CN111611469A - Identification information determination method and device, electronic equipment and storage medium - Google Patents

Identification information determination method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111611469A
CN111611469A CN201910133975.4A CN201910133975A CN111611469A CN 111611469 A CN111611469 A CN 111611469A CN 201910133975 A CN201910133975 A CN 201910133975A CN 111611469 A CN111611469 A CN 111611469A
Authority
CN
China
Prior art keywords
label
article
modularity
identification information
tag
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.)
Pending
Application number
CN201910133975.4A
Other languages
Chinese (zh)
Inventor
苏福顺
黄翊轩
罗长虹
丁卓冶
殷大伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201910133975.4A priority Critical patent/CN111611469A/en
Publication of CN111611469A publication Critical patent/CN111611469A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The disclosure relates to an identification information determining method and device, electronic equipment and a storage medium, relates to the technical field of data mining, and can be applied to an application scenario of determining identification information of a label group consisting of a plurality of similar article labels. The identification information determining method comprises the steps of obtaining user behavior records of each article label; determining label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups; and determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles. The present disclosure may aggregate a plurality of similar item tags to form a plurality of tag groupings and determine identification information for each tag grouping.

Description

Identification information determination method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of data mining technologies, and in particular, to an identification information determining method, an identification information determining apparatus, an electronic device, and a storage medium.
Background
With the development of economy and the improvement of living standard of people, more and more articles are provided for people to select. When a user is faced with a plurality of optional articles, the article provider is expected to classify similar articles and determine corresponding article labels for the classified articles, so that the user can select proper articles from complicated articles.
Based on this, the article provider starts to adopt a manual marking mode, namely, after classifying a plurality of similar articles, corresponding identification information is determined for the similar articles. However, the manual marking method has huge workload; in addition, the manual marking method may not be able to accurately determine the most suitable identification information for each article due to objective factors, and the situation that the label information is not updated timely is likely to occur.
It is to be noted that the information disclosed in the above background section is only for enhancement of 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
An object of the present disclosure is to provide an identification information determination method, an identification information determination apparatus, an electronic device, and a computer-readable storage medium, thereby overcoming, at least to some extent, the problem of being unable to accurately determine identification information for an article within a tag group.
According to a first aspect of the present disclosure, there is provided an identification information determination method, including: acquiring user behavior records of each article label; determining label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups; and determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles.
Optionally, determining the tag similarity between the article tags based on the user behavior record of each article tag includes: acquiring the browsing times of the first article label from the user behavior record corresponding to the first article label; acquiring the browsing times of the second object label from the user behavior record corresponding to the second object label; and determining the label similarity between the first article label and the second article label according to the browsing times of the first article label and the browsing times of the second article label.
Optionally, the aggregating the article tags based on the tag similarity between the article tags to form a plurality of tag groups includes: constructing a label network diagram based on the label similarity among the labels of the articles; and dividing each node of the label network graph by adopting a maximum modularity aggregation processing method to form a plurality of label groups.
Optionally, constructing a tag network graph based on tag similarity between tags of each article includes: determining each article label as a node of a label network graph; taking the determined label similarity between the labels of the articles as the weight of a connecting line connecting the two nodes; and constructing a label network graph based on each node and the connecting lines of the nodes.
Optionally, the dividing each node of the label network graph by using the maximum modularity aggregation processing method to form a plurality of label packets includes: determining the modularity of a label network diagram where the current node is located as a first modularity; combining the current node with one or more similar nodes in a simulation mode, and determining the modularity of the label network graph after the current node is combined with the one or more similar nodes as the middle modularity; if a middle modularity is determined, taking the middle modularity as a second modularity; if a plurality of middle modularity degrees are determined, calculating difference values of the plurality of middle modularity degrees and the first modularity degree respectively, and taking the middle modularity degree corresponding to the maximum difference value as a second modularity degree; if the difference value between the second modularity and the first modularity is positive, combining the current node with the similar node corresponding to the second modularity; and taking the next node of the current node as the current node until the combination state among all nodes in the network is not changed so as to form a plurality of label packets.
Optionally, combining the current node with the similar node corresponding to the second modularity includes: and compressing the current node and the similar node corresponding to the second modularity to form a new node, and using the new node as a node in the label network graph.
Optionally, determining the identification information of the target tag grouping according to the attribute of the article under each target article tag in the target tag grouping and the user data corresponding to the article includes: generating one or more classification identifications based on the attributes of the items and user data corresponding to the items; and determining one or more classification identifications as the identification information of the target label group.
Optionally, the identification information determining method further includes: and responding to a search instruction of a user, determining the items under one or more item labels in the label group corresponding to the search instruction, and displaying the items at the user side.
According to a second aspect of the present disclosure, there is provided an identification information determination apparatus including: the behavior record acquisition module is used for acquiring the user behavior record of each article label; the label grouping and aggregating module is used for determining label similarity among the article labels based on the user behavior records of the article labels and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups; and the identification information determining module is used for determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles.
Optionally, the tag grouping and aggregating module includes a tag similarity determining unit, configured to obtain, from a user behavior record corresponding to the first article tag, browsing times of the first article tag by the user; acquiring the browsing times of the second object label from the user behavior record corresponding to the second object label; and determining the label similarity between the first article label and the second article label according to the browsing times of the first article label and the browsing times of the second article label.
Optionally, the tag grouping and aggregating module further includes a tag grouping determining unit, configured to construct a tag network graph based on tag similarity between tags of the articles; and dividing each node of the label network graph by adopting a maximum modularity aggregation processing method to form a plurality of label groups.
Optionally, the label grouping determination unit includes a network graph construction subunit, configured to determine that each item label is used as a node of the label network graph; taking the determined label similarity between the labels of the articles as the weight of a connecting line connecting the two nodes; and constructing a label network graph based on each node and the connecting lines of the nodes.
Optionally, the tag grouping determining unit includes a tag grouping determining subunit, configured to determine a modularity of a tag network graph where the current node is located as a first modularity; combining the current node with one or more similar nodes in a simulation mode, and determining the modularity of the label network graph after the current node is combined with the one or more similar nodes as the middle modularity; if a middle modularity is determined, taking the middle modularity as a second modularity; if a plurality of middle modularity degrees are determined, calculating difference values of the plurality of middle modularity degrees and the first modularity degree respectively, and taking the middle modularity degree corresponding to the maximum difference value as a second modularity degree; if the difference value between the second modularity and the first modularity is positive, combining the current node with the similar node corresponding to the second modularity; and taking the next node of the current node as the current node until the combination state among all nodes in the network is not changed so as to form a plurality of label packets.
Optionally, the identification information determining apparatus further includes a new node forming module, configured to perform compression processing on the current node and a similar node corresponding to the second modularity to form a new node, and use the new node as a node in the label network graph.
Optionally, the identification information determining module includes an identification information determining unit, configured to generate one or more classification identifiers based on the attribute of each article and user data corresponding to each article; and determining one or more classification identifications as the identification information of the target label group.
Optionally, the identification information determining apparatus further includes an article display module, configured to determine, in response to a search instruction of a user, an article under one or more article tags in a tag group corresponding to the search instruction, and display the article at the user side.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory having computer readable instructions stored thereon which, when executed by the processor, implement a method of identification information determination according to any of the above.
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 identification information determination method according to any one of the above.
In the identification information determining method in the exemplary embodiment of the present disclosure, first, a user behavior record of each article tag is obtained; secondly, determining label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups; and thirdly, determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles. Through the identification information determining method disclosed by the disclosure, on one hand, the label grouping formed by aggregating the label of each article according to the label similarity among the labels of each article is realized, so that a plurality of articles in the same label grouping have higher similarity in the strategy of deploying and guiding the user behavior. On the other hand, the label similarity is determined according to the user behavior record, the label group is formed, the newly formed label group can be adjusted in real time according to the user behavior record, the accuracy and the timeliness of the identification information in the label group are ensured, and the user behavior is guided by the aid of the newly formed group information. On the other hand, the identification information determining method can automatically generate the label grouping without manual operation, and greatly solves the problems of inaccurate marking or low efficiency caused by manual marking.
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 present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:
fig. 1 schematically illustrates a flow chart of an identification information determination method according to an exemplary embodiment of the present disclosure;
FIG. 2 schematically illustrates a tag network diagram constructed in accordance with an exemplary embodiment of the present disclosure;
FIG. 3 illustrates a schematic diagram of an aggregation process of a tag network graph into a plurality of tag packets, according to an example embodiment of the present disclosure;
FIG. 4 schematically illustrates a block diagram for determining identification information for an item tag according to an exemplary embodiment of the present disclosure;
fig. 5 schematically illustrates a first block diagram of an identification information determination apparatus, according to some example embodiments of the present disclosure;
fig. 6 schematically illustrates a first block diagram of a label packet aggregation module, in accordance with some demonstrative embodiments of the present disclosure;
fig. 7 schematically illustrates a second block diagram of a label packet aggregation module, in accordance with some demonstrative embodiments of the present disclosure;
fig. 8 schematically illustrates a first block diagram of a tag grouping determination unit, according to some exemplary embodiments of the present disclosure;
fig. 9 schematically illustrates a second block diagram of a tag grouping determination unit, according to some exemplary embodiments of the present disclosure;
fig. 10 schematically illustrates a second block diagram of an identification information determination apparatus according to some exemplary embodiments of the present disclosure;
fig. 11 schematically illustrates a block diagram of an identification information determination module, according to some example embodiments of the present disclosure;
fig. 12 schematically illustrates a third block diagram of an identification information determination apparatus, according to some example embodiments of the present disclosure;
FIG. 13 schematically illustrates a block diagram of an electronic device according to an exemplary embodiment of the present disclosure; and
fig. 14 schematically illustrates a schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, 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 disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in the form of software, or in one or more software-hardened modules, or in different networks and/or processor devices and/or microcontroller devices.
An article provider generally determines corresponding identification information for an article by means of manual marking, determines a plurality of similar articles from a plurality of articles to form a tag group, and determines corresponding identification information for the tag group. In the face of numerous and complicated articles, the manual marking mode undoubtedly brings huge workload for the article provider; in addition, in the manual marking process, due to the fact that collection of information of certain articles is insufficient, the given identification information of the label groups is not accurate enough. In addition, when the style or the attribute of the article changes, the label groups cannot be timely recombined by adopting a manual marking mode, and the corresponding identification information is updated.
Based on this, in the present exemplary embodiment, there is first provided an identification information determination method, which may be implemented by a server, and referring to fig. 1, may include the following steps:
and S110, acquiring user behavior records of each article label.
In some exemplary embodiments of the present disclosure, the item tag may be a specific set of features, benefits and services provided by the item provider to the user for a long time, and the item tag carries more of the approval of a part of people for its products and services, which is a product derived from mutual running-in between the purchasing activities of the item provider and the user. For example, an item tag may be a brand, and an item tag in this disclosure may be a brand corresponding to an item. Brands may be divided into international big brands, small-crowd brands, citizen brands, and so on. For example, the article label of the cosmetic may include high-end brands such as lanocon, yashirandi, dio, and also may include equivalent brands such as charilan, butcher's broom, and natura. The user behavior may include, but is not limited to, user clicking, browsing, purchasing, commenting on the items under the item tags, and the user behavior may be collated and generated into a user behavior record. The user behavior records of the labels of the articles can be obtained by obtaining behavior records of clicking, adding a shopping cart, placing orders, commenting and the like of the user on the e-commerce platform on the articles under different article labels, and behavior records of purchasing, paying attention to and the like of the user on the articles under different article labels in the special shopping mall cabinet. After the user behavior records of the article labels are obtained, the user behavior records can be sorted so as to be convenient for analyzing the user behavior records of the brands in the following process.
S120, determining the label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups.
In some exemplary embodiments of the present disclosure, the tag similarity between each article tag may be a pairwise tag similarity between two article tags. It is generally considered that items viewed by a user during the same period of time have certain similarities. For example, if a user wants to buy a sport pants, the user can perform condition search, click recommendation results, browse sales promotion activities on the e-commerce platform, possibly browse article labels such as nike, adidas, and powerful horses, and finally find the desired article for purchase through comparison. Therefore, it can be considered that if two item tags are browsed by many same users in the same time period, the two item tags have high similarity, and the number of times that the two item tags are browsed together can be used as a measure of the degree of tag similarity, i.e. the tag similarity. The label of each article can be further aggregated based on the label similarity between the labels of each article, so as to aggregate a plurality of article labels reaching a certain label similarity into a label group.
The manner of generating the label packet may include, but is not limited to, a manner of constructing a label network graph based on label similarity between labels of the respective articles, and generating a plurality of label packets based on the label network graph; and determining a plurality of label groups in a mode of clustering the labels of the articles directly based on the determined label similarity among the labels of the articles. Common methods for Clustering labels of items may include, but are not limited to, a K-Means (K-Means) Clustering algorithm, a mean shift Clustering algorithm, a Density-Based Clustering algorithm (DBSCAN), an Expectation Maximization (EM) Clustering method using Gaussian Mixture Model (GMM), a hierarchical Clustering algorithm, and a graph community Detection (graphcommunicity Detection) algorithm.
It is easily understood by those skilled in the art that the method of aggregating a plurality of article labels and generating a label group by using different clustering methods all belong to the protection scope of the present disclosure, and the present disclosure does not make any special limitation thereto.
According to some exemplary embodiments of the present disclosure, the browsing times of the first item tag by the user are acquired from the user behavior record corresponding to the first item tag; acquiring the browsing times of the second object label from the user behavior record corresponding to the second object label; and determining the label similarity between the first article label and the second article label according to the browsing times of the first article label and the browsing times of the second article label. The first item tag may be one item tag that requires a polymerization process and the second item tag may be one item tag that is different from the first item tag. When calculating the label similarity between the labels of the articles, some problems may occur, such as hot articles like mobile phones and laundry detergents may be browsed together with other unrelated article labels, thereby showing a great correlation with other article labels. In order to make the calculated tag similarity between the tags of the articles more accurate and avoid the above possible problems, the calculation method in formula 1 may be used to calculate the tag similarity between the tags of the articles.
Figure BDA0001976372230000091
Equation 1 defines the Jaccard coefficient, where given two sets A, B, the Jaccard coefficient is defined as the ratio of the size of the intersection of A and B to the size of the union of A and B. Therefore, the idea of using the Jaccard coefficient can calculate the tag similarity between the first item tag and the second item tag by the following formula 2:
J(A,B)＝ClickAB/(ClickA+ClickB-ClickAB) (formula 2)
Wherein, Click is adoptedAIndicating the number of views of the first item tag, using ClickBIndicating the number of views of the second item label, using ClickABIndicating the number of times the first item label and the second item label are viewed simultaneously.
By adopting the method, the similarity between every two of the plurality of article labels to be subjected to label similarity calculation can be determined. For example, the first item tag may be a TCL brand, and the item tags most similar to the TCL brand are shown in table 1 below, where the tag similarity between TCL and oxx (AUX) is 0.128042, the tag similarity between TCL and hain (Hisense) is 0.128042, the tag similarity between TCL and Haier (Haier) is 0.103581, and so on.
After the label similarity between the labels of the articles is calculated, the next operation can be performed based on the calculated label similarity, so that a plurality of labels of the articles meeting a certain similarity condition form a label group.
TABLE 1
Figure BDA0001976372230000092
Figure BDA0001976372230000101
According to another exemplary embodiment of the present disclosure, a tag network graph is constructed based on tag similarities between tags of respective items; and dividing each node of the label network graph by adopting a maximum modularity aggregation processing method to form a plurality of label groups. The label network graph may be a network graph representing similarity relationships between labels of each article, and the label network graph may be constructed based on the calculated label similarity between the labels of each article. The aggregation method for maximizing the modularity can be realized by adopting a community discovery algorithm (namely, a Louvain algorithm) based on the modularity. In the constructed label network diagram, the connection degree between some article labels is higher, and the connection degree between the article labels and other article labels is low. For example, the first group of item tags may include, but is not limited to, nike, adidas, pomma, underlay, etc., where the tag similarity between the item tags in the first group of item tags is high; the second set of item tags may be anjia, Tekko, pick, etc., with a higher degree of tag similarity between the item tags in the second set of item tags, however, with a relatively lower degree of tag similarity between the first set of item tags and the second set of item tags. Thus, a first group of article labels may be formed into one label grouping and a second group of article labels may be formed into another label grouping based on label similarity between the article labels. The label group can be a brand community, and the community (community) can be a subgraph corresponding to a subset of label labels of items with relatively close internal connection, and the phenomenon that the network graph contains individual communities is called a community structure, which is a common characteristic in the network.
According to some example embodiments of the present disclosure, each item label is determined as a node of a label network graph; taking the determined label similarity between the labels of the articles as the weight of a connecting line connecting the two nodes; and constructing a label network graph based on each node and the connecting lines of the nodes. Referring to fig. 2, a label network diagram constructed from the calculated label similarity between the labels of the respective articles is shown in fig. 2. Each article label corresponds to a node in the label network graph, the nodes with label similarity in the label network graph are connected by a connecting line, the similarity between two article labels can be used as the weight of the connecting line (namely, the corresponding edge in the label network graph), and the nodes are connected to construct the label network graph so as to aggregate the nodes in the label network graph to form a plurality of label groups.
According to another exemplary embodiment of the disclosure, the modularity of the label network graph where the current node is located is determined as a first modularity; combining the current node with one or more similar nodes in a simulation mode, and determining the modularity of the label network graph after the current node is combined with the one or more similar nodes as the middle modularity; if a middle modularity is determined, taking the middle modularity as a second modularity; if a plurality of middle modularity degrees are determined, calculating difference values of the plurality of middle modularity degrees and the first modularity degree respectively, and taking the middle modularity degree corresponding to the maximum difference value as a second modularity degree; if the difference value between the second modularity and the first modularity is positive, combining the current node with the similar node corresponding to the second modularity; and taking the next node of the current node as the current node until the combination state among all nodes in the network is not changed so as to form a plurality of label packets.
The current node may be the node for which the label packet is to be determined and the one or more similar nodes may be nodes directly connected to the current node. The idea of the Louvain algorithm is applied to the process of forming a plurality of item labels into a plurality of label groups, and the optimization goal of the Louvain algorithm is to maximize the modularity of the whole community network. The modularity may be a measurement method for evaluating the quality of a community network partition, and its physical meaning is that the edge number of a node in a community is only different from the edge number in a random case, and its value range may be [ -1/2,1), which is defined as follows:
Figure BDA0001976372230000111
wherein the content of the first and second substances,
Figure BDA0001976372230000112
Aijis the weight of the edge between node i and node j, in the label networkIn the figure AijLabel similarity between item label i represented by node i and item label j represented by node j); k is a radical ofi＝∑jAijRepresents the sum of the weights of all edges connected to node i; c. CiIndicating the label group to which the node i belongs;
Figure BDA0001976372230000113
representing the sum of the weights of all edges in the label net graph. In addition, the modularity can be understood as the weight of the edge inside the label group minus the weight sum of all edges connected with each node inside the label group, and the undirected graph with only edges and no corresponding weight is better understood, that is, the degree of the edge inside the community minus the total degree of the nodes inside the community.
Forming the plurality of tag groupings may be performed by:
(1) regarding each node in the label network graph as an independent label packet, wherein the number of the initial label packets is the same as that of the nodes in the label network graph, and the label network graph at the moment can be an initial state of the label packets to be formed through calculation;
(2) in the process of combining the current node and one or more similar nodes in a simulation mode, for the current node, sequentially trying to divide the current node into label groups where the similar nodes directly connected with the current node are located, and calculating the modularity of the label network graph after dividing the label groups each time as the middle modularity, so that one or more middle modularity can be determined. When the number of the determined middle modularity is only one, the middle modularity is taken as a second modularity, and the difference value between the second modularity and the first modularity is calculated; when the number of the determined middle modularity degrees is multiple, the multiple middle modularity degrees can be determined, the difference between the multiple middle modularity degrees and the first modularity degree is respectively calculated, and the middle modularity degree with the largest difference between the middle modularity degrees and the first modularity degree is taken as the second modularity degree.
And if the difference value between the second modularity and the first modularity is positive, recording the similar nodes corresponding to the second modularity, and dividing the current node into the label groups where the similar nodes corresponding to the second modularity are located. And if the difference value between the second modularity and the first modularity is negative or 0, keeping the division condition of the currently determined label group unchanged.
(3) And (3) adopting the process in the step (2) for each node in the label network graph, and dividing label packets for each node in the label network graph. When the label grouping is divided for each node in the label network graph, the community division operation can be performed on each node in the label network graph one by one in a mode of randomly selecting the node. In addition, a preset mode may also be adopted to select a node next to the current node, where the preset mode may be to select a node having the highest label similarity with the current node as the next node of the current node each time. And when the combination state among all the nodes in the label network graph does not change, namely the label packet to which each node belongs does not change any more, determining that the combination state of each node in the label network graph is the state of a plurality of label packets.
According to another exemplary embodiment of the present disclosure, the current node and the similar node corresponding to the second modularity are compressed to form a new node, and the new node is used as a node in the label network graph. The current node and the similar node corresponding to the second modularity may be two nodes combined together in the process of forming the tag packet because the tag similarity reaches a certain condition, which may be understood as a simulated middle tag packet in the process of forming the tag packet, and the two nodes may be compressed to form a new node. In the process of compressing the two nodes into one node, the weight of the edge between the nodes in the label packet is converted into the weight of the ring of the new node, and the weight of the edge between the label packets is converted into the weight of the edge between the new nodes. After the new node is determined, the operation of simulating and dividing the middle label packet can be continuously carried out on the formed new label network graph.
And repeating the compression processing on the nodes in the simulated intermediate label packet to form a new node, and performing the operation of simulating and dividing the label packet on the new label network diagram until the modularity of the whole label network diagram is not changed any more, wherein the formed label packet is in a final label packet state.
Referring to table 2, the case where the above article tag dividing operation is adopted to divide a plurality of article tags into 4 tag groups, for example: the label grouping numbered "3" may include, but is not limited to, millet, charm, nut, Huachi, Zhongxing Nubian, 360, American show, etc. item labels.
TABLE 2
Packet numbering Tagging group members
1 Nike, Adida, Bibushi, andermor, new balance …
2 Anduo, lie, 361 degree, pike, Tetuo, hongxingerke, Qiaodan …
3 Millet, charm, nut, Huashi, Zhongxing Nubia, 360, Meituxiu …
4 Mei, Auckema, Oks, Haixin, Haier, Kangjia, Changhong, Roche, Swan
It should be noted that the terms "first", "second", etc. are used in this disclosure only for distinguishing different item labels and different modularity corresponding to the label network diagram, and should not impose any limitation on this disclosure.
S130, determining identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles.
In some exemplary embodiments of the present disclosure, the attribute of the item may include an own attribute of the item and some extended attributes, for example, some attributes that may be abstracted according to a use, price, and the like of the item. For example, attributes of some articles of apparel may include a type of apparel, a style of apparel, a price range, and so forth. The user data corresponding to the item may include, but is not limited to, data of the user himself related to the item, and data such as a user behavior record of an operation performed by the user on the item. For example, the user data may include an abstracted user representation, and may also include actions of clicking, browsing, purchasing, commenting on an item by the user on the e-commerce platform. The identification information of the target tag grouping may be, for example, brand tonality, which may include a core value definition explanation of the brand, a brand value appeal, a brand logo, a brand story, a brand advertisement, and the like.
According to some exemplary embodiments of the present disclosure, one or more classification identifiers are generated based on attributes of each item and user data corresponding to each item; and determining one or more classification identifications as the identification information of the target label group. The classification identifier may be an identifier generated from an attribute of the item and user data of the item for an item tag corresponding to the item, and the identifiers may reflect a classification of the item. The generation of the classification identifier can be performed by artificially extracting keywords from the definition of each article label in advance, for example, the classification identifier of the article label of some clothes can be classified into sports, leisure, occupation and the like according to the wearing type; according to the style of clothes, the clothes can be divided into hip-hop wind, cultural wind, sports wind, gentlewoman wind and the like. The category identifier may also be determined by an extended attribute of the item, for example, a price attribute of the item may be divided into a lower price segment, a middle and low price segment, a medium price segment, a middle and high price segment, and a higher price segment according to a price interval. In addition, the category identification may also be determined by analyzing user data corresponding to the item, for example, the category identification may be determined according to a user group of different items, and the category identification generated according to the user group may include, but is not limited to, teenagers, middle-aged and elderly people, and the like.
Keywords having the same attribute among a plurality of article labels in a label group are extracted, and the classification identification of the label group can be determined based on the keywords. Referring to table 3, the results of determining the class identifier for some tag groupings are shown in table 3. The classification identifiers corresponding to the label groups formed by millet, charm, nuts, Huashi, Zhongxing Nubian, 360, beautiful pictures and the like can include but are not limited to high cost performance, middle and low price sections, smart phones, state goods, large screens, good photos, double-card double-standby and the like.
TABLE 3
Figure BDA0001976372230000141
Figure BDA0001976372230000151
According to another exemplary embodiment of the disclosure, in response to a search instruction of a user, an item under one or more item tags in a tag group corresponding to the search instruction is determined and displayed at a user terminal. The search instruction of the user can be the content input by the user in the search box on the e-commerce platform or other platforms, and after receiving the search instruction of the user, the server can determine the tag group corresponding to the search instruction of the user, and send the items corresponding to one or more item tags in the tag group to the user side for display at the user side, so that the user can browse more related items.
For example, in an application scenario of guiding user behavior, the user may recommend more items for the user according to the identification information of the tag group. If a user shows a high attention degree to an article, articles corresponding to other article tags in the tag group to which the article tag corresponding to the article belongs can be recommended to the user, so that more purchasing choices are provided for the user, and the user experience is enhanced.
To sum up, referring to fig. 4, in the identification information determining method of the present disclosure, first, a user behavior record of each article label is obtained; secondly, determining label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups; and thirdly, determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles. On one hand, by the identification information determining method, a mode of maximum module degree aggregation processing can be adopted, a plurality of article labels are divided into a plurality of label groups, and the identification information of one label group is determined, so that the similarity of one article belonging to one label group is high, and the plurality of similar articles in one label group can be conveniently recommended to a user when the user behavior is guided. On the other hand, the identification information determining method can subdivide the article labels in one label group into the production line of one article label according to the article attributes, so that the division granularity of a plurality of articles under the same article label in one label group is finer, and the identification information is more accurate. On the other hand, the identification information determining method disclosed by the invention can update the latest label group in real time according to the behavior record of the user, can update the division of the label group according to the change of the user behavior corresponding to some article labels, determines the corresponding identification information, and ensures that the identification information provided for the user to refer has higher timeliness.
Further, in the present exemplary embodiment, an identification information determination apparatus is also provided. Referring to fig. 5, the identification information determination apparatus 500 may include a behavior record acquisition module 510, a tag packet aggregation module 520, and an identification information determination module 530.
Specifically, the behavior record obtaining module 510 may be configured to obtain a user behavior record of each item tag; the tag grouping and aggregating module 520 may be configured to determine tag similarity between the tags of the articles based on the user behavior record of the tags of the articles, and aggregate the tags of the articles based on the tag similarity between the tags of the articles to form a plurality of tag groups; the identification information determining module 530 may be configured to determine the identification information of a tag group according to the attribute of the item under the tag of each item in the tag group and the user data corresponding to the item.
The identification information determination device 500 may determine the tag similarity between the tags of the articles according to the behavior record of the user, and determine the corresponding identification information for the tag grouping after dividing the tags of the articles into the corresponding tag grouping based on the determined tag similarity, which is an effective identification information determination device.
According to some exemplary embodiments of the present disclosure, referring to fig. 6, the tag grouping aggregation module 520 includes a tag similarity determination unit 610.
Specifically, the tag similarity determining unit 610 may be configured to obtain, from a user behavior record corresponding to a first article tag, browsing times of the first article tag by a user; acquiring the browsing times of the second object label from the user behavior record corresponding to the second object label; and determining the label similarity between the first article label and the second article label according to the browsing times of the first article label and the browsing times of the second article label.
The tag similarity determining unit 610 calculates a relationship between the browsing times of the first item tag and the browsing times of the second item tag by using a Jaccard coefficient calculation method, and uses the determined relationship as the tag similarity between the first item tag and the second item tag.
According to another exemplary embodiment of the present disclosure, referring to fig. 7, the tag grouping aggregation module 710 may further include a tag grouping determination unit 720 in addition to the tag similarity determination unit 610, compared to the tag grouping aggregation module 520.
Specifically, the tag grouping determination unit 720 may be configured to construct a tag network graph based on tag similarities between tags of the articles; and dividing each node of the label network graph by adopting a maximum modularity aggregation processing method so as to determine a plurality of label groups.
The label grouping determination unit 720 performs a division process on each node in the label network graph by using a maximum modularity aggregation processing method to form a plurality of label groupings from a plurality of article labels, and each article label in each label grouping has a higher label similarity.
According to some example embodiments of the present disclosure, referring to fig. 8, the tag packet determining unit 720 may include a network map constructing subunit 810.
Specifically, the network graph constructing subunit 810 may be configured to construct the label network graph based on the label similarity between the labels of the articles, including: determining each article label as a node of a label network graph; taking the determined label similarity between the labels of the articles as the weight of a connecting line connecting the two nodes; and constructing a label network graph based on each node and the connecting lines of the nodes.
The network graph constructing subunit 810 constructs the label network graph by using each article label as a node in the label network graph, and using the label similarity between two article labels as an edge connecting the nodes corresponding to the two article labels.
According to another exemplary embodiment of the present disclosure, referring to fig. 9, the tag packet determining unit 910 may further include a tag packet determining subunit 920 in addition to the network diagram constructing subunit 810, compared to the tag packet determining unit 720.
Specifically, the tag packet determining subunit 920 may be configured to determine a modularity of the tag network map where the current node is located as a first modularity; combining the current node with one or more similar nodes in a simulation mode, and determining the modularity of the label network graph after the current node is combined with the one or more similar nodes as the middle modularity; if a middle modularity is determined, taking the middle modularity as a second modularity; if a plurality of middle modularity degrees are determined, calculating difference values of the plurality of middle modularity degrees and the first modularity degree respectively, and taking the middle modularity degree corresponding to the maximum difference value as a second modularity degree; if the difference value between the second modularity and the first modularity is positive, combining the current node with the similar node corresponding to the second modularity; and taking the next node of the current node as the current node until the combination state among all nodes in the network is not changed so as to form a plurality of label packets.
The tag packet determining subunit 920 performs aggregation processing on each node in the tag network graph to generate a corresponding tag packet, where the tag network graph corresponding to the generated tag packet has the maximum modularity.
In another exemplary embodiment of the present disclosure, an identification information determination apparatus 1000 is further provided, and referring to fig. 10, the identification information determination apparatus 1000 may further include a new node forming module 1010 in addition to the behavior record obtaining module 510, the tag grouping aggregation module 520, and the identification information determination module 530, compared to the identification information determination apparatus 500.
Specifically, the new node forming module 1010 may be configured to perform compression processing on the current node and a similar node corresponding to the second modularity to form a new node, and use the new node as a node in the label network graph.
The new node forming module 1010 may compress a plurality of similar nodes to form a new node, and use the new node as a node in the label network graph to further perform label packet generation on the label network graph.
According to some exemplary embodiments of the present disclosure, referring to fig. 11, the identification information determination module 530 may include an identification information determination unit 1110.
Specifically, the identification information determining unit 1110 may be configured to generate one or more classification identifications based on the attribute of each item and user data corresponding to each item; and determines one or more class identifications as identification information of the tag packet.
The identification information determination unit 1110 may determine identification information for the generated plurality of tag groups, wherein the classification identifier may be obtained by extracting a keyword of a tag attribute of an article in one community or obtaining a classification tag of a user attribute in one community.
In still another exemplary embodiment of the present disclosure, an identification information determining apparatus 1200 is further provided, and referring to fig. 12, the identification information determining apparatus 1200 may further include an article display module 1210 in addition to the behavior record obtaining module 510, the tag grouping and aggregating module 520, the identification information determining module 530, and the new node forming module 1010, compared to the identification information determining apparatus 1000.
Specifically, the article display module 1210 may be configured to determine, in response to a search instruction of a user, an article under one or more article tags in a tag group corresponding to the search instruction, and display the article at the user end.
The article display module 1210 can display a plurality of similar products to the user according to the specific content of the user search instruction, so as to provide more purchase options for the user.
The specific details of each virtual identification information determination device module are already described in detail in the corresponding identification information determination method, and therefore are not described herein again.
It should be noted that although several modules or units of the identification information determination apparatus are mentioned in the above detailed description, such 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, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 1300 according to such an embodiment of the invention is described below with reference to fig. 13. The electronic device 1300 shown in fig. 13 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in fig. 13, the electronic device 1300 is in the form of a general purpose computing device. The components of the electronic device 1300 may include, but are not limited to: the at least one processing unit 1310, the at least one memory unit 1320, the bus 1330 connecting the various system components (including the memory unit 1320 and the processing unit 1310), the display unit 1340.
Wherein the memory unit stores program code that is executable by the processing unit 1310 to cause the processing unit 1310 to perform steps according to various exemplary embodiments of the present invention as described in the "exemplary methods" section above in this specification.
The storage 1320 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)1321 and/or a cache memory unit 1322, and may further include a read only memory unit (ROM) 1323.
Storage 1320 may also include a program/utility 1324 having a set (at least one) of program modules 1325, such program modules 1325 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Bus 1330 may be any bus representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 1300 may also communicate with one or more external devices 1370 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1300, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1300 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 1350. Also, the electronic device 1300 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) through the network adapter 1360. As shown, the network adapter 1360 communicates with other modules of the electronic device 1300 via the bus 1330. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above-mentioned "exemplary methods" section of the present description, when said program product is run on the terminal device.
Referring to fig. 14, a program product 1400 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a 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.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a 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 readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
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 variations, 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 will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims (11)

1. An identification information determination method, comprising:
acquiring user behavior records of each article label;
determining label similarity among the article labels based on the user behavior records of the article labels, and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups;
and determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles.
2. The method according to claim 1, wherein the determining of the tag similarity between the article tags based on the user behavior record of the article tags comprises:
acquiring the browsing times of a user on a first article label from a user behavior record corresponding to the first article label;
acquiring the browsing times of a user on a second object label from a user behavior record corresponding to the second object label;
and determining the label similarity between the first article label and the second article label according to the browsing times of the first article label and the browsing times of the second article label.
3. The method according to claim 1, wherein the aggregating the item tags based on tag similarity between the item tags to form a plurality of tag groups comprises:
constructing a label network graph based on the label similarity between the labels of the articles;
and dividing each node of the label network graph by adopting a maximum modularity aggregation processing method to form a plurality of label groups.
4. The method according to claim 3, wherein the constructing a tag network graph based on tag similarity between the tags of the items comprises:
determining each article label as a node of a label network graph;
taking the determined label similarity between the labels of the articles as the weight of a connecting line connecting two nodes;
and constructing the label network graph based on each node and the connecting lines of the nodes.
5. The method of claim 3, wherein the partitioning the nodes of the label network graph to form the plurality of label packets using a maximum modularity aggregation processing method comprises:
determining the modularity of a label network diagram where the current node is located as a first modularity;
combining the current node with one or more similar nodes in a simulation mode, and determining the modularity of the label network graph after the current node is combined with the one or more similar nodes as a middle modularity;
if a middle modularity is determined, taking the middle modularity as a second modularity; if a plurality of middle modularity degrees are determined, calculating the difference between the middle modularity degrees and the first modularity degree respectively, and taking the middle modularity degree corresponding to the maximum difference as a second modularity degree;
if the difference value between the second modularity and the first modularity is positive, combining the current node with a similar node corresponding to the second modularity;
and taking the next node of the current node as the current node until the combination state among all nodes in the network is not changed so as to form a plurality of label groups.
6. The method of claim 5, wherein the combining the current node with the similar node corresponding to the second modularity comprises:
and compressing the current node and the similar node corresponding to the second modularity to form a new node, and using the new node as a node in the label network graph.
7. The method according to claim 1, wherein the determining the identification information of the target tag group according to the attributes of the items under the tags of the target items in the target tag group and the user data corresponding to the items comprises:
generating one or more classification identifications based on attributes of each of the items and user data corresponding to each of the items;
determining the one or more class identifications as identification information of the target tag packet.
8. The identification information determination method according to claim 1, characterized in that the identification information determination method further comprises:
and responding to a search instruction of a user, determining the items under one or more item labels in the label group corresponding to the search instruction, and displaying the items at the user side.
9. An identification information determination apparatus, characterized by comprising:
the behavior record acquisition module is used for acquiring the user behavior record of each article label;
the brand community aggregation module is used for determining the label similarity among the article labels based on the user behavior records of the article labels and performing aggregation processing on the article labels based on the label similarity among the article labels to form a plurality of label groups;
and the identification information determining module is used for determining the identification information of the target label group according to the attributes of the articles under the labels of the target articles in the target label group and the user data corresponding to the articles.
10. An electronic device, comprising:
a processor; and
a memory having stored thereon computer readable instructions which, when executed by the processor, implement the identification information determination method according to any one of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the identification information determination method according to any one of claims 1 to 8.
CN201910133975.4A 2019-02-22 2019-02-22 Identification information determination method and device, electronic equipment and storage medium Pending CN111611469A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910133975.4A CN111611469A (en) 2019-02-22 2019-02-22 Identification information determination method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910133975.4A CN111611469A (en) 2019-02-22 2019-02-22 Identification information determination method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111611469A true CN111611469A (en) 2020-09-01

Family

ID=72197611

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910133975.4A Pending CN111611469A (en) 2019-02-22 2019-02-22 Identification information determination method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111611469A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131284A (en) * 2020-09-30 2020-12-25 国网智能科技股份有限公司 Transformer substation holographic data slicing method and system
CN112543121A (en) * 2020-12-11 2021-03-23 深圳市优必选科技股份有限公司 Multi-device group control method, electronic device, and computer-readable storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104598643A (en) * 2015-02-13 2015-05-06 成都品果科技有限公司 Article similarity contribution factor, similarity acquiring method, as well as article recommendation method and system thereof
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
CN106919619A (en) * 2015-12-28 2017-07-04 阿里巴巴集团控股有限公司 A kind of commercial articles clustering method, device and electronic equipment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104598643A (en) * 2015-02-13 2015-05-06 成都品果科技有限公司 Article similarity contribution factor, similarity acquiring method, as well as article recommendation method and system thereof
CN106919619A (en) * 2015-12-28 2017-07-04 阿里巴巴集团控股有限公司 A kind of commercial articles clustering method, device and electronic equipment
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

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CODEMEALS: "模块度与Louvain社区发现算法", pages 1 - 4, Retrieved from the Internet <URL:https://www.cnblogs.com/fengfenggirl/p/louvain.html> *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131284A (en) * 2020-09-30 2020-12-25 国网智能科技股份有限公司 Transformer substation holographic data slicing method and system
CN112131284B (en) * 2020-09-30 2024-05-24 国网智能科技股份有限公司 Holographic data slicing method and system for transformer substation
CN112543121A (en) * 2020-12-11 2021-03-23 深圳市优必选科技股份有限公司 Multi-device group control method, electronic device, and computer-readable storage medium
CN112543121B (en) * 2020-12-11 2023-09-22 深圳市优必选科技股份有限公司 Multi-device group control method, electronic device and computer readable storage medium

Similar Documents

Publication Publication Date Title
US11734725B2 (en) Information sending method, apparatus and system, and computer-readable storage medium
CN109978630A (en) A kind of Precision Marketing Method and system for establishing user&#39;s portrait based on big data
CN105718184A (en) Data processing method and apparatus
CN109902708A (en) A kind of recommended models training method and relevant apparatus
CN107633430A (en) A kind of Method of Commodity Recommendation based on community of colony
CN106126582A (en) Recommend method and device
CN106708821A (en) User personalized shopping behavior-based commodity recommendation method
CN103678335A (en) Method and device for identifying commodity with labels and method for commodity navigation
CN105989004A (en) Information releasing pretreatment method and device
KR20140026932A (en) System and method providing a suited shopping information by analyzing the propensity of an user
CN104835057A (en) Method and device for obtaining consumption feature information of network user
CN109636430A (en) Object identifying method and its system
CN106326318B (en) Searching method and device
CN108415913A (en) Crowd&#39;s orientation method based on uncertain neighbours
CN112380453B (en) Article recommendation method and device, storage medium and equipment
CN104615721B (en) For the method and system based on return of goods related information Recommendations
CN104616178A (en) Recommendation method of E-commerce goods based on big-data multi-label classification method
CN112287238B (en) User characteristic determination method and device, storage medium and electronic equipment
CN111626767B (en) Resource data issuing method, device and equipment
CN107885784A (en) The method and apparatus for extracting user characteristic data
CN116308684A (en) Online shopping platform store information pushing method and system
CN115392947A (en) Demand prediction method and device
CN115496523A (en) Advertisement publishing method, computer readable storage medium and electronic device
CN111611469A (en) Identification information determination method and device, electronic equipment and storage medium
CN110968670B (en) Method, device, equipment and storage medium for acquiring attributes of popular commodities

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