CN116340470B - Keyword associated retrieval system based on AIGC - Google Patents
Keyword associated retrieval system based on AIGC Download PDFInfo
- Publication number
- CN116340470B CN116340470B CN202310619228.8A CN202310619228A CN116340470B CN 116340470 B CN116340470 B CN 116340470B CN 202310619228 A CN202310619228 A CN 202310619228A CN 116340470 B CN116340470 B CN 116340470B
- Authority
- CN
- China
- Prior art keywords
- module
- association
- keyword
- target
- function module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 238000004891 communication Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 4
- 241000219095 Vitis Species 0.000 description 2
- 235000009754 Vitis X bourquina Nutrition 0.000 description 2
- 235000012333 Vitis X labruscana Nutrition 0.000 description 2
- 235000014787 Vitis vinifera Nutrition 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013434 data augmentation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3338—Query expansion
-
- 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
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/338—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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an AIGC-based keyword association retrieval system which comprises a keyword feature extraction module, an association module, a keyword acquisition module, a retrieval module and a function module manager, wherein the keyword feature extraction module, the association module, the keyword acquisition module and the retrieval module are respectively and electrically connected with the function module manager. The AIGC technology can be applied to the operations of a keyword feature extraction module, a correlation word acquisition module and a retrieval module so as to strengthen the functions of the modules. The keyword association search system based on AIGC disclosed by the invention has the keyword expansion function for searching, and has applicability to application scenes with compact computing resources.
Description
Technical Field
The invention relates to the technical field of intelligent systems, in particular to an AIGC-based keyword association retrieval system.
Background
Patent CN104516903a discloses a keyword expansion method, in which an initial keyword is used for searching, a keyword obtained by searching is used as a basis of the next searching, searching is performed in a keyword iteration mode, when the keyword error of the previous and the next searching is within a certain range, the searched keyword is used as an expansion keyword of the initial keyword, in this way, multiple expression modes and word senses with multiple meanings of the initial keyword are obtained, and the initial keyword is effectively and reasonably expanded.
According to the technical scheme, the expansion of the keywords is realized through keyword iteration, and when the operation of document retrieval is executed, the document range contained in the retrieval result is widened, so that the user can conveniently screen available document materials. However, the process of keyword iteration requires a large amount of computing resources, which is not applicable to an application scenario where the computing resources are compact.
Therefore, how to design a search system with applicability to application scenarios with compact computing resources is a technical problem to be solved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide the keyword association retrieval system based on the AIGC, which has applicability to application scenes with compact computing resources.
In order to solve the technical problems, the invention discloses a keyword association search system based on AIGC, which comprises a keyword feature extraction module, an association module, a keyword acquisition module, a search module and a function module manager, wherein the keyword feature extraction module, the association module, the keyword acquisition module and the search module are respectively and electrically connected with the function module manager, and the function module manager executes the following steps:
the function module manager acquires target keywords from the retrieval information input by the user through the keyword acquisition module;
the function module manager determines vocabulary characteristics of the target keywords through the keyword characteristic extraction module;
the function module manager controls the association module to screen out the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and marks the largest value as a target association word;
the function module manager inputs the target related words and the target keywords as indexes into a search module, so that the search module executes document search operation.
In the keyword association search system based on AIGC disclosed by the invention, the function module manager controls the association module to screen the largest numerical value of the association evaluation index from the predetermined association vocabulary data according to vocabulary characteristics and calibrate the association evaluation index as a target association word, the association evaluation index is used as an indication of the vocabulary covered in the expansion range of the determined keyword, the calculation resource occupation amount is reduced, and then the target association word and the target keyword are used as indexes to be input into the search module, so that the expansion of the keywords used for search is realized, the document range contained in the search result is widened, and the user can conveniently screen available document materials. Therefore, the keyword association search system based on AIGC disclosed by the invention has the keyword expansion function for searching, and has applicability to application scenes with compact computing resources.
In an alternative embodiment, the keyword association search system based on AIGC further comprises a communication module electrically connected with the function module manager, the function module manager is in communication connection with the data platform based on public network through the communication module,
before the function module manager controls the association module to screen the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and mark the largest value as the target association word, the step executed by the function module manager further comprises:
the function module manager obtains an associated vocabulary data updating instruction from the data platform through the communication module, wherein the associated vocabulary data updating instruction comprises updated associated vocabulary data;
the function module manager replaces the original associated vocabulary data with the updated associated vocabulary data to complete the operation of updating the associated vocabulary data.
In an alternative embodiment, in the step of controlling the association module by the function module manager to screen the largest value of the association evaluation index from the predetermined associated vocabulary data according to the vocabulary characteristics and mark the largest value as the target associated word,
the association module determines the association evaluation index using the following formula:
,
wherein S is the association evaluation index of a candidate target associated word in the predetermined associated vocabulary data,word frequency of the candidate target related word, +.>Feature vector for feature matrix of target keyword, < +.>For the feature vector of the candidate target associated word feature matrix,/I>Is->The written target keyword feature matrix +.>Line->Element value of column,/->Is->Mean value of element values of the written target keyword feature matrix, +.>Is->The number of rows of the written target keyword feature matrix, < ->Is->The number of columns of the target keyword feature matrix is written.
In an optional implementation manner, in the present invention, the communication module is further in communication connection with a service terminal based on a public network, and before the function module manager obtains a target keyword from the search information input by the user through the keyword obtaining module, the step performed by the function module manager includes:
the function module manager controls the keyword acquisition module to acquire the retrieval information received by the communication module and input by the user from the service terminal.
In an alternative embodiment, the search information input by the user is one or more of voice information, text information and picture information.
As an optional implementation manner, in the present invention, the keyword association search system based on AIGC further includes a search result output module, where the search result output module is electrically connected to the function module manager, and after the function module manager inputs the target associated word and the target keyword as indexes into a search module, so that the search module performs an operation of document search, the step performed by the function module manager further includes:
and the function module manager controls the search result output module to output the result of the search module for document search, so that the user can review the result.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a keyword association retrieval system based on AIGC according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps performed by the function module manager according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps performed by the function module manager according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps performed by the function module manager according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating steps performed by the function module manager according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
AIGC (artificial intelligence generated content, artificial Intelligence Generated Content, abbreviated as AIGC) is expected to be a new engine for innovation and development of digital content, and the advantages mainly include: 1) The AIGC can bear basic mechanical labor such as information mining, material calling, re-engraving editing and the like at a manufacturing capacity and knowledge level superior to those of human beings, and can meet mass personalized requirements in a low marginal cost and high-efficiency manner from the technical level; 2) AIGC can inoculate a new business state new mode by supporting multidimensional interaction, fusion and permeation of digital content and other industries; 3) The development of the "meta universe" is assisted, and the physical world is accelerated and repeated through AIGC to carry out infinite content creation, so that spontaneous organic growth is realized.
The invention discloses an AIGC-based keyword association retrieval system, which comprises a keyword feature extraction module, an association module, a keyword acquisition module, a retrieval module and a function module manager, wherein the keyword feature extraction module, the association module, the keyword acquisition module and the retrieval module are respectively and electrically connected with the function module manager.
Wherein, as shown in fig. 2, the steps executed by the function module manager include:
s101, the function module manager acquires target keywords from the retrieval information input by the user through the keyword acquisition module. Alternatively, the search information input by the user may be a plurality of words such as "red", apple, grape "at intervals of special symbols (e.g.", "or"/"), and then the target keywords acquired by the keyword acquisition module are" red "," apple "and" grape ". Further optionally, in step S101, the keyword obtaining module may use the search information input by the previous user as the basic information content and integrate the search information input by the current user to generate the corresponding target keyword based on the AIGC technology.
S102, the function module manager determines vocabulary characteristics of the target keywords through the keyword characteristic extraction module. Optionally, the lexical features of the target keywords may include category features of part of speech (e.g., verbs, nouns, or intonation words), word frequency features, and emotion features (e.g., sense, detract, or neutral).
S103, the function module manager controls the association module to screen out the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and calibrate the largest value as the target association word. Alternatively, the associated vocabulary data may be a data set formed by a plurality of vocabularies and mapping relations among the vocabularies. Further alternatively, the target keyword is used as an input, and a plurality of candidate target associated vocabularies can be output according to a mapping relation among vocabularies in the predetermined associated vocabulary data. Then, the target related words can be selected from the candidate target related words by executing step S103, which is beneficial to improving the accuracy of the expansion range of the search keyword. Still further optionally, before executing step S103, the associated vocabulary data used in the present stage may be obtained by performing data augmentation operation on the associated vocabulary data determined in the previous stage based on the AIGC technology, so that the data capacity of the associated vocabulary data can be continuously enlarged with the increase of the number of times or the use time of the search system, thereby being beneficial to the accuracy of the target associated word determined in step S103. Specifically, the key steps of the data augmentation process described above may be: inputting the related vocabulary data set determined in the previous stage into a data generator as an original data set, wherein the data generator generates an evolution data set so as to enlarge the number of data samples; the data discriminator performs a classification operation on the evolving data set to determine the enlarged data sample tags, and the mapping relationship between the plurality of words may be determined based on the relationship between the corresponding data sample tags.
S104, the function module manager inputs the target related words and the target keywords as indexes into the retrieval module, so that the retrieval module executes document retrieval operation. Alternatively, the search module may construct a search association data set for representing a mapping relationship between the target association word, the target keyword, and the index to be input using an AIGC technique.
In the keyword association search system based on AIGC disclosed by the invention, the function module manager controls the association module to screen the largest numerical value of the association evaluation index from the predetermined association vocabulary data according to vocabulary characteristics and calibrate the association evaluation index as a target association word, the association evaluation index is used as an indication of the vocabulary covered in the expansion range of the determined keyword, the calculation resource occupation amount is reduced, and then the target association word and the target keyword are used as indexes to be input into the search module, so that the expansion of the keywords used for search is realized, the document range contained in the search result is widened, and the user can conveniently screen available document materials. Therefore, the keyword association search system based on AIGC disclosed by the invention has the keyword expansion function for searching, and has applicability to application scenes with compact computing resources.
In order to enable the related vocabulary data predetermined by the keyword related search system based on the AIGC to be updated in time so as to improve the adaptability of the system when the application scene changes, the system can be in communication connection with an external data update source so as to execute the update operation on the related vocabulary data. Specifically, as shown in fig. 1, the keyword association search system based on the AIGC further includes a communication module electrically connected to a function module manager, the function module manager is in communication connection with the data platform based on the public network through the communication module, and as shown in fig. 3, before the function module manager controls the association module to screen out the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and calibrate the association index as the target association word, the step executed by the function module manager further includes:
s1020, the function module manager acquires an associated vocabulary data updating instruction from the data platform through the communication module. The associated vocabulary updating instruction comprises updated associated vocabulary data;
s1021, the function module manager replaces the original associated vocabulary data with updated associated vocabulary data to complete the operation of updating the associated vocabulary data.
To further reduce the computational resource footprint, the association module may calculate to determine the value of the associated rating index based on some predetermined formula. Specifically, in the step of controlling the association module by the function module manager to screen the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and calibrating the largest value as the target association word, the association module determines the following formula adopted when the association evaluation index is determined:
,
wherein S is the association evaluation index of a candidate target associated word in the predetermined associated vocabulary data,word frequency of the candidate target related word, +.>Feature vector for feature matrix of target keyword, < +.>For the feature vector of the candidate target associated word feature matrix, wherein the feature matrix is a matrix for characterizing the target keyword or the candidate target associated word from multiple dimensions, for example, a sample has n features, each feature has m types, and then the feature matrix can be written as m×n feature matrices. />Is->The corresponding target keyword feature matrix +.>Line->Element value of column,/->Is->Mean value of element values of corresponding target keyword feature matrix, +.>Is->The number of rows of the written target keyword feature matrix, < ->Is->The number of columns of the target keyword feature matrix is written. Optionally, when a plurality of words in the predetermined word association data need to be traversed in the process of screening the largest value of the association evaluation index, the candidate target associated words are the plurality of words which need to be traversed.
In order to improve the convenience of use, the communication module is also in communication connection with the service terminal based on the public network, and a user can input search information through the service terminal. Specifically, as shown in fig. 4, before the function module manager acquires the target keyword from the search information input by the user through the keyword acquisition module, the function module manager performs the steps of:
s100, the function module manager controls the keyword acquisition module to acquire the retrieval information received by the communication module and input by the user from the service terminal.
Alternatively, the type of the search information input by the user may be various, and specifically may be one or a combination of a plurality of voice information, text information, and picture information.
Further optionally, the keyword association search system based on the AIGC further includes a search result output module, where the search result output module is electrically connected to the function module manager, and the user may refer to the search result through the search result output module. Specifically, as shown in fig. 5, after the function module manager inputs the target related word and the target keyword as indexes into the search module so that the search module performs an operation of document search, the steps performed by the function module manager further include:
s105, the function module manager controls the search result output module to output the result of the search module to execute document search so as to be referred by a user.
Finally, it should be noted that: in the keyword association search system based on the AIGC disclosed in the embodiment of the present invention, the disclosure is only a preferred embodiment of the present invention, and is only for illustrating the technical scheme of the present invention, but not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (1)
1. The keyword association retrieval system based on AIGC is characterized by comprising a keyword feature extraction module, an association module, a keyword acquisition module, a retrieval module and a functional module manager, wherein the keyword feature extraction module, the association module, the keyword acquisition module and the retrieval module are respectively and electrically connected with the functional module manager, and the functional module manager performs the following steps:
the function module manager acquires target keywords from the retrieval information input by the user through the keyword acquisition module;
the function module manager determines vocabulary characteristics of the target keywords through the keyword characteristic extraction module;
the function module manager controls the association module to screen out the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and marks the largest value as a target association word;
the function module manager inputs the target related words and the target keywords as indexes into a retrieval module, so that the retrieval module executes document retrieval operation; the retrieval module adopts AIGC technology to construct a retrieval association data set for representing the mapping relation among the target association words, the target keywords and the indexes to be input;
the keyword association retrieval system based on AIGC also comprises a communication module electrically connected with the function module manager, the function module manager is in communication connection with the data platform based on public network through the communication module,
before the function module manager controls the association module to screen the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and mark the largest value as the target association word, the step executed by the function module manager further comprises:
the function module manager obtains an associated vocabulary data updating instruction from the data platform through the communication module, wherein the associated vocabulary data updating instruction comprises updated associated vocabulary data;
the function module manager replaces the original associated vocabulary data with the updated associated vocabulary data to complete the operation of updating the associated vocabulary data;
in the step that the function module manager controls the association module to screen the largest value of the association evaluation index from the predetermined association vocabulary data according to the vocabulary characteristics and calibrate the association module as the target association word,
the association module determines the association evaluation index using the following formula:
，
wherein S is the association evaluation index of a candidate target associated word in the predetermined associated vocabulary data,word frequency of the candidate target related word, +.>Feature vector for feature matrix of target keyword, < +.>For the feature vector of the candidate target associated word feature matrix,/I>Is->The written target keyword feature matrix +.>Line->Element value of column,/->Is->Mean value of element values of the written target keyword feature matrix, +.>Is->The number of rows of the written target keyword feature matrix, < ->Is thatThe column number of the characteristic matrix of the target keyword written;
the communication module is also in communication connection with the service terminal based on a public network, and before the function module manager obtains the target keyword from the search information input by the user through the keyword obtaining module, the function module manager executes the steps comprising:
the function module manager controls the keyword acquisition module to acquire retrieval information received by the communication module and input by a user from the service terminal;
the keyword association search system based on the AIGC further includes a search result output module electrically connected to the function module manager, and after the function module manager inputs the target association word and the target keyword as indexes into a search module, so that the search module performs an operation of document search, the function module manager performs the steps further including:
the function module manager controls the search result output module to output the result of the search module for document search, so as to be referred by a user;
the search information input by the user is one or a combination of more of voice information, text information and picture information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310619228.8A CN116340470B (en) | 2023-05-30 | 2023-05-30 | Keyword associated retrieval system based on AIGC |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310619228.8A CN116340470B (en) | 2023-05-30 | 2023-05-30 | Keyword associated retrieval system based on AIGC |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116340470A CN116340470A (en) | 2023-06-27 |
| CN116340470B true CN116340470B (en) | 2023-09-15 |
Family
ID=86879063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310619228.8A Active CN116340470B (en) | 2023-05-30 | 2023-05-30 | Keyword associated retrieval system based on AIGC |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116340470B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821319B (en) * | 2023-08-30 | 2023-10-27 | 环球数科集团有限公司 | Quick screening type processing system based on AIGC |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110174A (en) * | 2011-04-11 | 2011-06-29 | 重庆大学 | Keyword-based WEB server expansion search method |
| CN105159931A (en) * | 2015-08-06 | 2015-12-16 | 上海智臻智能网络科技股份有限公司 | Method and apparatus for generating synonyms |
| CN106886567A (en) * | 2017-01-12 | 2017-06-23 | 北京航空航天大学 | Microblogging incident detection method and device based on semantic extension |
| CN107368525A (en) * | 2017-06-07 | 2017-11-21 | 广州视源电子科技股份有限公司 | Search for method and device, storage medium and the terminal device of related term |
| CN108491462A (en) * | 2018-03-05 | 2018-09-04 | 昆明理工大学 | A kind of semantic query expansion method and device based on word2vec |
| CN108595696A (en) * | 2018-05-09 | 2018-09-28 | 长沙学院 | A kind of human-computer interaction intelligent answering method and system based on cloud platform |
| CN110032734A (en) * | 2019-03-18 | 2019-07-19 | 百度在线网络技术（北京）有限公司 | Near synonym extension and generation confrontation network model training method and device |
| CN112232065A (en) * | 2020-10-29 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Method and device for mining synonyms |
| CN112612875A (en) * | 2020-12-29 | 2021-04-06 | 重庆农村商业银行股份有限公司 | Method, device and equipment for automatically expanding query words and storage medium |
| CN116069939A (en) * | 2021-11-01 | 2023-05-05 | 腾讯科技（深圳）有限公司 | Object early warning method, device, computer equipment, storage medium and product |
-
2023
- 2023-05-30 CN CN202310619228.8A patent/CN116340470B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110174A (en) * | 2011-04-11 | 2011-06-29 | 重庆大学 | Keyword-based WEB server expansion search method |
| CN105159931A (en) * | 2015-08-06 | 2015-12-16 | 上海智臻智能网络科技股份有限公司 | Method and apparatus for generating synonyms |
| CN106886567A (en) * | 2017-01-12 | 2017-06-23 | 北京航空航天大学 | Microblogging incident detection method and device based on semantic extension |
| CN107368525A (en) * | 2017-06-07 | 2017-11-21 | 广州视源电子科技股份有限公司 | Search for method and device, storage medium and the terminal device of related term |
| CN108491462A (en) * | 2018-03-05 | 2018-09-04 | 昆明理工大学 | A kind of semantic query expansion method and device based on word2vec |
| CN108595696A (en) * | 2018-05-09 | 2018-09-28 | 长沙学院 | A kind of human-computer interaction intelligent answering method and system based on cloud platform |
| CN110032734A (en) * | 2019-03-18 | 2019-07-19 | 百度在线网络技术（北京）有限公司 | Near synonym extension and generation confrontation network model training method and device |
| CN112232065A (en) * | 2020-10-29 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Method and device for mining synonyms |
| CN112612875A (en) * | 2020-12-29 | 2021-04-06 | 重庆农村商业银行股份有限公司 | Method, device and equipment for automatically expanding query words and storage medium |
| CN116069939A (en) * | 2021-11-01 | 2023-05-05 | 腾讯科技（深圳）有限公司 | Object early warning method, device, computer equipment, storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116340470A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570180B (en) | Voice search method and device based on artificial intelligence | |
| CN110019647B (en) | Keyword searching method and device and search engine | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN106503231B (en) | Search method and device based on artificial intelligence | |
| US8356065B2 (en) | Similar text search method, similar text search system, and similar text search program | |
| US20190392824A1 (en) | Voice conversation method and system with enhanced word features | |
| CN116340470B (en) | Keyword associated retrieval system based on AIGC | |
| CN108446316A (en) | Recommendation method, apparatus, electronic equipment and the storage medium of associational word | |
| CN109284358B (en) | Chinese address noun hierarchical method and device | |
| CN112650842A (en) | Human-computer interaction based customer service robot intention recognition method and related equipment | |
| CN113326267A (en) | Address matching method based on inverted index and neural network algorithm | |
| CN116663618A (en) | Operator optimization method and device, storage medium and electronic equipment | |
| CN115982416A (en) | Data processing method and device, readable storage medium and electronic equipment | |
| CN116306603A (en) | Training method of title generation model, title generation method, device and medium | |
| CN112102840A (en) | Semantic recognition method, device, terminal and storage medium | |
| CN111209746B (en) | Natural language processing method and device, storage medium and electronic equipment | |
| CN113553844B (en) | Domain identification method based on prefix tree features and convolutional neural network | |
| KR101482148B1 (en) | Group mapping data building server, sound recognition server and method thereof by using personalized phoneme | |
| CN109361399A (en) | A kind of method, apparatus, equipment and storage medium obtaining byte sequence | |
| CN115879440A (en) | Natural language processing method, natural language processing device, natural language model training equipment and storage medium | |
| CN111222011B (en) | Video vector determining method and device | |
| CN111626059B (en) | Information processing method and device | |
| CN113836917A (en) | Text word segmentation processing method and device, equipment and medium thereof | |
| CN116186272B (en) | Combined training method and device, storage medium and electronic equipment | |
| CN117252183B (en) | Semantic-based multi-source table automatic matching method, device and storage medium |
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 |