CN110287977B - Content clustering method and device - Google Patents
Content clustering method and device Download PDFInfo
- Publication number
- CN110287977B CN110287977B CN201810226492.4A CN201810226492A CN110287977B CN 110287977 B CN110287977 B CN 110287977B CN 201810226492 A CN201810226492 A CN 201810226492A CN 110287977 B CN110287977 B CN 110287977B
- Authority
- CN
- China
- Prior art keywords
- node
- content
- contents
- category
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000006399 behavior Effects 0.000 claims description 40
- 238000003860 storage Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 239000000835 fiber Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a content clustering method and device. The method comprises the following steps: acquiring a plurality of groups of user behavior data; for each group of user behavior data, respectively determining a content sequence corresponding to the user behavior data; determining the correlation among the contents according to the position relation among the contents in the content sequence; and determining the category of each content by adopting a label propagation algorithm according to the correlation among the contents. The method and the device can automatically perform content clustering, do not need manual content clustering, save labor, easily perform clustering on a large amount of contents, and can better mine the correlation among the contents and improve the accuracy of content clustering.
Description
Technical Field
The present disclosure relates to the field of information technologies, and in particular, to a content clustering method and apparatus.
Background
In the related art, contents such as videos are manually clustered to obtain contents of each category. The manual content clustering method consumes a lot of manpower, and the obtained similarity between the contents in each category is difficult to be ensured.
Disclosure of Invention
In view of this, the present disclosure provides a content clustering method and device.
According to an aspect of the present disclosure, there is provided a content clustering method including:
acquiring a plurality of groups of user behavior data;
for each group of user behavior data, respectively determining a content sequence corresponding to the user behavior data;
determining the correlation among the contents according to the position relation among the contents in the content sequence;
and determining the category of each content by adopting a label propagation algorithm according to the correlation among the contents.
In a possible implementation manner, determining the correlation between the contents according to the position relationship between the contents in the content sequence includes:
determining a correlation between adjacent content in the sequence of content as a correlation.
In a possible implementation manner, determining a category to which each content belongs by using a tag propagation algorithm according to a correlation between the contents includes:
establishing an undirected graph, and taking each content as a node in the undirected graph respectively;
if the correlation between the two contents is correlation, establishing an edge between nodes corresponding to the two contents;
respectively distributing labels for each node;
for any node, updating the label of the node according to the labels of the neighbor nodes of the node, wherein the neighbor nodes of the node represent the nodes connected with the node;
and when the label of each node is stable, determining the category to which the content corresponding to each node belongs according to the label of each node.
In a possible implementation manner, for any node, updating the label of the node according to the labels of the neighboring nodes of the node includes:
and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
In one possible implementation, before updating the label of the node, the method further includes:
and for two contents with the correlation, determining the similarity between the two contents according to the adjacent occurrence times of the two contents in each content sequence and the respective occurrence times of the two contents in each content sequence.
In a possible implementation manner, for any node, updating the label of the node according to the labels of the neighboring nodes of the node includes:
determining the weight of an edge between nodes corresponding to two contents according to the similarity between the two contents with the correlation;
for any node, updating the label of the node according to the label of the neighbor node of the node and the weight of the edge between the node and the neighbor node.
In a possible implementation manner, for any node, updating the label of the node according to the labels of the neighboring nodes of the node and the weights of the edges between the node and the neighboring nodes includes:
for any node, respectively determining the labels of the neighbor nodes of the node as candidate labels;
determining neighbor nodes corresponding to all candidate labels in neighbor nodes of the node;
determining the weight corresponding to each candidate label according to the sum of the weights of the edges between the neighbor node corresponding to each candidate label and the node;
and updating the label of the node according to the candidate label with the highest weight.
In one possible implementation, after determining the category to which each content belongs, the method further includes:
and if the similarity of the contents in the first category and the second category meets a first condition, combining the first category and the second category.
In one possible implementation, after determining the category to which each content belongs, the method further includes:
determining a first number of contents in an intersection of the first category and the second category;
determining a second number of contents in a union of the first category and the second category;
if the ratio of the first content number to the second content number is greater than a first threshold, determining that the similarity of the content in the first category and the content in the second category meets the first condition;
if the ratio of the first content number to the second content number is smaller than or equal to the first threshold, determining that the similarity of the content in the first category and the second category does not meet the first condition.
In one possible implementation, after determining the category to which each content belongs, the method further includes:
and deleting the contents which do not satisfy the second condition in each category.
In one possible implementation, the second condition includes: the click through rate of the content is less than a second threshold.
According to another aspect of the present disclosure, there is provided a content clustering apparatus including:
the acquisition module is used for acquiring a plurality of groups of user behavior data;
the first determining module is used for respectively determining a content sequence corresponding to each group of user behavior data;
the second determining module is used for determining the correlation among the contents according to the position relation among the contents in the content sequence;
and the third determining module is used for determining the category of each content by adopting a label propagation algorithm according to the correlation among the contents.
In one possible implementation manner, the second determining module is configured to:
determining a correlation between adjacent content in the sequence of content as a correlation.
In one possible implementation manner, the third determining module is configured to include:
the first establishing submodule is used for establishing an undirected graph and respectively taking each content as a node in the undirected graph;
the second establishing submodule is used for establishing an edge between nodes corresponding to the two contents if the correlation between the two contents is correlation;
the distribution submodule is used for distributing labels to each node;
the updating submodule is used for updating the label of any node according to the label of the neighbor node of the node, wherein the neighbor node of the node represents the node connected with the node;
and the determining submodule is used for determining the category to which the content corresponding to each node belongs according to the label of each node when the label of each node is stable.
In one possible implementation, the update submodule is configured to:
and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
In one possible implementation, the apparatus further includes:
and the fourth determining module is used for determining the similarity between the two contents with the correlation according to the adjacent occurrence times of the two contents in each content sequence and the respective occurrence times of the two contents in each content sequence.
In one possible implementation, the update sub-module includes:
the determining unit is used for determining the weight of an edge between nodes corresponding to two relevant contents according to the similarity between the two relevant contents;
and the updating unit is used for updating the label of the node according to the label of the neighbor node of the node and the weight of the edge between the node and the neighbor node for any node.
In one possible implementation manner, the updating unit includes:
a first determining subunit, configured to determine, for any one node, labels of neighbor nodes of the node as candidate labels, respectively;
the second determining subunit is used for determining neighbor nodes corresponding to all candidate labels in the neighbor nodes of the node;
the third determining subunit is used for determining the weight corresponding to each candidate label according to the sum of the weights of the edges between the neighbor node corresponding to each candidate label and the node;
and the updating subunit is used for updating the label of the node according to the candidate label with the highest weight.
In one possible implementation, the apparatus further includes:
and the merging module is used for merging the first category and the second category if the similarity of the contents in the first category and the second category meets a first condition.
In one possible implementation, the apparatus further includes:
a fifth determining module, configured to determine a first content number in an intersection of the first category and the second category;
a sixth determining module, configured to determine a second content number in a union of the first category and the second category;
a seventh determining module, configured to determine that the similarity of the content in the first category and the content in the second category satisfies the first condition if a ratio of the first content count to the second content count is greater than a first threshold;
an eighth determining module, configured to determine that the similarity of the content in the first category and the content in the second category does not meet the first condition if a ratio of the first content count to the second content count is smaller than or equal to the first threshold.
In one possible implementation, the apparatus further includes:
and the deleting module is used for deleting the contents which do not meet the second condition in each category.
In one possible implementation, the second condition includes: the click through rate of the content is less than a second threshold.
According to another aspect of the present disclosure, there is provided a content clustering apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the above method.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-described method.
According to the content clustering method and device in each aspect, the content sequences corresponding to the user behavior data are respectively determined for each group of user behavior data by acquiring the multiple groups of user behavior data, the correlation among the contents is determined according to the position relation among the contents in the content sequences, and the category of each content is determined by adopting a label propagation algorithm according to the correlation among the contents, so that the content clustering can be automatically carried out, the content clustering is not required to be carried out manually, the labor is saved, a large amount of contents are easy to cluster, the correlation among the contents can be better mined, and the accuracy of the content clustering is improved.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.
Fig. 1 shows a flow chart of a content clustering method according to an embodiment of the present disclosure.
Fig. 2 shows an exemplary flowchart of step S14 of the content clustering method according to an embodiment of the present disclosure.
Fig. 3 shows a schematic diagram of an undirected graph in a content clustering method according to an embodiment of the present disclosure.
Fig. 4 shows an exemplary flowchart of step S144 of the content clustering method according to an embodiment of the disclosure.
Fig. 5 shows an exemplary flowchart of the content clustering method step S1442 according to an embodiment of the present disclosure.
Fig. 6 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure.
Fig. 7 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure.
Fig. 8 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure.
Fig. 9 illustrates a block diagram of a content clustering apparatus according to an embodiment of the present disclosure.
Fig. 10 shows an exemplary block diagram of a content clustering device according to an embodiment of the present disclosure.
Fig. 11 is a block diagram illustrating an apparatus 1900 for content clustering according to an example embodiment.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
Fig. 1 shows a flow chart of a content clustering method according to an embodiment of the present disclosure. The method can be applied to a server. As shown in fig. 1, the method includes steps S11 through S14.
In step S11, a plurality of sets of user behavior data are acquired.
In the present embodiment, the user behavior data represents data generated by a user operating on content. For example, the content is a video, and the user behavior data may include data of a user watching the video, data of a user commenting on the video, video data of a user posting a barrage, data of a user collecting the video, data of a user sharing the video, data of a user agreeing with the video, and the like.
In step S12, for each set of user behavior data, a content sequence corresponding to the user behavior data is determined.
For example, if it is determined that the user watches videos V1, V2, … … and VN in sequence according to a certain set of user behavior data, the content sequence corresponding to the set of user behavior data may be determined to be { V1, V2, … … and VN }.
In step S13, the correlation between the contents is determined based on the positional relationship between the contents in the content sequence.
In one possible implementation manner, determining the correlation between the contents according to the position relationship between the contents in the content sequence includes: the correlation between adjacent contents in the content sequence is determined as correlation. For example, if the content sequence is { V1, V2, … …, VN }, then it can be determined that V1 is associated with V2, V2 is associated with V3, and … …, and V (N-1) is associated with VN.
It should be noted that, although the above description has been made on determining the correlation between the contents according to the positional relationship between the contents in the content sequence in order to determine the correlation between the adjacent contents in the content sequence as the correlation, those skilled in the art will understand that the present disclosure should not be limited thereto. Those skilled in the art can flexibly set the specific manner of determining the correlation between the contents according to the actual application scene requirements and/or personal preferences, as long as the correlation between the contents is determined according to the position relationship between the contents in the content sequence. For example, the correlation between contents having a distance smaller than or equal to D, where D is a natural number, in the content sequence may also be determined as the correlation. The distance between two contents in the content sequence may refer to the number of contents between the two contents in the content sequence. For example, the distance between V1 and V2 is 0 and the distance between V1 and V3 is 1. If D is equal to 1, then V1 is associated with not only V2, but also V3.
In one possible implementation, a pair of contents may be generated based on two contents for which the correlation is a correlation. For example, pairs of contents { V1, V2}, { V2, V3}, … …, { V (N-1), VN }, may be generated.
In step S14, a label propagation algorithm is used to determine the category to which each content belongs, based on the correlation between the contents.
In this embodiment, similar contents can be grouped into the same category by an unsupervised clustering method according to the correlation between the contents and by using a label propagation algorithm.
The Label Propagation Algorithm may be LPA (Label Propagation Algorithm), or may be an improved Label Propagation Algorithm, such as COPRA (Community overlay Propagation Algorithm) or SLPA (Speaker-driver Label Propagation Algorithm based on Label Propagation nodes and Label receiving nodes).
In the embodiment, by acquiring a plurality of groups of user behavior data, a content sequence corresponding to the user behavior data is respectively determined for each group of user behavior data, the correlation between the contents is determined according to the position relationship between the contents in the content sequence, and the category to which each content belongs is determined by adopting a label propagation algorithm according to the correlation between the contents, so that the content clustering can be automatically performed, the content clustering is not required to be performed manually, the manpower is saved, a large amount of contents are easy to cluster, the correlation between the contents can be better mined, and the accuracy of the content clustering is improved.
Fig. 2 shows an exemplary flowchart of step S14 of the content clustering method according to an embodiment of the present disclosure. As shown in fig. 2, step S14 may include steps S141 to S145.
In step S141, an undirected graph is created, and each content is taken as a node in the undirected graph.
Fig. 3 shows a schematic diagram of an undirected graph in a content clustering method according to an embodiment of the present disclosure. As shown in fig. 3, for example, the content includes content V1, content V2, content V3, content V4, and content V5, and then nodes corresponding to the respective contents may be respectively established in the undirected graph, that is, node V1 corresponding to content V1, node V2 corresponding to content V2, node V3 corresponding to content V3, node V4 corresponding to content V4, and node V5 corresponding to content V5 may be established in the undirected graph.
In step S142, if the correlation between the two contents is correlation, an edge between nodes corresponding to the two contents is established.
As shown in fig. 3, for example, content V2 is related to content V1, content V3, content V4, and content V3 is related to content V5, respectively, an edge between node V2 and node V1, an edge between node V2 and node V3, an edge between node V2 and node V4, and an edge between node V3 and node V5 can be established.
In step S143, a label is assigned to each node, respectively.
For example, node V1 may be assigned tag T1, node V2 may be assigned tag T2, and so on.
In step S144, for any node, the label of the node is updated according to the labels of the neighboring nodes of the node, wherein the neighboring nodes of the node represent the nodes connected to the node.
In a possible implementation manner, for any node, updating the label of the node according to the labels of the neighboring nodes of the node includes: and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
In a possible implementation manner, updating the label of the node according to the label with the largest occurrence number in labels of neighbor nodes of the node includes: if the number of the labels with the maximum occurrence times in the labels of the neighbor nodes of the node is 1, determining the label with the maximum occurrence times in the labels of the neighbor nodes of the node as the label of the node; and if the number of the labels with the maximum occurrence times in the labels of the neighbor nodes of the node is more than 1, randomly selecting one label from the labels with the maximum occurrence times in the labels of the neighbor nodes of the node to determine the label as the label of the node.
In step S145, when the label of each node is stable, the category to which the content corresponding to each node belongs is determined according to the label of each node.
In this embodiment, the label of each node may be continuously updated according to the label of the neighbor node of each node until the label of each node is not changed any more.
In this embodiment, when the labels of the nodes are stable, the nodes with the same label can be classified into the same category.
In one possible implementation, before updating the label of the node, the method further includes: and for two contents with the correlation, determining the similarity between the two contents according to the adjacent occurrence times of the two contents in each content sequence and the respective occurrence times of the two contents in each content sequence.
For example, if the first content V1 is related to the second content V2, the number of times the first content V1 and the second content V2 appear adjacent in each content sequence is C (V1, V2), the number of times the first content V1 appears in each content sequence is C (V1), and the number of times the second content V2 appears in each content sequence is C (V2), the similarity between the first content V1 and the second content V2 may be determined using expression 1, expression 2, expression 3, or the like.
In this implementation, for two contents that do not adjacently appear in each content sequence, the similarity between the two contents may be 0.
Fig. 4 shows an exemplary flowchart of step S144 of the content clustering method according to an embodiment of the disclosure. As shown in fig. 4, step S144 may include step S1441 and step S1442.
In step S1441, according to the similarity between two contents whose correlation is related, the weight of the edge between the nodes corresponding to the two contents is determined.
For example, the similarity between two contents may be used as the weight of an edge between nodes corresponding to the two contents.
In step S1442, for any node, the label of the node is updated according to the labels of the neighboring nodes of the node and the weights of the edges between the node and the neighboring nodes.
In a possible implementation manner, for any node, updating the label of the node according to the labels of the neighboring nodes of the node and the weights of the edges between the node and the neighboring nodes includes: if the number of the labels with the maximum occurrence times in the labels of the neighbor nodes of the node is 1, determining the label with the maximum occurrence times in the labels of the neighbor nodes of the node as the label of the node; and if the number of the labels with the maximum occurrence times in the labels of the neighbor nodes of the node is more than 1, selecting the label with the maximum weight from the labels with the maximum occurrence times in the labels of the neighbor nodes of the node as the label of the node. For example, the neighbor nodes of the node V2 include a node V1, a node V3, a node V4, and a node V6, the labels of the node V1 and the node V3 are T1, and the labels of the node V4 and the node V6 are T2, so the occurrence frequency of the label T1 and the label T2 are both 2, that is, the number of labels with the largest occurrence frequency in the labels of the neighbor nodes of the node V2 is greater than 1. If the weight of the edge between node V1 and node V2 is W1, the weight of the edge between node V3 and node V2 is W2, the weight of the edge between node V4 and node V2 is W3, and the weight of the edge between node V6 and node V2 is W4, then it can be determined that the weight of label T1 is W1+ W2 and the weight of label T2 is W3+ W4. If the weight of tag T1 is greater than the weight of tag T2, then tag T1 can be the tag of node V2.
Fig. 5 shows an exemplary flowchart of the content clustering method step S1442 according to an embodiment of the present disclosure. As shown in fig. 5, step S1442 may include steps S14421 to S14424.
In step S14421, for any node, the labels of the neighbor nodes of the node are respectively determined as candidate labels.
For example, if neighbor nodes of node V2 include node V1, node V3, node V4, node V6, and node V7, and labels of node V1 and node V3 are T1, labels of node V4 and node V6 are T2, and label V7 is T3, then label T1, label T2, and label T3 may be determined as candidate labels, respectively.
In step S14422, a neighbor node corresponding to each candidate label in the neighbor nodes of the node is determined.
For example, it may be determined that the neighbor node to which candidate tag T1 corresponds includes node V1 to node V3, the neighbor node to which candidate tag T2 corresponds includes node V4 and node V6, and the neighbor node to which candidate tag T3 corresponds includes node V7.
In step S14423, the weight corresponding to each candidate label is determined according to the sum of the weights of the edges between the neighboring node corresponding to each candidate label and the node.
For example, if the weight of the edge between node V1 and node V2 is W1, and the weight of the edge between node V3 and node V2 is W2, then the candidate label T1 may be determined to have a weight of W1+ W2; if the weight of the edge between the node V4 and the node V2 is W3, and the weight of the edge between the node V6 and the node V2 is W4, it may be determined that the candidate label T2 corresponds to W3+ W4; the weight of the edge between node V7 and node V2 is W5, then candidate tag T3 may be determined to correspond to a weight of W5.
In step S14424, the label of the node is updated according to the candidate label with the highest weight.
For example, if candidate tag T2 is the highest weighted among candidate tag T1, candidate tag T2, and candidate tag T3, candidate tag T2 may be updated as the tag of node V2.
Fig. 6 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure. As shown in fig. 6, the method may include steps S11 through S15.
In step S11, a plurality of sets of user behavior data are acquired.
In step S12, for each set of user behavior data, a content sequence corresponding to the user behavior data is determined.
In step S13, the correlation between the contents is determined based on the positional relationship between the contents in the content sequence.
In step S14, a label propagation algorithm is used to determine the category to which each content belongs, based on the correlation between the contents.
In step S15, if the similarity of the content in the first category and the second category satisfies the first condition, the first category and the second category are merged.
In one possible implementation, content clustering may be performed at a specified frequency. For example, new user behavior data may be obtained daily and content clustering may be performed based on the new user behavior data. If the similarity of the content in a newly determined category (e.g., a first category) and an old category (e.g., a second category) satisfies a first condition, the newly determined category and the old category may be merged.
In this embodiment, when the similarity of the content in the first category and the second category satisfies the first condition, the first category and the second category are merged, so that the stability of the categories can be ensured, and the categories can be automatically expanded.
Fig. 7 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure. As shown in fig. 7, the method may include steps S21 through S29.
In step S21, a plurality of sets of user behavior data are acquired.
Wherein, for step S21, refer to the description above for step S11.
In step S22, for each set of user behavior data, a content sequence corresponding to the user behavior data is determined.
Wherein, for step S22, refer to the description above for step S12.
In step S23, the correlation between the contents is determined based on the positional relationship between the contents in the content sequence.
Wherein, for step S23, refer to the description above for step S13.
In step S24, a label propagation algorithm is used to determine the category to which each content belongs, based on the correlation between the contents.
Wherein, for step S24, refer to the description above for step S14.
In step S25, a first number of contents in the intersection of the first category and the second category is determined.
Wherein the first content number represents the number of contents in an intersection of the first category and the second category.
In step S26, a second number of contents in the union of the first category and the second category is determined.
Wherein the second number of contents represents the number of contents in a union of the first category and the second category.
In step S27, if the ratio of the first number of contents to the second number of contents is greater than the first threshold, it is determined that the similarity of the contents in the first category and the second category satisfies the first condition.
In step S28, if the similarity of the content in the first category and the second category satisfies the first condition, the first category and the second category are merged.
Wherein, for step S28, refer to the description above for step S15.
In step S29, if the ratio of the first number of contents to the second number of contents is less than or equal to the first threshold, it is determined that the similarity of the contents in the first category and the second category does not satisfy the first condition.
Fig. 8 illustrates an exemplary flow chart of a content clustering method according to an embodiment of the present disclosure. As shown in fig. 8, the method may include steps S31 through S35.
In step S31, a plurality of sets of user behavior data are acquired.
Wherein, for step S31, refer to the description above for step S11.
In step S32, for each set of user behavior data, a content sequence corresponding to the user behavior data is determined.
Wherein, for step S32, refer to the description above for step S12.
In step S33, the correlation between the contents is determined based on the positional relationship between the contents in the content sequence.
Wherein, for step S33, refer to the description above for step S13.
In step S34, a label propagation algorithm is used to determine the category to which each content belongs, based on the correlation between the contents.
Wherein, for step S34, refer to the description above for step S14.
In step S35, the content that does not satisfy the second condition in each category is deleted.
The present embodiment can ensure the quality of the content in each category by deleting the content that does not satisfy the second condition in each category.
In one possible implementation, the second condition includes: the click through rate of the content is less than a second threshold. Wherein, the click rate of the content is equal to the ratio of the number of times the content is clicked to the number of times the content is displayed.
In another possible implementation, the second condition may include: the number of clicks of the content within the specified time frame is less than a third threshold.
It should be noted that although the second condition is described above in the above two implementations, those skilled in the art can understand that the disclosure should not be limited thereto. The person skilled in the art can flexibly set the second condition according to the requirements of the actual application scenario and/or personal preferences.
Fig. 9 illustrates a block diagram of a content clustering apparatus according to an embodiment of the present disclosure. As shown in fig. 9, the apparatus includes: an obtaining module 901, configured to obtain multiple sets of user behavior data; a first determining module 902, configured to determine, for each group of user behavior data, a content sequence corresponding to the user behavior data; a second determining module 903, configured to determine, according to a position relationship between contents in the content sequence, a correlation between the contents; a third determining module 904, configured to determine, according to the correlation between the contents, a category to which each content belongs by using a tag propagation algorithm.
In one possible implementation manner, the second determining module 903 is configured to: the correlation between adjacent contents in the content sequence is determined as correlation.
Fig. 10 shows an exemplary block diagram of a content clustering device according to an embodiment of the present disclosure. As shown in fig. 10:
in one possible implementation, the third determining module 904 is configured to include: the first establishing submodule 9041 is used for establishing an undirected graph and taking each content as a node in the undirected graph respectively; a second establishing sub-module 9042, configured to establish an edge between nodes corresponding to the two contents if the correlation between the two contents is correlation; a distribution submodule 9043, configured to distribute a label to each node; an update submodule 9044, configured to update, for any node, a label of the node according to a label of a neighbor node of the node, where the neighbor node of the node represents a node connected to the node; the determining submodule 9045 is configured to determine, when the label of each node is stable, a category to which the content corresponding to each node belongs according to the label of each node.
In one possible implementation, the update submodule 9044 is configured to: and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
In one possible implementation, the apparatus further includes: a fourth determining module 905, configured to, for two contents whose correlations are related, determine a similarity between the two contents according to the number of times that the two contents appear adjacently in each content sequence and the number of times that the two contents appear in each content sequence respectively.
In one possible implementation, the update sub-module 9044 includes: the determining unit is used for determining the weight of an edge between nodes corresponding to two relevant contents according to the similarity between the two relevant contents; and the updating unit is used for updating the label of the node according to the label of the neighbor node of the node and the weight of the edge between the node and the neighbor node for any node.
In one possible implementation, the updating unit includes: a first determining subunit, configured to determine, for any one node, labels of neighbor nodes of the node as candidate labels, respectively; the second determining subunit is used for determining neighbor nodes corresponding to all candidate labels in the neighbor nodes of the node; the third determining subunit is used for determining the weight corresponding to each candidate label according to the sum of the weights of the edges between the neighbor node corresponding to each candidate label and the node; and the updating subunit is used for updating the label of the node according to the candidate label with the highest weight.
In one possible implementation, the apparatus further includes: a merging module 906, configured to merge the first category and the second category if the similarity of the content in the first category and the second category satisfies a first condition.
In one possible implementation, the apparatus further includes: a fifth determining module 907 for determining a first content number in an intersection of the first category and the second category; a sixth determining module 908 for determining a second number of contents in the union of the first category and the second category; a seventh determining module 909, configured to determine that the similarity of the content in the first category and the content in the second category satisfies the first condition if the ratio of the first content count to the second content count is greater than the first threshold; an eighth determining module 910, configured to determine that the similarity of the content in the first category and the content in the second category does not meet the first condition if a ratio of the first number of content to the second number of content is smaller than or equal to a first threshold.
In one possible implementation, the apparatus further includes: a deleting module 911, configured to delete the content that does not satisfy the second condition in each category.
In one possible implementation, the second condition includes: the click through rate of the content is less than a second threshold.
In the embodiment, by acquiring a plurality of groups of user behavior data, a content sequence corresponding to the user behavior data is respectively determined for each group of user behavior data, the correlation between the contents is determined according to the position relationship between the contents in the content sequence, and the category to which each content belongs is determined by adopting a label propagation algorithm according to the correlation between the contents, so that the content clustering can be automatically performed, the content clustering is not required to be performed manually, the manpower is saved, a large amount of contents are easy to cluster, the correlation between the contents can be better mined, and the accuracy of the content clustering is improved.
Fig. 11 is a block diagram illustrating an apparatus 1900 for content clustering according to an example embodiment. For example, the apparatus 1900 may be provided as a server. Referring to FIG. 11, the device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by the processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.
The device 1900 may also include a power component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input/output (I/O) interface 1958. The device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the apparatus 1900 to perform the above-described methods.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart 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 instructions, which comprises one or more executable instructions for implementing the specified logical function(s). 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 and/or flowchart illustration, and combinations of blocks in the block diagrams and/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.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (20)
1. A method for clustering content, comprising:
acquiring a plurality of groups of user behavior data;
for each group of user behavior data, respectively determining a content sequence corresponding to the user behavior data;
determining the correlation among the contents according to the position relation among the contents in the content sequence;
establishing an undirected graph, and taking each content as a node in the undirected graph respectively;
if the correlation between the two contents is correlation, establishing an edge between nodes corresponding to the two contents;
respectively distributing labels for each node;
for any node, updating the label of the node according to the labels of the neighbor nodes of the node, wherein the neighbor nodes of the node represent the nodes connected with the node;
when the label of each node is stable, determining the category to which the content corresponding to each node belongs according to the label of each node;
before updating the label of the node, the method further comprises:
for two contents whose correlation is related, the similarity between the two contents is determined by equation 1, equation 2, or equation 3 according to the number of times C that the two contents adjacently appear in each content sequence and the numbers of times C1, C2 that the two contents respectively appear in each content sequence, where equation 1, equation 2, or equation 3 includes:
sim ═ C/(C1 × C2) -formula 1; sim ═ C/(C1+ C2) -formula 2; sim ═ C/(C1+ C2-C) -formula 3.
2. The method of claim 1, wherein determining the correlation between the contents according to the position relationship between the contents in the content sequence comprises:
determining a correlation between adjacent content in the sequence of content as a correlation.
3. The method of claim 1, wherein updating the label of any node according to the labels of the neighbor nodes of the node comprises:
and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
4. The method of claim 1, wherein updating the label of any node according to the labels of the neighbor nodes of the node comprises:
determining the weight of an edge between nodes corresponding to two contents according to the similarity between the two contents with the correlation;
for any node, updating the label of the node according to the label of the neighbor node of the node and the weight of the edge between the node and the neighbor node.
5. The method of claim 4, wherein for any node, updating the label of the node according to the labels of the neighboring nodes of the node and the weights of the edges between the node and the neighboring nodes comprises:
for any node, respectively determining the labels of the neighbor nodes of the node as candidate labels;
determining neighbor nodes corresponding to all candidate labels in neighbor nodes of the node;
determining the weight corresponding to each candidate label according to the sum of the weights of the edges between the neighbor node corresponding to each candidate label and the node;
and updating the label of the node according to the candidate label with the highest weight.
6. The method of claim 1, wherein after determining the category to which each content belongs, the method further comprises:
and if the similarity of the contents in the first category and the second category meets a first condition, combining the first category and the second category.
7. The method of claim 6, wherein after determining the category to which each content belongs, the method further comprises:
determining a first number of contents in an intersection of the first category and the second category;
determining a second number of contents in a union of the first category and the second category;
if the ratio of the first content number to the second content number is greater than a first threshold, determining that the similarity of the content in the first category and the content in the second category meets the first condition;
if the ratio of the first content number to the second content number is smaller than or equal to the first threshold, determining that the similarity of the content in the first category and the second category does not meet the first condition.
8. The method of claim 1, wherein after determining the category to which each content belongs, the method further comprises:
and deleting the contents which do not satisfy the second condition in each category.
9. The method of claim 8, wherein the second condition comprises: the click through rate of the content is less than a second threshold.
10. A content clustering apparatus, comprising:
the acquisition module is used for acquiring a plurality of groups of user behavior data;
the first determining module is used for respectively determining a content sequence corresponding to each group of user behavior data;
the second determining module is used for determining the correlation among the contents according to the position relation among the contents in the content sequence;
the first establishing submodule is used for establishing an undirected graph and respectively taking each content as a node in the undirected graph;
the second establishing submodule is used for establishing an edge between nodes corresponding to the two contents if the correlation between the two contents is correlation;
the distribution submodule is used for distributing labels to each node;
the updating submodule is used for updating the label of any node according to the label of the neighbor node of the node, wherein the neighbor node of the node represents the node connected with the node;
the determining submodule is used for determining the category of the content corresponding to each node according to the label of each node when the label of each node is stable;
a fourth determining module, configured to, for two contents whose correlation is related, determine, according to a number C of adjacent occurrences of the two contents in each content sequence and a number C1, C2 of occurrences of the two contents in each content sequence, a similarity between the two contents according to equation 1, equation 2, or equation 3, where equation 1, equation 2, or equation 3 includes:
sim ═ C/(C1 × C2) -formula 1; sim ═ C/(C1+ C2) -formula 2; sim ═ C/(C1+ C2-C) -formula 3.
11. The apparatus of claim 10, wherein the second determining module is configured to:
determining a correlation between adjacent content in the sequence of content as a correlation.
12. The apparatus of claim 10, wherein the update submodule is configured to:
and for any node, updating the label of the node according to the label with the maximum occurrence frequency in the labels of the neighbor nodes of the node.
13. The apparatus of claim 10, wherein the update submodule comprises:
the determining unit is used for determining the weight of an edge between nodes corresponding to two relevant contents according to the similarity between the two relevant contents;
and the updating unit is used for updating the label of the node according to the label of the neighbor node of the node and the weight of the edge between the node and the neighbor node for any node.
14. The apparatus of claim 13, wherein the updating unit comprises:
a first determining subunit, configured to determine, for any one node, labels of neighbor nodes of the node as candidate labels, respectively;
the second determining subunit is used for determining neighbor nodes corresponding to all candidate labels in the neighbor nodes of the node;
the third determining subunit is used for determining the weight corresponding to each candidate label according to the sum of the weights of the edges between the neighbor node corresponding to each candidate label and the node;
and the updating subunit is used for updating the label of the node according to the candidate label with the highest weight.
15. The apparatus of claim 10, further comprising:
and the merging module is used for merging the first category and the second category if the similarity of the contents in the first category and the second category meets a first condition.
16. The apparatus of claim 15, further comprising:
a fifth determining module, configured to determine a first content number in an intersection of the first category and the second category;
a sixth determining module, configured to determine a second content number in a union of the first category and the second category;
a seventh determining module, configured to determine that the similarity of the content in the first category and the content in the second category satisfies the first condition if a ratio of the first content count to the second content count is greater than a first threshold;
an eighth determining module, configured to determine that the similarity of the content in the first category and the content in the second category does not meet the first condition if a ratio of the first content count to the second content count is smaller than or equal to the first threshold.
17. The apparatus of claim 10, further comprising:
and the deleting module is used for deleting the contents which do not meet the second condition in each category.
18. The apparatus of claim 17, wherein the second condition comprises: the click through rate of the content is less than a second threshold.
19. A content clustering apparatus, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method of any one of claims 1 to 9.
20. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226492.4A CN110287977B (en) | 2018-03-19 | 2018-03-19 | Content clustering method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226492.4A CN110287977B (en) | 2018-03-19 | 2018-03-19 | Content clustering method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110287977A CN110287977A (en) | 2019-09-27 |
| CN110287977B true CN110287977B (en) | 2021-09-21 |
Family
ID=68001077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810226492.4A Active CN110287977B (en) | 2018-03-19 | 2018-03-19 | Content clustering method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110287977B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444387A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Video classification method and device, computer equipment and storage medium |
| CN111538837A (en) * | 2020-04-27 | 2020-08-14 | 北京同邦卓益科技有限公司 | Method and device for analyzing enterprise operation range information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254038A (en) * | 2011-08-11 | 2011-11-23 | 武汉安问科技发展有限责任公司 | System and method for analyzing network comment relevance |
| CN102768670A (en) * | 2012-05-31 | 2012-11-07 | 哈尔滨工程大学 | Webpage clustering method based on node property label propagation |
| CN103226470A (en) * | 2013-03-21 | 2013-07-31 | 北京神州绿盟信息安全科技股份有限公司 | Method and device for determining weighted value of check item based on BVS (benchmark verification system) |
| CN103577562A (en) * | 2013-10-24 | 2014-02-12 | 河海大学 | Multi-measurement time series similarity analysis method |
| CN104951505A (en) * | 2015-05-20 | 2015-09-30 | 中国科学院信息工程研究所 | Large-scale data clustering method based on graphic calculation technology |
| EP2980754A1 (en) * | 2014-07-28 | 2016-02-03 | Thomson Licensing | Method and apparatus for generating temporally consistent superpixels |
-
2018
- 2018-03-19 CN CN201810226492.4A patent/CN110287977B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254038A (en) * | 2011-08-11 | 2011-11-23 | 武汉安问科技发展有限责任公司 | System and method for analyzing network comment relevance |
| CN102768670A (en) * | 2012-05-31 | 2012-11-07 | 哈尔滨工程大学 | Webpage clustering method based on node property label propagation |
| CN103226470A (en) * | 2013-03-21 | 2013-07-31 | 北京神州绿盟信息安全科技股份有限公司 | Method and device for determining weighted value of check item based on BVS (benchmark verification system) |
| CN103577562A (en) * | 2013-10-24 | 2014-02-12 | 河海大学 | Multi-measurement time series similarity analysis method |
| EP2980754A1 (en) * | 2014-07-28 | 2016-02-03 | Thomson Licensing | Method and apparatus for generating temporally consistent superpixels |
| CN104951505A (en) * | 2015-05-20 | 2015-09-30 | 中国科学院信息工程研究所 | Large-scale data clustering method based on graphic calculation technology |
Non-Patent Citations (2)
| Title |
|---|
| 陈羽中 等.面向微博热点话题发现的多标签传播聚类方法研究.《模式识别与人工智能》.2015,第28卷(第1期), * |
| 韩玉想.基于聚类分析的标签传播半监督学习研究.《中国优秀硕士学位论文全文数据库 信息科技辑》.2013,(第3期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110287977A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10846052B2 (en) | Community discovery method, device, server and computer storage medium | |
| CN109871311B (en) | Method and device for recommending test cases | |
| CN110515968B (en) | Method and apparatus for outputting information | |
| CN107908662B (en) | Method and device for realizing search system | |
| CN110287977B (en) | Content clustering method and device | |
| CN115757400B (en) | Data table processing method, device, electronic equipment and computer readable medium | |
| CN112100489A (en) | Object recommendation method, device and computer storage medium | |
| CN112988753B (en) | Data searching method and device | |
| CN112115153A (en) | Data processing method, device, equipment and storage medium | |
| CN115205305A (en) | Instance segmentation model training method, instance segmentation method and device | |
| CN110781658A (en) | Resume analysis method and device, electronic equipment and storage medium | |
| CN113821249A (en) | Project development configuration method and device, electronic equipment and readable storage medium | |
| CN112364185A (en) | Method and device for determining characteristics of multimedia resource, electronic equipment and storage medium | |
| CN111177479A (en) | Method and device for acquiring feature vectors of nodes in relational network graph | |
| CN112801053B (en) | Video data processing method and device | |
| CN113365104B (en) | Video concentration method and device | |
| CN112035581B (en) | Model-based task processing method, device, equipment and medium | |
| CN110413603B (en) | Method and device for determining repeated data, electronic equipment and computer storage medium | |
| CN114780847A (en) | Object information processing and information pushing method, device and system | |
| CN109286823B (en) | Multimedia content acquisition method and device | |
| CN110309294B (en) | Content set label determination method and device | |
| CN108197961B (en) | User management method and device | |
| CN113760469A (en) | Distributed computing method and device | |
| CN108881953B (en) | Video encryption method and device | |
| CN105224617A (en) | Recommendation method, device and system for broadcast content |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200429 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant before: Youku network technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240617 Address after: 101400 Room 201, 9 Fengxiang East Street, Yangsong Town, Huairou District, Beijing Patentee after: Youku Culture Technology (Beijing) Co.,Ltd. Country or region after: China Address before: 310052 room 508, 5th floor, building 4, No. 699 Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Patentee before: Alibaba (China) Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |