CN110008331B - Information display method and device, electronic equipment and computer readable storage medium - Google Patents
Information display method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110008331B CN110008331B CN201910300538.7A CN201910300538A CN110008331B CN 110008331 B CN110008331 B CN 110008331B CN 201910300538 A CN201910300538 A CN 201910300538A CN 110008331 B CN110008331 B CN 110008331B
- Authority
- CN
- China
- Prior art keywords
- information
- session
- user
- candidate
- context 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
Abstract
The embodiment of the invention discloses an information display method, an information display device, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: when session trigger operation of a user is received, acquiring context information based on the session trigger operation, wherein the context information is information acquired based on historical operation of the user; and determining first candidate information corresponding to the session triggering operation according to the context information, and displaying the first candidate information to the user. According to the scheme of the invention, the corresponding context information can be acquired based on the session triggering operation of the user, the first candidate information corresponding to the session triggering operation is determined to be displayed to the user based on the context information, and the context information is acquired based on the historical operation of the user, so that the determined first candidate information can better reflect the real intention of the user, more accurate candidate information is provided for the user to perform related processing based on the session triggering operation, and the interaction experience of the user is improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to an information display method and apparatus, an electronic device, and a computer-readable storage medium.
Background
In the prior art, when a user carries out a conversation, a system provides some template sentences for replying for the user based on information currently input by the user, and the user can select information to be replied next in the template sentences.
Disclosure of Invention
In view of this, embodiments of the present invention provide an information displaying method, an information displaying apparatus, an electronic device, and a computer-readable storage medium, which can provide a function of providing accurate candidate information for a user.
In order to solve the above problems, embodiments of the present invention mainly provide the following technical solutions:
in a first aspect, an embodiment of the present invention provides an information display method, where the method includes:
when session trigger operation of a user is received, acquiring context information based on the session trigger operation, wherein the context information is information acquired based on historical operation of the user;
and determining first candidate information corresponding to the session triggering operation according to the context information, and displaying the first candidate information to the user.
In an optional embodiment of the present invention, determining, according to the context information, first candidate information corresponding to a session trigger operation includes:
and determining first candidate information corresponding to the session triggering operation according to the information associated with the session triggering operation in the context information.
In an optional embodiment of the present invention, if the context information is not acquired or the acquired context information is not related to the session trigger operation, the method further includes:
determining second candidate information corresponding to the session triggering operation according to a pre-configured first-word corpus;
and displaying the second candidate information to the user.
In an optional embodiment of the present invention, determining, according to information associated with a session trigger operation in context information, first candidate information corresponding to the session trigger operation includes:
determining information associated with the session triggering operation according to the session type corresponding to the session triggering operation;
based on the information associated with the session triggering operation, first candidate information corresponding to the session triggering operation is determined.
In an optional embodiment of the present invention, if the context information includes related information of a contact, the first candidate information includes contact information of the contact;
if the context information includes the relevant information of the event, the first candidate information includes text information associated with the event.
In an optional embodiment of the present invention, if the context information includes information related to an event, determining, according to the context information, first candidate information corresponding to a session trigger operation includes:
acquiring first candidate information corresponding to session triggering operation from a session corpus based on keywords in the relevant information of the event;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
In an optional embodiment of the present invention, if at least two pieces of information in the context information each include related information of a contact, before the first candidate information is presented to the user, the method further includes:
and determining the arrangement sequence of the contact information of the contact persons corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information.
In an optional embodiment of the present invention, if the text information includes at least two pieces of text information, before presenting the first candidate information to the user, the method further includes:
determining the similarity between the context information and each piece of text information in at least two pieces of text information;
and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
In an alternative embodiment of the invention, the method further comprises:
and reordering at least two pieces of text information after sequencing based on the personalized information of the user.
In an optional embodiment of the present invention, the context information is context information within a set duration taking the current time as the end time.
In a second aspect, an embodiment of the present invention further provides an information display apparatus, where the apparatus includes:
the context information acquisition module is used for acquiring context information based on session trigger operation when session trigger operation of a user is received, wherein the context information is information acquired based on historical operation of the user;
and the candidate information display module is used for determining first candidate information corresponding to the session triggering operation according to the context information and displaying the first candidate information to the user.
In an optional embodiment of the present invention, when determining, according to the context information, first candidate information corresponding to the session trigger operation, the candidate information presentation module is specifically configured to:
and determining first candidate information corresponding to the session triggering operation according to the information associated with the session triggering operation in the context information.
In an optional embodiment of the present invention, the candidate information displaying module is further configured to, when the context information is not acquired or the acquired context information is not related to the session triggering operation, determine, according to a preconfigured first language corpus, second candidate information corresponding to the session triggering operation, and display the second candidate information to the user.
In an optional embodiment of the present invention, when determining, according to information associated with the session trigger operation in the context information, the first candidate information corresponding to the session trigger operation, the candidate information presentation module is specifically configured to:
determining information associated with the session triggering operation in the context information according to the session type corresponding to the session triggering operation;
based on the information associated with the session triggering operation, first candidate information corresponding to the session triggering operation is determined.
In an optional embodiment of the present invention, if the context information includes related information of a contact, the first candidate information includes contact information of the contact;
if the context information includes the relevant information of the event, the first candidate information includes text information associated with the event.
In an optional embodiment of the present invention, if the context information includes information related to an event, the candidate information display module is specifically configured to, when determining, according to the context information, first candidate information corresponding to the session trigger operation:
acquiring first candidate information corresponding to session triggering operation from a session corpus based on keywords in the relevant information of the event;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
In an alternative embodiment of the invention, the apparatus further comprises:
and the contact information sorting module is used for determining the arrangement sequence of the contact information of the contacts corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information before the at least two pieces of information in the context information respectively comprise the related information of the contacts and the first candidate information is displayed to the user.
In an alternative embodiment of the invention, the apparatus further comprises:
the text information ordering module is used for determining the similarity between the context information and each piece of text information in the at least two pieces of text information before the text information comprises at least two pieces of text information and the first candidate information is displayed to the user; and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
In an optional embodiment of the present invention, the text information sorting module is further configured to reorder the at least two pieces of text information after sorting based on personalized information of the user.
In an optional embodiment of the present invention, the context information is context information within a set duration taking the current time as the end time.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes a processor;
and a memory, a bus connected with the processor; wherein:
the processor and the memory complete mutual communication through the bus;
the processor is adapted to invoke program instructions in the memory to perform a method as shown in the first aspect of the invention or any alternative embodiment of the first aspect.
In a fourth aspect, the embodiments of the present invention also provide a computer-readable storage medium, which stores computer instructions, the computer instructions causing a computer to execute the method shown in the embodiments of the first aspect of the present invention.
By the technical scheme, the technical scheme provided by the embodiment of the invention at least has the following advantages:
the information display method, the information display device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention, the corresponding context information can be obtained based on the session triggering operation of the user, the first candidate information corresponding to the session triggering operation and determined based on the context information is displayed to the user, because the context information is the information acquired based on the historical operation of the user, the first candidate information corresponding to the session triggering operation determined based on the context information can better reflect the real intention of the user, by the scheme of the embodiment of the invention, the user response, namely the potential operation processing mode of the user, can be well predicted based on the context information, and more accurate candidate information is provided for the user to perform relevant processing based on the session triggering operation, so that the interaction experience of the user is improved, and the actual application requirements are better met.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the embodiments of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flow chart illustrating an information presentation method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an information presentation apparatus according to an embodiment of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
An embodiment of the present invention provides an information display method, and as shown in fig. 1, the method provided in the embodiment of the present invention may include:
step S110, when receiving a session trigger operation of a user, acquiring context information based on the session trigger operation.
The session refers to an operation of interaction between the user and another user or the interaction platform, and may include, but is not limited to, short message interaction (such as sending a short message and sending a picture), call interaction (such as making a call), and the like. The session triggering operation refers to an operation that a user wants to start a session, for example, an operation of opening a certain instant messaging application program to enter a session interface of the program, an action of opening call software to enter a related interface (for example, an action of clicking an address book to enter an address book list), and the like. The invention does not limit the implementation form of the session triggering operation, and can be triggered by voice or touch.
The context information is information acquired based on a historical operation of the user, and specifically may be information directly or indirectly acquired based on the historical operation of the user, where the historical operation refers to an operation performed by the user on the terminal device, and may include, but is not limited to, an operation performed by the user on an application on the terminal device, a setting operation performed by the user on the terminal device, and the like. As an example, for example, upon detecting that the user purchased a movie ticket for two pm (assuming that the movie name is a) on movie ticket purchasing software on a mobile terminal or a PC or the like, a piece of context information may be generated based on the operation of the user and the end time of the movie (four pm, below), and specifically, may be "movie a was viewed at 14 to 16 pm".
Step S120, according to the context information, determining first candidate information corresponding to the session triggering operation, and displaying the first candidate information to the user.
Since the context information is obtained based on the historical operation of the user, the intention of the user for the next operation can be inferred based on the context information, and the first candidate information determined based on the context information can accurately provide the reference information which may be needed for the user, that is, the first candidate information can provide relevant reference information for the next operation of the user.
In practical application, the context information is context information within a set duration taking the current time as the end time.
The set time length can be configured based on actual requirements, and when the context information is acquired based on the session triggering operation of the user, in order to predict the intention of the current session triggering operation of the user, the context information in the set time length with the current time as the ending time can be selected, that is, the context information in the set time period before the current time is selected, and the context information in the set time period can reflect the real intention of the user more accurately.
In an example, if the set time length is 5 minutes and the current time is 8 o ' clock and 10 minutes, the obtained context information is information from 8 o ' clock and 5 minutes to 8 o ' clock and 10 minutes.
In practical applications, the first candidate information may include a plurality of candidate sentences, and the candidate sentences may be provided to the user in the form of a candidate sentence list for the user to conveniently view.
According to the scheme provided by the embodiment of the invention, the corresponding context information can be acquired based on the session triggering operation of the user, the first candidate information corresponding to the session triggering operation and determined based on the context information is displayed to the user, and the context information is acquired based on the historical operation of the user, so that the first candidate information corresponding to the session triggering operation and determined based on the context information can better reflect the real intention of the user.
In an optional embodiment of the invention, the session trigger operation comprises at least one of a session trigger operation at the start of the session and a session trigger operation in the course of the session.
The session triggering operation at the beginning of the session refers to a related operation of starting the session, for example, an operation of starting a certain session application, and the session triggering operation in the session refers to a related operation of replying to information in the current session, for example, an operation of replying to a previous piece of information. Based on the session trigger operation, the first candidate information can be provided for the user based on the context information not only when the session starts, but also in the session process, the first candidate information can be provided for the user based on the context information, and the interaction experience of the user is further improved. The context information acquired based on the session triggering operation includes at least one of context information corresponding to the session triggering operation (starting operation) at the beginning of the session and session information in the session process.
In an optional embodiment of the present invention, in step S120, determining, according to the context information, first candidate information corresponding to the session triggering operation may include:
and determining first candidate information corresponding to the session triggering operation according to the information associated with the session triggering operation in the context information.
In order to more accurately predict the real intention of the user, more accurate first candidate information is provided, and the processing may be performed based on only the information related to the session operation start in the context information.
In an optional embodiment of the present invention, if the context information is not acquired or the acquired context information is not related to the session trigger operation, the method may further include:
determining second candidate information corresponding to the session triggering operation according to a pre-configured first-word corpus;
and displaying the second candidate information to the user.
If the context information is not acquired, it indicates that the user does not have a history operation before the session triggering operation is triggered, or does not have a history operation within a preset time period before the current time, and further, the context information corresponding to the history operation may not be acquired, so that the first candidate information related to the context information cannot be provided for the user based on the context information. Furthermore, if the context information is acquired, but the acquired context information is not related to the session triggering operation, for example, the session triggering operation is to start a call interface, it may indicate that the user is about to call a certain person, and at this time, if the acquired context information is a video watched for a certain period through a certain application program, the context information is not related to the session triggering operation, and thus the first candidate information related to the context information cannot be provided for the user based on the context information.
For either of the two cases, if the user triggers the session trigger operation, it indicates that the user may be about to perform operations related to the session trigger operation, such as making a call, sending a message, publishing text information, etc., and if the user cannot be provided with related reference information, i.e., the first candidate information, based on the context information, the user may be matched with corresponding second candidate information in the preconfigured first-speaking corpus based on the session trigger operation, and based on the second candidate information, the user may be provided with related opening phrases. The first language corpus pre-stores first language corpora under various information interaction scenes, and specifically, the first language corpora refer to opening languages during information interaction.
The acquisition of the first-spoken corpus and the establishment of the first-spoken corpus can be realized by adopting the existing mode.
In an optional embodiment of the present invention, the process of establishing the first-word corpus may specifically be: crawling chat information on a network as corpora, generally crawling a plurality of segments of chat information at a time, and then performing corpus cleaning on the crawled corpora, for example, filtering out corpora with specific names and specific locations, so that the smoothness and universality of the corpora can be ensured, that is, the filtered corpora can be suitable for various conversation scenes; and extracting the first sentence of each segment of chat information corresponding to the cleaned corpus to obtain a first-spoken corpus, finally counting high-frequency corpuses in the first-spoken corpus by means of clustering and the like, and establishing a first-spoken corpus based on the obtained high-frequency corpuses. It can be understood that, in practical applications, the corpus can be updated based on the update of the crawled chat information, so as to better meet practical requirements.
It should be noted that the above way of establishing the initial corpus is only an optional implementation way, and the invention is not limited to the way of establishing the initial corpus, and other processing ways that can achieve establishing the corpus are all within the scope of the invention. In addition, in the process of establishing the first-word corpus, each step may be implemented in different implementations, and is not limited to the specific implementation in each step.
In an optional embodiment of the present invention, the second candidate information includes a corresponding candidate first-spoken sentence, and the presenting the second candidate information to the user may include:
and providing the candidate first-speaking sentences to the user in a form of a candidate first-speaking sentence list.
For the convenience of viewing by the user, the candidate first spoken sentences may be provided to the user in the form of a candidate first spoken sentence list, and the first spoken sentence list may be displayed on a display interface of the terminal device of the user.
In an optional embodiment of the present invention, determining, according to information associated with the session trigger operation in the context information, first candidate information corresponding to the session trigger operation may include:
determining information associated with the session triggering operation in the context information according to the session type corresponding to the session triggering operation;
based on the information associated with the session triggering operation, first candidate information corresponding to the session triggering operation is determined.
The session type can be configured based on actual requirements, and the session type corresponding to the session trigger operation can know what type of session the user wants to perform, such as making a call, or publishing text information for a certain event.
Since the obtained context information may include information of different session types, in the context information, information associated with the session trigger operation may be determined based on the session type corresponding to the session trigger operation, and information of a session type that does not correspond to the session trigger operation may not be used as information associated with the session trigger operation. Determining the information associated with the session triggering operation based on the session type corresponding to the session triggering operation can improve the speed and accuracy of information processing, and the first candidate information determined based on the associated information is more accurate.
In an optional embodiment of the present invention, if the context information includes related information of a contact, the first candidate information includes contact information of the contact;
if the context information includes the relevant information of the event, the first candidate information includes text information associated with the event.
In order to accurately infer the next true intention of the user based on the context information, the first candidate information may be determined by combining different information included in the context information.
The context information may include, but is not limited to, at least one of related information of a contact and related information of an event. The related information of the contact may include information that may represent an identity of the contact, for example, name information, the contact information of the contact refers to identification information that may perform communication, for example, a phone number, mailbox information, and the like, and the related information of the event may be behavior record information of the user itself, such as context information generated according to a behavior record of the user watching a movie.
The following describes a scheme of what kind of information the first candidate information is when the context information includes the above two different information:
first, if the information type of the information included in the context information is related to a contact, it can be inferred that the user may want to have a conversation with the contact, such as sending information or making a call, based on the related information of the contact. If a user wants to send information or make a call, the user needs to know the contact information of the contact person to perform a conversation with the contact person, the first candidate information provided for the user can include the contact information of the contact person, and the contact information of the contact person is preferentially provided for the user, for example, the contact information of the contact person is displayed at a designated position of an interface corresponding to an address book, so that the user can conveniently obtain the contact information of the contact person, and other related operations for searching the contact information of the contact person are not needed.
In an example, if a session trigger operation of a user is an operation of opening a telephone address book in a terminal device, context information is acquired based on the session trigger operation, and if the acquired context information is: when the user is supposed to make a call with the AA (name of a person), the first candidate information provided for the user can include the telephone number of the AA, and the telephone number of the AA is displayed at the specified position of the corresponding interface of the address book, such as the top of a call list, so that the user can conveniently acquire the contact information of the contact person, and the user can directly make a call to the AA based on the telephone number, thereby saving the process of searching the AA telephone number in the address book and improving the interaction experience of the user.
Secondly, if the information type of the information included in the context information is related to an event, it may be inferred that the user may be text information related to the event to be published based on the related information of the event, for example, publishing evaluation information or reply information, and the first candidate information provided for the user may include the text information related to the event, that is, the text information corresponding to the meaning that the user may want to express, for example, comment information related to an event, and the like.
In an example, if a session trigger operation of a user is to enter a text input box on a user interface of a terminal device, and the user interface is a user interface corresponding to an application program for purchasing movie tickets, context information is acquired based on the session trigger operation, and if the acquired context information is: if the movie XX is watched just before 20 minutes in the movie theater, then at this time, it can be inferred that the user may want to publish information related to the movie theater and/or the movie XX based on the context information, the first candidate information provided for the user may include text information related to the movie theater and/or the movie XX, and the user may directly select information that the user wants to express to publish directly or publish after editing on the basis of the provided candidate information based on the provided text information related to the movie theater and/or the movie XX, thereby omitting a process of editing the text information related to the event that the user wants to publish, and improving the interaction experience of the user.
In an optional embodiment of the present invention, the context information obtained based on the session trigger operation of the user may be text information of the user in a chat process before the session trigger operation, or may be information generated based on a history operation of the user before the session trigger operation, for example, the context information may be generated based on a detected relevant operation record of the user at the terminal device.
In the above example, if the context information is information generated based on a history operation of the user before the session trigger operation, it may be detected that the user purchases a movie ticket in an application program for purchasing the movie ticket based on the session trigger operation of the user, and the information for purchasing the movie ticket may include name information of a movie theater, name information of a movie theater being watched, and playing time information, and the like, and then the context information may be generated from the information for purchasing the movie ticket, for example, the name information of the movie theater is movie theater a, the name information of the movie being watched is XX, and the time is TT, and then the generated context information may be: "at movie theater a, TT time finishes watching a movie XX".
In an optional embodiment of the present invention, if the context information includes information related to an event, determining, according to the context information, first candidate information corresponding to a session trigger operation may include:
acquiring first candidate information corresponding to session triggering operation from a session corpus based on keywords in the relevant information of the event;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
If the context information includes the relevant information of the event, the following two ways are used for determining the first candidate information corresponding to the session triggering operation according to the context information:
first, based on keywords in relevant information of events, first candidate information corresponding to a session trigger operation is obtained from a session corpus.
The conversation corpus is a pre-established corpus in which a large number of corpora used for giving opinions about events are stored, information corresponding to the conversation triggering operation can be retrieved from the conversation corpus as first candidate information based on keywords in relevant information of the events, a retrieval formula can be further formed by the keywords, and the information corresponding to the conversation triggering operation can be more accurately retrieved from the conversation corpus as the first candidate information based on the retrieval formula.
In an optional embodiment of the present invention, the process of establishing the session corpus specifically includes: the chat information on the network is crawled as the corpus, multiple sections of chat information can be crawled at one time generally, then, the crawled corpus is subjected to corpus cleaning processing, for example, the corpus with specific names and specific places is filtered out, the smoothness and universality of the corpus can be ensured, namely, the filtered corpus can be suitable for various conversation scenes (various types of events), and then, a conversation corpus is obtained based on the cleaned corpus, so that the conversation corpus can be updated based on the update of the crawled chat information, and more requirements can be met.
It should be noted that the above-mentioned establishment method of the session corpus is only an optional implementation method, and the establishment method of the session corpus is not limited in the present invention, and other processing methods that can implement establishment of the corpus are within the scope of the present invention. In addition, in the process of establishing the session corpus, each step may be implemented in different implementations, and is not limited to the specific implementation in each step.
In addition, in the process of establishing the conversation corpus and the first-word corpus, the same corresponding processing steps are provided, and the same processing steps can be realized by the same processing mode or different processing modes, for example, the same processing mode or different processing modes can be adopted for cleaning the corpus.
Secondly, the context information is used as a candidate information determination model to be input, and first candidate information corresponding to the conversation triggering operation is generated through the candidate information determination model.
The candidate information determination model is used for obtaining first candidate information based on the context information, the context information can be input into the candidate information determination model, the first candidate information corresponding to the conversation triggering operation is determined, the candidate information determination model is a deep learning model obtained based on collected conversation corpus training, the conversation corpus comprises various context information and corresponding candidate information, and the deep learning module can be any one of a Sequence-to-Sequence (seq 2 seq) model, a convolutional neural network model and a recurrent neural network model. It is to be appreciated that the candidate information determination model may be continuously updated based on the updating of the corpus of sessions.
In an optional embodiment of the present invention, if at least two pieces of information in the context information each include related information of a contact, before the first candidate information is presented to the user, the method may further include:
and determining the arrangement sequence of the contact information of the contact persons corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information.
If at least two pieces of information in the context information respectively include information of contacts, which indicates that at least two candidate contacts (people that the user may want to contact) may exist, before the first candidate information is provided for the user, that is, before the contact information of the candidate contacts is provided for the user, the contact information of the at least two candidate contacts may be sorted based on the acquisition times of the at least two pieces of information.
In practical applications, since the obtaining time of each piece of information is different, and a contact corresponding to information with a later obtaining time (i.e., closest to the time of the current session triggering operation) may be a person that the user wants to contact, the contact information of the contact corresponding to the information with the later obtaining time may be arranged in front of the contact information of all the contacts.
In an example, two pieces of information in the context information are information a and information B, the acquisition time of the information a is 17: 5 minutes, the acquisition time of the information B is 17: 8 minutes, the information a and the information B respectively include related information of one contact, the information a includes related information of the contact a, the information B includes related information of the contact B, and the contact information of the contact B is arranged before the contact information of the contact a.
In an optional embodiment of the present invention, if the text information includes at least two pieces of text information, before the first candidate information is presented to the user, the method may further include:
determining the similarity between the context information and each piece of text information in at least two pieces of text information;
and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
The text information may include a plurality of pieces of information, if the text information includes at least two pieces of text information, it is indicated that the first candidate information may provide more choices for the user, the similarity between the context information and each piece of text information in the at least two pieces of text information may reflect, semantic relevance between each piece of text information and the context information, that is, which piece of text information is closer to the semantic expressed by the context information, and then the at least two pieces of text information may be ranked based on the similarity between the context information and each piece of text information in the at least two pieces of text information before the first candidate information is displayed to the user.
In practical applications, the similarity between the context information and each of the at least two pieces of text information may be determined by calculating a confidence level between the context information and each of the at least two pieces of text information.
In an optional embodiment of the invention, the method may further comprise:
and reordering at least two pieces of text information after sequencing based on the personalized information of the user.
The personalized information of the user refers to information which can reflect the preference of the user, such as food which likes what tastes, what types of music and the like, can be provided by the user through terminal equipment, and can also be generated based on the online behavior information of the user, such as websites which the user frequently visits, sentences which are frequently used when the user replies and the like. The at least two pieces of text information are reordered based on the personalized information of the user, so that the personal characteristics of the user can be considered, and the interactive experience of the user is further improved.
In an optional embodiment of the invention, the method may further comprise:
and displaying the first candidate information and/or the second candidate information at a designated position on a user interface of the application program corresponding to the session triggering operation.
For convenience of a user to select the first candidate information and/or the second candidate information, the first candidate information and/or the second candidate information may be displayed at a specified position of a user interface of the application program corresponding to the session triggering operation, where the specified position may be configured based on actual requirements, for example, the specified position is the top of the user interface of the application program.
Based on the same principle as the method shown in fig. 1, an information presentation apparatus 20 is further provided in an alternative embodiment of the present invention, as shown in fig. 2, the apparatus provided in the embodiment of the present invention may include a context information obtaining module 210 and a candidate information presentation module 220, where:
the context information acquiring module 210 is configured to, when a session trigger operation of a user is received, acquire context information based on the session trigger operation, where the context information is information acquired based on a history operation of the user;
and the candidate information display module 220 is configured to determine, according to the context information, first candidate information corresponding to the session trigger operation, and display the first candidate information to the user.
According to the scheme provided by the embodiment of the invention, the corresponding context information can be acquired based on the session triggering operation of the user, the first candidate information corresponding to the session triggering operation and determined based on the context information is displayed to the user, and the context information is acquired based on the historical operation of the user, so that the first candidate information corresponding to the session triggering operation and determined based on the context information can better reflect the real intention of the user.
In an optional embodiment of the present invention, when determining, according to the context information, the first candidate information corresponding to the session triggering operation, the candidate information displaying module 220 is specifically configured to:
and determining first candidate information corresponding to the session triggering operation according to the information associated with the session triggering operation in the context information.
In an optional embodiment of the present invention, the candidate information determining module is further configured to determine, when the context information is not acquired or the acquired context information is not related to the session triggering operation, second candidate information corresponding to the session triggering operation according to a preconfigured first language corpus; and displaying the second candidate information to the user.
In an optional embodiment of the present invention, when determining, according to the information associated with the session triggering operation in the context information, the candidate information displaying module 220 is specifically configured to:
determining information associated with the session triggering operation in the context information according to the session type corresponding to the session triggering operation;
based on the information associated with the session triggering operation, first candidate information corresponding to the session triggering operation is determined.
In an optional embodiment of the present invention, if the context information includes related information of a contact, the first candidate information includes contact information of the contact;
if the context information includes the relevant information of the event, the first candidate information includes text information associated with the event.
In an optional embodiment of the present invention, if the context information includes information related to an event, when determining, according to the context information, first candidate information corresponding to a session trigger operation, the candidate information displaying module 220 is specifically configured to:
acquiring first candidate information corresponding to session triggering operation from a session corpus based on keywords in the relevant information of the event;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
In an alternative embodiment of the present invention, the apparatus may further include:
and the contact information sorting module is used for determining the arrangement sequence of the contact information of the contacts corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information before the at least two pieces of information in the context information both comprise the relevant information of the contacts and the first candidate information is displayed to the user.
In an alternative embodiment of the present invention, the apparatus may further include:
the text information ordering module is used for determining the similarity between the context information and each piece of text information in the at least two pieces of text information before the text information comprises at least two pieces of text information and the first candidate information is displayed to the user; and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
In an optional embodiment of the present invention, the text information sorting module is further configured to reorder the at least two pieces of text information after sorting based on personalized information of the user.
In an optional embodiment of the present invention, the context information is context information within a set duration taking the current time as the end time.
In an alternative embodiment of the present invention, the apparatus may further include:
and the display module is used for displaying the first candidate information and/or the second candidate information at a designated position on the user interface of the application program corresponding to the session triggering operation.
It can be understood that, since the information displaying apparatus described in this embodiment is an apparatus capable of executing the information displaying method in the embodiment of the present invention, based on the information displaying method described in the embodiment of the present invention, a person skilled in the art can understand a specific implementation manner of the information displaying apparatus of this embodiment and various variations thereof, so that how to implement the information displaying method in the embodiment of the present invention by the information displaying apparatus is not described in detail herein. As long as the person skilled in the art implements the information display device used in the information display method in the embodiment of the present invention, the information display device is within the scope of the present invention.
An embodiment of the present invention provides an electronic device, as shown in fig. 3, including: at least one processor (processor) 41; and at least one memory (memory)42, a bus 43 connected to the processor 41; wherein the content of the first and second substances,
the processor 41 and the memory 42 complete mutual communication through the bus 43;
the processor 41 is arranged to call program instructions in the memory 42 to perform the steps in the above-described method embodiments.
The present embodiments provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the method embodiments described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (18)
1. An information display method, comprising:
when session triggering operation of a user is received, acquiring context information based on the session triggering operation, wherein the context information is acquired based on historical operation of the user, the session triggering operation comprises session triggering operation at the beginning of a session, and the historical operation refers to operation performed by the user on terminal equipment;
determining the intention of the session triggering operation according to the context information, determining first candidate information corresponding to the session triggering operation according to the intention, and displaying the first candidate information to the user;
wherein, if the context information is not acquired or the acquired context information is not related to the session triggering operation, the method further comprises:
determining second candidate information matched with the session triggering operation according to a pre-configured initial language database, wherein initial language corpora under various session scenes are pre-stored in the initial language database;
and displaying the second candidate information to the user.
2. The method of claim 1, wherein the determining, according to the context information, first candidate information corresponding to the session trigger operation comprises:
and determining first candidate information corresponding to the session triggering operation according to the information related to the session triggering operation in the context information.
3. The method according to claim 2, wherein the determining, according to the information associated with the session trigger operation in the context information, first candidate information corresponding to the session trigger operation includes:
determining information associated with the session triggering operation in the context information according to the session type corresponding to the session triggering operation;
and determining first candidate information corresponding to the session triggering operation based on the information associated with the session triggering operation.
4. The method of claim 1, wherein if the context information includes event related information, the determining, according to the context information, first candidate information corresponding to the session triggering operation comprises:
acquiring first candidate information corresponding to the session triggering operation from a session corpus based on keywords in the event related information;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
5. The method of claim 1, wherein if at least two pieces of the contextual information each comprise information related to a contact, prior to said presenting the first candidate information to the user, the method further comprises:
and determining the arrangement sequence of the contact information of the contact persons corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information.
6. The method of claim 1, wherein if the text message includes at least two text messages, before presenting the first candidate message to the user, the method further comprises:
determining similarity between the context information and each piece of text information in the at least two pieces of text information;
and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
7. The method of claim 6, further comprising:
and reordering the at least two pieces of text information after the ordering based on the personalized information of the user.
8. The method according to any one of claims 1 to 3, wherein the context information is context information within a set time length with a current time as an end time.
9. An information presentation device, comprising:
the context information acquisition module is used for acquiring context information based on session trigger operation when session trigger operation of a user is received, wherein the context information is acquired based on historical operation of the user, the session trigger operation comprises session trigger operation at the beginning of a session, and the historical operation refers to operation performed by the user on terminal equipment;
the candidate information display module is used for determining the intention of the conversation triggering operation according to the context information, determining first candidate information corresponding to the conversation triggering operation according to the intention, and displaying the first candidate information to the user;
the candidate information display module is further configured to determine second candidate information matched with the session triggering operation according to a pre-configured first-spoken corpus and display the second candidate information to a user when the context information is not acquired or the acquired context information is unrelated to the session triggering operation, where the first-spoken corpus stores first-spoken corpora in various session scenes in advance.
10. The apparatus of claim 9, wherein the candidate information presentation module, when determining, according to the context information, first candidate information corresponding to the session trigger operation, is specifically configured to:
and determining first candidate information corresponding to the session triggering operation according to the information related to the session triggering operation in the context information.
11. The apparatus according to claim 10, wherein the candidate information presentation module, when determining, according to the information associated with the session trigger operation in the context information, the first candidate information corresponding to the session trigger operation, is specifically configured to:
determining information associated with the session triggering operation in the context information according to the session type corresponding to the session triggering operation;
and determining first candidate information corresponding to the session triggering operation based on the information associated with the session triggering operation.
12. The apparatus according to claim 9, wherein if the context information includes event-related information, the candidate information presentation module, when determining, according to the context information, first candidate information corresponding to the session trigger operation, is specifically configured to:
acquiring first candidate information corresponding to the session triggering operation from a session corpus based on keywords in the event related information;
or, the context information is input as a candidate information determination model, and first candidate information corresponding to the session trigger operation is generated through the candidate information determination model.
13. The apparatus of claim 9, further comprising:
and the contact information ordering module is used for determining the arrangement sequence of the contact information of the contacts corresponding to the at least two pieces of information according to the acquisition time of the at least two pieces of information before the first candidate information is displayed to the user, wherein the at least two pieces of information in the context information both comprise the relevant information of the contacts.
14. The apparatus of claim 9, further comprising:
the text information ordering module is used for determining the similarity between the context information and each piece of text information in at least two pieces of text information before the first candidate information is displayed to the user; and determining the arrangement sequence of the at least two pieces of text information according to the similarity to obtain the at least two pieces of text information after sequencing.
15. The apparatus of claim 14, wherein the text information ranking module is further configured to reorder the at least two ranked text information based on personalized information of a user.
16. The apparatus according to any one of claims 9 to 11, wherein the context information is context information within a set duration with a current time as an end time.
17. An electronic device, comprising:
at least one processor;
and at least one memory, bus connected with the processor; wherein:
the processor and the memory complete mutual communication through the bus;
the processor is configured to invoke program instructions in the memory to perform the method of any one of claims 1 to 8.
18. A computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910300538.7A CN110008331B (en) | 2019-04-15 | 2019-04-15 | Information display method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910300538.7A CN110008331B (en) | 2019-04-15 | 2019-04-15 | Information display method and device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110008331A CN110008331A (en) | 2019-07-12 |
| CN110008331B true CN110008331B (en) | 2021-09-14 |
Family
ID=67171905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910300538.7A Active CN110008331B (en) | 2019-04-15 | 2019-04-15 | Information display method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008331B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339910B (en) * | 2020-02-24 | 2023-11-28 | 支付宝实验室(新加坡)有限公司 | Text processing and text classification model training method and device |
| CN113286113A (en) * | 2020-10-23 | 2021-08-20 | 常熟友乐智能科技有限公司 | Video conference operation management method, device and system |
| CN113407686B (en) * | 2021-06-03 | 2022-11-15 | 北京得间科技有限公司 | Interactive display method, computing equipment and computer storage medium for dialogue novel |
| CN114900739A (en) * | 2022-04-25 | 2022-08-12 | 北京达佳互联信息技术有限公司 | Session processing method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107612814A (en) * | 2017-09-08 | 2018-01-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating candidate's return information |
| WO2018014341A1 (en) * | 2016-07-22 | 2018-01-25 | 华为技术有限公司 | Method and terminal device for presenting candidate item |
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| CN108960934A (en) * | 2018-07-19 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Information recommendation method and system during voice dialogue |
| CN109036588A (en) * | 2018-09-10 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | The method, apparatus, equipment and computer-readable medium of interrogation on line |
| CN109478106A (en) * | 2016-07-15 | 2019-03-15 | 微软技术许可有限责任公司 | Using environmental context with the communication throughput for enhancing |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201019288A (en) * | 2008-11-13 | 2010-05-16 | Ind Tech Res Inst | System and method for conversation practice in simulated situations |
| US9880714B2 (en) * | 2014-10-30 | 2018-01-30 | Ebay Inc. | Dynamic loading of contextual ontologies for predictive touch screen typing |
| US20170357521A1 (en) * | 2016-06-13 | 2017-12-14 | Microsoft Technology Licensing, Llc | Virtual keyboard with intent-based, dynamically generated task icons |
| CN108279828A (en) * | 2016-12-30 | 2018-07-13 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and terminal starting application program |
| CN107831915A (en) * | 2017-10-17 | 2018-03-23 | 北京三快在线科技有限公司 | One kind input complementing method, device, electronic equipment and readable storage medium storing program for executing |
| CN109087135B (en) * | 2018-07-25 | 2020-08-28 | 百度在线网络技术（北京）有限公司 | Mining method and device for user intention, computer equipment and readable medium |
-
2019
- 2019-04-15 CN CN201910300538.7A patent/CN110008331B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109478106A (en) * | 2016-07-15 | 2019-03-15 | 微软技术许可有限责任公司 | Using environmental context with the communication throughput for enhancing |
| WO2018014341A1 (en) * | 2016-07-22 | 2018-01-25 | 华为技术有限公司 | Method and terminal device for presenting candidate item |
| CN107612814A (en) * | 2017-09-08 | 2018-01-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating candidate's return information |
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| CN108960934A (en) * | 2018-07-19 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Information recommendation method and system during voice dialogue |
| CN109036588A (en) * | 2018-09-10 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | The method, apparatus, equipment and computer-readable medium of interrogation on line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110008331A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008331B (en) | Information display method and device, electronic equipment and computer readable storage medium | |
| CN110378732B (en) | Information display method, information association method, device, equipment and storage medium | |
| US20170097984A1 (en) | Method and system for generating a knowledge representation | |
| US10540666B2 (en) | Method and system for updating an intent space and estimating intent based on an intent space | |
| US11042590B2 (en) | Methods, systems and techniques for personalized search query suggestions | |
| US10110544B2 (en) | Method and system for classifying a question | |
| US20170098013A1 (en) | Method and system for entity extraction and disambiguation | |
| US11080287B2 (en) | Methods, systems and techniques for ranking blended content retrieved from multiple disparate content sources | |
| US10417206B2 (en) | Method and system for associating data from different sources to generate a person-centric space | |
| CN104462364A (en) | Search recommendation method and device | |
| CN115842798A (en) | Interactive content information processing method, related device and terminal equipment | |
| US11232522B2 (en) | Methods, systems and techniques for blending online content from multiple disparate content sources including a personal content source or a semi-personal content source | |
| CN109492152B (en) | Method, device, computer equipment and storage medium for pushing custom content | |
| US20230179554A1 (en) | Method and system for dynamically generating a card | |
| CN108170294B (en) | Vocabulary display method, field conversion method, client, electronic equipment and computer storage medium | |
| CN106682006B (en) | Information prompting method and device about communication content | |
| US20170098012A1 (en) | Methods, systems and techniques for ranking personalized and generic search query suggestions | |
| US20170097986A1 (en) | Methods, systems and techniques for providing search query suggestions based on non-personal data and user personal data according to availability of user personal data | |
| WO2016138349A1 (en) | Systems and methods of structuring reviews with auto-generated tags | |
| CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
| CN108449255B (en) | Comment interaction method and equipment, client device and electronic equipment | |
| CN106815284A (en) | The recommendation method and recommendation apparatus of news video | |
| US20170098144A1 (en) | Method and system for generating a card based on intent | |
| CN110750975B (en) | Introduction text generation method and device | |
| CN111191132A (en) | Information recommendation method and device and electronic equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200727 Address after: 518057 Nanshan District science and technology zone, Guangdong, Zhejiang Province, science and technology in the Tencent Building on the 1st floor of the 35 layer Applicant after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. Address before: 100029, Beijing, Chaoyang District new East Street, building No. 2, -3 to 25, 101, 8, 804 rooms Applicant before: Tricorn (Beijing) Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |