CN113076413A - Parameter association service method, system, device and storage medium - Google Patents
Parameter association service method, system, device and storage medium Download PDFInfo
- Publication number
- CN113076413A CN113076413A CN202110480007.8A CN202110480007A CN113076413A CN 113076413 A CN113076413 A CN 113076413A CN 202110480007 A CN202110480007 A CN 202110480007A CN 113076413 A CN113076413 A CN 113076413A
- Authority
- CN
- China
- Prior art keywords
- knowledge base
- information
- parameter
- association
- knowledge
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000013507 mapping Methods 0.000 claims abstract description 132
- 238000006243 chemical reaction Methods 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 18
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000005429 filling process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/027—Frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and provides a parameter association service method, a system, a device and a storage medium. The method comprises the following steps: acquiring configuration information of a dialog system, acquiring information in a knowledge base, and performing associated mapping on the configuration information and the information in the knowledge base to obtain an associated mapping relation; receiving a calling request sent by a dialog system, calling information associated with the calling request in a knowledge base according to the associated mapping relation, and sending the information to the knowledge base for service inquiry; and receiving the query result output by the knowledge base, calling the information associated with the query result according to the association mapping relation, and returning the information to the dialogue system to generate a reply dialogue. The invention adopts an entity-relation-entity triple mode to form the association mapping relation, and completes data transmission between the dialogue system and the knowledge base according to the association mapping relation in the service process, thereby realizing the decoupling of the dialogue system and the knowledge base, improving the flexibility and the expandability of the knowledge base service, and improving the parameter association and the service efficiency.
Description
Technical Field
The present invention relates to the field of artificial intelligence robot technology, and in particular, to a parameter association service method, system, apparatus, and storage medium.
Background
The text robot is used as a main component of intelligent customer service, and is widely applied to government affair service websites, e-commerce platforms, life service platforms and the like. Unlike conventional software, the robot provides services such as consultation, office, etc. by means of a dialogue with the user; for the scenes of consultation, question answering and the like, the flexibility and expandability of the knowledge base service become a key factor influencing the overall service quality of the robot.
Existing knowledge base services mainly include two types:
one is to integrate the knowledge base into the dialog management platform. The administrator can only maintain knowledge on the dialogue management platform according to needs, and directly call corresponding knowledge service to meet the inquiry requirements during service. However, the method can only support a small number of knowledge service types with simpler structures, cannot meet the requirements of complex and diversified knowledge base structure types, and is difficult to support the calling of third-party knowledge services.
And the other method is to provide a set of interface parameter documents for accessing the third-party knowledge service at the dialog system side and call the third-party knowledge service in the form of an interface. However, in the existing method, a set of interface parameter documents is provided by a dialog system side, and development and adaptation are performed by a third-party application manufacturer, so that the development efficiency is low, and the flexible association relationship between natural language understanding and knowledge base service cannot be realized.
Based on the method and the system, the parameter association service method and the system are provided to achieve decoupling of the dialogue system and the knowledge base, flexibility and expandability of services of the dialogue system knowledge base are improved, and configuration efficiency of skills is improved.
Disclosure of Invention
The invention aims to provide a parameter association service method, a system, a device and a storage medium, which are used for realizing the decoupling of a dialog system and a knowledge base and solving the problems of poor flexibility, poor expandability and low efficiency of association service between the dialog system and the knowledge base service in the prior art.
The above purpose is realized by the following technical scheme:
according to an aspect of the present invention, the present invention provides a parameter association service method applied to an electronic device, the method including:
acquiring configuration information of a dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation; the dialogue system and the knowledge base are mutually independent systems, the configuration information of the dialogue system comprises intentions, word slot parameters and request parameters, knowledge services are stored in the knowledge base, the information in the knowledge base comprises knowledge service information and knowledge base parameter information, and the association mode in the association mapping relation comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many;
receiving a calling request sent by a dialog system, calling knowledge base information of the information associated with the calling request from the associated mapping relation, and sending the knowledge base information to a knowledge base so as to carry out service inquiry through knowledge services stored in the knowledge base;
and receiving a query result output by the knowledge base, calling configuration information associated with the query result from the association mapping relation, and sending the configuration information to the dialogue system so as to generate a reply dialogue through the dialogue system.
Optionally, the step of obtaining configuration information of the dialog system, obtaining information in a knowledge base, and performing association mapping between the configuration information and the information in the knowledge base includes: acquiring an intention of a dialog system, acquiring knowledge service in a knowledge base, and mapping the intention to the knowledge service; wherein one intention is associated with one or more knowledge services, or a plurality of intents are associated with one knowledge service; when one intention is associated with a plurality of knowledge services, different scenes are configured according to the intention, and the intention association is mapped to different knowledge services according to different scenes.
Optionally, the step of obtaining configuration information of the dialog system, obtaining information in a knowledge base, and performing association mapping between the configuration information and the information in the knowledge base further includes: acquiring word slot parameters of a dialog system, acquiring knowledge base parameters, and mapping the word slot parameters and the knowledge base parameters; wherein, one word slot parameter is associated with different knowledge base parameters according to different intents.
Optionally, the step of obtaining configuration information of the dialog system, obtaining information in a knowledge base, and performing association mapping between the configuration information and the information in the knowledge base further includes: acquiring an intention request parameter of a dialog system, acquiring a knowledge base parameter, and mapping the intention request parameter and the knowledge base parameter; wherein, the answer corresponding to the intention request under different intentions is mapped to the same knowledge base parameter or is mapped to a plurality of different knowledge base parameters.
Optionally, before the step of performing association mapping on the configuration information and information in a knowledge base, the method further includes: and converting the form of the configuration information into a digital ID form.
Optionally, the step of calling the knowledge base information associated with the call request from the association mapping relationship and sending the knowledge base information to the knowledge base includes: and according to the association mapping relation, performing parameter conversion on the received call request, converting the parameter into a parameter corresponding to the knowledge base information associated with the call request, and sending the converted parameter to a knowledge base.
Optionally, the step of calling the configuration information associated with the query result from the association mapping relationship and returning the configuration information to the dialog system includes: and according to the association mapping relation, performing parameter conversion on the received query result, converting the received query result into a parameter corresponding to the configuration information of the information associated with the query result, and returning the converted parameter to the dialog system.
Optionally, the method further comprises: when the acquired configuration information of the dialog system is an intention, configuring a storage unit for storing the converted parameters for the intention; when the received information is an intention, judging whether the storage content in the storage unit corresponding to the intention is empty; determining whether parameter conversion is needed or not according to the judgment result, and determining an information sending object; if the intention is empty, converting parameters of the intention according to the association mapping relation, and transmitting the converted parameters to a knowledge base; and if not, directly transmitting the parameters in the storage unit corresponding to the intention to a knowledge base.
According to another aspect of the present invention, the present invention provides a parameter association service system, including:
the association mapping unit is used for acquiring configuration information of the dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation; the dialogue system and the knowledge base are mutually independent systems, the configuration information of the dialogue system comprises intentions, word slot parameters and request parameters, knowledge services are stored in the knowledge base, the information in the knowledge base comprises knowledge service information and knowledge base parameter information, and the association mode in the association mapping relation comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many;
the calling service unit is used for receiving a calling request sent by the dialog system, calling knowledge base information associated with the calling request from the associated mapping relation and sending the knowledge base information to a knowledge base so as to carry out service inquiry through the knowledge service stored in the knowledge base; and the system is used for receiving the query result output by the knowledge base, calling the configuration information associated with the query result from the association mapping relation and sending the configuration information to the dialogue system so as to generate a reply language through the dialogue system.
According to still another aspect of the present invention, there is provided an electronic apparatus, including: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the above-described parameter association service method are implemented when the processor executes the computer program.
According to yet another aspect of the present invention, the present invention further provides a computer-readable storage medium, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the above-mentioned parameter association service method.
Has the advantages that: according to the invention, the association mapping relation is formed by performing association mapping in an entity-relation-entity triple mode, so that the decoupling of the dialog system and the knowledge base is realized, information in the dialog system or the knowledge base is called and transmitted through the association mapping relation, the flexibility and the expandability of the dialog system knowledge base service are improved, and the configuration efficiency and the service efficiency of skills are improved; and various types of knowledge bases including structured knowledge and unstructured knowledge can be flexibly compatible, and the platform side of the dialog system can also be concentrated on the design and the research and development of the dialog system.
Drawings
Other objects and results of the present invention will become more apparent and more readily appreciated as the same becomes better understood by reference to the following description taken in conjunction with the accompanying drawings. In the drawings:
fig. 1 is a flowchart illustrating a parameter association service method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating parameter association mapping according to an embodiment of the invention;
FIG. 3 is a schematic flow chart of parameter conversion determination according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a parameter association service system according to an embodiment of the present invention;
FIG. 5 is a logical block diagram of a parameter association service system according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of the electronic device of the present invention.
Detailed Description
The technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention:
fig. 1 schematically shows a flowchart of a parameter association service method, and as shown in fig. 1, a parameter association service method provided by the present invention includes:
and step S1, acquiring configuration information of the dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation. The dialog system and the knowledge base are mutually independent systems, configuration information of the dialog system comprises intentions for completing natural language processing, word slot parameters and request parameters, knowledge services are stored in the knowledge base, information in the knowledge base comprises knowledge service information and knowledge base parameter information, and an association mode in the association mapping relationship comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many; the configuration information may include intent, word slot parameters, request parameters, and the like. The knowledge base is used for storing knowledge and supporting the system to perform service; including information such as one or more knowledge services and knowledge base parameters. The knowledge service is used for providing services such as inquiry and the like to support the system to complete related services. The knowledge base further comprises knowledge management for storing and managing structured knowledge and unstructured knowledge; the structured knowledge includes, but is not limited to, tables, knowledge maps, and the like, and the unstructured knowledge includes, but is not limited to, office documents of all formats, texts, pictures, XML, HTML, various types of reports, images, audio/video information, and the like.
And step S2, receiving a call request sent by the dialog system, calling knowledge base information associated with the call request from the association mapping relation, and sending the knowledge base information to a knowledge base so as to perform service inquiry through knowledge services stored in the knowledge base.
And step S3, receiving the query result output by the knowledge base, calling the information associated with the query result according to the association mapping relation, and returning the information to the dialog system so as to generate a reply dialect through the dialog system.
The method carries out association mapping by adopting an entity-relation-entity triple way and forms an association mapping relation; in the service process, the associated information is called according to the associated mapping relation and the data transmission between the dialogue system and the knowledge base is completed, so that the decoupling of the dialogue system and the knowledge base is realized, the flexibility and the expandability of the knowledge base service are improved, and the system skill configuration efficiency is improved.
In the invention, step S1, the configuration information of the dialog system is obtained, the knowledge base information is obtained, and the configuration information and the knowledge base information are associated and mapped to obtain the associated mapping relation. Specifically, the method may include: mapping the acquired intention of the dialog system to a knowledge service in a knowledge base, mapping the acquired word slot parameters of the dialog system with the knowledge base parameters, and mapping the acquired intention request parameters of the dialog system with the knowledge base parameters. Fig. 2 schematically shows a case of a parameter association map, including three association maps of step S11 to step S13. Each mapping is described in detail below:
the method comprises the steps of obtaining the intention of the dialog system, obtaining the knowledge service in the knowledge base, and mapping the intention to the knowledge service in the knowledge base so as to subsequently call the corresponding knowledge service for inquiry. By completing the mapping of the intentions and the knowledge services, when the corresponding intentions are triggered by the user, the associated knowledge services can be called to perform corresponding service operations. For example, the intention parameters such as "find weather", "order", "check place or person" in the dialog system are mapped to the knowledge services such as "find weather", "order", "check place or person" in the knowledge base, and if the user triggers the intention, the user can inquire by calling the corresponding knowledge service, so that the problem that the intention is inconsistent with the calling of the knowledge service can be avoided.
Further, in the step of mapping the intent to knowledge services in the knowledge base, one intent may be associated with one or more knowledge services, or multiple intents may be associated with one knowledge service. The present invention differs from the traditional simple parameter-parameter mapping; the invention adopts the entity-relation-entity triple way to carry out the association mapping, and one intention can be associated with a plurality of knowledge services, thereby improving the compatibility of the system and the flexibility of the association services between the dialogue system and the knowledge base.
Preferably, when one intention is associated with a plurality of knowledge services, the method further comprises the following steps: configuring different scenes according to the intention, and mapping the intention association into different knowledge services according to different scenes. That is, when one intention corresponds to a plurality of knowledge services, the knowledge service corresponding to the intention is determined according to the scene of the intention, that is, the corresponding service is located and searched through the relationship. The invention can improve the compatibility of the system by configuring different scenes for the same intention and then associating the corresponding knowledge services, and can complete the implementation service of the scene intention even if a new scene exists.
Illustratively, one intent is "satisfaction rating"; the intention corresponds to two different scenarios, namely 'booking tickets' and 'checking weather'; during association mapping, intentions are respectively associated and mapped into two different knowledge services according to different scenes, namely, "congratulate you on a trip, please score the service" and "ask you what help they need, for example, in the knowledge service that does not need to score the service".
Further, the knowledge service in the knowledge base can be exposed in the form of a service interface. Specifically, the method comprises the following steps: firstly, packaging knowledge services in a knowledge base into a service interface; and then, associating the acquired certain intention with a service interface corresponding to the corresponding knowledge service, thereby mapping the intention to the knowledge service in the knowledge base. Each knowledge service is packaged into an interface, and the knowledge service can be understood as being called by calling the interface; the display form can be a card, a link or a text, etc., and is not limited in particular as long as the corresponding interface is represented.
Illustratively, acquiring 'intent of checking a train ticket', corresponding to 12306 an API (application programming interface) of the ticket checking service, and associating the intent of the train ticket created in the dialogue system with the API of the ticket checking service; when the user inputs that i want to inquire about the train ticket, and triggers the intention, the system recognizes that the inquiry is to be made through the 12306 interface, and then the information input by the user is: in tomorrow, Beijing goes to Shanghai, and the information is transmitted to 12306 ticket checking service through the interface to be inquired.
The method comprises the steps of obtaining word slot parameters of a dialogue system, obtaining knowledge base parameters, and mapping the word slot parameters and the knowledge base parameters so as to complete answer query of subsequent intention requests, or complete query and judgment of specific word slots according to needs. By completing the associated mapping of the word slot parameters and the knowledge base parameters, the associated knowledge base parameters can be called to perform word slot query or complete answer query together with the intention request parameters subsequently according to the word slot parameters. Further, a word slot parameter is associated with different knowledge base parameters according to different intents; specifically, the knowledge service corresponding to the intention may be determined first, and then the word slot parameter may be associated with a knowledge base parameter in the knowledge service.
Illustratively, a word slot parameter associates parameters in different knowledge bases under different intents. Two intentions are: look for weather and order a train ticket, it all has a word groove: time. The method comprises the following specific steps: acquiring an intention parameter ' train ticket booking ' and a word slot parameter ' time ' in a dialog system, and performing association mapping on the ' time ' and a start-time knowledge base parameter ' in a train ticket booking knowledge base; acquiring a weather searching intention parameter and a time word slot parameter in a dialogue system, and performing association mapping on the time and a knowledge service corresponding to the weather searching, namely a time knowledge base parameter in a weather knowledge base. Of course, one knowledge base parameter can be associated with a plurality of word slot parameters at the same time in the invention. For example, the train ticket knowledge base has a parameter of position, and in the ticket booking intention, the corresponding word slot is the destination; in the purpose of returning the ticket, the corresponding word slot is a place. Parameters in the knowledge base under the same knowledge service can correspond to the word slot parameters in different intentions.
Further, the completing the specific word slot query and judgment as required includes: and judging whether services such as the word slot exist in the knowledge base or not. For example, the word slot parameter of the location "Beijing" is acquired, the "position knowledge base parameter" in the knowledge base is called, and whether the "Beijing" exists in the knowledge base is judged according to the "position knowledge base parameter".
The method comprises the steps of obtaining an intention request parameter of a dialogue system, and mapping the intention request parameter and a knowledge base parameter so as to complete answer inquiry according to the intention request parameter and a word slot parameter. The answers corresponding to the intention requests under different intentions can be mapped to the same knowledge base parameter or can be mapped to a plurality of different knowledge base parameters. For example, the returned answers are different between the checking personnel and the checking location, and the corresponding knowledge base parameters are different.
In an optional embodiment, before the step of mapping the configuration information with the information in the knowledge base in association, the method further comprises: and converting the form of the configuration information into a digital ID form. Specifically, the form of the intention or word slot initial parameter can be converted into the form of a digital ID, and the calculation speed of the system is improved by converting the form of the intention request initial parameter or the word slot initial parameter.
Illustratively, the initial parameter is in a form of English + underline, the speed of the form is low in the process of computer operation, when an intention or a word slot is created, a 12-bit digital ID is automatically generated, and when the computer needs to perform related operation, the converted ID is automatically extracted for operation, so that the system association mapping efficiency is improved, the subsequent operation efficiency is improved, and the service efficiency is improved.
In the invention, in step S2, a call request sent by a dialog system is received, knowledge base information associated with the call request is called from the association mapping relationship and sent to a knowledge base, so as to perform service query through knowledge services in the knowledge base, and the call process is completed in a manner that the received information is subjected to parameter conversion according to the association mapping relationship, the received information is converted into parameters corresponding to the knowledge base information associated with the information, and the converted parameters are sent to the knowledge base.
The step of transmitting information by calling request sent by the dialogue system includes: receiving information input by a user; performing intention identification on the information; according to the recognized intentions, carrying out conversation management and slot filling management, and collecting the intentions and word slots; and sending a calling request to the parameter association service system according to the collected intents and word slots.
In the present invention, in step S3, the query result output by the knowledge base is received, the configuration information associated with the query result is called from the association mapping relationship and sent to the dialog system, so as to generate a reply dialog through the dialog system, and the calling process is completed by performing parameter conversion on the received transmitted information, such as the query result, according to the association mapping relationship, converting the received transmitted information into a parameter corresponding to the configuration information of the information associated with the query result, and sending the converted parameter to the dialog system.
Exemplarily, after the dialog system completes slot filling, receiving a call request sent by the dialog system, wherein the call request comprises information such as an intention request and a word slot; according to the association mapping relation, performing parameter conversion on the intention request and the word slot in the call request, namely converting the intention request and the word slot into knowledge base parameters; and transmitting the converted parameters to a knowledge base so that the knowledge base completes answer query according to the converted parameters and outputs a query result. Acquiring a query result output by a knowledge base, and performing data conversion on the query result to convert the query result into parameters in a dialog system; and returning the converted query result to a dialogue system, and generating a reply language by the dialogue system based on natural language understanding and outputting the reply language to the user.
In the following, the service process of the present invention is described by taking "look up weather intention" as an example, wherein the example does not include the step of querying word slots, and the answer query is directly performed. The method specifically comprises the following steps: 1. receiving a user input 'I want to look up weather' through a dialog system; intent to identify "look up weather intent"; dialogue and slot filling management is performed, and the following are collected: checking weather, Beijing and tomorrow information; 2. acquiring the information collected by a dialogue system, namely 'searching weather, Beijing and tomorrow', and performing parameter conversion on the information to convert the information into knowledge base parameters; 3. transmitting the converted parameters to a knowledge base, finishing weather query service according to the converted parameters by the knowledge base, and outputting a query result 'raining'; 4. acquiring a query result 'raining' output by a knowledge base, and performing data conversion on the query result to convert the query result into parameters in a dialogue system; 5. and returning the converted query result to a dialogue system, generating a reply dialect 'the weather of Mingtian Beijing is rainy' through the dialogue system, and outputting the reply dialect to the user.
Optionally, the parameter association service method of the present invention may further include a word slot query step in the service invocation process; namely, in the process of filling the slot, if the knowledge base needs to be requested to carry out word slot query service, the knowledge base is requested after parameters are converted by a parameter correlation service system KB-Hub.
Specifically, the following steps may be included: acquiring a word slot in the slot filling process of the dialogue system; converting the word slot into knowledge base parameters through parameter conversion; transmitting the converted parameters to a knowledge base so that the knowledge base judges whether the word slot exists in the knowledge base according to the converted parameters and outputs a word slot query result; acquiring a word slot query result output by a knowledge base, and performing parameter conversion to convert the word slot query result into parameters in a dialogue system; and returning the converted parameters to the dialog system so that the dialog system can carry out the next operation.
Further, in this embodiment, the method may further include: acquiring a word slot query configuration request in a dialogue system; and inquiring the configuration request according to the word slot or filling the word slot in the slot missing process. The word slot query configuration request can be to call a knowledge base for querying word slots such as places, time and the like.
Compared with the traditional method, the traditional method is a knowledge base queried according to the word slots, the method does not query the knowledge base according to the word slots, but queries according to the parameters of the knowledge base associated in the associated mapping relation, and performs parameter conversion operation in the associated mapping relation, and the conversion in the associated mapping relation can decouple the dialog system and the knowledge base, so that the conversion relation can be set freely, the flexibility and the expandability of knowledge base services are improved, and the system skill configuration efficiency is improved.
Illustratively, the word slot query is performed first, and then the answer query is performed. The method specifically comprises the following steps: 1. receiving user input of 'I want to look up weather' through a dialogue system; intent to identify "look up weather intent"; conducting dialogue and slot filling management "please enter place"; the user inputs "Beijing"; 2. acquiring a word slot 'Beijing' in the slot filling process of the dialogue system; 3. converting parameters of Beijing into knowledge base parameters, such as position: beijing; 4. transmitting the converted parameters to a knowledge base, inquiring the knowledge base according to the converted parameters to obtain corresponding values, and outputting a word slot inquiry result 'pass' when the obtained place word slot 'Beijing' exists in the knowledge base; 5. transmitting the word slot query result output by the knowledge base to a dialogue system, and continuing dialogue management and slot filling management through the dialogue system, wherein the dialogue system is used for inputting time, inputting tomorrow by a user and the like until information is collected: looking up weather, Beijing, tomorrow; 6. acquiring the information 'find weather, Beijing and tomorrow' collected by a dialog system, performing parameter conversion on the information, and converting the information into knowledge base parameters, such as 'find weather- > intent weather'; beijing- > position, Beijing; tomorrow- > time tomorrow; 7. transmitting the converted parameters to a knowledge base, finishing weather inquiry service according to the converted parameters by the knowledge base, and outputting an answer 'raining'; 8. acquiring a query result 'raining' output by a knowledge base, and performing data conversion on the query result to convert the query result into parameters in a dialogue system; 9. and returning the converted query result to a dialogue system, generating a reply grammar 'the weather of Mingtian Beijing is rainy' based on natural language understanding through the dialogue system, and outputting the reply grammar to a user.
In the invention, whether to carry out word slot query or not can be configured in the dialogue system, if the dialogue system is configured about the word slot query, in the slot filling process, when a user inputs a related word slot, the knowledge base is called to carry out the word slot query, namely, whether a corresponding value of the word slot exists or not is searched in the knowledge base. If the corresponding value of the word slot exists in the knowledge base, the parameters and the corresponding values transmitted by the knowledge base are subjected to parameter conversion, and the parameters and the corresponding values are returned to the dialogue system after being converted into configuration parameters in the dialogue system, so that the dialogue system can continuously complete operations such as dialogue management, slot filling management and the like.
In an optional embodiment, the parameter association service method further includes: and configuring a storage unit for storing the converted parameters for the intention, and before sending the information (namely before calling the association mapping relation, namely before parameter conversion), determining whether the parameter conversion is needed and determining whether a sending object is a dialog system or a knowledge base according to the judgment of whether the storage unit is empty or not.
Fig. 3 schematically illustrates a flow of parameter conversion determination in an embodiment of the present invention, and as shown in fig. 3, the flow may include:
in step S14, when the acquired configuration information of the dialogue system is an intention, a storage unit for storing the converted parameter is configured for the intention.
Step S24, when the received information is intention, judging whether the storage content in the storage unit corresponding to the intention is empty; determining whether parameter conversion is needed or not according to the judgment result, and determining an information sending object; if the intention is empty, converting parameters of the intention according to the association mapping relation, and transmitting the converted parameters to a knowledge base; and if not, directly transmitting the parameters in the storage unit corresponding to the intention to a knowledge base.
Illustratively, the method comprises the following steps: adding a field t-intent (namely a storage unit) for the intention field intent, wherein the field t-intent is used for storing the converted parameters; subsequently judging whether a field t-intent corresponding to the intent field intent is empty or not; if the intention is empty, performing parameter conversion on the content in the intention according to the associated mapping relation, and transmitting the converted content to a knowledge base; if not, the parameters in the t-intent are automatically transmitted to the knowledge base each time, and the intention does not need to be converted again.
The embodiment of the invention reduces the workload of system parameter conversion and further improves the working efficiency of parameter association service. Because the parameter association service of the invention can frequently use the conversion function, in order to improve the service efficiency, a field t-intent, namely a storage unit for storing the converted parameters, is added at the field of the intention; for example, if the storage unit is empty in the initial state, the content in intent is subjected to parameter conversion by default and then transmitted to a knowledge base; after one-time parameter association is completed, the converted parameters are directly stored in the t-intent corresponding to the intention, when association is needed next time, the system judges whether the parameters are empty or not, if the parameters are not empty, the parameters in the t-intent corresponding to the intention are automatically transmitted to the knowledge base every time, and therefore conversion is not needed every time. Therefore, the workload of system parameter conversion is reduced, and the working efficiency is improved.
In an optional embodiment, the parameter association service method further includes: judging whether a third-party system in a knowledge base needs to be called or not according to the configuration information in the calling request; and if the knowledge base can not be subjected to answer query, calling a third-party system connected with the knowledge base to carry out answer query, wherein parameters in the third-party system are subjected to associated mapping with configuration parameters in the dialogue system in advance. Other business services or other services such as knowledge queries may be provided through third party systems connected to the knowledge base. Specifically, a third-party service interface parameter document can be configured in the knowledge base, and a third-party system is connected and called through an interface form to perform services such as other business services or other knowledge queries.
Fig. 4 schematically shows the structure of the parameter association service system of the present invention. FIG. 5 schematically illustrates a logical block diagram of a parameter association service system of an embodiment. As shown in fig. 4 and 5, the parameter association service system connects between the dialog system and the knowledge base, and includes: the association mapping unit 100 calls the service unit 200.
The association mapping unit 100 is configured to obtain configuration information of the dialog system, obtain information in a knowledge base, and perform association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relationship. The dialogue system and the knowledge base are mutually independent systems, the dialogue system is used for finishing natural language processing, and configuration information in the dialogue system comprises intents, word slot parameters and request parameters; the knowledge base is used for storing knowledge and supporting a system to perform service, namely storing various knowledge services, wherein information in the knowledge base comprises knowledge services and knowledge base parameter information. The association mode in the association mapping relation comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many.
The calling service unit 200 is configured to receive a calling request sent by the acquisition dialog system, call knowledge base information associated with the calling request configuration information from the associated mapping relationship, and send the information to the knowledge base, so as to perform service query through a knowledge service stored in the knowledge base; and the system is used for receiving the query result output by the knowledge base, calling the configuration information associated with the query result from the association mapping relation and returning the configuration information to the dialog system so as to generate a reply dialog through the dialog system. When the calling service is carried out, the dialogue system transmits the information in the calling request to the parameter correlation service system through the natural language generation module.
The parameter association service system (KB-Hub for short) is arranged between a conversation system and a knowledge base, obtains an association mapping relation through pre-association mapping, transfers the association mapping relation between the conversation system and the knowledge base during service, can complete inquiry service of calling the knowledge base by the conversation system, realizes flexible association between natural language understanding and knowledge base service, and improves the flexibility and expandability of the knowledge base service of the conversation system; meanwhile, the knowledge base can be flexibly compatible with various knowledge services; the knowledge base operator or a third-party knowledge service system connected with the knowledge base can complete the knowledge service docking required by the dialog system through less service development, and the platform side of the dialog system can also be concentrated on the design and research and development of the platform side, so that the skill configuration efficiency is improved.
In an optional embodiment, the association mapping unit 100 includes: one or more of a knowledge mapping module, a word slot mapping module, and a reply mapping module.
The knowledge mapping module is used for acquiring the intention of the dialog system and mapping the intention to the knowledge service of the knowledge base. When the mapping is associated, one intention is associated with one or more knowledge services, or a plurality of intents are associated with one knowledge service.
The word slot mapping module is used for acquiring word slot parameters of the dialog system and mapping the word slot parameters with a certain parameter in the knowledge base. Wherein, one word slot parameter can be associated with different knowledge base parameters according to different intentions.
The reply mapping module is used for acquiring the intention request parameter of the dialog system and mapping the intention request parameter with the knowledge base parameter. The answers corresponding to the intention requests under different intentions can be mapped to the same knowledge base parameter or can be mapped to a plurality of different knowledge base parameters.
In an optional embodiment, the invoking service unit further includes: the initial parameter form conversion module is used for performing association mapping on the word slot parameter or the intention request parameter and the knowledge base parameter, and further comprises the following steps: and converting the form of the intention or initial parameter of the word slot into a digital ID form. By converting the form of the initial parameter of the intention request or the initial parameter of the word slot, the operation speed of the system is improved.
In an optional embodiment, the invoking service unit further includes: and the word slot query module is used for querying whether the word slot acquired from the dialogue system exists in the knowledge base. When the word slot is inquired, the word slot information is transmitted to the parameter association service system through the dialogue management module. After the association is completed, the dialogue management module transmits word slot information to the KB-Hub, the KB-Hub automatically completes the conversion from the word slot to the parameters of the knowledge base, and the converted parameters are transmitted to the knowledge base; when the knowledge base returns a certain parameter and a corresponding value, the KB-Hub automatically completes the conversion from the knowledge base parameter to the word slot, and transmits the converted word slot parameter to an algorithm submodule in the natural language generation module to generate a reply language.
In the present invention, as shown in fig. 5, the dialog system may include: the system comprises an input module, an intention identification module, a conversation management module, a natural language generation module and an output module. Wherein the content of the first and second substances,
the input module is used for receiving information input by a user.
The intention identification module is used for identifying the intention of the user for the information input by the user.
And the dialogue management module is used for managing dialogue states and the slot filling process and finishing the collection of information such as intentions, word slots and the like. Wherein the managing of the dialog state may include: jumping among different states under the skill, wherein the states are artificially defined; such as the first hit problem may be set to state 1, multiple problems hit simultaneously may be set to state 2, any problems not hit may be set to state 3, etc. The management of the slot filling process may include: and acquiring which word slots need to be filled with the current intention, which word slots are filled with the current intention, which word slots need to be filled with the current intention, and the like from the configuration table.
The natural language generation module is used for transmitting a calling request; and the answer generation module is used for receiving the query result and generating an answer dialog according to the query result. Further, the natural language generation module further comprises an algorithm sub-module, and the algorithm sub-module calculates the query result to generate a reply grammar.
And the output module is used for outputting the reply speech generated by the natural language generation module to the user.
In an optional embodiment, the parameter association service system further includes: and the parameter conversion judging module is used for determining whether parameter conversion is needed or not according to the judgment whether the content stored in the storage unit is empty or not and determining a sending object. Wherein the storage unit is a storage converted parameter configured for the intention in advance. Before sending information, namely before calling the associated mapping relation, namely before parameter conversion, according to the judgment whether the storage unit is empty, whether the parameter conversion is needed is determined, and whether a sending object is a dialogue system or a knowledge base is determined.
In an optional embodiment, the knowledge base further includes: and the third-party system calls the module, and the third-party system is used for providing other business services or other services such as knowledge inquiry and the like. Specifically, a third-party service interface parameter document can be configured in the knowledge base, and a third-party system is called through an interface form to perform services such as other business services or other knowledge queries.
Fig. 6 schematically shows a structural schematic diagram of an electronic device 1 according to the present invention, and as shown in fig. 6, the electronic device 1 provided by the present invention may be a terminal device such as a television, a smart phone, a tablet computer, a computer, and the like. The electronic device includes: the system comprises a memory 11, a processor 10 and a computer program, such as a parameter association service program 12, stored in the memory and operable on the processor, wherein the processor implements acquisition of configuration information of a dialog system, acquisition of information in a knowledge base, and association mapping between the configuration information and information in the knowledge base to obtain an association mapping relationship when executing the computer program; receiving a calling request sent by a dialog system, calling information associated with the calling request in a knowledge base according to the association mapping relation, and sending the information to the knowledge base so as to perform service inquiry through the knowledge base; and receiving the query result output by the knowledge base, calling the information associated with the query result according to the association mapping relation, and returning the information to the dialog system so as to generate a reply dialog through the dialog system.
Illustratively, a computer program may be partitioned into one or more modules/units, which are stored in a memory and executed by a processor to implement the present invention. One or more modules/units may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of a computer program in an electronic device. For example, the parameter association service program may be divided into an association mapping unit 100 and a calling service unit 200 in the parameter association service system. The functional role of which is described in detail above, is not repeated herein.
The steps of the parameter association service method of the present invention implemented when the processor executes the computer program are similar to the above, and are not detailed here, for example, the following steps are performed: acquiring configuration information of a dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation; receiving a calling request sent by a dialog system, calling information associated with the calling request in a knowledge base according to the association mapping relation, and sending the information to the knowledge base so as to perform service inquiry through the knowledge base; and receiving the query result output by the knowledge base, calling the information associated with the query result according to the association mapping relation, and returning the information to the dialog system so as to generate a reply dialog through the dialog system.
The Processor may be a Central Processing Unit (CPU), or may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory may be an external storage device of the electronic apparatus, such as a plug-in hard disk provided on the electronic apparatus, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory may also include both an internal storage unit and an external storage device of the electronic apparatus. The memory is used for storing computer programs and other programs and data required by the electronic device. The memory may also be used to temporarily store data that has been output or is to be output.
The computer-readable storage medium provided by the present invention stores a computer program thereon, and when the computer program is executed by a processor, the steps of the parameter association service method and the functions of each unit/module of the parameter association service system of the present invention are implemented, and are not described herein again to avoid repetition.
In an alternative embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program or instructions, where the program can be executed to implement corresponding functions via hardware in association with stored program instructions. For example, the computer readable storage medium may be a computer diskette, hard disk, random access memory, read only memory, or the like. The invention is not so limited and can be any means that stores the instructions or software and any associated data files or data structures in a non-transitory manner and that can be provided to a processor to cause the processor to execute the programs or instructions therein. The computer-readable storage medium comprises a parameter association service program, and when the parameter association service program is executed by a processor, the parameter association service program realizes the acquisition of configuration information of a dialog system, the acquisition of information in a knowledge base, and the association mapping of the configuration information and the information in the knowledge base to obtain an association mapping relation; receiving a calling request sent by a dialog system, calling information associated with the calling request in a knowledge base according to the association mapping relation, and sending the information to the knowledge base so as to perform service inquiry through the knowledge base; and receiving the query result output by the knowledge base, calling the information associated with the query result according to the association mapping relation, and returning the information to the dialog system so as to generate a reply dialog and other method steps through the dialog system.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A parameter association service method is applied to an electronic device, and is characterized in that the method comprises the following steps:
acquiring configuration information of a dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation; the dialogue system and the knowledge base are mutually independent systems, the configuration information of the dialogue system comprises intentions, word slot parameters and request parameters, knowledge services are stored in the knowledge base, the information in the knowledge base comprises knowledge service information and knowledge base parameter information, and the association mode in the association mapping relation comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many;
receiving a calling request sent by a dialog system, calling knowledge base information associated with the calling request from the associated mapping relation, and sending the knowledge base information to a knowledge base so as to perform service query through knowledge services in the knowledge base;
and receiving a query result output by the knowledge base, calling configuration information associated with the query result from the association mapping relation, and sending the configuration information to the dialogue system so as to generate a reply dialogue through the dialogue system.
2. The parameter association service method according to claim 1, wherein the step of obtaining configuration information of the dialog system, obtaining information in a knowledge base, and performing association mapping between the configuration information and the information in the knowledge base comprises:
acquiring an intention of a dialog system, acquiring knowledge service in a knowledge base, and mapping the intention to the knowledge service; wherein one intention is associated with one or more knowledge services, or a plurality of intents are associated with one knowledge service; when one intention is associated with a plurality of knowledge services, different scenes are configured according to the intention, and the intention association is mapped to different knowledge services according to different scenes.
3. The parameter association service method according to claim 2, wherein the step of obtaining configuration information of the dialog system, obtaining information in a knowledge base, and performing association mapping between the configuration information and the information in the knowledge base further comprises:
acquiring word slot parameters of a dialog system, acquiring knowledge base parameters, and mapping the word slot parameters and the knowledge base parameters; wherein, one word slot parameter is associated with different knowledge base parameters according to different intents.
4. The parameter association service method according to claim 2 or 3, wherein the step of obtaining the configuration information of the dialog system, obtaining the information in the knowledge base, and performing association mapping between the configuration information and the information in the knowledge base further comprises:
acquiring an intention request parameter of a dialog system, acquiring a knowledge base parameter, and mapping the intention request parameter and the knowledge base parameter; wherein, the answer corresponding to the intention request under different intentions is mapped to the same knowledge base parameter or is mapped to a plurality of different knowledge base parameters.
5. The parameter association service method of claim 1, wherein before the step of mapping the configuration information into association with information in a knowledge base, the method further comprises: and converting the form of the configuration information into a digital ID form.
6. The parameter association service method according to claim 1,
the step of calling the knowledge base information associated with the calling request from the association mapping relation and sending the knowledge base information to the knowledge base comprises the following steps: according to the association mapping relation, performing parameter conversion on the received call request, converting the call request into parameters corresponding to the knowledge base information associated with the call request, and sending the converted parameters to a knowledge base;
the step of calling the configuration information associated with the query result from the association mapping relationship and sending the configuration information to the dialog system includes: and according to the association mapping relation, performing parameter conversion on the received query result, converting the received query result into a parameter corresponding to the configuration information of the information associated with the query result, and returning the converted parameter to the dialog system.
7. The parameter association service method of claim 6, wherein the method further comprises:
when the acquired configuration information of the dialog system is an intention, configuring a storage unit for storing the converted parameters for the intention;
when the received information is an intention, judging whether the storage content in the storage unit corresponding to the intention is empty; determining whether parameter conversion is needed or not according to the judgment result, and determining an information sending object; if the intention is empty, converting parameters of the intention according to the association mapping relation, and transmitting the converted parameters to a knowledge base; and if not, directly transmitting the parameters in the storage unit corresponding to the intention to a knowledge base.
8. A parameter association service system, the system comprising:
the association mapping unit is used for acquiring configuration information of the dialog system, acquiring information in a knowledge base, and performing association mapping on the configuration information and the information in the knowledge base to obtain an association mapping relation; the dialogue system and the knowledge base are mutually independent systems, the configuration information of the dialogue system comprises intentions, word slot parameters and request parameters, knowledge services are stored in the knowledge base, the information in the knowledge base comprises knowledge service information and knowledge base parameter information, and the association mode in the association mapping relation comprises: one or more of one-to-one, one-to-many, many-to-one, and many-to-many;
the calling service unit is used for receiving a calling request sent by the dialog system, calling knowledge base information associated with the calling request from the associated mapping relation and sending the knowledge base information to a knowledge base so as to carry out service inquiry through knowledge services in the knowledge base; and the system is used for receiving the query result output by the knowledge base, calling the configuration information associated with the query result from the association mapping relation and sending the configuration information to the dialogue system so as to generate a reply language through the dialogue system.
9. An electronic device, the electronic device comprising: memory, processor and computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the parameter association service method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is included in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the parameter correlation service method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110480007.8A CN113076413B (en) | 2021-04-30 | 2021-04-30 | Parameter association service method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110480007.8A CN113076413B (en) | 2021-04-30 | 2021-04-30 | Parameter association service method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076413A true CN113076413A (en) | 2021-07-06 |
| CN113076413B CN113076413B (en) | 2023-12-26 |
Family
ID=76616120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110480007.8A Active CN113076413B (en) | 2021-04-30 | 2021-04-30 | Parameter association service method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076413B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
| CN111506719A (en) * | 2020-04-20 | 2020-08-07 | 深圳追一科技有限公司 | Associated question recommending method, device and equipment and readable storage medium |
| KR20200114920A (en) * | 2019-03-27 | 2020-10-07 | 한국과학기술원 | Conversation leading method and apparatus for knowledge learning dialog agent |
| US20200320407A1 (en) * | 2019-04-05 | 2020-10-08 | International Business Machines Corporation | Performing natural language based reasoning and automation by transforming a configuration management database to a knowledge base |
| WO2021047186A1 (en) * | 2019-09-09 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Method, apparatus, device, and storage medium for processing consultation dialogue |
-
2021
- 2021-04-30 CN CN202110480007.8A patent/CN113076413B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
| KR20200114920A (en) * | 2019-03-27 | 2020-10-07 | 한국과학기술원 | Conversation leading method and apparatus for knowledge learning dialog agent |
| US20200320407A1 (en) * | 2019-04-05 | 2020-10-08 | International Business Machines Corporation | Performing natural language based reasoning and automation by transforming a configuration management database to a knowledge base |
| WO2021047186A1 (en) * | 2019-09-09 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Method, apparatus, device, and storage medium for processing consultation dialogue |
| CN111506719A (en) * | 2020-04-20 | 2020-08-07 | 深圳追一科技有限公司 | Associated question recommending method, device and equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113076413B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103377652B (en) | A kind of method, device and equipment for carrying out speech recognition | |
| US11934394B2 (en) | Data query method supporting natural language, open platform, and user terminal | |
| CN109636582B (en) | Credit information management method, apparatus, device and storage medium | |
| CN112182174A (en) | Business question-answer knowledge query method and device, computer equipment and storage medium | |
| CN113626223A (en) | Interface calling method and device | |
| CN111382252B (en) | Method, device, equipment and medium for determining problem category based on user request | |
| CN110674205B (en) | Single table query method, device, terminal and readable storage medium | |
| CN113626512A (en) | Data processing method, device, equipment and readable storage medium | |
| CN106485520B (en) | Cross-channel communication control method and server | |
| CN114416049A (en) | Configuration method and device of service interface combining RPA and AI | |
| CN111368549A (en) | Natural language processing method, device and system supporting multiple services | |
| CN103379022B (en) | A kind of instant communication method based on Internet map search and system | |
| CN111914073A (en) | Customer service response method, device, equipment and storage medium | |
| CN113761016A (en) | Data query method, device, equipment and storage medium | |
| CN108959294A (en) | A kind of method and apparatus accessing search engine | |
| CN111538672A (en) | Test case layered test method, computer device and computer-readable storage medium | |
| CN113076413B (en) | Parameter association service method, system, device and storage medium | |
| CN111045928A (en) | Interface data testing method, device, terminal and storage medium | |
| CN110471708B (en) | Method and device for acquiring configuration items based on reusable components | |
| CN110737662B (en) | Data analysis method, device, server and computer storage medium | |
| CN114493799A (en) | Method and system for managing special vehicle order data in warehouse and table dividing manner | |
| CN113709187A (en) | Multi-server data request method, device, equipment and storage medium | |
| CN113342845A (en) | Data synchronization method, computer device and readable storage medium | |
| CN111708828A (en) | Tagged data management method, device, equipment and computer readable storage medium | |
| CN112445811A (en) | Data service method, device, storage medium and component based on SQL configuration |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |