CN112015876A - Time analysis method and device, electronic equipment and storage medium - Google Patents
Time analysis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112015876A CN112015876A CN202010877950.8A CN202010877950A CN112015876A CN 112015876 A CN112015876 A CN 112015876A CN 202010877950 A CN202010877950 A CN 202010877950A CN 112015876 A CN112015876 A CN 112015876A
- Authority
- CN
- China
- Prior art keywords
- target
- question
- time
- crf model
- analysis result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—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
-
- 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
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of artificial intelligence, and discloses a time analysis method, which comprises the following steps: acquiring at least one target question-answer sentence to be analyzed; and analyzing the target question-answer sentence by utilizing a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence. According to the time analysis method, the accuracy of the analysis result is improved by using the rule database and the CRF model trained in advance to analyze the target question and answer sentence. The application also discloses a time analysis device, electronic equipment and a storage medium.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and for example, to a time analysis method, an apparatus, an electronic device, and a storage medium.
Background
At present, in many service scenes in the field of artificial intelligence question answering, accurate identification of time factors in question sentences asked by users is particularly important. The related technology mainly adopts the modes of machine learning, deep learning and the like to identify time factors.
In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:
the related technology has the defects of high recognition error rate of time factor information, inaccurate recognition result and the like.
Disclosure of Invention
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview nor is intended to identify key/critical elements or to delineate the scope of such embodiments but rather as a prelude to the more detailed description that is presented later.
The embodiment of the disclosure provides a time analysis method and device, an electronic product and a storage medium, and aims to solve the technical problems of high recognition error rate and inaccurate recognition result of time factor information in the related art.
The embodiment of the disclosure provides a time analysis method, which includes:
acquiring at least one target question-answer sentence to be analyzed;
and analyzing the target question-answer sentence by utilizing a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence.
In some embodiments, analyzing the target question-answer sentence by using a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, including:
under the condition that a target time factor in a target question-answering sentence is identified by utilizing a pre-established rule database, determining a target analysis result according to the target time factor;
and under the condition that the target time factor in the target question-answering sentence is not identified by utilizing the pre-established rule database, inputting the target question-answering sentence into the pre-trained CRF model so that the pre-trained CRF model outputs the identification result of the updated data of the time factor.
In some embodiments, further comprising:
and under the condition that the updating data of the time factor is determined to be identified according to the identification result, updating the rule database by using the updating data.
In some embodiments, further comprising:
converting the time format of the target time factor according to the standard time format to obtain the target time factor of the standard time format;
and analyzing and processing the target time factor in the standard time format to obtain the target time type corresponding to the target time factor in the standard time format.
In some embodiments, the rules database is constructed by:
acquiring a plurality of historical question-answer sentences containing at least one historical time factor;
and constructing a rule database according to the mapping relation between the historical question-answer sentences and the historical time factors.
In some embodiments, a pre-trained CRF model is trained by:
acquiring historical question-answer sentences containing historical time factors and historical analysis results;
marking the historical question and answer sentences to obtain marked question and answer sentences;
inputting the marked question and answer sentences as training corpora into an initial CRF model so as to enable the initial CRF model to output an analysis result;
under the condition that the similarity between the analysis result and the historical analysis result is greater than a set similarity threshold, successfully training the initial CRF model to obtain a CRF model which is trained in advance;
and under the condition that the similarity between the analysis result and the historical analysis result is less than or equal to the set similarity threshold, continuously training the initial CRF model by adjusting the parameters in the initial CRF model until the initial CRF model is successfully trained.
The embodiment of the present disclosure further provides a time resolution apparatus, including:
an acquisition unit configured to acquire at least one target question-answer sentence to be parsed;
and the analysis unit is configured to analyze the target question-answer sentence by utilizing a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence.
In some embodiments, the parsing unit comprises:
a time factor identification unit configured to determine a target analysis result according to a target time factor in the target question-answering sentence when the target time factor is identified by using a pre-established rule database;
and the updating data identification unit is configured to input the target question and answer sentence to the CRF model trained in advance under the condition that the target time factor in the target question and answer sentence is not identified by utilizing the rule database established in advance, so that the CRF model trained in advance outputs the identification result of the updating data of the time factor.
The disclosed embodiments also provide an electronic device comprising a processor and a memory storing program instructions, the processor being configured to perform the above-mentioned method when executing the program instructions.
The embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the time analysis method are implemented.
The time analysis method, the time analysis device, the electronic equipment and the storage medium provided by the embodiment of the disclosure can achieve the following technical effects:
the accuracy of the analysis result is improved by a method for analyzing the target question-answer sentence by combining the rule database with the CRF model trained in advance.
The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.
Drawings
At least one embodiment is illustrated by the accompanying drawings, which correspond to the accompanying drawings, and which do not form a limitation on the embodiment, wherein elements having the same reference numeral designations are shown as similar elements, and which are not to scale, and wherein:
fig. 1 is a schematic flow chart of a time analysis method according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of another time resolution method provided by the embodiment of the present disclosure;
fig. 3 is a schematic flow chart of another time resolution method provided by the embodiment of the present disclosure;
fig. 4 is a schematic flow chart of another time resolution method provided by the embodiment of the present disclosure;
fig. 5 is a schematic flow chart of another time resolution method provided by the embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a time resolution apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
So that the manner in which the features and elements of the disclosed embodiments can be understood in detail, a more particular description of the disclosed embodiments, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, at least one embodiment may be practiced without these specific details. In other instances, well-known structures and devices may be shown in simplified form in order to simplify the drawing.
Referring to fig. 1, in some embodiments, the present disclosure provides a time resolution method, which may include:
s101, obtaining at least one target question-answer sentence to be analyzed;
the target question-answering words may be time-related question sentences input by the user through voice or the like, and for example, the target question-answering words may be input to the intelligent device, and the question sentences of the user are subjected to voice recognition through the intelligent device.
S102, analyzing the target question-answer sentence by using a pre-constructed rule database and a pre-trained CRF (Conditional Random Field) model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence.
The target time factor may be a time-dependent factor in the target question-answering sentence, and may include, for example: today, this day, the last year, this month, etc.
Referring to fig. 2, in some embodiments, in step S102, analyzing the target question-answer sentence by using a pre-established rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, where the target analysis result includes:
s201, under the condition that a target time factor in a target question-answering sentence is identified by utilizing a pre-established rule database, determining a target analysis result according to the target time factor;
s202, under the condition that the target time factor in the target question-answer sentence is not identified by utilizing the pre-established rule database, the target question-answer sentence is input into the pre-trained CRF model, so that the pre-trained CRF model outputs the identification result of the updated data of the time factor.
When the target time factor is identified by using the rule database, the target time factor can be used as a target analysis result of the target question-answering sentence; when the target time factor is not identified by using the rule database, a new time factor in the target question-answering sentence is identified through a CRF model which is trained in advance.
Alternatively, in the case where the update data recognized as the time factor is determined from the above recognition result, the rule database is updated with the update data.
Therefore, if the CRF model trained in advance identifies a new time factor, the new time factor is added into the rule database, the data in the rule database is updated, the existing time factors in the rule database are enriched, the analysis mode is more flexible, the maintenance of the rule database is facilitated, and the accuracy of the subsequent analysis result can be improved.
Referring to fig. 3, in some embodiments, the present disclosure further provides another time resolution method, including:
s301, converting the time format of the target time factor according to the standard time format to obtain the target time factor in the standard time format.
On one hand, the target time factor in the target question-answering sentence is extracted through the time extraction regular expression through the rule database, and on the other hand, the target time factor can be converted into a standardized time format from a non-standardized time format. For example, convert the time of "today" to a standardized time format of "xxxx year/xx month/xx day". For another example, the "previous day" adopts a standardized time format of "systim, day, -,1, ymd", where the parameter 1 "systim" represents the current system time, and addition and subtraction operations can be performed on the current system time; the parameter 2 "day" represents the granularity of time calculation, such as the time expression "day" represents that one day is subtracted from today's base and the operation is performed on "day"; the parameter 3 '-' represents the calculation mode of the current time, including addition and subtraction operations; the parameter 4 '1' is the value added or subtracted by the parameter 3; the parameter 5 is the granularity returned at standard time, y is year, m is month, d is day.
By converting the time format of the target time factor, the time in the target question-answer sentence can be more flexibly standardized, and flexible configurability is realized. Each parameter is used for flexibly analyzing a new time type, so that the time analysis can be configured.
S302, analyzing and processing the target time factor in the standard time format to obtain a target time type corresponding to the target time factor in the standard time format.
After the spoken time format in the target question and answer sentence input by the user is converted into the standardized time format, the time type expressed in the target question and answer sentence can be analyzed, and the time types can be divided into four types which are respectively a specific certain time point, such as 9 months in 2019; a comparison between two time points, such as "9 months in 2019 vs 10 months in 2019", a certain time period, such as "9 months in 2019 to 10 months in 2019"; a comparison between two time periods, such as "this week over last week"; according to the four time types, a time type dictionary is combed out, and the time type dictionary is shown in a table 2; on one hand, the converted standard time format is replaced by special characters @ to form a certain mode, for example, the mode of '9 months in 2019 to 10 months in 2019' is formed after the replacement, and the mode of '@ to @' is formed, on the other hand, the time type corresponding to the target time factor of the standard time format can be represented by '@ to @' to compare two time points.
Referring to FIG. 4, in some embodiments, the rules database is constructed by:
s401, obtaining a plurality of historical question-answer sentences containing at least one historical time factor.
For example, the historical question-and-answer sentence may include "what is the oil production of the S86 well on the previous day", "water production of AD7 slotted unit in 2007? "and the like. The "previous day" and "2007" in the historical question-answer sentence are historical time factors.
S402, constructing a rule database according to the mapping relation between the historical question-answer sentences and the historical time factors.
Referring to FIG. 5, in some embodiments, a pre-trained CRF model is trained by:
s501, obtaining historical question-answer sentences containing historical time factors and historical analysis results.
And S502, labeling the historical question-answer sentences to obtain the labeled question-answer sentences.
By labeling the historical question and answer sentences, the labeled question and answer sentences are in a format which can be identified by a CRF algorithm, and for example, the following labeling mode can be adopted: TK002 well NN | this Btime | one Mtime | year Etime | fluid production volume NN | how many NN |? NN.
And S503, inputting the marked question-answer sentences serving as training corpora into the initial CRF model so as to enable the initial CRF model to output analysis results.
S504, judging whether the similarity between the analysis result and the historical analysis result is greater than a set similarity threshold value; if the similarity between the analysis result and the historical analysis result is greater than the set similarity threshold, executing step S505; if the similarity between the analysis result and the historical analysis result is less than or equal to the set similarity threshold, step S506 is executed.
For example, the similarity threshold may be 85%, and if the similarity is 65%, it indicates that the similarity is smaller than the similarity threshold, and the initial CRF model fails to be trained; if the similarity is 90%, the similarity is larger than the similarity threshold value, and the initial CRF model is successfully trained. The similarity threshold can be set according to actual requirements.
And S505, successfully training the initial CRF model to obtain a CRF model which is trained in advance.
S506, training the initial CRF model is continued by adjusting parameters in the initial CRF model until the initial CRF model is successfully trained.
Referring to fig. 6, an embodiment of the present disclosure further provides a time resolution apparatus, including:
an acquisition unit 601 configured to acquire at least one target question-answer sentence to be parsed;
the parsing unit 602 is configured to parse the target question-answer sentence by using a pre-constructed rule database and a pre-trained CRF model to obtain a target parsing result of the target question-answer sentence, where the parsing result includes a target time factor in the target question-answer sentence.
In some embodiments, parsing unit 602 includes:
a time factor identification unit configured to determine a target analysis result according to a target time factor in the target question-answering sentence when the target time factor is identified by using a pre-established rule database;
and the updating data identification unit is configured to input the target question and answer sentence to the CRF model trained in advance under the condition that the target time factor in the target question and answer sentence is not identified by utilizing the rule database established in advance, so that the CRF model trained in advance outputs the identification result of the updating data of the time factor.
An embodiment of the present disclosure provides an electronic device, a structure of which is shown in fig. 7, including:
a processor (processor)700 and a memory (memory)701, and may further include a Communication Interface 702 and a bus 703. The processor 700, the communication interface 702, and the memory 701 may communicate with each other via a bus 703. Communication interface 702 may be used for information transfer. The processor 700 may call logic instructions in the memory 701 to perform the time resolution method of the above embodiment.
In addition, the logic instructions in the memory 701 may be implemented in the form of software functional units and may be stored in a computer readable storage medium when the logic instructions are sold or used as independent products.
The memory 701 is a computer-readable storage medium and can be used for storing software programs, computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor 700 executes the functional application and data processing by executing the program instructions/modules stored in the memory 701, that is, implements the time resolution method in the above-described method embodiment.
The memory 701 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 terminal device, and the like. Further, memory 701 may include high speed random access memory, and may also include non-volatile memory.
The embodiment of the disclosure provides a product (for example, a computer, a mobile phone, etc.), which comprises the time analysis device.
According to the time analysis method, the time analysis device, the electronic equipment and the storage medium, the accuracy of the analysis result is improved by the method of analyzing the target question and answer sentence by combining the rule database with the CRF model which is trained in advance.
The disclosed embodiments provide a computer-readable storage medium storing computer-executable instructions configured to perform the above-described time resolution method.
The disclosed embodiments provide a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the time resolution method.
The computer-readable storage medium described above may be a transitory computer-readable storage medium or a non-transitory computer-readable storage medium.
According to the computer-readable storage medium and the computer program product provided by the embodiment of the disclosure, the accuracy of the analysis result is improved by using the method of analyzing the target question-answer sentence by combining the rule database with the pre-trained CRF model.
The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, where the computer software product is stored in a storage medium and includes at least one instruction to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium comprising: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes, and may also be a transient storage medium.
Those of skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software may depend upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments. It is clear to those skilled in the art that, for convenience and brevity of description, the working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit may be merely a division of a logical function, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. Units described as separate parts may or may not be physically separate, and 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 units can be selected according to actual needs to implement the present embodiment. In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises at least one executable instruction for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than disclosed in the description, and sometimes there is no specific order between the different operations or steps. For example, two sequential operations or steps may in fact be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. Each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Claims (10)
1. A time resolution method, comprising:
acquiring at least one target question-answer sentence to be analyzed;
and analyzing the target question-answer sentence by utilizing a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence.
2. The method according to claim 1, wherein the analyzing the target question-answer sentence by using a pre-established rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence comprises:
under the condition that a target time factor in the target question-answering sentence is identified by utilizing a pre-established rule database, determining a target analysis result according to the target time factor;
and under the condition that the target time factor in the target question-answering sentence is not identified by utilizing a pre-established rule database, inputting the target question-answering sentence into the pre-trained CRF model so that the pre-trained CRF model outputs the identification result of the updated data of the time factor.
3. The method of claim 2, further comprising:
and under the condition that the updating data of the time factor is determined to be identified according to the identification result, updating the rule database by using the updating data.
4. The method of claim 2, further comprising:
converting the time format of the target time factor according to a standard time format to obtain the target time factor in the standard time format;
and analyzing and processing the target time factor in the standard time format to obtain a target time type corresponding to the target time factor in the standard time format.
5. The method of claim 1, wherein the rules database is constructed by:
acquiring a plurality of historical question-answer sentences containing at least one historical time factor;
and constructing the rule database according to the mapping relation between the historical question-answering sentences and the historical time factors.
6. The method according to claim 1 or 2, wherein the pre-trained CRF model is trained by:
acquiring historical question-answer sentences containing historical time factors and historical analysis results;
marking the historical question and answer sentences to obtain marked question and answer sentences;
inputting the marked question and answer sentences as training corpora into an initial CRF model so as to enable the initial CRF model to output an analysis result;
under the condition that the similarity between the analysis result and the historical analysis result is greater than a set similarity threshold, successfully training the initial CRF model to obtain the CRF model which is trained in advance;
and under the condition that the similarity between the analysis result and the historical analysis result is less than or equal to a set similarity threshold, continuously training the initial CRF model by adjusting parameters in the initial CRF model until the initial CRF model is successfully trained.
7. A time resolution device, comprising:
an acquisition unit configured to acquire at least one target question-answer sentence to be parsed;
and the analysis unit is configured to analyze the target question-answer sentence by using a pre-constructed rule database and a pre-trained CRF model to obtain a target analysis result of the target question-answer sentence, wherein the analysis result comprises a target time factor in the target question-answer sentence.
8. The apparatus of claim 7, wherein the parsing unit comprises:
a time factor identification unit configured to determine a target analysis result according to a target time factor in the target question-answering sentence when the target time factor is identified by using a pre-established rule database;
and the updating data identification unit is configured to input the target question and answer sentence to the CRF model trained in advance under the condition that the target time factor in the target question and answer sentence is not identified by utilizing a rule database established in advance, so that the CRF model trained in advance outputs the identification result of the updating data of the time factor.
9. An electronic device comprising a processor and a memory storing program instructions, wherein the processor is configured to perform the method of any of claims 1-6 when executing the program instructions.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, realizes the steps of the time resolution method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010877950.8A CN112015876A (en) | 2020-08-27 | 2020-08-27 | Time analysis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010877950.8A CN112015876A (en) | 2020-08-27 | 2020-08-27 | Time analysis method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112015876A true CN112015876A (en) | 2020-12-01 |
Family
ID=73502605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010877950.8A Pending CN112015876A (en) | 2020-08-27 | 2020-08-27 | Time analysis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112015876A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108959529A (en) * | 2018-06-29 | 2018-12-07 | 北京百度网讯科技有限公司 | Determination method, apparatus, equipment and the storage medium of problem answers type |
| CN109086274A (en) * | 2018-08-23 | 2018-12-25 | 电子科技大学 | English social media short text time expression recognition method based on restricted model |
| CN110569332A (en) * | 2019-09-09 | 2019-12-13 | 腾讯科技（深圳）有限公司 | Sentence feature extraction processing method and device |
| CN111382571A (en) * | 2019-11-08 | 2020-07-07 | 南方科技大学 | Information extraction method, system, server and storage medium |
| CN111506723A (en) * | 2020-07-01 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Question-answer response method, device, equipment and storage medium |
-
2020
- 2020-08-27 CN CN202010877950.8A patent/CN112015876A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108959529A (en) * | 2018-06-29 | 2018-12-07 | 北京百度网讯科技有限公司 | Determination method, apparatus, equipment and the storage medium of problem answers type |
| CN109086274A (en) * | 2018-08-23 | 2018-12-25 | 电子科技大学 | English social media short text time expression recognition method based on restricted model |
| CN110569332A (en) * | 2019-09-09 | 2019-12-13 | 腾讯科技（深圳）有限公司 | Sentence feature extraction processing method and device |
| CN111382571A (en) * | 2019-11-08 | 2020-07-07 | 南方科技大学 | Information extraction method, system, server and storage medium |
| CN111506723A (en) * | 2020-07-01 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Question-answer response method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109147767B (en) | Method, device, computer equipment and storage medium for recognizing numbers in voice | |
| CN111581229B (en) | SQL statement generation method and device, computer equipment and storage medium | |
| CN114757176B (en) | Method for acquiring target intention recognition model and intention recognition method | |
| CN112633003A (en) | Address recognition method and device, computer equipment and storage medium | |
| CN111611769A (en) | Text conversion method and device for multiple language models | |
| CN110825827A (en) | Entity relationship recognition model training method and device and entity relationship recognition method and device | |
| CN113255331B (en) | Text error correction method, device and storage medium | |
| CN114783421A (en) | Intelligent recommendation method and device, equipment and medium | |
| CN115238143A (en) | Query statement generation method and device, model training method, equipment and medium | |
| CN112951233A (en) | Voice question and answer method and device, electronic equipment and readable storage medium | |
| CN110705217B (en) | Wrongly written or mispronounced word detection method and device, computer storage medium and electronic equipment | |
| CN109213988B (en) | Barrage theme extraction method, medium, equipment and system based on N-gram model | |
| CN115862031B (en) | Text processing method, neural network training method, device and equipment | |
| CN112015876A (en) | Time analysis method and device, electronic equipment and storage medium | |
| CN116631400A (en) | Voice-to-text method and device, computer equipment and storage medium | |
| CN115796141A (en) | Text data enhancement method and device, electronic equipment and storage medium | |
| CN111695350B (en) | Word segmentation method and word segmentation device for text | |
| CN113239245A (en) | Method and device for information query, electronic equipment and readable storage medium | |
| CN115130455A (en) | Article processing method and device, electronic equipment and storage medium | |
| CN114611529A (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN109657207B (en) | Formatting processing method and processing device for clauses | |
| CN112765958A (en) | Pronoun resolution method, device, electronic equipment and storage medium | |
| CN112966510A (en) | Weapon equipment entity extraction method, system and storage medium based on ALBERT | |
| CN113688615A (en) | Method, device and storage medium for generating field annotation and understanding character string | |
| CN113065333A (en) | Method and device for recognizing word types |
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 |