CN113421172A - Policy information pushing method and device - Google Patents
Policy information pushing method and device Download PDFInfo
- Publication number
- CN113421172A CN113421172A CN202110776594.5A CN202110776594A CN113421172A CN 113421172 A CN113421172 A CN 113421172A CN 202110776594 A CN202110776594 A CN 202110776594A CN 113421172 A CN113421172 A CN 113421172A
- Authority
- CN
- China
- Prior art keywords
- policy
- enterprise
- portrait
- calculating
- matrix
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims abstract description 65
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for pushing policy information, which generate a policy portrait according to policy data and calculate a similar matrix according to the policy portrait; acquiring an enterprise data calculation scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix; the policy information is pushed according to the similarity matrix and the enterprise portrait, manual intervention is not needed through the automatically generated policy portrait and the enterprise portrait, the labor cost is reduced, the accuracy of policy pushing is improved, a hot recommendation set is obtained through the similarity matrix, the current recommended content is guaranteed to be in accordance with the hot direction at the moment, hot policies cannot be omitted, the comprehensiveness is high, the policy recommendation set of the enterprise is obtained through calculation based on a user and a collaborative filtering model based on articles, the interest points of the enterprise can be better reflected, and the problem that only clicking events are relied on in traditional click rate estimation is solved through a scoring matrix, so that the policy recommendation scene can be better conformed.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a policy information pushing method and device.
Background
The policy information service is used as a key ring in various park services of cloud industry park projects, and convenient services such as retrieval, pushing, matching and subscription of policy information are provided for park resident enterprises. In the conventional policy information service, a platform administrator of a campus manually sets a policy classification tag library based on past expert experience. When a new enterprise is in the park area, the enterprise administrator selects the interested policy label from the policy classification label library according to the operation range of the enterprise. When a new enterprise-facilitating policy is issued, the platform administrator classifies the policy of the new enterprise-facilitating policy by using the policy classification label library. The platform pushes related enterprise-benefitting policies to the enterprises by matching the enterprise interest tags with the classification tags of the policies, and the enterprises make corresponding policy declaration according to the pushed information. Through the propelling movement of the enterprise-facilitating policy, the business can acquire the latest and suitable policy information in real time, the channel for acquiring the policy information by the enterprise is increased, and various subsidies such as corresponding tax exemption, talent discount and the like are acquired through the enterprise-facilitating policy, so that the capital pressure of enterprise operation is reduced, the benign development of the enterprise is ensured, however, the traditional policy propelling movement has the following defects:
disadvantage 1: when a new policy is issued, classification and labeling of policy labels are manually carried out, workload of a platform administrator is increased, and label classification of the policy is mainly based on experience and cannot be guaranteed in accuracy.
And (2) disadvantage: enterprises in the park subscribe in a policy subscription mode by manually setting interest tags, so that actual interest points of the enterprises cannot be mined.
Disadvantage 3: in the process of matching aiming at the enterprise policy, the similar labels are simply used for matching the enterprise and the policy, and the matching effect is not ideal.
Disadvantage 4: the change of the attention points of the policy every year is large, and the fixed enterprise interest tags cannot mine the current hot policy.
Therefore, a method and an apparatus for pushing policy information are needed, which can improve the accuracy and comprehensiveness of policy pushing.
Disclosure of Invention
Technical problem to be solved
In order to solve the above problems in the prior art, the present invention provides a method and an apparatus for pushing policy information, which can improve the accuracy and comprehensiveness of policy pushing.
(II) technical scheme
In order to achieve the purpose, the invention adopts a technical scheme that:
a policy information pushing method comprises the following steps:
s1, generating a policy portrait according to the policy data, and calculating to obtain a similar matrix according to the policy portrait;
s2, acquiring enterprise data, calculating a scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
and S3, pushing policy information according to the similarity matrix and the enterprise portrait.
In order to achieve the purpose, the invention adopts another technical scheme as follows:
a policy information pushing apparatus comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
s1, generating a policy portrait according to the policy data, and calculating to obtain a similar matrix according to the policy portrait;
s2, acquiring enterprise data, calculating a scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
and S3, pushing policy information according to the similarity matrix and the enterprise portrait.
(III) advantageous effects
The invention has the beneficial effects that: generating a policy portrait according to policy data, and calculating to obtain a similar matrix according to the policy portrait; acquiring an enterprise data calculation scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix; the policy information is pushed according to the similarity matrix and the enterprise portrait, manual intervention is not needed through the automatically generated policy portrait and the enterprise portrait, the labor cost is reduced, the accuracy of policy pushing is improved, a hot recommendation set is obtained through the similarity matrix, the current recommended content is guaranteed to be in accordance with the hot direction at the moment, hot policies cannot be omitted, the comprehensiveness is high, the policy recommendation set of the enterprise is obtained through calculation based on a user and a collaborative filtering model based on articles, the interest points of the enterprise can be better reflected, and the problem that only clicking events are relied on in traditional click rate estimation is solved through a scoring matrix, so that the policy recommendation scene can be better conformed.
Drawings
FIG. 1 is a flowchart illustrating a policy information pushing method according to an embodiment of the present invention;
fig. 2 is a schematic overall structure diagram of a policy information pushing apparatus according to an embodiment of the present invention;
FIG. 3 is a time decay function of an embodiment of the present invention.
[ description of reference ]
1: a policy information pushing device;
2: a memory;
3: a processor.
Detailed Description
For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, a method for pushing policy information includes the steps of:
s1, generating a policy portrait according to the policy data, and calculating to obtain a similar matrix according to the policy portrait;
step S1 specifically includes:
s11, segmenting policy data, and respectively calculating keywords of each policy by using textrank and tfidf to obtain a basic vector model and a middle model generated after tifidf calculation;
s12, taking keywords appearing in textrank and tfidf as subject words of the policy, and constructing the keywords and the subject words to obtain a dynamic policy portrait;
s13, training national standard industries, policy categories, regions and implementation departments in the policy data through a word2vec model according to the intermediate model to obtain a trained word2vec model;
s14, calculating a word vector model of each policy according to the dynamic policy portrait and the trained word2vec model, and taking an average word vector of the word vector model as a policy vector;
and S15, calculating the Euclidean distance of all policy vectors pairwise to serve as the similarity among different policies, and obtaining a policy similarity matrix.
S2, acquiring enterprise data, calculating a scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
the step S2 of calculating the scoring matrix specifically includes:
and calculating a scoring matrix according to policy clicking, policy reading, policy attachment downloading and policy application data in the enterprise data.
In step S2, generating an enterprise sketch according to the scoring matrix specifically includes:
calculating to obtain a policy recommendation set of the enterprise according to the scoring matrix through a collaborative filtering model based on the user and the article;
and according to the policy recommendation set and the dynamic policy representation, performing correlation calculation to obtain keywords and subject words combined by the recommended policies of each enterprise, and taking the keywords and the subject words as the enterprise representation.
And S3, pushing policy information according to the similarity matrix and the enterprise portrait.
Step S3 specifically includes:
s31, calculating according to the scoring matrix to obtain a popular recommendation set;
s32, obtaining the latest policy information set according to the policy recommendation set and the hot recommendation set and through a time reverse order, and merging to obtain a merged recommendation set;
and S33, carrying out policy information pushing on the merged recommendation set, the similar matrix and the enterprise portrait.
Example two
The difference between this embodiment and the first embodiment is that this embodiment will further explain how the policy information pushing method of the present invention is implemented in combination with a specific application scenario:
1. the method comprises the steps of building a big data basic platform, wherein a CDP platform of Cloudera is mainly adopted to deploy a big data cluster, the cluster comprises three servers, and the main deployed product services comprise Hadoop, Hive, Hbase, Spark, Sqoop and Kafka. The big data cluster is used as a basic service platform and mainly provides a bottom layer for subsequent various data processing and model training.
2. The method comprises the steps of enterprise behavior data embedded point design and collection, wherein dynamic portraits in enterprise portraits need to be collected, and the collection mainly comprises the following events: policy clicking, policy reading, policy attachment downloading, policy applying and policy recommending data. The collected data are stored in a big data cluster Hive to prepare for subsequent analysis
3. Generating a policy portrait according to policy data, and calculating to obtain a similar matrix according to the policy portrait, specifically:
3.1, segmenting the policy data, and respectively calculating the keywords of each policy by adopting textrank and tfidf to obtain a basic vector model and an intermediate model generated after tifidf calculation, wherein the intermediate model generated after tifidf calculation is stored in the HDFS;
3.2, using keywords appearing in both textrank and tfidf as subject words of the policy, constructing the keywords and the subject words to obtain a dynamic policy portrait, and storing the dynamic policy portrait in Hive;
3.3, training national standard industries, policy categories, regions and implementation departments in the policy data through a word2vec model according to the intermediate model to obtain a trained word2vec model;
3.4, calculating to obtain a word vector model of each policy according to the dynamic policy portrait and the trained word2vec model, and taking an average word vector of the word vector model as a policy vector;
and 3.5, calculating the Euclidean distances of all policy vectors pairwise to serve as the similarity among different policies, obtaining a policy similarity matrix, and reserving 20 highest in similarity of each policy to be stored in Hbase.
4. Acquiring an enterprise data calculation scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
the step 4 of calculating the scoring matrix specifically comprises the following steps:
and calculating a scoring matrix according to policy clicking, policy reading, policy attachment downloading and policy application data in the enterprise data.
Specifically, since no historical data is used for supervised training, the selection of key features and weights cannot be performed, the setting is performed by adopting expert experience, the policy click event is 1 point, the policy reading (the reading time is greater than a threshold value) event is 2 points, the downloading event is 4 points, the applying event is 8 points, and each policy keeps the operation time of the last event. Considering that the score of the event is about to be the end of the month earlier than the current time, a time decay function 1/(log (t +1) +1) about the date is added, t is the difference between the current date and the event date, and the calculated score is multiplied by the decay function to obtain a final enterprise-policy score matrix which is stored in Hbase. The overall scoring formula is: time decay function (whether there is download, download event weight + whether there is click, click event weight + whether there is application, application event weight + whether there is reading, reading event weight). The time decay function is shown in fig. 3, the horizontal axis represents the date difference, the vertical axis represents the decay coefficient, and it can be seen that the time does not decay in the current day, and the time also basically remains between 0.4 and 0.5 after the interval date is increased.
Generating the enterprise portrait according to the scoring matrix in the step 4 specifically comprises the following steps:
calculating to obtain a policy recommendation set of the enterprise according to the scoring matrix through a collaborative filtering model based on the user and the article, and reserving 20 policy recommendation sets to be stored in the Hbase;
and according to the policy recommendation set and the dynamic policy portrait, performing correlation calculation to obtain keywords and subject words combined by recommended policies of each enterprise, and storing the keywords and the subject words as the enterprise portrait in Hbase.
5. And carrying out policy information pushing according to the similar matrix and the enterprise portrait.
The step 5 specifically comprises the following steps:
5.1, calculating according to the scoring matrix to obtain a hot recommendation set, and storing 30 policy information with the highest total score as a current hot policy into Redis;
5.2, obtaining the latest policy information set according to the policy recommendation set and the hot recommendation set and through a time reverse order, and merging to obtain a merged recommendation set;
and 5.3, carrying out policy information pushing on the merged recommendation set, the similar matrix and the enterprise portrait.
EXAMPLE III
Referring to fig. 2, a policy information pushing apparatus 1 includes a memory 2, a processor 3, and a computer program stored on the memory 2 and executable on the processor 3, wherein the processor 3 implements the steps of the first embodiment when executing the computer program.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (10)
1. A policy information pushing method is characterized by comprising the following steps:
s1, generating a policy portrait according to the policy data, and calculating to obtain a similar matrix according to the policy portrait;
s2, acquiring enterprise data, calculating a scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
and S3, pushing policy information according to the similarity matrix and the enterprise portrait.
2. The method for pushing policy information according to claim 1, wherein step S1 specifically comprises:
s11, segmenting policy data, and respectively calculating keywords of each policy by using textrank and tfidf to obtain a basic vector model and a middle model generated after tifidf calculation;
s12, taking keywords appearing in textrank and tfidf as subject words of the policy, and constructing the keywords and the subject words to obtain a dynamic policy portrait;
s13, training national standard industries, policy categories, regions and implementation departments in the policy data through a word2vec model according to the intermediate model to obtain a trained word2vec model;
s14, calculating a word vector model of each policy according to the dynamic policy portrait and the trained word2vec model, and taking an average word vector of the word vector model as a policy vector;
and S15, calculating the Euclidean distance of all policy vectors pairwise to serve as the similarity among different policies, and obtaining a policy similarity matrix.
3. The method for pushing policy information according to claim 1, wherein the step S2 of calculating the score matrix specifically comprises:
and calculating a scoring matrix according to policy clicking, policy reading, policy attachment downloading and policy application data in the enterprise data.
4. The method for pushing policy information according to claim 2, wherein the step S2 of generating an enterprise image according to the rating matrix includes:
calculating to obtain a policy recommendation set of the enterprise according to the scoring matrix through a collaborative filtering model based on the user and the article;
and according to the policy recommendation set and the dynamic policy representation, performing correlation calculation to obtain keywords and subject words combined by the recommended policies of each enterprise, and taking the keywords and the subject words as the enterprise representation.
5. The method for pushing policy information according to claim 4, wherein step S3 specifically comprises:
s31, calculating according to the scoring matrix to obtain a popular recommendation set;
s32, obtaining the latest policy information set according to the policy recommendation set and the hot recommendation set and through a time reverse order, and merging to obtain a merged recommendation set;
and S33, carrying out policy information pushing on the merged recommendation set, the similar matrix and the enterprise portrait.
6. A policy information pushing apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of:
s1, generating a policy portrait according to the policy data, and calculating to obtain a similar matrix according to the policy portrait;
s2, acquiring enterprise data, calculating a scoring matrix, and generating a corresponding enterprise portrait according to the scoring matrix;
and S3, pushing policy information according to the similarity matrix and the enterprise portrait.
7. The policy information pushing apparatus according to claim 6, wherein step S1 specifically comprises:
s11, segmenting policy data, and respectively calculating keywords of each policy by using textrank and tfidf to obtain a basic vector model and a middle model generated after tifidf calculation;
s12, taking keywords appearing in textrank and tfidf as subject words of the policy, and constructing the keywords and the subject words to obtain a dynamic policy portrait;
s13, training national standard industries, policy categories, regions and implementation departments in the policy data through a word2vec model according to the intermediate model to obtain a trained word2vec model;
s14, calculating a word vector model of each policy according to the dynamic policy portrait and the trained word2vec model, and taking an average word vector of the word vector model as a policy vector;
and S15, calculating the Euclidean distance of all policy vectors pairwise to serve as the similarity among different policies, and obtaining a policy similarity matrix.
8. The policy information pushing apparatus according to claim 6, wherein the step S2 of calculating the score matrix specifically comprises:
and calculating a scoring matrix according to policy clicking, policy reading, policy attachment downloading and policy application data in the enterprise data.
9. The policy information pushing apparatus according to claim 7, wherein the step S2 of generating an enterprise image based on the scoring matrix includes:
calculating to obtain a policy recommendation set of the enterprise according to the scoring matrix through a collaborative filtering model based on the user and the article;
and according to the policy recommendation set and the dynamic policy representation, performing correlation calculation to obtain keywords and subject words combined by the recommended policies of each enterprise, and taking the keywords and the subject words as the enterprise representation.
10. The policy information pushing apparatus according to claim 9, wherein step S3 specifically comprises:
s31, calculating according to the scoring matrix to obtain a popular recommendation set;
s32, obtaining the latest policy information set according to the policy recommendation set and the hot recommendation set and through a time reverse order, and merging to obtain a merged recommendation set;
and S33, carrying out policy information pushing on the merged recommendation set, the similar matrix and the enterprise portrait.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110776594.5A CN113421172B (en) | 2021-07-09 | 2021-07-09 | Policy information pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110776594.5A CN113421172B (en) | 2021-07-09 | 2021-07-09 | Policy information pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113421172A true CN113421172A (en) | 2021-09-21 |
| CN113421172B CN113421172B (en) | 2022-04-05 |
Family
ID=77720720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110776594.5A Active CN113421172B (en) | 2021-07-09 | 2021-07-09 | Policy information pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421172B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842272A (en) * | 2023-08-29 | 2023-10-03 | 四川邕合科技有限公司 | Policy information pushing method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, server and storage medium |
| CN109447762A (en) * | 2018-11-12 | 2019-03-08 | 深圳市喂车科技有限公司 | Method of Commodity Recommendation and its device, server, commercial product recommending system |
| CN110532431A (en) * | 2019-07-23 | 2019-12-03 | 平安科技（深圳）有限公司 | Short-sighted frequency keyword extracting method, device and storage medium |
| CN111815421A (en) * | 2019-04-09 | 2020-10-23 | 百度在线网络技术（北京）有限公司 | Tax policy processing method and device, terminal equipment and storage medium |
| CN111899075A (en) * | 2020-08-11 | 2020-11-06 | 恒瑞通（福建）信息技术有限公司 | Personalized commodity recommendation method and device based on user behaviors |
| CN112184525A (en) * | 2020-09-28 | 2021-01-05 | 上海市浦东新区行政服务中心(上海市浦东新区市民中心) | System and method for realizing intelligent matching recommendation through natural semantic analysis |
-
2021
- 2021-07-09 CN CN202110776594.5A patent/CN113421172B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, server and storage medium |
| CN109447762A (en) * | 2018-11-12 | 2019-03-08 | 深圳市喂车科技有限公司 | Method of Commodity Recommendation and its device, server, commercial product recommending system |
| CN111815421A (en) * | 2019-04-09 | 2020-10-23 | 百度在线网络技术（北京）有限公司 | Tax policy processing method and device, terminal equipment and storage medium |
| CN110532431A (en) * | 2019-07-23 | 2019-12-03 | 平安科技（深圳）有限公司 | Short-sighted frequency keyword extracting method, device and storage medium |
| CN111899075A (en) * | 2020-08-11 | 2020-11-06 | 恒瑞通（福建）信息技术有限公司 | Personalized commodity recommendation method and device based on user behaviors |
| CN112184525A (en) * | 2020-09-28 | 2021-01-05 | 上海市浦东新区行政服务中心(上海市浦东新区市民中心) | System and method for realizing intelligent matching recommendation through natural semantic analysis |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116842272A (en) * | 2023-08-29 | 2023-10-03 | 四川邕合科技有限公司 | Policy information pushing method, device, equipment and storage medium |
| CN116842272B (en) * | 2023-08-29 | 2023-11-03 | 四川邕合科技有限公司 | Policy information pushing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113421172B (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10592769B2 (en) | Searching for images by video | |
| CN107229708B (en) | Personalized travel service big data application system and method | |
| CN111259263B (en) | Article recommendation method and device, computer equipment and storage medium | |
| CN102483745B (en) | Co-selected image classification | |
| CN105160545B (en) | Method and device for determining release information style | |
| CN111159341B (en) | Information recommendation method and device based on user investment and financial management preference | |
| CN103942337A (en) | Video search system based on image recognition and matching | |
| CN103988202A (en) | Image attractiveness based indexing and searching | |
| CN109389423A (en) | A kind of marketing application method based on big data fusion business | |
| CN111639988B (en) | Broker recommendation method, device, electronic equipment and storage medium | |
| US20220172476A1 (en) | Video similarity detection method, apparatus, and device | |
| CN105005982B (en) | Image procossing including Object Selection | |
| CN105183739B (en) | Image processing method | |
| CN110413888A (en) | A kind of books recommended method and device | |
| CN113657087A (en) | Information matching method and device | |
| CN113191896A (en) | Recommendation method and device for bidding information and computer equipment | |
| CN113421172B (en) | Policy information pushing method and device | |
| CN112989213A (en) | Content recommendation method, device and system, electronic equipment and storage medium | |
| CN116823410B (en) | Data processing method, object processing method, recommending method and computing device | |
| CN112330426A (en) | Product recommendation method, device and storage medium | |
| CN109146606A (en) | A kind of brand recommended method, electronic equipment, storage medium and system | |
| CN112115354A (en) | Information processing method, information processing apparatus, server, and storage medium | |
| CN113946753B (en) | Service recommendation method, device, equipment and storage medium based on location fence | |
| US20230004595A1 (en) | Image retrieval method, image retrieval devices, image retrieval system and image display system | |
| WO2015009767A1 (en) | Determining a likelihood and degree of derivation among media content items |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |