CN110633358A - Method, apparatus and medium for processing robot and user session - Google Patents
Method, apparatus and medium for processing robot and user session Download PDFInfo
- Publication number
- CN110633358A CN110633358A CN201810554432.5A CN201810554432A CN110633358A CN 110633358 A CN110633358 A CN 110633358A CN 201810554432 A CN201810554432 A CN 201810554432A CN 110633358 A CN110633358 A CN 110633358A
- Authority
- CN
- China
- Prior art keywords
- user
- input information
- robot
- intention
- conversation
- 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
Images
Abstract
The present disclosure provides a method for handling a robot-user session, comprising: receiving input information of a user; determining a keyword of the input information according to the input information; determining the user intention according to the keywords of the input information; generating reply content of the robot based on the user intention and the keyword of the input information. The present disclosure also provides an apparatus and medium for processing a robot-user conversation.
Description
Technical Field
The present disclosure relates to the field of natural language processing, and in particular, to a method, an apparatus, and a medium for processing a conversation between a robot and a user.
Background
With the rapid development of artificial intelligence, a conversation system in the field of natural language processing receives more and more attention, and various chat robots are generated. For example, an open-world chat robot (e.g., microsoft mini-ice), and, for another example, a task-based conversation robot (e.g., a smart assistant to the kyoto electric business guide). The user can interact with the chat robot in a voice or text mode. For example, in the interaction, the voice or text input by the user can be received by the dialog system, and then the dialog system can match the voice or text based on a preset rule template (e.g., a dialect template), so as to obtain the reply content of the chat robot. However, in the process of implementing the concept of the present invention, the inventor finds that at least the following problems exist in the prior art: in the prior art, when the pattern-based dialect matching method is used, an engineer is required to write a large number of regular expressions, so that the labor cost is high. And it is not flexible enough in matching, for example, when matching with the voice or text input by the user, only the sentence pattern in the template can be recognized, and the semantics can not be recognized by slightly changing the sentence pattern, if new technical requirements are added, the cost of development and maintenance is increased.
Disclosure of Invention
Accordingly, the present disclosure is directed to a method, apparatus, and medium for processing a robot-user conversation that, in turn, at least partially solves one or more problems due to limitations and disadvantages of the related art.
The present disclosure provides, in one aspect, a method for handling a robot conversation with a user, including: receiving input information of a user; determining a keyword of the input information according to the input information; determining the user intention according to the keywords of the input information; generating reply content of the robot based on the user intention and the keyword of the input information.
According to an embodiment of the present disclosure, when the dialog of the user with the robot is a multi-turn conversation, the method further includes: judging whether the user intentions of the adjacent input information of the users in the multi-turn conversation are the same or not; and if the current input information is different from the current input information of the user, determining the current intention of the user.
According to an embodiment of the present disclosure, the method further includes: judging whether the input information of the user contains characters related to the interrupted conversation of the robot; if so, the robot is shut down.
According to an embodiment of the present disclosure, determining the user intention according to the keyword of the input information includes: analyzing the keywords of the input information by using an LSTM algorithm to obtain the user intention; or analyzing the keywords of the input information by using a Pipeline method to obtain the user intention.
According to the embodiment of the disclosure, the method further comprises setting a simulated user to have a conversation with the robot, and storing the content of the conversation.
According to an embodiment of the present disclosure, when the input information includes a character with a negative meaning, the method further includes: characters with negative meanings are deleted from the input information, and the true intention of the user is determined according to the deleted input information.
According to an embodiment of the present disclosure, the user intent includes any one of: commodity inquiry, commodity preference inquiry, commodity after-sale consultation and commodity order inquiry.
Another aspect of the present disclosure provides an apparatus for handling a conversation between a robot and a user, comprising: the receiving module is used for receiving input information of a user; the first determining module is used for determining keywords of the input information according to the input information; the second determining module is used for determining the user intention according to the key words of the input information; and the generating module is used for generating the reply content of the robot based on the user intention and the keywords of the input information.
According to the embodiment of the disclosure, when the dialog between the user and the robot is a multi-turn dialog, the apparatus further includes: the first judgment module is used for judging whether the user intentions of the adjacent input information of the users in the multi-turn conversation are the same or not; and the third determining module is used for determining the current intention of the user according to the current input information of the user if the current intention is different from the current intention of the user.
According to an embodiment of the present disclosure, the apparatus further includes: the second judgment module is used for judging whether the input information of the user contains characters related to the interrupted conversation of the robot; a shutdown module to shutdown the robot if included.
According to an embodiment of the present disclosure, the first determining module includes: the first analysis module is used for analyzing the keywords of the input information by using an LSTM algorithm to obtain the user intention; or the second analysis module analyzes the keywords of the input information by using a Pipeline method to obtain the user intention.
According to the embodiment of the disclosure, the device further comprises a setting module, which is used for setting the conversation between the simulation user and the robot and storing the content of the conversation.
According to the embodiment of the disclosure, when the input information contains characters with negative meanings, the device further comprises a deleting module, which is used for deleting the characters with negative meanings from the input information and determining the true intention of the user according to the deleted input information.
According to an embodiment of the present disclosure, the user intent includes any one of: commodity inquiry, commodity preference inquiry, commodity after-sale consultation and commodity order inquiry.
Another aspect of the present disclosure provides an apparatus for handling a robot conversation with a user. The apparatus includes one or more processors, and a storage device. The storage device is used for storing one or more programs. Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method for handling robot-to-user sessions as described above.
Another aspect of the present disclosure provides a computer-readable medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform a method for handling a robot conversation with a user as described above.
Another aspect of the disclosure provides a computer program comprising computer executable instructions for a method of handling a robot conversation with a user when executed.
According to the embodiment of the disclosure, the problems brought by the prior art when matching the user input information based on the dialogical template can be at least partially solved, for example, a large number of regular expressions need to be preset, thereby causing high labor cost. As another example, the linguistic template may only identify patterns in the template, and is not flexible enough. However, by adopting the method disclosed by the invention, the user intention can be determined according to the keywords in the user input information, and then the reply content of the robot is generated according to the user intention and the keywords, so that an engineer is not required to edit a large number of regular expressions in advance, and the labor cost is saved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Fig. 1 schematically shows a flow chart of a method for handling a robot conversation with a user according to an embodiment of the present disclosure;
FIG. 2 schematically shows a flow diagram of a method for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 3 schematically shows a flow diagram of a method for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 4 schematically shows a flow diagram of a method for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 5 schematically shows a flow diagram of a method for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 6 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to an embodiment of the present disclosure;
FIG. 7 schematically illustrates a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 8 schematically illustrates a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 9 schematically illustrates a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure;
FIG. 10 schematically illustrates a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure; and
fig. 11 schematically shows a block diagram of a computer system for handling a robot conversation with a user according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). It will be further understood by those within the art that virtually any disjunctive word and/or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase "a or B" should be understood to include the possibility of "a" or "B", or "a and B".
Embodiments of the present disclosure provide a method for handling a robot-user session, comprising: receiving input information of a user; determining a keyword of the input information according to the input information; determining the user intention according to the keywords of the input information; generating reply content of the robot based on the user intention and the keyword of the input information.
According to the embodiment of the disclosure, the problems brought by the prior art when matching the user input information based on the dialogical template can be at least partially solved, for example, a large number of regular expressions need to be preset, thereby causing high labor cost. As another example, the linguistic template may only identify patterns in the template, and is not flexible enough. By adopting the method, the user intention can be determined according to the keywords in the user input information, and then the reply content of the robot is generated according to the user intention and the keywords, so that an engineer does not need to edit a large number of regular expressions in advance, and the labor cost is saved.
Fig. 1 schematically shows a flow chart of a method for handling a robot conversation with a user according to an embodiment of the present disclosure.
As shown in fig. 1, the method for processing a robot conversation with a user includes steps S101 to S104.
In step S101, input information of a user is received.
In step S102, a keyword of the input information is determined according to the input information.
In step S103, the user intention is determined according to the keyword of the input information.
In step S104, reply content of the robot is generated based on the user intention and the keyword of the input information.
The method can determine the user intention according to the keywords in the user input information, and in this way, the keywords of the input information are processed without an engineer editing a large number of regular expressions in advance, so that the labor cost is saved. And then generating the reply content of the robot based on the user intention and the keywords, so that the defect that the prior art can only identify the sentence pattern in the grammar template to bring inflexibility can be at least partially solved.
For example, the sentence of voice conversion into text is "from which ox air conditioner i bought to which?", the keyword extracted from "from which ox air conditioner i bought to which?" may be "ox", "air conditioner", "to which", for example, the sentence of voice conversion into text is "how to fill a return delivery"? ", the keyword extracted from" my delivery "?", the keyword extracted from "my delivery.
In some embodiments of the present disclosure, the user intention may be determined according to the extracted keywords. For example, it may be determined from the extracted "oxx", "air conditioner", "where to" that the user of the input information intends to be "commodity order query". For another example, it may be determined that the user of the input information intends to "after-sale consultation of goods" from the extracted "return goods" and "delivery slip number". For another example, it may be determined that the user of the input information intends to be "commodity inquiry" from the extracted "buy", "telecom", "landline". For another example, it may be determined that the user of the input information intends to be "product offer query" according to the extracted "air humidifier" and "offer".
For example, the business scenario of the "fuzzy offer query" may be "most recently discounted merchandise?". The business scenario of the "specific merchandise offer query" may be "whether there is cheap artificial intelligence related book?".
In some embodiments of the present disclosure, the robot may be an intelligent assistant in the kyoto mall, which is a little dong, or may also be another intelligent voice assistant, which is not limited herein.
Fig. 2 schematically shows a flow diagram of a method for handling a robot conversation with a user according to another embodiment of the present disclosure.
If 2, the method includes step S201 and step S202 in addition to step S101 to step S104 described in the embodiment of fig. 1.
In step S201, when the user 'S dialog with the robot is a multi-turn dialog, it is determined whether the user' S intentions of input information adjacent to the user in the multi-turn dialog are the same.
In step S202, if the user intentions of adjacent input information in a plurality of sessions are different, the current intention of the user is determined according to the current input information of the user.
The method can track the user intention in real time by judging whether the user intentions of adjacent input information in multiple rounds of conversation are the same or not, so that the current user intention of the user can be obtained, inaccurate answering content generated by a robot is effectively avoided, and the user experience is improved.
In some embodiments of the present disclosure, when the dialog content between the user and the robot is a multi-turn conversation, for example, the adjacent input information of the user in the multi-turn conversation is "i buy the latest mobile phone in millet" and "i want to buy about 3000 mobile phones", it is determined in real time through the above step S201 whether the user intentions of the adjacent input information of the user in the multi-turn conversation are the same, that is, whether the user intentions of "i buy the latest mobile phone in millet" and "i want to buy about 3000 mobile phones" are the same, and if they are different, the current user intention is determined according to "i want to buy about 3000 mobile phones". Specifically, the keywords in each piece of input information may be determined according to the keywords in the adjacent pieces of input information, and then the corresponding user intention may be determined according to the keywords in each piece of input information, and then the comparison may be performed. If not, the user intention of the currently input information is taken as the true intention of the user at the moment.
Fig. 3 schematically shows a flow chart of a method for handling a robot conversation with a user according to another embodiment of the present disclosure.
If 3, the method includes step S301 and step S302 in addition to step S101 to step S104 described in the embodiment of fig. 1.
In step S301, it is determined whether or not the input information of the user includes a character related to the interrupted session of the robot.
In step S302, if the input information of the user includes a character related to the interrupted session of the robot, the robot is closed.
The method can close the robot by judging whether the input information of the user contains the characters related to the interrupted conversation of the robot, thereby realizing a humanized control mode and being beneficial to saving network resources.
In some embodiments of the present disclosure, when the input information of the user includes a character related to the interruption of the session by the robot, the session is interrupted, and the robot is closed. For example, the user's input information is "i do not want to buy", "i buy a bar later", "this card is out of stock, next time, etc., but not so. In this case, keywords "do not want to buy", "buy again", "stock out", "next time", "come again" are extracted from the above input information, and it is determined whether the keywords are the same as or similar to a preset breaking word, and if the keywords are the same as or similar to the preset breaking word, the robot is turned off.
In some embodiments of the present disclosure, the predetermined interruptive word may be a word with a negative meaning (e.g., not buying, not wanting to buy, etc.), or other words with a similar meaning (e.g., again, next time, etc.).
According to an embodiment of the present disclosure, the determining the user intention according to the keyword of the input information described in the embodiment of fig. 1 may include: analyzing the keywords of the input information by using an LSTM algorithm to obtain the user intention; or analyzing the keywords of the input information by using a Pipeline method to obtain the user intention. Reference may be made in particular to fig. 4 and 5.
Fig. 4 schematically shows a flow chart of a method for handling a robot conversation with a user according to another embodiment of the present disclosure.
If shown in fig. 4, step S102 described in the embodiment of fig. 1 may specifically include step S401.
In step S101, input information of a user is received.
In step S102, a keyword of the input information is determined according to the input information.
In step S401, the LSTM algorithm is used to analyze the keywords of the input information, so as to obtain the user intention.
In step S104, reply content of the robot is generated based on the user intention and the keyword of the input information.
According to the method, the LSTM algorithm is used for analyzing the keywords of the input information to obtain the user intention, then the reply content of the robot is generated based on the user intention and the keywords of the input information, the reply content generated in the mode is closer to the answer desired by the user, and the user experience is further improved.
In some embodiments of the present disclosure, the keywords determined in step S102 may be classified to obtain a category of each keyword. For example, the categories of keywords may be product words, modifiers, brand words, and so forth. And then converting the keywords into word vectors, inputting the categories and the word vectors of the keywords into an LSTM recurrent neural network, and analyzing the categories and the word vectors by using an LSTM algorithm to obtain the user intention of the input information. Specifically, the input information can be analyzed through a WordEmbedding layer of the LSTM recurrent neural network, a GRU structure, a pooling layer and an activation layer of the GRU. For example, wordlebelling layer may convert chinese characters and words input by a user into vectors, GRU structure may convert sentences into vectors, pooling layer and activating layer of GRU may calculate text matching degree scores of current input information and historical input information, and text with the highest score is used as the reply content of the robot.
Fig. 5 schematically shows a flow chart of a method for handling a robot conversation with a user according to another embodiment of the present disclosure.
If shown in fig. 5, step S102 described in the embodiment of fig. 1 may further include step S402.
In step S101, input information of a user is received.
In step S102, a keyword of the input information is determined according to the input information.
In step S402, the keywords of the input information are analyzed by using the method of the PipeLine to obtain the user intention.
In step S104, reply content of the robot is generated based on the user intention and the keyword of the input information.
The method can analyze the keywords of the input information by using a Pipeline method to obtain the user intention, so that the defects caused by identifying the input information of the user by using a dialect template can be overcome.
In some embodiments of the present disclosure, the rule-based method may be constructed before executing the method, and then the Pipeline-based method may be constructed after obtaining a large amount of user input information. The PipeLine-based method may include a natural speech understanding NLU method, a multi-session management method, and a reply content selection method, among others. For example, the method for natural speech understanding NLU may extract keywords from the input information of the user, and the method for multi-turn conversation management may track the user intention of each piece of input information, specifically, confirm the intention of the user according to the keywords of the input information of each user, and determine the true intention of the user. The method of selecting the reply content may screen out a text having a high degree of matching from a preset data table based on the user intention and the keyword.
According to the embodiment of the disclosure, the method further comprises setting a simulated user to have a conversation with the robot, and storing the content of the conversation.
In some embodiments of the present disclosure, a simulated user may be placed in a conversation with the robot through a user simulator, and the content of the conversation may be stored. This may provide more data for constructing a Pipeline-based method, thereby improving the accuracy of determining a user's intent using the Pipeline-based method.
According to an embodiment of the present disclosure, the method further includes deleting characters with negative meanings from the input information, and determining the true intention of the user according to the deleted input information.
In some embodiments of the present disclosure, when a negative meaning character is included in the input information of the user, the negative meaning character may be deleted, and the true intention of the user may be determined from the deleted input information. For example, the input information of the user is "i do not want the iphone7 handset, i want to buy a 7 handset", in which case, a sentence with a word having a negative meaning, i.e., "i do not want the iphone7 handset", needs to be deleted, and then the true intention of the user is determined from the deleted input information (e.g., "i want to buy a 7 handset"), improving the accuracy in confirming the intention of the user.
Fig. 6 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to an embodiment of the present disclosure.
As shown in fig. 6, the apparatus 500 for processing a robot-user session includes a receiving module 510, a first determining module 520, a second determining module 530, and a generating module 540.
The receiving module 510 is configured to receive input information of a user.
The first determining module 520 is configured to determine a keyword of the input information according to the input information.
A second determining module 530, configured to determine the user intention according to the keyword of the input information.
A generating module 510 for generating reply content of the robot based on the user intention and the keyword of the input information.
The device 500 for processing the conversation between the robot and the user can determine the user intention according to the keywords in the input information of the user, and in this way, the keyword processing of the input information does not need an engineer to edit a large number of regular expressions in advance, so that the labor cost is saved. And then generating the reply content of the robot based on the user intention and the keywords, so that the defect that the prior art can only identify the sentence pattern in the grammar template to bring inflexibility can be at least partially solved.
According to an embodiment of the present disclosure, the apparatus 500 for processing a robot conversation with a user may be used to implement the method described in the embodiment of fig. 1.
Fig. 7 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure.
As shown in fig. 7, the apparatus 600 for processing a robot conversation with a user includes a first determining module 610 and a third determining module 620 in addition to the receiving module 510, the first determining module 520, the second determining module 530 and the generating module 540 described in the embodiment of fig. 6.
The first determining module 610 is configured to determine whether the user intentions of the input information adjacent to each other in the multiple sessions of the user are the same.
The third determining module 620 determines the current intention of the user according to the current input information of the user if the user intentions of adjacent input information in multiple sessions are different.
The device 600 for processing the conversation between the robot and the user can track the user intention in real time by judging whether the user intentions of adjacent input information in multiple conversations are the same, so that the current user intention of the user can be obtained, inaccurate response contents generated by the robot are effectively avoided, and the user experience is improved.
According to an embodiment of the present disclosure, the apparatus 600 for processing a robot conversation with a user may be used to implement the method described in the embodiment of fig. 2.
Fig. 8 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure.
As shown in fig. 8, the apparatus 700 for processing a robot conversation with a user includes a second judging module 710 and a closing module 720 in addition to the receiving module 510, the first determining module 520, the second determining module 530 and the generating module 540 described in the embodiment of fig. 6.
A second determining module 710, configured to determine whether the input information of the user includes a character related to the interrupted session of the robot.
And a closing module 720, for closing the robot if the input information of the user includes the character related to the interrupted conversation of the robot.
The device 700 for processing the conversation between the robot and the user can close the robot by judging whether the input information of the user contains the characters related to the interrupted conversation of the robot, thereby realizing a humanized control mode and being beneficial to saving network resources.
According to an embodiment of the present disclosure, the apparatus 700 for processing a robot conversation with a user may be used to implement the method described in the embodiment of fig. 3.
Fig. 9 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure.
As shown in fig. 9, the first determining module 520 described in the embodiment of fig. 6 may specifically include a first analyzing module 521 or a second analyzing module 522.
The first analysis module 521 analyzes the keywords of the input information by using an LSTM algorithm to obtain the user intention.
The second analysis module 522 analyzes the keywords of the input information by using a PipeLine method to obtain the user intention.
According to the embodiment of the present disclosure, the first analysis module 521 or the second analysis module 522 may be used to implement the method described in the embodiment of fig. 4 or fig. 5.
Fig. 10 schematically shows a block diagram of an apparatus for handling a robot conversation with a user according to another embodiment of the present disclosure.
As shown in fig. 10, the apparatus 800 for processing a robot conversation with a user includes a setting module 810 and a deleting module 820, in addition to the receiving module 510, the first determining module 520, the second determining module 530, and the generating module 540 described in the embodiment of fig. 6.
And the setting module 810 is used for setting a conversation between a simulation user and the robot and storing the content of the conversation.
A deleting module 820, configured to delete the character with the negative meaning from the input information, and determine the true intention of the user according to the deleted input information.
It is understood that the receiving module 510, the first determining module 520, the first analyzing module 521, the second analyzing module 522, the second determining module 530, the generating module 540, the first judging module 610, the third determining module 620, the second judging module 710, the closing module 720, the setting module 810, and the deleting module 820 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the receiving module 510, the first determining module 520, the first analyzing module 521, the second analyzing module 522, the second determining module 530, the generating module 540, the first determining module 610, the third determining module 620, the second determining module 710, the closing module 720, the setting module 810, and the deleting module 820 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, or as a suitable combination of three implementations of software, hardware, and firmware. Alternatively, at least one of the receiving module 510, the first determining module 520, the first analyzing module 521, the second analyzing module 522, the second determining module 530, the generating module 540, the first judging module 610, the third determining module 620, the second judging module 710, the closing module 720, the setting module 810, and the deleting module 820 may be at least partially implemented as a computer program module, which may perform the functions of the respective modules when the program is executed by a computer.
Fig. 11 schematically shows a block diagram of a computer system for handling a robot conversation with a user according to an embodiment of the present disclosure. The computer system illustrated in FIG. 11 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.
As shown in fig. 11, a computer system 900 for processing a robot-user session according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. Processor 901 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 901 may also include on-board memory for caching purposes. The processor 901 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure described with reference to fig. 1-5.
In the RAM 903, various programs and data necessary for the operation of the system 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The processor 901 performs the various steps for handling the robot and user session described above with reference to fig. 1-5 by executing programs in the ROM 902 and/or RAM 903. Note that the program may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform the various steps described above with reference to fig. 1-5 for handling the robot and user session by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, the method described above with reference to the flow chart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program, when executed by the processor 901, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
It should be noted that the computer readable media shown in the present disclosure may be computer readable signal media or computer readable storage media or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing. According to embodiments of the present disclosure, a computer-readable medium may include the ROM 902 and/or the RAM 903 described above and/or one or more memories other than the ROM 902 and the RAM 903.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As another aspect, the present disclosure also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to perform a method for handling a robot conversation with a user according to an embodiment of the disclosure. The method comprises the following steps: receiving input information of a user; determining a keyword of the input information according to the input information; determining the user intention according to the keywords of the input information; generating reply content of the robot based on the user intention and the keyword of the input information.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (16)
1. A method for handling a robot-user session, comprising:
receiving input information of a user;
determining a keyword of the input information according to the input information;
determining the user intention according to the keywords of the input information;
generating reply content of the robot based on the user intention and the keyword of the input information.
2. The method of claim 1, wherein when the user's dialog with the robot is a multi-turn conversation, the method further comprises:
judging whether the user intentions of the adjacent input information of the users in the multi-turn conversation are the same or not;
and if the current input information is different from the current input information of the user, determining the current intention of the user.
3. The method of claim 1, further comprising:
judging whether the input information of the user contains characters related to the interrupted conversation of the robot;
if so, the robot is shut down.
4. The method of claim 1, wherein determining the user intent from the keywords of the input information comprises:
analyzing the keywords of the input information by using an LSTM algorithm to obtain the user intention; or
And analyzing the keywords of the input information by using a Pipeline method to obtain the user intention.
5. The method of claim 1, further comprising:
setting a simulated user conversation with the robot, and storing the conversation content.
6. The method of claim 1, wherein when the input information includes a negative meaning character, the method further comprises:
characters with negative meanings are deleted from the input information, and the true intention of the user is determined according to the deleted input information.
7. The method of claim 1, wherein the user intent comprises any of: commodity inquiry, commodity preference inquiry, commodity after-sale consultation and commodity order inquiry.
8. An apparatus for handling a robot-user session, comprising:
the receiving module is used for receiving input information of a user;
the first determining module is used for determining keywords of the input information according to the input information;
the second determining module is used for determining the user intention according to the key words of the input information;
and the generating module is used for generating the reply content of the robot based on the user intention and the keywords of the input information.
9. The apparatus of claim 8, wherein when the user's dialog with the robot is a multi-turn conversation, the apparatus further comprises:
the first judgment module is used for judging whether the user intentions of the adjacent input information of the users in the multi-turn conversation are the same or not;
and the third determining module is used for determining the current intention of the user according to the current input information of the user if the current intention is different from the current intention of the user.
10. The apparatus of claim 8, further comprising:
the second judgment module is used for judging whether the input information of the user contains characters related to the interrupted conversation of the robot;
a shutdown module to shutdown the robot if included.
11. The apparatus of claim 8, wherein the first determining means comprises:
the first analysis module is used for analyzing the keywords of the input information by using an LSTM algorithm to obtain the user intention; or
And the second analysis module analyzes the keywords of the input information by using a Pipeline method to obtain the user intention.
12. The apparatus of claim 8, further comprising:
and the setting module is used for setting a conversation between a simulation user and the robot and storing the content of the conversation.
13. The apparatus of claim 8, wherein when the input information contains a negative-meaning character, the apparatus further comprises:
and the deleting module is used for deleting the characters with negative meanings from the input information and determining the true intention of the user according to the deleted input information.
14. The apparatus of claim 8, wherein the user intent comprises any of: commodity inquiry, commodity preference inquiry, commodity after-sale consultation and commodity order inquiry.
15. An apparatus for handling a robot-user session, comprising:
one or more processors; and
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-7.
16. A computer readable medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554432.5A CN110633358A (en) | 2018-05-31 | 2018-05-31 | Method, apparatus and medium for processing robot and user session |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554432.5A CN110633358A (en) | 2018-05-31 | 2018-05-31 | Method, apparatus and medium for processing robot and user session |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110633358A true CN110633358A (en) | 2019-12-31 |
Family
ID=68966166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810554432.5A Pending CN110633358A (en) | 2018-05-31 | 2018-05-31 | Method, apparatus and medium for processing robot and user session |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110633358A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208556A1 (en) * | 2006-03-03 | 2007-09-06 | Samsung Electronics Co., Ltd. | Apparatus for providing voice dialogue service and method of operating the same |
| CN106095834A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on topic |
| CN107193865A (en) * | 2017-04-06 | 2017-09-22 | 上海奔影网络科技有限公司 | Natural language is intended to understanding method and device in man-machine interaction |
| CN107193978A (en) * | 2017-05-26 | 2017-09-22 | 武汉泰迪智慧科技有限公司 | A kind of many wheel automatic chatting dialogue methods and system based on deep learning |
| CN107798032A (en) * | 2017-02-17 | 2018-03-13 | 平安科技（深圳）有限公司 | Response message treating method and apparatus in self-assisted voice session |
-
2018
- 2018-05-31 CN CN201810554432.5A patent/CN110633358A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208556A1 (en) * | 2006-03-03 | 2007-09-06 | Samsung Electronics Co., Ltd. | Apparatus for providing voice dialogue service and method of operating the same |
| CN106095834A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Intelligent dialogue method and system based on topic |
| CN107798032A (en) * | 2017-02-17 | 2018-03-13 | 平安科技（深圳）有限公司 | Response message treating method and apparatus in self-assisted voice session |
| CN107193865A (en) * | 2017-04-06 | 2017-09-22 | 上海奔影网络科技有限公司 | Natural language is intended to understanding method and device in man-machine interaction |
| CN107193978A (en) * | 2017-05-26 | 2017-09-22 | 武汉泰迪智慧科技有限公司 | A kind of many wheel automatic chatting dialogue methods and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102204740B1 (en) | Method and system for processing unclear intention query in conversation system | |
| CN108877782B (en) | Speech recognition method and device | |
| RU2708941C1 (en) | Method and apparatus for recognizing segmented sentences for a human-machine intelligent question-answer system | |
| CN111212190B (en) | Conversation management method, device and system based on conversation strategy management | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| CN111144128A (en) | Semantic parsing method and device | |
| US11176466B2 (en) | Enhanced conversational bots processing | |
| KR102170088B1 (en) | Method and system for auto response based on artificial intelligence | |
| CN111339309B (en) | Corpus expansion method and system for user intention | |
| CN111508478B (en) | Speech recognition method and device | |
| CN112541068A (en) | Method, system, device and storage medium for recognizing intention of voice conversation | |
| CN115658875B (en) | Data processing method based on chat service and related products | |
| CN113051381B (en) | Information quality inspection method, information quality inspection device, computer system and computer readable storage medium | |
| CN112784024B (en) | Man-machine conversation method, device, equipment and storage medium | |
| CN110633358A (en) | Method, apparatus and medium for processing robot and user session | |
| CN114860910A (en) | Intelligent dialogue method and system | |
| CN114722171A (en) | Multi-turn conversation processing method and device, electronic equipment and storage medium | |
| CN116724306A (en) | Multi-feature balancing for natural language processors | |
| US10559298B2 (en) | Discussion model generation system and method | |
| CN112837159A (en) | Transaction guiding method and device based on scene elements, electronic equipment and medium | |
| CN112307162A (en) | Method and device for information interaction | |
| CN112002325B (en) | Multi-language voice interaction method and device | |
| KR102448733B1 (en) | Dialog system for response selecting considering turn configuration in context and the method thereof | |
| CN112711654B (en) | Chinese character interpretation technique generation method, system, equipment and medium for voice robot | |
| CN113241061B (en) | Method and device for processing voice recognition result, 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 |