CN113343046A - Intelligent search sequencing system - Google Patents
Intelligent search sequencing system Download PDFInfo
- Publication number
- CN113343046A CN113343046A CN202110560938.9A CN202110560938A CN113343046A CN 113343046 A CN113343046 A CN 113343046A CN 202110560938 A CN202110560938 A CN 202110560938A CN 113343046 A CN113343046 A CN 113343046A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- field
- service
- correlation
- business
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses an intelligent search sequencing system, which develops a correlation analysis module, a sequencing algorithm module and a service integration module on a search engine; the correlation analysis module comprises a correlation algorithm unit and a mixed recall analysis unit; the correlation algorithm unit comprises a tf-idf algorithm and a field customization algorithm which is irrelevant to the field length factor and is customized in weight; the sequencing algorithm module comprises an attenuation algorithm, a normalization algorithm and a dynamic score; the service integration module comprises service field weight and service parameter input. Besides the traditional tf-idf algorithm, a correlation algorithm is self-established, the correlation analysis scene of diversified service fields is met, the service field normalization processing is introduced, and the high-reliability sequencing of more complex service scenes can be adapted; the dynamic mixed scoring function during the running of the multi-service fields is supported, and the operation and maintenance cost of the human data is reduced; and mixed sequencing of different weights of multiple service fields is supported, and the searching efficiency and the quality of recall results are improved.
Description
Technical Field
The invention belongs to the technical field of intelligent search sequencing, is used for meeting rooms, and relates to an intelligent search sequencing system.
Background
In a traditional search ranking scenario, a user would enter a keyword search. As shown in fig. 3, the search engine uses the keywords to search the database for relevant records according to the preset query field and the single matching algorithm. After the relevant records are hit, sorting is completed through the sorting field pre-stored in the row. The traditional text correlation algorithm cannot meet the analysis scenes of various service fields.
According to analysis, the existing search scheme has the following objective disadvantages:
the traditional text correlation algorithm cannot meet the analysis scenes of various service fields. At present, the mainstream text correlation algorithm is tf-idf algorithm, and the text is analyzed by analyzing the word frequency and the reverse file frequency in the text to hit the related records. In the inverse file frequency analysis algorithm, the field length can be used as an important factor to participate in operation, and the longer the field is, the weaker the correlation degree is. In a specific service scenario, different fields usually require different correlation algorithms, such as: for the title and text field of an article, when searching for keywords, the word frequency and the field length of the keywords need to be concerned. If the keywords appear more frequently and the field lengths are shorter (tf-idf considers shorter and more important), the more relevant the document is; this conforms to the default definition of the tf-idf algorithm. And for some other fields, such as: the user name, or the label of the document, the developing department of the hospital, etc. should not be influenced by the field length, and once the search word is hit, the search word is considered to have the same weight. Therefore, in an actual business scenario, different correlation algorithms need to be used for different fields in one search, and the comprehensive correlation score is calculated, and finally the record is recalled.
The traditional search engine cannot deal with the problem of normalization, so that the mixing and sorting of different types of data are difficult. In a common search scenario, one or more fields are designated, and sorting is performed according to the size of the field values. Even the same field in the actual service is not suitable for sorting by using a uniform standard. For example, the employee form may have a "performance" field, although the employee sales ranking may be obtained by directly sorting through this field. However, companies generally develop in different areas in different situations, and simply rely on the 'performance' field sorting, so that a good result cannot be obtained. The better mode is as follows: and counting and calculating the highest sales value of each area, and carrying out normalization operation on the current recorded value to obtain the employee sales ranking of each area.
Conventional search schemes typically do not consider multi-service field runtime dynamic hybrid scoring functionality. In a general search scenario, the rank field is typically pre-computed to be stored in the field. However, as traffic changes, the need to adjust the ranking algorithm often arises. If a scheme of pre-operation is adopted, the sorting value needs to be re-operated every time the sorting rule changes, and the database is updated, which consumes a large labor cost. If the sorting value is operated through the service field each time, for the traditional relational database, the performance problem can become a great obstacle due to the fact that a relatively complex score algorithm is involved and the number of operation factors is large.
Disclosure of Invention
The invention aims to: an intelligent search ranking system is provided that solves one or more of the problems set forth in the background.
The technical scheme adopted by the invention is as follows:
an intelligent search ordering system, which develops a correlation analysis module, an ordering algorithm module and a service integration module on a search engine;
the correlation analysis module comprises a correlation algorithm unit and a mixed recall analysis unit; the correlation algorithm unit comprises a tf-idf algorithm and a field customization algorithm irrelevant to field length factors and customized by weight, the search keywords are recorded and recalled on different fields through the preconfigured tf-idf algorithm or the field customization algorithm, and comprehensive operation is performed through a mixed recall analysis unit;
the sequencing algorithm module comprises an attenuation algorithm, a normalization algorithm and a dynamic score; the dynamic score calculation method comprises the steps that attenuation calculation is carried out on a business entity through an attenuation algorithm, the normalization algorithm is used for normalization calculation to obtain a final ranking value, each factor is read during operation according to a business field, a built-in function and a script are called, and a final score value is obtained through calculation;
the service integration module comprises service field weight and service parameter input; the business field weight endows different business fields with different calculation weights, the business parameter input is used for inputting different business parameters under different business scenes, and the business parameters are substituted into a search script during search execution to carry out dynamic condition query.
Further, the field customization algorithm is as follows:
in the formula, score (q, d) is a correlation score function, wherein q is a query statement, d is a matched document, t is each word after the query statement is segmented, a defaultNorm parameter is a normalization factor after the technology is adjusted and optimized according to actual services and by integrating the effect of an ElasticSearch default tf-idf algorithm, boost (q) is a service weight when the correlation is calculated for a specific field, N (d) is a field frequency evaluation function, n (t, d) is a segmentation frequency evaluation function, freq (t, d) is a document segmentation frequency evaluation function, and a k1 parameter is a segmentation saturation constant.
Further, for different traffic fields, a correlation analysis algorithm is specified when defined by the table structure.
Further, the decay algorithm includes a gaussian decay function, a linear decay function, and an exponential decay function.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
the intelligent search sequencing system disclosed by the invention has the advantages that besides the traditional tf-idf algorithm, a correlation algorithm is self-established, the correlation analysis scene of diversified service fields is met, the service field normalization processing is introduced, and the high-reliability sequencing of more complex service scenes can be adapted; the dynamic mixed scoring function during the running of the multi-service fields is supported, the operation and maintenance cost of the human data is reduced, the change cost of the sorting algorithm is lower, and the sorting algorithm can adapt to the market change more quickly; based on the secondary development of a search engine, a high-efficiency and high-performance search solution is provided; and diversified algorithms such as a normalization algorithm, an attenuation function algorithm and the like are provided, mixed sequencing of different weights of multiple service fields is supported, and the search efficiency and the quality of a recall result are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that for those skilled in the art, other relevant drawings can be obtained according to the drawings without inventive effort, wherein:
FIG. 1 is a block diagram of a framework for an intelligent search ranking system of the present invention;
FIG. 2 is a data flow diagram of an intelligent search ranking system of the present invention;
fig. 3 is a prior art search engine data flow diagram.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Examples
As shown in fig. 1, in the intelligent search ranking system provided in the preferred embodiment of the present invention, a correlation analysis module, a ranking algorithm module, and a service integration module are developed on a search engine;
the correlation analysis module comprises a correlation algorithm unit and a mixed recall analysis unit; the correlation algorithm unit comprises a tf-idf algorithm and a field customization algorithm irrelevant to field length factors and customized by weight, the search keywords are recorded and recalled on different fields through the preconfigured tf-idf algorithm or the field customization algorithm, and comprehensive operation is performed through a mixed recall analysis unit;
the sequencing algorithm module comprises an attenuation algorithm, a normalization algorithm and a dynamic score; the dynamic score calculation method comprises the steps that attenuation calculation is carried out on a business entity through an attenuation algorithm, the normalization algorithm is used for normalization calculation to obtain a final ranking value, each factor is read during operation according to a business field, a built-in function and a script are called, and a final score value is obtained through calculation;
the service integration module comprises service field weight and service parameter input; the business field weight endows different business fields with different calculation weights, the business parameter input is used for inputting different business parameters under different business scenes, and the business parameters are substituted into a search script during search execution to carry out dynamic condition query.
The present invention is illustrated, as shown in FIG. 2, in the following steps:
s1, inputting query keywords by a user: "Zhang";
s2, the search engine inquires all records related to the page characters;
s3, operating a native tf-idf algorithm analysis on the 'city' field by a search engine according to the table structure pre-configuration of the service field to obtain a correlation score 1; for the name field, because the name field is insensitive to the field length, a primary tf-idf algorithm is not suitable to be used, and a field customization algorithm which does not analyze the field length is used instead to obtain a relevance score 2; calculating to obtain a final relevance score through a specified algorithm, and determining a basic recall result set;
s4, acquiring a normalization operation parameter for the recall result set based on the region of the employee in the total performance field, performing normalization operation, and performing Gaussian attenuation operation on the normalization operation result to finally obtain a weight 1; the 'business ring ratio change' field and the 'passenger order' field of the staff can obtain the weight 2 and the weight 3 through the operation of a specific business script; finally, the final weighting is obtained by weighting each weight, and the final ranking score is obtained by multiplying the weighting by the correlation score calculated in step S3.
And S5, returning a final query sorting result for the user according to the sorting scores.
Specifically, the field customization algorithm is as follows:
in the formula, score (q, d) is a correlation score function, wherein q is a query statement, d is a matched document, t is each word after the query statement is segmented, a defaultNorm parameter is a normalization factor after the technology is adjusted and optimized according to actual services and by integrating the effect of an ElasticSearch default tf-idf algorithm, boost (q) is a service weight when the correlation is calculated for a specific field, N (d) is a field frequency evaluation function, n (t, d) is a segmentation frequency evaluation function, freq (t, d) is a document segmentation frequency evaluation function, and a k1 parameter is a segmentation saturation constant.
In this embodiment, in an actual service scenario, when searching for the "name" field of the "employee" table, the correlation thereof should not be affected by the field length, and once a search word is hit, the search word is considered to have the same weight. Such as: the search for "Zhang" surname man-hour, "Zhang three" and "Zhang three Feng" should have the same relevance score, and should not be affected by the length of their names. The correlation algorithm can be used, the algorithm efficiency is improved, and the intervention of irrelevant factors is reduced. Similarly for some other enumerated, array fields, such as: the technology also generally uses the algorithm to carry out correlation score independent of the field length.
In this embodiment, score (q, d) is a relevance score function, where q is a query statement, d is a matched document, and for each word t after the query statement is segmented, its score is calculated respectively, and the relevance scores score of the specified field of the current document is obtained by merging (e.g., summing, weighting, and maximum). The defaultNorm parameter is a normalization factor which is adjusted and optimized according to actual services and by integrating the effect of an ElasticSearch default tf-idf algorithm, and the default value is 2.2; after adding this parameter, the scores calculated by the different correlation algorithms are normalized and a mixing operation and comparison can be performed. boost (q) calculates the traffic weight for a particular field when calculating the correlation. In the service scene, different service fields have different searching important programs, and control can be dynamically transmitted according to the value. N (d) is a field frequency evaluation function, and is calculated by the formula: the table contains the number of documents for this field. n (t, d) is a word segmentation frequency evaluation function and is calculated by the formula: the table contains the number of documents for the current participle. freq (t, d) is a document word segmentation frequency evaluation function, and is calculated by the formula: the frequency of occurrence of the current participle in the current document. The k1 parameter is a participle saturation constant, and the default value is 1.2.
Preferably, the correlation analysis algorithm is specified when defined by the table structure for different traffic fields.
Specifically, the attenuation algorithm includes a gaussian attenuation function, a linear attenuation function, and an exponential attenuation function.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, and any modifications, equivalents and improvements made by those skilled in the art within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. An intelligent search ranking system, characterized by: developing a correlation analysis module, a sequencing algorithm module and a service integration module on a search engine;
the correlation analysis module comprises a correlation algorithm unit and a mixed recall analysis unit; the correlation algorithm unit comprises a tf-idf algorithm and a field customization algorithm irrelevant to field length factors and customized by weight, the search keywords are recorded and recalled on different fields through the preconfigured tf-idf algorithm or the field customization algorithm, and comprehensive operation is performed through a mixed recall analysis unit;
the sequencing algorithm module comprises an attenuation algorithm, a normalization algorithm and a dynamic score; the dynamic score calculation method comprises the steps that attenuation calculation is carried out on a business entity through an attenuation algorithm, the normalization algorithm is used for normalization calculation to obtain a final ranking value, each factor is read during operation according to a business field, a built-in function and a script are called, and a final score value is obtained through calculation;
the service integration module comprises service field weight and service parameter input; the business field weight endows different business fields with different calculation weights, the business parameter input is used for inputting different business parameters under different business scenes, and the business parameters are substituted into a search script during search execution to carry out dynamic condition query.
2. The intelligent search ranking system of claim 1 wherein: the field customization algorithm is as follows:
in the formula, score (q, d) is a correlation score function, wherein q is a query statement, d is a matched document, t is each word after the query statement is segmented, a defaultNorm parameter is a normalization factor after the technology is adjusted and optimized according to actual services and by integrating the effect of an ElasticSearch default tf-idf algorithm, boost (q) is a service weight when the correlation is calculated for a specific field, N (d) is a field frequency evaluation function, n (t, d) is a segmentation frequency evaluation function, freq (t, d) is a document segmentation frequency evaluation function, and a k1 parameter is a segmentation saturation constant.
3. The intelligent search ranking system of claim 1 wherein: the correlation analysis algorithm is specified when defined by the table structure for different traffic fields.
4. The intelligent search ranking system of claim 1 wherein: the attenuation algorithm includes a gaussian attenuation function, a linear attenuation function, and an exponential attenuation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560938.9A CN113343046B (en) | 2021-05-20 | 2021-05-20 | Intelligent search ordering system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560938.9A CN113343046B (en) | 2021-05-20 | 2021-05-20 | Intelligent search ordering system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113343046A true CN113343046A (en) | 2021-09-03 |
| CN113343046B CN113343046B (en) | 2023-08-25 |
Family
ID=77470901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110560938.9A Active CN113343046B (en) | 2021-05-20 | 2021-05-20 | Intelligent search ordering system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113343046B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116738065A (en) * | 2023-08-15 | 2023-09-12 | 浙江同信企业征信服务有限公司 | Enterprise searching method, device, equipment and storage medium |
Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8145636B1 (en) * | 2009-03-13 | 2012-03-27 | Google Inc. | Classifying text into hierarchical categories |
| CN102662959A (en) * | 2012-03-07 | 2012-09-12 | 南京邮电大学 | Method for detecting phishing web pages with spatial mixed index mechanism |
| CN103092844A (en) * | 2011-10-28 | 2013-05-08 | 腾讯科技（深圳）有限公司 | Index creating method, index creating system, searching method and searching system |
| CN103116582A (en) * | 2011-11-16 | 2013-05-22 | 阿里巴巴集团控股有限公司 | Information retrieval method and relevant system and device |
| CN103365915A (en) * | 2012-04-10 | 2013-10-23 | 北京易盟天地信息技术有限公司 | Search result ranking method based on search engine and database query system |
| CN103365870A (en) * | 2012-03-29 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Method and system for sorting search results |
| US20140201126A1 (en) * | 2012-09-15 | 2014-07-17 | Lotfi A. Zadeh | Methods and Systems for Applications for Z-numbers |
| CN104063523A (en) * | 2014-07-21 | 2014-09-24 | 焦点科技股份有限公司 | E-commerce search scoring and ranking method and system |
| CN104115178A (en) * | 2011-11-30 | 2014-10-22 | 汤姆森路透社全球资源公司 | Methods and systems for predicting market behavior based on news and sentiment analysis |
| CN106294487A (en) * | 2015-06-08 | 2017-01-04 | 腾讯科技（深圳）有限公司 | Self-adapted search method based on the Internet, equipment and system |
| CN106649302A (en) * | 2015-10-28 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Search sequencing method and device |
| CN106919641A (en) * | 2017-01-12 | 2017-07-04 | 北京三快在线科技有限公司 | A kind of interest point search method and device, electronic equipment |
| CN109033386A (en) * | 2018-07-27 | 2018-12-18 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
| CN109063108A (en) * | 2018-07-27 | 2018-12-21 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
| CN109947902A (en) * | 2019-03-06 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of data query method, apparatus and readable medium |
| CN110619036A (en) * | 2019-08-25 | 2019-12-27 | 南京理工大学 | Full-text retrieval system based on improved IF-IDF algorithm |
| CN110633399A (en) * | 2018-06-01 | 2019-12-31 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
| CN110647679A (en) * | 2019-09-04 | 2020-01-03 | 达疆网络科技(上海)有限公司 | Search result comprehensive ordering method under o2o scene |
| CN111061836A (en) * | 2019-12-18 | 2020-04-24 | 焦点科技股份有限公司 | Custom scoring method suitable for Lucene full-text search engine |
| CN111061942A (en) * | 2018-10-17 | 2020-04-24 | 阿里巴巴集团控股有限公司 | Search ranking monitoring method and system |
| CN111079035A (en) * | 2019-11-21 | 2020-04-28 | 北方信息控制研究院集团有限公司 | Domain search ordering method based on dynamic map link analysis |
| CN112100529A (en) * | 2020-11-17 | 2020-12-18 | 北京三快在线科技有限公司 | Search content ordering method and device, storage medium and electronic equipment |
| CN112131491A (en) * | 2020-11-20 | 2020-12-25 | 震坤行网络技术(南京)有限公司 | Hierarchical ordering method, computing device and computer readable storage medium |
| CN112528124A (en) * | 2020-12-18 | 2021-03-19 | 浙江融象数科控股有限公司 | Search and recommendation design system for search engine |
| CN112597396A (en) * | 2020-12-29 | 2021-04-02 | 深圳Tcl新技术有限公司 | Search recall ranking method, system and computer readable storage medium |
-
2021
- 2021-05-20 CN CN202110560938.9A patent/CN113343046B/en active Active
Patent Citations (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8145636B1 (en) * | 2009-03-13 | 2012-03-27 | Google Inc. | Classifying text into hierarchical categories |
| CN103092844A (en) * | 2011-10-28 | 2013-05-08 | 腾讯科技（深圳）有限公司 | Index creating method, index creating system, searching method and searching system |
| CN103116582A (en) * | 2011-11-16 | 2013-05-22 | 阿里巴巴集团控股有限公司 | Information retrieval method and relevant system and device |
| CN104115178A (en) * | 2011-11-30 | 2014-10-22 | 汤姆森路透社全球资源公司 | Methods and systems for predicting market behavior based on news and sentiment analysis |
| CN102662959A (en) * | 2012-03-07 | 2012-09-12 | 南京邮电大学 | Method for detecting phishing web pages with spatial mixed index mechanism |
| CN103365870A (en) * | 2012-03-29 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Method and system for sorting search results |
| CN103365915A (en) * | 2012-04-10 | 2013-10-23 | 北京易盟天地信息技术有限公司 | Search result ranking method based on search engine and database query system |
| US20140201126A1 (en) * | 2012-09-15 | 2014-07-17 | Lotfi A. Zadeh | Methods and Systems for Applications for Z-numbers |
| CN104063523A (en) * | 2014-07-21 | 2014-09-24 | 焦点科技股份有限公司 | E-commerce search scoring and ranking method and system |
| CN106294487A (en) * | 2015-06-08 | 2017-01-04 | 腾讯科技（深圳）有限公司 | Self-adapted search method based on the Internet, equipment and system |
| CN106649302A (en) * | 2015-10-28 | 2017-05-10 | 腾讯科技（深圳）有限公司 | Search sequencing method and device |
| CN106919641A (en) * | 2017-01-12 | 2017-07-04 | 北京三快在线科技有限公司 | A kind of interest point search method and device, electronic equipment |
| CN110633399A (en) * | 2018-06-01 | 2019-12-31 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
| CN109033386A (en) * | 2018-07-27 | 2018-12-18 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
| CN109063108A (en) * | 2018-07-27 | 2018-12-21 | 天津字节跳动科技有限公司 | Search ordering method, device, computer equipment and storage medium |
| CN111061942A (en) * | 2018-10-17 | 2020-04-24 | 阿里巴巴集团控股有限公司 | Search ranking monitoring method and system |
| CN109947902A (en) * | 2019-03-06 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of data query method, apparatus and readable medium |
| CN110619036A (en) * | 2019-08-25 | 2019-12-27 | 南京理工大学 | Full-text retrieval system based on improved IF-IDF algorithm |
| CN110647679A (en) * | 2019-09-04 | 2020-01-03 | 达疆网络科技(上海)有限公司 | Search result comprehensive ordering method under o2o scene |
| CN111079035A (en) * | 2019-11-21 | 2020-04-28 | 北方信息控制研究院集团有限公司 | Domain search ordering method based on dynamic map link analysis |
| CN111061836A (en) * | 2019-12-18 | 2020-04-24 | 焦点科技股份有限公司 | Custom scoring method suitable for Lucene full-text search engine |
| CN112100529A (en) * | 2020-11-17 | 2020-12-18 | 北京三快在线科技有限公司 | Search content ordering method and device, storage medium and electronic equipment |
| CN112131491A (en) * | 2020-11-20 | 2020-12-25 | 震坤行网络技术(南京)有限公司 | Hierarchical ordering method, computing device and computer readable storage medium |
| CN112528124A (en) * | 2020-12-18 | 2021-03-19 | 浙江融象数科控股有限公司 | Search and recommendation design system for search engine |
| CN112597396A (en) * | 2020-12-29 | 2021-04-02 | 深圳Tcl新技术有限公司 | Search recall ranking method, system and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| BETÜL BULUT 等: ""A Paper Recommendation System Based on User’s Research Interests"", 《2018 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM)》, pages 911 - 915 * |
| 吴婷: ""云环境下改进的动态模糊多关键字查询算法研究"", 《科技通报》, pages 211 - 214 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116738065A (en) * | 2023-08-15 | 2023-09-12 | 浙江同信企业征信服务有限公司 | Enterprise searching method, device, equipment and storage medium |
| CN116738065B (en) * | 2023-08-15 | 2024-04-19 | 浙江同信企业征信服务有限公司 | Enterprise searching method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113343046B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | An expert recommendation algorithm based on Pearson correlation coefficient and FP-growth | |
| Önder | Forecasting tourism demand with Google trends: Accuracy comparison of countries versus cities | |
| CN104835072B (en) | Method and system for compatibility scoring of users in a social network | |
| JP4920023B2 (en) | Inter-object competition index calculation method and system | |
| Johnson | Market segmentation: A strategic management tool | |
| US7783620B1 (en) | Relevancy scoring using query structure and data structure for federated search | |
| Currim | Predictive testing of consumer choice models not subject to independence of irrelevant alternatives | |
| CN102929939B (en) | The offer method and device of customized information | |
| US20050149507A1 (en) | Systems and methods for identifying an internet resource address | |
| US20080005101A1 (en) | Method and apparatus for determining the significance and relevance of a web page, or a portion thereof | |
| WO2018053966A1 (en) | Click rate estimation | |
| Lubke et al. | Assessing model selection uncertainty using a bootstrap approach: an update | |
| JP2019502979A (en) | Automatic interpretation of structured multi-field file layouts | |
| US7783636B2 (en) | Personalized information retrieval search with backoff | |
| US11226972B2 (en) | Ranking collections of document passages associated with an entity name by relevance to a query | |
| CN103177066A (en) | Analyzing and representing interpersonal relations | |
| CN111159563A (en) | Method, device and equipment for determining user interest point information and storage medium | |
| CN111159561A (en) | Method for constructing recommendation engine according to user behaviors and user portrait | |
| CN105159898B (en) | A kind of method and apparatus of search | |
| CN113343046B (en) | Intelligent search ordering system | |
| KR100557874B1 (en) | Method of scientific information analysis and media that can record computer program thereof | |
| KR20210030808A (en) | Estimating apparatus for market size, and control method thereof | |
| CN113051482A (en) | Web page search intelligent matching recommendation method based on user feature recognition and behavior analysis | |
| Gezici | Quantifying political bias in news articles | |
| CN112434140A (en) | Reply information processing method and system |
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 |