CN116401346A - Task type multi-round dialogue construction method, equipment and computer readable storage medium - Google Patents
Task type multi-round dialogue construction method, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN116401346A CN116401346A CN202310219903.8A CN202310219903A CN116401346A CN 116401346 A CN116401346 A CN 116401346A CN 202310219903 A CN202310219903 A CN 202310219903A CN 116401346 A CN116401346 A CN 116401346A
- Authority
- CN
- China
- Prior art keywords
- dialogue
- intention
- dialog
- round
- type multi
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000001960 triggered effect Effects 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 11
- 238000005352 clarification Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 29
- 230000006870 function Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a task type multi-round dialogue construction method, equipment and a computer readable storage medium, wherein the method comprises the following steps: through intention management, task type dialogue intention to be triggered in dialogue can be configured; in the intention management step, the configuration of the dialog intention specifically includes: the word slot setting is used for defining each slot position information and the range of extraction content which need to be extracted in the dialogue, and realizing the information which needs to be filled for the intention of the dialogue; trigger setting, wherein the trigger setting is used for defining conditions for triggering dialogue intention; and the reply setting is used for setting the condition for completing the dialogue and the reply result, and the condition for triggering the final reply can be configured according to the word slot condition. The task type multi-round dialogue construction method, the device and the computer readable storage medium provided by the invention meet dialogue interaction requirements of various practical application scenes.
Description
Technical Field
The present invention relates to the field of session configuration technology, and in particular, to a task type multi-round session construction method, apparatus, and computer readable storage medium.
Background
The description of the background art to which the present invention pertains is merely for illustrating and facilitating understanding of the summary of the invention, and should not be construed as an explicit recognition or presumption by the applicant that the applicant regards the prior art as the filing date of the first filed application.
The existing task type multi-round dialogue construction methods generally have three types: firstly, a conversation process is constructed through detailed configuration and debugging of a plurality of links and steps such as intention, word slots, dictionary and the like, the details required to be configured in common products are more, and the operation process is more complicated; secondly, a dialogue is built through configuration operations such as dragging and the like on a canvas, and although the whole interface is more visual, a certain learning cost exists; thirdly, through the written configuration file, the operation is effective based on fixed code logic, the operation cost is high, and the conversation flow which can be realized is fixed, so that the flexible adjustment of combining scenes is inconvenient. The existing task type multi-round dialogue construction method is realized through complex configuration operation of a product function layer or through background code layer development, has relatively high operation cost, and is difficult to flexibly combine with other types of question-answering or dialogue capability. In addition, the multi-round conversations constructed by the above three types of methods are generally independent conversational capabilities, relatively isolated from other types of conversational capabilities or skills, and thus relatively closed.
In order to solve the technical problems, the invention provides a task type multi-round dialogue construction method, equipment and a computer readable storage medium, which can realize the construction of task type multi-round dialogue through a simpler operation flow, can realize the combination application of the question-answering capability with FAQ, knowledge graph question-answering and the like, and can meet the dialogue interaction requirements of various practical application scenes.
Disclosure of Invention
The invention provides a task type multi-round dialogue construction method, equipment and a computer readable storage medium, which can realize the construction of task type multi-round dialogue through a simpler operation flow, can realize the combination application of the question-answer capability with FAQ, knowledge graph question-answer and the like, and can meet the dialogue interaction requirements of various practical application scenes.
The embodiment of the first aspect of the invention provides a task type multi-round dialogue construction method, which comprises the following steps: through intention management, task type dialogue intention to be triggered in dialogue can be configured; through intention management, the configuration of the dialog intention in the task dialog intention step needing to be triggered in the dialog specifically comprises the following steps: the word slot setting is used for defining each slot position information and the range of extraction content which need to be extracted in the dialogue, and realizing the information which needs to be filled for the intention of the dialogue; trigger setting, wherein the trigger setting is used for defining conditions for triggering dialogue intention; and the reply setting is used for setting the condition for completing the dialogue and the reply result, and the condition for triggering the final reply can be configured according to the word slot condition.
Preferably, the word slot setting step specifically includes defining, one by one, related word slot information involved in the dialog intention; word slot information includes the name of the word slot, the associated dictionary, whether the dictionary value is presented as an option, whether the word slot must be filled, the maximum number of clarification rounds and the speaking, and the clarification order when multiple word slots are missing at the same time.
Preferably, in the trigger setting step, trigger dialogs can be added singly or imported in batches, word slot information can be inserted when the trigger dialogs are added singly, and setting precision or fuzzy matching is supported.
Preferably, in the reply setting step, the reply type may select a reply session or perform a call as required, where the reply session is used to give a unified session to a terminating session; executing the call for word slot filling influences the condition of returning the result, the api interface information to be called can be filled in the input box, so that interfaces for calling other types of dialogue capability replies are configured.
Preferably, the method further comprises: dictionary management, which may add custom dictionaries for supporting word slot related information in intent management.
Preferably, the method further comprises: rule management, which serves word slot extraction in intention recognition, is preset with extraction rules.
Preferably, the extraction rule comprises a mailbox, an identity card, a mobile phone number, a date and a related rule type in a fixed phone preset by the system, and the custom addition rule is supported.
Preferably, in the intention management step, a plurality of dialog intention to be realized can be added and managed, each intention is a dialog target with definite trigger condition and flow, and the intention completes tasks through multiple rounds of dialog; priorities may be configured between intents, which are sequentially executed when a user's question hits multiple intents at the same time.
Embodiments of the second aspect of the present invention also provide a task-type multi-round dialog construction device comprising a memory and a processor; wherein the memory is for storing executable program code; the processor is configured to read executable program code stored in the memory to perform the task-style multi-round dialog construction method.
An embodiment of the third aspect of the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements a task-type multi-round dialog construction method.
The task type multi-round dialogue construction method, the task type multi-round dialogue construction equipment and the computer readable storage medium can realize the construction of task type multi-round dialogue through a simpler operation flow, can realize the combined application of the question-answer capabilities of FAQ, knowledge graph question-answer and the like, and can meet the dialogue interaction requirements of various practical application scenes.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 shows a flow chart of a task-based multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 2 shows a dialog execution flow diagram of a task-type multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of an intent management interface in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 4 illustrates an add intent interface diagram in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of an edit word slot interface in a task-based multi-round dialog construction method according to an embodiment of the present invention;
FIG. 6 is a diagram of a word slot setup interface in a task-based multi-round dialog construction method according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a trigger setting interface in a task-based multi-round dialog construction method according to an embodiment of the invention;
FIG. 8 is a diagram showing a reply setup interface in a task-based multi-round dialog construction method according to an embodiment of the present invention;
FIG. 9 is a diagram of a dictionary management interface in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 10 is a schematic diagram of a rule management interface in a task-based multi-round dialog construction method according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of an add rule interface in a task-based multi-round dialog construction method according to an embodiment of the present invention;
FIG. 12 is a block diagram of one embodiment of the task-style multi-round dialog construction device of the present specification;
fig. 13 is a block diagram of one embodiment of a computer-readable storage medium of the task-oriented multi-round dialog construction method of the present specification.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
The following discussion provides various embodiments of the invention. While each embodiment represents a single combination of the invention, different embodiments of the invention may be substituted or combined, and the invention is thus to be considered to include all possible combinations of the same and/or different embodiments described. Thus, if one embodiment comprises A, B, C and another embodiment comprises a combination of B and D, then the present invention should also be considered to include embodiments comprising one or more of all other possible combinations comprising A, B, C, D, although such an embodiment may not be explicitly recited in the following.
FIG. 1 shows a flow chart of a task-based multi-round dialog construction method in accordance with an embodiment of the present invention; FIG. 2 shows a dialog execution flow diagram of a task-type multi-round dialog construction method in accordance with an embodiment of the present invention; FIG. 3 is a schematic diagram of an intent management interface in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention;
FIG. 4 illustrates an add intent interface diagram in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention; FIG. 5 is a schematic diagram of an edit word slot interface in a task-based multi-round dialog construction method according to an embodiment of the present invention; FIG. 6 is a diagram of a word slot setup interface in a task-based multi-round dialog construction method according to an embodiment of the present invention; FIG. 7 is a schematic diagram of a trigger setting interface in a task-based multi-round dialog construction method according to an embodiment of the invention; fig. 8 is a schematic diagram of a reply setup interface in a task-type multi-round dialog construction method according to an embodiment of the present invention. As shown in fig. 1 to 8, the task-type multi-round dialog construction method includes the steps of: step S01, adding intention, and configuring task type dialogue intention to be triggered in dialogue through intention management; step S02, setting word slots, wherein the word slot settings are used for defining the range of each slot position information and extraction content required to be extracted in the dialogue and realizing the information required to be filled for the intention of the dialogue; step S03, setting triggering conditions, triggering settings, wherein the triggering settings are used for defining conditions for triggering dialogue intents; step S04, setting reply conditions and contents, replying settings, wherein the reply settings are used for setting conditions for completing the dialogue and reply results, and the conditions for triggering final reply can be configured according to word slot conditions; step S05, completing the intention setting. The dialogue execution flow of the task type multi-round dialogue construction method is as follows: step T01, acquiring a question text input by a user; step T02, identifying dialogue intents meeting the triggering conditions; step T03, confirming word slots contained in the intention one by one, and extracting slot position information in a user text; and step T04, when judging that the trigger condition of the reply setting is met, calling the set reply content to output, and completing the multi-round dialogue.
As shown in fig. 1-8, task-type dialog intents to be triggered in a dialog can be configured through intent management. In a conversation robot instance, a plurality of conversation intents to be realized can be added and managed, one intention can be regarded as a conversation target with definite trigger conditions and flow, and the conversation intention is a task which can be completed through multiple conversations. Priorities may be configured between intents, which are sequentially executed when a user's question hits multiple intents at the same time. In the 'intention management', clicking an 'add intention' button, filling in an English name and a Chinese name of intention, and adding a plurality of rounds of dialogue intention to be realized to a list; clicking on the "view" button of the row corresponding to the added intent may enter a specific setting of that intent. One intended configuration is to go through three steps of "word slot setting", "trigger setting" and "reply setting".
As shown in fig. 1-8, in the word slot arrangement, the related word slot information related to the dialog intention needs to be defined one by one, including the names of the word slots, the related dictionary, whether the dictionary values are displayed as options, whether the word slots have to be filled, the maximum number of clarification rounds and the speaking, and the clarification order when a plurality of word slots are simultaneously deleted. This link can be regarded as the core of a task-type multi-round dialogue configuration, and through the arrangement of word slots, the scope of each slot information and extracted content which need to be extracted in the dialogue is defined, so as to realize the information which needs to be filled in the dialogue intention. For example, if the dialogue task of "booking" is completed through a slot-filled multi-round dialogue, it is necessary to provide basic slot information such as departure place, destination, departure date, etc. for obtaining a corresponding return result.
1-8, the specific arrangement of word slots is edited in the right popup window by clicking the word slot; english names and Chinese names of word slots need to be added; selecting a dictionary or rule to be referenced for the word slot, and extracting a value capable of filling the word slot from text input by a user (the content of the referenceable dictionary comes from dictionary management, and the priority of the referenceable dictionary in the process of configuring the multi-turn dialogue capability can be considered to enter the dictionary management for the customization of the required dictionary; when the dictionary type is a custom dictionary, the word slot can be triggered in the dialogue by setting whether the dictionary value is displayed as an option or not to select yes, and the corresponding dictionary value is displayed above the input box for clicking, so that the user can more conveniently respond, and the dialogue flow is ensured to be controllable; if the word groove is necessary to be filled, if so, the dialogue process is repeated with the user to confirm the word groove according to the maximum clarification round number set below, namely, the clarification is set by the adding button below. In the process of confirming word slots one by one and responding to the conversation, if the responding content meets the condition (such as FAQ question and answer) for triggering other conversational capabilities, the method can also realize the combined application of the multi-round conversational capabilities and other capabilities, and conveniently meet the requirements of specific scenes.
1-8, after a plurality of word slots exist in the word slot list of the outer layer, the "move up" or "move down" can be clicked to set the sequential clarification order when the plurality of word slots are absent. After the word slot setting is completed, clicking the next step at the lower right corner can save the setting about the word slot and enter the trigger setting. The trigger setting is used for defining the condition for triggering the dialogue intention, the trigger ticket operation can be added singly or imported in batches, word slot information can be inserted when the trigger ticket operation is added singly, and setting precision or fuzzy matching is supported. In trigger settings, batch or single add-on may be selected as the speaking of the intended trigger condition; if batch uploading is selected as a trigger condition, clicking a downloading template, and uploading after filling with a reference template; if a single addition is selected, the word slots which are configured in the word slot setting can be selected and inserted for triggering the situation that a word slot possibly exists in the speaking operation; a single add can add up to 20 utterances or less, so the manner of addition can be selected according to the number of utterances to be added. Clicking the next step after finishing to enter a reply setting for setting the condition of finishing the dialogue and the reply result, and configuring the condition for triggering the final reply according to the word slot condition. The reply type can select "reply phone" or "execute call" as required, and "reply phone" is used for giving unified phone and terminal dialogue (e.g. questionnaire feedback, etc. scene of collecting information) no matter what the word slot filling content is; the 'execution call' is used for directly influencing the condition of the word slot filling content to return results, api interface information to be called can be filled in an input box, and by means of the function, interfaces for calling replies of other types of dialogue capabilities, such as related interfaces of map question-answering, can be configured for outputting corresponding results according to the condition of filling slots, so that fusion application with other dialogue capabilities can be realized.
As shown in fig. 1-8, the trigger conditions are configured according to the situation that the word slots are filled, where the existing word slots and the states that need to be satisfied can be selected; typically only the selection of word slots to complete the filling is involved, and special condition settings are provided such as "include", "do not include", "equal" and "do not equal"; if the filling of each word slot is completed in the dialogue, but the set reply triggering condition is not met, a' condition is not met, the conversation is preset, and the conversation can be modified as required. Clicking the 'save' of the lower right corner after finishing setting, finishing the save of the whole setting of the intention, and returning to the intention list; if some of the settings are incomplete or unsatisfactory, an error prompt is given, and the settings can be modified accordingly; after returning to the intention list, the configuration state of the intention is 'completed', and the intention takes effect after clicking an 'enable' button, so that the task type multi-round dialogue can be applied in the dialogue system.
FIG. 9 is a diagram of a dictionary management interface in a task-based multi-round dialog construction method in accordance with an embodiment of the present invention; FIG. 10 is a schematic diagram of a rule management interface in a task-based multi-round dialog construction method according to an embodiment of the present invention; fig. 11 is a schematic diagram illustrating an add rule interface in a task-type multi-round dialog construction method according to an embodiment of the present invention. As shown in fig. 9-11, the method further comprises: dictionary management, which can add custom dictionary for supporting word slot related information in intention management; rule management, wherein the rule management serves for word slot extraction in intention recognition, and extraction rules are preset in the rule management; the extraction rule comprises a plurality of rule types including a mailbox, an identity card, a mobile phone number, a date and a fixed phone preset by the system, and the rule can be added in a self-defined mode. The method combines three parts of 'intention management', 'dictionary management', 'rule management' to realize the configuration of task type multi-round dialogue, wherein only the intention management is a necessary configuration link, and the dictionary management and the rule management are configured and used according to the need.
As shown in fig. 9-11, in "dictionary management", a custom dictionary may be added for supporting word slot related information in "intention management". The system presets a part of available system dictionary, and the user can add the custom dictionary according to the need; clicking the "add dictionary" button, editing dictionary names and dictionary values in the window developed on the right, the dictionary values supporting the addition of synonyms. After the custom dictionary is added, the user-defined dictionary can be selected and used in word slots of intention management. The rule management is used for extracting word slots in intention recognition, wherein some common extraction rules, such as common rule types of a mailbox, an identity card, a mobile phone number, a date, a fixed phone and the like, are preset, references can be set in the word slots, and corresponding information contained in the text of a user is recognized; the user can also add rules by himself, and the requirements of specific scenes can be met by editing regular expressions conforming to the python grammar to define the rules required for extracting word slot values.
The task type multi-round dialogue construction method provided by the embodiment of the invention is relatively simplified, and is convenient for completing multi-round dialogue configuration more quickly; meanwhile, the method of the invention can break through the configuration bottleneck of the task type multi-round dialogue, and can be used for fusing configuration and application with other types of dialogue capability. The configuration of the slot filling type task type multi-wheel dialogue is realized by a simple and easy-to-use method, the task type multi-wheel dialogue intention can be rapidly configured, and the operation flow is simpler; the priority can be flexibly adjusted between a plurality of intents and a plurality of word slots in one intention; the reply sets up the trigger condition that can be configured freely, and support and call the result of the external interface and return as the result; the extraction rule to be applied for the word slots can be customized, and the basic regular grammar can be satisfied; the configuration flow in the intention has more definite sequence guidance, so that the usability is enhanced, and meanwhile, the configuration can be prevented from being wrong or missing through verification.
Those skilled in the art will appreciate that adding relevant setup links or configuration conditions beyond the methods provided in the present embodiment is useful in supporting more complex dialog settings; or may simplify the configuration content contained in the solution, such as reducing the number of session configuration methods that the trigger settings can support, or reducing the trigger conditions or types of replies allowed by the reply settings. In the dialog system of the current application provided by the embodiment of the method, the same robot instance can be simultaneously configured with a plurality of task type multi-round dialog capability instances, namely, a plurality of task type dialog capability scenes can be flexibly configured on one robot by the stated method, so that the requirement of various dialog scenes can be met conveniently.
The specification also provides a task type multi-round dialogue constructing device, which comprises: the intention management module can configure task type dialogue intention to be triggered in dialogue through intention management; the intention management module specifically comprises: the word slot setting module is used for defining each slot position information and the range of extraction content which need to be extracted in the dialogue and realizing the information which needs to be filled for the intention of the dialogue; the trigger setting module is used for defining conditions for triggering the dialogue intention; and the reply setting module is used for setting the condition of conversation completion and the reply result, and can configure the condition for triggering final reply according to the word slot condition.
FIG. 12 is a block diagram of one embodiment of the task-style multi-round dialog construction device of the present specification; referring now to fig. 12, a schematic diagram of a task-type multi-round dialog construction device 300 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 12 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 12, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.
In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 12 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.
FIG. 13 is a block diagram of one embodiment of a computer-readable storage medium of the task-oriented multi-round dialog construction method of the present specification; as shown in fig. 13, a computer-readable storage medium 40 according to an embodiment of the present disclosure has stored thereon non-transitory computer-readable instructions 41. When the non-transitory computer readable instructions 41 are executed by the processor, all or part of the steps of the task-type multi-round dialog construction method of the various embodiments of the disclosure described previously are performed.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: constructing a basic page, wherein the page code of the basic page is used for constructing an environment required by the operation of the service page and/or realizing the same abstract workflow in the similar service scene; constructing one or more page templates, wherein the page templates are used for providing code templates for realizing service functions in service scenes; based on the corresponding page template, generating a final page code of each page of the service scene through code conversion of a specific function of each page of the service scene; and merging the generated final page code of each page into the page code of the basic page to generate the code of the service page.
Alternatively, the computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: constructing a basic page, wherein the page code of the basic page is used for constructing an environment required by the operation of the service page and/or realizing the same abstract workflow in the similar service scene; constructing one or more page templates, wherein the page templates are used for providing code templates for realizing service functions in service scenes; based on the corresponding page template, generating a final page code of each page of the service scene through code conversion of a specific function of each page of the service scene; and merging the generated final page code of each page into the page code of the basic page to generate the code of the service page.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The name of the unit does not in any way constitute a limitation of the unit itself, for example the first acquisition unit may also be described as "unit acquiring at least two internet protocol addresses".
The task type multi-round dialogue construction method, the device, the equipment and the computer readable storage medium can realize the construction of task type multi-round dialogue through a simpler operation flow, can realize the combined application of the question-answer capabilities of FAQ, knowledge graph question-answer and the like, and can meet the dialogue interaction requirements of various practical application scenes.
In the present invention, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; the term "plurality" means two or more, unless expressly defined otherwise. The terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; "coupled" may be directly coupled or indirectly coupled through intermediaries. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the description of the present invention, it should be understood that the directions or positional relationships indicated by the terms "upper", "lower", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of description and simplification of the description, and do not indicate or imply that the apparatus or unit referred to must have a specific direction, be constructed and operated in a specific direction, and therefore, should not be construed as limiting the present invention.
In the description of the present specification, the terms "one embodiment," "some embodiments," "particular embodiments," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative of certain embodiments of the present invention and is not intended to limit the invention so that various modifications and changes may be made to the invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The task type multi-round dialogue construction method is characterized by comprising the following steps of:
through intention management, task type dialogue intention to be triggered in dialogue can be configured;
the configuration of the dialog intention in the task-type dialog intention step to be triggered in the dialog through intention management specifically comprises the following steps:
the word slot setting is used for defining the range of each slot position information and extraction content which need to be extracted in the dialogue and realizing the information which needs to be filled in the dialogue intention;
trigger settings for defining conditions for triggering the dialog intention;
and the reply setting is used for setting the condition for completing the dialogue and the reply result, and the condition for triggering the final reply can be configured according to the word slot condition.
2. The task type multi-round dialog construction method of claim 1, wherein the word slot setting step specifically includes defining the related word slot information involved in the dialog intention one by one; the word slot information includes the name of the word slot, the associated dictionary, whether the dictionary value is presented as an option, whether the word slot must be filled, the maximum number of clarification rounds and the speaking, and the clarification order when multiple word slots are missing simultaneously.
3. The task type multi-round dialogue constructing method according to claim 1, wherein in the trigger setting step, a trigger dialogue can be added singly or imported in batches, word slot information can be inserted when single adding, and setting precision or fuzzy matching is supported.
4. The task type multi-round dialogue constructing method according to claim 1, wherein in the reply setting step, a reply type can be selected or called as required, and the reply type is used for giving a unified dialogue and a terminal dialogue; and the executing call is used for the condition that word slot filling content influences the returned result, and api interface information to be called can be filled in an input box so as to configure an interface for calling other types of dialogue capability replies.
5. The task type multi-round dialog construction method of claim 1, wherein the method further comprises:
dictionary management, which may add custom dictionaries, for supporting word slot related information in the intent management.
6. The task type multi-round dialog construction method of claim 1, wherein the method further comprises:
rule management serving word slot extraction in intent recognition, the rule management being preset with extraction rules.
7. The method for constructing task type multi-turn conversations according to claim 6, wherein the extraction rules include preset mailbox, id card, phone number, date, and rule types in fixed phone, and support custom addition rules.
8. The task type multi-turn dialog construction method according to any one of claims 1 to 7, wherein in the intention management step, a plurality of dialog intents to be implemented, each of which is a dialog target with a clear trigger condition and flow, can be added and managed, and the intents complete tasks through multiple rounds of dialog; priorities may be configured between intents, which are sequentially executed when a user's question hits multiple intents at the same time.
9. A task-type multi-round dialog construction device comprising a memory and a processor; wherein the memory is for storing executable program code; the processor is configured to read executable program code stored in the memory to perform the task type multi-round dialog construction method according to any of claims 1-8.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the task-oriented multi-round dialog construction method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310219903.8A CN116401346A (en) | 2023-03-09 | 2023-03-09 | Task type multi-round dialogue construction method, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310219903.8A CN116401346A (en) | 2023-03-09 | 2023-03-09 | Task type multi-round dialogue construction method, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116401346A true CN116401346A (en) | 2023-07-07 |
Family
ID=87011435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310219903.8A Pending CN116401346A (en) | 2023-03-09 | 2023-03-09 | Task type multi-round dialogue construction method, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116401346A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182171A (en) * | 2020-09-18 | 2021-01-05 | 国网湖南省电力有限公司 | Method and device for constructing operation assistant based on human-computer conversation dispatching robot |
| CN114036268A (en) * | 2021-10-13 | 2022-02-11 | 上海交通大学 | Task type multi-turn dialogue method and system based on intention gate |
| CN115146047A (en) * | 2022-07-20 | 2022-10-04 | 阿里巴巴（中国）有限公司 | Information processing method, apparatus, storage medium, and program product |
| CN115525753A (en) * | 2022-10-26 | 2022-12-27 | 上海交通大学 | Task-oriented multi-turn dialogue method and system based on 1+ N |
| US20230017449A1 (en) * | 2021-09-29 | 2023-01-19 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus for processing natural language text, device and storage medium |
-
2023
- 2023-03-09 CN CN202310219903.8A patent/CN116401346A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182171A (en) * | 2020-09-18 | 2021-01-05 | 国网湖南省电力有限公司 | Method and device for constructing operation assistant based on human-computer conversation dispatching robot |
| US20230017449A1 (en) * | 2021-09-29 | 2023-01-19 | Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd. | Method and apparatus for processing natural language text, device and storage medium |
| CN114036268A (en) * | 2021-10-13 | 2022-02-11 | 上海交通大学 | Task type multi-turn dialogue method and system based on intention gate |
| CN115146047A (en) * | 2022-07-20 | 2022-10-04 | 阿里巴巴（中国）有限公司 | Information processing method, apparatus, storage medium, and program product |
| CN115525753A (en) * | 2022-10-26 | 2022-12-27 | 上海交通大学 | Task-oriented multi-turn dialogue method and system based on 1+ N |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11188298B2 (en) | Electronic device and method for generating short cut of quick command | |
| US10452251B2 (en) | Transactional conversation-based computing system | |
| US20200225839A1 (en) | Natural language task completion platform authoring for third party experiences | |
| CN109545205B (en) | Context-based virtual assistant implementation | |
| US11468881B2 (en) | Method and system for semantic intelligent task learning and adaptive execution | |
| CN107733722B (en) | Method and apparatus for configuring voice service | |
| CN109992338B (en) | Method and system for exposing virtual assistant services across multiple platforms | |
| CN109313668B (en) | System and method for constructing session understanding system | |
| CN111143523B (en) | Intention confirming method and device | |
| CN110727869A (en) | Page construction method and device | |
| CN110837334B (en) | Method, device, terminal and storage medium for interactive control | |
| CN109814915B (en) | Parameter configuration method, device, medium and electronic equipment based on lua | |
| CN116401346A (en) | Task type multi-round dialogue construction method, equipment and computer readable storage medium | |
| US20180190287A1 (en) | Selection system and method | |
| CN111666068B (en) | Platform development framework, construction method, equipment and medium | |
| CN111782992B (en) | Display control method, device, equipment and readable storage medium | |
| CN114168251A (en) | Language switching method, device, equipment, computer readable storage medium and product | |
| CN111314209B (en) | Message sending method, device, terminal and storage medium | |
| CN114580361A (en) | Document processing method and device, electronic equipment and storage medium | |
| CN113260979A (en) | Stack-based communication system and method | |
| CN111858864A (en) | Method and device for realizing slot filling, electronic equipment and readable medium | |
| CN114661397B (en) | Download management method, device, electronic equipment and storage medium | |
| CN118296122A (en) | Message processing method, device, equipment and medium | |
| US20240211161A1 (en) | Data processing method and apparatus, electronic device, storage medium, and program product | |
| CN116795339A (en) | Service interface generation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230707 |