CN111414467A - Question-answer dialogue method and device, electronic equipment and computer readable storage medium - Google Patents
Question-answer dialogue method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111414467A CN111414467A CN202010203765.0A CN202010203765A CN111414467A CN 111414467 A CN111414467 A CN 111414467A CN 202010203765 A CN202010203765 A CN 202010203765A CN 111414467 A CN111414467 A CN 111414467A
- Authority
- CN
- China
- Prior art keywords
- question
- target
- intention
- user
- entity
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006870 function Effects 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004904 shortening Methods 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a question-answer dialogue method, a question-answer dialogue device, electronic equipment and a computer-readable storage medium, which are applied to the technical field of computers, wherein the method comprises the following steps: the method comprises the steps of obtaining a target question of a user, carrying out intention identification on the basis of the target question of the user to obtain an intention identification result, carrying out entity identification on the basis of the target question of the user to obtain an entity identification result, determining a target standard question on the basis of the intention identification result and the entity identification result, and feeding back an answer of the target standard question to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a question and answer dialog method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
Compared with the traditional manual customer service, the intelligent question and answer customer service has the advantages of greatly improving the customer service efficiency, shortening the waiting time of users, providing professional customer service for 7x24 hours and the like, and is popular with the majority of service providers.
At present, intelligent question answering mainly depends on a knowledge base imported in the early stage, then the distance between a question and a standard question stored in the knowledge base is calculated by using a similarity algorithm, and finally a standard answer corresponding to the standard question is fed back. However, the prior art has the problem of low accuracy in determining the standard.
Disclosure of Invention
The application provides a question-answer dialogue method, a question-answer dialogue device, electronic equipment and a computer-readable storage medium, which are used for improving accuracy of answer providing, and the technical scheme adopted by the application is as follows:
in a first aspect, a question-answer dialog method is provided, which includes,
acquiring a target problem of a user;
performing intention recognition based on a target question of a user to obtain an intention recognition result;
carrying out entity identification based on a target problem of a user to obtain an entity identification result;
and determining a target standard question based on the intention recognition result and the entity recognition result, and feeding back an answer of the target standard question to the user.
Optionally, the intention recognition result includes explicit intention, ambiguous intention, and no intention, and the entity recognition result includes existence of entity and entity information.
Optionally, if the intention recognition result is an explicit intention, the entity recognition result is an entity, and the target criterion is determined based on the intention recognition result and the entity recognition result, including:
and determining a target standard question from a plurality of candidate standard questions based on the clear intention of the intention recognition result and the entity of the entity recognition result, and feeding back the answer of the target standard question to the user.
Optionally, if the intention recognition result is an ambiguous intention, the entity recognition result is an entity, the method further comprises:
prompting the user for the obscured intent;
based on the user's intent selection, the user's explicit intent of the target question is determined.
Optionally, if the intention identification result is no intention, the entity identification result is an entity, and the method further comprises:
prompting at least one potential intention corresponding to the entity of the entity recognition result to a user;
based on the user's intent selection, the user's explicit intent of the target question is determined.
Optionally, the target question is a text question, and performing intent recognition based on the target question of the user to obtain an intent recognition result, including:
determining a text vector of the text target question based on the text target question;
the intention recognition result is determined by a pre-trained softmax model based on the text vector of the target question.
Optionally, the target question is a voice question, and performing intent recognition based on the target question of the user to obtain an intent recognition result, including:
carrying out voice recognition on the voice target problem to obtain a text of the voice target problem;
determining a text vector of the voice target question based on the text of the voice target question;
and obtaining an intention recognition result through a pre-trained softmax model based on the text vector of the voice target problem.
In a second aspect, there is provided a question-answering conversation apparatus, comprising,
the acquisition module is used for acquiring a target problem of a user;
the intention identification module is used for carrying out intention identification on the basis of a target problem of a user to obtain an intention identification result;
the entity identification module is used for carrying out entity identification based on the target problem of the user to obtain an entity identification result;
and the first determining module is used for determining a target standard question based on the intention recognition result and the entity recognition result and feeding back an answer of the target standard question to the user.
Optionally, the intention recognition result includes explicit intention, ambiguous intention, and no intention, and the entity recognition result includes existence of entity and entity information.
Optionally, if the intention recognition result is an explicit intention and the entity recognition result is an entity, the intention recognition module is specifically configured to determine a target standard question from the plurality of candidate standard questions based on the explicit intention of the intention recognition result and the entity of the entity recognition result, and feed back an answer to the target standard question to the user.
Optionally, if the intention recognition result is an ambiguous intention, the entity recognition result is an entity, the apparatus further comprises:
the first prompting module is used for prompting the fuzzy intention to a user;
and the second determination module is used for determining the clear intention of the target question of the user based on the intention selection of the user.
Optionally, if the intention recognition result is no intention, the entity recognition result is an entity, and the apparatus further includes:
the second prompting module is used for prompting at least one potential intention corresponding to the entity of the entity recognition result to the user;
and the third determination module is used for determining the clear intention of the target problem of the user based on the intention selection of the user.
Optionally, the target question is a text question, and the intention identification module comprises:
a first determination unit, configured to determine a text vector of the text target question based on the text target question;
a second determination unit for determining an intention recognition result through a pre-trained softmax model based on the text vector of the target question.
Optionally, the target problem is a speech problem, and the intention recognition module comprises:
the recognition unit is used for carrying out voice recognition on the voice target problem to obtain a text of the voice target problem;
a third determination unit for determining a text vector of the voice target question based on the text of the voice target question;
a fourth determination unit for determining an intention recognition result through a pre-trained softmax model based on the text vector of the speech target problem.
In a third aspect, an electronic device is provided, which includes:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the question-answer dialog method shown in the first aspect is performed.
In a fourth aspect, a computer-readable storage medium is provided, which is used for storing computer instructions, which when run on a computer, make the computer execute the question-answering dialogue method shown in the first aspect.
Compared with the prior art that a target standard question is determined based on the similarity between a question of a user and a standard question and an answer of the target standard question is fed back to the user, the question answering method, the question answering device, the electronic equipment and the computer-readable storage medium have the advantages that the target standard question is determined based on the similarity between the question of the user and the standard question, the intention identification result is obtained by acquiring the target question of the user, the entity identification result is obtained by performing intention identification based on the target question of the user, the target standard question is determined based on the intention identification result and the entity identification result, and the answer of the target standard question is fed back to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a question-answering conversation method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a question-answering conversation apparatus according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of another question answering session device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The embodiment of the application provides a question-answer dialog method, as shown in fig. 1, the method may include the following steps:
step S101, acquiring a target problem of a user;
specifically, a target question of the user is obtained, where the target question may be a text question input by the user (for example, the user may input question information in a corresponding dialog box), or a voice question made by the user through voice.
Step S102, performing intention identification based on a target question of a user to obtain an intention identification result;
specifically, the type of the target problem (text problem, voice problem) may be determined first, and then the corresponding intention recognition method is selected and applied based on the determined type of the target problem to perform intention recognition, wherein if the target problem is a voice problem, the target problem may be converted into text first and then intention recognition is performed, or the corresponding intention may be recognized directly according to the voice.
Step S103, carrying out entity identification based on the target problem of the user to obtain an entity identification result;
specifically, if the target problem is a text problem, the problem may be directly subjected to word segmentation processing to obtain a word segmentation list, and then the word segmentation list is compared with a pre-stored entity set to identify a corresponding entity. If the voice problem is detected, the voice problem can be converted into a text, and then the text is compared with a pre-stored entity set, so that a corresponding entity is identified.
And step S104, determining a target standard question based on the intention recognition result and the entity recognition result, and feeding back an answer of the target standard question to the user.
Specifically, a target standard question is determined based on the intention recognition result and the entity recognition result, and an answer of the target standard question is fed back to the user; wherein, a corresponding vector can be generated based on the identified intention and the entity, then the similarity between the generated vector and a plurality of pre-stored candidate standard questions is calculated, and the target standard question is determined based on the calculation result of the similarity, wherein the determination that the similarity is highest can be determined as the target standard question.
Compared with the prior art that a target standard question is determined based on the similarity between a question of a user and the standard question and an answer of the target standard question is fed back to the user, the question answering method comprises the steps of obtaining the target question of the user, performing intention identification based on the target question of the user to obtain an intention identification result, performing entity identification based on the target question of the user to obtain an entity identification result, determining the target standard question based on the intention identification result and the entity identification result, and feeding the answer of the target standard question back to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
The embodiment of the present application provides a possible implementation manner, where the intention identification result includes an explicit intention, an ambiguous intention, and no intention, and the entity identification result includes whether there is an entity (i.e., whether or not entity information is included), and entity information (where an entity may include one or more entities).
The embodiment of the present application provides a possible implementation manner, where if the intention identification result is an explicit intention, and the entity identification result is an entity, the determining the target criterion based on the intention identification result and the entity identification result in step S104 includes:
in step S1041 (not shown), a target standard question is determined from the plurality of candidate standard questions based on the explicit intention of the intention recognition result and the entity of the entity recognition result, and the answer of the target standard question is fed back to the user.
Specifically, if the intention recognition result is an explicit intention and the entity recognition result is an entity, a vector may be generated based on the identified explicit intention and the entity, then the similarity between the candidate standard questions and the generated vector may be calculated, and the target standard question may be determined based on the calculation result of the similarity. And if the number of the entities is multiple, matching the entities with the intentions is carried out, wherein the matching of the entities and the intentions can be realized in a similarity calculation mode.
For the embodiment of the application, the determination problem of the target standard question is solved.
The embodiment of the present application provides a possible implementation manner, and if the intention identification result is a fuzzy intention, the entity identification result is an entity, further, the method further includes:
step S105 (not shown in the figure), presenting the blur intention to the user;
step S106 (not shown in the figure), based on the user 'S intention selection, determines the clear intention of the user' S target question.
Specifically, the intention recognition result is a probability value of each intention, if the intention recognition result is a fuzzy intention, that is, the probability that none of the recognized intentions exceeds a predetermined first probability value, the intention with the probability value exceeding a predetermined second probability value can be prompted or presented to the user, the user can select a corresponding intention based on the presentation or the prompt, so as to obtain a clear intention, and then the objective standard question is determined according to the clear intention and the entity.
With the embodiment of the application, the problem of how to determine the target standard question in the situation that the intention is fuzzy intention and an entity exists is solved.
The embodiment of the present application provides a possible implementation manner, and if the intention identification result is an intention-free result, the entity identification result is an entity, further, the method further includes:
step S107 (not shown in the figure), prompting the user of at least one potential intention corresponding to the entity of the entity identification result;
step S108 (not shown in the figure), based on the user 'S intention selection, determines the clear intention of the user' S target question.
Specifically, if the intention identification result is no intention, namely the probability value of each intention is lower than a predetermined third threshold value, the possible intention corresponding to the entity is prompted to the user according to the identified entity, and then the clear intention of the target problem of the user is determined based on the intention selection of the user. Thereby converting the determined target standard question without the intention of the entity into the determined target standard question with the definite intention of the entity.
With the embodiment of the application, the problem of how to determine the target standard in case of no intention of an entity is solved.
The embodiment of the present application provides a possible implementation manner, where the target problem is a text problem, and the performing intent recognition based on the target problem of the user in step S104 to obtain an intent recognition result includes:
step S1042 (not shown in the figure), determining a text vector of the text target question based on the text target question;
in step S1043 (not shown in the figure), an intention recognition result is determined by the pre-trained softmax model based on the text vector of the target question.
Specifically, word segmentation processing may be performed on the text target problem, then word embedding processing is performed to obtain a text vector of the text target problem, and then the text vector of the target problem is input into a pre-trained softmax model to determine an intention recognition result, where the intention recognition result may be a probability value of each intention.
With the embodiment of the application, the problem of how to identify the intention according to the text target problem is solved.
The embodiment of the present application provides a possible implementation manner, where the target question is a voice question, and the performing intent recognition based on the target question of the user in step S104 to obtain an intent recognition result includes:
step S1044 (not shown in the figure), performing speech recognition on the speech target problem to obtain a text of the speech target problem;
step S1045 (not shown in the figure), determining a text vector of the voice target question based on the text of the voice target question;
in step S1046 (not shown in the figure), an intention recognition result is obtained through a pre-trained softmax model based on the text vector of the speech target problem.
Specifically, if the target problem is a voice problem, the voice target problem may be subjected to voice recognition to obtain a text of the voice target problem, where the voice recognition method may be implemented based on a long-term and short-term network model, or may be another model capable of implementing the present application. And then, obtaining a text vector of the text of the voice target problem through a word embedding model, and then inputting the text vector of the voice target problem into a pre-trained softmax model to obtain an intention recognition result.
With the embodiment of the application, the problem of how to identify the intention according to the voice target problem is solved.
Fig. 2 is a question answering conversation apparatus provided in an embodiment of the present application, where the apparatus 20 includes: an acquisition module 201, an intent recognition module 202, an entity recognition module 203, a first determination module 204, wherein,
an obtaining module 201, configured to obtain a target question of a user;
the intention recognition module 202 is used for performing intention recognition based on a target problem of the user to obtain an intention recognition result;
the entity identification module 203 is used for carrying out entity identification based on the target problem of the user to obtain an entity identification result;
the first determining module 204 is configured to determine a target standard question based on the intention recognition result and the entity recognition result, and feed back an answer to the target standard question to the user.
The embodiment of the application provides a question-answer dialogue device, and compared with the prior art that a target standard question is determined based on the similarity between a question of a user and the standard question, and an answer of the target standard question is fed back to the user, the question-answer dialogue device obtains the target question of the user, performs intention identification based on the target question of the user to obtain an intention identification result, performs entity identification based on the target question of the user to obtain an entity identification result, determines the target standard question based on the intention identification result and the entity identification result, and feeds back the answer of the target standard question to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
The question-answering conversation device of the present embodiment can execute the question-answering conversation method provided in the above embodiments of the present application, and the implementation principles thereof are similar, and are not described herein again.
As shown in fig. 3, an embodiment of the present application provides another question-answering conversation apparatus, where the apparatus 30 includes: an acquisition module 301, an intent recognition module 302, an entity recognition module 303, a first determination module 304, wherein,
an obtaining module 301, configured to obtain a target question of a user;
the acquiring module 301 in fig. 3 has the same or similar function as the acquiring module 201 in fig. 2.
An intention recognition module 302, configured to perform intention recognition based on a target question of a user to obtain an intention recognition result;
wherein the intent recognition module 302 of fig. 3 is functionally the same as or similar to the intent recognition module 202 of fig. 2.
An entity identification module 303, configured to perform entity identification based on a target problem of a user to obtain an entity identification result;
the entity identification module 303 in fig. 3 has the same or similar function as the entity identification module 203 in fig. 2.
A first determining module 304, configured to determine a target standard question based on the intention recognition result and the entity recognition result, and feed back an answer to the target standard question to the user.
Wherein the first determining module 304 in fig. 3 has the same or similar function as the first determining module 204 in fig. 2.
The embodiment of the application further provides a possible implementation manner, wherein the intention identification result comprises a clear intention, a fuzzy intention and an unintended intention, and the entity identification result comprises the existence of an entity and entity information.
The embodiment of the present application provides a possible implementation manner, if the intention identification result is an explicit intention, and the entity identification result is an entity, the intention identification module 302 is specifically configured to determine a target standard question from a plurality of candidate standard questions based on the explicit intention of the intention identification result and the entity of the entity identification result, and feed back an answer to the target standard question to the user.
For the embodiment of the application, the determination problem of the target standard question is solved.
The embodiment of the present application provides a possible implementation manner, further, if the intention identification result is an ambiguous intention, and the entity identification result is an entity, the apparatus 30 further includes:
a first prompting module 305 for prompting the fuzzy intent to the user;
a second determination module 306 for determining the explicit intent of the user's target question based on the user's intent selections.
With the embodiment of the application, the problem of how to determine the target standard question in the situation that the intention is fuzzy intention and an entity exists is solved.
The embodiment of the present application provides a possible implementation manner, further, if the intention identification result is an intention-free result, and the entity identification result is an entity, the apparatus 30 further includes:
a second prompting module 307, configured to prompt the user of at least one potential intention corresponding to the entity of the entity identification result;
a third determination module 308 for determining the explicit intent of the user's target question based on the user's intent selections.
With the embodiment of the application, the problem of how to determine the target standard in case of no intention of an entity is solved.
The embodiment of the present application provides a possible implementation manner, where the target problem is a text problem, and the intention identifying module 302 includes:
a first determining unit 3021 (not shown in the figure) for determining a text vector of the text target question based on the text target question;
a second determination unit 3022 (not shown in the figure) for determining an intention recognition result by a pre-trained softmax model based on the text vector of the target question.
With the embodiment of the application, the problem of how to identify the intention according to the text target problem is solved.
The embodiment of the present application provides a possible implementation manner, where the target problem is a speech problem, and the intention identifying module 302 includes:
a recognition unit 3023 (not shown in the figure) for performing speech recognition on the speech target problem to obtain a text of the speech target problem;
a third determining unit 3024 (not shown in the figure) for determining a text vector of the voice target question based on the text of the voice target question;
a fourth determination unit 3025 (not shown in the figure) for determining an intention recognition result by a pre-trained softmax model based on the text vector of the speech target problem.
With the embodiment of the application, the problem of how to identify the intention according to the voice target problem is solved.
The embodiment of the application provides a question-answer dialogue device, and compared with the prior art that a target standard question is determined based on the similarity between a question of a user and the standard question, and an answer of the target standard question is fed back to the user, the question-answer dialogue device obtains the target question of the user, performs intention identification based on the target question of the user to obtain an intention identification result, performs entity identification based on the target question of the user to obtain an entity identification result, determines the target standard question based on the intention identification result and the entity identification result, and feeds back the answer of the target standard question to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
The embodiment of the present application provides a question-answering conversation device, which is suitable for the method shown in the above embodiment, and is not described herein again.
An embodiment of the present application provides an electronic device, as shown in fig. 4, an electronic device 40 shown in fig. 4 includes: a processor 401 and a memory 403. Wherein the processor 401 is coupled to the memory 403, such as via a bus 402. Further, the server 40 may also include a transceiver 404. It should be noted that the transceiver 404 is not limited to one in practical application, and the structure of the server 40 is not limited to the embodiment of the present application. The processor 401 is applied to the embodiment of the present application, and is configured to implement the functions of the obtaining module, the intention identifying module, the entity identifying module, and the first determining module shown in fig. 2 or fig. 3, and the functions of the first prompting module, the second determining module, the second prompting module, and the third determining module shown in fig. 3. The transceiver 404 includes a receiver and a transmitter.
The processor 401 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 401 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
The memory 403 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 403 is used for storing application program codes for executing the scheme of the application, and the execution is controlled by the processor 401. Processor 401 is configured to execute application program code stored in memory 403 to implement the functions of the question and answer dialog device provided by the embodiment shown in fig. 2 or fig. 3.
Compared with the prior art that a target standard question is determined based on the similarity between the question of the user and the standard question and the answer of the target standard question is fed back to the user, the electronic equipment obtains the target question of the user, conducts intention identification based on the target question of the user to obtain an intention identification result, conducts entity identification based on the target question of the user to obtain an entity identification result, determines the target standard question based on the intention identification result and the entity identification result, and feeds the answer of the target standard question back to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
The embodiment of the application provides an electronic device suitable for the method embodiment. And will not be described in detail herein.
The present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method shown in the above embodiments is implemented.
Compared with the prior art that a target standard question is determined based on the similarity between a question of a user and the standard question and an answer of the target standard question is fed back to the user, the target question of the user is obtained, intention recognition is carried out based on the target question of the user to obtain an intention recognition result, entity recognition is carried out based on the target question of the user to obtain an entity recognition result, the target standard question is determined based on the intention recognition result and the entity recognition result, and the answer of the target standard question is fed back to the user. The target standard question is determined based on the identified intention and the entity, and the answer corresponding to the target standard question is fed back to the user, so that the relevance of the fed-back answer and the user question is improved.
The embodiment of the application provides a computer-readable storage medium which is suitable for the method embodiment. And will not be described in detail herein.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.
Claims (10)
1. A question-answer dialog method, comprising:
acquiring a target problem of a user;
performing intention recognition based on the target question of the user to obtain an intention recognition result;
carrying out entity identification based on the target problem of the user to obtain an entity identification result;
and determining a target standard question based on the intention recognition result and the entity recognition result, and feeding back an answer of the target standard question to the user.
2. The method of claim 1, wherein the intention recognition result comprises an explicit intention, an ambiguous intention, and an unintentional intention, and the entity recognition result comprises existence of an entity and entity information.
3. The method of claim 2, wherein if the intention recognition result is an explicit intention, the entity recognition result is an entity, and the determining the target criteria based on the intention recognition result and the entity recognition result comprises:
and determining a target standard question from a plurality of candidate standard questions based on the clear intention of the intention recognition result and the entity of the entity recognition result, and feeding back the answer of the target standard question to the user.
4. The method of claim 3, wherein if the intent recognition result is an ambiguous intent, the entity recognition result is an entity, the method further comprising:
prompting the user for the obscured intent;
based on the user's intent selection, the user's explicit intent of the target question is determined.
5. The method of claim 3, wherein if the intention recognition result is no intention, the entity recognition result is an entity, the method further comprising:
prompting at least one potential intention corresponding to the entity of the entity identification result to a user;
based on the user's intent selection, the user's explicit intent of the target question is determined.
6. The method according to any one of claims 1-5, wherein the target question is a text question, and the performing intent recognition based on the target question of the user to obtain an intent recognition result comprises:
determining a text vector of the text target question based on the text target question;
determining the intent recognition result through a pre-trained softmax model based on the text vector of the target question.
7. The method of claim 1, wherein the target question is a voice question, and performing intent recognition based on the target question of the user to obtain an intent recognition result comprises:
carrying out voice recognition on a voice target problem to obtain a text of the voice target problem;
determining a text vector of the voice target question based on the text of the voice target question;
and obtaining the intention recognition result through a pre-trained softmax model based on the text vector of the voice target problem.
8. A question-answering conversation apparatus, comprising:
the acquisition module is used for acquiring a target problem of a user;
the intention recognition module is used for recognizing the intention based on the target problem of the user to obtain an intention recognition result;
the entity identification module is used for carrying out entity identification on the basis of the target problem of the user to obtain an entity identification result;
and the first determination module is used for determining a target standard question based on the intention recognition result and the entity recognition result and feeding back an answer of the target standard question to the user.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: executing the question-answer dialog method according to any one of claims 1 to 7.
10. A computer-readable storage medium for storing computer instructions which, when executed on a computer, cause the computer to perform the question-answering dialogue method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203765.0A CN111414467A (en) | 2020-03-20 | 2020-03-20 | Question-answer dialogue method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203765.0A CN111414467A (en) | 2020-03-20 | 2020-03-20 | Question-answer dialogue method and device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111414467A true CN111414467A (en) | 2020-07-14 |
Family
ID=71493129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010203765.0A Pending CN111414467A (en) | 2020-03-20 | 2020-03-20 | Question-answer dialogue method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111414467A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073600A (en) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of intelligent answer exchange method, device and electronic equipment |
| CN108170792A (en) * | 2017-12-27 | 2018-06-15 | 北京百度网讯科技有限公司 | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence |
| CN109858022A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of user's intension recognizing method, device, computer equipment and storage medium |
| CN110427467A (en) * | 2019-06-26 | 2019-11-08 | 深圳追一科技有限公司 | Question and answer processing method, device, computer equipment and storage medium |
| KR20190131270A (en) * | 2018-05-16 | 2019-11-26 | (주)아이브릭스 | The syntax grammar rules automatic generation method of understanding user query intention |
| CN110674639A (en) * | 2019-09-24 | 2020-01-10 | 拾音智能科技有限公司 | Natural language understanding method based on pre-training model |
| CN110717026A (en) * | 2019-10-08 | 2020-01-21 | 腾讯科技（深圳）有限公司 | Text information identification method, man-machine conversation method and related device |
-
2020
- 2020-03-20 CN CN202010203765.0A patent/CN111414467A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073600A (en) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of intelligent answer exchange method, device and electronic equipment |
| CN108170792A (en) * | 2017-12-27 | 2018-06-15 | 北京百度网讯科技有限公司 | Question and answer bootstrap technique, device and computer equipment based on artificial intelligence |
| KR20190131270A (en) * | 2018-05-16 | 2019-11-26 | (주)아이브릭스 | The syntax grammar rules automatic generation method of understanding user query intention |
| CN109858022A (en) * | 2019-01-04 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of user's intension recognizing method, device, computer equipment and storage medium |
| CN110427467A (en) * | 2019-06-26 | 2019-11-08 | 深圳追一科技有限公司 | Question and answer processing method, device, computer equipment and storage medium |
| CN110674639A (en) * | 2019-09-24 | 2020-01-10 | 拾音智能科技有限公司 | Natural language understanding method based on pre-training model |
| CN110717026A (en) * | 2019-10-08 | 2020-01-21 | 腾讯科技（深圳）有限公司 | Text information identification method, man-machine conversation method and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021174717A1 (en) | Text intent recognition method and apparatus, computer device and storage medium | |
| CN109492764B (en) | Training method, related equipment and medium for generating countermeasure network | |
| US9582757B1 (en) | Scalable curation system | |
| CN110472027B (en) | Intent recognition method, apparatus, and computer-readable storage medium | |
| CN108153800B (en) | Information processing method, information processing apparatus, and recording medium | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| US8521511B2 (en) | Information extraction in a natural language understanding system | |
| CN110874401B (en) | Information processing method, model training method, device, terminal and computing equipment | |
| CN110717027B (en) | Multi-round intelligent question-answering method, system, controller and medium | |
| KR102030551B1 (en) | Instant messenger driving apparatus and operating method thereof | |
| CN109979450A (en) | Information processing method, device and electronic equipment | |
| CN112487381A (en) | Identity authentication method and device, electronic equipment and readable storage medium | |
| CN114218945A (en) | Entity identification method, device, server and storage medium | |
| CN111027316A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| CN109033082B (en) | Learning training method and device of semantic model and computer readable storage medium | |
| CN110750626B (en) | Scene-based task-driven multi-turn dialogue method and system | |
| CN110413750B (en) | Method and device for recalling standard questions according to user questions | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| CN111414467A (en) | Question-answer dialogue method and device, electronic equipment and computer readable storage medium | |
| CN113867707A (en) | Folder naming method and device | |
| CN111708862B (en) | Text matching method and device and electronic equipment | |
| CN110175241B (en) | Question and answer library construction method and device, electronic equipment and computer readable medium | |
| CN112395402A (en) | Depth model-based recommended word generation method and device and computer equipment | |
| CN111401011B (en) | Information processing method and device and electronic equipment |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220919 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |