CN111581362A - Processing method and device - Google Patents

Processing method and device Download PDF

Info

Publication number
CN111581362A
CN111581362A CN202010354651.6A CN202010354651A CN111581362A CN 111581362 A CN111581362 A CN 111581362A CN 202010354651 A CN202010354651 A CN 202010354651A CN 111581362 A CN111581362 A CN 111581362A
Authority
CN
China
Prior art keywords
language
conversation
content
session
interaction
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
Application number
CN202010354651.6A
Other languages
Chinese (zh)
Inventor
邢运
胡长建
刘欣然
温子玥
陈静萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lenovo Beijing Ltd
Original Assignee
Lenovo Beijing Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN202010354651.6A priority Critical patent/CN111581362A/en
Publication of CN111581362A publication Critical patent/CN111581362A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Human Computer Interaction (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Machine Translation (AREA)

Abstract

The application provides a processing method and a processing device, wherein a conversation interaction system in the method obtains first conversation content input by a user, determines a first language set by the conversation interaction system for conversation interaction, determines whether the first conversation content meets a first set condition to reply by determining whether the first conversation content meets the first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, namely a language different from the first language, and maintains the language used by the conversation interaction system for conversation interaction as the first language if the first conversation content meets the first set condition, so that the accuracy of language switching is improved, and the fluency of conversation is improved.

Description

Processing method and device
Technical Field
The present application belongs to the field of intelligent conversation technologies, and in particular, to a processing method and apparatus.
Background
In the current intelligent dialogue system, in order to solve the problem proposed by the user, the intelligent dialogue system performs language detection on the information input by the user each time, and replies with the detected language.
However, in an actual dialog scenario, due to the habit of the user or other reasons, there may be a case where the user uses different languages to communicate with the intelligent dialog system in the same dialog, and if the above scheme is continued, unnecessary or wrong language switching may occur, which affects the fluency of the dialog.
Disclosure of Invention
In view of the above, the present application provides a processing method and apparatus.
Therefore, the application discloses the following technical scheme:
a method of processing, comprising:
the conversation interactive system obtains first conversation content input by a user;
determining a first language set by the conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by the user before the first conversation content;
determining whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, wherein the second language is different from the first language;
and if the first conversation content meets the first set condition, maintaining the language used by the conversation interaction system for conversation interaction as the first language.
Further comprising:
acquiring target information;
determining whether the first session content meets a second set condition based on the first session content and the target information;
and if the first session content meets a second set condition, changing the language used for session interaction by the session interaction system.
The changing the language used by the conversation interaction system for conversation interaction comprises the following steps:
the conversation interactive system outputs conversation contents in a third language in at least one subsequent conversation; or
Switching the language used by the conversational interaction system for conversational interaction from the first language to a third language;
wherein the third language is different from the first language.
The target information comprises at least one piece of fourth session content, and the fourth session content is the session content input by the user before the first session content;
the determining whether the first session content meets a second set condition based on the first session content and the target information includes:
determining whether the fourth session content satisfies the first set condition.
At least one of the fourth session content and the first session content are arranged in series.
The target information includes:
based on the first session content, obtaining information;
the information includes: the location information corresponding to at least a part of information in the first session content, and/or the user attribute information of the user associated with the first session content.
Before determining whether the first session content satisfies a first set condition, the method further includes:
analyzing the first conversation content and determining the grade of the first conversation content; the level of the first session content is used for representing the requirement degree of whether language switching is needed or not;
the determining whether the first session content meets a first set condition includes:
it is determined whether the level of the first session content is a first set level.
The method further comprises the following steps: if the level of the first session content is determined to be a second set level, the session interactive system outputs the session content in a third language in at least one subsequent session; the requirement degree corresponding to the second setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
The method further comprises the following steps: if the level of the first session content is determined to be a third set level, the session interaction system switches the language used for session interaction from the first language to a third language; the requirement degree corresponding to the third setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
A processing apparatus, comprising:
the user input content acquisition module is used for acquiring first session content input by a user;
the language identification module is used for determining a first language set by a conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by the user before the first conversation content;
the detection module is used for detecting whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, wherein the second language is different from the first language;
and the control module is used for maintaining the voice used for conversation interaction by the conversation interaction system as the first language if the first conversation content meets the first set condition.
According to the scheme, the conversation interaction system obtains the first conversation content input by the user, determines the first language set by the conversation interaction system for conversation interaction, determines which language is adopted for replying by determining whether the first conversation content meets the first set condition or not under the condition that the language adopted by the first conversation content at least comprises the second language, namely the language different from the first language, and if the first conversation content meets the first set condition, maintains the language used by the conversation interaction system for conversation interaction as the first language, so that the accuracy of language switching is improved, and the fluency of conversation is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of example 1 of a treatment method provided herein;
FIG. 2 is a schematic flow chart of example 2 of a processing method provided by the present application;
FIG. 3 is a schematic flow chart of embodiment 3 of a processing method provided by the present application;
FIG. 4 is a schematic flow chart of embodiment 4 of a processing method provided by the present application;
FIG. 5 is a schematic flow chart of example 5 of a processing method provided herein;
FIG. 6 is a schematic flow chart of example 6 of a processing method provided by the present application;
FIG. 7 is a schematic flow chart of example 6 of a processing method provided by the present application;
fig. 8 is a schematic structural diagram of an electronic device embodiment 1 provided in the present application;
fig. 9 is a schematic logical structure diagram of a processing device provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, there is a schematic flow chart of a processing method provided in embodiment 1 of the present application, the method may be applied to an electronic device, and the product type of the electronic device is not limited in the present application, as shown in fig. 1, the method may include, but is not limited to, the following steps:
step S101, the conversation interactive system obtains first conversation content input by a user.
The conversational interactive system may be understood as: based on machine algorithm (such as intelligent algorithm like machine learning, deep learning, etc.), the system can understand the intention of the user to input the content and the adopted language, and communicate with the user. In this embodiment, the application scenario of the session interaction system is not limited. For example, the session interaction system may be applied to an internet webpage, a conversation function of a robot, or a man-machine conversation function of a terminal (e.g., a mobile phone, a sound box, etc.), etc.
When the user inputs the first session content to the session interaction system, the session interaction system can obtain the first session content input by the user in real time.
And S102, determining that the conversation interaction system sets a first language for conversation interaction.
In this embodiment, the first language is set by the session interaction system before the user inputs the first session content.
The conversation interaction system can set a first language for conversation interaction based on a language adopted by a piece of second conversation content, wherein the second conversation content is the conversation content input by the user before the first conversation content. Specifically, a piece of second session content may be analyzed to obtain an analysis result, and the first language used for the session interaction is set based on the analysis result and the language used by the second session content. For example, if the language currently used by the session interaction system is chinese and the language used by the second session content input by the user is english, in this case, the session interaction system may analyze the second session content, and if it is analyzed that the user supports multiple languages, such as chinese and english, the first language used by the session interaction system for session interaction may be set to chinese or english; if the analysis shows that the user only supports Chinese, the first language applied to the conversation interaction by the conversation interaction system can be set to be still Chinese.
Of course, the conversation interaction system may also set the first language for conversation interaction based on the language adopted by the plurality of pieces of second conversation content.
Specifically, the first language for the conversation interaction may be set based only on the languages adopted for the plurality of pieces of second conversation content. For example, if the language currently used by the conversational interaction system is chinese, the languages used for acquiring the 3 pieces of second conversational content input by the user are chinese, and english, respectively, and by determining that the proportion of the second conversational content in chinese is greater than that in english, chinese may be set as the first language used for conversational interaction.
Alternatively, the first language for the session interaction may be set based on the language used by the plurality of pieces of second session content and the result obtained by analyzing the plurality of pieces of second session content. For example, if the language currently used by the conversational interaction system is english, the language used for acquiring 3 pieces of second conversational content input by the user is english, chinese, and if a plurality of pieces of second conversational content are analyzed to determine that the language supported by the user includes chinese and english, the conversational interaction system may maintain english and set english as the first language used for conversational interaction, although the ratio of the second conversational content in chinese is greater than the ratio of the second conversational content in english. Of course, the conversational interaction system may change the currently used language and set chinese as the first language for conversational interaction after determining that the languages supported by the user include chinese and english, and the ratio of the second conversational content in chinese is greater than the ratio of the second conversational content in english.
Step S103, determining whether the first session content satisfies a first setting condition when the language adopted by the first session content at least includes a second language, where the second language is different from the first language.
In this embodiment, after the first session content input by the user is obtained, the language adopted by the first session content is identified. In this embodiment, the language used by the first session content may be identified based on a language identification model. Specifically, the first session content is input into the language identification model to obtain the language output by the language identification model, and the language output by the language identification model is used as the language adopted by the first session content.
The language identification model may be composed of an information extraction model and a text classification model. In the case that the language identification model is composed of an information extraction model and a text classification model, identifying the language used by the first session content may include: inputting the first session content into an information extraction model; and if the information extraction model outputs the entity information, the auxiliary text classification model performs language classification on the first session content based on the entity information output by the information extraction model.
The auxiliary text classification model performs language classification on the first session content based on the entity information output by the information extraction model, and may include:
and carrying out normalization processing on the entity information output by the information extraction model, and combining the entity information after the normalization processing to assist the text classification model in carrying out language classification on the first conversation content.
The entity information output by the information extraction model is normalized, so that the characteristic space can be optimized, and the difficulty of user intention analysis is reduced.
In this embodiment, based on the entity information output by the information extraction model, the auxiliary text classification model performs language classification on the first session content, which may include but is not limited to:
inputting the first session content into a text classification model to obtain a language output by the text classification model, and if the information extraction model outputs entity information, confirming or updating the language output by the text classification model in combination with the entity information;
or inputting the entity information and the first session content output by the information extraction model into the text classification model to obtain the language output by the text classification model.
The information extraction model in this embodiment may be, but is not limited to: CRF or RNN + CRF, etc. The text classification model may be, but is not limited to: rule-based SVM, CNN or RNN, etc.
And if the language adopted by the first conversation content at least comprises a second language different from the first language, determining whether the first conversation content meets a first set condition.
The first setting condition may be understood as: and setting conditions based on the conversation scene that the language used by the conversation interaction system for conversation interaction needs to be maintained as the first language.
If the first session content satisfies the first setting condition, step S104 is executed.
And step S104, maintaining the language used for conversation interaction by the conversation interaction system as a first language.
On the basis of maintaining the language used by the conversation interaction system for conversation interaction as the first language, the conversation interaction system can continue to output the conversation content in the first language and reply to the first conversation content input by the user.
The conversation interactive system obtains first conversation content input by a user, determines a first language set by the conversation interactive system for conversation interaction, determines which language is adopted for replying by determining whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, namely a language different from the first language, and maintains the language used by the conversation interactive system for conversation interaction as the first language if the first conversation content meets the first set condition, so that the accuracy of language switching is improved, and the fluency of conversation is improved.
As another alternative embodiment of the present application, referring to fig. 2, a flowchart of an embodiment 2 of a control method provided by the present application is shown, where this embodiment mainly relates to a refinement of the control method described in the above embodiment 1, as shown in fig. 2, the method may include, but is not limited to, the following steps:
step S201, the session interaction system obtains the first session content input by the user.
Step S202, determining that the conversation interaction system sets a first language for conversation interaction.
The first language is set based on the language adopted by at least one piece of second conversation content, and the second conversation content is the conversation content input by the user before the first conversation content.
The detailed processes of steps S201 to S202 can be referred to the related descriptions of steps S101 to S102 in embodiment 1, and are not described herein again.
Step S203, under the condition that the language adopted by the first conversation content at least comprises a second language, analyzing the first conversation content and determining the grade of the first conversation content; wherein the level of the first session content is used to characterize the degree of need for language switching.
In this embodiment, analyzing the first session content, and determining the level of the first session content may include:
s2031, analyzing the first conversation content to obtain at least one first language influence factor.
In this embodiment, analyzing the first session content to obtain at least one first language impact factor may include:
and analyzing the user intention in the first session content, and taking the user intention information as a first language influence factor when analyzing the user intention information.
The user intent may be understood as: the user wants to achieve the real purpose when interacting with the conversation interactive system. Such as: if the first conversation content input by the user is: i want to repair my phone. The corresponding user intent is then: and (5) requesting for maintenance.
In this embodiment, the user intention analysis model may be trained in advance, and the trained user intention analysis model may be used to analyze the user intention of the session content.
The user intention parsing model may be composed of an information extraction model and a text classification model. In the case that the user intention analysis model is composed of an information extraction model and a text classification model, analyzing the user intention of the first session content may include: inputting the first session content into an information extraction model; and if the information extraction model outputs the entity information, the auxiliary text classification model classifies the user intention of the first session content based on the entity information output by the information extraction model.
The auxiliary text classification model classifies the user intention of the first session content based on the entity information output by the information extraction model, and may include:
and normalizing the entity information output by the information extraction model, and classifying the user intention of the first session content by combining the normalized entity information and the auxiliary text classification model.
The entity information output by the information extraction model is normalized, so that the characteristic space can be optimized, and the difficulty of user intention analysis is reduced.
The auxiliary text classification model classifies the user's intention of the first session content based on the entity information output by the information extraction model, which may include but is not limited to:
inputting the first session content into a text classification model to obtain user intention information output by the text classification model, and if the information extraction model outputs entity information, confirming or updating the user intention information output by the text classification model in combination with the entity information;
or inputting the entity information and the first session content output by the information extraction model into the text classification model to obtain the user intention information output by the text classification model.
The information extraction model in this embodiment may be, but is not limited to: CRF, RNN + CRF, and the like. The text classification model may be, but is not limited to: rule-based SVM, CNN or RNN, etc.
The training process of the user intention analysis model may include: acquiring user input information marked with a label, wherein the label at least comprises: a user-intended discrete information tag (e.g., { maintenance request, logistics problem … });
and training the user intention analysis model by using the user input information marked with the label.
The label output by the trained user intention analysis model can be used as user intention information.
Of course, the process of training the user intention analysis model may also include: acquiring user input information marked with a label, wherein the label at least comprises: user-intended discrete information tags (e.g., { maintenance request, logistics problem … }), entity information (e.g., product name, accessory name …), and language discrete information tags (e.g., { English, Chinese, portuguese … });
and training the user intention analysis model by using the user input information marked with the label.
The trained user intent parsing model may output a plurality of labels, wherein the output user intent labels may serve as the user intent information.
In this embodiment, analyzing the first session content to obtain at least one first language influence factor may also include:
and acquiring user attribute information associated with the first session content, and taking the acquired user attribute information as a first language influence factor.
The user attribute information may include, but is not limited to: user portrait information. The portrait information of the user can be understood as multi-dimensional information of the user, such as age, gender, nationality and hobbies. In special business scenarios, user profile information may include: information of a particular dimension, such as purchase records, purchase trends, etc.
In this embodiment, analyzing the first session content to obtain at least one first language influence factor may also include:
analyzing the first conversation content, determining the question to be solved, and taking the language supported by the answer corresponding to the question to be solved in the conversation interactive system as a first language influence factor.
Based on the first conversation, the extracted switching inquiry context comprises a language switching inquiry statement output by the conversation interactive system and a reply statement input to the conversation interactive system and aiming at the language switching inquiry statement.
In this embodiment, analyzing the first session content to obtain at least one first language influence factor may also include:
and analyzing the first conversation content, determining the language characteristic of the language adopted by the first conversation content, and taking the language characteristic as a first language influence factor.
The language features may include: whether the language or language expression is common across different regions. For example, "Ok" represents "good" in many languages; "Ciao" is Italian, meaning "hello" or "goodbye", a common expression in Europe in many countries; "Coucou" is the cry of cuckoo, a way to call out among friends in French.
S2032, determining the grade of the first conversation content based on at least one first language influence factor, wherein the grade of the first conversation content is used for representing the requirement degree whether language switching is needed or not.
In this embodiment, determining the level of the first session content based on the at least one first language impact factor may include: determining a rating of the first session content based on a first language impact factor; alternatively, the ranking of the first session content is determined based on a plurality of first language impact factors.
The process of determining a rating of the first session content based on a first language impact factor may include:
s3211, determining a threshold range to which the value of the first language influence factor representing the language influence degree belongs.
After the first language influence factor is obtained, the language influence degree represented by the first language influence factor can be determined, and the language influence degree represented by the first language influence factor is quantized to obtain a value of the language influence degree represented by the first language influence factor.
S3212, if the threshold range to which the value of the first language influence factor representing the degree of language influence belongs is the first threshold range, determining the level of the first session content to be the first set level.
The first threshold range may be determined by a first degree of demand characterized by a first language impact factor that does not require language switching.
S3213, if the threshold range to which the value of the first language influence factor representing the degree of language influence belongs is a second threshold range, determining the level of the first session content to be a second set level.
The second threshold range may be determined by a second degree of demand characterized by the first language impact factor requiring the conversational interaction system not to switch language contexts, but to output conversational content in a different language in at least one subsequent conversation. Wherein the second demand level is higher than the first demand level. Accordingly, the degree of demand corresponding to the second setting level is higher than the degree of demand corresponding to the first setting level.
S3214, if the threshold range to which the value of the first language influence factor representing the degree of language influence belongs is a third threshold range, determining that the level of the first session content is a third set level.
The third threshold range may be determined by a third degree of need for the conversational interaction system to switch language environments (i.e., switch languages for conversational interaction) characterized by the first language impact factor. Wherein the third demand level is higher than the second demand level. Accordingly, the degree of demand corresponding to the third setting level is higher than the degree of demand corresponding to the second setting level.
The process of determining a rating of the first session content based on the plurality of first language impact factors may include:
s3221, the values of the language influence degrees represented by the first language influence factors are determined to be added, and the obtained values belong to the threshold range.
After the first language influence factor is obtained, the language influence degree represented by the first language influence factor can be determined, and the language influence degree represented by the first language influence factor is quantized to obtain a value of the language influence degree represented by the first language influence factor.
S3222, if the threshold range to which the sum of the values representing the language influence degrees of the first language influence factors belongs is the first threshold range, determining that the level of the first session content is the first set level.
The first threshold range is determined by a first degree of need, characterized by a first language impact factor, for whether a language switch is required.
S3223, if the threshold range to which the obtained value represents the language influence degree is obtained by adding the values of the first language influence factors, and the threshold range is the second threshold range, determining the level of the first session content to be the second set level.
The second threshold range may be determined by a second degree of demand characterized by the first language impact factor requiring the conversational interaction system not to switch language contexts, but to output conversational content in a different language in at least one subsequent conversation. Wherein the second demand level is higher than the first demand level. Accordingly, the degree of demand corresponding to the second setting level is higher than the degree of demand corresponding to the first setting level.
S3224, if the threshold range to which the obtained value represents the language influence degree is obtained by adding the values of the first language influence factors, and the threshold range is a third threshold range, determining the level of the first session content to be a third set level.
The third threshold range may be determined by a third degree of need for the conversational interaction system to switch language environments (i.e., switch languages for conversational interaction) characterized by the first language impact factor. Wherein the third demand level is higher than the second demand level. Accordingly, the degree of demand corresponding to the third setting level is higher than the degree of demand corresponding to the second setting level.
Step S204, determining whether the level of the first session content is a first set level.
If the level of the first session content is the first set level, it indicates that the conversational interactive system does not need to perform language switching, so step S205 may be performed.
Steps S203 to S204 are a specific implementation of step S103 in example 1.
Step S205, the language used by the conversation interaction system for conversation interaction is maintained as the first language.
In this embodiment, the steps S201 to S205 are described as an example, for example, if the first language adopted by the session interaction system is chinese, for example: the content output by the conversation interaction system is as follows: please indicate the operation as follows: ..., the first session content input by the user is: and Ok. The conversational interaction system may determine that the language in which the first conversational content is in english (i.e., the second language), in which case, analyze the pair of first conversational content, determine that the level of the first conversational content is a first set level, and maintain the language used by the conversational interaction system for conversational interaction in the first language.
The detailed process of step S205 can refer to the related description of step S104 in embodiment 1, and is not described herein again.
In this embodiment, the conversation interaction system obtains a first conversation content input by a user, determines a first language set by the conversation interaction system for conversation interaction, analyzes the first conversation content when the language adopted by the first conversation content at least includes a second language, that is, a language different from the first language, determines a level of the first conversation content, determines whether the level of the first conversation content is the first set level to determine which language is adopted for replying, and maintains the language used by the conversation interaction system for conversation interaction as the first language if the first conversation content meets the first set level, thereby improving accuracy of language switching and fluency of conversation.
As another alternative embodiment of the present application, referring to fig. 3, a flowchart of an embodiment 3 of a control method provided by the present application is shown, where this embodiment is mainly an extension of the control method described in the above embodiment 2, and as shown in fig. 3, the method may include, but is not limited to, the following steps:
step S301, the conversation interaction system obtains the first conversation content input by the user.
Step S302, determining a first language set by the conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by a user before the first conversation content.
Step S303, analyzing the first session content to determine the level of the first session content when the language adopted by the first session content at least includes the second language.
The level of the first conversation content is used for representing the requirement degree of whether language switching is needed or not, and the second language is different from the first language.
Step S304, determining whether the level of the first session content is a first set level.
If the level of the first session content is the first set level, go to step S305; if the level of the first session content is not the first set level, step S306 is executed.
Step S305, the language used by the conversation interaction system for conversation interaction is maintained as a first language.
The detailed processes of steps S301 to S305 can refer to the related descriptions of steps S201 to S205 in embodiment 2, and are not described herein again.
Step S306, determining whether the level of the first session content is a second set level.
If the level of the first session content is the second set level, step S307 is executed.
Step S307, the conversation interactive system outputs the conversation content in a third language in at least one subsequent conversation.
The requirement degree corresponding to the second setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
If it is determined in step S306 that the level of the first session content is the second set level, the session interaction system does not switch the language environment, but outputs the session content in a language different from the first language in at least one subsequent session.
In this embodiment, the conversation interaction system may determine to output the conversation content in the third language based on the first language influence factor.
The third language may be different from the second language, for example, if the first language adopted by the conversation interaction system is chinese, for example: the content output by the conversation interaction system is as follows: please set up as follows: setting- > fingerprint unlocking- > opening fingerprint unlocking, and correspondingly, the first session content input by the user is as follows: is is a Spanish system, while do you say in Spanish in the same stages? . The conversational interaction system may determine that the language in which the first conversational content is in english (i.e., the second language), in which case, analyzing the first conversational content pair results in the user intent (i.e., the first language impact factor) being: the user needs to translate the contents output from the conversation interaction system into spanish, and based on the user's intention, the level of the first conversation contents may be determined to be the second set level, and further spanish may be determined to be the third language.
Of course, the third language may also be the same as the second language, for example, if the first language adopted by the conversational interaction system is chinese, for example, the output content of the conversational interaction system is: please set up as follows: setting- > fingerprint unlocking- > opening fingerprint unlocking, and correspondingly, the first session content input by the user is as follows: this is a system of English? . The conversational interaction system may determine that the language in which the first conversational content is in english (i.e., the second language), in which case, analyzing the first conversational content pair results in the user intent (i.e., the first language impact factor) being: the user needs to translate the contents outputted from the session interactive system into english, and based on the user's intention, the level of the first session contents may be determined as the second set level, and further, english may be determined as the third language.
Before the session interactive system outputs the session content in the third language in at least one subsequent session, the session interactive system may determine whether to actively inquire the user according to an actual situation, and if it is determined that the inquiry is possible, may actively inquire whether the user agrees to output the session content in the third language, and if the user agrees, the session interactive system outputs the session content in the third language in at least one subsequent session.
In this embodiment, when the level of the first session content is not the first set level, the level of the first session content is further determined to be the second set level, and the level of the first session content is determined multiple times, so as to ensure reliability of whether the session interaction system performs language switching.
As another alternative embodiment of the present application, referring to fig. 4, a flowchart of an embodiment 4 of a control method provided by the present application is shown, where this embodiment is mainly an extension of the control method described in the foregoing embodiment 2, and as shown in fig. 4, the method may include, but is not limited to, the following steps:
step S401, the conversation interaction system obtains the first conversation content input by the user.
Step S402, determining a first language set by the conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by a user before the first conversation content.
Step S403, analyzing the first session content and determining the level of the first session content when the language adopted by the first session content at least includes the second language.
The level of the first conversation content is used for representing the requirement degree of whether language switching is needed or not, and the second language is different from the first language.
Step S404, determining whether the level of the first session content is a first set level.
If the level of the first session content is the first set level, go to step S405; if the level of the first session content is not the first set level, step S406 is executed.
Step S405, the language used by the conversation interaction system for conversation interaction is maintained as a first language.
The detailed processes of steps S401 to S405 can be referred to the related descriptions of steps S201 to S205 in embodiment 2, and are not described herein again.
Step S406, determining whether the level of the first session content is a third set level.
If the level of the first session content is the third set level, step S407 is executed.
Step S407, the conversation interaction system switches the language used for conversation interaction from the first language to the third language.
The requirement degree corresponding to the third setting level is higher than that corresponding to the first setting level, and the third language is different from the first language.
In step S406, when determining that the level of the first session content is the third set level, the conversational interaction system may switch the language environment, and specifically, may switch the language used for conversational interaction from the first language to the third language.
In this embodiment, the conversation interaction system may determine to output the conversation content in the third language based on the first language influence factor.
The third language may be different from the second language, for example, if the first language adopted by the conversation interaction system is chinese, the first conversation content input by the user is: do you spread span, then it can be determined that the language used by the first session content is english (i.e. the second language), in this case, the first session content pair is analyzed to obtain the user intention (i.e. the first language influence factor) as: it is desirable that the conversation interaction system adopts spanish language, and based on the user intention, the level of the first conversation contents may be determined to be a third set level, and further spanish language may be determined to be a third language.
Of course, the third language may also be the same as the second language, for example, if the first language adopted by the conversation interaction system is chinese, the first conversation content input by the user is: do you spread English, then can determine that the language used by the first session content is English (i.e. the second language), in this case, the first session content pair is analyzed to obtain the user intention (i.e. the first language influence factor) as: it is desirable that the conversation interactive system adopts english, and based on the user intention, the level of the first conversation content can be determined as the third set level, and further, english can be determined as the third language.
Before the conversational interaction system switches the language used for conversational interaction from the first language to the third language, the conversational interaction system may determine whether to actively ask the user whether to approve switching the language according to an actual situation, actively ask the user whether to approve switching to the third language when determining the inquiry, and switch the language used for conversational interaction from the first language to the third language if the user approves.
In this embodiment, when the level of the first session content is not the first set level, the level of the first session content is further determined to be the third set level, and the level of the first session content is determined multiple times, so as to ensure reliability of whether the session interaction system performs language switching.
As another alternative embodiment of the present application, referring to fig. 5, a flowchart of an embodiment 5 of a control method provided by the present application is shown, where this embodiment is mainly an extension of the control method described in the above embodiment 1, and as shown in fig. 5, the method may include, but is not limited to, the following steps:
step S501, the session interaction system obtains the first session content input by the user.
Step S502, determining a first language set by the conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by a user before the first conversation content.
Step S503, in a case that the language adopted by the first session content at least includes a second language, determining whether the first session content satisfies a first setting condition, where the second language is different from the first language.
If the first session content satisfies the first setting condition, step S504 is executed.
The detailed processes of steps S501 to S503 can refer to the related descriptions of steps S101 to S103 in embodiment 1, and are not described herein again.
And step S504, acquiring target information.
The target information may be understood as: information different from the first session content.
In the case where the first session content does not satisfy the first setting condition, information different from the first session content may be acquired as the target information.
And step S505, determining whether the first conversation content meets a second set condition based on the first conversation content and the target information.
The second setting condition may be understood as: and setting conditions based on the conversation scene of the language of the conversation interaction of the user of the conversation interaction system needing to be changed.
Determining whether the first session content satisfies a second set condition based on the first session content and the target information may include, but is not limited to: it is determined whether the language in which the first session content is in is the same as the language associated with the target information.
If the first session content satisfies the second setting condition, go to step S506; if the first session content does not satisfy the second setting condition, step S507 is executed.
And S506, changing the language used by the conversation interaction system for conversation interaction.
On the basis of changing the language used by the conversation interaction system for conversation interaction, the conversation interaction system can output the conversation content in the changed language used for conversation interaction so as to reply to the first conversation content input by the user.
It should be noted that, when the second session content satisfies a different second setting condition, the process of changing the language used by the session interaction system for session interaction may be all different, and specifically, the language used by the session interaction system for session interaction may include, but is not limited to:
the conversation interactive system outputs conversation contents in a third language in at least one subsequent conversation; or the like, or, alternatively,
switching a language used by the session interaction system for session interaction from the first language to a third language;
wherein the third language is different from the first language.
Before changing the language used by the conversation interaction system for conversation interaction, the conversation interaction system can determine whether to actively inquire whether the user agrees to change the language or not according to the actual situation, actively inquire whether the user agrees to change the language into a third language or not when determining that the inquiry can be carried out, and change the language used by the conversation interaction system for conversation interaction if the user agrees.
Step S507, maintaining the language used by the session interaction system for session interaction as the first language.
The detailed process of step S507 can be referred to the related description of step S104 in embodiment 1, and is not described herein again.
In this embodiment, when the first session content satisfies the first setting condition, the target information is obtained, and based on more information (e.g., the first session content and the target information), it is determined whether the first session content satisfies the second setting condition, when the second setting condition is satisfied, the language used by the session interaction system for the session interaction is changed, so that the language used by the session interaction system for the session interaction is changed, and when the second setting condition is not satisfied, the language used by the session interaction system for the session interaction is maintained as the first language. Furthermore, compared with a mode of directly maintaining the language used for conversation interaction of the conversation interaction system as the first language if the first conversation content meets the first set condition, the method is more accurate and reliable.
As another alternative embodiment of the present application, referring to fig. 6, a flowchart of an embodiment 6 of a control method provided by the present application is shown, and this embodiment mainly relates to a refinement of the control method described in the above embodiment 5, as shown in fig. 6, the method may include, but is not limited to, the following steps:
step S601, the conversation interactive system obtains the first conversation content input by the user.
Step S602, determining that the session interaction system sets a first language for session interaction, where the first language is set based on a language adopted by at least one piece of second session content, and the second session content is a session content input by a user before the first session content.
Step S603, determining whether the first session content satisfies a first setting condition when the language adopted by the first session content at least includes a second language, where the second language is different from the first language.
If the first session content satisfies the first setting condition, step S604 is executed.
The detailed processes of steps S601-S603 can be referred to the related descriptions of steps S501-S503 in embodiment 5, and are not described herein again.
Step S604, at least one piece of fourth session content is obtained, where the fourth session content is a session content input by the user before the first session content.
Step S604 is a specific implementation manner of step S504 in example 5.
And step S605, determining whether the fourth conversation content meets the first set condition.
In this embodiment, for a detailed process of determining whether the fourth session content satisfies the first setting condition, reference may be made to related descriptions of determining whether the first session content satisfies the first setting condition in embodiments 1 to 4, which are not described herein again.
The first setting condition in this step is the same as the first setting condition in step S603.
Step S605 is a specific implementation manner of step S505 in example 5.
If the first setting condition is satisfied, executing step S606; if the first setting condition is not satisfied, step S607 is executed.
And step S606, changing the language used by the conversation interaction system for conversation interaction.
When the first session content meets the first setting condition and the fourth session content meets the first setting condition, the session interaction system determines that at least two pieces of session content both meet the first setting condition, and based on this, it may be determined that the language used by the session interaction system for session interaction does not need to be maintained, and specifically, the language used by the session interaction system for session interaction may be changed.
In this embodiment, at least one of the fourth session content and the first session content may be arranged in series. When at least one fourth session content and the first session content are continuously arranged, if the fourth session content meets the first set condition, the accuracy of changing the language used for session interaction by the session interaction system can be further ensured. For example, three sessions in a conversational interactive system are assumed to be:
a conversation interaction system: please indicate the operation as follows: ....
The user: ok
A conversation interaction system: is your question resolved?
The user: yes
A conversation interaction system: can a score be given to this service?
The user: no proplem
In the above session, the first session content is "No publishing", and the fourth session contents are "Yes" and "Ok", respectively. When the continuously arranged conversation contents input by the user all meet a first set condition of using a language different from that of the conversation interactive system, the conversation interactive system is determined not to maintain Chinese, but can change the Chinese into English.
Step S607, the language used by the session interaction system for session interaction is maintained as the first language.
In this embodiment, when the first session content satisfies the first setting condition but the fourth session content does not satisfy the first setting condition, the language used by the session interaction system for session interaction may be maintained as the first language. For example, three sessions in a conversational interactive system are assumed to be:
a conversation interaction system: please indicate the operation as follows: ....
The user: good
A conversation interaction system: is your question resolved?
The user: is
A conversation interaction system: can a score be given to this service?
The user: and Ok.
In the above sessions, the first session content is "Ok", and the fourth session contents are "good" and "yes", respectively. If the first session content satisfies the first setting condition using the language different from the language of the session interaction system and the fourth session content does not satisfy the first setting condition using the language different from the language of the session interaction system, it may be determined that the language in which the session interaction system is maintained for session interaction is chinese.
In this embodiment, whether to perform language switching is determined by obtaining the conversation content input before the first conversation content and determining whether the conversation content input before the first conversation content meets the first setting condition when the first conversation content meets the first setting condition, so that the language switching is more conformable to the interaction scene, and the conversation interaction system is ensured to interact with the user more accurately.
As another alternative embodiment of the present application, referring to fig. 7, a flowchart of an embodiment 7 of a control method provided by the present application is shown, and this embodiment mainly relates to a refinement of the control method described in the above embodiment 5, as shown in fig. 7, the method may include, but is not limited to, the following steps:
step S701, the session interaction system obtains the first session content input by the user.
Step S702, determining that the session interaction system sets a first language for session interaction, where the first language is set based on a language adopted by at least one piece of second session content, and the second session content is a session content input by a user before the first session content.
Step S703, determining whether the first session content satisfies a first setting condition under the condition that the language adopted by the first session content at least includes a second language, where the second language is different from the first language.
If the first session content satisfies the first setting condition, step S704 is executed.
The detailed processes of steps S701 to S703 can refer to the related descriptions of steps S501 to S503 in embodiment 5, and are not described herein again.
Step S704, information obtained based on the first session content is obtained.
In this embodiment, based on the first session content, the obtained information may include, but is not limited to:
location information corresponding to at least a part of information in the first session content (e.g., a product purchasing place queried according to the product information);
and/or user attribute information of the user associated with the first session content (e.g., a representation of the user including the user's nationality or common language, etc.).
Step S704 is a specific implementation manner of step S504 in example 5.
Step S705, determining whether the first session content satisfies a second setting condition based on the first session content and the information obtained based on the first session content.
Determining whether the first session content satisfies a second set condition based on the first session content and the information obtained based on the first session content, which may include but is not limited to: and determining whether the language adopted by the first session content is the same as the language associated with the information acquired based on the first session content.
If the first session content satisfies the second set condition, step S706 is executed.
And step S706, changing the language used by the conversation interaction system for conversation interaction.
In this embodiment, the steps S703 to S706 are described as an example, for example, a session in the session interaction system is as follows:
the user: can my mobile phone be water filled and can be guaranteed?
A conversation interaction system: please input your product serial number
The user: okay, SR01020230041123
In the above session, the first session content is "Okay, SR 01020230041123", and based on the first session content "Okay, SR 01020230041123", the information that can be obtained includes: according to the product purchase place queried by the product sequence (SR01020230041123) and the user representation of the user associated with the first session content, if the product purchase place is Spanish and the user representation indicates that the user is Spanish, it can be determined that the language required to change the session interaction system for session interaction is Spanish language.
In this embodiment, the information acquired based on the first session content is acquired when the first session content meets the first setting condition, and whether the information acquired based on the first session content and the first session content meets the second setting condition is determined to determine whether to perform language switching, so that the session interaction system can interact with the user more accurately.
Corresponding to the embodiment of the processing method provided by the application, the application also provides an embodiment of the electronic device applying the processing method.
As shown in fig. 8, which is a schematic structural diagram of an embodiment 1 of an electronic device provided in the present application, the electronic device may include the following structures:
a memory 100 and a processor 200.
A memory 100 for storing at least one set of instructions;
the processor 200 is used for calling and executing the instruction set in the memory 100, and the following processing is performed by executing the instruction set:
the conversation interactive system obtains first conversation content input by a user;
determining a first language set by a conversation interaction system for conversation interaction, wherein the first language is set based on at least one language adopted by second conversation content, and the second conversation content is conversation content input by a user before the first conversation content;
determining whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, wherein the second language is different from the first language;
and if the first conversation content meets the first set condition, maintaining the language used by the conversation interaction system for conversation interaction as the first language.
In this embodiment, the processor 200, by executing the instruction set, may further perform the following processing:
acquiring target information;
determining whether the first session content meets a second set condition based on the first session content and the target information;
and if the first session content meets the second set condition, changing the language used by the session interaction system for session interaction.
In this embodiment, changing the language used by the session interaction system for session interaction may include:
the conversation interactive system outputs conversation contents in a third language in at least one subsequent conversation; or
Switching a language used by the session interaction system for session interaction from the first language to a third language;
wherein the third language is different from the first language.
In this embodiment, the target information may include at least one piece of fourth session content, where the fourth session content is a session content input by the user before the first session content;
accordingly, determining whether the first session content satisfies a second set condition based on the first session content and the target information may include:
it is determined whether the fourth session content satisfies a first set condition.
Wherein the at least one piece of fourth session content and the first session content may be arranged in series.
In this embodiment, the target information may also include:
based on the first session content, obtaining information;
the information includes: the location information corresponding to at least a part of the information in the first session content, and/or the user attribute information of the user associated with the first session content.
In this embodiment, the processor 200 is configured to call and execute an instruction set in the memory 100, and the following processing may be specifically performed by executing the instruction set:
the conversation interactive system obtains first conversation content input by a user;
determining a first language set by a conversation interaction system for conversation interaction, wherein the first language is set based on at least one language adopted by second conversation content, and the second conversation content is conversation content input by a user before the first conversation content;
under the condition that the language adopted by the first conversation content at least comprises a second language, analyzing the first conversation content and determining the grade of the first conversation content; the level of the first session content is used for representing the requirement degree of whether language switching is needed or not;
determining whether the level of the first session content is a first set level;
and if the first conversation content meets the first set level, maintaining the language used by the conversation interaction system for conversation interaction as the first language.
In this embodiment, the processor 200 is configured to call and execute an instruction set in the memory 100, and by executing the instruction set, the following processing may be performed:
if the level of the first session content is determined to be a second set level, the session interactive system outputs the session content in a third language in at least one subsequent session; the requirement degree corresponding to the second setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
In this embodiment, the processor 200 is configured to call and execute an instruction set in the memory 100, and by executing the instruction set, the following processing may be performed:
if the level of the first conversation content is determined to be a third set level, the conversation interaction system switches the language used for conversation interaction from the first language to a third language; the requirement degree corresponding to the third setting level is higher than that corresponding to the first setting level, and the third language is different from the first language.
Corresponding to the embodiment of the control method provided by the application, the application also provides an embodiment of a control device.
Referring to fig. 9, the control device may include: a user input content acquisition module 11, a language recognition module 12, a detection module 13 and a control module 14.
A user input content obtaining module 11, configured to obtain first session content input by a user;
the language identification module 12 is configured to determine a first language set by the conversational interaction system for conversational interaction, where the first language is set based on a language adopted by at least one piece of second conversational content, and the second conversational content is conversational content input by a user before the first conversational content;
the detection module 13 is configured to detect whether the first session content meets a first set condition under the condition that the language adopted by the first session content at least includes a second language, where the second language is different from the first language;
and the control module 14 is configured to maintain the voice used by the session interaction system for session interaction in the first language if the first session content satisfies the first set condition.
In this embodiment, the control module 14 may specifically be configured to:
if the first session content meets a first set condition, acquiring target information;
determining whether the first session content meets a second set condition based on the first session content and the target information;
if the first session content meets a second set condition, changing the language used for session interaction by the session interaction system;
and if the first conversation content does not meet the second set condition, maintaining the language used for conversation interaction by the conversation interaction system as the first language.
In this embodiment, changing the language used by the session interaction system for session interaction may include:
the conversation interactive system outputs conversation contents in a third language in at least one subsequent conversation; or
Switching a language used by the session interaction system for session interaction from the first language to a third language;
wherein the third language is different from the first language.
In this embodiment, the target information may include at least one piece of fourth session content, where the fourth session content is a session content input by the user before the first session content;
correspondingly, based on the first session content and the target information, determining whether the first session content meets a second set condition includes:
it is determined whether the fourth session content satisfies a first set condition.
In this embodiment, at least one piece of the fourth session content and the first session content are arranged in series.
In this embodiment, the target information may include:
based on the first session content, obtaining information;
the information includes: the location information corresponding to at least a part of the information in the first session content, and/or the user attribute information of the user associated with the first session content.
In this embodiment, the detection module 13 may specifically be configured to:
under the condition that the language adopted by the first conversation content at least comprises a second language, analyzing the first conversation content and determining the grade of the first conversation content; the level of the first session content is used for representing the requirement degree of whether language switching is needed or not;
it is determined whether the level of the first session content is a first set level.
The detection module 13 may be further configured to: if the level of the first session content is determined to be a second set level, the session interactive system outputs the session content in a third language in at least one subsequent session; the requirement degree corresponding to the second setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
The detection module 13 may be further configured to: if the level of the first conversation content is determined to be a third set level, the conversation interaction system switches the language used for conversation interaction from the first language to a third language; the requirement degree corresponding to the third setting level is higher than that corresponding to the first setting level, and the third language is different from the first language.
Corresponding to the embodiment of the processing method provided by the application, the application also provides an embodiment of a storage medium.
In this embodiment, the storage medium stores a computer program for implementing the processing method according to any one of the foregoing embodiments, and the computer program is executed by the processor to implement the steps of the processing method according to any one of the foregoing embodiments.
It should be noted that, in the present specification, each embodiment is mainly described as a difference from the other embodiments, and the same and similar parts between the embodiments may be referred to each other.
For convenience of description, the above system or apparatus is described as being divided into various modules or units by function, respectively. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
Finally, it is further noted that, herein, relational terms such as first, second, third, fourth, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (10)

1. A method of processing, comprising:
the conversation interactive system obtains first conversation content input by a user;
determining a first language set by the conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by the user before the first conversation content;
determining whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, wherein the second language is different from the first language;
and if the first conversation content meets the first set condition, maintaining the language used by the conversation interaction system for conversation interaction as the first language.
2. The method of claim 1, further comprising:
acquiring target information;
determining whether the first session content meets a second set condition based on the first session content and the target information;
and if the first session content meets a second set condition, changing the language used for session interaction by the session interaction system.
3. The method of claim 2, the altering a language used by the conversational interaction system for conversational interaction comprising:
the conversation interactive system outputs conversation contents in a third language in at least one subsequent conversation; or
Switching the language used by the conversational interaction system for conversational interaction from the first language to a third language;
wherein the third language is different from the first language.
4. The method according to any one of claims 2 or 3, wherein the target information includes at least one piece of fourth session content, the fourth session content being session content input by the user before the first session content;
the determining whether the first session content meets a second set condition based on the first session content and the target information includes:
determining whether the fourth session content satisfies the first set condition.
5. The method of claim 4, wherein at least one of the fourth session content and the first session content are arranged in series.
6. The method of any of claims 2 or 3, the target information comprising:
based on the first session content, obtaining information;
the information includes: the location information corresponding to at least a part of information in the first session content, and/or the user attribute information of the user associated with the first session content.
7. The method of claim 1, prior to determining whether the first session content satisfies a first set condition, the method further comprising:
analyzing the first conversation content and determining the grade of the first conversation content; the level of the first session content is used for representing the requirement degree of whether language switching is needed or not;
the determining whether the first session content meets a first set condition includes:
it is determined whether the level of the first session content is a first set level.
8. The method of claim 7, further comprising: if the level of the first session content is determined to be a second set level, the session interactive system outputs the session content in a third language in at least one subsequent session; the requirement degree corresponding to the second setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
9. The method of claim 7, further comprising: if the level of the first session content is determined to be a third set level, the session interaction system switches the language used for session interaction from the first language to a third language; the requirement degree corresponding to the third setting level is higher than the requirement degree corresponding to the first setting level, and the third language is different from the first language.
10. A processing apparatus, comprising:
the user input content acquisition module is used for acquiring first session content input by a user;
the language identification module is used for determining a first language set by a conversation interaction system for conversation interaction, wherein the first language is set based on a language adopted by at least one piece of second conversation content, and the second conversation content is conversation content input by the user before the first conversation content;
the detection module is used for detecting whether the first conversation content meets a first set condition or not under the condition that the language adopted by the first conversation content at least comprises a second language, wherein the second language is different from the first language;
and the control module is used for maintaining the voice used for conversation interaction by the conversation interaction system as the first language if the first conversation content meets the first set condition.
CN202010354651.6A 2020-04-29 2020-04-29 Processing method and device Pending CN111581362A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010354651.6A CN111581362A (en) 2020-04-29 2020-04-29 Processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010354651.6A CN111581362A (en) 2020-04-29 2020-04-29 Processing method and device

Publications (1)

Publication Number Publication Date
CN111581362A true CN111581362A (en) 2020-08-25

Family

ID=72126264

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010354651.6A Pending CN111581362A (en) 2020-04-29 2020-04-29 Processing method and device

Country Status (1)

Country Link
CN (1) CN111581362A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102929505A (en) * 2011-11-14 2013-02-13 微软公司 Switching of a self-adaptive input language
US20150006147A1 (en) * 2013-07-01 2015-01-01 Toyota Motor Engineering & Manufacturing North America, Inc. Speech Recognition Systems Having Diverse Language Support
CN106774976A (en) * 2016-12-01 2017-05-31 北京小米移动软件有限公司 input method switching method and device
CN109949795A (en) * 2019-03-18 2019-06-28 北京猎户星空科技有限公司 A kind of method and device of control smart machine interaction
CN110385723A (en) * 2018-04-17 2019-10-29 株式会社日立大厦系统 Guided robot system and speech selection method
CN110414014A (en) * 2019-08-05 2019-11-05 珠海格力电器股份有限公司 A kind of speech ciphering equipment control method, device, storage medium and speech ciphering equipment
CN110462730A (en) * 2018-03-07 2019-11-15 谷歌有限责任公司 Promote with the end-to-end communication of multilingual and automation assistant
CN111052229A (en) * 2018-04-16 2020-04-21 谷歌有限责任公司 Automatically determining a language for speech recognition of a spoken utterance received via an automated assistant interface

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102929505A (en) * 2011-11-14 2013-02-13 微软公司 Switching of a self-adaptive input language
US20150006147A1 (en) * 2013-07-01 2015-01-01 Toyota Motor Engineering & Manufacturing North America, Inc. Speech Recognition Systems Having Diverse Language Support
CN106774976A (en) * 2016-12-01 2017-05-31 北京小米移动软件有限公司 input method switching method and device
CN110462730A (en) * 2018-03-07 2019-11-15 谷歌有限责任公司 Promote with the end-to-end communication of multilingual and automation assistant
CN111052229A (en) * 2018-04-16 2020-04-21 谷歌有限责任公司 Automatically determining a language for speech recognition of a spoken utterance received via an automated assistant interface
CN110385723A (en) * 2018-04-17 2019-10-29 株式会社日立大厦系统 Guided robot system and speech selection method
CN109949795A (en) * 2019-03-18 2019-06-28 北京猎户星空科技有限公司 A kind of method and device of control smart machine interaction
CN110414014A (en) * 2019-08-05 2019-11-05 珠海格力电器股份有限公司 A kind of speech ciphering equipment control method, device, storage medium and speech ciphering equipment

Similar Documents

Publication Publication Date Title
CN110765244B (en) Method, device, computer equipment and storage medium for obtaining answering operation
CN110110062B (en) Machine intelligent question and answer method and device and electronic equipment
CN112417102B (en) Voice query method, device, server and readable storage medium
CN110472224B (en) Quality of service detection method, apparatus, computer device and storage medium
CN110334179B (en) Question-answer processing method, device, computer equipment and storage medium
CN110060674B (en) Table management method, device, terminal and storage medium
JP2017505964A (en) Automatic task classification based on machine learning
CN112468659B (en) Quality evaluation method, device, equipment and storage medium applied to telephone customer service
CN110309504B (en) Text processing method, device, equipment and storage medium based on word segmentation
KR20190072823A (en) Domain specific dialogue acts classification for customer counseling of banking services using rnn sentence embedding and elm algorithm
US20210360109A1 (en) Unsupervised method and system to automatically train a chatbot using domain conversations
CN113326702B (en) Semantic recognition method, semantic recognition device, electronic equipment and storage medium
CN111177307A (en) Test scheme and system based on semantic understanding similarity threshold configuration
CN110717021A (en) Input text and related device for obtaining artificial intelligence interview
CN111639162A (en) Information interaction method and device, electronic equipment and storage medium
CN111783471A (en) Semantic recognition method, device, equipment and storage medium of natural language
CN114399396A (en) Insurance product recommendation method and device, computer equipment and storage medium
CN112632248A (en) Question answering method, device, computer equipment and storage medium
CN115481229A (en) Method and device for pushing answer call, electronic equipment and storage medium
CN111400340A (en) Natural language processing method and device, computer equipment and storage medium
CN114186041A (en) Answer output method
CN113051384A (en) User portrait extraction method based on conversation and related device
CN112632956A (en) Text matching method, device, terminal and storage medium
CN111581362A (en) Processing method and device
CN114242047A (en) Voice processing 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