CN111159384B - Rule-based sentence generation method and device - Google Patents
Rule-based sentence generation method and device Download PDFInfo
- Publication number
- CN111159384B CN111159384B CN201911414731.XA CN201911414731A CN111159384B CN 111159384 B CN111159384 B CN 111159384B CN 201911414731 A CN201911414731 A CN 201911414731A CN 111159384 B CN111159384 B CN 111159384B
- Authority
- CN
- China
- Prior art keywords
- question
- syntax
- attributes
- speech
- attribute
- 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
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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a sentence generating method and device based on rules, wherein the sentence generating method based on the rules comprises the following steps: responding to attributes of an inquiry sentence to be generated submitted by a user, and inquiring whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of inquiry sentences corresponding to the attributes; if the attribute exists in the syntax library, at least one question sentence pattern corresponding to the attribute is obtained from the syntax library; and generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern. According to the scheme of the embodiment of the application, a traditional rule editing mode of firstly preparing the question method and then writing the regular rule is not needed, but possible Chinese sentence patterns are matched through the part of speech of each attribute, the rule editing efficiency is greatly improved, and after the sentence patterns are prepared, a user only needs to care about the part of speech related to each attribute.
Description
Technical Field
The invention belongs to the technical field of intelligent conversation, and particularly relates to a sentence generation method and device based on rules.
Background
In the related art, the current query based on the knowledge graph mainly depends on 2 ways of matching, one is matching based on a statistical model, and the other is matching based on a regular rule. For the matching of regular rules, developers generally edit and manage files in a Json format in the market.
The inventor finds that the prior scheme has at least the following defects in the process of implementing the application: on one hand, the editor is not provided with a visual interface, so that the query and the writing of the rule are very inconvenient; on the other hand, the rule editing can utilize functions such as synonym management and multiplexing rule management, so that the editing efficiency is greatly improved, but the cost achieved through Json is too high, and a large amount of time is consumed.
Disclosure of Invention
The embodiment of the invention provides a sentence generation method and device based on rules, which are used for solving at least one of the technical problems.
In a first aspect, an embodiment of the present invention provides a rule-based sentence generation method, including: responding to attributes of an inquiry sentence to be generated submitted by a user, and inquiring whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of inquiry sentence patterns corresponding to the attributes; if the attribute exists in the syntax library, at least one question sentence pattern corresponding to the attribute is obtained from the syntax library; and generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
In a second aspect, an embodiment of the present invention provides a rule-based sentence generation apparatus, including: the attribute query module is configured to respond to attributes of question sentences to be generated submitted by users and query whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of question sentence patterns corresponding to the attributes; the syntax library acquisition module is configured to acquire at least one syntax sentence corresponding to the attribute from the syntax library if the attribute exists in the syntax library; and a question sentence generating module configured to generate a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the rule-based sentence generation method of any of the embodiments of the invention.
In a fourth aspect, the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the steps of the rule-based sentence generation method according to any one of the embodiments of the present invention.
The scheme provided by the method and the device does not need to use the traditional rule editing mode of firstly preparing the question method and then writing the regular rule, but matches the possible Chinese sentence patterns through the part of speech of each attribute, thereby greatly improving the efficiency of rule editing, and after the sentence patterns are prepared, the user only needs to care about the part of speech related to each attribute; aiming at the maintained attributes, the user can directly reuse the part of speech of the attributes to directly generate a batch of questions; considering the scenario of the question method first, users may not exhaust the question method for different attributes, but based on parts of speech and sentence patterns, most of the user question methods can be matched.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a method for rule-based sentence generation according to an embodiment of the present invention;
FIG. 2 is a flow chart of another rule-based sentence generation method according to an embodiment of the present invention;
FIG. 3 is an example of an interface of a conventional rule editor of the prior art;
FIG. 4 is a diagram illustrating an implementation of editing based on parts of speech and sentence patterns according to an embodiment of the present invention;
FIG. 5 is a block diagram of a rule-based sentence generation apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
Referring to fig. 1, which shows a flowchart of an embodiment of the rule-based sentence generation method of the present application, the rule-based sentence generation method of the present application may be applied to a device that needs to generate example sentences, for example, when a user customizes his or her own product on an intelligent speech platform (e.g., a think-away DUI platform), some sentences with labels need to be given, the more example sentences the better the recognition and understanding capability of the product, and the present application is not limited herein.
As shown in fig. 1, in step 101, in response to a property of a to-be-generated question sentence submitted by a user, querying whether the property exists in a syntax base;
in step 102, if the attribute exists in the syntax library, at least one question and sentence pattern corresponding to the attribute is obtained from the syntax library;
in step 103, a plurality of question sentences corresponding to the attributes are generated based on the at least one question sentence pattern.
In this embodiment, for step 101, the rule-based sentence generation apparatus queries an existing syntax base, which stores at least a plurality of attributes and a plurality of question patterns corresponding to the plurality of attributes, according to the attribute to be generated by the question sentence submitted by the user, so that for step 102, if the attribute exists in the syntax base, the plurality of question patterns corresponding to the attribute can be obtained by querying the syntax base. For example, for a question sentence pattern of names, "name? Is "? Is called/called? "wait for a question and sentence pattern, then for step 103, a plurality of question and sentences corresponding to the attribute can be generated based on the question and sentence pattern.
In the method of this embodiment, by establishing the syntax library, when the attribute submitted by the user is acquired, a plurality of question-sentence patterns corresponding to the attribute in the syntax library are queried, and then a batch of question-sentence for the attribute can be generated according to the question-sentence patterns, without requiring the user to exemplify the question, if the attribute exists in the syntax library, the user only needs to submit the attribute for querying.
Referring to FIG. 2, a flow diagram of another embodiment of the rule-based sentence generation method of the present application is shown. The scheme of the flow chart is mainly a scheme which is additionally explained for the additional steps of the scheme of the flow chart 1.
As shown in fig. 2, in step 201, if the attribute does not exist in the syntax base, at least one part of speech corresponding to the attribute is obtained;
in step 202, querying at least one question and sentence pattern corresponding to the at least one part of speech in the syntactic base based on the at least one part of speech;
in step 203, a plurality of question sentences corresponding to the attributes are generated based on the at least one question sentence pattern.
In this embodiment, for step 201, after "querying whether the attribute exists in the syntax library," the rule-based sentence generation apparatus needs to acquire at least one part of speech corresponding to the attribute if the attribute does not exist in the syntax library, and the acquisition mode may be acquired from the user at any time or may be an inquiry from another place, which is not limited herein. For step 202, the rule-based sentence generation apparatus queries, based on at least one part of speech, at least one question sentence pattern corresponding to the at least one part of speech in the syntax base, wherein the syntax base further stores a plurality of parts of speech and a plurality of question sentence patterns corresponding to the plurality of parts of speech; finally, with respect to step 203, the rule-based sentence generation means generates a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
For example, the attribute of the story source may be a noun, and the corresponding question and sentence pattern may be "a verb with entity as subject and attribute as noun type object", and the corresponding question and sentence pattern may be "quote/ceremony? Go/come ", may also be used as prepositions, and the corresponding question-and-law sentence pattern, for example," uses entity as subject and has property as verb of preposition object ", may be" quote/record ", may also be used for" uses entity as subject and has property as verb of preposition ", and may be" record/record ", and will not be described herein again.
In the method of this embodiment, for an attribute that does not exist in the syntax base, at least one part of speech corresponding to the attribute may be obtained first, and then the syntax base is queried according to the part of speech to obtain a corresponding question sentence pattern, so that a batch of question sentences can be generated based on the question sentence pattern.
In some optional embodiments, the method further comprises: and filling the attribute which does not exist in the syntax base and at least one question sentence pattern corresponding to the nonexistent attribute into the syntax base. Thus, the syntax library can be continuously refined, and then a user can provide attributes to generate a batch of question sentences.
In a further alternative embodiment, the syntactic library is exhaustive of Chinese question sentences and parts of speech. The commonly used sentence patterns are divided into dozens of types, such as judgment sentence, passive sentence, preposition of object, component omission sentence, preposition of pronoun object in negative sentence, preposition of pronoun object in question sentence, preposition of preposition object, postposition of fixed language, postposition of idiom, postposition of subject and the like. There are also 14 parts of speech, such as nouns, verbs, adjectives, quantifiers, pronouns, various kinds of virtual words, etc.
Further optionally, querying at least one question sentence pattern corresponding to the at least one part of speech in the syntactic base based on the at least one part of speech includes: filling the at least one part of speech into the syntax library, and generating a plurality of question methods corresponding to the attributes according to the slot positions required by a plurality of question method sentences in the syntax library. Therefore, the acquired parts of speech can be filled into the required slots in the question sentence pattern to generate a plurality of question methods corresponding to the attributes, and then a batch of question sentences can be generated according to the plurality of question methods.
The following description is given to a specific example describing some problems encountered by the inventor in implementing the present invention and a final solution so as to enable those skilled in the art to better understand the solution of the present application.
When the above problems are solved, the technical solutions of the present application are not easily conceived by those skilled in the art because: on one hand, in the working process, the problem needing to be solved mainly is the editing problem of a large number of question and law rules, while the Chinese question and law sentence pattern is grammatically infertile, and the scheme mainly solves the editing and generating of the question and law rules and answer rules based on the knowledge graph; on the other hand, in the rule editor of the scheme, the rules are generated based on the Chinese sentence patterns and the grammar, a certain linguistic and literature professional basis is needed, practitioners in the industry are mainly technical personnel, the cut-in from the aspect of the linguistic and literature specialty is not easy, and the generation of the rules by utilizing the parts of speech, the Chinese sentence patterns and the grammar is considered.
In the present invention, we propose a matching scheme based on Chinese parts of speech, grammar and sentence pattern to generate rules.
The technical innovation points of the invention are as follows:
the conventional rule editor needs to prepare different questions based on attributes and edit the questions one by one, the workload is huge, and the same questions with different attributes cannot be reused, please refer to fig. 3, which shows an interface example of the conventional rule editor.
In the scheme, a user does not need to prepare different question methods based on attributes, only needs to prepare all sentence patterns and part-of-speech slots required by the sentence patterns, and can greatly improve the rule compiling efficiency by maintaining the sentence pattern library and the part-of-speech library.
(1) As the Chinese question and sentence pattern is finite, there are dozens of commonly used sentence patterns after subdivision, such as judgment sentence, passive sentence, object preposition, component omission sentence, pronoun of pronoun object in negative sentence, pronoun of pronoun object in question sentence, preposition of preposition object in preposition object, postposition of fixed language, postposition of idiom, postposition of subject language, etc. There are also 14 parts of speech, such as nouns, verbs, adjectives, quantifiers, pronouns, various kinds of imaginary words, etc. By establishing a syntax and grammar library, a user only needs to fill the part of speech associated with each attribute into the table aiming at each attribute, and can generate a plurality of question methods according to the slot positions required by the sentence correlation.
(2) And (3) constructing a syntax base, namely combining and matching sentence patterns in the syntax base according to a plurality of parts of speech filled by the user, and then generating a corresponding regular rule.
Refer to fig. 4, which illustrates an implementation of editing based on parts of speech and sentence patterns provided by an embodiment of the present application.
The scheme of this application can realize following technological effect:
1. the scheme does not need to use the traditional rule editing mode of firstly preparing the question method and then writing the regular rule, but matches the possible Chinese sentence patterns through the part of speech of each attribute, thereby greatly improving the efficiency of rule editing, and after the sentence patterns are prepared, the user only needs to care about the part of speech related to each attribute;
2. aiming at the maintained attributes, the user can directly reuse the part of speech of the attributes to directly generate a batch of questions;
3. considering the scenario of the question method first, users may not exhaust the question method for different attributes, but based on parts of speech and sentence patterns, most of the user question methods can be matched.
Referring to fig. 5, a block diagram of a rule-based sentence generation apparatus according to an embodiment of the invention is shown.
As shown in fig. 5, the rule-based sentence generation apparatus 500 includes an attribute query module 510, a question sentence acquisition module 520, and a question sentence generation module 530.
The attribute query module 510 is configured to query, in response to an attribute of a question sentence to be generated, submitted by a user, whether the attribute exists in a syntax library, where the syntax library at least stores a plurality of attributes and a plurality of question sentences corresponding to the plurality of attributes; a question and sentence pattern obtaining module 520 configured to, if the attribute exists in the syntax base, obtain at least one question and sentence pattern corresponding to the attribute from the syntax base; and a question sentence generating module 530 configured to generate a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
In some optional embodiments, the apparatus further comprises: a part-of-speech obtaining module (not shown in the figure) configured to obtain at least one part-of-speech corresponding to the attribute if the attribute does not exist in the syntax base; a question sentence pattern query module (not shown in the figure) configured to query at least one question sentence pattern corresponding to the at least one part of speech in the syntax base based on the at least one part of speech, wherein the syntax base further stores a plurality of parts of speech and a plurality of question sentence patterns corresponding to the plurality of parts of speech; the above-mentioned question sentence generating module is configured to generate a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
Further optionally, the apparatus further comprises: a syntax base update module (not shown in the figure) configured to populate the syntax base with attributes that do not exist in the syntax base and at least one question sentence corresponding to the non-existing attributes.
It should be understood that the modules depicted in fig. 5 correspond to various steps in the methods described with reference to fig. 1 and 2. Thus, the operations and features described above for the method and the corresponding technical effects are also applicable to the modules in fig. 5, and are not described again here.
It should be noted that the modules in the embodiments of the present application are not intended to limit the solution of the present application, for example, the attribute query module may be described as a module that queries whether the attribute exists in the syntax library in response to the attribute of the query sentence to be generated, which is submitted by the user. In addition, the related function module may also be implemented by a hardware processor, for example, the attribute query module may also be implemented by a processor, which is not described herein again.
In other embodiments, an embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores computer-executable instructions, and the computer-executable instructions may execute the rule-based sentence generation method in any of the above method embodiments;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
responding to attributes of an inquiry sentence to be generated submitted by a user, and inquiring whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of inquiry sentences corresponding to the attributes;
if the attribute exists in the syntax library, at least one question sentence pattern corresponding to the attribute is obtained from the syntax library;
and generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the rule-based sentence generation apparatus, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer-readable storage medium optionally includes a memory remotely located from the processor, which may be connected to the rule-based sentence generation apparatus over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform any of the above-described rule-based sentence generation methods.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device includes: one or more processors 610 and a memory 620, one processor 610 being illustrated in fig. 6. The apparatus of the rule-based sentence generation method may further include: an input device 630 and an output device 640. The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other means, such as the bus connection in fig. 6. The memory 620 is a non-volatile computer-readable storage medium as described above. The processor 610 executes various functional applications of the server and data processing, i.e., implements the rule-based sentence generation method of the above-described method embodiment, by running the non-volatile software programs, instructions, and modules stored in the memory 620. The input means 630 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the rule-based sentence generation means. The output device 640 may include a display device such as a display screen.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
As an embodiment, the electronic device applied to the rule-based sentence generation apparatus includes:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
responding to attributes of an inquiry sentence to be generated submitted by a user, and inquiring whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of inquiry sentences corresponding to the attributes;
if the attribute exists in the syntax library, at least one question sentence pattern corresponding to the attribute is obtained from the syntax library;
and generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has mobile internet access characteristics. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A rule-based sentence generation method, comprising:
responding to attributes of an inquiry sentence to be generated submitted by a user, and inquiring whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of inquiry sentences corresponding to the attributes;
if the attribute exists in the syntax library, at least one question sentence pattern corresponding to the attribute is obtained from the syntax library;
generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern;
if the attribute does not exist in the syntax library, acquiring at least one part of speech corresponding to the attribute;
inquiring at least one question sentence pattern corresponding to the at least one part of speech in the syntax base based on the at least one part of speech, wherein the syntax base also stores a plurality of parts of speech and a plurality of question sentence patterns corresponding to the plurality of parts of speech;
and generating a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
2. The method of claim 1, wherein the method further comprises:
and filling the attribute which does not exist in the syntax base and at least one question sentence pattern corresponding to the nonexistent attribute into the syntax base.
3. The method of any of claims 1-2, wherein the syntactic base is exhaustive of Chinese question sentences and parts of speech.
4. The method of claim 3, wherein querying the syntactic base for at least one question sentence in the syntactic base corresponding to the at least one part of speech, based on the at least one part of speech, comprises:
filling the at least one part of speech into the syntax library, and generating a plurality of question methods corresponding to the attributes according to the slot positions required by a plurality of question method sentences in the syntax library.
5. A rule-based sentence generation apparatus comprising:
the attribute query module is configured to respond to attributes of question sentences to be generated submitted by users and query whether the attributes exist in a syntax library, wherein the syntax library at least stores a plurality of attributes and a plurality of question sentence patterns corresponding to the attributes;
the syntax library acquisition module is configured to acquire at least one syntax sentence corresponding to the attribute from the syntax library if the attribute exists in the syntax library;
a question sentence generating module configured to generate a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern;
a part-of-speech obtaining module configured to obtain at least one part-of-speech corresponding to the attribute if the attribute does not exist in the syntax base;
the query module of the question sentence pattern is configured to query at least one question sentence pattern corresponding to the at least one part of speech in the syntax base based on the at least one part of speech, wherein the syntax base also stores a plurality of parts of speech and a plurality of question sentence patterns corresponding to the plurality of parts of speech;
the question sentence generating module is configured to generate a plurality of question sentences corresponding to the attributes based on the at least one question sentence pattern.
6. The apparatus of claim 5, wherein the apparatus further comprises:
a syntax base updating module configured to fill in the syntax base attributes that do not exist in the syntax base and at least one question sentence corresponding to the non-existing attributes.
7. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any one of claims 1 to 4.
8. A storage medium having stored thereon a computer program, characterized in that the program, when being executed by a processor, is adapted to carry out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911414731.XA CN111159384B (en) | 2019-12-31 | 2019-12-31 | Rule-based sentence generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911414731.XA CN111159384B (en) | 2019-12-31 | 2019-12-31 | Rule-based sentence generation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111159384A CN111159384A (en) | 2020-05-15 |
| CN111159384B true CN111159384B (en) | 2022-07-08 |
Family
ID=70560079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911414731.XA Active CN111159384B (en) | 2019-12-31 | 2019-12-31 | Rule-based sentence generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111159384B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686024B (en) * | 2020-12-31 | 2023-12-22 | 竹间智能科技（上海）有限公司 | Syntax analysis method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140330551A1 (en) * | 2013-05-06 | 2014-11-06 | Facebook, Inc. | Methods and systems for generation of a translatable sentence syntax in a social networking system |
| CN109783819A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Regular expression generation method and system |
| CN110489538A (en) * | 2019-08-27 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Sentence answer method, device and electronic equipment based on artificial intelligence |
-
2019
- 2019-12-31 CN CN201911414731.XA patent/CN111159384B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140330551A1 (en) * | 2013-05-06 | 2014-11-06 | Facebook, Inc. | Methods and systems for generation of a translatable sentence syntax in a social networking system |
| CN109783819A (en) * | 2019-01-18 | 2019-05-21 | 广东小天才科技有限公司 | Regular expression generation method and system |
| CN110489538A (en) * | 2019-08-27 | 2019-11-22 | 腾讯科技（深圳）有限公司 | Sentence answer method, device and electronic equipment based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111159384A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11334692B2 (en) | Extracting a knowledge graph from program source code | |
| US11461377B2 (en) | Generating three-dimensional scenes from natural language requests | |
| CN107741976B (en) | Intelligent response method, device, medium and electronic equipment | |
| US11710486B2 (en) | Removal of identifying traits of a user in a virtual environment | |
| CN110334347A (en) | Information processing method, relevant device and storage medium based on natural language recognition | |
| CN110998590B (en) | Domain specific vocabulary driven preresolved | |
| Derwojedowa et al. | Words, concepts and relations in the construction of Polish WordNet | |
| CN111553138B (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN112416962A (en) | Data query method, device and storage medium | |
| CN110727782A (en) | Question and answer corpus generation method and system | |
| CN116955569A (en) | Dialogue generation method, device, equipment and storage medium | |
| EP4075263A1 (en) | Dependency graph generation method and apparatus, device, storage medium, and program product | |
| CN111159384B (en) | Rule-based sentence generation method and device | |
| CN117971661A (en) | Large model test method and device, electronic equipment and storage medium | |
| KR20190131270A (en) | The syntax grammar rules automatic generation method of understanding user query intention | |
| US20230214688A1 (en) | Method, Apparatus for Determining Answer to Question, Device, Storage Medium and Program Product | |
| CN110998587B (en) | Method and system for domain-specific lexical analysis | |
| CN111966803B (en) | Dialogue simulation method and device, storage medium and electronic equipment | |
| CN116010571A (en) | Knowledge base construction method, information query method, device and equipment | |
| CN114595702A (en) | Text translation model training method, text translation method and related device | |
| CN109145084B (en) | Data processing method, data processing device and server | |
| CN106682221B (en) | Question-answer interaction response method and device and question-answer system | |
| US10303764B2 (en) | Using multilingual lexical resources to improve lexical simplification | |
| CN111858949B (en) | Method and device for expanding regular expression based on knowledge graph and learning equipment | |
| WO2024187581A1 (en) | Multi-round dialogue method and apparatus for dynamic government affair updating, and electronic device |
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 | ||
| CB02 | Change of applicant information |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant before: AI SPEECH Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |