CN107092602B - Automatic response method and system - Google Patents
Automatic response method and system Download PDFInfo
- Publication number
- CN107092602B CN107092602B CN201610090173.6A CN201610090173A CN107092602B CN 107092602 B CN107092602 B CN 107092602B CN 201610090173 A CN201610090173 A CN 201610090173A CN 107092602 B CN107092602 B CN 107092602B
- Authority
- CN
- China
- Prior art keywords
- service
- question
- matching
- user
- answer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2423—Interactive query statement specification based on a database schema
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of computers, and provides an automatic response method, which comprises the following steps: acquiring user input information; the user input information is matched with the question template, corresponding processing is carried out according to the matching result, and the method comprises a service handling method, so that the user can handle the service directly in an automatic answering system through a simple question-answering mode, the labor cost of internet operation is reduced, and the user experience can be improved. In addition, the invention also provides an automatic response system.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an automatic response method and an automatic response system.
Background
With the rapid popularization and application of the internet, it is a goal pursued by each website system to provide efficient, fast and accurate services for users, and in the prior art, in many application programs of internet services, automatic response services are provided for general problems of users, so that good experience is provided for users.
The traditional automatic answering system generally answers based on a predefined knowledge base, namely, a question template, an answer and a corresponding relation between the question template and the answer are stored in the knowledge base in advance, when the system is applied, the corresponding question template is matched in the knowledge base aiming at the input of a user, if the matching is successful, the corresponding answer is found according to the corresponding relation between the question template and the answer, and the answer is directly returned to the user. For example, the user inputs the charging standard, the system matches the answer corresponding to the charging standard from the knowledge base, and returns the found answer to the user, and the session is ended. The automatic response system basically only can process simple dialogue scenes of asking for a question and answering, and cannot provide further services for users, if the users need to handle specific services, the users need to request manual services or log in other entrances of the system again for handling the services, the internet service handling is more and more popular along with the increasing capability of the internet system for handling the services, if each service needs to depend on manual work or requires the users to enter the handling through the corresponding service entrance, the labor cost of internet operation is increased, the user experience is poor, and therefore, the automatic response system with the service handling function is one of the main targets to be achieved by the existing automatic response system.
Disclosure of Invention
In order to solve the technical problems mentioned in the background technology, the invention provides the automatic response method and the automatic response system, so that the automatic response system has the function of automatically accepting the service, and a user can directly conduct service handling in the automatic response system in a simple question and answer mode, thereby not only reducing the labor cost of internet operation, but also improving the user experience.
The invention provides an automatic response method, which comprises the following steps: acquiring user input information; matching the user input information with a question template; if the matching is successful, obtaining a corresponding question answer according to the successfully matched question template, judging the type of the question answer, and if the question answer is a direct answer, directly returning the question answer to the user; if the answer to the question is a service acceptance request, adding the answer to a service theme stack to be processed, setting the answer to the question as a current processing service theme, simultaneously backtracking a historical response record of the session as an input set to be detected, and starting a parameter collection process, wherein the parameter collection process comprises the following steps: iteratively extracting service parameters which are not collected in the input set to be detected according to the currently processed service theme, judging whether the parameters required by the currently processed service theme are fully collected, if so, executing a service program corresponding to the currently processed service theme, returning a service processing result to a user, if not, returning a parameter collection prompt to the user, guiding the user to input corresponding parameters, receiving user input information, and performing matching again; if the matching fails, firstly confirming whether the to-be-processed service exists in the to-be-processed service theme stack, if so, extracting a latest added theme from the to-be-processed service theme stack as a current processing service theme, taking the current user input information as the to-be-detected input set, and starting the parameter collection process; and if the to-be-processed service does not exist in the to-be-processed service theme stack, returning a preset response failure prompt to the user.
In a preferred embodiment of the present invention, when matching the user input information with a problem template, an exact matching is performed first, where the exact matching includes performing word segmentation on the user input information, and performing matching with the problem template based on a Trie Tree sequence search algorithm, and if the matching is unsuccessful, the user input information after word segmentation is expanded first, and then the matching is performed.
In a preferred embodiment of the present invention, the expansion processing includes performing part-of-speech tagging on the part-of-speech of the user input information, and then performing at least one of non-keyword part-of-speech removal, error-prone word correction, synonym expansion, ontology-based semantic expansion, and keyword sequence exchange on the part-of-speech.
In a preferred embodiment of the present invention, the problem template is stored in the form of a word segmentation based on a Trie tree data structure.
In addition, the invention also provides an automatic response system, which comprises a front-end module, a processing module and a display module, wherein the front-end module is used for receiving the input information of the user and displaying the processing result; the question matching module is connected with the front-end module and used for matching the user input information received by the front-end module with a question template and sending a matching result to the response processing module, if the matching is successful, the response processing module searches a corresponding question answer according to the question template successfully matched, if the question answer is a direct answer, the response processing module returns the question answer to the front-end module, the front-end module displays the question answer to the user, and if the question answer is a service acceptance request, the service processing module is started; the service processing module adds the question answers to a service theme stack to be processed, sets the question answers as the current processing service theme, backtracks the historical answer records of the session as an input set to be detected, and starts a parameter collecting module; the parameter collecting module iteratively extracts service parameters which are not collected in the input set to be detected according to the currently processed service theme, judges whether the parameters required by the currently processed service theme are full, starts a service execution module if the input set is full, returns a service processing result to a user, returns a parameter collecting prompt to the user if the input set is not full, and guides the user to input corresponding parameters; the service execution module executes the service program corresponding to the currently processed service theme and returns service processing to the front-end module; if the matching fails, the response processing module firstly confirms whether the to-be-processed service exists in the to-be-processed service theme stack, if so, extracts a latest added theme from the to-be-processed service theme stack as a current processing service theme, takes the current user input information as the to-be-detected input set, and starts the parameter collecting module; and if the to-be-processed service does not exist in the to-be-processed service theme stack, returning a preset response failure prompt to the front-end module.
In a preferred embodiment of the present invention, the question template, the question answers, and the correspondence between the question template and the question answers are stored in a knowledge base.
The automatic response method provided by the invention can carry out corresponding response processing aiming at the content input by the user, not only retains the original simple response mode, but also can accept the service request provided by the user, guide the user to input the required parameters through the simple question-answer mode, automatically execute the service program and directly return the processing result to the user.
Drawings
FIG. 1 is a flow chart of an automatic response method according to a preferred embodiment of the present invention;
FIG. 2 is a flow chart illustrating parameter collection according to the embodiment of FIG. 1;
fig. 3 is a schematic structural diagram of an automatic answering system according to a preferred embodiment of the invention.
Detailed Description
The invention will be explained in more detail below with reference to the drawings. It should be noted that the following described embodiments are illustrative and are only illustrative and not to be construed as limiting the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating an auto-answer method according to a preferred embodiment of the invention.
As shown in fig. 1, the automatic answering method includes the steps of:
s1: and acquiring user input information.
S2: and matching the user input information with a question template. The matching method comprises the following steps: the method comprises the steps of firstly, carrying out accurate matching, wherein the accurate matching refers to the step of carrying out word segmentation processing on user input information through a word segmentation technology, and matching with a problem template based on a Trie Tree sequence search algorithm, wherein the Trie Tree is also called a dictionary Tree or a word search Tree, is a Tree structure and is a variant of a Hash Tree.
And if the matching result of the accurate matching is unsuccessful, further performing expansion processing on the user input information after word segmentation, and then performing matching, wherein the expansion processing comprises performing part-of-speech tagging on the word segmentation of the user input information, then performing at least one of processing of removing non-keyword, correcting error-prone words, expanding synonyms, performing body-based semantic expansion and exchanging keyword word sequences on the word segmentation, and performing correction and word sense expansion on the user input information to improve the matching rate.
The non-keyword characteristics are removed, that is, after the user input information is segmented, non-keyword characteristics without practical meaning, such as adverbs, may exist in the segmented words, however, when matching is performed, the non-keyword characteristics interfere with the matching result, so that the matching accuracy can be improved to a certain extent by removing the non-keyword characteristics in the user input information.
The correction of the error-prone words refers to understanding of the error-prone words based on an error-prone word library, in actual situations, user input information may contain error words which may be easily generated in daily life, the error words can be stored in the error-prone word library in a pre-induction mode, and the user input information can be corrected directly based on the error-prone word library subsequently, so that the meaning of the user input information can be accurately understood under the condition that the error-prone words exist in the user input information.
The expansion of synonyms means that expansion of synonyms is carried out based on keywords in user input information, so that the matching range is expanded; ontology-based semantic expansion refers to expanding the semantic meaning to be expressed by a user based on semantic understanding of information input by the user, for example, if the user inputs "pet", the semantic meaning can be expanded downward to "cat" or "dog", and similarly, if the user inputs "cat", the semantic meaning can be expanded upward to "pet" or "animal".
The exchange of the keyword sequence means that the participles after the participles are performed on the information input by the user have a certain sequence, and when the problem template matching is performed, the sequence of the participles can influence the matching result, so that the repeated attempt can be performed by means of changing the participle sequence when the matching is not successful.
It should be noted that the problem template is stored in the knowledge base in advance, and is also stored based on the Trie tree data structure in the form of word segmentation. If the matchable problem template formed by the participles can be found in the knowledge base by the user input information participles, the matching is successful, and if the matchable problem template can not be found, the matching is failed, wherein the user input information participles are completely consistent with the found problem template, or the matching degree is in an approved range, the problem template which can be matched with the user input information participles exists in the knowledge base.
S3 a: if the result of step S2 is a successful matching, a corresponding question answer is obtained according to the question template successfully matched. The knowledge base not only stores the question template in advance, but also stores the question answer and the corresponding relationship between the question template and the question answer, and when the result of the step S2 is that the matching is successful, the system can find the corresponding question answer according to the matched question template and the corresponding relationship between the pre-stored question template and the question answer.
S4: and judging the type of the answer to the question. The problem answers in the knowledge base at least comprise two types, namely a direct answer type and a service acceptance request type, wherein the direct answer type can directly reply the information input by the user without other processing, and the service acceptance request type means that the problem template corresponding to the information input by the user is a service handling request, and the system needs further processing to obtain a processing result so as to reply the information input by the user.
S5 a: and if the question answer is a direct answer, directly returning the question answer to the user.
S5 b: if the answer to the question is a service acceptance request, the answer to the question is added to a stack of service topics to be processed, then the answer to the question is set as the current service topic to be processed, and meanwhile, a historical response record of the session is traced back as an input set to be detected, and a parameter collection process is started, please refer to fig. 2, where fig. 2 is a parameter collection process diagram in the embodiment shown in fig. 1 of the present invention. As shown in fig. 2, the parameter collection flow includes the steps of:
a1, iteratively extracting service parameters which are not collected in the input set to be detected according to the current processing service theme; a2, judging whether the parameter set required by the current processing business theme is full; a3a, if the set is full, executing the service program corresponding to the current processing service theme, and returning a service processing result to the user; and A3b, if the collection is not full, returning a parameter collection prompt to the user, guiding the user to input corresponding parameters, and returning to the step S1.
S3 b: and if the result of the step S2 is that matching fails, determining whether the to-be-processed service exists in the to-be-processed service theme stack.
S6 a: if the to-be-processed service exists in the to-be-processed service theme stack, extracting a latest added theme from the to-be-processed service theme stack as a current processing service theme, taking the current user input information as the to-be-detected input set, and starting the parameter collection process.
S6 b: and if the to-be-processed service does not exist in the to-be-processed service theme stack, returning a preset response failure prompt to the user.
By the method, the aim of transacting the business in the automatic answering system through a simple question answering mode can be fulfilled for the user, waiting for manual service or searching for a corresponding business transaction window in the system for business transaction is not needed, so that the user experience is improved, and the operation cost of an Internet system is saved. Furthermore, when the problem template is matched, the input information of the user is expanded, so that the matching rate can be improved, and the performance of the automatic response system is optimized.
In addition, the present invention also provides an automatic answering system, please refer to fig. 3, and fig. 3 is a schematic structural diagram of the automatic answering system according to a preferred embodiment of the present invention.
As shown in fig. 3, the automatic answering system 100 includes a front-end module 10, a question matching module 20, an answering processing module 30, a to-be-processed business theme stack 40, a parameter collecting module 50, and a business executing module 60, wherein the front-end module 10 is respectively connected to the question matching module 20, the answering processing module 30, the parameter collecting module 50, and the business executing module 60, and is configured to acquire user input information and transmit the user input information to the question matching module 20, and receive and display processing results returned from the answering processing module 30, the parameter collecting module 50, and the business executing module 60; the question matching module 20 is connected to the response processing module 30, and is configured to receive user input information from the front-end module 10, match the user input information with a question template, and transmit a matching result to the response processing module 30; the response processing module 30 is connected to the to-be-processed business theme stack 40 and the parameter collecting module 50, receives the matching result from the question matching module 20, and performs corresponding processing according to the matching result; the parameter collection module 50 is connected to the service execution module 60; the knowledge base 70 is used for storing the question templates, the question answers and the corresponding relations between the question templates and the question answers. The following will specifically describe each module and the connection relationship between the modules.
The front-end module 10 is used for realizing interaction between the automatic response system 100 and a user, mainly providing a user input interface, acquiring user input information and displaying system information, in the automatic response system 100 of the present invention, the main function of the front-end module 10 is to acquire the user input information and transmit the user input information to the question matching module 20, and in addition, the processing results returned to the user by other modules in the automatic response system 100 are also displayed to the user through the front-end module 10.
The question matching module 20 is connected to the front-end module 10 and the response processing module 30, respectively, receives the user input information from the front-end module 10, matches the user input information with the question templates in the knowledge base 70, and sends the matching result to the response processing module 30. When the problem matching module 20 performs matching, the following steps are mainly performed: the method comprises the steps of firstly, carrying out accurate matching, wherein the accurate matching refers to the step of carrying out word segmentation processing on user input information through a word segmentation technology, and matching with a problem template based on a Trie Tree sequence search algorithm, wherein the Trie Tree is also called a dictionary Tree or a word search Tree, is a Tree structure, and is a variant of a Hash Tree. And if the matching result of the accurate matching is unsuccessful, further performing expansion processing on the user input information after word segmentation, and then performing matching, wherein the expansion processing comprises the steps of performing part-of-speech tagging on the segmented words of the user input information, then performing non-keyword part-of-speech removal, correcting error-prone words, expanding synonyms, performing body-based semantic expansion and exchanging keyword word order processing, and performing correction and word sense expansion on the user input information to improve the matching rate. It should be noted that if the word segmentation of the user input information is completely consistent with the found problem template, or the matching degree is within the approved range, it indicates that a problem template which can be matched with the word segmentation of the user input information exists in the knowledge base.
And the response processing module 30 receives the matching result from the question matching module 20 and performs corresponding response processing according to the matching result.
When the matching result is successful, the response processing module 30 will obtain the corresponding question answer from the knowledge base 70 according to the matched question template, and determine the type of the question answer, and perform corresponding operations according to the type of the question answer. The problem answers in the knowledge base at least comprise two types, namely a direct answer type and a service acceptance request type, wherein the direct answer type can directly reply the information input by the user without other processing, the service acceptance request type means that a problem template corresponding to the information input by the user is a service acceptance request, and the system needs to process step by step to obtain a processing result and can reply the information input by the user. If the answer to the question is a direct answer, directly returning the answer to the front-end module 10 and displaying the answer to the user; if the answer to the question is a service acceptance request, adding the answer to the service theme stack 40 to be processed, setting the answer to the question as the current service theme to be processed, simultaneously backtracking the history response record of the session as an input set to be detected, and calling a parameter collection module 50 to collect parameters, wherein the parameter collection comprises the following steps: and iteratively extracting service parameters which are not collected in the input set to be detected according to the current processing service theme, judging whether the parameter set required by the current processing service theme is full, if so, calling a service execution module 60 to execute a service program corresponding to the current processing service theme, returning a service processing result to the front-end module 10, displaying the service processing result to a user, and if not, returning a parameter collection prompt to the front-end module 10, displaying the parameter collection prompt to the user, and guiding the user to input corresponding parameters.
If the result is that the matching fails, the response processing module 30 determines whether the pending service exists in the pending service theme stack 40.
If there is a service to be processed in the service subject stack 40 to be processed, the newly added subject is extracted from the service subject stack 40 to be processed as the current processing service subject, the current user input information is used as the input set to be detected, and the parameter collection module 50 is invoked to collect the parameters, the method steps of parameter collection are described in the foregoing, and are not described herein again.
If the to-be-processed service does not exist in the to-be-processed service theme stack 40, a preset response failure prompt is returned to the front-end module 10 and displayed to the user.
And a knowledge base 70 for storing the question template, the question answer and the corresponding relationship between the two. The problem template is stored in a knowledge base in advance and is stored in a word segmentation mode based on a Trie tree data structure. The problem answers comprise two types, namely a direct answer type and a service acceptance request type, wherein the direct answer type can directly reply the user input information without other processing, and the service acceptance request type means that a problem template corresponding to the user input information is a service acceptance request, and the system needs further processing to obtain a processing result so as to reply the user input information.
In summary, the present invention provides an automatic response method and system, and adds a service processing function on the basis of a traditional simple automatic response system, so that a user can directly obtain required information and handle related services in a simple and understandable question and answer manner, thereby enhancing the function of the automatic response system, improving the user experience, and reducing the operation cost of the system. Furthermore, the matching rate is improved and the performance of the automatic response system is improved by expanding the information input by the user. It should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention, and any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. An automatic answering method, comprising the steps of:
acquiring user input information;
matching the user input information with a question template;
if the matching is successful, obtaining a corresponding question answer according to the successfully matched question template, judging the type of the question answer, and if the question answer is a direct answer, directly returning the question answer to the user; if the answer to the question is a service acceptance request, adding the answer to a service theme stack to be processed, setting the answer to the question as a current processing service theme, simultaneously backtracking a historical response record of the session as an input set to be detected, and starting a parameter collection process, wherein the parameter collection process comprises the following steps: iteratively extracting service parameters which are not collected in the input set to be detected according to the currently processed service theme, judging whether the parameter set required by the currently processed service theme is full, if so, executing a service program corresponding to the currently processed service theme, returning a service processing result to a user, if not, returning a parameter collection prompt to the user, guiding the user to input corresponding parameters, receiving user input information, and performing matching again;
if the matching fails, firstly confirming whether the to-be-processed service exists in the to-be-processed service theme stack, if so, extracting a latest added theme from the to-be-processed service theme stack as a current processing service theme, taking the current user input information as the to-be-detected input set, and starting the parameter collection process; if the to-be-processed service does not exist in the to-be-processed service theme stack, returning a preset response failure prompt to the user;
when the user input information is matched with the problem template, firstly, performing precise matching, wherein the precise matching comprises the steps of performing word segmentation on the user input information, matching with the problem template based on a Trie Tree sequence search algorithm, and if the matching is unsuccessful, performing expansion processing on the user input information after word segmentation, and then performing matching.
2. The automatic answering method according to claim 1, wherein the expansion process includes performing part-of-speech tagging on the participle of the user input information, and then performing at least one of non-keyword part-of-speech removal, error-prone word correction, synonym expansion, ontology-based semantic expansion, and keyword sequence exchange on the participle.
3. The automated answering method according to claim 1, wherein the question template is stored in the form of a participle based on a Trie tree data structure.
4. An automatic answering system is characterized by comprising a front-end module, a front-end module and a back-end module, wherein the front-end module is used for receiving user input information and displaying a processing result; the question matching module is connected with the front-end module and used for matching the user input information received by the front-end module with a question template and sending a matching result to the response processing module, if the matching is successful, the response processing module searches a corresponding question answer according to the question template successfully matched, if the question answer is a direct answer, the response processing module returns the question answer to the front-end module, the front-end module displays the question answer to the user, and if the question answer is a service acceptance request, the service processing module is started; the service processing module adds the question answers to a service theme stack to be processed, sets the question answers as the current processing service theme, backtracks the historical answer records of the session as an input set to be detected, and starts a parameter collecting module; the parameter collecting module iteratively extracts service parameters which are not collected in the input set to be detected according to the currently processed service theme, judges whether the set of parameters required by the currently processed service theme is full, if the set is full, the service executing module is started, a service processing result is returned to a user, and if the set is not full, a parameter collecting prompt is returned to the user, and the user is guided to input corresponding parameters; the service execution module executes the service program corresponding to the currently processed service theme and returns service processing to the front-end module; if the matching fails, the response processing module firstly confirms whether the to-be-processed service exists in the to-be-processed service theme stack, if so, extracts a latest added theme from the to-be-processed service theme stack as a current processing service theme, takes the current user input information as the to-be-detected input set, and starts the parameter collecting module; if the to-be-processed service does not exist in the to-be-processed service theme stack, returning a preset response failure prompt to the front-end module;
when the user input information is matched with the problem template, firstly, performing precise matching, wherein the precise matching comprises the steps of performing word segmentation on the user input information, matching with the problem template based on a Trie Tree sequence search algorithm, and if the matching is unsuccessful, performing expansion processing on the user input information after word segmentation, and then performing matching.
5. The automatic answering system according to claim 4, wherein the question template, the question answer, and the correspondence between the question template and the question answer are stored in a knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610090173.6A CN107092602B (en) | 2016-02-18 | 2016-02-18 | Automatic response method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610090173.6A CN107092602B (en) | 2016-02-18 | 2016-02-18 | Automatic response method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107092602A CN107092602A (en) | 2017-08-25 |
| CN107092602B true CN107092602B (en) | 2021-02-05 |
Family
ID=59648737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610090173.6A Active CN107092602B (en) | 2016-02-18 | 2016-02-18 | Automatic response method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107092602B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020009B (en) * | 2017-09-29 | 2023-03-21 | 阿里巴巴集团控股有限公司 | Online question and answer method, device and system |
| CN107832291B (en) * | 2017-10-26 | 2020-03-31 | 平安科技（深圳）有限公司 | Man-machine cooperation customer service method, electronic device and storage medium |
| CN107944735A (en) * | 2017-12-06 | 2018-04-20 | 国云科技股份有限公司 | A kind of tourist attraction brand value analysis method based on classic poetry |
| CN108595307A (en) * | 2018-05-03 | 2018-09-28 | 广州供电局有限公司 | A kind of automatic self-healing method based on IT O＆Ms |
| CN112800170A (en) * | 2019-11-14 | 2021-05-14 | 华为技术有限公司 | Question matching method and device and question reply method and device |
| CN113094479B (en) * | 2019-12-20 | 2023-09-19 | 百度在线网络技术（北京）有限公司 | Problem processing method, device, electronic equipment and medium |
| CN111737425B (en) * | 2020-02-28 | 2024-03-01 | 北京汇钧科技有限公司 | Response method, device, server and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676909A (en) * | 2008-09-16 | 2010-03-24 | 联想(北京)有限公司 | Method and computer for providing self-service for users |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101076184B (en) * | 2006-07-31 | 2011-09-21 | 腾讯科技（深圳）有限公司 | Method and system for realizing automatic reply |
| US9063975B2 (en) * | 2013-03-15 | 2015-06-23 | International Business Machines Corporation | Results of question and answer systems |
| CN102103455A (en) * | 2009-12-18 | 2011-06-22 | 上海智问软件技术有限公司 | Interactive input-based intelligent prompting system and realization method thereof |
| CN102026124B (en) * | 2010-12-07 | 2013-04-17 | 中国电信股份有限公司 | Intelligent SMS (short message service) platform system and SMS (short message service) implementation method based on system |
-
2016
- 2016-02-18 CN CN201610090173.6A patent/CN107092602B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101676909A (en) * | 2008-09-16 | 2010-03-24 | 联想(北京)有限公司 | Method and computer for providing self-service for users |
| CN104050256A (en) * | 2014-06-13 | 2014-09-17 | 西安蒜泥电子科技有限责任公司 | Initiative study-based questioning and answering method and questioning and answering system adopting initiative study-based questioning and answering method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107092602A (en) | 2017-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107092602B (en) | Automatic response method and system | |
| US8560513B2 (en) | Searching for information based on generic attributes of the query | |
| CN106815311B (en) | Question matching method and device | |
| CN107103005B (en) | Question and answer corpus collection method and device | |
| WO2017181834A1 (en) | Intelligent question and answer method and device | |
| CN110970021B (en) | Question-answering control method, device and system | |
| CN111326140B (en) | Speech recognition result discriminating method, correcting method, device, equipment and storage medium | |
| CN111078856B (en) | Group chat conversation processing method and device and electronic equipment | |
| US11526512B1 (en) | Rewriting queries | |
| CN110807311B (en) | Method and device for generating information | |
| US11423219B2 (en) | Generation and population of new application document utilizing historical application documents | |
| CN107480197B (en) | Entity word recognition method and device | |
| US11379527B2 (en) | Sibling search queries | |
| CN111324705B (en) | System and method for adaptively adjusting associated search terms | |
| CN111782817A (en) | Knowledge graph construction method and device for information system and electronic equipment | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN109829048B (en) | Electronic device, interview assisting method, and computer-readable storage medium | |
| CN109977397B (en) | News hotspot extracting method, system and storage medium based on part-of-speech combination | |
| CN112199474A (en) | Voice customer service method and system | |
| CN116150376A (en) | Sample data distribution optimization method, device and storage medium | |
| CN116383234A (en) | Search statement generation method and device, computer equipment and storage medium | |
| CN111737543A (en) | Question and answer pair extraction method, device, equipment and storage medium | |
| CN112395402A (en) | Depth model-based recommended word generation method and device and computer equipment | |
| CN112905752A (en) | Intelligent interaction method, device, equipment and storage medium | |
| CN111859148A (en) | Theme extraction method, device and equipment and computer readable 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 214131 floor 10 and 11, building B, swan tower, Wuxi Software Park, No. 90, Jinghui East Road, Xinwu District, Wuxi City, Jiangsu Province Applicant after: Lanxin Technology Group Co., Ltd Address before: Wuxi District of Jiangsu city of Wuxi province Zhenze road 214131 No. 18 Wuxi Software Park, whale D Building Room 601 Applicant before: LONGSHINE TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |