CN112800317A - Search platform architecture for automobile vertical field - Google Patents
Search platform architecture for automobile vertical field Download PDFInfo
- Publication number
- CN112800317A CN112800317A CN202110151734.XA CN202110151734A CN112800317A CN 112800317 A CN112800317 A CN 112800317A CN 202110151734 A CN202110151734 A CN 202110151734A CN 112800317 A CN112800317 A CN 112800317A
- Authority
- CN
- China
- Prior art keywords
- module
- engine
- query
- search
- analyzer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
Abstract
The application discloses search platform framework towards perpendicular field of car, including engine and manual intervention module, the inside manual intervention module that is provided with of engine, the inside query filter module, error correction module, query interception module and the query of being provided with of engine rewrite the chain module, the inside analyzer chain module that is provided with of engine, the inside strategy that is provided with of engine of the output of analyzer chain module carries out analysis module. The system can identify the intention of a user according to search keywords of the user, returns corresponding vehicle types, articles, videos and other contents, encapsulates corresponding data according to service types, guarantees the stability of a service system, cannot influence the normal use of a page when an extraction interface is wrong, is still convenient for maintenance after dimensionality is increased, can quickly retrieve and simultaneously can carry out keyword matching according to the effectiveness of indexes, fully utilizes the near real-time function of the ES, and is matched with the efficient query function of red is.
Description
Technical Field
The application relates to a search platform architecture, in particular to a search platform architecture oriented to the vertical field of automobiles.
Background
At present, the front-end system and the back-end system are basically constructed by basic Spring + DataBase, and the data are formatted in the traditional service, such as age, surname and the like, so that the query advantages of the data can be fully exerted. But in a special vertical field, such as e-commerce, automobile, etc., it is more important to pay attention to full-text search, if the search is performed by using a database, the search will be very slow, even unusable, and now new words and hot words are layered endlessly, for example, when a user searches for "apple", we should return to the apple that we eat or an apple-related electronic product? And ordering of articles, etc., which are issues that a good search platform should address.
Part of the search architecture is to use NoSQL, such as MongoDB, which can search rapidly through unstructured articles, but NoSQL can search rapidly, but in the actual use process we will use a lot of query aggregation calculation operations, such as querying a certain price interval, etc., and the requirement on the effectiveness of the index is high, and like MongoDB, it can not solve this problem well, part of the search architecture is to match the keywords completely through a dictionary, correct or intend to recognize, but dictionary-based technology can solve most of words, but now internet hotwords and new words are layered endword easily, so it needs an automatic solution to process, part of the search architecture is to sort the recalled articles, and re-sort through defining calculation formula, but its artificially defined method is not suitable, it is entirely necessary to set values empirically, and as dimensions become more and more numerous, it becomes difficult to extend maintenance. Therefore, a search platform architecture facing the automobile vertical field is provided for the problems.
Disclosure of Invention
The search platform architecture for the vertical field of the automobile comprises an engine and a manual intervention module, wherein the manual intervention module is arranged in the engine, a query filtering module, an error correcting module, a query intercepting module and a query rewriting chain module are arranged in the engine, an analyzer chain module is arranged in the engine, a strategy execution analysis module is arranged in the engine at the output end of the analyzer chain module, an analyzer chain configuration module is arranged in the engine, an information processing module is arranged in the engine at the output end of the strategy execution analysis module, a search processing module is arranged in the engine, an ES engine service module is arranged in the engine, and a result display module is arranged in the engine.
Furthermore, a word identification module, a stop word processing module, a region normalization module, a label normalization module, a Sort analyzer module and a Filter analyzer module are arranged in the analyzer chain module.
Further, the output end of the analyzer chain configuration module is loaded into the analyzer chain module, and the output end of the analyzer chain module is loaded into the policy execution analysis module.
Further, the output end of the policy execution analysis module is loaded into the information processing module, and the output end of the information processing module is loaded into the ES engine service module.
Furthermore, a search processor and a feature module are arranged in the information processing module.
Furthermore, a search processor configuration and a Sorter configuration are arranged inside the search processing module.
Further, the output end of the ES engine service module is loaded into the result display module, and a build result set, no-result recommendation and result set intervention are arranged in the result display module.
Furthermore, a queryBuild module and a FilterBuild module are arranged inside the search processor.
Furthermore, a rank offline feature module and an online feature extraction are arranged in the feature module, and a position feature and a query correlation click feature are arranged in the online feature extraction.
Further, the output end of the search processor configuration is loaded to the search processor, and the output end of the Sorter configuration is loaded to the inside of the feature module.
The beneficial effect of this application is: the application provides a hospital intelligent management system with information extraction and doctor-patient contact reminding functions.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic diagram of a search system architecture according to an embodiment of the present application;
FIG. 2 is a system framework diagram of one embodiment of the present application;
FIG. 3 is a block diagram of an embodiment of an analyzer chain module;
FIG. 4 is a block diagram of a search processor according to an embodiment of the present application;
FIG. 5 is a schematic block diagram of a feature module according to an embodiment of the present application;
fig. 6 is a data flow diagram according to an embodiment of the present application.
In the figure: 1. an engine, 2, a manual intervention module, 3, a query filtering module, 4, an error correction module, 5, a query intercepting module, 6, a query rewrite chain module, 7, an analyzer chain module, 8, an analyzer chain configuration module, 9, a policy execution analysis module, 10, an information processing module, 11, a search processing module, 12, an ES engine service module, 13, a result presentation module, 14, a word recognition module, 15, a stop word processing module, 16, a region normalization module, 17, a tag normalization module, 18, a Sort analyzer module, 19, a Filter analyzer module, 20, a search processor, 21, a query build module, 22, a Filter build module, 23, a feature module, 24, a rank offline feature module, 25, an online feature extraction, 26, a location feature, 27, a query relevance click feature, 28, a search processor configuration, 29, a Sorter configuration, 30, a build result set, 31, a query result set, a query rewrite result set, and a search result set, Recommending without result, and 32, intervening in a result set.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1-6, a search platform architecture for the vertical field of automobiles includes an engine 1 and a manual intervention module 2, the manual intervention module 2 is disposed inside the engine 1, a query filtering module 3, an error correcting module 4, a query intercepting module 5, and a query rewriting chain module 6 are disposed inside the engine 1, an analyzer chain module 7 is disposed inside the engine 1, a policy execution analysis module 9 is disposed inside the engine 1 at an output end of the analyzer chain module 7, an analyzer chain configuration module 8 is disposed inside the engine 1, an information processing module 10 is disposed inside the engine 1 at an output end of the policy execution analysis module 9, a search processing module 11 is disposed inside the engine 1, an ES engine service module 12 is disposed inside the engine 1, and a result display module 13 is disposed inside the engine 1.
The analyzer chain module 7 is internally provided with a word recognition module 14, a stop word processing module 15, a region normalization module 16, a label normalization module 17, a Sort analyzer module 18 and a Filter analyzer module 19, the word recognition module 14, the stop word processing module 15, the region normalization module 16, the label normalization module 17, the Sort analyzer module 18 and the Filter analyzer module 19 are matched, and based on a dictionary and rule method, the method based on the dictionary and the rule is most common in searching, the good dictionary can generally solve the problem of more than 80% and even more, and the accuracy can also reach 90% and even more; the output end of the analyzer chain configuration module 8 is loaded into the analyzer chain module 7, and the output end of the analyzer chain module 7 is loaded into the strategy execution analysis module 9; the output end of the strategy execution analysis module 9 is loaded into the information processing module 10, and the output end of the information processing module 10 is loaded into the ES engine service module 12; the information processing module 10 is internally provided with a search processor 20 and a feature module 23; a search processor configuration 28 and a Sorter configuration 29 are arranged in the search processing module 11; the output end of the ES engine service module 12 is loaded into the result display module 13, and a built result set 30, a no-result recommendation 31 and a result set intervention 32 are arranged in the result display module 13; the search processor 20 is internally provided with a queryBuild module 21 and a FilterBuild module 22, and the queryBuild module 21 is a query generation module 21; a rank offline feature module 24 and an online feature extraction 25 are arranged in the feature module 23, and a position feature 26 and a query correlation click feature 27 are arranged in the online feature extraction 25; the output of search processor configuration 28 is loaded into search processor 20 and the output of Sorter configuration 29 is loaded inside feature module 23.
When the method is used, the whole system is built in hardware equipment and is connected with the ES cluster firstly, and the ES cluster can cache the query result to accelerate the query speed; elastic Search (ES) is responsible for data storage, index establishment and query function provision, then only keyword verification and partial parameter standardization, such as page turning, version number and the like, then word segmentation is performed on query words and query intention is analyzed, crawler filtering is performed first, then keyword error correction is performed, query can be performed according to pinyin and synonym, then intention identification is performed, such as identification of second-hand vehicles, new vehicles and the like, results returned by ES are refined, LTR and other related machine learning technologies are mainly used, a query interface is provided externally, then vehicle types and brand query are performed, finally classified query, articles and videos and other resources are queried, and index and query are performed: the method comprises the following steps of searching and using Lucene as a data storage engine at the bottom to provide functions of word segmentation, index establishment, query, scoring and the like, wherein Lucene is a sub-item of an apache software foundation 4jakarta item group and is a full-text retrieval engine toolkit of an open source code, but is not a complete full-text retrieval engine but a full-text retrieval engine architecture and provides a complete query engine and an index engine, and a partial text analysis engine (English and German western languages) aims to provide a simple and easy-to-use toolkit for software developers to conveniently realize the full-text retrieval function in a target system, or the complete full-text retrieval engine is established on the basis of the Lucene and mainly comprises three parts, namely index establishment, storage index, three query indexes and intention identification: the intention recognition mainly includes: based on a dictionary and rule method, the method based on the dictionary and the rule is most common in searching, the good dictionary can generally solve the problems of more than 80 percent and even more, the accuracy rate can also reach 90 percent and even more, based on machine learning and deep learning, the generalization capability of the rule and the dictionary is insufficient, the recall rate cannot reach expectation, the content input by a user is complex, the rule and the dictionary are difficult to cover, and the searching is ordered: the sequencing learning is a supervised machine learning process, for each given query-document pair, characteristics are extracted, real data labels are obtained through a log mining or manual labeling method, then input can be similar to actual data through a sequencing model, an interface which accords with a RESTFUL style is provided for a middle station, the RESTFUL is a design style and a development mode of a network application program, an XML format definition or a JSON format definition can be used based on HTTP, the RESTFUL is suitable for a scene that a mobile internet manufacturer serves as an industry enabling interface, the function that a third party OTT calls mobile network resources is realized, and the action type is to add, change and delete the called resources.
The application has the advantages that: the system can identify the intention of a user according to the search keywords of the user, return corresponding contents such as vehicle types, articles, videos and the like, package corresponding data according to the service types, ensure the stability of the service system, cannot influence the normal use of pages when an extraction interface is wrong, is convenient for people to maintain after the dimensionality is increased, can perform keyword matching according to the effectiveness of indexes while performing quick retrieval, fully utilizes the near real-time function of the ES, is matched with the efficient query function of redis, quickly identifies the automobile related words in the phrase text, analyzes the query intention of the user, queries according to the intention in a background, and finally sorts the results, so that the user can quickly and accurately find the contents to be queried, and the problem that the search results of the traditional search platform are disordered is solved, the retrieval efficiency of the user is improved.
It is well within the skill of those in the art to implement, without undue experimentation, the present application is not directed to software and process improvements, as they relate to circuits and electronic components and modules.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. Search platform framework oriented to automobile vertical field is characterized in that: comprises an engine (1) and a manual intervention module (2), wherein the manual intervention module (2) is arranged in the engine (1), the engine (1) is internally provided with a query filtering module (3), an error correcting module (4), a query intercepting module (5) and a query rewriting chain module (6), an analyzer chain module (7) is arranged in the engine (1), a strategy execution analysis module (9) is arranged in the engine (1) at the output end of the analyzer chain module (7), an analyzer chain configuration module (8) is arranged in the engine (1), an information processing module (10) is arranged in the engine (1) at the output end of the strategy execution analysis module (9), the engine (1) is internally provided with a search processing module (11), the engine (1) is internally provided with an ES engine service module (12), and the engine (1) is internally provided with a result display module (13).
2. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the analyzer chain module (7) is internally provided with a word identification module (14), a stop word processing module (15), a region normalization module (16), a tag normalization module (17), a Sort analyzer module (18) and a Filter analyzer module (19).
3. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the output end of the analyzer chain configuration module (8) is loaded into the analyzer chain module (7), and the output end of the analyzer chain module (7) is loaded into the strategy execution analysis module (9).
4. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the output end of the strategy execution analysis module (9) is loaded into the information processing module (10), and the output end of the information processing module (10) is loaded into the ES engine service module (12).
5. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the information processing module (10) is internally provided with a search processor (20) and a feature module (23).
6. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the search processing module (11) is internally provided with a search processor configuration (28) and a Sorter configuration (29).
7. The vehicle vertical domain oriented search platform architecture of claim 1, wherein: the output end of the ES engine service module (12) is loaded into the result display module (13), and a build result set (30), a no-result recommendation (31) and a result set intervention (32) are arranged in the result display module (13).
8. The vehicle vertical domain oriented search platform architecture of claim 5, wherein: the search processor (20) is internally provided with a queryBuild module (21) and a FilterBuild module (22).
9. The vehicle vertical domain oriented search platform architecture of claim 5, wherein: a rank offline feature module (24) and an online feature extraction (25) are arranged in the feature module (23), and a position feature (26) and a query correlation click feature (27) are arranged in the online feature extraction (25).
10. The vehicle vertical domain oriented search platform architecture of claim 5, wherein: the output end of the search processor configuration (28) is loaded to the search processor (20), and the output end of the Sorter configuration (29) is loaded inside the feature module (23).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151734.XA CN112800317A (en) | 2021-02-04 | 2021-02-04 | Search platform architecture for automobile vertical field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110151734.XA CN112800317A (en) | 2021-02-04 | 2021-02-04 | Search platform architecture for automobile vertical field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112800317A true CN112800317A (en) | 2021-05-14 |
Family
ID=75814098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110151734.XA Pending CN112800317A (en) | 2021-02-04 | 2021-02-04 | Search platform architecture for automobile vertical field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800317A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326702A (en) * | 2021-06-11 | 2021-08-31 | 北京猎户星空科技有限公司 | Semantic recognition method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246492A (en) * | 2008-02-26 | 2008-08-20 | 华中科技大学 | Full text retrieval system based on natural language |
| CN102200974A (en) * | 2010-03-25 | 2011-09-28 | 北京师范大学 | Unified information retrieval intelligent agent system and method for search engine |
| CN106095778A (en) * | 2016-05-26 | 2016-11-09 | 达而观信息科技（上海）有限公司 | The Chinese search word automatic error correction method of search engine |
| CN107562726A (en) * | 2017-09-06 | 2018-01-09 | 国家电网公司 | A kind of electric service search engine based on hot word |
| CN108922633A (en) * | 2018-06-22 | 2018-11-30 | 北京海德康健信息科技有限公司 | A kind of disease name standard convention method and canonical system |
| CN110543595A (en) * | 2019-08-12 | 2019-12-06 | 南京莱斯信息技术股份有限公司 | in-station search system and method |
| CN111090674A (en) * | 2019-12-28 | 2020-05-01 | 安徽微沃信息科技股份有限公司 | Search engine system based on hot words and cache |
| CN111339421A (en) * | 2020-02-28 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Information search method, device, equipment and storage medium based on cloud technology |
| CN112307762A (en) * | 2020-12-24 | 2021-02-02 | 完美世界(北京)软件科技发展有限公司 | Search result sorting method and device, storage medium and electronic device |
-
2021
- 2021-02-04 CN CN202110151734.XA patent/CN112800317A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246492A (en) * | 2008-02-26 | 2008-08-20 | 华中科技大学 | Full text retrieval system based on natural language |
| CN102200974A (en) * | 2010-03-25 | 2011-09-28 | 北京师范大学 | Unified information retrieval intelligent agent system and method for search engine |
| CN106095778A (en) * | 2016-05-26 | 2016-11-09 | 达而观信息科技（上海）有限公司 | The Chinese search word automatic error correction method of search engine |
| CN107562726A (en) * | 2017-09-06 | 2018-01-09 | 国家电网公司 | A kind of electric service search engine based on hot word |
| CN108922633A (en) * | 2018-06-22 | 2018-11-30 | 北京海德康健信息科技有限公司 | A kind of disease name standard convention method and canonical system |
| CN110543595A (en) * | 2019-08-12 | 2019-12-06 | 南京莱斯信息技术股份有限公司 | in-station search system and method |
| CN111090674A (en) * | 2019-12-28 | 2020-05-01 | 安徽微沃信息科技股份有限公司 | Search engine system based on hot words and cache |
| CN111339421A (en) * | 2020-02-28 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Information search method, device, equipment and storage medium based on cloud technology |
| CN112307762A (en) * | 2020-12-24 | 2021-02-02 | 完美世界(北京)软件科技发展有限公司 | Search result sorting method and device, storage medium and electronic device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326702A (en) * | 2021-06-11 | 2021-08-31 | 北京猎户星空科技有限公司 | Semantic recognition method and device, electronic equipment and storage medium |
| CN113326702B (en) * | 2021-06-11 | 2024-02-20 | 北京猎户星空科技有限公司 | Semantic recognition method, semantic recognition device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11514096B2 (en) | Natural language processing for entity resolution | |
| US9846748B2 (en) | Searching for information based on generic attributes of the query | |
| CN102012900B (en) | An information retrieval method and system | |
| Tavakoli et al. | Extracting useful software development information from mobile application reviews: A survey of intelligent mining techniques and tools | |
| Lupiani-Ruiz et al. | Financial news semantic search engine | |
| US20150254230A1 (en) | Method and system for monitoring social media and analyzing text to automate classification of user posts using a facet based relevance assessment model | |
| US10664888B2 (en) | Method and system for attribute extraction from product titles using sequence labeling algorithms | |
| US10423724B2 (en) | Optimizations of search engines for merging search results | |
| CN103544267A (en) | Search method and device based on search recommended words | |
| CN107832338B (en) | Method and system for recognizing core product words | |
| CN112257419A (en) | Intelligent retrieval method and device for calculating patent document similarity based on word frequency and semantics, electronic equipment and storage medium thereof | |
| CN105183803A (en) | Personalized search method and search apparatus thereof in social network platform | |
| US20230161961A1 (en) | Techniques for enhancing the quality of human annotation | |
| CN113268615A (en) | Resource label generation method and device, electronic equipment and storage medium | |
| Xia et al. | The unified collocation framework for opinion mining | |
| CN114090762B (en) | Automatic question-answering method and system in futures field | |
| CN102902705B (en) | Ambiguity in location data | |
| CN112800317A (en) | Search platform architecture for automobile vertical field | |
| CN102982025A (en) | Identification method and device for searching requirement | |
| US11328005B2 (en) | Machine learning (ML) based expansion of a data set | |
| CN113254623B (en) | Data processing method, device, server, medium and product | |
| CN111597296A (en) | Commodity data processing method, device and system | |
| Chang et al. | Mining semantics for large scale integration on the web: evidences, insights, and challenges | |
| US11347937B2 (en) | Inclusion of protocol conditions within search engine results | |
| CN109165297B (en) | Universal entity linking device and method |
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 |