CN113868410A - Short message interception method, device, equipment and medium based on user interest - Google Patents
Short message interception method, device, equipment and medium based on user interest Download PDFInfo
- Publication number
- CN113868410A CN113868410A CN202111093693.XA CN202111093693A CN113868410A CN 113868410 A CN113868410 A CN 113868410A CN 202111093693 A CN202111093693 A CN 202111093693A CN 113868410 A CN113868410 A CN 113868410A
- Authority
- CN
- China
- Prior art keywords
- short message
- suspicious
- weight
- interest
- user
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to artificial intelligence, and provides a short message intercepting method, a device, computer equipment and a computer readable medium based on user interest, wherein the short message intercepting method based on the user interest comprises the steps of obtaining a short message to be identified, configuring a suspicious label for the short message to be identified according to the information of a sender of the short message to be identified to obtain a suspicious short message, extracting a keyword of the suspicious short message, matching the keyword with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message, configuring a non-interest label for the suspicious short message according to the weight value to obtain a non-interest short message, and executing intercepting operation on the non-interest short message. The short message interception method based on the user interest can accurately identify whether the content of the short message meets the interest of the user or not, so that the short message interception is more intelligent and accurate.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a short message intercepting method, a device, equipment and a medium based on user interest.
Background
With the development of information technology, mobile phones have become communication devices which people can not leave everyday, and the mobile phones bring convenience to the life of people and also bring troubles, such as receiving short messages which are not interesting or irrelevant to the mobile phones. After receiving the short message, the user can usually unsubscribe according to the prompt reply of the short message, namely 'T' or 'N' or 'TD', but for a part of platforms, the reply can not only unsubscribe, but also remind the message sender that the number is used by people, and further can seriously continue to send the related short message. For example, when a user unsuccessfully subscribes to a sales promotion short message of a certain network platform, the network platform can still exchange another number for continuous transmission, and the user can only screen short messages of all platform merchants by one key, but the sales promotion of commodities which the user really is interested in cannot receive a prompt. The user can also decide to receive the short message sent by the number which is not interested by setting the blacklist on the mobile phone, although the method can accord with the real interest of the user, the method needs the user to browse the received short message contents one by one, the recognition efficiency is very low, and the new sending number cannot be set in advance. Therefore, how to provide a method capable of automatically identifying whether the content of the short message meets the interest of the user and further intercepting the short message which does not meet the interest of the user is a problem to be solved at present.
Disclosure of Invention
The embodiment of the invention provides a short message intercepting method and device based on user interest and computer equipment, and aims to solve the problems that in the prior art, whether the content of a short message meets the interest of a user cannot be automatically identified, and further, the short message which does not meet the interest of the user cannot be selectively intercepted.
One aspect of the present application provides a short message intercepting method based on user interests, including:
acquiring a short message to be identified, and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and performing interception operation on the uninteresting short messages.
A second aspect of the embodiments of the present application provides a short message intercepting apparatus based on user interests, including:
the first identification module is used for acquiring a short message to be identified and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
the weight matching module is used for extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
the second identification module is used for configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and the short message interception module is used for executing interception operation on the uninteresting short messages.
A third aspect of the embodiments of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements a short message intercepting method based on user interests provided by the first aspect when executing the computer program.
A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for intercepting a short message based on user interest provided by the first aspect is implemented.
The short message intercepting method, the short message intercepting device, the computer equipment and the computer readable storage medium based on the user interest have the following beneficial effects that:
the method comprises the steps of obtaining a short message to be identified, configuring a suspicious tag for the short message to be identified according to information of a sender of the short message to be identified to obtain a suspicious short message, extracting a keyword of the suspicious short message, matching the extracted keyword with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message, configuring a non-interest tag for the suspicious short message according to the weight value of the suspicious short message to obtain a non-interest short message, and finally performing interception operation on the non-interest short message. Therefore, the short message interception method in the embodiment of the invention can accurately identify whether the content of the short message meets the interest of the user, further intercept the short message which does not meet the interest of the user, and receive the short message which meets the interest of the user, so that the short message interception is more intelligent and accurate.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic view of an application environment of a short message intercepting method based on user interests in an embodiment of the present application;
FIG. 2 is a flowchart of a short message intercepting method based on user interests in an embodiment of the present application;
FIG. 3 is a sub-flowchart of the step S1 of the short message intercepting method based on user interest according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for creating a weighted list of interest keywords according to an embodiment of the present application;
FIG. 5 is a sub-flowchart of the step S3 of the short message intercepting method based on user interest according to an embodiment of the present application;
FIG. 6 is a block diagram of an embodiment of a short message intercepting apparatus based on user interests;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
With the development of information technology, mobile phones have become communication devices which people can not leave everyday, and the mobile phones bring convenience to the life of people and also bring troubles, such as receiving short messages which are not interesting or irrelevant to the mobile phones. After receiving the short message, the user can usually unsubscribe according to the prompt reply of the short message, namely 'T' or 'N' or 'TD', but for a part of platforms, the reply can not only unsubscribe, but also remind the message sender that the number is used by people, and further can seriously continue to send the related short message. For example, when a user unsuccessfully subscribes to a sales promotion short message of a certain network platform, the network platform can still exchange another number for continuous transmission, and the user can only screen short messages of all platform merchants by one key, but the sales promotion of commodities which the user really is interested in cannot receive a prompt. The user can also decide to receive the short message sent by the number which is not interested by setting the blacklist on the mobile phone, although the method can accord with the real interest of the user, the method needs the user to browse the received short message contents one by one, the recognition efficiency is very low, and the new sending number cannot be set in advance. The existing interception methods mostly have the following problems: unknown numbers or network numbers cannot be intercepted; each number needs to be operated, which is too troublesome; and selective interception cannot be carried out according to the recent requirements of users. Therefore, how to provide a method capable of automatically identifying whether the content of the short message meets the interest of the user and further intercepting the short message which does not meet the interest of the user is a problem which is expected to be solved by the embodiment of the application.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating an application environment of a short message intercepting method based on user interests in an embodiment of the present application.
In the short message intercepting method based on user interest provided in this embodiment, as in the application environment of fig. 1, a user terminal and a short message sending platform communicate with each other through a network. The user terminal includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The short message sending platform can be an independent server, and can also be a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data and artificial intelligence platform and the like.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
Referring to fig. 2, fig. 2 is a flowchart illustrating a short message intercepting method based on user interests in an embodiment of the present application.
As shown in fig. 2, a method for intercepting a short message based on user interest is provided, which is described by taking the application of the method to the terminal device in fig. 1 as an example, and includes the following steps:
s1, obtaining the short message to be identified, and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain the suspicious short message.
In the method in this embodiment, a message receiving port of a user terminal is monitored, when a short message arrives, the short message is first acquired, and sender information is extracted from the short message, where the sender information may be an identification code capable of uniquely characterizing sender information or a network address of a sender, and the sender information may characterize a source of the short message, and whether the short message is a short message related to a user of the terminal may be preliminarily determined by analyzing the sender information. It can be understood that the step of acquiring the short message does not mean receiving the short message, but can be understood as a step of "checking" the short message before the user terminal receives the short message, so that the user cannot be triggered to ring or shake the alert in the process.
If the short message is determined to be related to the terminal user through the sender information, the short message is normally received, and the user is reminded according to a reminding mode set in the user terminal. If there is no correlation between the sender information and the terminal user, it indicates that the short message has a possibility that the short message is a short message that the terminal user is not interested in, so in this step, a suspicious tag is configured for the short message to distinguish the suspicious short message, so as to further analyze the content of the suspicious short message in the following.
S2, extracting the keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain the weight value of the suspicious short message.
In this embodiment, because the short message usually includes a relatively long text content, if the content of the short message is comprehensively understood to identify the content of the short message, a relatively large amount of system resources are consumed, and the short message is represented by using the keywords in the content of the short message, and then the keywords are analyzed, so that the overhead of the system can be reduced. Therefore, in the step, the keyword extraction model is adopted to extract the keywords from the content of the suspicious short message to obtain the keywords of the suspicious short message, and then the keywords are matched with the pre-established interest keyword weight list to obtain the weight value of the suspicious short message.
The content in the interest keyword weight list is the corresponding relation between the keywords related to the user interest and the weight values. The keywords in the interest keyword weight list refer to keywords of related contents which are frequently noticed by the user or relatively noticed by the user in a recent period of time, the weight value of the keyword indicates the interest degree of the user in the contents corresponding to the keyword, the higher the weight value of the keyword is, the higher the interest degree of the user in the keyword is, and the lower the weight value of the keyword is, the lower the interest degree of the user in the keyword is. It should be noted that, if a plurality of keywords are extracted from a certain suspicious short message, the highest weight value is used as the weight value of the suspicious short message. And if the keywords extracted from a certain suspicious short message do not match with the corresponding keywords in the interest keyword weight list, taking the lowest weight value in the list as the weight value of the suspicious short message.
S3, configuring uninteresting labels for the suspicious messages according to the weight values to obtain uninteresting messages.
In this embodiment, after the weight value of the suspicious short message is matched from the interest keyword weight list, the interest degree of the user for the suspicious short message is obtained, and it can be determined whether the suspicious short message belongs to the short message in which the user is interested by using the interest degree as a reference.
Specifically, the suspicious message is determined whether the suspicious message is a message which the user is interested in by setting an interest threshold, and when the weighted value of the suspicious message is greater than the interest threshold, the suspicious message is indicated to belong to the message which the user is interested in; when the weight value of the suspicious short message is smaller than the interest threshold, the suspicious short message is indicated to not belong to the short message which is interested by the user, and the label which is not interested in the suspicious short message is configured to be distinguished.
And S4, performing interception operation on the uninteresting short messages.
In this embodiment, the short messages that are not of interest to the user can be determined through the foregoing steps, and then the short messages that are not of interest need to be intercepted. The purpose of intercepting the uninteresting short messages is not to allow the short messages to enter an inbox of a user, and the short messages are not reminded of the user by the bell or vibration, so that the user does not perceive the short messages at all, just as if the short messages are not received. It can be understood that while the present embodiment identifies the short message that is not of interest to the user, the suspicious short message that is not determined as the short message that is not of interest may be normally received. Therefore, the work of short message interception based on the user interest is completed.
Referring to fig. 3, fig. 3 is a sub-flowchart illustrating a step S1 of a short message intercepting method based on user interests according to an embodiment of the present application.
As an embodiment of the present application, as shown in fig. 3, the configuring a suspicious tag for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message includes:
and S11, extracting the sender information of the short message to be identified, and matching the sender information with the address list information in the terminal equipment.
In this embodiment, the originator information is extracted from the short message to be identified, where the originator information at least includes the number of the originator, and then the extracted originator information is matched with the address book information in the user terminal device, so as to determine whether the number in the originator information is in the address book of the terminal device in sequence. The address book information referred to herein is contact information in the user terminal device, and is created manually one by the user.
And S12, when the sender information is in the address list, receiving the short message to be identified.
If the sender information can be matched with the contact information in the address list after matching, the short message is sent by a person or a unit familiar to a terminal user and has a certain relevance with the terminal user, the short message can be determined to be seen by the user, so that normal receiving operation is performed on the short message, and the short message is received to an inbox and rings or vibrates to remind the user.
Further, when the method in this embodiment matches the information of the originator with the information of the address book, the information of the originator may be further matched with a black-and-white list in the information of the address book, if the information of the originator is successfully matched with the white list in the address book, a receiving operation is performed on the short message, and if the information of the originator is successfully matched with the black list in the address book, an intercepting operation is performed on the short message.
And S13, when the sender information is not in the address list, configuring a suspicious label for the short message to be identified corresponding to the sender information to obtain a suspicious short message.
If the sender information is matched and the corresponding contact information cannot be matched in the address list, the short message is sent by a person or a unit unfamiliar to the terminal user, and the short messages may contain contents which are not interested by the terminal user, so that the short message is temporarily determined as a suspicious short message by configuring a suspicious label for the short message.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for creating a weighted list of interest keywords according to an embodiment of the present application.
As an embodiment of the present application, as shown in fig. 4, the method for creating the interest keyword weight list includes:
and S21, monitoring the terminal equipment and acquiring the terminal use data in the terminal equipment.
In this embodiment, the use condition of the terminal by the user may reflect the interest of the user, for example, the user often uses a certain video playing software to watch a certain popular play in the recent period, or the user often chats with friends about a certain digital product through a chatting software in the recent period, and so on. Therefore, the use condition of the user on the terminal is monitored, the terminal use data of the user in the recent period of time is obtained, the terminal use data of the user is analyzed and mined, and the interest point of the user can be obtained.
Wherein the terminal usage data includes: the terminal comprises a network access record of the terminal, an APP usage record on the terminal and information input through an input module on the terminal.
The network access record refers to network site information accessed by a user using the terminal in the last period of time, the APP use record refers to an APP used and a use duration used in the last period of time by the user, and the information input by the input module refers to content input by the user through the input module of the terminal in the last period of time, such as content input by the user through a keyboard of an input method.
S22, extracting keywords of the terminal use data through the LDA document main body model and calculating weight values corresponding to the keywords.
Inputting the terminal use data extracted in the above steps into an lda (late Dirichlet allocation) main body model for keyword extraction and weight calculation.
The LDA topic model is a document topic generation model, and the idea is that each word of an article is considered to be obtained through a process of selecting a certain topic with a certain probability and selecting a certain word from the topic with a certain probability. Document-to-topic follows a polynomial distribution, and topic-to-word follows a polynomial distribution. The LDA topic model can give the topic of each document in the document set in a probability distribution mode, and after the topics are extracted by analyzing the documents, the probability of each topic can be calculated according to the distribution of the topics, so that the weight value of each topic is obtained.
In this example, the extracted terminal usage data is input into the LDA topic model as a document, and the parameter format of the terminal usage data is adjusted as follows according to the terminal scene requirements:
when the data source is the network access record of the terminal, the input parameter format is as follows: date _ web page address _ dwell time, inputting the data into the model, the model will actively request the address, download the web page content, and extract the keywords from the content.
When the data source is the APP usage record on the terminal, the input content is: and the date _ APPID _ duration is used, and the Chinese name, English name, Pinyin and abbreviation of the application are identified from the stored application information list in the model according to the terminal type and the APPID and are output as key words.
When the data source is the information input by the input module on the terminal, the input parameter format is as follows: and in the date _ input content model, the input content is subjected to word segmentation, and keywords are extracted.
It should be noted here that the dimension of calculating the weight value of the keyword by the LDA topic model does not include a time dimension, so that before the LDA topic model is used to obtain the keyword weight list, the time dimension is added on the basis of the existing LDA model in this embodiment, so that the weight value in the keyword weight list obtained by the LDA model can be simultaneously affected by the time from the document date to the current time, the dwell time of the web page, and the use time of the app. The time dimension of the LDA model may be increased by using the time dimension as a module and encapsulating the LDA model, or the interior of the LDA model may be directly modified to increase the time dimension, which is not limited herein.
S23, establishing the interest keyword weight list according to the keywords and the weight values corresponding to the keywords.
The three parameters are input into an LDA topic model to obtain results, the results are summarized, and the results are stored in a (keyword and weight) mode to obtain an interest keyword weight list, wherein the longer the document date corresponding to the keyword in the interest keyword weight list is away from the current time, the lower the weight value is, the longer the web page stay time is, the longer the APP use time is, the more the number of times of occurrence of the keyword is, and the higher the weight value is correspondingly.
Referring to fig. 5, fig. 5 is a sub-flowchart illustrating step S3 of a short message intercepting method based on user interests according to an embodiment of the present application.
As an embodiment of the present application, as shown in fig. 5, the step S3, according to the weight value, configuring the uninteresting tag for the suspicious short message to obtain the uninteresting short message includes:
in this embodiment, after obtaining the interest keyword weight list, the keyword of the suspicious short message may be matched with the keyword in the list to obtain the weight value of the suspicious short message, and then whether the suspicious short message is a short message in which the user is interested is determined according to the weight value.
S31, dividing the keywords in the interest keyword weight list into a first weight interval, a second weight interval and a third weight interval according to the sequence of the weight values from high to low.
Firstly, arranging keywords in an interest keyword weight list according to the sequence of high weight values to low weight values, and then dividing the keywords into a plurality of weight areas according to different proportions for integrally distinguishing the keywords with different weights.
In this embodiment, the keywords are divided into three sections according to the order of the weights from high to low, which are a first weight section, a second weight section and a third weight section, where the first weight section is a section with the highest weight value, the second weight section is a section with the middle weight value, and the third weight section is a section with the lowest weight value. For example, the first 40% of the weight values are divided into a first weight interval, the middle 30% of the weight values are divided into a second weight interval, and the last 30% of the weight values are divided into a third weight interval. The specific division method may be empirically performed, and the specific division ratio and standard are not limited herein.
S32, when the weight value of the suspicious short message falls into the first weight interval, executing receiving operation on the suspicious short message.
The keyword falling into the first weight interval represents that the user has high interest in the keyword in the area, and the part of the short message needs to be seen by the user, so when the weight value of the suspicious short message falls into the first weight interval, normal receiving operation is performed on the short message, the short message is received to an inbox, and the user is reminded through ringing or vibration.
S33, when the weight value of the suspicious short message falls into the second weight interval, configuring a tracking mark for the suspicious short message to obtain a tracking mark short message.
The keywords falling into the second weight interval represent general interest values of the keywords of the area for the user, and whether the short messages are interested by the user needs to be confirmed by the user, so that the short messages need to be seen by the user. And at the moment, normal receiving operation is also carried out on the short message, the short message is received to an inbox, and the user is reminded through ringing or vibration, but not the same, a tracking mark is configured on the short message, and the subsequent operation behavior of the user on the short message is tracked, so that whether the short message is the short message which the user is interested in is further determined.
The tracking mark may be an electronic mark invisible to the user, or a graphic mark visible to the user or other representations visible to the user so that the user can distinguish the tracking mark from other normally received messages in the message inbox.
And S34, when the weight value of the suspicious short message falls into the third weight interval, configuring a non-interest label for the suspicious short message to obtain a non-interest short message.
The keyword falling into the third weight interval represents that the interest value of the keyword in the area is very low, the user does not want to see the short message related to the keyword, the suspicious short message meeting the conditions is configured with the interest disappearing label and is determined as the uninteresting short message, and therefore the follow-up steps can execute the intercepting operation on the uninteresting short message.
As an embodiment of the present application, after performing an interception operation on the short message not of interest, the method further includes:
and tracking and acquiring processing state information of the tracking and marking short message, and adjusting the weight value of the keyword corresponding to the tracking and marking short message in the interest keyword weight list according to the processing state information.
In this embodiment, in order to determine whether the short message configured with the tracking flag is a short message of interest to the user, the processing state of the received tracking flag short message needs to be tracked continuously, and if the short message is deleted immediately after the user opens the short message, or the short message is deleted after the user opens the short message, or the short message is not deleted after a period of time elapses after the user opens the short message, the three processing states respectively indicate that the user has different interest values for the short message. Therefore, in this embodiment, the interest level of the user in the short message can be known by tracking the processing state of the user on the tracking mark short message, so that the keywords corresponding to the short message are adjusted according to the interest level of the user in the short message, and the weight value in the interest keyword list better conforms to the interest of the user. The specific adjustment rule may be set according to needs or experience, for example, the weight adjustment rule may be set as:
when the user does not click on the short message to be deleted directly, the weight of all keywords corresponding to the content of the short message is reduced by 10 percent; when the short message is deleted within 5s after the user clicks on, the weight of all keywords corresponding to the content of the short message is reduced by 5 percent; and when the user does not delete the short message after opening the short message for 5s, adding 3% to the weight of all keywords corresponding to the content of the short message.
It can be understood that effective time can be set for the tracking mark, when the effective time passes, the tracking mark on the short message of the tracking mark automatically loses efficacy, and stops tracking the processing state of the short message, and if the user deletes the short message, the user does not influence the weight value of the keyword corresponding to the short message in the interest keyword weight list.
It can be seen that, the weight values of the keywords in the interest keyword weight list in this embodiment are constantly changing, and not only can be influenced by the recent web browsing behavior, input behavior and app use behavior image of the user, but also by the operation behavior of the user on the tracking mark short message, and the short message identification method in this embodiment is based on this setting, so that the short message content that the user is not interested in by the recent short message can be well identified, and the short messages are further intercepted.
As an embodiment of the present application, the intercepting operation performed on the uninteresting short message includes:
acquiring the current state of each short message reminding function switch of the terminal equipment, and setting each short message reminding function switch of the terminal equipment to be in a closed state; deleting the uninteresting short messages or moving the uninteresting short messages to a short message garbage box; and restoring the state of each short message reminding function switch of the terminal equipment to the current state.
In this embodiment, when the interception operation is performed on the uninteresting short message, in order to make the user not perceive the arrival of the short message, the short message reminding function in the user terminal needs to be completely closed when the interception operation is performed, then the short message is received, the short message is directly deleted or moved to a short message trash bin after the short message is received, and then the short message reminding function in the user terminal is restored to the state before the short message is received, so that the uninteresting filtering interception is realized in a 'unknowingly' manner, and the user can not perceive the existence of the uninteresting short message completely.
The method comprises the steps of obtaining a short message to be identified, configuring a suspicious tag for the short message to be identified according to information of a sender of the short message to be identified to obtain a suspicious short message, extracting a keyword of the suspicious short message, matching the extracted keyword with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message, configuring a non-interest tag for the suspicious short message according to the weight value of the suspicious short message to obtain a non-interest short message, and finally performing interception operation on the non-interest short message. Therefore, the short message interception method in the embodiment of the invention can accurately identify whether the content of the short message meets the interest of the user, further intercept the short message which does not meet the interest of the user, and receive the short message which meets the interest of the user, so that the short message interception is more intelligent and accurate.
Referring to fig. 6, fig. 6 is a diagram illustrating a structure of a short message intercepting apparatus based on user interests according to an embodiment of the present application.
Referring to fig. 6, the short message intercepting apparatus 1 based on interest includes: the system comprises a first identification module 10, a weight matching module 20, a second identification module 30 and a short message intercepting module 40, wherein:
the first identification module 10 is configured to acquire a short message to be identified, and configure a suspicious tag for the short message to be identified according to sender information of the short message to be identified to obtain a suspicious short message;
the weight matching module 20 is configured to extract keywords of the suspicious short message, match the keywords with a pre-created interest keyword weight list, and obtain a weight value of the suspicious short message;
the second identification module 30 is configured to configure a non-interest tag for the suspicious short message according to the weight value to obtain a non-interest short message;
and the short message intercepting module 40 is used for executing intercepting operation on the uninteresting short messages.
As an embodiment of the present application, the first identification module 10 further includes:
the address list matching unit is used for extracting the sender information of the short message to be identified and matching the sender information with the address list information in the terminal equipment;
the interception execution unit is used for executing receiving operation on the short message to be identified when the sender information is in the address list;
and the suspicious tag configuration unit is used for configuring a suspicious tag for the short message to be identified corresponding to the sender information to obtain the suspicious short message when the sender information is not in the address list.
As an embodiment of the present application, the second identification module 30 further includes:
the weight region dividing unit is used for dividing the keywords in the interest keyword weight list into a first weight interval, a second weight interval and a third weight interval according to the sequence of the weight values from high to low;
the first weight area processing unit is used for executing receiving operation on the suspicious short message when the weight value of the suspicious short message falls into the first weight interval;
the second weight area processing unit is used for configuring a tracking mark for the suspicious short message to obtain a tracking mark short message when the weight value of the suspicious short message falls into the second weight interval;
and the third weight area processing unit is used for configuring a non-interest tag for the suspicious short message to obtain the non-interest short message when the weight value of the suspicious short message falls into the third weight interval.
Referring to fig. 7, fig. 7 is a schematic diagram of a computer device according to an embodiment of the present application.
As an embodiment of the present application, a computer device is provided, where the computer device may be a server, and an internal structure diagram of the computer device may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the readable storage medium. The database of the computer equipment is used for storing data related to the short message intercepting method based on the user interest. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by the processor, implement a method for intercepting short messages based on user interests. The readable storage media provided by the present embodiment include nonvolatile readable storage media and volatile readable storage media.
As an embodiment of the present application, there is provided a computer device including a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer readable instructions:
acquiring a short message to be identified, and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and performing interception operation on the uninteresting short messages.
One or more computer-readable storage media storing computer-readable instructions are provided as an embodiment of the present application, and the readable storage media provided by the present embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage medium has stored thereon computer readable instructions which, when executed by one or more processors, perform the steps of:
acquiring a short message to be identified, and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and performing interception operation on the uninteresting short messages.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware related to computer readable instructions, which may be stored in a non-volatile readable storage medium or a volatile readable storage medium, and when executed, the computer readable instructions may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A short message intercepting method based on user interest is characterized by comprising the following steps:
acquiring a short message to be identified, and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and performing interception operation on the uninteresting short messages.
2. The method as claimed in claim 1, wherein the configuring a suspicious tag for the short message to be recognized according to the sender information of the short message to be recognized to obtain a suspicious short message comprises:
extracting sender information of the short message to be identified, and matching the sender information with address list information in terminal equipment;
when the sender information is in the address list, receiving the short message to be identified;
and when the sender information is not in the address list, configuring a suspicious label for the short message to be identified corresponding to the sender information to obtain a suspicious short message.
3. The method as claimed in claim 1, wherein the interest keyword weight list is created by:
monitoring terminal equipment to acquire terminal use data in the terminal equipment;
extracting key words of the terminal use data through an LDA document main body model and calculating weight values corresponding to the key words;
and establishing the interest keyword weight list according to the keywords and the weight values corresponding to the keywords.
4. The method as claimed in claim 3, wherein the terminal usage data includes:
the terminal comprises a network access record of the terminal, an APP usage record on the terminal and information input through an input module on the terminal.
5. The method as claimed in claim 3, wherein the configuring the uninteresting tag for the suspicious SMS according to the weight value to obtain the uninteresting SMS comprises:
dividing keywords in the interest keyword weight list into a first weight interval, a second weight interval and a third weight interval according to the sequence of the weight values from high to low;
when the weight value of the suspicious short message falls into the first weight interval, receiving the suspicious short message;
when the weight value of the suspicious short message falls into the second weight interval, configuring a tracking mark for the suspicious short message to obtain a tracking mark short message;
and when the weight value of the suspicious short message falls into the third weight interval, configuring a non-interest tag for the suspicious short message to obtain the non-interest short message.
6. The method as claimed in claim 1, wherein the intercepting operation of the uninteresting short message comprises:
acquiring the current state of each short message reminding function switch of the terminal equipment, and setting each short message reminding function switch of the terminal equipment to be in a closed state;
deleting the uninteresting short messages or moving the uninteresting short messages to a short message garbage box;
and restoring the state of each short message reminding function switch of the terminal equipment to the current state.
7. The method as claimed in claim 5, wherein after the intercepting operation is performed on the uninteresting short message, the method further comprises:
and tracking and acquiring processing state information of the tracking and marking short message, and adjusting the weight value of the keyword corresponding to the tracking and marking short message in the interest keyword weight list according to the processing state information.
8. A short message intercepting device based on user interest, the device comprising:
the first identification module is used for acquiring a short message to be identified and configuring a suspicious label for the short message to be identified according to the sender information of the short message to be identified to obtain a suspicious short message;
the weight matching module is used for extracting keywords of the suspicious short message, and matching the keywords with a pre-established interest keyword weight list to obtain a weight value of the suspicious short message;
the second identification module is used for configuring uninteresting labels for the suspicious short messages according to the weight values to obtain uninteresting short messages;
and the short message interception module is used for executing interception operation on the uninteresting short messages.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for intercepting short messages based on user interest according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the method for intercepting short messages based on user interests according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111093693.XA CN113868410A (en) | 2021-09-17 | 2021-09-17 | Short message interception method, device, equipment and medium based on user interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111093693.XA CN113868410A (en) | 2021-09-17 | 2021-09-17 | Short message interception method, device, equipment and medium based on user interest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113868410A true CN113868410A (en) | 2021-12-31 |
Family
ID=78996462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111093693.XA Pending CN113868410A (en) | 2021-09-17 | 2021-09-17 | Short message interception method, device, equipment and medium based on user interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113868410A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117041978A (en) * | 2023-10-08 | 2023-11-10 | 北京国都互联科技有限公司 | Method for monitoring short message sending content in real time |
-
2021
- 2021-09-17 CN CN202111093693.XA patent/CN113868410A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117041978A (en) * | 2023-10-08 | 2023-11-10 | 北京国都互联科技有限公司 | Method for monitoring short message sending content in real time |
| CN117041978B (en) * | 2023-10-08 | 2023-12-29 | 北京国都互联科技有限公司 | Method for monitoring short message sending content in real time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103176982B (en) | The method and system that a kind of e-book is recommended | |
| CN108491720B (en) | Application identification method, system and related equipment | |
| CN105989144B (en) | Notification message management method, device and system and terminal equipment | |
| US20130159408A1 (en) | Action-oriented user experience based on prediction of user response actions to received data | |
| US20240146676A1 (en) | Computerized system and method for controlling electronic messages and their responses after delivery | |
| CN111726456B (en) | Data processing method and related device | |
| US11784948B2 (en) | Cognitive determination of message suitability | |
| US10033850B2 (en) | Method for real time displaying information and mobile communication terminal | |
| CN110545232A (en) | group message prompting method, group message prompting device, data processing method, data processing device, electronic equipment and storage equipment | |
| CN112868004A (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| US20150052203A1 (en) | System and method for mailing list identification and representation | |
| CN113254815A (en) | Document processing method, page processing method and equipment | |
| CN114422271B (en) | Data processing method, device, equipment and readable storage medium | |
| WO2016188334A1 (en) | Method and device for processing application access data | |
| US10217455B2 (en) | Linguistic model database for linguistic recognition, linguistic recognition device and linguistic recognition method, and linguistic recognition system | |
| CN113868410A (en) | Short message interception method, device, equipment and medium based on user interest | |
| CN114995791A (en) | API (application program interface) polymerization method and device, electronic equipment and storage medium | |
| CN115023922B (en) | Information pushing method, device, server and storage medium | |
| CN109145115B (en) | Product public opinion discovery method, device, computer equipment and storage medium | |
| CN111083705A (en) | Group-sending fraud short message detection method, device, server and storage medium | |
| CN114491093B (en) | Multimedia resource recommendation and object representation network generation method and device | |
| CN115544558A (en) | Sensitive information detection method and device, computer equipment and storage medium | |
| CN115426299A (en) | Method and device for identifying non-characteristic data, computer equipment and storage medium | |
| CN115442091A (en) | Instant messaging application behavior identification method and system based on network security | |
| CN114238585A (en) | Query method and device based on 5G message, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220916 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |