedback vector according to the behavior feedback information corresponding to the seed entry, for example, the basic feature information of the seed entry may be encoded first, and then a dense vector determination mechanism may be used to form a dense basic feature vector corresponding to each seed entry.
S205, splicing the basic feature vector and the behavior feedback vector of each seed item to form a feature splicing vector of each seed item.
It can be appreciated that one main purpose of this embodiment is to combine behavior feedback information generated when a target user accesses a seed entry with basic feature information of a corresponding seed entry accessed by the target user to obtain splicing information corresponding to each seed entry, and then extract interest point information such as interest points of the target user on the corresponding seed entry and corresponding preference degree from each splicing information. Illustratively, the element values in the behavior feedback vector may be directly spliced into the basic feature vector in sequence in this step, thereby forming a feature splice vector.
S206, sequentially taking each characteristic splicing vector as input data, inputting a given self-attention network model, and obtaining an attention matrix corresponding to each seed item output.
It can be understood that the self-attention network model is a network model capable of capturing internal correlation of data or features, and in this embodiment, different behavior feedback information generated by the target user on the accessed seed item substantially reflects attention of the target user to different degrees of investment of the accessed seed item, the self-attention network model can be used for processing the feature stitching vector, and the processed output attention moment array can effectively express correlation of basic feature information of one seed item and behavior feedback information of the target user.
Specifically, the feature stitching vector corresponding to each seed item can be respectively input into the self-attention network model as input data, so that after the self-attention network model is processed, an attention matrix corresponding to the output of the network model can be obtained, and the attention moment matrix is used for representing the attention of a user relative to the seed item.
S207, determining at least one interest point vector corresponding to the target user according to each attention matrix.
In this embodiment, the interest point vector may represent the interest points of the target user with respect to all the seed entries, and in this step, the interest point vector may be determined by analyzing the attention matrix corresponding to each seed entry, and the same number of interest point vectors as the number of groups may be obtained according to the number of groups of the set analysis parameters.
Specifically, the present embodiment may consider that one interest point vector corresponds to a summary of interest features of the target user with respect to each seed entry, and the interest features of the target user with respect to each seed entry are actually included in the attention matrix of each seed entry. The step can analyze the attention matrix of the seed item by adopting a full-connection network model capable of carrying out feature extraction and information integration, and can be a network model with a fixed network structure and variable full-connection parameters, so that the step can actually analyze all the attention matrices by adopting a plurality of full-connection network models with different full-connection parameters, and finally obtain an interest point vector of a relative target user from each full-connection network.
Further, fig. 3 shows an example flowchart of determining a user interest point vector in the second embodiment of the present invention, as shown in fig. 3, where the determining, according to each of the attention matrices, at least one interest point vector corresponding to the target user specifically includes the following operations:
s2071, taking the whole attention moment array as input data, inputting at least one given first full-connection network model, and obtaining interest point weight vectors and interest point projection matrixes which are correspondingly output by the first full-connection network models.
The first full-connection network models are network models with the same network structure but different full-connection parameters. In the step, attention matrixes of each seed item are input into each first full-connection network model as a whole, namely, all attention moment matrixes are spliced into a whole attention matrix to be used as input data, wherein each attention moment matrix in the input data of the input full-connection network model corresponds to one seed item, in the processing based on the first full-connection network model, the characteristics of each attention matrix in the input data can be considered to be extracted firstly, so that the characteristics of interest points of a target user relative to the corresponding seed item can be extracted relative to each attention moment matrix, and each interest point characteristic can be represented in a multi-dimensional matrix mode; and then, the weight value occupied by each interest point feature in all the interest point features can be integrally determined, and the multidimensional matrix representing each interest feature can be subjected to dimension reduction processing to obtain a corresponding interest feature vector.
After the input data is processed by the first fully-connected network model, an interest point weight vector and an interest point projection matrix can be finally obtained, wherein the interest point weight vector can be regarded as the set of the determined weight values, the number of the element values contained in the set of the weight values is the same as the total number of the seed entries, and the interest point projection matrix can be regarded as the set of the interest feature vectors, and the number of the line vectors contained in the set of the interest point projection matrix is the same as the total number of the seed entries. The interest point weight matrix and the interest point projection matrix obtained in the step represent the interest point characteristics of the target user relative to all seed items and the weight occupied by each interest point characteristic. In this embodiment, subjectivity of manually setting weights of various seed items according to behavior feedback information of a target user for each seed item can be effectively avoided by obtaining the interest point weight vector.
S2072, determining the product vector of the interest point weight vector and the interest point projection matrix in each first fully connected network, and determining each product vector as the corresponding interest point vector of the target user in each first fully connected network.
By multiplying the interest point weight vectors in the first fully-connected networks with the interest point projection matrix, weighted accumulation of interest point information of the target user reflected by all the seed entries can be realized, and the obtained interest point vectors can fully reflect cross information among interest points of the target user reflected by various seed entries, so that the purpose of accurately predicting the interest point information of the target user is achieved.
It can be appreciated that the total number of interest point vectors possessed by the target user is the same as the number of models of the first fully connected network model. In the implementation of the step S2071 in this embodiment, a plurality of first fully connected network models with the same network structure and different fully connected parameters are considered, and a point-of-interest weight vector and a point-of-interest projection matrix are obtained corresponding to each first fully connected network, and through the operation of this step, the point-of-interest vectors with the same number as the first fully connected network models can be obtained.
S208, determining each interest point vector as interest point information of the target user.
In this embodiment, the point of interest vector may be further understood as point of interest information of the target user commonly represented by each of the seed entries. And the interest point information of the target user formed by the plurality of interest point vectors can be acquired by acquiring the interest point vectors obtained by the plurality of different first fully connected network models.
According to the method for determining the user interest point information, provided by the embodiment of the invention, the interest degree of the user on each seed item is effectively determined on the premise of not increasing the processing time by combining the behavior feedback information of the user on different seed items, so that the user interest point information with high accuracy is obtained, and further, in the product recommendation based on the user interest point information with high accuracy, the viscosity of the product and the user is effectively improved.
As an alternative embodiment of the present invention, the further optimization of this alternative embodiment includes: and determining candidate items from a given item set to be recommended according to the interest point information of the target user, and recommending the candidate items to the target user. This step may specifically be performed after S208 described above in the present embodiment.
It can be appreciated that the essence of the determination of the user interest point information is resource recommendation, and the present embodiment can predict the subsequent behavior of the user through the user interest point information, so as to find the resource of interest to the user.
In this embodiment, the set of items to be recommended may be understood as a set of resource items including all the intention recommendation items provided for the target user, where the intention recommendation items included in the set of items to be recommended may be determined according to specific resource recommendation requirements of the resource recommendation platform. The candidate item may be understood as a resource item selected from the set of items to be recommended that is actually recommended to the target user. Alternatively, the candidate items may be determined by scoring all the intention recommendation items in the set of items to be recommended, and selecting a set number of intention recommendation items as candidate items actually recommended to the target user according to the score.
Further, fig. 4 is a schematic flow chart of candidate item determination and recommendation in the second embodiment of the present invention, as shown in fig. 4, the determining candidate items from a given set of items to be recommended and recommending the candidate items to the target user according to the interest point information of the target user specifically includes the following operations:
s301, determining an item basic feature vector of each item to be recommended in the item set to be recommended.
In this embodiment, the item to be recommended is an intention recommendation item for the target user, which is determined according to a specific resource recommendation requirement of the resource recommendation platform in the set of items to be recommended. The item basic feature vector may be determined according to the basic feature information of the item to be recommended, and the specific acquisition method of the item basic feature vector may refer to the acquisition method of the basic feature vector corresponding to the seed item, which is not described herein.
S302, determining cosine similarity values of the item basic feature vectors relative to all the interest point vectors in the interest point information.
In this embodiment, the cosine similarity value is specifically a cosine value of an included angle between the item basic feature vector and each interest point vector in the interest point information. Cosine similarity uses the cosine value of the included angle of two vectors in the vector space as a measure for the difference between two individuals, and the closer the cosine value is to 1, the closer the included angle is to 0 degree, namely the more similar the two vectors are, also called as cosine similarity.
It can be understood that by determining the cosine similarity value of the basic feature vector of the item relative to each interest point vector in the interest point information, which item to be recommended is closer to the interest point of the user can be known, so that the item to be recommended can be used as an effective basis for recommending resources to the target user, and the accuracy of resource recommendation is improved.
S303, determining a recommendation score corresponding to the item to be recommended according to each cosine similarity value.
It can be appreciated that, after each cosine similarity value, to further improve accuracy of resource recommendation, the cosine similarity value may be further combined with some features of the item to be recommended and the target user, so as to obtain a more accurate recommendation score of the item to be recommended relative to the target user.
Further, fig. 5 is a schematic flow chart of determining a recommendation score in a second alternative embodiment of the present invention, and specifically, as shown in fig. 5, determining, according to each cosine similarity value, a recommendation score corresponding to the item to be recommended includes the following operations:
s3031, determining user basic feature vectors of the target user and additional feature vectors of the items to be recommended.
In this embodiment, to obtain a recommendation score of an item to be recommended relative to a target user, a user basic feature vector corresponding to user basic feature information of the target user and an additional feature vector of the item to be recommended may be first determined.
The user basic feature information may be understood as feature information for characterizing the target user itself, and includes, for example, the sex, age, access account ID, access device location, etc. of the target user. The user basic feature vector can be understood as a vector obtained by performing the reduction and densification processing on the user basic information. The additional feature vector may be understood as a feature attribute or a distinguishing feature attribute unique to each item to be recommended, and the embodiment may be a vector obtained by performing the process of reducing and densifying on feature attribute information unique to the item to be recommended (for example, when the item to be recommended is a video, information such as resolution of the video may be regarded as unique feature attribute information).
S3032, splicing the user basic feature vector, the item basic feature vector and the additional feature vector of the item to be recommended and each cosine similarity value to form an item recommendation feature vector.
In this embodiment, the item basic feature vector may be understood as a feature attribute shared by each item to be recommended, and the present embodiment correlates the user basic feature vector, the item basic feature vector of the item to be recommended, the additional feature vector, and each cosine similarity value and then scores the associated item basic feature vector, the additional feature vector, and each cosine similarity value, so as to jointly serve as an effective basis for recommending resources for the target user, thereby further improving accuracy of resource recommendation.
In this embodiment, for each item to be recommended, the item recommendation feature vector may be understood as sequentially connecting the user basic feature vector, the item basic feature vector and the additional feature vector of the item to be recommended, and each cosine similarity value in turn to obtain the item recommendation feature vector.
S3033, the item recommendation feature vector is used as input data, a given second full-connection network model is input, and the output value of the second full-connection network model is determined to be the recommendation score of the item to be recommended.
In this embodiment, the second fully-connected network model may be specifically configured to perform some form of weighted summation processing on the above-mentioned item physical examination feature vector, so as to obtain a recommendation score of a recommended item relative to the target user for a recommended item recommendation feature vector.
Specifically, the input layer of the second fully-connected network model is equivalent to including the same number of nodes as the element values included in the item recommendation feature vector, meanwhile, the network model may include an implicit layer, the number of nodes included in the implicit layer and the fully-connected parameters of each input node relative to each node in the hidden layer may be predetermined, and finally, the weighted summation processing performed by the second fully-connected network model may output a weighted summation value corresponding to the recommendation score of the item to be recommended relative to the target user.
And the item recommendation weight vector corresponding to the item recommendation feature vector dimension can be given in the second full-connection network model, and the product of the item recommendation feature vector and the item recommendation weight vector is obtained, so that the recommendation score of the corresponding item to be recommended is determined by the value obtained by weighting and summing the user basic feature vector contained in the item recommendation vector, the item basic feature vector and the additional feature vector of the item to be recommended and each cosine similarity value.
It should be noted that, unlike the first fully-connected network model, the second fully-connected network model is used for scoring the item recommendation vectors, and since the rules of scoring the item recommendation vectors by the second fully-connected network model are consistent, only one second fully-connected network model is needed.
S304, determining at least one candidate item according to the recommendation score of each item to be recommended, and recommending each candidate item to the target user.
After determining the recommendation score of each item to be recommended, the candidate items that can be recommended to the target user may be selected according to the recommendation score.
Specifically, the determining at least one candidate item according to the recommendation score of each item to be recommended may further include ranking each item to be recommended from high to low according to the corresponding recommendation score, and taking the items to be recommended that are in the pre-set value after ranking as candidate items; wherein the set value is greater than or equal to 1.
It can be understood that the degree of matching between the corresponding item to be recommended and the interest point information of the target user is reflected by the height of the recommendation score, and the higher the recommendation score is, the more the recommendation score is matched with the interest point of the user; the method has the advantages that the number of the items to be recommended, which are set before the ranking of the recommendation scores, is selected to be used as candidate items to be actually recommended to the target user, so that high accuracy of resource recommendation can be guaranteed, and the requirement of a resource recommendation platform on the number of recommended resource items can be met as much as possible.
The above technical implementation of the present optional embodiment provides specific method steps for recommending resources to a target user according to the point of interest information of the target user, so that the determining method of the user point of interest information provided by the embodiment of the present invention, on the basis of obtaining high-accuracy user point of interest information, determines an entry basic feature vector and an additional feature vector of each entry to be recommended in a set of entries to be recommended, and a user basic feature vector of the target user, and determines cosine similarity values of each entry basic feature vector with respect to each point of interest vector in the point of interest information, thereby, for each entry to be recommended, scoring the entry to be recommended based on the user basic feature vector, the entry basic feature vector and the additional feature vector of the entry to be recommended, and each cosine similarity value, so as to more accurately determine the fit degree of the entry to be recommended with the target user point of interest information. Therefore, the items to be recommended with higher fitting degree are selected to be recommended to the target user as candidate items, and the accuracy of resource recommendation is further improved.
Example III
Fig. 6 is a block diagram of a device for determining user interest point information according to a third embodiment of the present invention, where the device is suitable for determining interest points of a target user, and the device may be implemented by software and/or hardware and may be generally integrated in a device for determining user interest point information, where the device for determining user interest point information is equivalent to an execution carrier device of a method for determining user interest point information, and may specifically be a background server with a data processing function for performing service support. As shown in fig. 6, the apparatus includes: a basic information determination module 31, a point of interest vector determination module 32, and a target information determination module 33.
The basic information determining module 31 is configured to obtain at least one seed entry corresponding to a target user, and determine a behavior feedback vector of the target user with respect to each seed entry;
the interest point vector determining module 32 is configured to determine at least one interest point vector corresponding to the target user according to the basic feature information of each seed entry and the corresponding behavior feedback vector;
the target information determining module 33 is configured to determine each of the interest point vectors as interest point information of the target user.
According to the determining device for the user interest point information, provided by the embodiment of the invention, the interest degree of the user on each seed item is effectively determined on the premise of not increasing the processing time by combining the behavior feedback information of the user on different seed items, so that the high-accuracy user interest point information is obtained, and further, in the product recommendation based on the high-accuracy user interest point information, the viscosity between a product and the user is effectively improved.
Further, the point of interest vector determination module 32 may include:
a basic vector construction unit for constructing a basic feature vector according to basic feature information of each seed item;
The splicing vector determining unit is used for splicing the basic feature vector and the behavior feedback vector of each seed item to form a feature splicing vector of each seed item;
the information processing unit is used for sequentially taking each characteristic splicing vector as input data, inputting a given self-attention network model and obtaining an attention matrix corresponding to each seed item output;
and the vector information determining unit is used for determining at least one interest point vector corresponding to the target user according to each attention matrix.
Further, the vector information determining unit may be specifically configured to input, with each attention moment array as input data, at least one given first fully-connected network model, and obtain a point-of-interest weight vector and a point-of-interest projection matrix that are output correspondingly by each first fully-connected network model; determining the product vector of the interest point weight vector and the interest point projection matrix in each first fully-connected network, and determining each product vector as the interest point vector corresponding to the target user under each first fully-connected network; wherein, each first full-connection network model is a network model with the same network structure but different full-connection parameters; the total number of the interest point vectors of the target user is the same as the number of the models of the first fully-connected network model.
Further, the apparatus may further include an information recommendation module, where the information recommendation module is configured to determine candidate items from a given set of items to be recommended and recommend the candidate items to the target user according to the point of interest information of the target user.
Based on the optimization, the information recommendation module specifically may include:
an item feature determining unit, configured to determine, for each item to be recommended in the set of items to be recommended, an item basic feature vector of the item to be recommended;
the similarity value determining unit is used for determining cosine similarity values of the item basic feature vectors relative to all the interest point vectors in the interest point information;
the recommendation score determining unit is used for determining a recommendation score corresponding to the item to be recommended according to each cosine similarity value;
and the candidate item recommending unit is used for determining at least one candidate item according to the recommending score of each item to be recommended and recommending each candidate item to the target user.
Further, the recommendation score determining unit may specifically be configured to determine a user basic feature vector of the target user and an additional feature vector of the item to be recommended; splicing the user basic feature vector, the item basic feature vector and the additional feature vector of the item to be recommended and each cosine similarity value to form an item recommendation feature vector; and taking the item recommendation feature vector as input data, inputting a given second full-connection network model, and determining an output value of the second full-connection network model as a recommendation score of the item to be recommended.
Further, the candidate item recommending unit may specifically be configured to rank each item to be recommended according to the corresponding recommendation score from high to low, and use the item to be recommended that is in the pre-set value after ranking as the candidate item; wherein the set value is greater than or equal to 1.
Further, the basic information determining module 31 may be specifically configured to obtain, for each seed entry, all behavior feedback information of the target user with respect to the seed entry; searching the coding information corresponding to each piece of behavior feedback information, and processing each piece of coding information by adopting a dense vector determination mechanism to obtain a behavior feedback vector with a set dimension.
Based on the optimization, the behavior feedback information of the target user relative to various sub-items comprises at least one of the following: praise behavior feedback, share behavior feedback, comment behavior feedback and collection behavior feedback.
Example IV
Fig. 7 is a schematic hardware structure of a device for determining user interest point information according to a fourth embodiment of the present invention. As shown in fig. 7, the apparatus for determining the user interest point information may specifically include: a processor 40, a storage device 41, an input device 42 and an output device 43. The number of processors 40 in the device for determining the user point of interest information may be one or more, one processor 40 being exemplified in fig. 7. The number of storage means 41 in the apparatus for determining the user interest point information may be one or more, and one storage means 41 is exemplified in fig. 7. The processor 40, the storage means 41, the input means 42 and the output means 43 of the user point of interest information determination device may be connected by a bus or by other means, in fig. 7 by way of example.
The storage device 41 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and a module, which are corresponding to a program request/module of a method for determining user interest point information and/or an image stitching method according to any embodiment of the present invention (for example, the basic information determining module 31, the interest point vector determining module 32, and the target information determining module 33 in the device for determining user interest point information). The storage device 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating device, at least one application program required for a function; the storage data area may store data created according to the use of the determination device of the user point of interest information, and the like. In addition, the storage 41 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, storage 41 may further include memory remotely located with respect to processor 40, which may be connected to the user's point of interest information determination device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 42 may be used for receiving input numeric or character information and generating key signal inputs related to user settings and function control of a determining device for user point of interest information, and may also be a camera for capturing images and a determining device for capturing sound pick-up user point of interest information for audio in video data. The output means 43 may comprise a device for determining video user interest point information, such as a display screen, and a device for determining audio user interest point information, such as a speaker. The specific composition of the input device 42 and the output device 43 may be set according to the actual situation.
The processor 40 executes various functional applications and data processing of the user point of interest information determination apparatus by running the software programs, requests and modules stored in the storage 41, i.e., implements the above-described user point of interest information determination method.
Specifically, in the embodiment, when the processor 40 executes one or more programs stored in the storage device 41, the following operations are specifically implemented: acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item; determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector; and determining each interest point vector as interest point information of the target user.
The embodiment of the invention also provides a computer readable storage medium, wherein the program in the storage medium is executed by a processor of a determining device for user interest point information, so that the determining device for user interest point information can execute the determining method for user interest point information according to the embodiment of the method. Exemplary, the method for determining the user interest point information includes: acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item; determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector; and determining each interest point vector as interest point information of the target user.
It should be noted that, for the device, the determination device of the user interest point information, and the storage medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and the relevant points refer to the part of the description of the method embodiment.
From the above description of embodiments, it will be clear to a person skilled in the art that the present invention may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, etc., including a plurality of determining devices (which may be robots, personal computers, servers, or network devices, etc.) requesting to enable a user to perform the method for determining user interest point information and/or the image stitching method according to any embodiment of the present invention.
It should be noted that, in the above-mentioned determination device for user interest point information, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (11)
1. A method for determining information of a user interest point, comprising:
acquiring at least one seed item corresponding to a target user, and determining a behavior feedback vector of the target user relative to each seed item;
Determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector;
determining each interest point vector as interest point information of the target user;
the determining the behavior feedback vector of the target user relative to each seed item comprises the following steps:
for each seed item, acquiring all behavior feedback information of the target user relative to the seed item;
searching the coding information corresponding to each piece of behavior feedback information, and processing each piece of coding information by adopting a dense vector determination mechanism to obtain a behavior feedback vector with a set dimension.
2. The method of claim 1, wherein determining at least one point of interest vector corresponding to the target user based on the base characteristic information of each of the seed entries and the corresponding behavioral feedback vector comprises:
constructing a basic feature vector according to the basic feature information of each seed item;
splicing the basic feature vector and the behavior feedback vector of each seed item to form a feature splicing vector of each seed item;
sequentially taking each characteristic splicing vector as input data, inputting a given self-attention network model, and obtaining an attention matrix corresponding to each seed item output;
And determining at least one interest point vector corresponding to the target user according to each attention matrix.
3. The method of claim 2, wherein said determining at least one point of interest vector corresponding to the target user from each of the attention matrices comprises:
taking the whole attention moment array as input data, inputting at least one given first fully-connected network model, and obtaining interest point weight vectors and interest point projection matrixes which are correspondingly output by the first fully-connected network models;
determining the product vector of the interest point weight vector and the interest point projection matrix in each first fully-connected network, and determining each product vector as the interest point vector corresponding to the target user under each first fully-connected network;
wherein, each first full-connection network model is a network model with the same network structure but different full-connection parameters; the total number of the interest point vectors of the target user is the same as the number of the models of the first fully-connected network model.
4. The method as recited in claim 1, further comprising:
and determining candidate items from a given item set to be recommended according to the interest point information of the target user, and recommending the candidate items to the target user.
5. The method of claim 4, wherein determining candidate items from a given set of items to be recommended and recommending to the target user based on the point of interest information of the target user, comprises:
determining an item basic feature vector of each item to be recommended in the item set to be recommended;
determining cosine similarity values of the item basic feature vectors relative to all the interest point vectors in the interest point information;
determining a recommendation score corresponding to the item to be recommended according to each cosine similarity value;
and determining at least one candidate item according to the recommendation score of each item to be recommended, and recommending each candidate item to the target user.
6. The method of claim 5, wherein determining the recommendation score corresponding to the item to be recommended according to each cosine similarity value comprises:
determining a user basic feature vector of the target user and an additional feature vector of the item to be recommended;
splicing the user basic feature vector, the item basic feature vector and the additional feature vector of the item to be recommended and each cosine similarity value to form an item recommendation feature vector;
And taking the item recommendation feature vector as input data, inputting a given second full-connection network model, and determining an output value of the second full-connection network model as a recommendation score of the item to be recommended.
7. The method of claim 5, wherein said determining at least one candidate item based on a recommendation score for each of said items to be recommended comprises:
sorting all the items to be recommended according to the corresponding recommendation scores from high to low, and taking the items to be recommended which are in the preset numerical value after sorting as candidate items;
wherein the set value is greater than or equal to 1.
8. The method of claim 1, wherein the behavioral feedback information of the target user with respect to the various sub-items comprises at least one of: praise behavior feedback, share behavior feedback, comment behavior feedback and collection behavior feedback.
9. A device for determining information of points of interest of a user, comprising:
the basic information determining module is used for obtaining at least one seed item corresponding to a target user and determining a behavior feedback vector of the target user relative to each seed item;
the interest point vector determining module is used for determining at least one interest point vector corresponding to the target user according to the basic characteristic information of each seed item and the corresponding behavior feedback vector;
The target information determining module is used for determining each interest point vector as the interest point information of the target user;
the basic information determining module is specifically used for acquiring all behavior feedback information of the target user relative to each seed item; searching the coding information corresponding to each piece of behavior feedback information, and processing each piece of coding information by adopting a dense vector determination mechanism to obtain a behavior feedback vector with a set dimension.
10. A device for determining user point of interest information, comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs being executed by the one or more processors to cause the one or more processors to implement the method of any of claims 1-8.
11. A computer storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911418383.3A CN111159563B (en) | 2019-12-31 | 2019-12-31 | Method, device, equipment and storage medium for determining user interest point information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911418383.3A CN111159563B (en) | 2019-12-31 | 2019-12-31 | Method, device, equipment and storage medium for determining user interest point information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111159563A CN111159563A (en) | 2020-05-15 |
| CN111159563B true CN111159563B (en) | 2024-02-09 |
Family
ID=70560472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911418383.3A Active CN111159563B (en) | 2019-12-31 | 2019-12-31 | Method, device, equipment and storage medium for determining user interest point information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159563B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112559901B (en) * | 2020-12-11 | 2022-02-08 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device, electronic equipment, storage medium and computer program product |
| CN113407849B (en) * | 2021-07-15 | 2024-06-14 | 百果园技术(新加坡)有限公司 | Coarse ordering method and device |
| CN113626686A (en) * | 2021-07-19 | 2021-11-09 | 上海泛宥信息科技有限公司 | Automatic pushing method and device based on user data analysis and computer equipment |
| CN113704587B (en) * | 2021-08-31 | 2023-06-06 | 中国平安财产保险股份有限公司 | User adhesion analysis method, device, equipment and medium based on stage division |
| CN115190357A (en) * | 2022-07-05 | 2022-10-14 | 三星电子（中国）研发中心 | Video abstract generation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109299327A (en) * | 2018-11-16 | 2019-02-01 | 广州市百果园信息技术有限公司 | Video recommendation method, device, equipment and storage medium |
| CN109783727A (en) * | 2018-12-24 | 2019-05-21 | 东软集团股份有限公司 | Retrieve recommended method, device, computer readable storage medium and electronic equipment |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110162703A (en) * | 2019-05-13 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Content recommendation method, training method, device, equipment and storage medium |
| CN110347776A (en) * | 2019-07-17 | 2019-10-18 | 北京百度网讯科技有限公司 | Interest point name matching process, device, equipment and storage medium |
-
2019
- 2019-12-31 CN CN201911418383.3A patent/CN111159563B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804619A (en) * | 2018-05-31 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Interest preference prediction technique, device, computer equipment and storage medium |
| CN109299327A (en) * | 2018-11-16 | 2019-02-01 | 广州市百果园信息技术有限公司 | Video recommendation method, device, equipment and storage medium |
| CN109783727A (en) * | 2018-12-24 | 2019-05-21 | 东软集团股份有限公司 | Retrieve recommended method, device, computer readable storage medium and electronic equipment |
| CN110162703A (en) * | 2019-05-13 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Content recommendation method, training method, device, equipment and storage medium |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110347776A (en) * | 2019-07-17 | 2019-10-18 | 北京百度网讯科技有限公司 | Interest point name matching process, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111159563A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111159563B (en) | Method, device, equipment and storage medium for determining user interest point information | |
| CN110321422B (en) | Method for training model on line, pushing method, device and equipment | |
| CN109902708B (en) | Recommendation model training method and related device | |
| US10958748B2 (en) | Resource push method and apparatus | |
| AU2009347535B2 (en) | Co-selected image classification | |
| CN109872242B (en) | Information pushing method and device | |
| CN110223186B (en) | User similarity determining method and information recommending method | |
| CN109993627B (en) | Recommendation method, recommendation model training device and storage medium | |
| CA2783446A1 (en) | Personalized tag ranking | |
| CN106951527B (en) | Song recommendation method and device | |
| CN111242310A (en) | Feature validity evaluation method and device, electronic equipment and storage medium | |
| CN113688310B (en) | Content recommendation method, device, equipment and storage medium | |
| CN111858969B (en) | Multimedia data recommendation method, device, computer equipment and storage medium | |
| JP6203304B2 (en) | Information processing apparatus, information processing method, and information processing program | |
| CN104615723B (en) | The determination method and apparatus of query word weighted value | |
| CN113742578A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN113204699B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN109299351B (en) | Content recommendation method and device, electronic equipment and computer readable medium | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN113836390A (en) | Resource recommendation method and device, computer equipment and storage medium | |
| CN110827078A (en) | Information recommendation method, device, equipment and storage medium | |
| CN112487277B (en) | Data distribution method and device, readable storage medium and electronic equipment | |
| CN114741489A (en) | Document retrieval method, document retrieval device, storage medium and electronic equipment | |
| CN114491093A (en) | Multimedia resource recommendation and object representation network generation method and device | |
| KR101663359B1 (en) | Method and apparatus for providing updated news contents |
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 |