CN109992654B - Information processing method and computer readable storage medium - Google Patents
Information processing method and computer readable storage medium Download PDFInfo
- Publication number
- CN109992654B CN109992654B CN201910239432.0A CN201910239432A CN109992654B CN 109992654 B CN109992654 B CN 109992654B CN 201910239432 A CN201910239432 A CN 201910239432A CN 109992654 B CN109992654 B CN 109992654B
- Authority
- CN
- China
- Prior art keywords
- information
- processed
- output
- output information
- outputting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses an information processing method, which is applied to an information feedback system, wherein the information feedback system can respond to information input into the information feedback system and output feedback information, and the method comprises the following steps: acquiring information to be processed; processing the information to be processed to obtain a plurality of first output information, wherein the first output information can represent the intention of the information to be processed; outputting the plurality of first output information; receiving first acknowledgement information, wherein the first acknowledgement information is used for corresponding to at least one of the first output information; and obtaining and outputting second output information at least according to the first confirmation information, wherein the second output information is used for responding to the information to be processed. The embodiment of the invention also discloses a computer storage medium.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an information processing method and a computer-readable storage medium.
Background
With the improvement of network technology, the service awareness of people is more and more strong, and the intelligent customer service system is popularized in various industries and goes deep into various links of daily business services.
In practical application, in order to convey the understanding result of the intelligent customer service system on the user input question, the intelligent customer service system matches the locally stored standard question according to the question input by the user, and provides the matched standard question as the understanding result of the user input question to the user, so that the user can select the relevant service answer according to the real intention of the user. However, in the prior art, the standard problem of the local storage of the intelligent customer service system is preset, and the preset standard problem is often greatly different from the problem input by the user, which easily causes misunderstanding of the user, and is difficult to effectively meet the service requirement of the user, and cannot be well accepted by the user, so that many users are unwilling to communicate with the intelligent customer service system, and many times, the artificial customer service is directly clicked, so that the intelligent customer service system is similar to a nominal one, and the problem resolution of the intelligent customer service system is reduced.
Disclosure of Invention
To solve the above technical problem, embodiments of the present invention desirably provide an information processing method and a computer-readable storage medium.
The technical scheme of the invention is realized as follows:
in a first aspect, an information processing method is provided, which is applied to an information feedback system, and the information feedback system is capable of outputting feedback information in response to information input into the information feedback system, and the method includes:
acquiring information to be processed;
processing the information to be processed to obtain a plurality of first output information, wherein the first output information can represent the intention of the information to be processed;
outputting the plurality of first output information;
receiving first acknowledgement information, wherein the first acknowledgement information is used for corresponding to at least one of the first output information;
and obtaining and outputting second output information at least according to the first confirmation information, wherein the second output information is used for responding to the information to be processed.
In a second aspect, an embodiment of the present invention further provides a computer-readable storage medium, where one or more programs are stored in the computer-readable storage medium, and the one or more programs are executable by one or more processors to implement the steps of the information processing method according to the first aspect.
The information processing method and the computer-readable storage medium provided by the embodiment of the invention can process the information to be processed after the information to be processed is obtained, so as to obtain a plurality of first output information, wherein the first output information can represent the intention of the information to be processed; outputting a plurality of first output information; receiving first confirmation information, wherein the first confirmation information is used for corresponding to at least one of the first output information; and obtaining and outputting second output information at least according to the first confirmation information, wherein the second output information is used for responding to the information to be processed. That is to say, the information processing method provided by the embodiment of the present invention can generate the first output information in real time according to the information to be processed, and does not need to match the information to be processed with a preset standard problem; in addition, the first output information can represent the intention of the information to be processed and can be closer to the information to be processed input by the user, so that the user can accept the pushed understanding result more easily, and the problem solving rate of the intelligent customer service system is improved.
Drawings
Fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a manner of obtaining the first output information according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating another information processing method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a display interface according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating another information processing method according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
The embodiment of the invention provides an information processing method, which is applied to an information feedback system, and the information feedback system can respond to information input into the information feedback system and output feedback information.
Fig. 1 is a schematic flow chart illustrating an implementation of an information processing method according to an embodiment of the present invention; referring to fig. 1, the method includes the steps of:
Here, the step 101 of acquiring the information to be processed may be implemented by any type of electronic device equipped with the information feedback system; the electronic devices include, but are not limited to, servers, tablet computers, Ultra-mobile Personal computers (UMPCs), industrial computers, netbooks, Personal Digital Assistants (PDAs), and the like.
In other embodiments of the present invention, the information to be processed refers to information input into the information feedback system; the information feedback system can be an intelligent customer service system, an intelligent question-answering system and the like; it is understood that the information to be processed is a question that the user inputs into the intelligent customer service system or the intelligent question and answer system.
It should be noted that the types of the information to be processed at least include one or more of the following: text type, audio type, image type, video type.
And 102, processing the information to be processed to obtain a plurality of first output information.
Wherein the first output information is capable of characterizing an intent of the information to be processed.
In other embodiments of the present invention, the step 102 of processing the information to be processed to obtain a plurality of first output information may be implemented by an electronic device. Here, the first output information refers to a result of the electronic device understanding the information to be processed input by the user.
Specifically, the processing of the information to be processed to obtain a plurality of first output information may be: analyzing the information to be processed to obtain various intents corresponding to the information to be processed; and obtaining a plurality of first output information at least based on a plurality of intentions contained in the information to be processed. Here, the intention of the information to be processed means a true purpose that a user wants to achieve when interacting with the information feedback system through the information to be processed.
In practical applications, the information to be processed is information with a thick subjective color input by a user, and the electronic device needs to recognize an intention corresponding to the information to be processed and respond based on the intention of the information to be processed. However, in some cases, one to-be-processed information corresponds to a plurality of intentions; for example, when the to-be-processed information is "the mobile phone cannot be used", the intention of the to-be-processed information may be "purchase the mobile phone", or "repair the mobile phone". Therefore, the electronic device needs to provide the first output information containing the intention of the information to be processed to the user after performing intention recognition on the information to be processed, so that the user can confirm the real intention of the user from a plurality of intentions. It should be noted that one intention of the information to be processed corresponds to one first output information, and the intentions of the information to be processed corresponding to different first output information are different.
Likewise, the type of the first output information includes at least one or more of: text type, audio type, image type, video type.
And step 103, outputting a plurality of pieces of first output information.
Here, the step 103 of outputting the plurality of first output information may be implemented by an electronic device.
Specifically, the electronic device may determine a corresponding output device according to the type of the first output information, and output the first output information in the determined output device. For example, when the first output information is voice-type information, the electronic device may output the plurality of first output information through the audio output device.
And 104, receiving first confirmation information.
The first confirmation information is used for corresponding to at least one of the first output information.
In other embodiments of the present invention, the step 104 of receiving the first confirmation information may be implemented by the electronic device.
Specifically, the electronic equipment outputs a plurality of first output information for the user to select; and the user selects one or more pieces of first output information matched with the real intention from the plurality of pieces of first output information according to the real intention of inputting the information to be processed by the user. Here, the first confirmation information is one or more first output information selected by the user based on the user's actual intention.
And 105, obtaining and outputting second output information at least according to the first confirmation information.
The second output information is used for responding to the information to be processed.
In other embodiments of the present invention, the step 105 of obtaining and outputting the second output information according to at least the first confirmation information may be implemented by an electronic device. Here, the second output information is response information of the electronic device to the information to be processed, and it can be understood that the second output information is a service answer corresponding to the information to be processed. Here, the type of the second output information includes at least one or more of: text type, audio type, image type, video type.
Here, obtaining and outputting the second output information based on at least the first confirmation information further includes:
obtaining and outputting second output information according to the first confirmation information and the information to be processed; or obtaining and outputting second output information according to the first confirmation information and the first output information; or obtaining and outputting second output information according to the first confirmation information, the information to be processed and the first output information.
Specifically, obtaining and outputting second output information at least according to the first confirmation information includes:
determining at least part of the first output information in the plurality of first output information indicated by the first confirmation information as target first output information; acquiring target related information contained in to-be-processed information linked with target first output information; and outputting the target related information as second output information.
Wherein, different first output information in the plurality of first output information is used for linking to different related information contained in the information to be processed.
In other embodiments of the present invention, the information to be processed may include a plurality of related information, where the plurality of related information may refer to a plurality of service answers to which the information to be processed may correspond. In the present embodiment, one intention corresponds to one service answer, that is, each piece of relevant information included in the information to be processed may correspond to one intention of the information to be processed. And the first output information can characterize the intention of the information to be processed, so said first output information can correspond to the information related to the information to be processed; it is understood that the first output information can be linked to the relevant information corresponding to the information to be processed.
Based on this, in step 105, the electronic device may determine the target first output information selected by the user according to the first confirmation information, and obtain the second output information according to the target related information of the information to be processed linked by the target first output information.
The information processing method provided by the embodiment of the invention can process the information to be processed after the information to be processed is obtained, so as to obtain a plurality of first output information, wherein the first output information can represent the intention of the information to be processed; outputting a plurality of first output information; receiving first confirmation information, wherein the first confirmation information is used for corresponding to at least one of the first output information; and obtaining and outputting second output information at least according to the first confirmation information, wherein the second output information is used for responding to the information to be processed. That is to say, the information processing method provided by the embodiment of the present invention can generate the first output information in real time according to the information to be processed, and does not need to match the information to be processed with a preset standard problem; in addition, the first output information can represent the intention of the information to be processed and can be closer to the information to be processed input by the user, so that the user can accept the pushed understanding result more easily, and the problem solving rate of the intelligent customer service system is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides an information processing method applied to an information feedback system, where the information feedback system is capable of outputting feedback information in response to information input to the information feedback system, and the method includes the following steps:
step 201, the electronic device obtains information to be processed.
Step 202, the electronic device processes the information to be processed to obtain a plurality of first output information.
Wherein the first output information is capable of characterizing an intent of the information to be processed.
In other embodiments of the present invention, obtaining and outputting a plurality of first output information based on the information to be processed includes:
inputting information to be processed into a natural language understanding model to obtain at least one corresponding intention information of the information to be processed; the natural language understanding model is obtained by training by adopting preset processing information and a user real intention corresponding to the preset processing information;
a plurality of first output information is generated based at least on the at least one intent information.
In other embodiments of the invention, the intent resolution of the information to be processed is achieved by building a natural language understanding model through a deep learning algorithm. The preset processing information may be a historical question input by the user. In order to accurately analyze the intention of the information to be processed, firstly, the preset processing information needs to be labeled manually, and each preset processing information is labeled with the real intention of the user corresponding to the preset processing information. After the labeling is finished, training of the natural language understanding model is started, the input of the model is preset processing information, and the output of the model is corresponding real intention of the user. However, the language understanding model can adopt a text classification model, such as SVM, CNN or LSTM; information extraction models such as CRF, LSTM + CRF and the like can also be selected; text classification models and information extraction models can also be fused. The invention is not limited thereto.
Here, after obtaining the at least one intention information corresponding to the information to be processed, the electronic device may directly use the at least one intention information as the first output information.
In another embodiment, in order to make it easier for the user to understand the first output information pushed by the electronic device, the generating of the plurality of first output information based on at least the at least one intention information may be implemented by:
converting the information to be processed into a text form to obtain a text element corresponding to the information to be processed; the text element is used for representing at least one word and/or at least one word in a text corresponding to the information to be processed;
inputting a text element corresponding to the information to be processed and at least one intention information into a preset generating model to obtain a plurality of first output information.
Specifically, the electronic device can convert various types of information to be processed into a text form, and remove meaningless words, such as stop words, non-keywords, and the like, in the information to be processed; and finally, obtaining the text element corresponding to the information to be processed. After the text element of the information to be processed is obtained, carrying out coded representation on the text element corresponding to the information to be processed to obtain a text representation code of the information to be processed; here, a text element of the information to be processed may be encoded using an encoder model based on the CNN, RNN, GRU/LSTM structure. In addition, at least One intention information corresponding to the information to be processed is coded and represented to obtain at least One intention representation code corresponding to the information to be processed, and here, the intention of the information to be processed can be represented by using a One-hot (One-hot) code or a distributed representation.
Further, the text representation code and the at least one intention representation code of the information to be processed are input into the generative model, so that at least one first output information is obtained. Here, the generative model may be an end-to-end (seq2seq) model, consisting of two parts, an encoder and a decoder. Specifically, the text representation code of the information to be processed and each intention representation code in the at least one intention representation code can be input into the generation model respectively, so that a plurality of first output information corresponding to the information to be processed are obtained.
In this embodiment, the input to the generative model is two parts: the text element of the information to be processed and the natural language understanding module understand the resulting intent of the information to be processed based on the user input. Here, directly taking the text element of the information to be processed as one of the inputs of the generation model, a direct association between the text element of the information to be processed and the first output information can be established, so that the user can more easily understand the first output information pushed by the electronic device; in addition, the purpose of the information to be processed is used as an input to ensure the consistency of the generated first output information and the real user purpose, and avoid the situation of text mismatching.
In other embodiments of the present invention, the first output information may be obtained in the manner shown in fig. 2. Specifically, information to be processed is obtained, the information to be processed is input into a natural language understanding model to obtain at least one intention information of the information to be processed, further, the at least one intention information of the information to be processed is input into an intention representation module to obtain at least one intention representation code; in addition, the information to be processed is input into the text representation module, and the text representation code of the information to be processed is obtained. Further, at least one intent representation encoding and text representation encoding are input into the generative model resulting in at least one first output information.
Illustratively, the comparison of the first output information obtained by using the information processing method described in fig. 2 and the understanding result of the information to be processed obtained by using the prior art can be shown in table 1.
| Information to be processed | First output information | Understanding results obtained by the prior art |
| Why I cannot update the mobile phone | Mobile phone incapable of updating | Update help |
| I want to know why i cannot download update packages | Downloading-impossible system | Update help |
| Can tell me when to update android 8.0 | When to update android 8.0 | Updating schedules |
| I renew the mobile phone yesterday, and can not receive the call now | Cannot answer the call after updating | Update problem |
As can be seen from table 1, when the information to be processed is "why i cannot update the mobile phone", the method provided in this embodiment obtains the first output information as "cannot update the mobile phone", whereas in the prior art, after the information to be processed is matched with the standard problem stored locally, the obtained understanding result of the information to be processed is "update help". Compared with the prior art, the information processing method provided by the embodiment can be closer to the expression mode of the user input on the premise of ensuring that the intention represented by the first output information is consistent with the real intention of the user, so that the information processing method is more easily accepted by the user, the user experience is improved, and the solution rate of the system is improved.
And step 203, outputting a plurality of pieces of first output information.
In another embodiment of the present invention, after outputting the plurality of first output information, the method further includes: obtaining a satisfaction degree for the at least one first output information;
updating the generative model based on the information to be processed, the at least one first output information, and a satisfaction with the at least one first output information.
Here, in order to improve the accuracy of the generative model, the present embodiment may continuously improve the generative model by accumulating data. Specifically, after outputting the first output information, the electronic device may further obtain the satisfaction degree of the user with respect to the first output information, for example, a scoring interface for the first output information may be displayed below the display of the first output information by the electronic device to obtain the satisfaction degree of the user with respect to the first output information.
Further, the electronic device adjusts parameters in the generated model based on the information to be processed, the at least one first output information and the satisfaction degree for the at least one first output information, so that the generated model can obtain the first output information more accurately.
Step 204, receiving a first confirmation message, where the first confirmation message is used to correspond to at least one of the plurality of first output messages.
And step 205, obtaining and outputting second output information at least according to the first confirmation information, wherein the second output information is used for responding to the information to be processed.
It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.
The information processing method provided by the embodiment of the invention can generate the first output information in real time according to the information to be processed, and the information to be processed does not need to be matched with a preset standard problem; moreover, the embodiment can generate the first output information based on the text element and the intention information of the information to be processed, so that the direct association between the text element and the first output information of the information to be processed can be established, and the user can understand the first output information pushed by the electronic device more easily; meanwhile, the consistency of the generated first output information and the intention of the real user is ensured, the condition of text-to-question is avoided, the pushed understanding result is easier to accept by the user, and the problem solving rate of the intelligent customer service system is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides an information processing method applied to an information feedback system, where the information feedback system is capable of outputting feedback information in response to information input into the information feedback system, as shown in fig. 3, and the method includes the following steps:
Wherein the first output information is capable of characterizing an intent of the information to be processed.
And step 303, the electronic device obtains and outputs at least one third output information based on the information to be processed.
Wherein the third output information is used for responding to the information to be processed.
In other embodiments of the present invention, in order to improve the efficiency of the information feedback system, the information to be processed may also be responded to when the first output information is output.
Specifically, through step 302, the electronic device can obtain a plurality of intention information of the information to be processed, and rank the intention information according to a matching degree with the information to be processed, where the matching degree may be a similarity; and selecting at least one intention information with high matching degree with the information to be processed from the plurality of intention information. Acquiring related information of the to-be-processed information corresponding to the at least one intention information with high matching degree; and the related information of the to-be-processed information corresponding to the at least one intention information with high matching degree is used as third output information.
Therefore, before outputting the first output information, the electronic device can output at least one service answer with high matching degree corresponding to the information to be processed as a default service answer, and a user can directly obtain the most relevant service answer of the information to be processed, so that the information feedback efficiency is improved.
Here, when the first output information and the third output information are information of text and image types, the first output information and the third output information may be displayed on the same page; and the user can easily select the service answer corresponding to other intentions in the display page. And when the first output information and the third output information are the audio and video types, the first output information is played after the third output information is played.
It should be noted that, in step 303, the service answer corresponding to at least one intention with a high matching degree of the information to be processed is already displayed, so that the first output information does not include the first output information corresponding to at least one intention with a high matching degree of the information to be processed.
Illustratively, as shown in FIG. 4, when the user interacts with the credit card smart customer service system, the user inputs questions of "how to set up automatic credit card repayment", the determination of the user's intent may be "automatic credit card repayment", "automatic credit card repayment date", and "automatic credit card debit card deduction"; the electronic equipment acquires the related information corresponding to the automatic payment of the credit card, associates the related information with a deposit card, automatically deducts corresponding money from the current account of the associated deposit card on the payment due date of the line card account, and displays the related information as third output information. Meanwhile, below the third output information, a plurality of first output information are displayed: "date of automatic payment by credit card" and "automatic deduction from debit card by credit card".
Wherein the first confirmation information is used for corresponding to at least one of the plurality of first output information;
and step 306, the electronic device obtains and outputs second output information at least according to the first confirmation information.
And the second output information is used for responding to the information to be processed.
It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.
The information processing method provided by the embodiment of the invention can output at least one service answer with high matching degree corresponding to the information to be processed as the default service answer before outputting the first output information, so that a user can directly obtain the most relevant service answer of the information to be processed, and the information feedback efficiency is improved.
Based on the foregoing embodiments, an embodiment of the present invention provides an information processing method applied to an information feedback system, where the information feedback system is capable of outputting feedback information in response to information input into the information feedback system, as shown in fig. 5, and the method includes the following steps:
Here, the electronic device may store the first output information corresponding to the to-be-processed information obtained each time in a local memory. And if the currently acquired information to be processed is matched with the historical information to be processed, directly calling first output information corresponding to the historical information to be processed. Thus, the processing efficiency of the information feedback system can be improved.
After step 503, step 505 is executed.
And step 504, the electronic equipment processes the information to be processed to obtain a plurality of first output information.
Wherein the first confirmation information is used for corresponding to at least one of the plurality of first output information.
And 507, the electronic device obtains at least one fourth output information based on the first confirmation information.
The fourth output information is sub information of the first output information corresponding to the first confirmation information. Here, the fourth output information is a further explanation for the corresponding first output information. And the fourth output information is capable of further characterizing the intent of the information to be processed on the basis of the corresponding first output information.
For example, when the information to be processed is "the mobile phone cannot be used", the obtained first output information may be "purchase the mobile phone" and "maintain the mobile phone"; when the user selects 'buy the mobile phone', the electronic equipment outputs sub-information of 'buy the mobile phone', such as 'buy Huashi mobile phone', 'buy millet mobile phone', and 'buy other mobile phones'.
The second confirmation information is used for corresponding to at least one of the fourth output information.
In step 509, the electronic device obtains and outputs second output information based on the second confirmation information.
Illustratively, when the second confirmation message corresponds to the fourth output message "buy millet mobile phone", the webpage information of the millet mall is obtained, and the information of the millet mall is displayed.
It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.
The information processing method provided by the embodiment of the invention can store the first output information corresponding to the information to be processed obtained each time into the local memory. And if the currently acquired information to be processed is matched with the historical information to be processed, directly calling first output information corresponding to the historical information to be processed. Thus, the processing efficiency of the information feedback system can be improved.
In an exemplary embodiment, the present invention further provides a computer readable storage medium, such as a memory, including a computer program, which is executable by a processor of an output control apparatus to perform the steps of the aforementioned method. The computer-readable storage medium may be a magnetic random access Memory (FRAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM), among other memories.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (8)
1. An information processing method applied to an information feedback system capable of outputting feedback information in response to information input to the information feedback system, the method comprising:
acquiring information to be processed;
inputting the information to be processed into a natural language understanding model to obtain at least one corresponding intention information of the information to be processed; the natural language understanding model is obtained by training by adopting preset processing information and a user real intention corresponding to the preset processing information;
converting information to be processed into a text form to obtain a text element corresponding to the information to be processed; the text element is used for representing at least one word and/or at least one word in the text corresponding to the information to be processed;
inputting the text element corresponding to the information to be processed and the at least one intention information into a preset generating model to obtain a plurality of first output information; the first output information is capable of characterizing an intent of the information to be processed;
outputting the plurality of first output information;
receiving first acknowledgement information, wherein the first acknowledgement information is used for corresponding to at least one of the first output information;
and obtaining and outputting second output information at least according to the information to be processed, the first output information and the first confirmation information, wherein the second output information is used for responding to the information to be processed.
2. The method of claim 1, wherein before outputting the first plurality of output information, further comprising:
obtaining and outputting at least one third output information based on the information to be processed; the third output information is used for responding to the information to be processed.
3. The method of claim 1, further comprising:
obtaining at least one fourth output information based on the first confirmation information; the fourth output information is sub information of the first output information corresponding to the first confirmation information;
receiving second confirmation information, wherein the second confirmation information is used for corresponding to at least one of the fourth output information;
and obtaining and outputting second output information based on the second confirmation information.
4. A method according to any one of claims 1 to 3, wherein:
the type of the second output information at least comprises one or more of the following: text type, audio type, image type, video type.
5. The method of claim 1, further comprising:
determining at least part of the first output information in the plurality of first output information indicated by the first confirmation information as target first output information; wherein, different first output information in the plurality of first output information is used for linking to different related information contained in the information to be processed;
acquiring target related information contained in the information to be processed linked with the target first output information;
and outputting the target related information as second output information.
6. The method according to claim 1, wherein after inputting the text element corresponding to the information to be processed and the at least one intention information into a preset generating model to obtain a plurality of first output information, the method further comprises:
obtaining a satisfaction degree for the at least one first output information;
updating the generative model based on the information to be processed, the at least one first output information, and a satisfaction with the at least one first output information.
7. The method of claim 1, further comprising:
judging whether the information to be processed is matched with at least one piece of stored historical information to be processed;
if the information to be processed is matched with at least one stored historical information to be processed, at least one historical first output information corresponding to the historical information to be processed matched with the information to be processed is obtained, and the at least one historical first output information is used as the first output information of the information to be processed.
8. A computer-readable storage medium characterized by storing one or more programs, which are executable by one or more processors, to implement the steps of the information processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239432.0A CN109992654B (en) | 2019-03-27 | 2019-03-27 | Information processing method and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910239432.0A CN109992654B (en) | 2019-03-27 | 2019-03-27 | Information processing method and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109992654A CN109992654A (en) | 2019-07-09 |
| CN109992654B true CN109992654B (en) | 2021-10-22 |
Family
ID=67131673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910239432.0A Active CN109992654B (en) | 2019-03-27 | 2019-03-27 | Information processing method and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109992654B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110971754B (en) * | 2019-10-28 | 2022-09-27 | 深圳绿米联创科技有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN111222043A (en) * | 2019-12-31 | 2020-06-02 | 联想(北京)有限公司 | Information processing method and system and electronic equipment |
| CN112527979A (en) * | 2020-11-10 | 2021-03-19 | 联想(北京)有限公司 | Information interaction method and device and readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8458168B2 (en) * | 2009-03-27 | 2013-06-04 | Microsoft Corporation | Anticipating interests of an online user |
| US9536001B2 (en) * | 2012-11-13 | 2017-01-03 | Microsoft Technology Licensing, Llc | Intent-based presentation of search results |
| CN105122240A (en) * | 2013-03-14 | 2015-12-02 | 微软技术许可有限责任公司 | Query intent expression for search in an embedded application context |
| CN106845624A (en) * | 2016-12-16 | 2017-06-13 | 北京光年无限科技有限公司 | The multi-modal exchange method relevant with the application program of intelligent robot and system |
| CN109298904B (en) * | 2018-08-10 | 2019-07-23 | 北京小蓦机器人技术有限公司 | Information processing method, device, storage medium and calculating equipment |
| CN109446217A (en) * | 2018-09-17 | 2019-03-08 | 平安科技（深圳）有限公司 | Data method, electronic device and computer readable storage medium |
-
2019
- 2019-03-27 CN CN201910239432.0A patent/CN109992654B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109992654A (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390108B (en) | Task type interaction method and system based on deep reinforcement learning | |
| CN109992654B (en) | Information processing method and computer readable storage medium | |
| CN109514586B (en) | Method and system for realizing intelligent customer service robot | |
| CN108121800B (en) | Information generation method and device based on artificial intelligence | |
| CN107885796B (en) | Information recommendation method, device and equipment | |
| US10853421B2 (en) | Segmented sentence recognition method and device for human-machine intelligent question answer system | |
| CN111768231B (en) | Product information recommendation method and device | |
| CN111460290B (en) | Information recommendation method, device, equipment and storage medium | |
| CN111428010A (en) | Man-machine intelligent question and answer method and device | |
| CN108681871B (en) | Information prompting method, terminal equipment and computer readable storage medium | |
| CN112925911B (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
| CN112100491A (en) | Information recommendation method, device and equipment based on user data and storage medium | |
| CN115757725A (en) | Question and answer processing method and device, computer equipment and storage medium | |
| CN111048115A (en) | Voice recognition method and device | |
| WO2024215252A1 (en) | Question and answer method, and question and answer model training method | |
| CN111159378B (en) | Method and device for classifying problem description information | |
| CN112308570B (en) | Method and device for generating business rule output value | |
| CN115186179A (en) | Insurance product pushing method and device | |
| CN117708266A (en) | Intention recognition method, device, electronic equipment and storage medium | |
| CN114360549A (en) | Voice recognition error correction method and device, electronic equipment and storage medium | |
| CN113688222A (en) | Insurance sales task conversational recommendation method, system and equipment based on context semantic understanding | |
| CN112767123B (en) | Credit card issuing risk identification method and device | |
| CN117236984B (en) | User hierarchical management method and device, electronic equipment and storage medium | |
| CN113194144B (en) | Online service remote assistance method and device | |
| CN117273848A (en) | Product recommendation method, device, equipment and storage medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |