CN114579702A

CN114579702A - Message sending method, device, terminal and storage medium for preventing misoperation

Info

Publication number: CN114579702A
Application number: CN202210186761.5A
Authority: CN
Inventors: 韩升; 孙伟
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-06-03

Abstract

The present disclosure relates to a message transmission method for preventing an erroneous operation, a message transmission device for preventing an erroneous operation, a terminal, and a storage medium. The message sending method for preventing misoperation comprises the following steps: when a user inputs information in an information input box of an interactive interface, extracting an interactive object label from the interactive interface; determining a message portrait corresponding to the interactive object tag based on the interactive object tag; the message portrait is used for representing the relationship between the characteristic information and the interactive object label; acquiring input information of a user in an information input box, and performing semantic recognition to obtain semantic information corresponding to the input information; if the semantic information is not matched with the message portrait, prompt information is output, and the prompt information is used for prompting a user that the current input information possibly has a risk of missending. According to the method and the device, when the user sees the prompt information for prompting that the current input information possibly has the risk of being sent by mistake, the input information and the interactive object can be verified, so that the condition that the input information is sent by mistake can be effectively reduced.

Description

Message sending method, device, terminal and storage medium for preventing misoperation

Technical Field

The present disclosure relates to the field of information processing technologies, and in particular, to a message sending method for preventing an incorrect operation, a message sending apparatus for preventing an incorrect operation, a terminal, and a storage medium.

Background

With the rapid development of electronic technology, many electronic products have interactive functions. And the information interaction between human and machine and between people is realized through the interactive interface of the electronic product. Especially, in the field of instant messaging, users often have a phenomenon of sending a wrong message object in the process of communicating with each other, for example, a user a may send a wrong message originally to a user B to a user C.

Disclosure of Invention

The present disclosure provides a message transmission method for preventing an erroneous operation, a message transmission apparatus for preventing an erroneous operation, a terminal, and a storage medium.

In a first aspect of the embodiments of the present disclosure, a message sending method for preventing misoperation is provided, including:

when a user inputs information in an information input box of an interactive interface, extracting an interactive object tag from the interactive interface, wherein the interactive object tag refers to a unique identifier of an interactive object for information interaction with the current user;

determining a message portrait corresponding to the interactive object tag in a pre-stored message portrait database based on the interactive object tag; the message portrait is a tagged information model determined according to feature information of historical interaction information, the message portrait is used for representing the relation between the feature information and the tag, and the historical interaction information is the historical interaction information of a current user and the interaction object;

acquiring input information of a user in the information input box;

performing semantic recognition on the input information to obtain semantic information corresponding to the input information;

and if the semantic information is not matched with the message portrait, outputting prompt information, wherein the prompt information is used for prompting a user that the current input information possibly has a risk of missending.

In some embodiments, the feature information comprises: at least one of time information, location information, character information, and event information;

the input information includes: at least one of time information, location information, character information, and event information.

In some embodiments, the method comprises: determining whether the semantic information matches the message representation by:

inputting the semantic information and the message portrait into a preset message misoperation identification model to obtain an output result; wherein the output result is used for representing the matching degree of the semantic information and the message image, and comprises the following steps:

and if the matching degree is larger than a preset threshold value, determining that the semantic information is matched with the message portrait, otherwise, determining that the semantic information is not matched with the message portrait.

In some embodiments, the preset message misoperation recognition model is obtained by inputting a training sample set into an initial model through a machine learning mode; wherein the set of training samples comprises a plurality of training samples; each training sample includes at least: the message portrait, semantic information corresponding to the message portrait and tagging information, wherein the tagging information is used for expressing the matching degree of the semantic information and the message portrait.

In some embodiments, the performing semantic recognition on the input information to obtain semantic information corresponding to the input information includes:

inputting the input information of the user to a natural language processing model, and extracting semantic information in the input information; wherein the semantic information characterizes at least feature elements of an event or person.

In a second aspect of the embodiments of the present disclosure, there is provided a message transmitting apparatus for preventing a malfunction, including:

the information processing device comprises a first processing unit, a second processing unit and a third processing unit, wherein the first processing unit is used for extracting an interactive object label from an interactive interface when a user inputs information in an information input box of the interactive interface, and the interactive object label refers to a unique identifier of an interactive object which performs information interaction with the current user;

the second processing unit is used for determining the message portrait corresponding to the interactive object label in a pre-stored message portrait database based on the interactive object label; the message image is a tagged information model determined according to characteristic information of historical interaction information, the message image is used for representing the relation between the characteristic information and the tag, and the historical interaction information is the historical interaction information of a current user and the interaction object;

the third processing unit is used for acquiring input information of a user in the information input box;

the fourth processing unit is used for carrying out semantic recognition on the input information to obtain semantic information corresponding to the input information;

and the fifth processing unit is used for outputting prompt information if the semantic information is not matched with the message portrait, wherein the prompt information is used for prompting a user that the current input information possibly has a risk of missending.

In some embodiments, the fifth processing unit is further configured to

Determining whether the semantic information matches the message representation by:

In some embodiments, the preset message misoperation recognition model is obtained by inputting a training sample set into an initial model through a machine learning mode; wherein the set of training samples comprises a plurality of training samples; each training sample includes at least: the system comprises a message portrait, semantic information corresponding to the message portrait and label information, wherein the label information is used for expressing the matching degree of the semantic information and the message portrait.

In some embodiments, the fourth processing unit is specifically configured to

In a third aspect of the embodiments of the present disclosure, a terminal is provided, including: a processor and a memory, the memory having stored thereon a computer program operable on the processor to, when executed, perform the steps of the method of the first aspect.

A fourth aspect of embodiments of the present disclosure provides a computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method of the first aspect.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

the message sending method for preventing misoperation in the embodiment of the disclosure comprises the following steps: when a user inputs information in an information input box of an interactive interface, extracting an interactive object label from the interactive interface, wherein the interactive object label refers to a unique identifier of an interactive object for information interaction with the current user; determining a message portrait corresponding to the interactive object tag in a pre-stored message portrait database based on the interactive object tag; the message portrait is a tagged information model determined according to the characteristic information of the historical interaction information, the message portrait is used for representing the relationship between the characteristic information and the interactive object tag, and the historical interaction information is the historical interaction information of the current user and the interactive object; acquiring input information of a user in an information input box; performing semantic recognition on input information to obtain semantic information corresponding to the input information; if the semantic information is not matched with the message portrait, prompt information is output, and the prompt information is used for prompting a user that the current input information possibly has a risk of missending. According to the method and the device, whether the input information of the user on the interactive interface corresponds to a correct interactive object or not is determined by matching the input information of the user on the interactive interface with the determined message portrait, and then prompt information is fed back to the user according to a matching result. For example, if semantic information extracted from the input information does not match the message portrait, prompt information for prompting the user that the current input information may be at risk of missending is output. Wherein the pre-stored message portrayal is used for representing the relationship between the characteristic information and the interactive object label. When the user sees the prompt information for prompting that the current input information possibly has the risk of sending the input information by mistake, the input information and the interactive object can be verified, so that the condition that the input information is sent by mistake can be effectively reduced.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 is a flow chart illustrating a method of messaging to prevent malfunction in accordance with an exemplary embodiment.

FIG. 2 is a diagram illustrating message representation creation in a method of messaging to prevent misoperations, according to an example embodiment.

FIG. 3 is a first diagram illustrating a comparison of message representations in a method for preventing misoperation in a message sending method according to an exemplary embodiment.

FIG. 4 is a second diagram illustrating a comparison of message representations in a method for preventing misoperation in a messaging system according to an exemplary embodiment.

Fig. 5 is a diagram illustrating a new message representation according to a comparison result in a message sending method for preventing misoperation according to an exemplary embodiment.

FIG. 6 is a diagram illustrating message portrayal optimization in a method of preventing misoperations in accordance with an exemplary embodiment.

Fig. 7 is a schematic diagram illustrating a structure of a message sending apparatus for preventing a malfunction according to an exemplary embodiment.

FIG. 8 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of devices consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The embodiment of the disclosure provides a message sending method for preventing misoperation. Fig. 1 is a flow chart illustrating a method of messaging to prevent malfunction in accordance with an exemplary embodiment. As shown in fig. 1, the message transmission method for preventing the misoperation includes:

step 10, when a user inputs information in an information input box of an interactive interface, extracting an interactive object label from the interactive interface, wherein the interactive object label refers to a unique identifier of an interactive object for information interaction with the current user;

step 11, determining a message portrait corresponding to the interactive object label in a pre-stored message portrait database based on the interactive object label; the message image is a tagged information model determined according to characteristic information of historical interaction information, the message image is used for representing the relation between the characteristic information and the tag, and the historical interaction information is the historical interaction information of a current user and the interaction object;

step 12, acquiring input information of a user in the information input box;

step 13, performing semantic recognition on the input information to obtain semantic information corresponding to the input information;

and 14, if the semantic information is not matched with the message portrait, outputting prompt information, wherein the prompt information is used for prompting that the current input information of the user possibly has a risk of missending.

In the embodiment of the present disclosure, the interactive object may be a single person or a group. For example, when the thumbnail and the thumbnail interact, the identification of the interaction object may be: ID number, nickname or remark name of pink; when a group of a class, a small and a group of two in three years, interact, the interaction object may be a group ID number, a nickname or a remark name of the group of two in three years.

In this embodiment of the disclosure, the performing semantic identification on the input information to obtain semantic information corresponding to the input information includes:

In the embodiment of the disclosure, when extracting semantic information from input information, the input information of a user can be input into the natural language processing model, and the semantic information is identified and extracted. Semantic recognition, namely a Natural Language Processing (NLP) semantic analysis technology, which is a technology already existing in the prior art, and the invention of the present application is not described here, and therefore, the description thereof is omitted. Wherein the characteristic elements of the event or person at least comprise: at least one of time information, location information, character information, and event information.

In the embodiment of the present disclosure, the feature information can be used to determine at least an identity feature or a personalized feature of the interaction object or the interaction event, that is, an essential feature that can reflect that the interaction is different from other objects or events for the object or the interaction. For example, the gender of the user B is female and the teacher is professional, and then the gender of the female and the teacher can be determined as the characteristic information of the user B. The semantic information mismatch with the message representation may be understood as a semantic information message representation feature information mismatch, i.e. the semantic information contradicts or conflicts with the feature information in the message representation. For example, when the user a inputs information in the interactive interface labeled "sprout", the input content is "bright and bright" and the work treatment of your officer is improved this year ", and it is obvious that the object that the user a wants to chat is the officer" bright "instead of the teacher" sprout ", and the semantics of the input information contradicts the characteristic information" sprout, teacher ", and the like, and it can be determined that the semantic information does not match the message portrait at this time.

In the embodiment of the present disclosure, the time information in the feature information may include: time when the interactive object interacts, work and rest time of the interactive object and the like extracted from the historical interactive information; the location information in the feature information may include: the working place, the accommodation place, the place of birth, the place of occurrence of the event and the like of the interactive object extracted from the historical interactive information; the personal information may include: the age, sex, identity, occupation, hobbies and the like of the interactive objects extracted from the historical interactive information; the event information may include: event information related to the interactive object, such as an activity/sport in which the interactive object participates, extracted from the historical interactive information.

In the embodiment of the present disclosure, the time information in the input information may include: the time when the current user enters information, the time mentioned at the time of interaction (e.g., meeting time of invitation interaction object, time of participation in the activity, etc.); the location information in the input information may include: the location information related to the current user input information, such as meeting location of the invitation interaction object, location of participating in the activity, etc.; the personal information in the input information may include: the names of the interactive objects, the ages, the sexes, the identities, the professions, the interests and the like of the interactive objects, which are related to the input information, are input; the event information in the input information may include: the activity/sport participated in the input information, etc. The semantics extracted from the input information in the present application may include information in corresponding time information, location information, person information, and event information. The feature information for matching may also include: time information, location information, person information, event information.

In the embodiment of the disclosure, when determining whether the semantic information is matched with the message portrait, the semantic information and the message portrait may be input into a preset message misoperation identification model, and whether the semantic information is matched with the message portrait is determined through an output result. Wherein the output result is used for representing the matching degree of the semantic information and the message portrait. For example, if the degree of match is greater than a preset threshold, then the semantic information is determined to match the message representation, otherwise, the semantic information is determined not to match the message representation. The preset threshold value in this application may be set to a specific threshold value, for example 80%. And when the output result shows that the matching degree of the semantic information and the message portrait is less than 80%, determining that the semantic information is not matched with the message portrait. Therefore, whether the semantic information of the input information is matched with the message portrait or not can be directly judged through the message misoperation recognition model, namely whether the current input information of the user corresponds to a correct interactive object or not is judged. When the output result shows that the matching degree of the semantic information and the message portrait is more than 80%, the semantic information is determined to be matched with the message portrait, at the moment, no prompt information is output, and the user can directly send the input information to the interactive object.

In the embodiment of the disclosure, the preset message misoperation recognition model can be obtained by training in advance. The method is obtained by inputting a training sample set into an initial model in a machine learning mode. The information portrait corresponding to the interactive object label can be established by extracting the characteristic information from the historical interactive information. And obtaining semantic information corresponding to the message image from the historical interactive information, and determining marking information representing the matching degree of the semantic information and the message image. And establishing a training sample based on the message portrait, semantic information corresponding to the message portrait and the labeling information. And inputting the training sample set integrated with a large number of training samples into the initial model to perform machine learning training to obtain a message misoperation recognition model.

In an embodiment of the present disclosure, the determining, based on the interactive object tag, a message portrait corresponding to the interactive object tag in a pre-stored message portrait database includes:

acquiring an interactive object label of a message picture;

and determining that the message image of the interactive object label which is the same as the interactive object label extracted from the interactive interface is the message image corresponding to the interactive object label.

In the embodiment of the present disclosure, the method further includes: and establishing a corresponding relation between the interactive object label and the message image. For example, extracting a first interactive object tag in a first interactive interface;

establishing a first message portrait corresponding to the first interactive object label based on first interactive content in a first interactive interface;

extracting a second interactive object label in the second interactive interface;

and establishing a second message portrait corresponding to the second interactive object label based on second interactive content in the second interactive interface.

The interactive object in the first interactive interface can be a first merchant, the first interactive content is electronic products purchased at the first merchant, the interactive object in the second interactive interface can be a second merchant, and the second interactive content is fruits purchased at the second merchant; determining that the first interactive object tag is: and (3) selling the electronic product, and determining that the second interactive object tag is: selling fruits; determining feature information contained in a first message portrait established based on the first interactive content as features related to the electronic product; the feature information contained in the second message image established based on the second interactive content is determined as the feature related to the fruit, so that different message images are distinguished from corresponding to different interactive object labels and the feature information, and the feature information is used for matching the input information of the user in the interactive interface to determine whether the input information conforms to the current interactive object. Thereby reducing the situation of the information error sending object.

In the embodiment of the present disclosure, when the pre-established message portrait is determined based on the interactive object tag, if the interactive object tag of the interactive interface of the current user input information is consistent with the interactive object tag of the existing message portrait, it is determined that the message portrait consistent with the interactive object tag of the interactive interface is: for verifying whether the user currently inputs information that corresponds to the message representation of the interactive object. FIG. 2 is a diagram illustrating message representation creation in a method of messaging to prevent inadvertent operation, according to an exemplary embodiment. As shown in fig. 2, corresponding interactive object tags are established according to different interactive interfaces, and include an interactive object tag 1, an interactive object tag 2, an interactive object tag 3, and an interactive object tag 4; creating a message representation based on historical messages or other information obtained from text input, comprising: message image 1, message image 2, message image 3, and message image 4. Establishing a corresponding relation between interactive object labels and message images, comprising: the interactive object tag 1 corresponds to the message image 1, the interactive object tag 2 corresponds to the message image 2, the interactive object tag 3 corresponds to the message image 3, and the interactive object tag 4 corresponds to the message image 4. FIG. 3 is a first diagram illustrating a comparison of message representations in a method for preventing misoperation in a message sending method according to an exemplary embodiment. As shown in fig. 3, the whole alignment process includes:

determining a corresponding message portrait through the interactive object tag;

after the user information is edited, understanding semantics through a natural language processing model NLP, and comparing corresponding message portraits;

and feeding back the comparison result to the terminal.

FIG. 4 is a second diagram illustrating a comparison of message representations in a method for preventing misoperation in a messaging system according to an exemplary embodiment. As shown in fig. 4, after understanding the semantic and message portrait comparison, if the semantic and message portrait are obviously inconsistent, then remind the user whether to send; if the semantic meaning is consistent with the message portrait, the user is not prompted and the message portrait is sent normally.

FIG. 5 is a diagram illustrating creation of a message representation based on a comparison in a method of preventing malfunction of a messaging process according to an exemplary embodiment. As shown in FIG. 5, in determining a message representation, if a message representation corresponding to an interactive object tag exists in the cloud, it is mapped to the corresponding message representation. If not, a message representation is created.

In some embodiments, the pre-established message representation is stored in a cloud;

the determining a pre-established message portrait based on the interactive object tag comprises:

and determining the message portrait corresponding to the interactive object tag stored in the cloud based on the interactive object tag.

In an embodiment of the disclosure, the created message representation may be stored in a cloud for invoking query message representations. Even if the user changes the electronic equipment, the message portrait corresponding to the interactive object tag can be directly inquired at the cloud end, so that the input information can be conveniently matched with the characteristic information in the message portrait.

In the embodiment of the disclosure, after the matching is completed, the interactive information of the user at this time can be used as an information source, the input information of the user is learned through a language learning model (for example, a deep learning model, a machine learning model, and the like), the message portrait corresponding to the interactive object tag is optimized, the cloud information is updated, and the model quality of the message portrait is further improved. FIG. 6 is a diagram illustrating message representation optimization in a method of messaging to prevent misoperation, according to an example embodiment. As shown in fig. 6, after the current session is completed, the message picture N may be optimized through a machine learning algorithm, and the cloud information may be updated.

The application has the following advantages:

1. automatic prompting is carried out, and the user does not need to find the user and withdraw the user again, so that the user cannot withdraw the user after overtime;

2. the self-learning ability is achieved without depending on page layout;

3. and the negative influence caused by sending information to a wrong object is avoided.

In a second aspect of the disclosed embodiments, a message sending apparatus for preventing a malfunction is provided. Fig. 7 is a schematic diagram illustrating a structure of a message sending apparatus for preventing a malfunction according to an exemplary embodiment. As shown in fig. 7, the message transmitting apparatus for preventing the malfunction includes:

a first processing unit 71, configured to extract an interactive object tag from an interactive interface when a user inputs information in an information input box of the interactive interface, where the interactive object tag refers to a unique identifier of an interactive object performing information interaction with a current user;

a second processing unit 72, configured to determine, based on the interactive object tag, a message portrait corresponding to the interactive object tag in a pre-stored message portrait database; the message image is a tagged information model determined according to characteristic information of historical interaction information, the message image is used for representing the relation between the characteristic information and the tag, and the historical interaction information is the historical interaction information of a current user and the interaction object;

a third processing unit 73 for acquiring the input information of the user in the information input box;

a fourth processing unit 74, configured to perform semantic identification on the input information to obtain semantic information corresponding to the input information;

a fifth processing unit 75, configured to output a prompt message if the semantic information does not match the message portrait, where the prompt message is used to prompt a user that there is a risk of missending the currently input message.

The message sending device for preventing misoperation in the embodiment of the disclosure is used for extracting an interactive object label from an interactive interface when a user inputs information in an information input box of the interactive interface, wherein the interactive object label refers to a unique identifier of an interactive object for information interaction with the current user; determining a message portrait corresponding to the interactive object tag in a pre-stored message portrait database based on the interactive object tag; the message portrait is a tagged information model determined according to the characteristic information of the historical interaction information, the message portrait is used for representing the relationship between the characteristic information and the interactive object tag, and the historical interaction information is the historical interaction information of the current user and the interactive object; acquiring input information of a user in an information input box; performing semantic recognition on input information to obtain semantic information corresponding to the input information; if the semantic information is not matched with the message portrait, prompt information is output, and the prompt information is used for prompting a user that the current input information possibly has a risk of missending. According to the method and the device, whether the input information of the user on the interactive interface corresponds to a correct interactive object or not is determined by matching the input information of the user on the interactive interface with the determined message portrait, and then prompt information is fed back to the user according to a matching result. For example, if semantic information extracted from the input information does not match the message portrait, prompt information for prompting the user that the current input information may be at risk of being missent is output. Wherein the pre-stored message portrayal is used for representing the relationship between the characteristic information and the interactive object label. When the user sees the prompt information for prompting that the current input information possibly has the risk of sending the input information by mistake, the input information and the interactive object can be verified, so that the condition that the input information is sent by mistake can be effectively reduced.

In the embodiment of the present disclosure, the time information in the feature information may include: time when the interactive object interacts, work and rest time of the interactive object and the like extracted from the historical interactive information; the location information in the feature information may include: the working place, the accommodation place, the place of birth, the place of occurrence of the event and the like of the interactive object extracted from the historical interactive information; the personal information may include: the age, sex, identity, occupation, hobby and the like of the interactive object extracted from the historical interactive information; the event information may include: event information related to the interactive object, such as an activity/sport in which the interactive object participates, extracted from the historical interactive information.

In the embodiment of the present disclosure, the time information in the input information may include: the time when the current user enters information, the time mentioned at the time of interaction (e.g., meeting time of invitation interaction object, time of participation in the activity, etc.); the location information in the input information may include: the location information related to the current user input information, such as meeting location of the invitation interaction object, location of participating in the activity, etc.; the personal information in the input information may include: the names of the interactive objects, the ages, the sexes, the identities, the professions, the interests and the like of the interactive objects, which are related to the input information, are input; the event information in the input information may include: the activity/sport participated in the input information, etc. The semantics extracted from the input information in the present application may include information in corresponding time information, location information, person information, and event information. The feature information for matching may also include: time information, location information, person information, and event information.

In some embodiments, the fifth processing unit is further configured to

In the embodiment of the disclosure, when determining whether the semantic information is matched with the message portrait, the semantic information and the message portrait may be input into a preset message misoperation identification model, and whether the semantic information is matched with the message portrait is determined through an output result. Wherein the output result is used for representing the matching degree of the semantic information and the message portrait. For example, if the degree of match is greater than a preset threshold, then the semantic information is determined to match the message representation, otherwise, the semantic information is determined not to match the message representation. The preset threshold value in this application may be set to a specific threshold value, for example 80%. And when the matching degree of the output result display semantic information and the message portrait is less than 80%, determining that the semantic information is not matched with the message portrait. Therefore, whether the semantic information of the input information is matched with the message portrait or not can be directly judged through the message misoperation identification model, and whether the current input information of the user corresponds to a correct interactive object or not is judged. When the matching degree of the output result display semantic information and the message portrait is larger than 80%, the semantic information is determined to be matched with the message portrait, no prompt information is output at the moment, and the user can directly send the input information to the interactive object.

In some embodiments, the preset message misoperation recognition model is obtained by inputting a training sample set into an initial model in a machine learning manner; wherein the set of training samples comprises a plurality of training samples; each training sample includes at least: the message portrait, semantic information corresponding to the message portrait and tagging information, wherein the tagging information is used for expressing the matching degree of the semantic information and the message portrait.

acquiring an interactive object label of a message picture;

The interactive object in the first interactive interface can be a first merchant, the first interactive content is electronic products purchased at the first merchant, the interactive object in the second interactive interface can be a second merchant, and the second interactive content is fruits purchased at the second merchant; determining that the first interactive object tag is: and (3) selling the electronic product, and determining that the second interactive object tag is: selling fruits; determining feature information contained in a first message portrait established based on the first interactive content as features related to the electronic product; the feature information contained in the second message image established based on the second interactive content is determined as the feature related to the fruit, so that different message images are distinguished from corresponding to different interactive object labels and the feature information, and the feature information is used for matching the input information of the user in the interactive interface to determine whether the input information conforms to the current interactive object. Thereby reducing the situation of the object with wrong information.

In the embodiment of the present disclosure, the fourth processing unit is specifically configured to

In the embodiment of the disclosure, when extracting semantic information from input information, the input information of a user can be input into the natural language processing model, and the semantic information is identified and extracted. The semantic recognition, namely a Natural Language Processing (NLP) semantic analysis technique, is a technique that already exists in the prior art, and the invention point of the present application is not here, and therefore, the description thereof is omitted. Wherein the characteristic elements of the event or person at least comprise: at least one of time information, location information, character information, and event information.

An embodiment of the present disclosure further provides a terminal, including: a processor and a memory, the memory having stored thereon a computer program operable on the processor to, when executed, perform the steps of the method of the embodiments.

The disclosed embodiments also provide a computer-readable storage medium, on which a computer program is stored, wherein the computer program is used for implementing the steps of the method according to the embodiments when being executed by a processor.

FIG. 8 is a block diagram illustrating an electronic device in accordance with an example embodiment. For example, the electronic device may be a mobile phone, a computer, a digital broadcast electronic device, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 8, an electronic device may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the electronic device, such as operations associated with touch, phone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power components 806 provide power to various components of the electronic device. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for electronic device devices.

The multimedia component 808 includes a screen that provides an output interface between the electronic device and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 814 includes one or more sensors for providing various aspects of state assessment for the electronic device. For example, the sensor assembly 814 may detect an open/closed state of the electronic device, the relative positioning of components, such as a display and keypad of the electronic device, the sensor assembly 814 may also detect a change in position of the electronic device or a component of the electronic device, the presence or absence of user contact with the electronic device, orientation or acceleration/deceleration of the electronic device, and a change in temperature of the electronic device. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, communications component 816 further includes a Near Field Communications (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A message transmission method for preventing a malfunction, comprising:

determining a message portrait corresponding to the interactive object tag in a pre-stored message portrait database based on the interactive object tag; the message image is a tagged information model determined according to characteristic information of historical interaction information, the message image is used for representing the relation between the characteristic information and an interaction object tag, and the historical interaction information is the historical interaction information of a current user and the interaction object;

acquiring input information of a user in the information input box;

if the semantic information is not matched with the message portrait, prompt information is output, and the prompt information is used for prompting a user that the current input information may have a risk of missending.

2. The malfunction prevention message transmission method according to claim 1,

the characteristic information includes: at least one of time information, location information, character information, and event information;

3. The method for sending a message for preventing misoperation according to claim 1, wherein the method comprises: determining whether the semantic information matches the message representation by:

4. The method for sending the message for preventing the misoperation according to claim 3, wherein the preset message misoperation recognition model is obtained by inputting a training sample set into an initial model through a machine learning mode; wherein the set of training samples comprises a plurality of training samples; each training sample includes at least: the message portrait, semantic information corresponding to the message portrait and tagging information, wherein the tagging information is used for expressing the matching degree of the semantic information and the message portrait.

5. The method for preventing the message sending with the misoperation according to claim 1, wherein the semantic recognition of the input information to obtain the semantic information corresponding to the input information comprises:

6. A message transmission device that prevents malfunction, comprising:

the information processing method comprises the steps that a first processing unit is used for extracting an interactive object label from an interactive interface when a user inputs information in an information input box of the interactive interface, wherein the interactive object label refers to a unique identifier of an interactive object for information interaction with the current user;

7. The malfunction prevention message transmission apparatus according to claim 6,

8. The misoperation-preventive message transmission device according to claim 6, wherein the fifth processing unit is further configured to

9. The misoperation prevention message transmission device according to claim 8, wherein the preset message misoperation recognition model is obtained by inputting a training sample set into an initial model through machine learning; wherein the set of training samples comprises a plurality of training samples; each training sample includes at least: the message portrait, semantic information corresponding to the message portrait and tagging information, wherein the tagging information is used for expressing the matching degree of the semantic information and the message portrait.

10. The misoperation-preventive message transmission device according to claim 6, wherein the fourth processing unit is specifically configured to

11. A terminal, comprising: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of claims 1 to 5 when executing the computer program.

12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of claims 1 to 5.