CN110674261A - Information processing method and device and computer readable storage medium - Google Patents
Information processing method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN110674261A CN110674261A CN201910972176.6A CN201910972176A CN110674261A CN 110674261 A CN110674261 A CN 110674261A CN 201910972176 A CN201910972176 A CN 201910972176A CN 110674261 A CN110674261 A CN 110674261A
- Authority
- CN
- China
- Prior art keywords
- information
- question
- request
- answer
- shorthand
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an information processing method, an information processing device and a computer readable storage medium, wherein the method comprises the following steps: receiving request information of a user or a user terminal; converting the received request information into text information; performing semantic analysis on the text information to judge the request type of the request information; and performing information interaction operation corresponding to the determined request type by using the question-answer library. When the method is used, a user sends request information, after the request information of the user is received, the request type required by the user is automatically analyzed, and then corresponding operation is automatically executed according to the request type, so that the time is greatly saved, the efficiency is improved, and meanwhile, the user experience is also improved.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to an information processing method and apparatus, and a computer-readable storage medium.
Background
In real life, people often forget something, such as meeting time, birthday date, etc. To solve the above mentioned problems, the conventional method is to record things easy to forget as a memo in a notebook in an electronic device such as a mobile phone, or in a paper book, and when checking, a user needs to search for memo information by searching for the notebook in the electronic device or from the paper book, wherein both the recording process and the checking process are complicated, which results in low efficiency.
Disclosure of Invention
The embodiment of the invention provides an information processing method, an information processing device and a computer readable storage medium, which have the advantages of improving the efficiency of information recording and searching.
One aspect of the present invention provides an information processing method, including: receiving request information of a user or a user terminal; converting the received request information into text information; performing semantic analysis on the text information to judge the request type of the request information; and performing information interaction operation corresponding to the determined request type by using the question-answer library.
In an embodiment, after converting the received request message into a text message, the method further comprises: judging whether the text information is a shorthand/question-answer related request; and if the text information is judged to be a shorthand/question-answer related request, further judging the request type of the request information.
In an embodiment, the semantic analyzing the text information to determine the request type of the request information includes: extracting keyword information in the text information; and judging the request type of the request information according to the extracted keyword information.
In an implementation manner, the performing, by using a question-and-answer library, an information interaction operation corresponding to the determined request type includes: if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information; and storing the extracted shorthand information into a question-answering library.
In an implementation manner, the performing, by using a question-and-answer library, an information interaction operation corresponding to the determined request type further includes: if the obtained request type is judged to be the question-answer type, extracting question-answer information in the text information; selecting specific shorthand information from a question-answer library according to the extracted question-answer information; and feeding back the selected specific shorthand information to the user or the user terminal.
In an embodiment, the selecting specific shorthand information from the question-answer library according to the extracted question-answer information includes: similarity calculation is carried out on all the stenographic information in the question-answer library and the extracted question-answer information one by one, and a similarity value corresponding to each piece of stenographic information is obtained; and selecting the shorthand information with the highest similarity value with the question-answer information as the specific shorthand information.
In one implementation, the method is applied to a smart wearable device.
Another aspect of the present invention provides an information processing apparatus, comprising: the receiving module is used for receiving request information of a user or a user terminal; the conversion module is used for converting the received request information into text information; the judging module is used for performing semantic analysis on the text information to judge the request type of the request information; and the interactive module is used for executing information interactive operation corresponding to the determined request type by utilizing the question-answering library.
In an implementation manner, the interaction module is specifically configured to: if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information; storing the extracted shorthand information into a question-answering library; if the obtained request type is judged to be the question-answer type, extracting question-answer information in the text information; selecting specific shorthand information from a question-answer library according to the extracted question-answer information; and feeding back the selected specific shorthand information to the user or the user terminal.
One aspect of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform a method of information processing.
In the embodiment of the invention, when the method is used, the user sends the request information, the request type required by the user is automatically analyzed after the request information of the user is received, and then the corresponding operation is automatically executed according to the request type, so that the time is greatly saved, the efficiency is improved, and the user experience is also improved.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a schematic diagram of an implementation flow of an information processing method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an implementation of an information processing method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
FIG. 1 is a schematic diagram of an implementation flow of an information processing method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a specific implementation of an information processing method according to an embodiment of the present invention.
As shown in fig. 1, an aspect of the present invention provides an information processing method, where the method includes:
103, performing semantic analysis on the text information to judge the request type of the request information;
and 104, performing information interaction operation corresponding to the determined request type by using the question-answer library.
In this embodiment, first, request information of a user or a user terminal is received, where the request information is generally voice information, then the voice information is converted into text information by using the existing voice-to-text conversion technology, then semantic analysis is performed on the text information to determine a request type of the request information, and then, according to a result of the determined request type, a question-and-answer library is used to perform corresponding information interaction operation.
When the method is used, a user sends request information, after the request information of the user is received, the request type required by the user is automatically analyzed, and then corresponding operation is automatically executed according to the request type, so that the time is greatly saved, the efficiency is improved, and meanwhile, the user experience is also improved.
In an embodiment, after converting the received request message into a text message, the method further comprises:
if the text information is judged to be the related request of the shorthand/question and answer, the request type of the request information is further judged.
In this embodiment, after the received request information is converted into text information in step 101, it is further determined whether the text information is related to shorthand/question-answer information, and the determination method may use a trained natural language processing model to perform the determination, and the text information is used as an input of the natural language processing model, so as to obtain a request type of the text information. If the text information is judged to be related information of shorthand/question and answer, continuing to perform the subsequent steps; and if the text information is judged not to be the related information of the shorthand/question and answer, the subsequent steps are not carried out.
Wherein, the general training process of the natural language processing model is as follows:
firstly, a large amount of linguistic information related to shorthand/question and answer is adopted, and the linguistic information comprises the shorthand/question and answer information and corresponding answers.
And then training the shorthand/question-answer information as the input of a natural language processing model to obtain corresponding output information.
And calculating a loss value by using the output information of the natural language processing model and the corresponding input answer through a loss function.
And (5) repeatedly training the steps for N times or finishing the model training when the gradient of the loss value is not reduced any more.
Therefore, whether the text information is the related information of the shorthand/question and answer is judged after the received request information is converted into the text information, so that the output accuracy can be improved, and the user experience is improved.
In one implementation, semantic analysis is performed on the text information to determine a request type of the request information, including:
extracting keyword information in the text information;
and judging the request type of the request information according to the extracted keyword information.
In this embodiment, the specific steps of step 103 are: after the text information is acquired, intercepting keyword information related to shorthand or question and answer from the text information, wherein the keyword information is generally positioned at the head part of the text information, judging whether the intercepted keyword information is contained in a shorthand/question and answer keyword library, and if the keyword information is contained in the shorthand keyword library, judging that the request type of the request information is a shorthand type; if the keyword information is contained in the question-answer keyword library, the request type of the request information is judged to be the question-answer type.
In one implementation, the performing, by using the question-answering library, the information interaction operation corresponding to the determined request type includes:
if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information;
and storing the extracted shorthand information into a question-answering library.
In this embodiment, the specific steps of step 104 are: if the request type of the text is judged to be the shorthand type from the steps, the shorthand information in the text information is extracted, wherein the shorthand information is generally the rest part of the text information except the keyword information, and then the extracted shorthand information is stored in a question-and-answer library.
In an implementation manner, the performing, by using the question-answering library, the information interaction operation corresponding to the determined request type further includes:
if the obtained request type is judged to be the question and answer type, extracting question and answer information in the text information;
selecting specific shorthand information from a question-answer library according to the extracted question-answer information;
and feeding back the selected specific shorthand information to the user or the user terminal.
In this embodiment, the specific steps of step 104 further include: if the request type of the text is judged to be the question-answer type from the steps, extracting question-answer information in the text information, wherein the question-answer information is generally the remaining part of the text information except the keyword information, selecting specific stenographic information from a question-answer library according to the extracted question-answer information, and finally feeding back the selected specific stenographic information to a user or a user terminal, wherein the feedback mode can be that the text information is displayed on a display terminal or can be informed in a voice transmission mode.
In one embodiment, selecting specific shorthand information from the question-answer library according to the extracted question-answer information includes:
similarity calculation is carried out on all the stenographic information in the question-answer library and the extracted question-answer information one by one, and a similarity value corresponding to each piece of stenographic information is obtained;
and selecting the shorthand information with the highest similarity value with the question-answer information as the specific shorthand information.
In this embodiment, the specific steps of "selecting specific shorthand information from the question-and-answer library according to the extracted question-and-answer information" in the above steps are as follows:
and performing similarity calculation on all the shorthand information stored in the question-answer library and the question-answer information one by one to obtain a similarity value corresponding to each piece of shorthand information, wherein the similarity calculation can be performed by a text similarity calculation method in the existing natural language processing.
And then selecting the shorthand information with the highest similarity as the specific shorthand information, wherein the shorthand information with the higher similarity is more likely to correspond to the request information of the user.
In one implementation, the method is applied to a smart wearable device.
In this embodiment, the method may be used in intelligent wearable devices such as a smart watch, a smart bracelet, and a smart headset, and a user may perform shorthand or question and answer operations anytime and anywhere.
Referring to fig. 2, the general using process includes firstly receiving request information of a user or a user terminal, then converting the request information into text information, then determining whether the text information is a shorthand/question-and-answer related request, further determining a request type of the text information if the text information is determined to be a shorthand/question-and-answer related request, storing the shorthand information in the text information into a question-and-answer library if the request type of the text information is determined to be a shorthand type, querying the shorthand information with the highest similarity from the question-and-answer library according to the text information if the request type of the text information is determined to be a question-and-answer type, and informing the user or the user terminal of the shorthand information in a form of voice or text.
Fig. 3 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention.
As shown in fig. 3, based on the information processing method provided above, an embodiment of the present invention further provides an information processing apparatus, including:
the receiving module is used for receiving request information of a user or a user terminal;
the conversion module is used for converting the received request information into text information;
the judging module is used for carrying out semantic analysis on the text information to judge the request type of the request information;
and the interactive module is used for executing information interactive operation corresponding to the determined request type by utilizing the question-answering library.
In this embodiment, the apparatus may be used in an intelligent wearable device such as a smart watch, a smart bracelet, and a smart headset, and first receives request information of a user or a user terminal through a receiving module, where the request information is generally voice information, and then a conversion module converts the voice information into text information by using an existing voice-to-text conversion technology.
And then, the judgment module carries out semantic analysis on the text information to judge the request type of the request information. The method comprises the steps of intercepting keyword information related to shorthand or question and answer from text information, wherein the keyword information is generally positioned at the head part of the text information, judging whether the intercepted keyword information is contained in a shorthand/question and answer keyword library, and if the keyword information is contained in the shorthand keyword library, judging that the request type of the request information is a shorthand type; if the keyword information is contained in the question-answer keyword library, the request type of the request information is judged to be the question-answer type.
And then the interactive module performs corresponding information interactive operation by using a question-answer library according to the judged request type result.
When the method is used, a user sends request information, after the request information of the user is received, the request type required by the user is automatically analyzed, and then corresponding operation is automatically executed according to the request type, so that the time is greatly saved, the efficiency is improved, and meanwhile, the user experience is also improved.
Further, after the conversion module converts the received request information into text information, the determination module is further specifically configured to determine whether the text information is a related request for shorthand/question-answer, and if the text information is determined to be a related request for shorthand/question-answer by the determination module, further determine a request type of the request information. The method for determining whether the text information is a shorthand/question-and-answer related request can determine the request type of the text information by inputting the text information as a trained natural language processing model, the training process of the natural language processing model is mentioned above, and is not described herein.
In an implementation, the interaction module is specifically configured to:
if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information;
storing the extracted shorthand information into a question-answering library;
if the obtained request type is judged to be the question and answer type, extracting question and answer information in the text information;
selecting specific shorthand information from a question-answer library according to the extracted question-answer information;
and feeding back the selected specific shorthand information to the user or the user terminal.
In this embodiment, the interaction module is specifically configured to:
if the judgment module judges that the request type is the shorthand type, the interaction module extracts shorthand information in the text information, wherein the shorthand information is generally the rest part of the text information except the keyword information, and then stores the extracted shorthand information into a question-answering library.
If the request type is judged to be the question-answer type by the judging module, the interactive module extracts the question-answer information in the text information, wherein the question-answer information is generally the rest part of the text information except the keyword information. Similarity calculation is carried out on all the stenographic information stored in the question-answer library and the question-answer information one by one to obtain a similarity value corresponding to each piece of stenographic information, wherein the similarity calculation can be carried out through a text similarity calculation method in the existing natural language processing; selecting the shorthand information with the highest similarity as specific shorthand information; and feeding back the selected specific shorthand information to the user or the user terminal, wherein the feedback mode can be that text information is displayed on a display terminal or that the text information is informed in a voice propagation mode.
Referring to fig. 2, the general using process includes firstly receiving request information of a user or a user terminal through a receiving module, then converting the request information into text information through conversion, then judging whether the text information is a shorthand/question-answer related request through a judging module, if the text information is judged to be the shorthand/question-answer related request, further judging the request type of the text information, if the request type of the text information is judged to be the shorthand type, storing the shorthand information in the text information into a question-answer library through an interactive module, and if the request type of the text information is judged to be the question-answer type, querying the shorthand information with the highest similarity from the question-answer library according to the text information through the interactive module, and informing the user or the user terminal of the shorthand information in a voice or text form.
Another aspect of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions for performing any one of the above-mentioned information processing methods when executed.
In an embodiment of the present invention, a computer-readable storage medium includes a set of computer-executable instructions, which when executed, are configured to receive a request for information from a user or a user terminal; converting the received request information into text information; performing semantic analysis on the text information to judge the request type of the request information; and performing information interaction operation corresponding to the determined request type by using the question-answer library.
When the method is used, a user sends request information, after the request information of the user is received, the request type required by the user is automatically analyzed, and then corresponding operation is automatically executed according to the request type, so that the time is greatly saved, the efficiency is improved, and meanwhile, the user experience is also improved.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An information processing method, characterized in that the method comprises:
receiving request information of a user or a user terminal;
converting the received request information into text information;
performing semantic analysis on the text information to judge the request type of the request information;
and performing information interaction operation corresponding to the determined request type by using the question-answer library.
2. The method of claim 1, wherein after converting the received request message to a text message, the method further comprises:
judging whether the text information is a shorthand/question-answer related request;
and if the text information is judged to be a shorthand/question-answer related request, further judging the request type of the request information.
3. The method of claim 1, wherein the semantically analyzing the text information to determine a request type of the request information comprises:
extracting keyword information in the text information;
and judging the request type of the request information according to the extracted keyword information.
4. The method of claim 1, wherein performing the information interaction operation corresponding to the determined request type by using a question-and-answer library comprises:
if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information;
and storing the extracted shorthand information into a question-answering library.
5. The method of claim 1, wherein the performing information interaction operations corresponding to the determined request type using a question-and-answer library further comprises:
if the obtained request type is judged to be the question-answer type, extracting question-answer information in the text information;
selecting specific shorthand information from a question-answer library according to the extracted question-answer information;
and feeding back the selected specific shorthand information to the user or the user terminal.
6. The method according to claim 5, wherein the selecting specific shorthand information from the question-answer library according to the extracted question-answer information comprises:
similarity calculation is carried out on all the stenographic information in the question-answer library and the extracted question-answer information one by one, and a similarity value corresponding to each piece of stenographic information is obtained;
and selecting the shorthand information with the highest similarity value with the question-answer information as the specific shorthand information.
7. The method according to any one of claims 1-6, wherein the method is applied in a smart wearable device.
8. An information processing apparatus characterized in that the apparatus comprises:
the receiving module is used for receiving request information of a user or a user terminal;
the conversion module is used for converting the received request information into text information;
the judging module is used for performing semantic analysis on the text information to judge the request type of the request information;
and the interactive module is used for executing information interactive operation corresponding to the determined request type by utilizing the question-answering library.
9. The apparatus of claim 8, wherein the interaction module is specifically configured to:
if the obtained request type is judged to be a shorthand type, extracting shorthand information in the text information;
storing the extracted shorthand information into a question-answering library;
if the obtained request type is judged to be the question-answer type, extracting question-answer information in the text information;
selecting specific shorthand information from a question-answer library according to the extracted question-answer information;
and feeding back the selected specific shorthand information to the user or the user terminal.
10. A computer-readable storage medium comprising a set of computer-executable instructions for performing an information processing method as claimed in any one of claims 1 to 7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972176.6A CN110674261A (en) | 2019-10-14 | 2019-10-14 | Information processing method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972176.6A CN110674261A (en) | 2019-10-14 | 2019-10-14 | Information processing method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110674261A true CN110674261A (en) | 2020-01-10 |
Family
ID=69082258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910972176.6A Pending CN110674261A (en) | 2019-10-14 | 2019-10-14 | Information processing method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674261A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004007986A (en) * | 2003-06-20 | 2004-01-08 | Mirai Ind Co Ltd | Box and information display plate |
| CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
| CN107273350A (en) * | 2017-05-16 | 2017-10-20 | 广东电网有限责任公司江门供电局 | A kind of information processing method and its device for realizing intelligent answer |
| CN109377162A (en) * | 2018-09-25 | 2019-02-22 | 浙江工业大学 | Intelligent prompt method based on social software |
| CN109766422A (en) * | 2018-12-29 | 2019-05-17 | 上海智臻智能网络科技股份有限公司 | Information processing method, apparatus and system, storage medium, terminal |
| CN109857850A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Counsel requests processing method, device, computer equipment and storage medium |
-
2019
- 2019-10-14 CN CN201910972176.6A patent/CN110674261A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004007986A (en) * | 2003-06-20 | 2004-01-08 | Mirai Ind Co Ltd | Box and information display plate |
| CN102880649A (en) * | 2012-08-27 | 2013-01-16 | 北京搜狗信息服务有限公司 | Individualized information processing method and system |
| CN107273350A (en) * | 2017-05-16 | 2017-10-20 | 广东电网有限责任公司江门供电局 | A kind of information processing method and its device for realizing intelligent answer |
| CN109377162A (en) * | 2018-09-25 | 2019-02-22 | 浙江工业大学 | Intelligent prompt method based on social software |
| CN109766422A (en) * | 2018-12-29 | 2019-05-17 | 上海智臻智能网络科技股份有限公司 | Information processing method, apparatus and system, storage medium, terminal |
| CN109857850A (en) * | 2019-01-18 | 2019-06-07 | 深圳壹账通智能科技有限公司 | Counsel requests processing method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727041B (en) | Intelligent customer service multi-turn question and answer method, equipment, storage medium and device | |
| CN107330120B (en) | Inquire answer method, inquiry answering device and computer readable storage medium | |
| CN109086303A (en) | The Intelligent dialogue method, apparatus understood, terminal are read based on machine | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| CN104836720A (en) | Method for performing information recommendation in interactive communication, and device | |
| CN106407393B (en) | information processing method and device for intelligent equipment | |
| US10089898B2 (en) | Information processing device, control method therefor, and computer program | |
| CN112579733B (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN111199732A (en) | Emotion-based voice interaction method, storage medium and terminal equipment | |
| JP7436077B2 (en) | Skill voice wake-up method and device | |
| CN111079428B (en) | Word segmentation and industry dictionary construction method and device and readable storage medium | |
| CN113342948A (en) | Intelligent question and answer method and device | |
| CN112417107A (en) | Information processing method and device | |
| CN112686051A (en) | Semantic recognition model training method, recognition method, electronic device, and storage medium | |
| CN110473543B (en) | Voice recognition method and device | |
| WO2023129255A1 (en) | Intelligent character correction and search in documents | |
| CN116881425A (en) | Universal document question-answering implementation method, system, device and storage medium | |
| CN109065015B (en) | Data acquisition method, device and equipment and readable storage medium | |
| CN111933128B (en) | Method and device for processing question bank of questionnaire and electronic equipment | |
| CN113220854A (en) | Intelligent dialogue method and device for machine reading understanding | |
| US20230252061A1 (en) | Providing responses to queries of transcripts using multiple indexes | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN109783612B (en) | Report data positioning method and device, storage medium and terminal | |
| CN110674261A (en) | Information processing method and device and computer readable storage medium | |
| CN113868271A (en) | Method and device for updating knowledge base of intelligent customer service, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |