CN110929014A - Information processing method, information processing device, electronic equipment and storage medium - Google Patents
Information processing method, information processing device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110929014A CN110929014A CN201911249755.4A CN201911249755A CN110929014A CN 110929014 A CN110929014 A CN 110929014A CN 201911249755 A CN201911249755 A CN 201911249755A CN 110929014 A CN110929014 A CN 110929014A
- Authority
- CN
- China
- Prior art keywords
- information
- intention
- input
- user
- input information
- 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.)
- Granted
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- User Interface Of Digital Computer (AREA)
- Machine Translation (AREA)
Abstract
The application discloses an information processing method, an information processing device, electronic equipment and a storage medium. Therefore, feedback information can be selected by acquiring associated background information while intention analysis is not clear or intention information cannot be matched with unique feedback information, and the problems of poor user experience effect and excessive occupied processing resources caused by directly selecting information can be avoided.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.
Background
With the increasing popularity of smart devices, a user may have an intelligent session with the smart device, for example, the user may input a question to be consulted through the smart device, and then the smart device may push a corresponding answer to the user.
However, when the smart device confirms the feedback information based on the input information of the user, the feedback information corresponding to the analyzed intention of the user may not be unique. At this time, if the intelligent device directly outputs the feedback information, the user is required to select to determine the unique feedback information, the intellectualization of the intelligent device cannot be highlighted, and the experience effect of the user is reduced. On the other hand, in this case, if the smart device determines the unique answer, it needs to generate guidance information or analyze the user's intention again, which may consume excessive processing resources.
Disclosure of Invention
In view of this, the present application provides the following technical solutions:
an information processing method comprising:
receiving input information of a user;
analyzing the intention of the input information to obtain intention information matched with the input information;
if the intention information meets a specific condition, obtaining background information, wherein the background information represents information associated with the intention information, and the specific condition represents that the intention information cannot be matched with unique feedback information corresponding to the input information;
and determining target feedback information matched with the input information based on the background information.
Optionally, the performing intent analysis on the input information to obtain intent information matched with the input information includes:
inputting the input information into a pre-constructed intention recognition model, and determining predicted intention information corresponding to the input information through the intention recognition model;
wherein the intention recognition model has the capability of trending intention information corresponding to the input information towards an actual intention corresponding to the input information; and the intention model is a model obtained by training each obtained sample information respectively as the training input of the neural network, wherein the sample information is information matched with the input information.
Optionally, the feedback information that the specific condition characterizes and matches with the intention information includes at least two pieces of information, and the obtaining the context information includes:
and acquiring first input information of a user aiming at the feedback information, wherein the first input information comprises part of keywords of the feedback information, and the first input information is the background information.
Optionally, the determining target feedback information matching the input information based on the context information includes:
and screening the feedback information based on the first input information to determine target feedback information.
Optionally, the obtaining of the context information includes:
judging whether storage information matched with the user exists or not, and if so, analyzing the feedback information to obtain a target keyword;
and extracting information in the storage information according to the target keyword to obtain background information.
Optionally, the extracting information from the storage information according to the target keyword to obtain background information includes:
inputting the target keyword into a pre-constructed information identification model, and determining predicted background information corresponding to the target keyword through the information identification model;
the information identification model has the capacity of enabling the background information corresponding to the target keyword to tend to the actual background information corresponding to the target keyword; the information identification model is obtained by training each obtained sample information as the training input of the neural network, and the sample information is keyword information.
Optionally, the determining target feedback information matching the input information based on the context information includes:
determining target feedback information matching the input information based on the context information and the intention information.
An information processing apparatus comprising:
a receiving unit for receiving input information of a user;
the analysis unit is used for carrying out intention analysis on the input information to obtain intention information matched with the input information;
an obtaining unit, configured to obtain context information if the intention information satisfies a specific condition, where the context information represents information associated with the intention information, and the specific condition represents that the intention information cannot match with unique feedback information corresponding to the input information;
and the determining unit is used for determining target feedback information matched with the input information based on the background information.
An electronic device, comprising:
a memory for storing a program;
a processor configured to execute the program, the program specifically configured to:
receiving input information of a user;
analyzing the intention of the input information to obtain intention information matched with the input information;
if the intention information meets a specific condition, obtaining background information, wherein the background information represents information associated with the intention information, and the specific condition represents that the intention information cannot be matched with unique feedback information corresponding to the input information;
and determining target feedback information matched with the input information based on the background information.
A storage medium storing computer program code which, when executed, implements an information processing method as in any one of the above.
According to the technical scheme, the information processing method, the information processing device, the electronic equipment and the storage medium are disclosed, input information of a user is received, intention analysis is carried out on the input information to obtain intention information, the intention information meets specific conditions, background information is obtained, and target feedback information matched with the input information is determined based on the background information. Therefore, feedback information can be selected by acquiring associated background information while intention analysis is not clear or intention information cannot be matched with unique feedback information, and the problems of poor user experience effect and excessive occupied processing resources caused by directly selecting information can be avoided.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced 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 to obtain other drawings based on the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of an information processing method according to an embodiment of the present application;
FIG. 2 is a diagram of a user interface with a voice assistant in the prior art;
FIG. 3 is a diagram of an interface for a user to interact with a voice assistant according to an embodiment of the present application;
FIG. 4 is a schematic view of another interactive interface according to an embodiment of the present application;
fig. 5 is a schematic flowchart of a method for obtaining background information according to an embodiment of the present application;
fig. 6 is a schematic flowchart illustrating a method for obtaining answer information according to an embodiment of the present disclosure;
FIG. 7 is a spatial diagram of background information of a user according to an embodiment of the present disclosure;
FIG. 8 is a spatial diagram of the intended answers of the user provided by the embodiment of the present application;
fig. 9 is a schematic structural diagram of an information processing apparatus according to an embodiment of 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.
The information processing method described in the embodiments of the present application can be applied in the field of intelligent response, such as intelligent client, voice assistant, intelligent robot, and other related applications or entities. The method mainly aims at how to realize accurate feedback of information under the condition that the unique feedback information cannot be directly obtained or only a series of guide words need to be generated in the prior art, and can reduce the occupation of excessive processing resources in the process of screening a plurality of feedback information or intentions by a processing system.
Referring to fig. 1, a schematic flow chart of an information processing method provided in an embodiment of the present application is shown, where the method may include the following steps:
s101, receiving input information of a user.
Because the information processing method provided by the application is applied to the field of intelligent question answering, the input information of the user can be character information, audio information, image information and the like. The input information of the user can be received through the terminal used by the user, for example, when the user triggers a certain application of the terminal, the input information of the user can be received through the application. Or when the user inputs the wake-up word of a certain function, for example, after the user outputs the wake-up word of a certain voice assistant, the voice assistant wakes up the voice interaction function according to the wake-up word and receives the input information sent by the user. The input information of the user is the voice information of the user.
And S102, performing intention analysis on the input information to obtain intention information matched with the input information.
And S103, if the intention information meets a specific condition, acquiring background information.
After the input information of the user is obtained, the intention analysis needs to be performed on the input information to obtain intention information matched with the input information. The intention information represents the intention of the user to input information, i.e., feedback of what is desired to be obtained through the input information. If the input information of the user is "time", the corresponding intention information may be "acquire current time information"; the input information of the user is "next week 15:30 refers to the meeting in the region of one's word", and the corresponding intention information is "memo information is described".
Therefore, the input information of the user is different, and the intention information matched with the input information is different. When the intention information of the user is acquired, the feature information of the input information is extracted to obtain the keywords of the input information, and the corresponding intention information is obtained according to the matching of the keywords and the intention information. The neural network can also be used for training the information samples to obtain corresponding models, input information is input into the trained models, and corresponding intention information is obtained through recognition and classification of the models. Specific procedures the present application will be described in detail in the following examples.
After the intention information of the user is obtained in the existing scheme, the feedback information matched with the intention information is directly output. After the intention information is obtained, the process of generating the feedback information is not directly performed, but the intention information needs to be judged, and if the intention information meets a specific condition, the background information is obtained. Wherein the background information characterizes information associated with the intent information, and the specific condition characterizing intent information cannot match unique feedback information corresponding to the input information.
The context information is information associated with intention information, and since the intention information corresponds to input information of a user, that is, the intention information is information associated with the user, the context information represents relevant context information of the user, may be identification information of the user, or information associated with previous input information input by the user. For example, the context information may include information such as the identity, location, age, gender, etc. of the user.
It should be noted that, in the embodiment of the present application, only when the intention information satisfies a specific condition, the background information is obtained. The calling of related resources can be reduced, and excessive processing resources are avoided. That is, when the intention information cannot match the unique feedback information, the background information is acquired. It can be understood that, if the intention analysis is performed according to the input information of the user, the obtained feedback information is not unique. If the information input by the user is a question, the background information is obtained when the corresponding feedback information is a plurality of answers. This background information may assist in obtaining a more accurate answer.
And S104, determining target feedback information matched with the input information based on the background information.
After the background information is obtained, the target feedback information is determined according to the background information and the intention information. Therefore, the target feedback information is obtained by selecting among a plurality of feedback information according to the background information.
Referring to FIG. 2, which shows an interface diagram of a user interacting with a voice assistant in the prior art, the interaction between the user and the voice assistant in FIG. 2 is as follows:
the user: you are good, I live in Beijing.
The voice assistant: you are good and happy to serve you.
The user: please give me the address of the service center.
The voice assistant: please choose what you need at the service center address below.
Tokyo: region and mark
London: street and number
Beijing: first street of zone
It can be seen from the interaction process presented in fig. 2 between the user and the voice assistant that the interaction process is not intelligent, the address of the service center output by the voice assistant is not unique, and the user is required to make a selection, so that the user feels that the voice assistant is not intelligent, even if the user provides information that can determine the output answer, the information is not utilized in the process, and the user needs to select the answer again. Therefore, the experience effect of the user is poor, and the output feedback information is not unique and occupies output resources.
Referring to fig. 3, which shows an interface diagram of a user interacting with a voice assistant according to an embodiment of the present application, in fig. 3, the user interacting with the voice assistant is as follows:
the user: you are good, I live in Beijing.
The voice assistant: you are good and happy to serve you.
The user: please give me the address of the service center.
The voice assistant: beijing: first street in the region.
It can be seen that, in the embodiment of the present application, when processing the input information of the user, the background information input by the user, that is, the region information "beijing" input by the user is used, and then when performing the intention analysis, the address of the service center that the user needs to obtain is obtained, and the address is directly located at the service center that obtains beijing, and then is output as the output answer. Therefore, on one hand, the output answer is unique and accurate, on the other hand, the user is prevented from selecting the answer again, and the experience effect of the user is improved.
The application discloses an information processing method, which includes the steps of receiving input information of a user, conducting intention analysis on the input information to obtain intention information, obtaining background information when the intention information meets specific conditions, and determining target feedback information matched with the input information based on the background information. Therefore, feedback information can be selected by acquiring associated background information while intention analysis is not clear or intention information cannot be matched with unique feedback information, and the problems of poor user experience effect and excessive occupied processing resources caused by directly selecting information can be avoided.
The respective technical features in the above-described embodiments are explained in detail below.
In another embodiment of the present application, intention information corresponding to a user may be acquired by a method using an artificial neural network. Namely, the process of acquiring the intention information includes:
s201, inputting the input information into a pre-constructed intention recognition model, and determining predicted intention information corresponding to the input information through the intention recognition model.
The intention recognition model has the capability of inputting an actual intention corresponding to the input information in an intention information area corresponding to the input information; and the intention model is a model obtained by training each obtained sample information respectively as the training input of the neural network, and the sample information is information matched with the input information. That is, the sample information may be the same application scenario or input information generated in the application environment as the input information of the user, such as historical input information of the user.
In order to achieve accurate user intention analysis, the intention information of the user is specifically analyzed from the input information of the user by using an intention recognition model trained on the basis of big data.
Specifically, in a model training phase, it is required to first obtain a plurality of pieces of historical input data as a training sample set, and perform manual labeling on each piece of historical input data in the training sample set, where a user intention corresponding to each piece of historical input data needs to be accurately labeled during labeling, so that the labeling information of each piece of historical input data may include zero or one or more pieces of user intention labeling information.
After the intention information of the historical input data is labeled, training of an intention recognition model can be conducted based on each training sample labeled with user intention information, and when the model is trained, the intention recognition model can adopt a text classification model, such as an SVM (Support Vector Machine), a CNN (Convolutional Neural Network), an LSTM (Long Short-Term Memory Network) or the like; an information extraction model such as CRF (conditional random field algorithm), LSTM + CRF, etc. may also be selected, or a text classification model and an information extraction model may also be effectively fused.
On the basis of completing model training, the input information of the user can be used as the input information of the intention recognition model to be input into the model, and the intention information set of the user is output after the model processes the input information of the user. For example, the user's input is "where i want to know the nearest bus stop", and the model may output a set of user intent information { address of bus stop }.
In the embodiment of the present application, the background information is acquired only when the intention information satisfies a specific condition. The specific condition representation intention information cannot be matched with the unique feedback information corresponding to the input information. That is, when the input information of the user is "day of the week" and the analysis user's intention is that the user wants to know that the day is day of the week, the answer is unique, so that the corresponding answer is directly output, for example, "day of the week", and the answer is determined without acquiring background information. The specific condition characterization intention information cannot be matched with the unique feedback information corresponding to the input information, and the analysis can obtain a plurality of intentions, namely the intentions can be matched with the feedback information; analysis may also include obtaining one intent message, but the intent message may result in multiple feedback messages.
If the feedback information matched with the characteristic condition representation and the intention information at least comprises two pieces of information, the obtaining of the background information comprises:
s301, first input information of the user for the feedback information is obtained.
Wherein the first input information comprises a part of keywords of the feedback information, and the first input information is used as background information.
It should be noted that part of the keywords of the feedback information may be obtained by directly extracting the feedback information, or may be obtained by performing semantic information on the feedback information. The background information may be acquired after the feedback information is output, or may be prepared to output the feedback information. For example, if all the feedback information represents information about a location, the first input information obtained is a location keyword. And if the feedback information is obtained through voice analysis, and all the feedback information included in the feedback information is related to the age, the obtained first input information is an age keyword.
Correspondingly, the determining the target feedback information matched with the input information based on the background information includes:
s302, screening the feedback information based on the first input information, and determining target feedback information.
Because the first input information represents part of keywords of the feedback information, the first information can be used for screening a plurality of pieces of feedback information to obtain target feedback information with the highest matching degree with the user background and intention.
The first input information may also be used to determine an output mode of the target feedback information when determining the target feedback information. For example, the first input information is used for determining the sorting of the feedback information, and the target feedback information is arranged at the head of the feedback information; or the target feedback information is displayed, and other display information except the target feedback information is output in a hidden mode, for example, the feedback information except the target feedback information is output in a pull-down list mode.
Referring to FIG. 4, a schematic diagram of another interactive interface of an embodiment of the present application is shown.
Fig. 4(a) shows an output mode in which the feedback information is output first and then the target feedback information is output; an output model for directly outputting feedback information is shown in fig. 4 (b).
The interaction process of the user with the voice assistant in FIG. 4(a) is:
the user: the vaccination site.
The voice assistant: floor No. 1 of epidemic prevention center, floor 2, 0-3 years old;
3-18 years old in storied 3 of epidemic prevention center 1;
The user: and the age of 15 years.
The voice assistant: epidemic prevention center floor 1 and floor 3.
According to the interaction process of the user and the voice assistant in fig. 4(a), it can be known that the two times before and after the user respectively input the "vaccination site" and the "15 years old". Although the user inputs information for many times in the process, the difference is that the information can not be effectively correlated twice in the prior art, or the user needs to rely on the prompt information of the voice assistant to input again when inputting information for the second time. In the embodiment of the application, the information input by the user can be combined twice, and for the processor corresponding to the voice assistant, the processor does not need to generate a prompt or guide information to assist the user in inputting the information again, so that the complexity of information processing and the waste of resources can be reduced.
The user interaction process with the voice assistant shown in FIG. 4(b) is:
the user: you good, I am 15 years old this year.
The voice assistant: you are good, very happy to serve you.
The user: the vaccination site.
The voice assistant: floor No. 1 and floor No. 3 in epidemic prevention center.
In fig. 4(b), when the user interacts with the voice assistant, the processor corresponding to the voice assistant may record input information of the user each time when processing an interaction process with the user, so that when the user inputs a question, the user may combine previously input background information to effectively filter answers and obtain target feedback information.
In another embodiment of the present application, a method for obtaining background information is further provided, and referring to fig. 5, a flowchart of a method for obtaining background information according to an embodiment of the present application is shown, where the method may include the following steps:
s401, judging whether storage information matched with a user exists or not, and if yes, executing S402;
s402, analyzing the feedback information to obtain a target keyword;
and S403, extracting information from the stored information according to the target keyword to obtain background information.
The embodiment of the application can analyze and store daily input information of the user, and extract some basic information of the user as background information of the user by taking the user as a center. Such background information may include the user's name, age, gender, birthday, native place, location and terminal device information, etc. When the background information needs to be acquired, whether the existing database has the storage information matched with the user or not can be judged, and if the existing database has the storage information matched with the user, the storage information still needs to be extracted or screened. Rather than directly applying all of the stored context information in its entirety, this increases the amount of computation and wastes additional data resources. At this time, it is necessary to analyze the feedback information matched with the intention information to obtain the target keyword. The target keyword may be obtained by summarizing each piece of feedback information, or may be partial information representing the semantics of the feedback information. And then extracting the stored information according to the target keywords to obtain background information. If the target keyword is age, information related to the age of the user is extracted from the stored information as background information.
Specifically, information extraction is performed in the storage information according to the target keyword to obtain the background information, and the following method is used for realizing the following steps:
enabling the target keywords to belong to a pre-constructed information identification model, and determining predicted background information corresponding to the target scissors through the information identification model;
the information identification model has the capability of enabling the background information corresponding to the target keyword to tend to the actual background information corresponding to the target keyword; and the information identification model is a model obtained by training by taking each obtained sample information as the training input of the neural network, and the sample information is keyword information.
Therefore, the process of acquiring the background information is more intelligent, and the background information is more quickly searched.
In the embodiment of the present invention, when the feedback information corresponding to the intention information is not unique, the feedback information may not be directly output, the background information is obtained according to the feedback information, and then the target feedback information is determined according to the background information and the intention information. The output feedback information is normalized and more accurate. For example, if the intention information of the user is "get bus stop" and the background information is "current location information of the user", the target feedback information "bus stop nearest to the user" may be obtained.
In another possible implementation, the input information of the user may be more embodied by using the background information and the input information, so that the input information corresponds to the unique or precise feedback information. For example, the input information of the user is "mobile phone maintenance store address", and the background information corresponding to the user is "city a is city D zone". Then, through the input information and the background information of the user, the mobile phone maintenance store address located in the area D of the city a when the accurate input information of the user is obtained can be obtained, so that the feedback information can be more accurate according to the accurate input information, that is, the mobile phone maintenance store address in the feedback information can be located in the area D of the city a, and the range of the feedback information obtained according to the initial input information of the user is reduced.
The present application is described by taking an intelligent session scenario as an example, and referring to fig. 6, a schematic flow chart of a method for obtaining answer information provided in the embodiment of the present application is shown, where the method includes the following steps:
s501, acquiring current input information of a user;
s502, extracting an intention space of the user according to the current input information;
s503, extracting an answer space corresponding to the intention space of the user;
s504, extracting background information of the user;
and S505, selecting answer information matched with the user background by using the answer space and the background information.
Referring to fig. 7, a background information space diagram of a user provided by an embodiment of the present application is shown. Namely, all the current and previous background information of the user is extracted. The user context information as extracted includes: name, age, gender, date of birth, place of departure, location, equipment, etc.
Referring to fig. 8, a spatial diagram of an intended answer of a user provided by an embodiment of the present application is shown. Analyzing all intentions of the information input by the user to obtain an intention set consisting of a plurality of intention information, wherein reasonable intention information can be sorted in a descending order according to weight, and the highest-sorted intention can be selected according to requirements. Namely, when the input information of the user corresponds to a plurality of intentions, the selection is carried out according to the weight of the intentions. And each intention has a corresponding number of answer information.
Therefore, final answer information matched with the user background can be determined according to the answer information and the background information. It should be noted that not all answers are related to the background information, in which case the answer information is directly output.
For example, in part of examples for solving the problem of the smart customer service system of the mobile phone product, the processing procedure is as follows:
example 1:
the user: HI, I is from China, I has a mobile phone A;
intelligent customer service: you are good and happy to serve you;
the user: a service center.
The treatment process comprises the following steps:
extracting all background information of the user { native place-China; mobile phone brand-A };
extracting the current input intention { service center };
searching a corresponding answer space { American service center, China service center } according to the intention;
according to the answer space and the background information, obtaining a user background answer { Chinese service center-W city M street }, and then outputting the user background answer.
Example 2:
the user: HI, i lived in india this year 80 years old;
intelligent customer service: you are good and happy to serve you;
the user: please give me the telephone number of the proxy center.
The processing flow is as follows:
extracting all background information of the user: { residence-india; age-80 };
extracting the intent of the current input: { telephone number of agent center };
searching a corresponding answer space { a telephone number of an agent center of the United states; the telephone number of the agency center of china; telephone number of the indian agent center };
according to the answer space and the background information, the user background answer { the telephone number of the proxy center in india 234 909} is obtained and then output to the user answer.
There is also provided in an embodiment of the present application an information processing apparatus, referring to fig. 9, the apparatus including:
a receiving unit 10 for receiving input information of a user;
an analysis unit 11, configured to perform intent analysis on the input information to obtain intent information that matches the input information;
an obtaining unit 12, configured to obtain context information if the intention information satisfies a specific condition, where the context information represents information associated with the intention information, and the specific condition represents that the intention information cannot match with unique feedback information corresponding to the input information;
a determining unit 13, configured to determine target feedback information matching the input information based on the context information.
The application discloses an information processing device, which receives input information of a user through a receiving unit, an analyzing unit performs intention analysis on the input information to obtain intention information, an acquiring unit acquires background information when the intention information meets specific conditions, and a determining unit determines target feedback information matched with the input information based on the background information. Therefore, feedback information can be selected by acquiring associated background information while intention analysis is not clear or intention information cannot be matched with unique feedback information, and the problems of poor user experience effect and excessive occupied processing resources caused by directly selecting information can be avoided.
On the basis of the above embodiment, the analysis unit includes:
the model analysis subunit is used for inputting the input information into a pre-constructed intention recognition model and determining predicted intention information corresponding to the input information through the intention recognition model;
wherein the intention recognition model has the capability of trending intention information corresponding to the input information towards an actual intention corresponding to the input information; and the intention model is a model obtained by training each obtained sample information respectively as the training input of the neural network, wherein the sample information is information matched with the input information.
On the basis of the foregoing embodiment, the feedback information that the specific condition representation matches the intention information includes at least two pieces of information, and the obtaining unit is specifically configured to:
and acquiring first input information of a user aiming at the feedback information, wherein the first input information comprises part of keywords of the feedback information, and the first input information is the background information.
Correspondingly, the determining unit is specifically configured to:
and screening the feedback information based on the first input information to determine target feedback information.
Optionally, the obtaining unit includes:
the judging subunit is used for judging whether the storage information matched with the user exists or not, and if so, analyzing the feedback information to obtain a target keyword;
and the extraction subunit is used for extracting information from the storage information according to the target keyword to obtain background information.
Optionally, the extracting subunit is specifically configured to:
inputting the target keyword into a pre-constructed information identification model, and determining predicted background information corresponding to the target keyword through the information identification model;
the information identification model has the capacity of enabling the background information corresponding to the target keyword to tend to the actual background information corresponding to the target keyword; the information identification model is obtained by training each obtained sample information as the training input of the neural network, and the sample information is keyword information.
On the basis of the foregoing embodiment, the determining unit is specifically configured to:
determining target feedback information matching the input information based on the context information and the intention information.
An embodiment of the present application further provides an electronic device, including:
a memory for storing a program;
a processor configured to execute the program, the program specifically configured to:
receiving input information of a user;
analyzing the intention of the input information to obtain intention information matched with the input information;
if the intention information meets a specific condition, obtaining background information, wherein the background information represents information associated with the intention information, and the specific condition represents that the intention information cannot be matched with unique feedback information corresponding to the input information;
and determining target feedback information matched with the input information based on the background information.
Further, the program is for:
the analyzing the intention of the input information to obtain intention information matched with the input information includes:
inputting the input information into a pre-constructed intention recognition model, and determining predicted intention information corresponding to the input information through the intention recognition model;
wherein the intention recognition model has the capability of trending intention information corresponding to the input information towards an actual intention corresponding to the input information; and the intention model is a model obtained by training each obtained sample information respectively as the training input of the neural network, wherein the sample information is information matched with the input information.
Further, the program is for:
the feedback information matched with the specific condition characterization and the intention information at least comprises two pieces of information, and the obtaining of the background information comprises:
and acquiring first input information of a user aiming at the feedback information, wherein the first input information comprises part of keywords of the feedback information, and the first input information is the background information.
Further, the program is for:
the determining target feedback information matching the input information based on the context information includes:
and screening the feedback information based on the first input information to determine target feedback information.
Optionally, the obtaining of the context information includes:
judging whether storage information matched with the user exists or not, and if so, analyzing the feedback information to obtain a target keyword;
and extracting information in the storage information according to the target keyword to obtain background information.
Optionally, the extracting information from the storage information according to the target keyword to obtain background information includes:
inputting the target keyword into a pre-constructed information identification model, and determining predicted background information corresponding to the target keyword through the information identification model;
the information identification model has the capacity of enabling the background information corresponding to the target keyword to tend to the actual background information corresponding to the target keyword; the information identification model is obtained by training each obtained sample information as the training input of the neural network, and the sample information is keyword information.
Optionally, the determining target feedback information matching the input information based on the context information includes:
determining target feedback information matching the input information based on the context information and the intention information.
An embodiment of the present application further provides a storage medium, where the storage medium stores computer program code, and when the computer program code is executed, the information processing method according to any one of the above-mentioned items is implemented.
The emphasis of each embodiment in the present specification is on the difference from the other embodiments, and the same and similar parts among the various embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An information processing method comprising:
receiving input information of a user;
analyzing the intention of the input information to obtain intention information matched with the input information;
if the intention information meets a specific condition, obtaining background information, wherein the background information represents information associated with the intention information, and the specific condition represents that the intention information cannot be matched with unique feedback information corresponding to the input information;
and determining target feedback information matched with the input information based on the background information.
2. The method of claim 1, wherein the analyzing the intent of the input information for intent information matching the input information comprises:
inputting the input information into a pre-constructed intention recognition model, and determining predicted intention information corresponding to the input information through the intention recognition model;
wherein the intention recognition model has the capability of trending intention information corresponding to the input information towards an actual intention corresponding to the input information; and the intention model is a model obtained by training each obtained sample information respectively as the training input of the neural network, wherein the sample information is information matched with the input information.
3. The method of claim 1, the specific condition characterizing the feedback information matching the intention information includes at least two pieces of information, and the obtaining context information includes:
and acquiring first input information of a user aiming at the feedback information, wherein the first input information comprises part of keywords of the feedback information, and the first input information is the background information.
4. The method of claim 3, the determining target feedback information that matches the input information based on the context information, comprising:
and screening the feedback information based on the first input information to determine target feedback information.
5. The method of claim 1, the obtaining context information comprising:
judging whether storage information matched with the user exists or not, and if so, analyzing the feedback information to obtain a target keyword;
and extracting information in the storage information according to the target keyword to obtain background information.
6. The method of claim 5, wherein extracting information from the stored information according to the target keyword to obtain background information comprises:
inputting the target keyword into a pre-constructed information identification model, and determining predicted background information corresponding to the target keyword through the information identification model;
the information identification model has the capacity of enabling the background information corresponding to the target keyword to tend to the actual background information corresponding to the target keyword; the information identification model is obtained by training each obtained sample information as the training input of the neural network, and the sample information is keyword information.
7. The method of claim 5, the determining target feedback information that matches the input information based on the context information, comprising:
determining target feedback information matching the input information based on the context information and the intention information.
8. An information processing apparatus comprising:
a receiving unit for receiving input information of a user;
the analysis unit is used for carrying out intention analysis on the input information to obtain intention information matched with the input information;
an obtaining unit, configured to obtain context information if the intention information satisfies a specific condition, where the context information represents information associated with the intention information, and the specific condition represents that the intention information cannot match with unique feedback information corresponding to the input information;
and the determining unit is used for determining target feedback information matched with the input information based on the background information.
9. An electronic device, comprising:
a memory for storing a program;
a processor configured to execute the program, the program specifically configured to:
receiving input information of a user;
analyzing the intention of the input information to obtain intention information matched with the input information;
if the intention information meets a specific condition, obtaining background information, wherein the background information represents information associated with the intention information, and the specific condition represents that the intention information cannot be matched with unique feedback information corresponding to the input information;
and determining target feedback information matched with the input information based on the background information.
10. A storage medium storing computer program code which, when executed, implements an information processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249755.4A CN110929014B (en) | 2019-12-09 | 2019-12-09 | Information processing method, information processing device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911249755.4A CN110929014B (en) | 2019-12-09 | 2019-12-09 | Information processing method, information processing device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929014A true CN110929014A (en) | 2020-03-27 |
| CN110929014B CN110929014B (en) | 2023-05-23 |
Family
ID=69857617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911249755.4A Active CN110929014B (en) | 2019-12-09 | 2019-12-09 | Information processing method, information processing device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929014B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111930904A (en) * | 2020-07-08 | 2020-11-13 | 联想(北京)有限公司 | Information response method, device, equipment and storage medium |
| CN112131364A (en) * | 2020-09-22 | 2020-12-25 | 沈阳东软智能医疗科技研究院有限公司 | Question answering method, device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
| CN106383875A (en) * | 2016-09-09 | 2017-02-08 | 北京百度网讯科技有限公司 | Artificial intelligence-based man-machine interaction method and device |
| CN109063100A (en) * | 2018-07-27 | 2018-12-21 | 联想(北京)有限公司 | A kind of data processing method, server and electronic equipment |
| CN109697230A (en) * | 2018-12-26 | 2019-04-30 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| WO2019084810A1 (en) * | 2017-10-31 | 2019-05-09 | 腾讯科技（深圳）有限公司 | Information processing method and terminal, and computer storage medium |
| CN110334201A (en) * | 2019-07-18 | 2019-10-15 | 中国工商银行股份有限公司 | A kind of intension recognizing method, apparatus and system |
-
2019
- 2019-12-09 CN CN201911249755.4A patent/CN110929014B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951456A (en) * | 2014-03-26 | 2015-09-30 | 上海智臻网络科技有限公司 | Method, device and equipment used for obtaining answer information |
| CN106383875A (en) * | 2016-09-09 | 2017-02-08 | 北京百度网讯科技有限公司 | Artificial intelligence-based man-machine interaction method and device |
| WO2019084810A1 (en) * | 2017-10-31 | 2019-05-09 | 腾讯科技（深圳）有限公司 | Information processing method and terminal, and computer storage medium |
| CN109063100A (en) * | 2018-07-27 | 2018-12-21 | 联想(北京)有限公司 | A kind of data processing method, server and electronic equipment |
| CN109697230A (en) * | 2018-12-26 | 2019-04-30 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN110334201A (en) * | 2019-07-18 | 2019-10-15 | 中国工商银行股份有限公司 | A kind of intension recognizing method, apparatus and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111930904A (en) * | 2020-07-08 | 2020-11-13 | 联想(北京)有限公司 | Information response method, device, equipment and storage medium |
| CN112131364A (en) * | 2020-09-22 | 2020-12-25 | 沈阳东软智能医疗科技研究院有限公司 | Question answering method, device, electronic equipment and storage medium |
| CN112131364B (en) * | 2020-09-22 | 2024-03-26 | 沈阳东软智能医疗科技研究院有限公司 | Question answering method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929014B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832286B (en) | Intelligent interaction method, equipment and storage medium | |
| CN110765244B (en) | Method, device, computer equipment and storage medium for obtaining answering operation | |
| KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
| CN105183761B (en) | Sensitive word replacing method and device | |
| CN110597952A (en) | Information processing method, server, and computer storage medium | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| CN104765791A (en) | Information inputting method and device | |
| CN110187780B (en) | Long text prediction method, long text prediction device, long text prediction equipment and storage medium | |
| CN109710739B (en) | Information processing method and device and storage medium | |
| CN108038165B (en) | Information searching method, searching device, terminal equipment and server equipment | |
| CN109684455A (en) | The implementation method and device of intelligent customer service system, equipment, readable storage medium storing program for executing | |
| CN113360622A (en) | User dialogue information processing method and device and computer equipment | |
| CN110597965B (en) | Emotion polarity analysis method and device for article, electronic equipment and storage medium | |
| CN114757176A (en) | Method for obtaining target intention recognition model and intention recognition method | |
| CN110929014B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110110143B (en) | Video classification method and device | |
| CN110750626B (en) | Scene-based task-driven multi-turn dialogue method and system | |
| CN112579031A (en) | Voice interaction method and system and electronic equipment | |
| CN112532507A (en) | Method and device for presenting expression image and method and device for sending expression image | |
| CN113901837A (en) | Intention understanding method, device, equipment and storage medium | |
| CN110874399A (en) | Information processing method and device, computing equipment and terminal | |
| CN114491010A (en) | Training method and device of information extraction model | |
| CN110209804B (en) | Target corpus determining method and device, storage medium and electronic device | |
| CN109683727A (en) | A kind of data processing method and device |
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 |