CN112860874B - Question-answer interaction method, device, equipment and storage medium - Google Patents
Question-answer interaction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112860874B CN112860874B CN202110313699.7A CN202110313699A CN112860874B CN 112860874 B CN112860874 B CN 112860874B CN 202110313699 A CN202110313699 A CN 202110313699A CN 112860874 B CN112860874 B CN 112860874B
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- news
- current candidate
- pair
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005096 rolling process Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000005562 fading Methods 0.000 claims description 6
- 238000003058 natural language processing Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 description 24
- 238000010586 diagram Methods 0.000 description 11
- 238000012800 visualization Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 235000019633 pungent taste Nutrition 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0483—Interaction with page-structured environments, e.g. book metaphor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a question-answer interaction method, a question-answer interaction device, question-answer interaction equipment and a question-answer interaction storage medium, and relates to the technical field of computers, in particular to the technical field of man-machine interaction. The specific implementation scheme is as follows: according to the hot news in the global scene and the historical question-answer pairs of the target scene in the historical question-answer period, determining the current candidate question-answer pairs of the target scene in the current question-answer period; and based on the current candidate question-answer pair, performing question-answer interaction with the user in the target scene. The method and the device can improve the question-answer interaction efficiency of the target scene.
Description
Technical Field
The disclosure relates to the technical field of computers, in particular to the technical field of man-machine interaction, and specifically relates to a question-answer interaction method, a question-answer interaction device, question-answer interaction equipment and a storage medium.
Background
With the development of computer technology, intelligent question-answering products are increasingly widely used. The intelligent question and answer product can acquire the questions of the user and pertinently solve the questions of the user.
However, the user has a great deal of problems due to the openness of the question-and-answer type product. It is important how to conduct the question-answer interaction.
Disclosure of Invention
The present disclosure provides a method, apparatus, device and storage medium for question-answering interaction.
According to an aspect of the present disclosure, there is provided a question-answer interaction method, including:
according to the hot news in the global scene and the historical question-answer pairs of the target scene in the historical question-answer period, determining the current candidate question-answer pairs of the target scene in the current question-answer period;
And based on the current candidate question-answer pair, performing question-answer interaction with the user in the target scene.
According to another aspect of the present disclosure, there is provided a question-answer interaction device, including:
The question-answer pair determining module is used for determining a current candidate question-answer pair of a target scene in a current question-answer period according to hot news in a global scene and the historical question-answer pair of the target scene in a historical question-answer period;
and the question-answer interaction module is used for carrying out question-answer interaction with the user in the target scene based on the current candidate question-answer pair.
According to still another aspect of the present disclosure, there is provided an electronic apparatus including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the question-answer interaction method provided by any embodiment of the present disclosure.
According to yet another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the question-answer interaction method provided by any embodiment of the present disclosure.
According to yet another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the question-answer interaction method provided by any embodiment of the present disclosure.
According to the technology disclosed by the invention, the question-answer interaction efficiency of the target scene can be improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a question-answer interaction method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of another question-answer interaction method according to an embodiment of the disclosure;
FIG. 3a is a schematic diagram of yet another question-answer interaction method according to an embodiment of the disclosure;
FIGS. 3b and 3c are schematic diagrams of candidate problem presentation interfaces provided in accordance with embodiments of the present disclosure;
FIG. 4 is a schematic diagram of a question-answering interaction device according to an embodiment of the present disclosure;
fig. 5 is a block diagram of an electronic device for implementing a question-answer interaction method of an embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The following describes in detail the solution provided by the embodiments of the present disclosure with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a question-answer interaction method provided according to an embodiment of the present disclosure, which is applicable to a case of providing an intelligent question-answer service to a user in a target scenario. The method can be implemented by a question-answering interaction device which can be implemented in hardware and/or software and can be configured in an interactive electronic device. Referring to fig. 1, the method specifically includes the following:
S110, determining a current candidate question-answer pair of a target scene in a current question-answer period according to hot news in a global scene and the historical question-answer pair of the target scene in a historical question-answer period;
S120, based on the current candidate question-answer pair, question-answer interaction is conducted with the user in the target scene.
The global scene is not limited by a specific scene, and can be applied to at least two scenes; the target scene refers to a working scene of the interaction device, and can be a library, a market, a hospital and the like. The time step of a single question-answer period can be a first time interval, namely, one question-answer period is set every first time; the historical question-answer period refers to at least two question-answer periods before the current question-answer period, and the historical question-answer pair refers to a question-answer pair used by the user in the interaction process of the historical question-answer period, namely, a question actually asked by the user and an answer associated with the question-answer. The current candidate question-answer pair refers to the candidate question and the answer to the candidate question that the user selected for the interactive device provided in the current question-answer period.
Specifically, a news hot search list can be grabbed from the Internet to obtain hot news in a global scene; the method can also acquire the historical question-answer pairs used by each interactive device in the target scene in the interactive process of the historical question-answer period, and determine the current candidate question-answer pair of the target scene in the current question-answer period by combining the hot news and the historical question-answer pairs of the target scene; the current candidate question in the current candidate question-answer pair is presented to the user, and in the event that the user selects any of the current candidate questions, an answer to the current candidate question is provided to the user. It should be noted that, a screen of the interaction device may be adopted to scroll and display the current candidate problem, so that the user can conveniently select the problem focused by himself from the current candidate problems and interact with the interaction device.
The method has the advantages that the current candidate question-answer pair of the target scene is determined according to the hot news and the historical question-answer pair of the target scene, so that the current candidate question-answer pair not only can provide heat search information for users and meet the attention requirement of the users on the global scene, but also can meet the use characteristics of the target scene, namely, the current candidate question-answer pair can hit the user requirement of the target scene, the interaction efficiency of the users in the target scene is improved, and the use requirement of the users on the target scene is met.
According to the technical scheme, the current candidate question-answer pair of the target scene in the current question-answer period is determined according to the hot news in the global scene and the historical question-answer pair of the target scene in the historical question-answer period, so that the real-time performance of the hot news and the use characteristics of the target scene can be considered by the current candidate question-answer pair, the hit rate of the current candidate question-answer pair on the user requirement in the target scene is improved, and the interaction efficiency with the user in the target scene is improved.
Fig. 2 is a flow chart of another question-answer interaction method provided according to an embodiment of the present disclosure. This embodiment is an alternative to the embodiments described above. Referring to fig. 2, the question-answer interaction method provided in this embodiment includes:
S210, selecting at least one piece from the hot news of the global scene as a current candidate news, and generating a hot news question-answer pair according to the current candidate news to serve as the current candidate question-answer pair;
s220, selecting at least one of the historical question-answer pairs in the historical question-answer period from the target scene as the current candidate question-answer pair;
S230, based on the current candidate question-answer pair, question-answer interaction is conducted with the user in the target scene.
Specifically, the hot news may be ranked according to the heat, and at least one hot news with relatively high heat may be selected as the current candidate news; and determining the question and answer of the current candidate news for each current candidate news, namely generating a hot news question-answer pair, wherein the question of the current candidate news can be provided for a user to use in the process of interacting with the user.
Specifically, the user question-answering frequency of the historical question-answering pairs of each historical question-answering period in the target scene can be counted, the historical question-answering pairs are ranked according to the user question-answering frequency, and the historical question-answering pairs with relatively more user question-answering frequency are selected as current candidate question-answering pairs. The total number of the current candidate question-answer pairs in the current question-answer period, the number of the current candidate question-answer pairs determined according to the hot news, and the number of the current candidate question-answer pairs determined according to the historical question-answer pairs can be a fixed value, such as 10; also, half of the current candidate question-answer pairs may be from hot news and the other half may be from historical question-answer pairs. The matching degree of the current candidate question-answer pair and the user question-answer requirement can be improved by selecting the current candidate question-answer pair according to the heat of the hot news and the question-answer frequency of the history question-answer pair, namely the use ratio of the user to the current candidate question-answer pair is improved, and the interaction efficiency with the user is further improved.
In the initialization phase of the target scenario, the current candidate question-answer pairs may all come from hot news. For example, at the initial stage of the target scene, 10 current candidate question-answer pairs are all from hot news; in the use stage of the target scene, 5 current candidate question-answer pairs can be 5 from hot news, and the other 5 historical question-answer pairs from the target scene. Specifically, in the initialization stage of the target scene, selecting N current candidate news from the hot news of the global scene, and generating N current candidate question-answer pairs according to the current candidate behaviors; in the using stage of the target scene, N1 pieces of current candidate news are selected from hot news of the global scene, N2 pieces of historical question-answer pairs are selected from the historical question-answer pairs of the target scene, and N pieces of current candidate news are generated according to the N1 pieces of current candidate news and the N2 pieces of historical question-answer pairs, wherein N is the sum of N1 and N2.
It should be noted that, in the use stage of the target scene, the first hot news in the panoramic scene may also be obtained at regular intervals, and if the first hot news does not belong to the current candidate news, the first hot news is added to the current candidate news, for example, the first hot news is used as the first hot news in the current candidate news, and the last hot news in the current candidate news is deleted. Wherein the second time interval is less than the time step of a single question-answer period. The first hot news is added to the current candidate news at fixed time, so that the timeliness of the current candidate question-answer pair is improved, and the hit rate of the current candidate question-answer pair on the user requirement is further improved.
In an alternative embodiment, generating a hot news question-answer pair from the current candidate news includes: determining the hot news question-answer pairs according to the current candidate news based on a natural language processing technology; wherein the number of question words in the hot news question-answering pair is less than a word number threshold.
Specifically, the current candidate news can be processed into question-answer forms based on natural language processing technology, and hot news question-answer pairs are obtained. Wherein the number of question words in the hot news question-answer pair may be less than a word number threshold (e.g., 8 characters), i.e., the questions in the hot news question-answer may be short questions. Through the hot news question-answering pair of the short questions, the questions are conveniently displayed, the questions are conveniently asked by the user, and the interaction efficiency can be further improved.
In an alternative embodiment, selecting at least one of the historical question-answer pairs of the historical question-answer period from the target scene as the current candidate question-answer pair includes: acquiring a history question-answer pair acquired by the interaction equipment in the target scene in a history question-answer period; removing the historical question-answer pairs repeated with the hot news question-answer pairs; and selecting at least one question and answer pair from the rest of the history question and answer pairs as the current candidate question and answer pair according to the history question frequency.
Specifically, in the process of selecting the current candidate question-answer pair from the history question-answer pair of the target scene, the history question-answer pair repeated with the hot news question-answer pair is removed, so that the current candidate question-answer pair determined according to the hot news is prevented from being repeated with the current candidate question-answer pair determined according to the history question-answer pair, and the quality of the current candidate question-answer pair is further improved.
According to the technical scheme, the current candidate question-answer pair is selected according to the hotness of the hot news and the question frequency of the history question-answer pair, so that the utilization rate of the user to the current candidate question-answer pair can be improved, and the interaction efficiency with the user is further improved; and the interactive efficiency and the quality of the current candidate question-answer pair are further improved by generating the current candidate question-answer pair of the short question and eliminating the historical question-answer pair repeated with the hot news question-answer pair.
Fig. 3a is a flow chart of another question-answer interaction method provided according to an embodiment of the present disclosure. This embodiment is an alternative to the embodiments described above. Referring to fig. 3a, the question-answer interaction method provided in this embodiment includes:
S310, determining a current candidate question-answer pair of a target scene in a current question-answer period according to hot news in a global scene and the historical question-answer pair of the target scene in a historical question-answer period;
s320, displaying the candidate questions in the current candidate question-answer pair in a rolling way by adopting interaction equipment in a target scene;
And S330, broadcasting an answer associated with any candidate question when the user is identified to select the candidate question.
The interaction device may be an intelligent robot with a screen, or an intelligent sound box with a screen, which is not specifically limited in the disclosure. Specifically, the candidate questions in the current candidate question pair can be displayed through scrolling of the interactive equipment in the target scene, so that the user can selectively ask questions according to the candidate questions displayed by the interactive equipment, and answer the questions of the user. The candidate questions are displayed to the user through the interaction equipment, so that the user can select the questions focused on by himself from the candidate questions without organizing the questions, the user can be guided to participate in the interaction process, and the interaction efficiency is improved; in addition, the answers associated with the candidate questions are predetermined and can be directly used, so that the interaction efficiency can be further improved.
The embodiments of the present disclosure do not specifically limit the manner of user interaction. Responding to the touch operation of the user on any candidate question book displayed in a rolling way, and taking the answer content associated with the candidate question as interaction information with the user; the answer content associated with any candidate question can be used as interaction information with the user under the condition that the user inputs any candidate question through voice, namely, interaction of the user through touch control and voice can be supported.
In an optional implementation manner, the step of using the interaction device in the target scene to scroll and display the candidate questions in the current candidate question-answer pair includes: and displaying the candidate questions in the current candidate question-answering pair in a rolling way by adopting interaction equipment in the target scene through the fading dynamic effect.
Specifically, the display sequence of each candidate problem in the current candidate question-answering pair is determined, the candidate problems are displayed in a rolling manner in the visual window according to the display sequence through the fading out dynamic effect, for example, the candidate problems at the top of the visual window gradually appear, the candidate problems at the bottom of the visual window gradually hide, visual continuity display of each candidate problem can be achieved, visual faults generated by whole screen rolling of the candidate problems can be avoided, the user can focus and browse the candidate problems, and the user can browse the candidate problems conveniently. FIGS. 3b and 3c are schematic diagrams of candidate problem presentation interfaces provided in accordance with embodiments of the present disclosure; referring to fig. 3B and 3C, the ith visualization window 31 may display candidate problem C, candidate problem D, and candidate problem E, in addition, candidate problem a, candidate problem B, candidate problem F, candidate problem G, …, candidate problem J are all hidden, the top candidate problem B may gradually appear in the process from the ith visualization window 31 to the (i+1) th visualization window 32, and the bottom candidate problem E of the visualization window 31 may gradually be hidden, so that candidate problem B, candidate problem C, and candidate problem D are displayed in the (i+1) th visualization window 32, in addition, candidate problem J, candidate problem a, candidate problem E, candidate problem F, …, and candidate problem I are all hidden.
In addition, the implementation manner of scroll presentation of candidate questions in the interactive device is not particularly limited in the embodiments of the present disclosure. Specifically, a text presentation element can be obtained, the text presentation element is used as a visual window, and an attribute value of the visual window is set, for example, the text box (TextView) label of an element in a row is used for obtaining the content and the font size of the text to be scrolled, and the width of the text to be scrolled is determined according to the content and the font size of the text to be scrolled; the characters obtained by the text box labels of the elements in the rows are longitudinally arranged in the middle; creating a linear layout (LinearLayout) for wrapping the text to be scrolled in the visual window, taking the width of the text to be scrolled as the width of the linear layout, and setting the absolute position of the linear layout in the visual window; scrolling the linear layout in the visual window, and scrolling the fixed height upwards at intervals of a first preset residence time, wherein a preset time interval is arranged between the first preset residence time and a second preset residence time, and the preset time interval is the text residence time of each text box label;
Different transparency change values are added in the visual window area, so that the dynamic effect of fading out of the linear layout in the text scrolling process can be achieved. Specifically, the text box label text field of the visual window can be rolled up to a fixed height at intervals of a first preset time, whether the text box label text field of the visual window needs to be displayed continuously or not is judged after the first rolling time, and if yes, the TextView label text field sequentially enters the end of a linear layout queue of package rolling text; otherwise discard the field. And acquiring a new field sequence in real time to enter the tail of the linear layout queue of the package rolling text.
Wherein, the setting of the visualization window may include: and displaying the area of the rolling characters in the screen of the visual display, wherein the height is a self-defined absolute value, the width is larger than the width of the linear layout, and the width of the linear layout is equal to the width of the rolling characters. And, the absolute position of the linear layout within the visualization window may be set as follows: and initially, centering the linear layout and the left and right of the visual window, wherein the upper edge of the linear layout is at a fixed distance from the upper edge of the visual window.
Specifically, the dissolve dynamic effect can be achieved by: and dividing the transparency value from top to bottom in the visual window area, wherein the transparency value presents a mountain peak shape. For example, the transparency value in the visualization window may be: 0. 50, 100, 50, 0, at least two text box label text fields may be included in the visualization window area, with a top text transparency of about 50, a middle text transparency of 100, and a bottom text transparency of about 50. Through the change of the character transparency level, the aim that the character animation in the bottom part of the visual window area is dissolved and disappeared when the linear layout is rolled from bottom to top is achieved, and the character animation at the top part is dissolved and appearing, so that the user achieves the continuity in the character visual experience of the rolling effect.
According to the technical scheme, the accuracy of candidate problem contents is improved by dynamically determining the candidate problems rolled in the visual window, so that the hit rate of the candidate problems on the user demand is improved, the frequency of using the candidate problems by the user is increased, and the utilization rate is improved. Moreover, by continuous scrolling, continuity in visual experience is realized; and a plurality of interaction modes of touch control and voice are supported, so that interaction convenience is improved.
Fig. 4 is a schematic diagram of a question-answer interaction device according to an embodiment of the present disclosure, where the embodiment may be suitable for a case of providing an intelligent question-answer service for a user in a target scenario, where the device is configured in an electronic device, and may implement a question-answer interaction method according to any embodiment of the present disclosure. The question-answer interaction device 400 specifically includes the following:
The question-answer pair determining module 401 is configured to determine a current candidate question-answer pair of the target scene in a current question-answer period according to the hot news in the global scene and the historical question-answer pair of the target scene in the historical question-answer period;
and a question-answer interaction module 402, configured to perform a question-answer interaction with the user in the target scenario based on the current candidate question-answer pair.
In an alternative embodiment, the question-answer pair determination module 401 includes:
The news question-answering unit is used for selecting at least one piece from the hot news of the global scene as a current candidate news, and generating a hot news question-answering pair according to the current candidate news to serve as the current candidate question-answering pair;
And the historical question-answer unit is used for selecting at least one of the historical question-answer pairs of the target scene in the historical question-answer period as the current candidate question-answer pair.
In an alternative embodiment, the news question-answering unit is specifically configured to:
Determining the hot news question-answer pairs according to the current candidate news based on a natural language processing technology; wherein the number of question words in the hot news question-answering pair is less than a word number threshold.
In an alternative embodiment, the history question-answering unit is specifically configured to:
acquiring a history question-answer pair acquired by the interaction equipment in the target scene in a history question-answer period;
Removing the historical question-answer pairs repeated with the hot news question-answer pairs;
And selecting at least one question and answer pair from the rest of the history question and answer pairs as the current candidate question and answer pair according to the history question frequency.
In an alternative embodiment, the question-answer interaction module 402 includes:
The problem display unit is used for displaying the candidate problems in the current candidate question-answer pair in a rolling way by adopting interaction equipment in the target scene;
And the answer broadcasting unit is used for broadcasting the answer associated with any candidate question when the user is identified to select the candidate question.
In an alternative embodiment, the problem display unit is specifically configured to:
And displaying the candidate questions in the current candidate question-answering pair in a rolling way by adopting interaction equipment in the target scene through the fading dynamic effect.
According to the technical scheme, the accuracy of candidate problem contents is improved by dynamically determining the candidate problems rolled in the visual window, so that the hit rate of the candidate problems on the user demand is improved, the frequency of using the candidate problems by the user is increased, and the utilization rate is improved. Moreover, by continuous scrolling, continuity in visual experience is realized; and a plurality of interaction modes of touch control and voice are supported, so that interaction convenience is improved.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 5 illustrates a schematic block diagram of an example electronic device 500 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the apparatus 500 includes a computing unit 501 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, ROM 502, and RAM503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Various components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, etc.; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508 such as a magnetic disk, an optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units executing machine learning model algorithms, a digital information processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the respective methods and processes described above, such as a question-answer interaction method. For example, in some embodiments, the question-answer interaction method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the question-answer interaction method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the question-answer interaction method in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs executing on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present disclosure may be performed in parallel, sequentially, or in a different order, so long as the information desired by the technical solution of the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (13)
1.A question-answer interaction method, comprising:
Selecting at least one hot news from hot news of a global scene as a current candidate news, and generating a hot news question-answer pair according to the current candidate news to serve as the current candidate question-answer pair;
Selecting at least one of the historical question-answer pairs of the historical question-answer period from the target scene as the current candidate question-answer pair; wherein the time step of a single question-answer period is a first time interval;
Based on the current candidate question-answer pair, performing question-answer interaction with a user in the target scene;
The method comprises the steps of acquiring first hot news in the global scene at regular time at a second time interval in a using stage of the target scene, taking the first hot news as the first hot news in the current candidate news and deleting last hot news in the current candidate news under the condition that the first hot news does not belong to the current candidate news; the second time interval is less than a time step of a single question-answer period.
2. The method of claim 1, wherein the generating a hot news question-answer pair from the current candidate news comprises:
Determining the hot news question-answer pairs according to the current candidate news based on a natural language processing technology; wherein the number of question words in the hot news question-answering pair is less than a word number threshold.
3. The method of claim 1, wherein the selecting at least one of the historical question-answer pairs of the historical question-answer period from the target scene as the current candidate question-answer pair comprises:
acquiring a history question-answer pair acquired by the interaction equipment in the target scene in a history question-answer period;
Removing the historical question-answer pairs repeated with the hot news question-answer pairs;
And selecting at least one question and answer pair from the rest of the history question and answer pairs as the current candidate question and answer pair according to the history question frequency.
4. The method of claim 1, wherein the conducting a question-answer interaction with a user in the target scene based on the current candidate question-answer pair comprises:
adopting interaction equipment in a target scene to scroll and display candidate questions in the current candidate question-answer pair;
In the event that a user is identified to select any of the candidate questions, an answer associated with the candidate question is broadcast.
5. The method of claim 4, wherein the employing the interactive device in the target scene to scroll through the candidate questions in the current candidate question-answer pair comprises:
And displaying the candidate questions in the current candidate question-answering pair in a rolling way by adopting interaction equipment in the target scene through the fading dynamic effect.
6. A question-answering interaction device, comprising:
The question-answer pair determining module is used for determining a current candidate question-answer pair of a target scene in a current question-answer period according to hot news in a global scene and the historical question-answer pair of the target scene in a historical question-answer period;
The question-answer interaction module is used for carrying out question-answer interaction with the user in the target scene based on the current candidate question-answer pair;
wherein, the question-answer pair determining module comprises:
The news question-answering unit is used for selecting at least one piece from the hot news of the global scene as a current candidate news, and generating a hot news question-answering pair according to the current candidate news to serve as the current candidate question-answering pair;
A history question-answer unit, configured to select at least one of the history question-answer pairs in the history question-answer period from the target scene as the current candidate question-answer pair; wherein the time step of a single question-answer period is a first time interval;
The method comprises the steps of acquiring first hot news in the global scene at regular time at a second time interval in a using stage of the target scene, taking the first hot news as the first hot news in the current candidate news and deleting last hot news in the current candidate news under the condition that the first hot news does not belong to the current candidate news; the second time interval is less than a time step of a single question-answer period.
7. The apparatus of claim 6, wherein the news question-answering unit is specifically configured to:
Determining the hot news question-answer pairs according to the current candidate news based on a natural language processing technology; wherein the number of question words in the hot news question-answering pair is less than a word number threshold.
8. The apparatus of claim 6, wherein the history question-answering unit is specifically configured to:
acquiring a history question-answer pair acquired by the interaction equipment in the target scene in a history question-answer period;
Removing the historical question-answer pairs repeated with the hot news question-answer pairs;
And selecting at least one question and answer pair from the rest of the history question and answer pairs as the current candidate question and answer pair according to the history question frequency.
9. The apparatus of claim 6, wherein the question-answer interaction module comprises:
The problem display unit is used for displaying the candidate problems in the current candidate question-answer pair in a rolling way by adopting interaction equipment in the target scene;
And the answer broadcasting unit is used for broadcasting the answer associated with any candidate question when the user is identified to select the candidate question.
10. The apparatus of claim 9, wherein the problem presentation unit is specifically configured to:
And displaying the candidate questions in the current candidate question-answering pair in a rolling way by adopting interaction equipment in the target scene through the fading dynamic effect.
11. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110313699.7A CN112860874B (en) | 2021-03-24 | 2021-03-24 | Question-answer interaction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110313699.7A CN112860874B (en) | 2021-03-24 | 2021-03-24 | Question-answer interaction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112860874A CN112860874A (en) | 2021-05-28 |
| CN112860874B true CN112860874B (en) | 2024-06-25 |
Family
ID=75992579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110313699.7A Active CN112860874B (en) | 2021-03-24 | 2021-03-24 | Question-answer interaction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112860874B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635098A (en) * | 2018-12-20 | 2019-04-16 | 东软集团股份有限公司 | A kind of intelligent answer method, apparatus, equipment and medium |
| CN110197454A (en) * | 2018-02-27 | 2019-09-03 | 深圳微盐传媒科技有限公司 | A kind of knowledge question processing method and interactive terminal |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164427B (en) * | 2011-12-13 | 2016-03-02 | 中国移动通信集团公司 | News Aggreagation method and device |
| CN106951435B (en) * | 2017-02-08 | 2020-05-22 | 广州神马移动信息科技有限公司 | News recommendation method and equipment and programmable equipment |
| CA3012211A1 (en) * | 2017-07-28 | 2019-01-28 | Virq Inc. | System and method of distributing tokens |
| CN107562843B (en) * | 2017-08-25 | 2020-07-14 | 贵州耕云科技有限公司 | News hot phrase extraction method based on title high-frequency segmentation |
| CN110162603B (en) * | 2018-11-30 | 2023-11-14 | 腾讯科技（深圳）有限公司 | Intelligent dialogue method, dynamic storage method and device |
| CN111984775A (en) * | 2020-08-12 | 2020-11-24 | 北京百度网讯科技有限公司 | Question and answer quality determination method, device, equipment and storage medium |
-
2021
- 2021-03-24 CN CN202110313699.7A patent/CN112860874B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110197454A (en) * | 2018-02-27 | 2019-09-03 | 深圳微盐传媒科技有限公司 | A kind of knowledge question processing method and interactive terminal |
| CN109635098A (en) * | 2018-12-20 | 2019-04-16 | 东软集团股份有限公司 | A kind of intelligent answer method, apparatus, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112860874A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2021089739A (en) | Question answering method and language model training method, apparatus, device, and storage medium | |
| CN112102448A (en) | Virtual object image display method and device, electronic equipment and storage medium | |
| CN112560461A (en) | News clue generation method and device, electronic equipment and storage medium | |
| CN113655895B (en) | Information recommendation method and device applied to input method and electronic equipment | |
| CN113535916B (en) | Question and answer method and device based on table and computer equipment | |
| CN113297371A (en) | Method, device and equipment for generating recommended question library and storage medium | |
| CN113360693A (en) | Method and device for determining image label, electronic equipment and storage medium | |
| CN112860874B (en) | Question-answer interaction method, device, equipment and storage medium | |
| CN115576480A (en) | Freely combined matrix questionnaire scoring and configuration method and device | |
| CN115859683A (en) | Scene simulation evaluation method and device based on automatic driving | |
| CN114530064A (en) | Calligraphy practicing method, calligraphy practicing device, calligraphy practicing equipment and calligraphy practicing storage medium based on video | |
| CN112861504A (en) | Text interaction method, device, equipment, storage medium and program product | |
| CN114035729A (en) | Electronic voting method and device and terminal equipment | |
| CN113722516A (en) | Online PK (Key distribution) display method and device for multimedia works | |
| CN115131709B (en) | Video category prediction method, training method and device for video category prediction model | |
| CN116628167B (en) | Response determination method and device, electronic equipment and storage medium | |
| CN114327059B (en) | Gesture processing method, device, equipment and storage medium | |
| CN114398130B (en) | Page display method, device, equipment and storage medium | |
| CN112527126B (en) | Information acquisition method and device and electronic equipment | |
| CN113743438B (en) | Data set generation method, device and system for text detection | |
| CN117494657A (en) | Content typesetting method and device and electronic equipment | |
| CN117076796A (en) | Comment ordering method and device, electronic equipment and storage medium | |
| CN117313677A (en) | Comment generation method and device, electronic equipment and medium | |
| CN112926419A (en) | Character judgment result processing method and device and electronic equipment | |
| CN116935417A (en) | Handwriting recognition method and device, electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |