CN108921530B - Information judgment method and device, storage medium and terminal - Google Patents
Information judgment method and device, storage medium and terminal Download PDFInfo
- Publication number
- CN108921530B CN108921530B CN201810650902.8A CN201810650902A CN108921530B CN 108921530 B CN108921530 B CN 108921530B CN 201810650902 A CN201810650902 A CN 201810650902A CN 108921530 B CN108921530 B CN 108921530B
- Authority
- CN
- China
- Prior art keywords
- information
- red packet
- interactive interface
- packet information
- group 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
- G06Q20/102—Bill distribution or payments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
- G06Q20/32—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
- G06Q20/325—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices using wireless networks
Abstract
The embodiment of the application discloses an information judgment method, an information judgment device, a storage medium and a terminal. The information judgment method comprises the following steps: training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model; when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information; and inputting the interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information. By adopting the technical scheme, whether the currently received group information is the red packet information or not can be accurately and quickly judged through the pre-trained red packet information judgment model, and when the currently received group information is determined to be the red packet information, the red packet robbing speed can be further improved.
Description
Technical Field
The embodiment of the application relates to the technical field of communication, in particular to an information judgment method, an information judgment device, a storage medium and a terminal.
Background
At present, terminals such as smart phones, tablet computers, and notebook computers have become essential electronic devices in daily life. With the continuous intellectualization of the terminal equipment, the operating system is loaded in most terminal equipment, so that the terminal equipment can install abundant and various application programs and meet different requirements of users.
With the rapid development and popularization of mobile internet and mobile payment, more and more application programs in terminal equipment develop an electronic red packet function, especially social application in instant messaging chatting such as QQ, wechat and the like. The users can jointly acquire the red packet information in a user group and other multi-user interactive scenes, and then click the red packet information to acquire the red packet. However, the speed of getting red envelope directly affects the user's result of getting red envelope, which directly affects the user experience.
Disclosure of Invention
The embodiment of the application provides an information judgment method, an information judgment device, a storage medium and a terminal, which can accurately and quickly judge whether group information is red packet information.
In a first aspect, an embodiment of the present application provides an information determining method, including:
training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information;
and inputting the interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information.
In a second aspect, an embodiment of the present application provides an information determining apparatus, including:
the model generation module is used for training a preset machine learning model based on the interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
the system comprises an image acquisition module, a display module and a display module, wherein the image acquisition module is used for acquiring an interactive interface image corresponding to group information when the group information corresponding to a preset application program is received;
and the group information judgment module is used for inputting the interactive interface image corresponding to the group information into the red packet information judgment model and determining whether the group information is red packet information.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the information determination method according to the first aspect of the embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides a terminal, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the information determining method according to the first aspect of the embodiment of the present application.
According to the information judgment scheme provided by the embodiment of the application, a preset machine learning model is trained on the basis of interactive interface images corresponding to different groups of information, and a red packet information judgment model is generated; when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information; and inputting the interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information. By adopting the technical scheme, whether the currently received group information is the red packet information can be accurately and quickly judged through the pre-trained red packet information judgment model, so that the red packet robbing speed is further improved.
Drawings
Fig. 1 is a schematic flowchart of an information determining method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of another information determination method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another information determination method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an information determining apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of another terminal provided in the embodiment of the present application.
Detailed Description
The technical scheme of the application is further explained by the specific implementation mode in combination with the attached drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures associated with the present application are shown in the drawings, not all of them.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Fig. 1 is a schematic flowchart of an information determining method according to an embodiment of the present disclosure, where the method may be executed by an information determining apparatus, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in a terminal. As shown in fig. 1, the method includes:
For example, the terminal in the embodiment of the present application may include a mobile phone, a tablet computer, a notebook computer, a smart appliance, and other terminal devices. The terminal is loaded with an operating system.
In this embodiment, the preset machine learning model may include any one of a convolutional neural network model, a decision tree model, a random forest model, and other machine learning models. The red packet information judgment model can be generated by training a preset machine learning model based on the interactive interface images corresponding to different groups of information. The interactive interface image corresponding to the group information may include an image obtained by screenshot of an interface corresponding to the group information. The information content corresponding to the group information may include a picture, an expression, a character, a website address and red packet information, and therefore, the interactive interface image corresponding to the group information may include at least one of the picture, the expression, the character, the website address and the red packet information. It can be understood that the group information is different, and the interactive interface image corresponding to the group information is also different. The red packet information judgment model can be generated according to rules presented in the interactive interface image corresponding to the group information containing the red packet information, and it can be understood that the group information content before and after the red packet information is different, the position of the red packet information in the interactive interface image is different, and the rules presented in the interactive interface image are different, so that the interactive interface image corresponding to different group information can be used as a training sample set, the training sample set is learned, and the red packet information judgment model is generated. The red packet information judgment model can be understood as a learning model which can quickly judge whether the group information is the red packet information after the interactive interface image corresponding to the group information is input.
It should be noted that the interactive interface images corresponding to different groups of information may be trained on the terminal side to generate a red packet information determination model, or the interactive interface images corresponding to different groups of information may be trained on the server side to generate a red packet information determination model. When the red packet information judgment model is generated by training at the server side, the terminal can directly call the trained red packet information judgment model from the server side.
102, when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information.
In this embodiment, the preset application program may include a selected application of a certain type or having a certain function, which is installed in the terminal. For example, the preset application programs may include APPs with functions of robbing/generating electronic red envelope, such as WeChat, Paibao, QQ, and the like. The predetermined application program includes a plurality of groups, and each group has a large amount of various information, i.e., group information. When group information corresponding to a preset application program is received, an interactive interface image corresponding to the group information is obtained. It can be understood that when group information corresponding to a preset application program is received, screenshot is performed on an interactive interface corresponding to the group information, and an image obtained through screenshot is used as an interactive interface image corresponding to the group information. The interactive interface image corresponding to the group information may only include the currently newly received group information, or may include the currently received group information and interactive information before the currently received group information, where the interactive information may include at least one of picture information, expression information, text information, website information, and red packet information.
In this embodiment of the present application, the interactive interface image corresponding to the group information obtained in step 102 is input into a red packet information judgment model to determine whether the group information is red packet information. It can be understood that after the interactive interface image corresponding to the group information is input to the red packet information judgment model, the red packet information judgment model analyzes the interactive interface image corresponding to the group information, and determines whether the group information is red packet information according to an analysis result. Illustratively, when the output result of the red packet information judgment model is "0", it is determined that the group information is not red packet information; and when the output result of the red packet information judgment model is '1', determining that the group information is the red packet information. Or when the output result of the red packet information judgment model is '1', determining that the group information is not red packet information; and when the output result of the red packet information judgment model is '0', determining that the group information is the red packet information. Of course, when the output result of the red packet information judgment model is "no", it may be determined that the group information is not red packet information; and when the output result of the red packet information judgment model is 'yes', determining that the group information is the red packet information. The embodiment of the application does not limit the expression form of the output result of the red packet information judgment model.
According to the information judgment method provided by the embodiment of the application, the preset machine learning model is trained on the basis of the interactive interface images corresponding to different group information, the red packet information judgment model is generated, when the group information corresponding to the preset application program is received, the interactive interface images corresponding to the group information are obtained, the interactive interface images corresponding to the group information are input into the red packet information judgment model, and whether the group information is the red packet information or not is determined. By adopting the technical scheme, whether the currently received group information is the red packet information can be accurately and quickly judged through the pre-trained red packet information judgment model, and when the currently received group information is determined to be the red packet information, the red packet robbing speed can be further improved.
In some embodiments, the interactive interface images corresponding to different groups of information include: the method comprises the steps of obtaining a first sample interactive interface image and a second sample interactive interface image, wherein the first sample interactive interface image comprises an interactive interface image of newly received red packet information, and the second sample interactive interface image comprises an interactive interface image of red packet information corresponding to a disassembled red packet and/or an interactive interface image without red packet information. The advantage that sets up like this lies in, can richen the training sample set of red envelope information judgment model, improves the precision of red envelope information judgment model training.
In the embodiment of the application, the interactive interface image containing newly received red packet information is used as a first sample interactive image, and the interactive interface image containing red packet information corresponding to the disassembled red packet and/or the interactive interface image without red packet information is used as a second sample interactive image. Illustratively, the interactive interface images corresponding to different groups of information include 5000 first sample interactive interface images, 3000 second sample interactive interface images including red packet information corresponding to the disassembled red packet, and 3000 second sample interactive interface images without red packet information. It should be noted that, in the embodiment of the present application, specific numbers of the first sample interactive interface image and the second sample interactive interface image are not limited. In the embodiment of the application, the interactive interface images corresponding to different groups of information comprise the first sample interactive interface image and the second sample interactive interface image, so that not only can the rule of red packet information presented in the interactive interface images corresponding to the group of information be learned, but also the overfitting condition in the training process of a red packet information judgment model can be effectively prevented, meanwhile, the precision of the red packet information judgment model can be further improved, and the accuracy of judging whether the group of information is red packet information or not can be improved.
In some embodiments, training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model, including: marking a first sample interactive interface image based on a first sample mark, and marking a second sample interactive interface image based on a second sample mark to obtain a training sample set; and training a preset machine learning model based on the training sample set to generate a red packet information judgment model. The advantage of setting up like this is, mark first sample interactive interface image and second sample interactive interface image based on different sample marks, can provide the accuracy of red packet information judgement greatly.
Illustratively, a "1" is taken as a first sample mark, that is, the first sample interactive interface image is marked by the "1"; and marking '0' as a second sample, namely marking the second sample interactive interface image with '0', namely marking the second sample interactive interface image as '0'. Optionally, "0" may also be used as the first sample mark, that is, the first sample interactive interface image is marked with "0"; and marking 1 as a second sample, namely marking the second sample interactive interface image with 1. The embodiments of the present application do not limit the specific expressions of the first sample marker and the second sample marker. It can be understood that the marked first sample interactive interface image and the marked second sample interactive interface image are used as a training sample set, and the training sample set is used for training a preset machine learning model to generate a red packet information judgment model.
In some embodiments, after determining whether the group information is red packet information, further comprising: and when the group information is determined to be the red packet information, prompting a user in a preset mode, and/or optimizing system resources to improve the response speed of the system resources to the red packet information. The advantage that sets up like this lies in, can effectively improve the speed of robbing the red packet, further promotes user experience.
In the embodiment of the application, when the crowd information is determined to be the red packet information through the red packet information judgment model, a user can be prompted in a preset mode, and/or system resources are optimized to improve the response speed of the system resources to the red packet information. Illustratively, prompting the user in a preset manner may include: displaying an interactive interface corresponding to the red packet information as a preset color; or prompting the user in a voice broadcast mode; or prompting the user in a preset window in a text mode. Therefore, the user can be reminded to rob the red envelope in time, and the probability of robbing the red envelope by the user is improved. Certainly, the terminal can be set to be in a preset vibration mode to remind the user, and particularly, the situation that the user misses the red packet can be effectively avoided for the situation that the user is distracted or busy in other affairs. Illustratively, optimizing system resources may include: improving performance parameters corresponding to a CPU or a GPU, wherein the performance parameters comprise the core number and the running frequency; or, the corresponding running speed of the network resource is increased. Therefore, the operation time of the user for robbing the red packet can be effectively shortened, the processing speed of the terminal on the red packet information is improved, and the probability of the user for robbing the red packet can be effectively improved.
In some embodiments, when it is determined that the group information is red packet information, optimizing a system resource to increase a response speed of the system resource to the red packet information includes: when the group information is determined to be red packet information, acquiring time information corresponding to the group information receiving time; and when the time information meets a preset time condition, optimizing system resources so as to improve the response speed of the system resources to the red packet information. It can be understood that if the group information is determined to be the red packet information, the system resources are optimized, so that the probability of robbing the user of the red packet can be improved, and meanwhile, the power consumption of the terminal can be greatly increased, and the normal use time of the user on the terminal is influenced. Especially, in daily life, even if the red packet information exists, the red packet amount corresponding to the red packet information is small, and user experience can be seriously influenced. Therefore, when the group information is determined to be the red packet information, time information corresponding to the receiving time of the group information is obtained, and when the time information meets the preset condition, system resources are optimized. The time information may be embodied in the form of a timestamp, may include specific time point information, and may also include specific date categories, such as specific year, month and day, and whether the specific date is a working day or a holiday. For example, when the group information receiving time is determined to be holiday, such as the morning and evening, the system resource can be optimized to improve the response speed of the system resource to the red packet information. It can be understood that, in holidays and some special dates, the peak period of red packet receiving and sending often occurs, and the amount of red packets is usually larger, for example, except at 0, at this time, system resources are optimized, so that the user experience can be greatly improved. The advantage of setting up like this lies in, can have corresponding system resource to optimize, both can promote the user and snatch the probability of red packet in, can suitably reduce terminal consumption again, promote user experience.
Optionally, after optimizing the system resources, the method further includes: and acquiring change information of an interactive interface corresponding to the red packet message, judging whether the red packet robbing operation is finished according to the change information of the interactive interface, and if so, restoring the system resources to a state before optimization. Therefore, the power consumption of the terminal can be effectively reduced.
After determining whether the group information is red packet information, the method further comprises: receiving feedback information of whether the judgment result of the user on the group information is accurate or not; and sending the interactive interface image of the group information corresponding to the feedback information to the red packet information judgment model for training. The red packet information judgment model has the advantages that the feedback information indicating whether the judgment result of the group information is accurate or not is obtained through the user, the interactive interface image of the group information corresponding to the feedback information is sent to the red packet information judgment model for training, the network parameters of the red packet information judgment model can be adjusted at any time according to the feedback information of the user, and the probability of the occurrence of the wrong judgment condition of the group information can be timely reduced.
The feedback information can be understood as correction information or judgment information indicating whether the judgment result of the group information output by the red packet information judgment model by the user is correct or not. For example, a correction option or a judgment option for the group information judgment result output by the red packet information judgment model may be set in the human-computer interaction interface of the terminal device. The correction options may include two options of "yes" and "no", and when the correction option is "yes", the judgment result indicating whether the group information output by the red packet information judgment model is red packet information is approved by the user, and when the correction option is "no", the judgment result indicating whether the group information output by the red packet information judgment model is red packet information is not approved by the user. The judgment options may include two options of "correct" and "incorrect", and when the judgment option is "correct", that is, when a judgment instruction of "correct" input by the user is received, the judgment result indicating whether the group information output by the red packet information judgment model is red packet information by the user is approved, that is, the judgment result indicating whether the group information output by the red packet information judgment model is red packet information is correct. When the judgment option is incorrect, that is, when an incorrect judgment instruction input by the user is received, the judgment result indicating whether the group information output by the red packet information judgment model is the red packet information is not approved by the user, that is, the judgment result indicating whether the group information output by the red packet information judgment model is the red packet information is wrong. The embodiment of the present application does not limit the specific form of receiving the feedback information of the user on the processing manner. And the terminal receives feedback information indicating whether the judgment result of the group information output by the user on the red packet information judgment model is accurate or not, and sends the interactive interface image of the corresponding group information to the red packet information judgment model for training so as to adaptively adjust the network parameters of the red packet information judgment model.
In some embodiments, before obtaining an interactive interface image corresponding to group information when group information corresponding to a preset application program is received, the method further includes: when detecting that a red packet information prediction event is triggered, acquiring current text interaction information corresponding to the preset application program; inputting the current text interaction information into the red packet information prediction model to predict whether red packet information is about to appear or not; the red packet information prediction model is generated by training different text interaction information samples; correspondingly, when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information, including: if the red packet information about to appear is predicted, when group information corresponding to a preset application program is received, an interactive interface image corresponding to the group information is obtained. The method has the advantages that the current text interaction information can be analyzed in advance through the red packet information prediction model to predict whether red packet information is about to appear, when the red packet information is predicted to appear, the newly received group information is further judged to be the red packet information through the red packet information judgment model, and the response speed of the red packet information and the probability of the user to rob the red packet when the newly received group information is the red packet information can be further improved.
In the embodiment of the present application, the triggering condition of the red packet information prediction event may be set according to an actual situation, and the embodiment of the present application is not limited specifically. For example, a red envelope information prediction event may be triggered when detecting that a user action satisfies a preset condition (e.g., entering a preset application program of the terminal, a user inputting a preset slide gesture, such as a "$" identifier input by the user, etc.); or may trigger a red envelope information prediction event when it is detected that the user triggers a physical key. After the red packet information prediction event is triggered, the system may detect that the red packet information prediction event has been triggered by reading a flag bit or receiving a trigger instruction, and the like.
For example, the current text interaction information corresponding to the preset application program may be understood as text interaction information only including text information extracted from the current group information corresponding to the preset application program. The current text interaction information may only include one piece of text information just received, may also include a preset number of pieces of text interaction information, may also include text interaction information traced back from the current time by a preset duration, and of course, may also include all text interaction information corresponding to a preset application program. Even, the current text interaction information may also be null, that is, when the group information corresponding to the preset application program does not include text information, such as when the group information only relates to expression information or picture information, the obtained current interaction information is null; for another example, when the group information interaction has not started in the group corresponding to the preset application program, the current text interaction information corresponding to the preset application program is also empty. It should be noted that, in the embodiment of the present application, the number of specific text messages included in the current text interaction message is not limited.
In the embodiment of the application, the obtained current text interaction information corresponding to the preset application program is input into a red envelope information prediction model to predict whether red envelope information is about to appear or not. It can be understood that, after the current text interaction information is input into the red packet information prediction model, the red packet information prediction model analyzes the current text interaction information, and predicts whether red packet information is about to occur according to an analysis result. For example, when the output result of the red packet information prediction model is "0", it is determined that red packet information is not about to occur; when the output result of the red packet information prediction model is '1', it is determined that red packet information is about to occur. Or when the output result of the red packet information prediction model is '1', determining that the red packet information is not about to appear; and when the output result of the red packet information prediction model is '0', determining that the red packet information is about to appear. Of course, when the output result of the red packet information prediction model is "no", it may be determined that red packet information is not about to occur; and when the output result of the red packet information prediction model is yes, determining that the red packet information is about to appear. The embodiment of the application does not limit the expression form of the output result of the red packet information prediction model.
In this embodiment of the present application, the red envelope information prediction model may be generated by training a second preset machine learning model based on different text interaction information samples. In this embodiment of the application, the second preset machine learning model may include any one of a Recurrent Neural Network (RNN) model, a Long Short-Term Memory (LSTM) network, a threshold cycle unit, a simple cycle unit, and other machine learning models. The different text interaction information samples can comprise chat records of different groups of different user groups, and text interaction information extracted from the chat records. It can be understood that the chat records of different groups, that is, the information content corresponding to the group information may include pictures, expressions, texts, websites and red packet information, and therefore, the text interaction information only including the text information is extracted from the chat records of different groups as a text interaction information sample. Illustratively, 2 ten thousand pieces of text interaction information in WeChat chat records of 500 users are collected, and the 2 ten thousand pieces of text interaction information are used as text interaction information samples for training a red packet information prediction model. The red envelope information prediction model may be generated according to a rule of presenting text interaction information samples corresponding to upcoming red envelope information, for example, more than a preset number (e.g., N) of "red" keywords may appear in text interaction information corresponding to the upcoming red envelope information. It can be understood that the text interaction information before the red packet information appears and the text interaction information corresponding to the red packet information do not appear have different feature rules, so that different text interaction information samples can be used as a training sample set, and the training sample set is learned to generate a red packet information prediction model. The red envelope information prediction model can be understood as a learning model which can quickly predict whether red envelope information is about to appear or not after text interaction information is input.
Fig. 2 is a schematic flow chart of an information determination method according to an embodiment of the present application. As shown in fig. 2, the method includes:
The first sample interactive interface image comprises an interactive interface image of newly received red packet information, and the second sample interactive interface image comprises an interactive interface image of red packet information corresponding to the removed red packet and/or an interactive interface image without red packet information.
And 203, training a preset machine learning model based on the training sample set to generate a red packet information judgment model.
And 204, when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information.
And step 206, when the group information is determined to be the red packet information, prompting a user in a preset mode, and/or optimizing system resources to improve the response speed of the system resources to the red packet information.
And step 207, receiving feedback information indicating whether the judgment result of the user on the group information is accurate.
And 208, sending the interactive interface image of the group information corresponding to the feedback information to a red packet information judgment model for training.
According to the information judgment method provided by the embodiment of the application, a first sample interactive interface image is marked based on a first sample mark, a second sample interactive interface image is marked based on a second sample mark to obtain a training sample set, a preset machine learning model is trained based on the training sample set to generate a red packet information judgment model, when group information corresponding to a preset application program is received, the interactive interface image corresponding to the group information is input into the red packet information judgment model to determine whether the group information is red packet information, and whether the currently received group information is red packet information or not can be accurately and quickly judged through the pre-trained red packet information judgment model. When the group information is determined to be the red packet information, prompting is carried out on the user through a preset mode, and when the time information corresponding to the receiving moment of the group information meets a preset time condition, system resources are optimized to improve the response speed of the system resources to the red packet information, so that the probability of the user robbing the red packet can be greatly improved, and the user experience is improved.
Fig. 3 is a schematic flowchart of an information determining method according to an embodiment of the present application. As shown in fig. 3, the method includes:
and 301, acquiring a first sample interactive interface image and a second sample interactive interface image.
The first sample interactive interface image comprises an interactive interface image of newly received red packet information, and the second sample interactive interface image comprises an interactive interface image of red packet information corresponding to the disassembled red packet and/or an interactive interface image without red packet information.
And 304, when the red packet information prediction event is triggered, acquiring current text interaction information corresponding to a preset application program.
And 305, inputting the current text interaction information into a red packet information prediction model to predict whether red packet information is about to appear.
The method comprises the following steps that a red packet information prediction model is used for training and generating different text interaction information samples;
And 306, if the red packet information is predicted to appear, acquiring an interactive interface image corresponding to the group information when the group information corresponding to the preset application program is received.
And 308, when the group information is determined to be the red packet information, prompting a user in a preset mode, and acquiring time information corresponding to the receiving time of the group information.
And 309, when the time information meets a preset time condition, optimizing the system resources to improve the response speed of the system resources to the red packet information.
And 310, receiving feedback information of whether the judgment result of the user on the group information is accurate.
And 311, sending the interactive interface image of the group information corresponding to the feedback information to a red packet information judgment model for training.
According to the information judgment method provided by the embodiment of the application, when a red packet information prediction event is triggered, the current text interaction information corresponding to a preset application program is obtained, the current text interaction information is input into a red packet information prediction model, and whether red packet information is about to appear or not is predicted, wherein the red packet information prediction model is generated by training different text interaction information samples, if the red packet information is about to appear, when the group information corresponding to the preset application program is received, the red packet information judgment model is further used for judging whether the group information is red packet information or not, and the response speed of the red packet information and the probability of red packet robbery of a user can be further improved when the newly received group information is red packet information.
Fig. 4 is a schematic structural diagram of an information determining apparatus provided in an embodiment of the present application, where the apparatus may be implemented by software and/or hardware, and is generally integrated in a terminal, and may determine whether group information is red packet information by executing an information determining method. As shown in fig. 4, the apparatus includes:
the model generation module 401 is configured to train a preset machine learning model based on the interactive interface images corresponding to different groups of information, and generate a red packet information judgment model;
an image obtaining module 402, configured to obtain, when group information corresponding to a preset application is received, an interactive interface image corresponding to the group information;
the group information judgment module 403 is configured to input the interactive interface image corresponding to the group information into the red packet information judgment model, and determine whether the group information is red packet information.
The information judgment device provided in the embodiment of the application trains the preset machine learning model based on the interactive interface images corresponding to different group information to generate the red packet information judgment model, acquires the interactive interface images corresponding to the group information when receiving the group information corresponding to the preset application program, inputs the interactive interface images corresponding to the group information into the red packet information judgment model, and determines whether the group information is red packet information. By adopting the technical scheme, whether the currently received group information is the red packet information can be accurately and quickly judged through the pre-trained red packet information judgment model, and when the currently received group information is determined to be the red packet information, the red packet robbing speed can be further improved.
Optionally, the interactive interface image includes at least one of a picture, an expression, a character, a website, and red package information.
Optionally, the interactive interface images corresponding to the different groups of information include:
the method comprises a first sample interactive interface image and a second sample interactive interface image, wherein the first sample interactive interface image comprises an interactive interface image of newly received red packet information, and the second sample interactive interface image comprises an interactive interface image of red packet information corresponding to a disassembled red packet and/or an interactive interface image without red packet information.
Optionally, the model generation module includes:
marking a first sample interactive interface image based on a first sample mark, and marking a second sample interactive interface image based on a second sample mark to obtain a training sample set;
and training a preset machine learning model based on the training sample set to generate a red packet information judgment model.
Optionally, the apparatus further comprises:
and the optimization module is used for prompting a user in a preset mode and/or optimizing system resources to improve the response speed of the system resources to the red packet information when the group information is determined to be the red packet information after determining whether the group information is the red packet information.
Optionally, when it is determined that the group information is red packet information, optimizing a system resource to improve a response speed of the system resource to the red packet information includes:
when the group information is determined to be red packet information, acquiring time information corresponding to the group information receiving time;
and when the time information meets a preset time condition, optimizing system resources to improve the response speed of the system resources to the red packet information.
Optionally, after determining whether the group information is red packet information, the method further includes:
receiving feedback information of whether the judgment result of the user on the group information is accurate or not;
and sending the interactive interface image of the group information corresponding to the feedback information to the red packet information judgment model for training.
Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for determining information, the method including:
training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information;
And inputting the interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDRRAM, SRAM, EDORAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application and containing the computer-executable instructions is not limited to the information determination operation described above, and may also perform related operations in the information determination method provided in any embodiments of the present application.
The embodiment of the application provides a terminal, and the terminal can be integrated with the information judgment device provided by the embodiment of the application. Fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application. The terminal 500 may include: the information judging method comprises a memory 501, a processor 502 and a computer program which is stored on the memory and can be run by the processor, wherein the information judging method is realized when the processor 502 executes the computer program.
The terminal provided by the embodiment of the application can accurately and quickly judge whether the currently received group information is the red packet information or not through the pre-trained red packet information judgment model, and is favorable for further improving the red packet robbing speed when the currently received group information is determined to be the red packet information.
Fig. 6 is a schematic structural diagram of another terminal provided in the embodiment of the present application, where the terminal may include: a housing (not shown), a memory 601, a Central Processing Unit (CPU) 602 (also called as a processor, hereinafter referred to as CPU), a circuit board (not shown), and a power circuit (not shown). The circuit board is arranged in a space enclosed by the shell; the CPU602 and the memory 601 are disposed on the circuit board; the power supply circuit is used for supplying power to each circuit or device of the terminal; the memory 601 is used for storing executable program codes; the CPU602 executes a computer program corresponding to the executable program code by reading the executable program code stored in the memory 601 to implement the steps of:
Training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information;
and inputting the interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information.
The terminal further comprises: peripheral interfaces 603, RF (Radio Frequency) circuitry 605, audio circuitry 606, speakers 611, a power management chip 608, an input/output (I/O) subsystem 609, other input/control devices 610, a touch screen 612, other input/control devices 610, and an external port 604, which communicate through one or more communication buses or signal lines 607.
It should be understood that the illustrated terminal 600 is merely one example of a terminal and that the terminal 600 may have more or fewer components than shown in the figures, may combine two or more components, or may have a different configuration of components. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.
The following describes in detail the terminal for information determination provided in this embodiment, where the terminal is a mobile phone as an example.
A memory 601, the memory 601 being accessible by the CPU602, the peripherals interface 603, etc., the memory 601 may comprise high speed random access memory, and may further comprise non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other volatile solid state storage devices.
A peripherals interface 603, said peripherals interface 603 allowing to connect input and output peripherals of the device to the CPU602 and the memory 601.
An I/O subsystem 609, the I/O subsystem 609 may connect input and output peripherals on the device, such as a touch screen 612 and other input/control devices 610, to the peripheral interface 603. The I/O subsystem 609 may include a display controller 6091 and one or more input controllers 6092 for controlling other input/control devices 610. Where one or more input controllers 6092 receive electrical signals from or transmit electrical signals to other input/control devices 610, the other input/control devices 610 may include physical buttons (push buttons, rocker buttons, etc.), dials, slide switches, joysticks, click wheels. It is noted that the input controller 6092 may be connected to any one of: a keyboard, an infrared port, a USB interface, and a pointing device such as a mouse.
A touch screen 612, which touch screen 612 is an input interface and an output interface between the user terminal and the user, displays visual output to the user, which may include graphics, text, icons, video, and the like.
The display controller 6091 in the I/O subsystem 609 receives an electrical signal from the touch screen 612 or transmits an electrical signal to the touch screen 612. The touch screen 612 detects a contact on the touch screen, and the display controller 6091 converts the detected contact into an interaction with a user interface object displayed on the touch screen 612, that is, to implement a human-computer interaction, where the user interface object displayed on the touch screen 612 may be an icon for running a game, an icon networked to a corresponding network, or the like. It is worth mentioning that the device may also comprise a light mouse, which is a touch sensitive surface that does not show visual output, or an extension of the touch sensitive surface formed by the touch screen.
The RF circuit 605 is mainly used to establish communication between the mobile phone and the wireless network (i.e., network side), and implement data reception and transmission between the mobile phone and the wireless network. Such as sending and receiving short messages, e-mails, etc. In particular, RF circuitry 605 receives and transmits RF signals, also referred to as electromagnetic signals, through which RF circuitry 605 converts electrical signals to or from electromagnetic signals and communicates with a communication network and other devices. RF circuitry 605 may include known circuitry for performing these functions including, but not limited to, an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC (CODEC) chipset, a Subscriber Identity Module (SIM), and so forth.
The audio circuit 606 is mainly used to receive audio data from the peripheral interface 603, convert the audio data into an electric signal, and transmit the electric signal to the speaker 611.
The speaker 611 is used to convert the voice signal received by the handset from the wireless network through the RF circuit 605 into sound and play the sound to the user.
And a power management chip 608 for supplying power and managing power to the hardware connected to the CPU602, the I/O subsystem, and the peripheral interface.
The information judgment device, the storage medium and the terminal provided in the above embodiments can execute the information judgment method provided in any embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details that are not described in detail in the above embodiments, reference may be made to the information determination method provided in any embodiment of the present application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. An information determination method, comprising:
training a preset machine learning model based on interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information;
inputting an interactive interface image corresponding to the group information into the red packet information judgment model, and determining whether the group information is red packet information;
when group information corresponding to a preset application program is received, before an interactive interface image corresponding to the group information is acquired, the method further comprises the following steps:
when detecting that a red packet information prediction event is triggered, acquiring current text interaction information corresponding to the preset application program;
inputting the current text interaction information into the red packet information prediction model to predict whether red packet information is about to appear or not; the red packet information prediction model is generated by training different text interaction information samples;
correspondingly, when group information corresponding to a preset application program is received, acquiring an interactive interface image corresponding to the group information, including:
and if the red packet information is predicted to appear, acquiring an interactive interface image corresponding to the group information when the group information corresponding to the preset application program is received.
2. The method of claim 1, wherein the interactive interface image comprises at least one of a picture, an expression, a text, a website address, and red envelope information.
3. The method of claim 1, wherein the interactive interface image corresponding to the different group information comprises:
the method comprises a first sample interactive interface image and a second sample interactive interface image, wherein the first sample interactive interface image comprises an interactive interface image of newly received red packet information, and the second sample interactive interface image comprises an interactive interface image of red packet information corresponding to a disassembled red packet and/or an interactive interface image without red packet information.
4. The method of claim 3, wherein training a preset machine learning model based on the interactive interface images corresponding to different groups of information to generate a red packet information judgment model comprises:
marking a first sample interactive interface image based on a first sample mark, and marking a second sample interactive interface image based on a second sample mark to obtain a training sample set;
and training a preset machine learning model based on the training sample set to generate a red packet information judgment model.
5. The method of claim 1, after determining whether the group information is red packet information, further comprising:
and when the group information is determined to be the red packet information, prompting a user in a preset mode, and/or optimizing system resources so as to improve the response speed of the system resources to the red packet information.
6. The method of claim 5, wherein when it is determined that the group information is red packet information, optimizing a system resource to increase a response speed of the system resource to the red packet information comprises:
when the group information is determined to be red packet information, acquiring time information corresponding to the group information receiving time;
and when the time information meets a preset time condition, optimizing system resources to improve the response speed of the system resources to the red packet information.
7. The method of claim 1, after determining whether the group information is red packet information, further comprising:
receiving feedback information of whether the judgment result of the user on the group information is accurate or not;
and sending the interactive interface image of the group information corresponding to the feedback information to the red packet information judgment model for training.
8. An information determination apparatus, comprising:
the model generation module is used for training a preset machine learning model based on the interactive interface images corresponding to different groups of information to generate a red packet information judgment model;
the system comprises an image acquisition module, a display module and a display module, wherein the image acquisition module is used for acquiring an interactive interface image corresponding to group information when the group information corresponding to a preset application program is received;
the group information judgment module is used for inputting the interactive interface image corresponding to the group information into the red packet information judgment model and determining whether the group information is red packet information;
wherein, still include:
the text interaction information acquisition module is used for acquiring current text interaction information corresponding to a preset application program when a red packet information prediction event is triggered before acquiring an interaction interface image corresponding to group information when the group information corresponding to the preset application program is received;
the red packet information prediction module is used for inputting the current text interaction information into the red packet information prediction model and predicting whether red packet information is about to appear or not; the red packet information prediction model is generated by training different text interaction information samples;
Correspondingly, the image acquisition module is configured to:
if the red packet information about to appear is predicted, when group information corresponding to a preset application program is received, an interactive interface image corresponding to the group information is obtained.
9. A computer-readable storage medium on which a computer program is stored, the program, when being executed by a processor, implementing the information determination method according to any one of claims 1 to 7.
10. A terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the information determination method according to any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810650902.8A CN108921530B (en) | 2018-06-22 | 2018-06-22 | Information judgment method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810650902.8A CN108921530B (en) | 2018-06-22 | 2018-06-22 | Information judgment method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108921530A CN108921530A (en) | 2018-11-30 |
| CN108921530B true CN108921530B (en) | 2022-06-28 |
Family
ID=64420487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810650902.8A Active CN108921530B (en) | 2018-06-22 | 2018-06-22 | Information judgment method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921530B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625353B (en) * | 2020-05-18 | 2024-03-12 | 北京达佳互联信息技术有限公司 | Virtual resource distribution processing method, device, server and storage medium |
| CN112053145B (en) * | 2020-07-20 | 2023-01-31 | 博瑞得科技有限公司 | Network red packet action identification method and device and storage medium |
| CN112637045B (en) * | 2020-12-14 | 2022-08-12 | 中国联合网络通信集团有限公司 | Group message notification method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010273256A (en) * | 2009-05-25 | 2010-12-02 | Konica Minolta Business Technologies Inc | Image forming device and image forming program |
| CN105323145A (en) * | 2014-07-17 | 2016-02-10 | 腾讯科技（深圳）有限公司 | Malicious information identification method, device and system |
| CN105827501A (en) * | 2015-07-30 | 2016-08-03 | 维沃移动通信有限公司 | Message reminding method and electronic equipment |
| CN105975144A (en) * | 2016-04-25 | 2016-09-28 | 维沃移动通信有限公司 | Information processing method and apparatus |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484867A (en) * | 2014-12-30 | 2015-04-01 | 小米科技有限责任公司 | Picture processing method and device |
| CN105099877B (en) * | 2015-06-26 | 2018-11-02 | 小米科技有限责任公司 | Instant communication message treating method and apparatus |
| WO2016045647A2 (en) * | 2015-11-26 | 2016-03-31 | 华为技术有限公司 | Red envelope data processing method and terminal |
-
2018
- 2018-06-22 CN CN201810650902.8A patent/CN108921530B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010273256A (en) * | 2009-05-25 | 2010-12-02 | Konica Minolta Business Technologies Inc | Image forming device and image forming program |
| CN105323145A (en) * | 2014-07-17 | 2016-02-10 | 腾讯科技（深圳）有限公司 | Malicious information identification method, device and system |
| CN105827501A (en) * | 2015-07-30 | 2016-08-03 | 维沃移动通信有限公司 | Message reminding method and electronic equipment |
| CN105975144A (en) * | 2016-04-25 | 2016-09-28 | 维沃移动通信有限公司 | Information processing method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108921530A (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363593B (en) | Application program preloading method and device, storage medium and terminal | |
| CN108647052B (en) | Application program preloading method and device, storage medium and terminal | |
| EP3579104B1 (en) | Method and apparatus for establishing an application prediction model, storage medium and terminal | |
| US11429880B2 (en) | Methods and systems for preloading applications and generating prediction models | |
| CN108614722B (en) | Application program preloading method and device, storage medium and terminal | |
| EP3575961B1 (en) | Method and apparatus for updating application prediction model, storage medium, and terminal | |
| US11604660B2 (en) | Method for launching application, storage medium, and terminal | |
| CN108595230B (en) | Application program preloading method and device, storage medium and terminal | |
| CN112041791B (en) | Method and terminal for displaying virtual keyboard of input method | |
| CN109947496B (en) | Application program preloading method and device, storage medium and mobile terminal | |
| US11099861B2 (en) | Method for preloading application, storage medium, and terminal | |
| CN107896243B (en) | Acceleration method and device for network data loading, storage medium and mobile terminal | |
| CN109947497B (en) | Application program preloading method and device, storage medium and mobile terminal | |
| CN107944259A (en) | Using the management-control method of startup, device and storage medium and mobile terminal | |
| CN108804153B (en) | Application program preloading method and device, storage medium and terminal | |
| CN108958828B (en) | Application program preloading method and device, storage medium and terminal | |
| CN108921530B (en) | Information judgment method and device, storage medium and terminal | |
| CN108647056B (en) | Application program preloading method and device, storage medium and terminal | |
| CN108762844B (en) | Application program preloading method and device, storage medium and terminal | |
| CN111918386B (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| CN107395888B (en) | Processing method, device, storage medium and the mobile terminal of blank screen gesture | |
| CN114430504B (en) | Recommendation method and related device for media content | |
| CN108829863B (en) | Information prediction method, information prediction device, storage medium and terminal | |
| CN108762633B (en) | Picture adding method and device, terminal equipment and storage medium | |
| CN111884906A (en) | Information notification 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |