CN108932326B - Instance extension method, device, equipment and medium - Google Patents
Instance extension method, device, equipment and medium Download PDFInfo
- Publication number
- CN108932326B CN108932326B CN201810714308.0A CN201810714308A CN108932326B CN 108932326 B CN108932326 B CN 108932326B CN 201810714308 A CN201810714308 A CN 201810714308A CN 108932326 B CN108932326 B CN 108932326B
- Authority
- CN
- China
- Prior art keywords
- expanded
- rule
- instance
- expansion
- model
- 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
Images
Landscapes
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an instance extension method, device, equipment and medium, and relates to the technical field of natural language processing. The embodiment of the invention provides an instance extension method, which comprises the following steps: acquiring an example rule to be expanded, which comprises keyword information; and inputting the obtained example rule to be expanded into the example expansion model to generate an expanded example. Embodiments of the present invention provide an instance extension method, apparatus, device, and medium, so as to generate an extension instance richer than a sentence pattern of an instance to be extended.
Description
Technical Field
The embodiment of the invention relates to the technical field of natural language processing, in particular to an instance extension method, device, equipment and medium.
Background
For a search term (query) understanding task, a more common way is to adopt a form of parsing the query into an intention and a slot, i.e., marking key information in the query as a slot and marking the purpose of the query as an intention. For example, "how the weather is tomorrow", the intention is weather inquiry, and the slot position information is tomorrow.
In machine learning, queries are typically understood and answered based on a sequence annotation model. However, training of the sequence annotation model requires a large amount of instance data with annotation intent and slot information as training samples. At present, the main methods for acquiring example data are as follows: and identifying a small amount of manually marked instances to be expanded, and replacing the identified key information to obtain more expanded instances.
However, because only the key information in the instances to be extended is replaced, the schema of the extended instances generated is the same as the schema of the instances to be extended, resulting in a single schema of the extended instances generated. However, the extended instance of a single sentence has limited improvement on the training of the sequence labeling model.
Disclosure of Invention
Embodiments of the present invention provide an instance expansion method, apparatus, device, and medium to generate an expanded instance richer than the schema of the instance to be expanded.
In a first aspect, an embodiment of the present invention provides an instance extension method, where the method includes:
acquiring an example rule to be expanded, which comprises keyword information;
and inputting the obtained example rule to be expanded into the example expansion model to generate an expanded example.
Further, inputting the obtained rule of the instance to be extended into the instance extension model, and generating the extension instance includes:
and inputting the obtained example rule to be expanded and the random seed into an example expansion model to generate an expansion example.
Further, before inputting the obtained rule of the instance to be extended into the instance extension model and generating the extended instance, the method further includes:
determining an example rule to be expanded associated with the example to be expanded;
and training an initial model to obtain the example extension model by taking the example to be extended and the example rule to be extended associated with the example to be extended as samples.
Further, determining the rule of the to-be-expanded instance associated with the to-be-expanded instance comprises:
and performing text analysis on the examples to be expanded, and extracting rules of the examples to be expanded from the examples to be expanded according to text analysis results.
Further, determining the rule of the to-be-expanded instance associated with the to-be-expanded instance comprises:
performing text analysis on the obtained example to be expanded;
and matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
In a second aspect, an embodiment of the present invention further provides an instance extension apparatus, where the apparatus includes:
the rule obtaining module is used for obtaining an example rule to be expanded, which comprises keyword information;
and the instance generation module is used for inputting the acquired rule of the instance to be expanded into the instance expansion model to generate an expanded instance.
Further, the instance generation module includes:
and the example generating unit is used for inputting the acquired example rule to be expanded and the random seed into the example expansion model to generate an expansion example.
Further, the device also comprises:
the sample rule determining module is used for determining the rule of the example to be expanded related to the example to be expanded before inputting the obtained rule of the example to be expanded into the example expansion model and generating the expansion example;
and the model training module is used for training an initial model to obtain the example extension model by taking the example to be extended and the example rule to be extended associated with the example to be extended as samples.
Further, the sample rule determination module includes:
and the rule extraction unit is used for performing text analysis on the examples to be expanded and extracting the rules of the examples to be expanded from the examples to be expanded according to the text analysis result.
Further, the sample rule determination module includes:
the text analysis unit is used for performing text analysis on the acquired example to be expanded;
and the rule matching unit is used for matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement an instance extension method as in any of the embodiments of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the example expanding method according to any one of the embodiments of the present invention.
The embodiment of the invention generates the extended instance by inputting the rule of the instance to be extended into the instance extended model. Because the rule of the example to be expanded only limits the key information of the expansion example and does not limit the sentence pattern of the expansion example, the generated sentence pattern of the expansion example is generally different from the example to be expanded, so that the expansion example with rich sentence pattern is generated.
Meanwhile, the rule of the example to be expanded limits the key information of the expanded example, so that the semantics of the expanded example can be controlled based on the key information, and the generation of the escape expanded example is avoided.
Drawings
Fig. 1 is a flowchart of an example expanding method according to an embodiment of the present invention;
FIG. 2 is a flowchart of an example expanding method according to a second embodiment of the present invention;
FIG. 3a is a flowchart of an example expanding method according to a third embodiment of the present invention;
FIG. 3b is a flowchart of an example extended model training method according to a third embodiment of the present invention
Fig. 4 is a schematic structural diagram of an example expansion device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an example expanding method according to an embodiment of the present invention. The present embodiment is applicable to a case where instance expansion is performed based on a small number of instances provided. The method may be performed by an instance extension apparatus, which may be implemented by software and/or hardware. Referring to fig. 1, the example expansion method provided by this embodiment includes:
and S110, acquiring the example rule to be expanded, which comprises the keyword information.
The keyword information may be any information describing the extended instance. The rule of the example to be expanded is used for limiting any part of the expanded example. Specifically, the keyword information may be keywords or relationships between keywords. Typically, the keyword information may be at least one of an intention of the text, a slot position, and an order of the slot position.
For example, the example rule to be extended may be: "from" is followed by a start. The example rule to be expanded may also be: "to" is followed by a terminating end (end). The example rule to be expanded may also be: the start is before the end.
On the basis of this, those skilled in the art can also think of many example rules to be expanded, and this embodiment does not set any limit to this.
Alternatively, the example rule to be expanded may be input by the user, or may be extracted from an exemplary sentence input by the user.
Specifically, extracting the example rule to be expanded from an exemplary sentence input by the user comprises:
identifying intents, slot positions and the sequence of the slot positions in the sentence;
at least one of the identified intent, the slot position, and the order of the slots is taken as an instance rule to be expanded.
And S120, inputting the acquired example rule to be expanded into the example expansion model to generate an expansion example.
The instance expansion model is trained in advance and used for generating an expansion instance which accords with the rule of the instance to be expanded according to the input rule of the instance to be expanded.
Alternatively, the extension instance may be a phrase or a text paragraph including a plurality of sentences. Typically, the expanded instance may be a sentence.
According to the technical scheme of the embodiment of the invention, the example rule to be expanded is input into the example expansion model, so that the expansion example is generated. Because the rule of the example to be expanded only limits the key information of the expansion example and does not limit the sentence pattern of the expansion example, the generated sentence pattern of the expansion example is generally different from the example to be expanded, so that the expansion example with rich sentence pattern is generated.
Meanwhile, the rule of the example to be expanded limits the key information of the expanded example, so that the semantics of the expanded example can be controlled based on the key information, and the generation of the escape expanded example is avoided.
A plurality of extended examples are obtained according to an example rule to be extended so as to realize the extension of the examples. Inputting the obtained example rule to be expanded into an example expansion model, and generating an expansion example comprises the following steps:
and inputting the obtained example rule to be expanded and the random seed into an example expansion model to generate an expansion example.
Specifically, to realize generation of an extended instance with a set required number, the obtained rule of the instance to be extended and the random seed are input into an extended instance model, and generating the extended instance includes:
inputting an obtained example rule to be expanded and a random seed into an example expansion model to generate an expansion example;
if the number of the expansion instances generated based on the rules of the instances to be expanded is smaller than a set requirement number threshold, adjusting random seeds, inputting the adjusted random seeds and the rules of the instances to be expanded into an instance expansion model to generate expansion instances, and enabling the number of the expansion instances generated based on the rules of the instances to be expanded to be equal to the set requirement number threshold.
Example two
Fig. 2 is a flowchart of an example expanding method according to a second embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 2, the example expansion method provided by this embodiment includes:
s210, determining the rules of the examples to be expanded associated with the examples to be expanded.
Specifically, determining the rule of the to-be-expanded instance associated with the to-be-expanded instance includes:
and performing text analysis on the examples to be expanded, and extracting rules of the examples to be expanded from the examples to be expanded according to text analysis results.
The determination of the example rule to be expanded can achieve the following effects: and training an instance extension model meeting the requirements of the user only according to a small number of instances to be extended provided by the user.
However, there are more rules of the examples to be expanded extracted from the examples to be expanded according to the text analysis result of the examples to be expanded, and it is not of interest to the user that the extracted more rules of the examples to be expanded may include part of the rules of the examples to be expanded. The example rule to be expanded, which is not concerned by the user, is adopted as a sample for training, so that the accuracy of the example expansion model is reduced, and resources are wasted.
Therefore, determining the rule of the to-be-expanded instance associated with the to-be-expanded instance may further include:
performing text analysis on the obtained example to be expanded;
and matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
The matching of the text analysis result and the obtained example rule to be expanded comprises the following steps:
extracting an example rule to be expanded from the example to be expanded according to the text analysis result;
and matching the extracted example rule to be expanded with the acquired example rule to be expanded.
The determination of the example rule to be expanded can achieve the following effects: establishing association for a small number of examples to be expanded provided by a user and example rules to be expanded provided by the user, and training an example expansion model meeting the requirements of the user by using the associated examples to be expanded and the example rules to be expanded as samples.
The example rules to be expanded, which are taken as training samples, are limited by the example rules to be expanded, which are provided by the user, so that the example rules to be expanded, which are taken as training samples, are all the example rules to be expanded, which are concerned by the user.
S220, taking the example to be expanded and the example rule to be expanded associated with the example to be expanded as samples, and training an initial model to obtain the example expansion model.
And S230, inputting the acquired example rule to be expanded into the example expansion model to generate an expansion example.
According to the technical scheme, the example rule to be expanded associated with the example to be expanded is determined according to the example to be expanded, the example to be expanded and the example rule to be expanded associated with the example to be expanded are used as samples, and an example expansion model is obtained through training. Thus realizing the training of the example extension model.
EXAMPLE III
Fig. 3a is a flowchart of an example expanding method according to a third embodiment of the present invention. The present embodiment is an alternative proposed on the basis of the above-described embodiments. Referring to fig. 3a, the example expansion method provided by this embodiment includes:
model generation under the line and example generation on the line.
Specifically, referring to fig. 3b, the model generation under line comprises:
extracting a plurality of examples to be expanded from a database in which a large amount of data is stored;
extracting a plurality of example rules to be expanded from the examples to be expanded;
the example rule to be expanded includes keywords or relationships among the keywords, for example, keyword a is to precede keyword B.
And taking an example rule to be expanded and an example to be expanded which accords with the example rule to be expanded as a pair of training samples, and putting the training samples into a machine learning model for training to obtain an example expansion model.
The input of the instance extension model is the rule of the instance to be extended, and the output is the extended instance.
Specifically, the online instance generation includes:
and inputting the rule of the example to be expanded to the trained example expansion model, and outputting the expanded example by the example expansion model.
According to the technical scheme of the embodiment of the invention, the instance extension model is obtained by training based on a small number of instances to be extended, and the extended instances are generated by using the instance extension model, so that the labor cost is reduced. And because the rule of the example to be expanded only limits the key information of the expansion example, the generated sentence pattern of the expansion example is generally different from the example to be expanded, so that the expansion example with rich sentence pattern is generated.
Meanwhile, the rule of the example to be expanded limits the key information of the expanded example, so that the expanded example can be controlled based on the key information, and the generation of the escape expanded example is avoided.
It should be noted that, through the technical teaching of the present embodiment, a person skilled in the art may motivate a combination of any one of the implementations described in the above embodiments to implement the example extension of the example to be extended.
Example four
Fig. 4 is a schematic structural diagram of an example expansion device according to a fourth embodiment of the present invention. Referring to fig. 4, an example expanding apparatus provided in this embodiment includes: a rule acquisition module 10 and an instance generation module 20.
The acquiring module 10 is configured to acquire an example rule to be expanded, which includes keyword information;
and the instance generating module 20 is configured to input the obtained rule of the instance to be extended into the instance extension model, and generate an extended instance.
According to the technical scheme of the embodiment of the invention, the example rule to be expanded is input into the example expansion model, so that the expansion example is generated. Because the rule of the example to be expanded only limits the key information of the expansion example and does not limit the sentence pattern of the expansion example, the generated sentence pattern of the expansion example is generally different from the example to be expanded, so that the expansion example with rich sentence pattern is generated.
Meanwhile, the rule of the example to be expanded limits the key information of the expanded example, so that the semantics of the expanded example can be controlled based on the key information, and the generation of the escape expanded example is avoided.
Further, the instance generation module includes: an instance generation unit.
The example generating unit is used for inputting the acquired example rule to be expanded and the random seed into the example expansion model to generate an expansion example.
Further, the device also comprises: the system comprises a sample rule determining module and a model training module.
The sample rule determining module is used for determining the rule of the example to be expanded associated with the example to be expanded before inputting the obtained rule of the example to be expanded into the example expansion model and generating the expansion example;
and the model training module is used for training an initial model to obtain the example extension model by taking the example to be extended and the example rule to be extended associated with the example to be extended as samples.
Further, the sample rule determination module includes: and a rule extraction unit.
The rule extraction unit is used for performing text analysis on the example to be expanded and extracting the rule of the example to be expanded from the example to be expanded according to the text analysis result.
Further, the sample rule determination module includes: a text analysis unit and a rule matching unit.
The text analysis unit is used for performing text analysis on the acquired to-be-expanded example;
and the rule matching unit is used for matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an apparatus according to a fifth embodiment of the present invention. Fig. 5 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 5 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present invention.
As shown in FIG. 5, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing an example extension method provided by an embodiment of the present invention, the method including:
acquiring an example rule to be expanded, which comprises keyword information;
and inputting the obtained example rule to be expanded into the example expansion model to generate an expanded example.
EXAMPLE six
Sixth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the example expanding method according to any one of the embodiments of the present invention. The method comprises the following steps:
acquiring an example rule to be expanded, which comprises keyword information;
and inputting the obtained example rule to be expanded into the example expansion model to generate an expanded example.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An instance expansion method, comprising:
acquiring an example rule to be expanded, wherein the example rule comprises keyword information, and the keyword information comprises at least one of an intention of a text, a slot position and a sequence of the slot position;
inputting the obtained rules of the instances to be expanded into the instance expansion model to generate expanded instances;
before inputting the obtained rules of the instances to be expanded into the instance expansion model and generating the expanded instances, the method further comprises the following steps:
determining an example rule to be expanded associated with the example to be expanded;
and training an initial model to obtain the example extension model by taking the example to be extended and the example rule to be extended associated with the example to be extended as samples.
2. The method of claim 1, wherein the obtained rules of the instances to be extended are input into an instance extension model, and generating the extended instances comprises:
and inputting the obtained example rule to be expanded and the random seed into an example expansion model to generate an expansion example.
3. The method of claim 1, wherein determining the to-be-expanded instance rule associated with the to-be-expanded instance comprises:
and performing text analysis on the examples to be expanded, and extracting rules of the examples to be expanded from the examples to be expanded according to text analysis results.
4. The method of claim 1, wherein determining the to-be-expanded instance rule associated with the to-be-expanded instance comprises:
performing text analysis on the obtained example to be expanded;
and matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
5. An instance expansion apparatus, comprising:
the rule obtaining module is used for obtaining an example rule to be expanded, wherein the example rule comprises keyword information, and the keyword information comprises at least one of an intention of a text, a slot position and a sequence of the slot position;
the instance generation module is used for inputting the obtained rules of the instances to be expanded into the instance expansion model to generate the expansion instances;
the sample rule determining module is used for determining the rule of the example to be expanded related to the example to be expanded before inputting the obtained rule of the example to be expanded into the example expansion model and generating the expansion example;
and the model training module is used for training an initial model to obtain the example extension model by taking the example to be extended and the example rule to be extended associated with the example to be extended as samples.
6. The apparatus of claim 5, wherein the instance generation module comprises:
and the example generating unit is used for inputting the acquired example rule to be expanded and the random seed into the example expansion model to generate an expansion example.
7. The apparatus of claim 6, wherein the sample rule determining module comprises:
and the rule extraction unit is used for performing text analysis on the examples to be expanded and extracting the rules of the examples to be expanded from the examples to be expanded according to the text analysis result.
8. The apparatus of claim 6, wherein the sample rule determining module comprises:
the text analysis unit is used for performing text analysis on the acquired example to be expanded;
and the rule matching unit is used for matching the text analysis result with the acquired example rule to be expanded, and taking the example rule to be expanded which is consistent in matching as the example rule to be expanded associated with the example to be expanded.
9. An instance expansion apparatus, the apparatus comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the instance extension method of any of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the example extension method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714308.0A CN108932326B (en) | 2018-06-29 | 2018-06-29 | Instance extension method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714308.0A CN108932326B (en) | 2018-06-29 | 2018-06-29 | Instance extension method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108932326A CN108932326A (en) | 2018-12-04 |
| CN108932326B true CN108932326B (en) | 2021-02-19 |
Family
ID=64447323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810714308.0A Active CN108932326B (en) | 2018-06-29 | 2018-06-29 | Instance extension method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108932326B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301227A (en) * | 2017-06-21 | 2017-10-27 | 北京百度网讯科技有限公司 | Search information analysis method and device based on artificial intelligence |
| CN107526725A (en) * | 2017-09-04 | 2017-12-29 | 北京百度网讯科技有限公司 | The method and apparatus for generating text based on artificial intelligence |
| CN108052659A (en) * | 2017-12-28 | 2018-05-18 | 北京百度网讯科技有限公司 | Searching method, device and electronic equipment based on artificial intelligence |
| CN108090169A (en) * | 2017-12-14 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | Question sentence extended method and device, storage medium, terminal |
| CN108304444A (en) * | 2017-11-30 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information query method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017027234A (en) * | 2015-07-17 | 2017-02-02 | 日本電信電話株式会社 | Frame creating device, method, and program |
| CN105786794B (en) * | 2016-02-05 | 2018-09-04 | 青岛理工大学 | A kind of question and answer are to search method and community's question and answer searching system |
| CN105912630B (en) * | 2016-04-07 | 2020-01-31 | 北京搜狗信息服务有限公司 | information expansion method and device |
| CN106294688A (en) * | 2016-08-05 | 2017-01-04 | 浪潮软件集团有限公司 | Query expansion method, device and system based on user characteristic analysis |
| US10558756B2 (en) * | 2016-11-03 | 2020-02-11 | International Business Machines Corporation | Unsupervised information extraction dictionary creation |
-
2018
- 2018-06-29 CN CN201810714308.0A patent/CN108932326B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301227A (en) * | 2017-06-21 | 2017-10-27 | 北京百度网讯科技有限公司 | Search information analysis method and device based on artificial intelligence |
| CN107526725A (en) * | 2017-09-04 | 2017-12-29 | 北京百度网讯科技有限公司 | The method and apparatus for generating text based on artificial intelligence |
| CN108304444A (en) * | 2017-11-30 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information query method and device |
| CN108090169A (en) * | 2017-12-14 | 2018-05-29 | 上海智臻智能网络科技股份有限公司 | Question sentence extended method and device, storage medium, terminal |
| CN108052659A (en) * | 2017-12-28 | 2018-05-18 | 北京百度网讯科技有限公司 | Searching method, device and electronic equipment based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108932326A (en) | 2018-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052577B (en) | Universal text content mining method, device, server and storage medium | |
| CN109002510B (en) | Dialogue processing method, device, equipment and medium | |
| CN110647614B (en) | Intelligent question-answering method, device, medium and electronic equipment | |
| US10657325B2 (en) | Method for parsing query based on artificial intelligence and computer device | |
| CN107291828B (en) | Spoken language query analysis method and device based on artificial intelligence and storage medium | |
| US11409813B2 (en) | Method and apparatus for mining general tag, server, and medium | |
| CN108932294B (en) | Resume data processing method, device, equipment and storage medium based on index | |
| US11521603B2 (en) | Automatically generating conference minutes | |
| CN107221328B (en) | Method and device for positioning modification source, computer equipment and readable medium | |
| WO2018205389A1 (en) | Voice recognition method and system, electronic apparatus and medium | |
| JP6909832B2 (en) | Methods, devices, equipment and media for recognizing important words in audio | |
| CN109299320B (en) | Information interaction method and device, computer equipment and storage medium | |
| AU2017408800B2 (en) | Method and system of mining information, electronic device and readable storable medium | |
| CN108932218B (en) | Instance extension method, device, equipment and medium | |
| CN110069698B (en) | Information pushing method and device | |
| CN110569335B (en) | Triple verification method and device based on artificial intelligence and storage medium | |
| CN107909088B (en) | Method, apparatus, device and computer storage medium for obtaining training samples | |
| CN111597800B (en) | Method, device, equipment and storage medium for obtaining synonyms | |
| CN110377750B (en) | Comment generation method, comment generation device, comment generation model training device and storage medium | |
| US20200218746A1 (en) | Method and apparatus for presenting information | |
| CN111259262A (en) | Information retrieval method, device, equipment and medium | |
| CN111708800A (en) | Query method and device and electronic equipment | |
| CN110737824B (en) | Content query method and device | |
| CN111738791B (en) | Text processing method, device, equipment and storage medium | |
| WO2020052060A1 (en) | Method and apparatus for generating correction statement |
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 |