CN112395487B - Information recommendation method and device, computer readable storage medium and electronic equipment - Google Patents
Information recommendation method and device, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112395487B CN112395487B CN201910750226.6A CN201910750226A CN112395487B CN 112395487 B CN112395487 B CN 112395487B CN 201910750226 A CN201910750226 A CN 201910750226A CN 112395487 B CN112395487 B CN 112395487B
- Authority
- CN
- China
- Prior art keywords
- vector
- information
- user
- target
- users
- 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 OR CALCULATING; 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
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 disclosure provides an information recommendation method, an information recommendation device, a computer readable storage medium and electronic equipment; relates to the technical field of computers. The information recommendation method comprises the following steps: clustering vectors corresponding to all users according to the vector similarity to obtain a plurality of clusters; determining related users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user; and determining the information to be recommended according to the historical browsing record of the related user so as to recommend the information to be recommended to the target user. The information recommending method can overcome the problem that the efficiency of recommending information to the user is reduced to a certain extent, and improves the efficiency of recommending information to the user by reducing manual operation.
Description
Technical Field
The disclosure relates to the field of computer technology, and in particular, to an information recommendation method, an information recommendation device, a computer readable storage medium and electronic equipment.
Background
In the context of internet big data, it is often necessary to recommend information of interest to a user according to the preference of the user, so as to enhance the use experience of the user.
Typically, the user preference is determined by providing the user with a plurality of interest choices, determining the interest selected by the user as the user preference, and recommending information related to the user preference. However, the manner in which the interest selection item is output to the user to enable the user to determine the interest therefrom requires the user to perform a plurality of manual operations, which may reduce the efficiency of recommending information to the user.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The disclosure aims to provide an information recommending method, an information recommending device, a computer readable storage medium and an electronic device, which can overcome the problem of reduced efficiency of recommending information to a user to a certain extent, and improve the efficiency of recommending information to the user by reducing manual operation.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to a first aspect of the present disclosure, there is provided an information recommendation method, including:
clustering vectors corresponding to all users according to the vector similarity to obtain a plurality of clusters;
Determining related users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user;
And determining the information to be recommended according to the historical browsing record of the related user so as to recommend the information to be recommended to the target user.
In an exemplary embodiment of the present disclosure, the information recommendation method further includes:
determining user models of all users, and extracting label information in each user model;
Calculating a weighted sum of target tag information in the tag information based on the preset weight;
and carrying out normalization processing on the weighted sum to obtain a vector corresponding to the user.
In an exemplary embodiment of the present disclosure, calculating a weighted sum of target tag information in tag information based on preset weights includes:
determining a vector of target tag information in the tag information according to a preset vector mapping relation;
A weighted sum of vectors of the target tag information is calculated based on the preset weights.
In an exemplary embodiment of the present disclosure, clustering vectors corresponding to all users according to vector similarity includes:
determining vector distances between vectors corresponding to all users, wherein the vector distances are used for representing the similarity degree of the vectors;
clustering vectors corresponding to all users according to the vector distance; wherein each user corresponds to a vector.
In an exemplary embodiment of the present disclosure, determining, according to the vector similarity, a relevant user in a cluster to which a target user belongs, includes:
determining vector distances between other vectors in a cluster to which a target vector of a target user belongs and the target vector;
And sorting the vector distance from high to low, and determining a relevant vector from other vectors according to the sorting result to obtain a relevant user corresponding to the relevant vector.
In an exemplary embodiment of the present disclosure, determining information to be recommended according to a history of browsing records of related users includes:
determining vectors corresponding to browsing information in a history browsing record of a relevant user; the vector corresponding to the browsing information and the vectors corresponding to all users are represented by base vectors;
Calculating a vector distance between a vector corresponding to each piece of browsing information and a target vector of a target user;
and determining the information to be recommended from the browsing information according to the vector distance.
In an exemplary embodiment of the present disclosure, determining a vector corresponding to browsing information in a history of browsing records of a related user includes:
Determining browsing information in a history browsing record of each relevant user;
Performing de-duplication processing on all browsing information;
and determining a vector corresponding to each piece of browsing information after de-duplication.
According to a second aspect of the present disclosure, there is provided an information recommendation apparatus including a vector clustering unit, a user determining unit, and an information determining unit, wherein:
The vector clustering unit is used for clustering the vectors corresponding to all the users according to the vector similarity to obtain a plurality of clusters;
the user determining unit is used for determining related users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user;
And the information determining unit is used for determining the information to be recommended according to the history browsing record of the related user so as to recommend the information to be recommended to the target user.
In an exemplary embodiment of the present disclosure, the information recommendation apparatus further includes a user model determining unit, a tag information extracting unit, a weighted sum calculating unit, and a vector normalizing unit, wherein:
a user model determining unit for determining user models of all users;
a tag information extracting unit for extracting tag information in each user model;
a weighted sum calculating unit for calculating a weighted sum of the target tag information in the tag information based on the preset weight;
And the vector normalization unit is used for normalizing the weighted sum to obtain a vector corresponding to the user.
In an exemplary embodiment of the present disclosure, the weighted sum calculating unit calculates a weighted sum of target tag information among tag information based on a preset weight, including:
the weighting and calculating unit determines the vector of the target tag information in the tag information according to a preset vector mapping relation;
the weighted sum calculating unit calculates a weighted sum of vectors of the target tag information based on the preset weights.
In an exemplary embodiment of the present disclosure, the vector clustering unit clusters vectors corresponding to all users according to vector similarity, including:
The vector clustering unit determines vector distances between every two vectors corresponding to all users, wherein the vector distances are used for representing the similarity degree of the vectors;
The vector clustering unit clusters vectors corresponding to all users according to the vector distance; wherein each user corresponds to a vector.
In an exemplary embodiment of the present disclosure, the user determining unit determines, according to the vector similarity, a relevant user among clusters to which the target user belongs, including:
The user determining unit determines the vector distance between other vectors in the cluster to which the target vector of the target user belongs and the target vector;
the user determining unit sorts the vector distances from high to low, and determines the relevant vector from other vectors according to the sorting result, so as to obtain the relevant user corresponding to the relevant vector.
In an exemplary embodiment of the present disclosure, the information determining unit determines information to be recommended according to a history browsing record of a related user, including:
the information determining unit determines vectors corresponding to browsing information in the history browsing records of related users; the vector corresponding to the browsing information and the vectors corresponding to all users are represented by base vectors;
The information determining unit calculates a vector distance between a vector corresponding to each piece of browsing information and a target vector of the target user;
the information determining unit determines information to be recommended from the browsing information according to the vector distance.
In an exemplary embodiment of the present disclosure, the information determining unit determines a vector corresponding to browsing information in a history browsing record of a related user, including:
the information determining unit determines browsing information in the history browsing record of each relevant user;
the information determining unit performs de-duplication processing on all browsing information;
The information determining unit determines a vector corresponding to each piece of browsing information after the de-duplication.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any of the above via execution of the executable instructions.
According to a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.
Exemplary embodiments of the present disclosure may have some or all of the following advantages:
In the information recommendation method provided by an example embodiment of the present disclosure, vectors corresponding to all users may be clustered according to a vector similarity, so as to obtain a plurality of clusters, where each cluster includes similar vectors; further, determining relevant users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user; furthermore, the information to be recommended can be determined according to the history browsing records of the related users so as to recommend the information to be recommended to the target users. According to the scheme, on one hand, the problem of reduced information recommending efficiency to the user can be solved to a certain extent, and the information recommending efficiency to the user is improved by reducing manual operation; on the other hand, the high similarity of users in the clusters can be ensured by clustering the user vector similarity; on the other hand, the related users are found in one cluster only, so that full-quantity searching can be avoided, and the searching efficiency is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 is a schematic diagram of an exemplary system architecture to which an information recommendation method and an information recommendation apparatus of embodiments of the present disclosure may be applied;
FIG. 2 illustrates a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure;
FIG. 3 schematically illustrates a flow diagram of an information recommendation method according to one embodiment of the present disclosure;
FIG. 4 schematically illustrates a flow diagram for determining information to be recommended based on historical browsing records of related users in one embodiment of the present disclosure;
FIG. 5 schematically illustrates a flow chart of an information recommendation method according to another embodiment of the present disclosure;
fig. 6 schematically shows a block diagram of the information recommendation apparatus in one embodiment according to the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
Fig. 1 is a schematic diagram illustrating a system architecture of an exemplary application environment to which an information recommendation method and an information recommendation apparatus according to an embodiment of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include one or more of the terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others. The terminal devices 101, 102, 103 may be various electronic devices with display screens including, but not limited to, desktop computers, portable computers, smart phones, tablet computers, and the like. It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.
The information recommendation method provided by the embodiments of the present disclosure is generally performed by the server 105, and accordingly, the information recommendation apparatus is generally disposed in the server 105. However, it is easily understood by those skilled in the art that the information recommendation method provided in the embodiment of the present disclosure may be performed by the terminal devices 101, 102, 103, and accordingly, the information recommendation apparatus may be provided in the terminal devices 101, 102, 103, which is not particularly limited in the present exemplary embodiment. For example, in an exemplary embodiment, the server 105 may cluster the vectors corresponding to all the users according to the vector similarity to obtain a plurality of clusters, determine the relevant user from the clusters to which the target user belongs according to the vector similarity, determine the information to be recommended according to the history browsing record of the relevant user, and further recommend the information to be recommended to the target user through the terminal device 101, 102 or 103.
Fig. 2 shows a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure.
It should be noted that the computer system 200 of the electronic device shown in fig. 2 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present disclosure.
As shown in fig. 2, the computer system 200 includes a Central Processing Unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 202 or a program loaded from a storage section 208 into a Random Access Memory (RAM) 203. In the RAM 203, various programs and data required for the system operation are also stored. The CPU 201, ROM 202, and RAM 203 are connected to each other through a bus 204. An input/output (I/O) interface 205 is also connected to bus 204.
The following components are connected to the I/O interface 205: an input section 206 including a keyboard, a mouse, and the like; an output portion 207 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage section 208 including a hard disk or the like; and a communication section 209 including a network interface card such as a LAN card, a modem, and the like. The communication section 209 performs communication processing via a network such as the internet. The drive 210 is also connected to the I/O interface 205 as needed. A removable medium 211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 210 as needed, so that a computer program read out therefrom is installed into the storage section 208 as needed.
In particular, according to embodiments of the present disclosure, the processes described below with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 209, and/or installed from the removable medium 211. The computer program, when executed by a Central Processing Unit (CPU) 201, performs the various functions defined in the method and apparatus of the present application. In some embodiments, the computer system 200 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.
It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by one of the electronic devices, cause the electronic device to implement the methods described in the embodiments below. For example, the electronic device may implement the steps shown in fig. 3 to 5, and so on.
The following describes the technical scheme of the embodiments of the present disclosure in detail:
Typically, the user preference is determined by providing the user with a plurality of interest choices, determining the interest selected by the user as the user preference, and recommending information related to the user preference. However, the manner in which the interest selection item is output to the user to enable the user to determine the interest therefrom requires the user to perform a plurality of manual operations, which may reduce the efficiency of recommending information to the user.
In addition, the manner in which the user preferences are determined may also be based on a collaborative filtering approach that shares neighbor clusters. In the method, a server firstly builds a user item scoring matrix, calculates the shared neighbor similarity of users according to the user item scoring matrix, clusters according to the shared neighbor density of each user to form a user cluster C= { C 1,C2,…,Cn }, and calculates a user cluster representative point set CP= { CP 1,CP2,…,CPn }; wherein CP i is a representative point of user cluster C i, i=1, 2,..n; furthermore, the similarity sim (u, CP i) of the target user u and the representative point CP i of the user cluster C i can be calculated, m representative points with higher similarity are selected from the obtained n similarities, and the user clusters where the m representative points are located form a similar cluster set sc= { SC 1,SC2,…,SCm }, where m is less than or equal to n; for each user u j in each similar cluster SC i, calculating the similarity sim (u, u j) of the target user u with the user u j in the similar cluster SC i; further, N users with higher similarity are determined to be nearest neighbor users of the target user u, a nearest neighbor user set N= { V 1,V2,...,VN } of the target user u is obtained, and a predictive score value pred (u, P) of the target user u on the item P is calculated through the nearest neighbor user set N; and determining the higher k items in the obtained predicted score values, and generating a final recommendation list RecList = { P 1,P2,…,Pk }, namely a recommendation list for the target user u, wherein the recommendation list contains information to be recommended.
However, the scoring matrix is a high-order sparse matrix, wherein the missing values are more, and data preprocessing is needed, so that higher storage cost is caused, and the complexity of calculating the similarity between every two is higher, so that the realization difficulty is high and the time consumption is long. In addition, the method for clustering through density cannot guarantee high similarity of members in clusters, similar users are searched in a plurality of clusters, and calculation complexity is high.
Based on one or more of the above problems, the present exemplary embodiment provides an information recommendation method. The information recommendation method may be applied to the server 105 or one or more of the terminal devices 101, 102, 103, which is not particularly limited in the present exemplary embodiment. Referring to fig. 3, the information recommendation method may include the following steps S310 to S330:
Step S310: and clustering vectors corresponding to all users according to the vector similarity to obtain a plurality of clusters.
Step S320: determining related users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user.
Step S330: and determining the information to be recommended according to the historical browsing record of the related user so as to recommend the information to be recommended to the target user.
In the information recommendation method provided by an example embodiment of the present disclosure, vectors corresponding to all users may be clustered according to a vector similarity, so as to obtain a plurality of clusters, where each cluster includes similar vectors; further, determining relevant users in clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user; furthermore, the information to be recommended can be determined according to the history browsing records of the related users so as to recommend the information to be recommended to the target users. According to the scheme, on one hand, the problem of reduced information recommending efficiency to the user can be solved to a certain extent, and the information recommending efficiency to the user is improved by reducing manual operation; on the other hand, the high similarity of users in the clusters can be ensured by clustering the user vector similarity; on the other hand, the related users are found in one cluster only, so that full-quantity searching can be avoided, and the searching efficiency is improved.
Next, the above steps of the present exemplary embodiment will be described in more detail.
In step S310, the vectors corresponding to all the users are clustered according to the vector similarity, so as to obtain a plurality of clusters.
In this example embodiment, the vector similarity is used to represent the similarity degree of two vectors, the method for calculating the vector similarity may be to calculate the euclidean distance between the two vectors, represent the vector similarity by using the euclidean distance, calculate the cosine distance between the two vectors, represent the vector similarity by using the cosine distance, represent the vector similarity by using the calculated Tanimoto coefficient, and represent the vector similarity by using the calculated pearson correlation coefficient.
Wherein, the Euclidean distance is the real distance between two points in m-dimensional space or the natural length of vector, and the Euclidean distance in two-dimensional and three-dimensional space is the real distance between two points; the pearson correlation coefficient is obtained by dividing the covariance by the standard deviation of the two variables; the cosine distance is a measure for measuring the difference between two individuals by taking the cosine value of the included angle of two vectors in the vector space; the Tanimoto coefficient is a generalized Jaccard similarity, and if x and y are both binary vectors, the Tanimoto coefficient is equivalent to the Jaccard Distance (Jaccard Distance), which is an index for measuring the difference between two sets. The specific expression is as follows:
euclidean distance:
pearson correlation coefficient:
Cosine distance:
Tanimoto coefficient:
where i may be a positive integer, x and y are used to represent x and y coordinates.
In this example embodiment, the resulting plurality of clusters may be understood as a plurality of sets, each set containing a plurality of vectors.
In this example embodiment, a clustering method used in clustering vectors corresponding to all users according to the vector similarity may be: the embodiments of the present disclosure are not limited by a K-means clustering method, a mean shift clustering, a density-based clustering method, a Gaussian Mixture Model (GMM) -based maximum Expectation (EM) clustering method, a condensed hierarchical clustering method, or a graph group detection method.
The K-means clustering algorithm (K-means clustering algorithm) is an iterative solution clustering analysis algorithm, which can randomly select K objects as initial clustering centers, then calculate the distance between each object and each seed clustering center, and assign each object to the closest clustering center, and the clustering centers and the objects assigned to the clustering centers represent a cluster. For each sample assigned, the cluster center of the cluster is recalculated based on the existing objects in the cluster. This process will repeat until a certain termination condition is met.
Furthermore, mean shift clustering is a sliding window based algorithm whose idea is to try to find dense areas of data points. This is a centroid-based algorithm, meaning that its goal is to locate the center point of each group/class, by updating the candidate points for the center point to the mean of the points within the sliding window. Further, these candidate windows are filtered in a post-processing stage to eliminate approximate duplicates, forming the final set of centerpoints and their corresponding groups.
In addition, the core idea of the density-based clustering method is to find the points with higher density first, and gradually connect the similar points with high density into one piece, so as to generate various clusters. In addition, the maximum Expectation (EM) clustering method based on Gaussian Mixture Model (GMM) has the main idea that model parameters and hidden variables (categories) are subjected to iterative optimization by using observed values, and finally ideal model parameters and classification results are obtained. In addition, in the aggregation hierarchical clustering method, each sample point is used as a class cluster in the initial stage, so that the size of the original class cluster is equal to the number of the sample points, and the initial class clusters are combined according to a preset criterion until the preset classification number is reached.
In this example embodiment, optionally, the information recommendation method further includes:
determining user models of all users, and extracting label information in each user model;
Calculating a weighted sum of target tag information in the tag information based on the preset weight;
and carrying out normalization processing on the weighted sum to obtain a vector corresponding to the user.
In this example embodiment, the user model is a tagged user model that is abstracted based on information such as user social attributes, lifestyles, and consumption behavior. The core effort to build a user model is to label the user, and the label is a highly refined feature identification through analysis of the user information. The user model may include at least one of gender, age, growing environment, life style, lifestyle, description of personality, consumer emotion, preference, expectations of mind, unmet needs, world view, human view, value view, social characteristics, media contact habits, curiosity and degree of reaction to novelty, level of association with product needs, and contact points of the product and ordering of key elements affecting shopping, and embodiments of the present disclosure are not limited.
In this example embodiment, the tag information in the user model includes target tag information, and the number of tag information in the user model is greater than or equal to the number of target tag information, where the number of target tag information may be one or more, and the embodiment of the disclosure is not limited.
In this example embodiment, the preset weights are preset corresponding weights configured for different target tag information. For example, if the weight configured for the target tag 1 is 3, the weight configured for the target tag 2 is 4, and the weight configured for the target tag 3 is 5 in the preset weights, the weighted sum of the target tag information may be 3×target tag 1+4×target tag 2+5×target tag 3.
In the present exemplary embodiment, normalization is a way to simplify computation, i.e., to transform a dimensionalized expression into a dimensionless expression, making it a scalar. And similarly, the vector corresponding to each user can be determined according to different user models by the alternative implementation mode.
In this exemplary embodiment, the label information in the user model has a sorting order, which is sorted from large to small according to a preset weight. The target tag information is the first N tag information in the user model, and N is a positive integer.
Therefore, by implementing the optional implementation manner, the vector corresponding to the user can be determined through the label information in the user model, so that the efficiency of determining the vector corresponding to each user can be improved, and the efficiency of determining the information to be recommended is further improved.
In this example embodiment, optionally, calculating the weighted sum of the target tag information in the tag information based on the preset weight includes:
determining a vector of target tag information in the tag information according to a preset vector mapping relation;
A weighted sum of vectors of the target tag information is calculated based on the preset weights.
In this example embodiment, the preset vector mapping relationship is used to represent vectors corresponding to different tag information, and the vector of the target tag information can be determined by referring to the preset vector mapping relationship. In addition, the server can determine vectors corresponding to different tag information respectively through word2vec so as to construct a preset vector mapping relation. Where word2vec is the tool for word vector computation.
Therefore, by implementing the optional implementation manner, the vector of the target tag information can be determined by referring to the preset vector mapping relationship, so that the efficiency of determining the information to be recommended is improved.
In this example embodiment, optionally, clustering vectors corresponding to all users according to the vector similarity includes:
determining vector distances between vectors corresponding to all users, wherein the vector distances are used for representing the similarity degree of the vectors;
clustering vectors corresponding to all users according to the vector distance; wherein each user corresponds to a vector.
In this example embodiment, the vector distance may be a euclidean distance or a cosine distance, which is not limited by the embodiment of the present disclosure.
It can be seen that, in implementing this alternative embodiment, the vectors corresponding to the users can be clustered by the vector distance, so that the vectors of the users can be classified, so as to determine the information to be recommended to the target users.
In step S320, determining relevant users in the clusters to which the target users belong according to the vector similarity; wherein the relevant user corresponds to the target user.
In the present exemplary embodiment, the relevant user is a user similar to the target user in the cluster to which the target user belongs.
In this example embodiment, optionally, determining, according to the vector similarity, the relevant user in the cluster to which the target user belongs includes:
determining vector distances between other vectors in a cluster to which a target vector of a target user belongs and the target vector;
And sorting the vector distance from high to low, and determining a relevant vector from other vectors according to the sorting result to obtain a relevant user corresponding to the relevant vector.
In this exemplary embodiment, the relevant users respectively correspond to one relevant vector, the relevant users are the first N vectors most similar to the target user, and N is a positive integer.
Therefore, by implementing the alternative implementation manner, the related users can be determined in the cluster to which the target user belongs, so that compared with global search, the waste of computer resources can be reduced, and the efficiency of determining the related users can be improved.
In step S330, the information to be recommended is determined according to the history browsing record of the relevant user, so as to recommend the information to be recommended to the target user.
In this example embodiment, the relevant user may be understood as a similar user of the target user, and the history of the similar user may be W articles read by each similar user in M days recently, where M and W are positive integers. And combining W articles corresponding to each similar user to form a candidate set, wherein each article corresponds to a vector, determining the vector of the first N articles which are most similar to the vector of the target user from the candidate set, wherein N is a positive integer, and further determining the first N articles as information to be recommended and storing.
In this example implementation, referring to fig. 4, fig. 4 schematically illustrates a flowchart of determining information to be recommended according to a history of a related user in accordance with an embodiment of the present disclosure. As shown in fig. 4, determining information to be recommended according to the history browsing record of the relevant user includes steps S410 to S430, wherein:
Step S410: determining vectors corresponding to browsing information in a history browsing record of a relevant user; the vector corresponding to the browsing information and the vectors corresponding to all users are represented by the base vector.
Step S420: and calculating the vector distance between the vector corresponding to each piece of browsing information and the target vector of the target user.
Step S430: and determining the information to be recommended from the browsing information according to the vector distance.
Further, determining a vector corresponding to browsing information in the history browsing record of the relevant user includes:
Determining browsing information in a history browsing record of each relevant user;
Performing de-duplication processing on all browsing information;
and determining a vector corresponding to each piece of browsing information after de-duplication.
In this example embodiment, the browsing information may be W articles read by the similar user in M days recently.
In this example embodiment, the manner of determining the information to be recommended from the browsing information according to the vector distance is specifically: and sequencing the browsing information according to the sequence of the vector distances from large to small, and determining the browsing information of the front preset bit (such as the front 3 bits) in the sequencing result as the information to be recommended.
Therefore, by implementing the optional implementation manner, the browsing information in the history browsing record can be subjected to repeated processing, and the information to be recommended is determined according to the vector distance, so that the accuracy of the determined information to be recommended can be improved, and the information recommendation effect is improved.
Therefore, by implementing the information recommendation method shown in fig. 3, the problem of reduced efficiency of recommending information to the user can be overcome to a certain extent, and the efficiency of recommending information to the user is improved by reducing manual operation; and, can be through clustering user vector similarity, have guaranteed the high similarity of users in the cluster; in addition, the related users are found in one cluster, so that full search can be avoided, and the search efficiency is improved.
Referring to fig. 5, fig. 5 schematically illustrates a flowchart of an information recommendation method according to another embodiment of the present disclosure, as shown in fig. 5, the information recommendation method of another embodiment includes steps S510 to S590, wherein:
step S510: a user model is obtained.
Step S520: an image of the object is obtained.
Step S530: a basis vector is determined.
Step S540: a user vector is determined from the basis vector.
Step S550: an item vector is determined from the basis vector.
Step S560: clustering vectors according to the vector similarity to obtain a plurality of clusters.
Step S570: and determining the related users in the clusters to which the target users belong.
Step S580: browsing information in the historical browsing records of each relevant user is determined and combined into a candidate information set.
Step S590: and calculating the similarity between the user vector of the target user and the item vector of the candidate information, so as to determine the information to be recommended from the candidate information according to the similarity.
In linear algebra, basis is a basic tool to describe and characterize vector space. The basis of the vector space is a special subset of it, and the elements of the basis are called basis vectors. Any one element in the vector space can be uniquely represented as a linear combination of basis vectors. If the number of elements in the base is limited, the vector space is called a limited-dimensional vector space, and the number of elements is called the dimension of the vector space.
Specifically, the server can represent the user and the article by the same basic vector, calculate similar users of the user through vector distance clustering, perform collaborative filtering recall in the similar users, and calculate vector distances of the user and the article to perform rough sequencing of recall articles. The article may be the article described above, and the vector of the article may be understood as the vector of the article. Further, a high-precision N-dimensional basis vector e is calculated through a word embedding technology, image features of all users are mapped to a vector space taking e as a basis vector in a vector linear combination mode, then the users are clustered into M clusters through distance clustering calculation, K similar users of target users in the clusters and similarity values of the K similar users are calculated for each cluster, historical browsing records of the K users form a set C, the similarity of each element C i in the set C and the target users in the vector space e is calculated, and H articles (namely articles) with highest comprehensive similarity in the set C are recommended to the target users.
Therefore, by implementing the information recommendation method shown in fig. 5, the problem of reduced efficiency of recommending information to the user can be overcome to a certain extent, and the efficiency of recommending information to the user is improved by reducing manual operation; and, can be through clustering user vector similarity, have guaranteed the high similarity of users in the cluster; in addition, the related users are found in one cluster, so that full search can be avoided, and the search efficiency is improved.
Further, in this example embodiment, an information recommendation apparatus is also provided. The information recommending apparatus may be applied to a server or terminal device. Referring to fig. 6, the information recommendation apparatus may include: vector clustering unit 601, user determining unit 602, and information determining unit 603, wherein:
The vector clustering unit 601 is configured to cluster vectors corresponding to all users according to the vector similarity, so as to obtain a plurality of clusters;
A user determining unit 602, configured to determine, according to the vector similarity, a relevant user in a cluster to which the target user belongs; wherein the relevant user corresponds to the target user;
the information determining unit 603 is configured to determine information to be recommended according to a history browsing record of the relevant user, so as to recommend the information to be recommended to the target user.
Therefore, the information recommending device shown in fig. 6 can overcome the problem of reduced efficiency of recommending information to the user to a certain extent, and the efficiency of recommending information to the user is improved by reducing manual operation; and, can be through clustering user vector similarity, have guaranteed the high similarity of users in the cluster; in addition, the related users are found in one cluster, so that full search can be avoided, and the search efficiency is improved.
In an exemplary embodiment of the present disclosure, the information recommendation apparatus further includes a user model determining unit (not shown), a tag information extracting unit (not shown), a weighted sum calculating unit (not shown), and a vector normalizing unit (not shown), wherein:
a user model determining unit for determining user models of all users;
a tag information extracting unit for extracting tag information in each user model;
a weighted sum calculating unit for calculating a weighted sum of the target tag information in the tag information based on the preset weight;
And the vector normalization unit is used for normalizing the weighted sum to obtain a vector corresponding to the user.
Therefore, by implementing the exemplary embodiment, the vector corresponding to the user can be determined through the label information in the user model, so that the efficiency of determining the vector corresponding to each user can be improved, and the efficiency of determining the information to be recommended is further improved.
In an exemplary embodiment of the present disclosure, the weighted sum calculating unit calculates a weighted sum of target tag information among tag information based on a preset weight, including:
the weighting and calculating unit determines the vector of the target tag information in the tag information according to a preset vector mapping relation;
the weighted sum calculating unit calculates a weighted sum of vectors of the target tag information based on the preset weights.
It can be seen that, by implementing the exemplary embodiment, the vector of the target tag information can be determined by referring to the preset vector mapping relationship, so that the efficiency of determining the information to be recommended is improved.
In an exemplary embodiment of the present disclosure, the vector clustering unit clusters vectors corresponding to all users according to vector similarity, including:
The vector clustering unit determines vector distances between every two vectors corresponding to all users, wherein the vector distances are used for representing the similarity degree of the vectors;
The vector clustering unit clusters vectors corresponding to all users according to the vector distance; wherein each user corresponds to a vector.
It can be seen that, when the exemplary embodiment is implemented, the vectors corresponding to the users can be clustered by the vector distance, so that the vectors of the users can be classified, so as to determine the information to be recommended to the target users.
In an exemplary embodiment of the present disclosure, the user determining unit determines, according to the vector similarity, a relevant user among clusters to which the target user belongs, including:
The user determining unit determines the vector distance between other vectors in the cluster to which the target vector of the target user belongs and the target vector;
the user determining unit sorts the vector distances from high to low, and determines the relevant vector from other vectors according to the sorting result, so as to obtain the relevant user corresponding to the relevant vector.
It can be seen that, by implementing the exemplary embodiment, the related user can be determined in the cluster to which the target user belongs, and compared with global search, the waste of computer resources can be reduced, and the efficiency of determining the related user can be improved.
In an exemplary embodiment of the present disclosure, the information determining unit determines information to be recommended according to a history browsing record of a related user, including:
the information determining unit determines vectors corresponding to browsing information in the history browsing records of related users; the vector corresponding to the browsing information and the vectors corresponding to all users are represented by base vectors;
The information determining unit calculates a vector distance between a vector corresponding to each piece of browsing information and a target vector of the target user;
the information determining unit determines information to be recommended from the browsing information according to the vector distance.
Further, the information determining unit determines a vector corresponding to browsing information in the history browsing record of the relevant user, including:
the information determining unit determines browsing information in the history browsing record of each relevant user;
the information determining unit performs de-duplication processing on all browsing information;
The information determining unit determines a vector corresponding to each piece of browsing information after the de-duplication.
Therefore, by implementing the exemplary embodiment, the browsing information in the history browsing record can be subjected to repeated processing, and the information to be recommended is determined according to the vector distance, so that the accuracy of the determined information to be recommended can be improved, and the information recommendation effect is improved.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Since each functional module of the information recommendation device according to the exemplary embodiment of the present disclosure corresponds to a step of the exemplary embodiment of the information recommendation method described above, for details not disclosed in the embodiment of the device of the present disclosure, please refer to the embodiment of the information recommendation method described above in the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (8)
1. An information recommendation method, comprising:
Determining user models of all users, and extracting label information in each user model;
calculating a weighted sum of target tag information in the tag information based on a preset weight, wherein the target tag information is first N tag information in the user model ordered from big to small according to the preset weight, and N is a positive integer;
normalizing the weighted sum to obtain a vector corresponding to the user;
clustering vectors corresponding to all users according to the vector similarity to obtain a plurality of clusters;
Determining related users in clusters to which the target users belong according to the vector similarity; the related users correspond to the target users, the related users are the first N vectors which are most similar to the target users, and N is a positive integer;
Determining vectors corresponding to browsing information in the history browsing records of the related users; the vectors corresponding to the browsing information and the vectors corresponding to all users are represented by the same base vector;
calculating a vector distance between a vector corresponding to each piece of browsing information and a target vector of the target user;
And determining information to be recommended from the browsing information according to the vector distance so as to recommend the information to be recommended to the target user.
2. The method of claim 1, wherein calculating a weighted sum of target tag information in the tag information based on a preset weight comprises:
Determining a vector of target tag information in the tag information according to a preset vector mapping relation;
and calculating the weighted sum of the vectors of the target tag information based on the preset weight.
3. The method of claim 1, wherein clustering vectors corresponding to all users according to vector similarity comprises:
determining vector distances between vectors corresponding to all users, wherein the vector distances are used for representing the similarity degree of the vectors;
Clustering vectors corresponding to all users according to the vector distance; wherein each user corresponds to a vector.
4. The method of claim 1, wherein determining the relevant user from the cluster to which the target user belongs based on the vector similarity comprises:
determining vector distances between other vectors in a cluster to which a target vector of a target user belongs and the target vector;
And sequencing the vector distance from high to low, and determining a relevant vector from the other vectors according to the sequencing result so as to obtain a relevant user corresponding to the relevant vector.
5. The method of claim 1, wherein determining a vector corresponding to browsing information in the historical browsing records of the relevant user comprises:
determining browsing information in the history browsing record of each relevant user;
Performing de-duplication processing on all browsing information;
and determining a vector corresponding to each piece of browsing information after de-duplication.
6. An information recommendation device, characterized by comprising:
a user model determining unit for determining user models of all users;
a tag information extracting unit for extracting tag information in each user model;
The weighting and calculating unit is used for calculating the weighted sum of target tag information in tag information based on preset weights, wherein the target tag information is the first N tag information in the user model which is sequenced from big to small according to the preset weights, and N is a positive integer;
the vector normalization unit is used for carrying out normalization processing on the weighted sum to obtain a vector corresponding to the user;
The vector clustering unit is used for clustering the vectors corresponding to all the users according to the vector similarity to obtain a plurality of clusters;
the user determining unit is used for determining related users in clusters to which the target users belong according to the vector similarity; the related users correspond to the target users, the related users are the first N vectors which are most similar to the target users, and N is a positive integer;
The information determining unit is used for determining vectors corresponding to browsing information in the history browsing records of the related users; the vectors corresponding to the browsing information and the vectors corresponding to all users are represented by the same base vector; calculating a vector distance between a vector corresponding to each piece of browsing information and a target vector of the target user; and determining information to be recommended from the browsing information according to the vector distance so as to recommend the information to be recommended to the target user.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-5.
8. An electronic device, comprising:
A processor; and
A memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-5 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910750226.6A CN112395487B (en) | 2019-08-14 | 2019-08-14 | Information recommendation method and device, computer readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910750226.6A CN112395487B (en) | 2019-08-14 | 2019-08-14 | Information recommendation method and device, computer readable storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112395487A CN112395487A (en) | 2021-02-23 |
| CN112395487B true CN112395487B (en) | 2024-04-26 |
Family
ID=74601403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910750226.6A Active CN112395487B (en) | 2019-08-14 | 2019-08-14 | Information recommendation method and device, computer readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395487B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010794A (en) * | 2021-04-12 | 2021-06-22 | 北京明略软件系统有限公司 | Method and device for information recommendation, electronic equipment and storage medium |
| CN113301442B (en) * | 2021-05-20 | 2022-10-21 | 北京百度网讯科技有限公司 | Method, apparatus, medium and program product for determining live broadcast resources |
| CN113392200A (en) * | 2021-06-18 | 2021-09-14 | 中国工商银行股份有限公司 | Recommendation method and device based on user learning behaviors |
| CN113468419B (en) * | 2021-06-28 | 2025-02-14 | 北京达佳互联信息技术有限公司 | Content recommendation method, device, electronic device and storage medium |
| CN114415845A (en) * | 2021-12-30 | 2022-04-29 | 北京百度网讯科技有限公司 | Feedback information processing method, device, electronic equipment, medium and product |
| CN114357309B (en) * | 2022-03-08 | 2022-06-24 | 蜗牛货车网(山东)电子商务有限公司 | Intelligent client recommendation method for second-hand vehicle cross-border trade |
| CN114880580A (en) * | 2022-06-15 | 2022-08-09 | 北京百度网讯科技有限公司 | Information recommendation method and device, electronic equipment and medium |
| CN115374351A (en) * | 2022-08-05 | 2022-11-22 | 中国银行股份有限公司 | Movie and television product pushing method and device |
| CN116308644A (en) * | 2023-03-03 | 2023-06-23 | 中国工商银行股份有限公司 | Recommendation method, device, equipment, storage medium and product of target product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126669A (en) * | 2016-06-28 | 2016-11-16 | 北京邮电大学 | User collaborative based on label filters content recommendation method and device |
| CN108363804A (en) * | 2018-03-01 | 2018-08-03 | 浙江工业大学 | Local model weighted fusion Top-N movie recommendation method based on user clustering |
| CN108763314A (en) * | 2018-04-26 | 2018-11-06 | 深圳市腾讯计算机系统有限公司 | A kind of interest recommends method, apparatus, server and storage medium |
| CN109360057A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110096614A (en) * | 2019-04-12 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Information recommendation method and device, electronic equipment |
-
2019
- 2019-08-14 CN CN201910750226.6A patent/CN112395487B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126669A (en) * | 2016-06-28 | 2016-11-16 | 北京邮电大学 | User collaborative based on label filters content recommendation method and device |
| CN108363804A (en) * | 2018-03-01 | 2018-08-03 | 浙江工业大学 | Local model weighted fusion Top-N movie recommendation method based on user clustering |
| CN108763314A (en) * | 2018-04-26 | 2018-11-06 | 深圳市腾讯计算机系统有限公司 | A kind of interest recommends method, apparatus, server and storage medium |
| CN109360057A (en) * | 2018-10-12 | 2019-02-19 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110096614A (en) * | 2019-04-12 | 2019-08-06 | 腾讯科技（深圳）有限公司 | Information recommendation method and device, electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112395487A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112395487B (en) | Information recommendation method and device, computer readable storage medium and electronic equipment | |
| CN111046275B (en) | User label determining method and device based on artificial intelligence and storage medium | |
| CN112528025A (en) | Text clustering method, device and equipment based on density and storage medium | |
| CN114283350B (en) | Visual model training and video processing method, device, equipment and storage medium | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN109460519B (en) | Browsing object recommendation method and device, storage medium and server | |
| CN113591881B (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN118193806B (en) | Target retrieval method, target retrieval device, electronic equipment and storage medium | |
| CN113360788A (en) | Address recommendation method, device, equipment and storage medium | |
| CN111191825A (en) | User default prediction method and device and electronic equipment | |
| Zhang et al. | Deep unsupervised self-evolutionary hashing for image retrieval | |
| CN115033801B (en) | Article recommendation method, model training method and electronic equipment | |
| CN118468863A (en) | Title generation method and device | |
| CN116957128A (en) | Service index prediction method, device, equipment and storage medium | |
| CN113094584A (en) | Method and device for determining recommended learning resources | |
| CN113672804A (en) | Recommendation information generation method, system, computer device and storage medium | |
| CN111428486B (en) | Article information data processing method, device, medium and electronic equipment | |
| CN118229465B (en) | Pre-application patent quality assessment method and system based on cluster center representation | |
| WO2022009013A1 (en) | Automated data linkages across datasets | |
| CN112948589B (en) | Text classification method, text classification device and computer-readable storage medium | |
| CN112434174B (en) | Method, device, equipment and medium for identifying a publishing account of multimedia information | |
| CN117435685A (en) | Document retrieval method, document retrieval device, computer equipment, storage medium and product | |
| CN118820458A (en) | Text opinion recognition method, device, storage medium and electronic device | |
| CN117332787A (en) | A visual text data classification method based on text clustering semantic cloud | |
| CN116756281A (en) | Knowledge question and answer methods, devices, equipment and media |
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 |