CN112036912A - Question-answering method and question-answering device - Google Patents
Question-answering method and question-answering device Download PDFInfo
- Publication number
- CN112036912A CN112036912A CN202010882345.XA CN202010882345A CN112036912A CN 112036912 A CN112036912 A CN 112036912A CN 202010882345 A CN202010882345 A CN 202010882345A CN 112036912 A CN112036912 A CN 112036912A
- Authority
- CN
- China
- Prior art keywords
- application
- scene
- scenario
- template
- consultation
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a question answering method and a question answering device, which comprise the following steps: acquiring a consultation conversation screenshot and performing character recognition on the consultation conversation screenshot to obtain corresponding consultation characters; matching a corresponding first application scene in a dialect library according to the consultation characters; and acquiring a first template dialog in a dialog library according to the first application scene. The invention can identify the chat content with the client, automatically extract the accurate dialogs to be used by the client for answering by combining the set keywords and the dialogs corresponding to different scenes, has richer and more accurate dialogs content, and can improve the answering quality of the answering efficiency of the salespersons.
Description
Technical Field
The invention relates to the technical field of sales question answering, in particular to a question answering method and a question answering device.
Background
In the sales industry, sales personnel often communicate with customers through WeChat to promote customer transaction and increase of brand and company image.
In the prior art, some chat robots can receive conversation sentences and analyze the sentences so as to feed template dialogues back to users, but the chat robots can only receive voice consultation information and perform voice relative question-answering, but the existing sales consultation is usually performed through on-line question-answering ways such as WeChat and the like, particularly in the automobile sales industry, so that the chat robots in the prior art have limited application scenes and cannot be applied to the automobile sales industry with complex consultation scenes.
Therefore, a question and answer method for accurately identifying online consultation contents, which is suitable for the automobile sales industry, is needed.
Disclosure of Invention
The invention provides a question answering method, which comprises the following steps: acquiring a consultation conversation screenshot and performing character recognition on the consultation conversation screenshot to obtain corresponding consultation characters; matching a corresponding first application scene in a dialect library according to the consultation characters; and acquiring a first template dialog in a dialog library according to the first application scene.
In one embodiment, the first application scenario is associated with a first application sub-scenario and a corresponding first template scenario in the scenario library, and the obtaining a first template scenario in the scenario library according to the first application scenario includes: and acquiring a first application sub-scene and a corresponding first template dialect in a dialect library according to the first application scene.
In an embodiment, the method further comprises: associating a second application sub-scene and a corresponding second template dialog with the first application scene in the dialog library, wherein correspondingly, the acquiring of the first template dialog in the dialog library according to the first application scene comprises the following steps: and acquiring a first template dialect, a second application sub-scene and a second template dialect in a dialect library according to the first application scene.
In one embodiment, the consulting text is matched with a keyword associated with the first application scene in the dialect library.
In an embodiment, the method further comprises: acquiring input characters; and matching the corresponding first application scene in the dialect library according to the input characters.
In an embodiment, the method further comprises: acquiring weather forecast information; and adding a weather application scene and a corresponding weather dialect in the dialect library according to the weather forecast information.
In an embodiment, the first application scenario is one or more, and the obtaining a first template dialog in a dialog library according to the first application scenario includes: and if the matched first application scene is the only scene, outputting a corresponding first template dialog.
Another aspect of the embodiments of the present invention provides a question answering device, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a consultation conversation screenshot and performing character recognition on the consultation conversation screenshot to obtain corresponding consultation characters; the first matching module is used for matching a corresponding first application scene in the dialogistic library according to the consultation characters; and the speech technology acquisition module is used for acquiring a first template speech technology in a speech technology library according to the first application scene.
In an implementation manner, the first application scenario is associated with a first application sub-scenario and a corresponding first template scenario in the scenario library, and the scenario acquisition module is further configured to acquire the first application sub-scenario and the corresponding first template scenario in the scenario library according to the first application scenario.
In one embodiment, the method further comprises: a scene association module for associating a second application sub-scene and a corresponding second template dialog to the first application scene in the dialog library; the conversation acquiring module is further used for acquiring a first template conversation, a second application sub-scene and a second template conversation in a conversation library according to the first application scene.
In one embodiment, the method further comprises: the input character acquisition module is used for acquiring input characters; the first matching module is also used for matching a corresponding first application scene in the dialogistic library according to the input characters.
The question answering method and the question answering device provided by the invention have the following beneficial effects:
(1) the invention can identify the chat content with the client, and automatically extract the accurate speech to the client for reply and use by combining the set keywords and corresponding different scenes of speech, besides, the guidance and inspiration suggested by the telephone reception template, the salesperson can also automatically add small scenes and speech and store the small scenes and speech for the next use, when similar problems are communicated with the client again, the speech content is richer and more accurate, thereby improving the reply efficiency and the reply quality, and improving the personal service capability by the long-term application of the standardized speech.
(2) The method can help the salesperson to quickly extract the practical dialect for the customer relationship management, and the accurate dialect extraction is maintained through keyword retrieval, so that the applicable dialect library capacity of the salesperson is large, and the problem of the extraction efficiency of the dialect can be better solved.
(3) The invention can help the salesperson to carry out relationship maintenance and effective invitation by means of weather conditions, and improve the customer goodness and invitation rate.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present application 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 flow chart of a question answering method according to the present invention;
FIG. 2 is a schematic view of a specific flow chart of a question answering method according to the present invention
Fig. 3 is a structural diagram of a question answering device according to the present invention.
Detailed Description
In order to make the objects, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only a part of the embodiments of the present application, and not all 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 application.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means 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 application. 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 application, "a plurality" means two or more unless specifically limited otherwise.
The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present specification. Rather, they are merely examples of methods, apparatus or devices consistent with certain aspects of the specification, as detailed in the claims that follow.
The invention will be further illustrated with reference to the following examples and drawings:
referring to fig. 1 to fig. 2, an embodiment of the present invention provides a question answering method, including:
102, matching a corresponding first application scene in a dialect library according to the consultation characters;
In the embodiment of the invention, the consultation conversation screenshot can be obtained by a method of setting screenshot once every five seconds or refreshing the current consultation interface and the like through an automatic screenshot technology, and then the client chat content is identified from the consultation conversation screenshot through an OCR (Optical Character Recognition) technology.
Wherein, the first application scene in the word operation library is related to the corresponding keyword and the first application scene in the word operation library is related to the first application sub-scene and the corresponding first template word operation, for example, the keyword related to the first application scene for consulting the price of a certain model car is: price, low price and the like, correspondingly, the application scenario is associated with a first application sub-scenario as a recent preferential price of the vehicle, and a first template language corresponding to the first application sub-scenario is as follows: "do you well, the manufacturer of this model of car guides the price to be twelve thousand, you can also apply for you in a particularly preferential shop, but you please feel relieved in price because we's shop is a nationwide ten-best shop, not only is the price advantageous, but also the after-sales is very good, you have time to come in the shop and I introduce you, I can also win the best price for you to the best of my ability, certainly can not let you run, you have a blank day on two days? If the first application scene is associated with a plurality of sub-application scenes and corresponding template dialogs, the information and the first application sub-scenes and the first template dialogs are obtained from the dialogs library together and displayed for the use of the salespersons. In an implementation manner, if the matched first application scene is the only scene, the corresponding first template dialog is directly output, so that the manual clicking time of a user is saved, and the reply rate is improved.
The corresponding first application scenario automatically matched in the dialect library according to the consultation text matching is as follows: when the obtained consultation characters are identified as follows: when the price of the vehicle is more or less, matching the consultation characters with the keywords in the dialect library to obtain that the corresponding matched keywords are the price, namely the matched first application scene is the price of the vehicle, so that the corresponding first application sub-scene and the first template dialect can be obtained in the dialect library according to the application scene. If the consultation characters are matched with a plurality of application scenes, the salesperson can manually select the application scene with the highest accuracy from the matched application scenes as the first application scene, and then obtain the application sub-scene corresponding to the first application scene and the corresponding template word operation from the word operation.
In an embodiment, the method further comprises: associating a second application sub-scene and a corresponding second template dialog with the first application scene in the dialog library, wherein correspondingly, the step of acquiring the first template dialog in the dialog library according to the first application scene comprises the following steps: and acquiring a first template dialog, a second application sub-scene and a second template dialog in the dialog library according to the first application scene.
In the embodiment of the present invention, the user may add the second application sub-scenario and the corresponding second template dialog in the dialog library, and if the first application scenario is to consult the price of a car of a certain model, the user may manually add the second application sub-scenario as follows: the preferential activities of the vehicle of the model are consulted, and the corresponding second template language is as follows: "you are good, the manufacturer of this model guides the price to be twelve thousand, and recently 618 we have the preferential activity of making eight folds and sending a large gift bag, the discount strength is the biggest all year round, the machine is not lost, the pre-purchase is from speed! By adding the second application sub-scene and the corresponding dialect, when the salesperson communicates similar problems with the client again, the content of the dialect is richer and more accurate, so that the response efficiency and the response quality are improved, and the sales service capability is improved by long-term application of the standardized dialect.
In an embodiment, the method further comprises:
acquiring input characters;
and matching the corresponding first application scene in the dialect library according to the input characters.
The embodiment of the invention is applied to the condition that the consultation screenshot of the consultation conversation cannot be extracted or the extracted consultation character cannot be matched with the application scene due to the fact that the consultation problem of the client is carried out in a non-online consultation mode such as calling or the like, or the wrong character is typed or the non-conventional consultation operation is used, and at the moment, a salesperson can manually input the character according to the understanding of the consultation problem of the client so as to retrieve the corresponding application scene and the template operation in the operation library. The embodiment of the invention can adapt to various different sales scenes and has wide application range. The embodiment of the invention is embedded with a customer problem reply dialect retrieval function, which can help a salesperson to quickly extract a practical dialect for customer relationship management and use, the dialect in the prior art is only presented in a list form, and related dialect can be inquired and extracted and used by manually pulling a rolling button without the key character retrieval technology related to the invention, so that if the size of a dialect library is large, the dialect acquisition efficiency is influenced, and the service plates related to automobile sales are more, the complexity of customer problems is also high, such as a series of problems of finance, insurance, replacement, decoration, fine products, branding, after-sale service, vehicle type, price, discount and the like.
In an embodiment, the method further comprises:
acquiring weather forecast information;
and adding weather application scenes and corresponding weather dialogs in the dialogs library according to the weather forecast information.
The embodiment of the invention can acquire real-time weather forecast information through technologies such as a crawler and the like, and add weather application scenes and corresponding sub-application scenes and weather dialogs in the dialogs library according to different weather information so as to be used by sellers for online chatting or telephone follow-up, help the sellers to carry out relationship maintenance and effective invitation by means of weather conditions, and improve the customer enjoyment and the invitation rate.
Referring to fig. 3, another aspect of the present invention provides a question answering device, including:
a first obtaining module 201, configured to obtain a consultation session screenshot and perform text recognition on the consultation session screenshot to obtain corresponding consultation text;
the first matching module 202 is used for matching a corresponding first application scene in the dialogistic library according to the consultation characters;
a dialect obtaining module 203, configured to obtain a first template dialect in a dialect library according to the first application scenario.
In the embodiment of the present invention, the first obtaining module 201 may obtain the user consultation session screenshot by setting a screenshot once every five seconds or a screenshot after refreshing the current consultation interface through an automatic screenshot technology, and then identify the chat content of the client from the consultation session screenshot by an OCR (Optical Character Recognition) technology, that is, obtain the corresponding consultation text, so as to automatically identify the content of the chat with the wished buyer client.
Wherein, the first application scene in the word operation library is related to the corresponding keyword and the first application scene in the word operation library is related to the first application sub-scene and the corresponding first template word operation, for example, the keyword related to the first application scene for consulting the price of a certain model car is: price, low price and the like, correspondingly, the application scenario is associated with a first application sub-scenario as a recent preferential price of the vehicle, and a first template language corresponding to the first application sub-scenario is as follows: "do you well, the manufacturer of this model of car guides the price to be twelve thousand, you can also apply for you in a particularly preferential shop, but you please feel relieved in price because we's shop is a nationwide ten-best shop, not only is the price advantageous, but also the after-sales is very good, you have time to come in the shop and I introduce you, I can also win the best price for you to the best of my ability, certainly can not let you run, you have a blank day on two days? If the first application scene is associated with a plurality of sub-application scenes and corresponding template dialogs, the information and the first application sub-scenes and the first template dialogs are obtained from the dialogs library together and displayed for the use of the salespersons. In an implementation manner, if the matched first application scene is the only scene, the corresponding first template dialog is directly output, so that the manual clicking time of a user is saved, and the reply rate is improved.
The first matching module 202 matches the corresponding first application scenario automatically matched in the dialogistic library according to the query text specifically as follows: when the obtained consultation characters are identified as follows: when the price of the vehicle is more or less, matching the consultation characters with the keywords in the dialect library to obtain that the corresponding matched keywords are the price, namely the matched first application scene is the price of the vehicle, so that the corresponding first application sub-scene and the first template dialect can be obtained in the dialect library according to the application scene. If the consultation characters are matched with a plurality of application scenes, the salesperson can manually select the application scene with the highest accuracy from the matched application scenes as the first application scene, and then obtain the application sub-scene corresponding to the first application scene and the corresponding template word operation from the word operation.
In one embodiment, the method further comprises:
the scene association module is used for associating a second application sub-scene and a corresponding second template tactic to the first application scene in the tactic library;
the dialogue acquiring module is further used for acquiring a first template dialogue, a second application sub-scene and a second template dialogue in the dialogue library according to the first application scene.
In the embodiment of the present invention, the user may add the second application sub-scenario and the corresponding second template scenario in the scenario library, for example, when the first application scenario refers to a price for consulting a car of a certain model, the user may manually add the second application sub-scenario through the scenario association module as follows: the preferential activities of the vehicle of the model are consulted, and the corresponding second template language is as follows: "you are good, the manufacturer of this model guides the price to be twelve thousand, and recently 618 we have the preferential activity of making eight folds and sending a large gift bag, the discount strength is the biggest all year round, the machine is not lost, the pre-purchase is from speed! By adding the second application sub-scene and the corresponding dialect, when the salesperson communicates similar problems with the client again, the content of the dialect is richer and more accurate, so that the response efficiency and the response quality are improved, and the sales service capability is improved by long-term application of the standardized dialect.
In one embodiment, the method further comprises:
the input character acquisition module is used for acquiring input characters;
the first matching module is also used for matching the corresponding first application scene in the dialect library according to the input characters.
The embodiment of the invention is applied to the condition that the consultation problem of the client is not taken through a non-online consultation mode such as calling and the like, or the consultation conversation screenshot cannot be extracted or the extracted consultation characters cannot be matched with the application scene due to wrong words or use of an unconventional consultation conversation, and at the moment, a salesperson can manually input the characters through the input character acquisition module according to the understanding of the consultation problem of the client so as to retrieve the corresponding application scene and the template conversation in the conversation library. The embodiment of the invention can adapt to various different sales scenes and has wide application range. The embodiment of the invention is embedded with a customer problem reply dialect retrieval function, which can help a salesperson to quickly extract a practical dialect for customer relationship management and use, the dialect in the prior art is only presented in a list form, and related dialect can be inquired and extracted and used by manually pulling a rolling button without the key character retrieval technology related to the invention, so that if the size of a dialect library is large, the dialect acquisition efficiency is influenced, and the service plates related to automobile sales are more, the complexity of customer problems is also high, such as a series of problems of finance, insurance, replacement, decoration, fine products, branding, after-sale service, vehicle type, price, discount and the like.
In one embodiment, the method further comprises:
the weather obtaining module is used for obtaining weather forecast information;
and the scene adding module is used for adding a weather application scene and a corresponding weather dialect in the dialect library according to the weather forecast information.
The weather obtaining module can obtain real-time weather forecast information through technologies such as a crawler and the like, and a scene adding module is used for adding a weather application sub-scene and a corresponding weather conversation in a conversation bank according to different weather information so as to be used by sellers for online chatting or telephone follow-up, help the sellers to carry out relationship maintenance and effective invitation by means of weather conditions, and improve the customer goodness and invitation rate.
In the embodiment of the present application, the implementation order among multiple steps may be replaced without affecting the implementation purpose.
The above description is only for the specific embodiments of the present application, but the scope of the present application 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 application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (11)
1. A question-answering method, comprising:
acquiring a consultation conversation screenshot and performing character recognition on the consultation conversation screenshot to obtain corresponding consultation characters;
matching a corresponding first application scene in a dialect library according to the consultation characters;
and acquiring a first template dialog in a dialog library according to the first application scene.
2. The method of claim 1, wherein the first application scenario is associated with a first application sub-scenario and a corresponding first template scenario in the scenario library, and wherein obtaining a first template scenario in the scenario library according to the first application scenario comprises:
and acquiring a first application sub-scene and a corresponding first template dialect in a dialect library according to the first application scene.
3. The method of claim 1, further comprising: associating a second application sub-scene and a corresponding second template dialog with the first application scene in the dialog library, wherein correspondingly, the acquiring of the first template dialog in the dialog library according to the first application scene comprises the following steps: and acquiring a first template dialect, a second application sub-scene and a second template dialect in a dialect library according to the first application scene.
4. The method of claim 2, wherein the consulting text is matched with a keyword associated with the first application scenario in the linguistic library.
5. The method of claim 2, further comprising:
acquiring input characters;
and matching the corresponding first application scene in the dialect library according to the input characters.
6. The method of claim 1, further comprising:
acquiring weather forecast information;
and adding a weather application scene and a corresponding weather dialect in the dialect library according to the weather forecast information.
7. The method of claim 1, wherein the first application scenario is one or more, and wherein obtaining a first template dialog in a dialog library according to the first application scenario comprises: and if the matched first application scene is the only scene, outputting a corresponding first template dialog.
8. A question answering device, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a consultation conversation screenshot and performing character recognition on the consultation conversation screenshot to obtain corresponding consultation characters;
the first matching module is used for matching a corresponding first application scene in the dialogistic library according to the consultation characters;
and the speech technology acquisition module is used for acquiring a first template speech technology in a speech technology library according to the first application scene.
9. The apparatus of claim 7, wherein the first application scenario is associated with a first application sub-scenario and a corresponding first template scenario in the scenario library, and wherein the scenario acquisition module is further configured to acquire the first application sub-scenario and the corresponding first template scenario in the scenario library according to the first application scenario.
10. The apparatus of claim 8, further comprising:
a scene association module for associating a second application sub-scene and a corresponding second template dialog to the first application scene in the dialog library;
the conversation acquiring module is further used for acquiring a first template conversation, a second application sub-scene and a second template conversation in a conversation library according to the first application scene.
11. The apparatus of claim 8, further comprising:
the input character acquisition module is used for acquiring input characters;
the first matching module is also used for matching a corresponding first application scene in the dialogistic library according to the input characters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010882345.XA CN112036912A (en) | 2020-08-27 | 2020-08-27 | Question-answering method and question-answering device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010882345.XA CN112036912A (en) | 2020-08-27 | 2020-08-27 | Question-answering method and question-answering device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112036912A true CN112036912A (en) | 2020-12-04 |
Family
ID=73586739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010882345.XA Withdrawn CN112036912A (en) | 2020-08-27 | 2020-08-27 | Question-answering method and question-answering device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112036912A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800199A (en) * | 2021-01-20 | 2021-05-14 | 广州佰锐网络科技有限公司 | Method and system for supporting dynamic flexible configuration of verbal text content |
-
2020
- 2020-08-27 CN CN202010882345.XA patent/CN112036912A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800199A (en) * | 2021-01-20 | 2021-05-14 | 广州佰锐网络科技有限公司 | Method and system for supporting dynamic flexible configuration of verbal text content |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112182197A (en) | Method, device and equipment for recommending dialect and computer readable medium | |
| DE60014743T2 (en) | Method and apparatus for analyzing natural language | |
| US20100332287A1 (en) | System and method for real-time prediction of customer satisfaction | |
| DE60017000T2 (en) | Method for goal-oriented language translation by means of extraction of meaning and dialogue | |
| EP4036823A1 (en) | Customization platform and method for service quality evaluation product | |
| US20220138770A1 (en) | Method and apparatus for analyzing sales conversation based on voice recognition | |
| CN106709049A (en) | Phonetic character key word identifying and searching system | |
| KR20200092499A (en) | Method and apparatus for counseling support using interactive artificial intelligence technology | |
| CN112235470B (en) | Incoming call client follow-up method, device and equipment based on voice recognition | |
| CN110598008A (en) | Data quality inspection method and device for recorded data and storage medium | |
| CN112925888A (en) | Method and device for training question-answer response and small sample text matching model | |
| CN114357126A (en) | Intelligent question-answering system | |
| CN114817507A (en) | Reply recommendation method, device, equipment and storage medium based on intention recognition | |
| EP1983493B1 (en) | Shop scale for processing purchases | |
| CN112036912A (en) | Question-answering method and question-answering device | |
| CN114783421A (en) | Intelligent recommendation method and device, equipment and medium | |
| WO2019003395A1 (en) | Call center conversational content display system, method, and program | |
| CN115564529A (en) | Voice navigation control method and device, computer terminal and storage medium | |
| CN107871254A (en) | The method and device of data object information is provided | |
| CN113505606B (en) | Training information acquisition method and device, electronic equipment and storage medium | |
| CN111651554A (en) | Insurance question-answer method and device based on natural language understanding and processing | |
| CN115602160A (en) | Service handling method and device based on voice recognition and electronic equipment | |
| CN110765242A (en) | Method, device and system for providing customer service information | |
| US11842372B2 (en) | Systems and methods for real-time processing of audio feedback | |
| CN113095868A (en) | Method, device and system for assisting in selling commodities |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201204 |
|
| WW01 | Invention patent application withdrawn after publication |