CN115208946A - Message pushing method, message pushing server and storage medium - Google Patents
Message pushing method, message pushing server and storage medium Download PDFInfo
- Publication number
- CN115208946A CN115208946A CN202210843062.3A CN202210843062A CN115208946A CN 115208946 A CN115208946 A CN 115208946A CN 202210843062 A CN202210843062 A CN 202210843062A CN 115208946 A CN115208946 A CN 115208946A
- Authority
- CN
- China
- Prior art keywords
- keyword
- suspicious
- message
- word
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a message pushing method, a message pushing server and a storage medium, which can be applied to the field of mobile interconnection or financial field, wherein the method comprises the following steps: receiving a message pushing request sent by a target mobile terminal, and for each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, calculating the matching degree of the initial keyword based on the preset word data table, screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, and for each suspicious keyword: and calculating a correlation parameter according to the word type of the suspicious keyword by using a preset misjudgment check algorithm, determining each suspicious keyword of which the correlation parameter is greater than a second preset threshold as an alternative keyword, determining a message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal. The invention improves the accuracy of message pushing.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a message pushing method, a message pushing server, and a storage medium.
Background
Along with popularization of terminal applications, message push services based on application information and service promotion are increasingly frequent due to requirements for improving user experience and business expansion. Most message push methods push the whole amount of messages through a message server. However, these full-size pushed messages have a low degree of matching with the user's needs, resulting in a reduction in the accuracy of message pushing. Therefore, in the prior art, a machine learning model is adopted, and the accuracy of message pushing is improved by a method of filtering a message to be pushed by acquiring user browsing data. However, because the machine learning model has strong generalization, when filtering, the machine learning model may filter out some messages matching with the user's requirements by mistake, so that the accuracy of message pushing is reduced.
Disclosure of Invention
The embodiment of the invention aims to provide a message pushing method, a message pushing server and a storage medium, so as to achieve the purpose of improving the accuracy of message pushing. The specific technical scheme is as follows:
a message pushing method, the message pushing method comprising:
receiving a message pushing request sent by a target mobile terminal, wherein the message pushing request comprises an initial key phrase.
For each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table.
And screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group comprises a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold value.
For each suspicious keyword: and calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm.
And determining each suspicious keyword of which the associated parameter is greater than a second preset threshold as an alternative keyword, wherein the first preset threshold is different from the second preset threshold.
And determining a message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal.
Optionally, the calculating, by using a preset false positive check algorithm, the association parameter of the suspicious keyword according to the word type of the suspicious keyword includes:
and determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword.
And performing product operation on the word frequency and the inverse document frequency by using the preset misjudgment check algorithm, and determining an operation result as the associated parameter of the suspicious keyword.
Optionally, the determining, according to the term type of the suspicious keyword, the term frequency and the inverse document frequency of the suspicious keyword includes:
determining a first numerical value according to the word type of the suspicious keyword, wherein the first numerical value is the number of the suspicious keywords which are consistent with the word type of the suspicious keyword in the suspicious keyword group.
And determining the number of times of the suspicious keyword appearing in the first numerical value as a second numerical value.
And dividing the second numerical value by the quotient of the first numerical value by using the preset misjudgment check algorithm to determine the word frequency of the suspicious keyword.
Optionally, the determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword further includes:
and determining the total number of the suspicious keywords in the suspicious keyword group as a third numerical value.
By the formula:
IDF t ＝lg(D n /N t )，
calculating the inverse document frequency IDF of the suspicious keyword t t Wherein, the D is n Is the third value, thenN is described t Is the second value, and n is the number of the suspicious keywords in the suspicious keyword group.
Optionally, the calculating the matching degree of the initial keyword based on the preset word data table includes:
and inputting the initial keyword and each word data in the preset word data table into a preset character string matching algorithm to obtain the matching degree output by the preset character string matching algorithm, wherein the matching degree represents the association degree of the initial keyword and each word data in the preset word data table.
Optionally, the message pushing request further includes terminal usage data of the mobile terminal, and the pushing the message to be pushed to the target mobile terminal includes:
and reading the use time period in the terminal use data.
And judging whether the pushing time of the message to be pushed is in the using time period, if so, pushing the message to be pushed to the target mobile terminal.
A message push server, the message push server comprising:
the data receiving module is used for receiving a message pushing request sent by a target mobile terminal, wherein the message pushing request comprises an initial key phrase.
A matching degree calculation module, configured to, for each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table.
And the first data screening module is used for screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group comprises a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold value.
The misjudgment inspection module is used for carrying out the following steps on each suspicious keyword: and calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm.
And the second data screening module is used for determining each suspicious keyword of which the associated parameter is greater than a second preset threshold as a candidate keyword, wherein the first preset threshold is different from the second preset threshold.
And the message pushing module is used for determining a message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal.
Optionally, the misjudgment checking module is configured to:
and determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword.
And performing product operation on the word frequency and the inverse document frequency by using the preset misjudgment check algorithm, and determining an operation result as the associated parameter of the suspicious keyword.
Optionally, when determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword, the misjudgment checking module is configured to:
determining a first numerical value according to the word type of the suspicious keyword, wherein the first numerical value is the number of the suspicious keywords which are consistent with the word type of the suspicious keyword in the suspicious keyword group.
And determining the number of times of the suspicious keyword appearing in the first numerical value as a second numerical value.
And dividing the second numerical value by the quotient of the first numerical value by using the preset misjudgment check algorithm to determine the word frequency of the suspicious keyword.
Optionally, when determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword, the misjudgment checking module is further configured to:
and determining the total number of the suspicious keywords in the suspicious keyword group as a third numerical value.
By the formula:
IDF t ＝lg(D n /N t )，
calculating the inverse document frequency IDF of the suspicious keyword t t Wherein, the D is n Is said third value, said N t Is the second value, and n is the number of the suspicious keywords in the suspicious keyword group.
Optionally, the matching degree calculating module is configured to:
and inputting the initial keyword and each word data in the preset word data table into a preset character string matching algorithm to obtain the matching degree output by the preset character string matching algorithm, wherein the matching degree represents the association degree of the initial keyword and each word data in the preset word data table.
Optionally, the message pushing module is configured to:
and reading the use time period in the terminal use data.
And judging whether the pushing time of the message to be pushed is in the using time period, if so, pushing the message to be pushed to the target mobile terminal.
A message push server, the message push server comprising:
a processor;
a memory for storing the processor-executable instructions.
Wherein the processor is configured to execute the instructions to implement the message push method as described in any of the above.
A computer readable storage medium, in which instructions, when executed by a processor of a message push server, enable the message push server to perform a message push method as in any one of the above.
According to the message pushing method, the message pushing server and the storage medium provided by the embodiment of the invention, the matching degree of the initial keyword is calculated through the preset matching degree calculation model, so that the secondary verification of the word type of the initial keyword can be realized. Thereby improving the accuracy of determining the word type of the initial keyword. And then the accuracy of determining the message to be pushed according to the initial keyword is improved. Meanwhile, a preset misjudgment checking algorithm is introduced, and the correlation parameters are calculated, so that the correlation between the suspicious keywords and the word types is checked. Compared with the prior art, the method and the device avoid the risk of mistakenly filtering the keywords due to the generalization of the machine learning model. The method and the device improve the determination precision of the word types of the keywords, and further improve the final message pushing accuracy. Therefore, the invention achieves the aim of improving the message pushing accuracy.
Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a message pushing method according to an embodiment of the present invention;
fig. 2 is a block diagram of a message push server according to an alternative embodiment of the present invention;
fig. 3 is a block diagram of a message push server according to another alternative embodiment of the present invention.
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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the message pushing method, the message pushing server and the storage medium provided by the present invention can be used in the mobile internet field or the financial field. The foregoing is merely an example, and does not limit the application fields of the message pushing method, the message pushing server, and the storage medium provided by the present invention.
An embodiment of the present invention provides a message pushing method, and as shown in fig. 1, the message pushing method includes:
s101, receiving a message pushing request sent by a target mobile terminal, wherein the message pushing request comprises an initial key phrase.
The message push request may be sent by an application plugin deployed in the target mobile terminal.
Optionally, in an optional embodiment of the present invention, the initial keyword group may be a data group composed of keywords that characterize the user subscription requirement or intention. The initial keyword group may include various types of initial keywords such as a user's occupation, a subscribed public name, browser search data, browsing web page titles, browser tab content, and the like. The invention filters the pushed message based on the initial keyword group, and can improve the accuracy of message pushing.
S102, for each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table.
Optionally, in an optional embodiment of the present invention, the word type of the initial keyword may be determined according to a type tag of the initial keyword. For example: and judging whether the type label of the initial keyword is matched with data in a preset type data table or not, if so, determining the word type matched with the type label in the preset type data table as the word type of the initial keyword.
Optionally, in another optional embodiment of the present invention, the preset word data table may be determined according to historical statistical data, and includes a data table of words with a plurality of consistent word types. For example, if the word type matched with the current preset word data table is set as "finance", the words in the table may be words such as "crude oil price", "gold price", and the like.
Optionally, in another optional embodiment of the present invention, the matching degree of the initial keyword is calculated through a preset matching degree calculation model, so that secondary verification of the term type of the initial keyword can be realized. Thereby improving the accuracy of determining the word type of the initial keyword. And then the accuracy of determining the message to be pushed according to the initial keyword is improved.
S103, screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group comprises a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold value.
It should be noted that, in an actual application scenario, the first preset threshold may be determined according to historical data and the calculation accuracy of the preset matching degree calculation model, and the specific numerical value and the determination manner of the first preset threshold are not limited and described in detail in the present invention.
S104, for each suspicious keyword: and calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm.
The preset erroneous judgment checking algorithm may be a text mining algorithm constructed based on a term Frequency-Inverse Document Frequency (TF-IDF) technology.
The association parameter may be a parameter for characterizing a degree of association between the suspicious keyword and the word type.
It should be noted that the technical idea of TF-IDF is that the association between a word in a corpus and the corpus increases in proportion to the number of times the word appears in the corpus, and decreases in inverse proportion to the frequency of the word appearing in the corpus. Therefore, in the step S103 shown in fig. 1, the matching degree fluctuates along with the number of words in the preset word data table, for example, if the number of words in the table is large, the probability of matching the initial keyword with the words in the data table is large. If the number of the words in the table is small, the matching probability of the initial keyword and the words in the data table is small. Therefore, there is a certain probability of misjudgment for the suspicious keyword screened in step S103 shown in fig. 1. The association parameters are calculated by introducing the preset misjudgment checking algorithm, so that the association between the suspicious keywords and the word types is checked. Compared with the prior art, the method and the device avoid the risk of mistakenly filtering the keywords due to the generalization of the machine learning model. The method and the device improve the determination precision of the word types of the keywords, and further improve the final message pushing accuracy.
And S105, determining each suspicious keyword of which the associated parameter is greater than a second preset threshold as an alternative keyword, wherein the first preset threshold is different from the second preset threshold.
Optionally, in an alternative embodiment of the present invention, the word filtering performed by the preset threshold in step S103 and step S105 shown in fig. 1 may be implemented in various manners, for example, by using random sample Consensus (RANSAC) algorithm.
And S106, determining the message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal.
Optionally, in an optional embodiment of the present invention, there may be multiple implementations of step S106 shown in fig. 1, for example:
and extracting the type identifier of the word type of each candidate keyword and each keyword in the keyword group. And determining the push message corresponding to each type identifier in a preset push message library as the message to be pushed. And then calling the corresponding communication interface according to the identifier of the target mobile terminal. And sending the message to be pushed to the target mobile terminal through the communication interface.
The matching degree of the initial keywords is calculated through a preset matching degree calculation model, and secondary verification of the word types of the initial keywords can be achieved. Thereby improving the accuracy of determining the word type of the initial keyword. And further, the accuracy of determining the message to be pushed according to the initial keyword is improved. Meanwhile, a preset misjudgment checking algorithm is introduced, and the association parameters are calculated, so that the association between the suspicious keywords and the word types is checked. Compared with the prior art, the method and the device avoid the risk of mistakenly filtering the keywords due to the generalization of the machine learning model. The method and the device improve the determination precision of the word types of the keywords, and further improve the final message pushing accuracy. Therefore, the invention achieves the aim of improving the message pushing accuracy.
Optionally, calculating the association parameters of the suspicious keyword according to the word type of the suspicious keyword by using a preset misjudgment check algorithm, including:
and determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword.
And performing product operation on the word frequency and the inverse document frequency by using a preset misjudgment checking algorithm, and determining an operation result as an associated parameter of the suspicious keyword.
Optionally, determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword includes:
and determining a first numerical value according to the word type of the suspicious keyword, wherein the first numerical value is the number of the suspicious keywords which are consistent with the word type of the suspicious keyword in the suspicious keyword group.
And determining the number of times of the suspicious keyword appearing in the first numerical value as a second numerical value.
And dividing the second numerical value by the quotient of the first numerical value by using a preset misjudgment check algorithm to determine the word frequency of the suspicious keyword.
Optionally, the determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword further includes:
and determining the total number of the suspicious keywords in the suspicious keyword group as a third numerical value.
By the formula:
IDF t ＝lg(D n /N t )，
calculating the inverse document frequency IDF of the suspicious keyword t t Wherein D is n Is a third value, N t Is the second value, and n is the number of suspicious keywords in the suspicious keyword set.
It should be noted that, in an actual application scenario, there are various embodiments of determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword, and an exemplary embodiment herein provides:
the current suspicious keyword group is set to include 10 suspicious keywords. These keywords total 3 word types. One of the word types is "finance". There are 3 keywords matching the word type, which are "oil price", "grain price" and "oil price", respectively. It should be noted that, since the source of the initial keyword may be various, the "oil price" may be two keywords respectively extracted from the public name subscribed by the user and the browser search data.
Then, for the keyword "grain price", since there are 3 suspicious keywords in the current suspicious keyword group that are consistent with the word type of "grain price", the first value is 3. Since the "grain price" occurs only 1 time, the second value is 1. Then by the formula:
TF＝N t /N n ，
the Term Frequency (TF) for "grain price" is 1/3.
And since the current suspicious keyword group includes 10 suspicious keywords, the third value is 10. The pseudo document frequency of "grain price" obtained by the above formula is 1.
Optionally, calculating the matching degree of the initial keyword based on a preset word data table includes:
and inputting the initial keyword and each word data in the preset word data table into a preset character string matching algorithm to obtain the matching degree output by the preset character string matching algorithm, wherein the matching degree represents the correlation degree of the initial keyword and each word data in the preset word data table.
It should be noted that, in an actual application scenario, the specific type of The preset string matching Algorithm may be multiple, for example, the Knuth-Morris-Pratt Algorithm (KMP) Algorithm. The invention does not limit and describe the specific construction process of the algorithm too much.
Optionally, the message pushing request further includes terminal usage data of the mobile terminal, and the pushing of the message to be pushed to the target mobile terminal includes:
and reading the use period in the terminal use data.
And judging whether the pushing time of the message to be pushed is in the use time period, if so, pushing the message to be pushed to the target mobile terminal.
It should be noted that the terminal usage data may include a browser usage period, terminal location data, and the like, in addition to the usage period. The invention is not limited to a particular type of terminal usage data.
Optionally, in an optional embodiment of the present invention, the type in the message to be pushed belongs to personal privacy data of the user. Therefore, in order to avoid the problem of privacy disclosure caused by stealing of the message to be pushed, the pushing of the message to be pushed can be performed through the blockchain. The specific implementation mode can be as follows:
compressing the message to be pushed into a data block, and performing uplink operation on the data block. And sets the corresponding sending trigger condition. And when the current moment meets the triggering requirement of the triggering condition, the block chain node point stored with the data block sends the data block to an application plug-in deployed in the target mobile terminal through the block chain.
Correspondingly to the above method embodiment, the present invention further provides a message push server, as shown in fig. 2, where the message push server includes:
the data receiving module 201 is configured to receive a message pushing request sent by a target mobile terminal, where the message pushing request includes an initial keyword group.
A matching degree calculation module 202, configured to, for each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table.
The first data screening module 203 screens each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group includes a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold.
A misjudgment checking module 204, configured to, for each suspicious keyword: and calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm.
The second data screening module 205 is configured to determine each suspicious keyword of which the associated parameter is greater than a second preset threshold as an alternative keyword, where the first preset threshold is different from the second preset threshold.
And the message pushing module 206 is configured to determine a message to be pushed according to the keyword group and each alternative keyword, and push the message to be pushed to the target mobile terminal.
Optionally, the misjudgment checking module 204 is configured to:
and determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword.
And performing product operation on the word frequency and the inverse document frequency by using a preset misjudgment checking algorithm, and determining an operation result as an associated parameter of the suspicious keyword.
Optionally, when determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword, the misjudgment checking module 204 is configured to:
and determining a first numerical value according to the word type of the suspicious keyword, wherein the first numerical value is the number of the suspicious keywords which are consistent with the word type of the suspicious keyword in the suspicious keyword group.
And determining the number of times of the suspicious keyword appearing in the first numerical value as a second numerical value.
And dividing the second numerical value by the quotient of the first numerical value by using a preset misjudgment check algorithm to determine the word frequency of the suspicious keyword.
Optionally, when determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword, the misjudgment checking module 204 is further configured to:
and determining the total number of the suspicious keywords in the suspicious keyword group as a third numerical value.
By the formula:
IDF t ＝lg(D n /N t )，
calculating the inverse document frequency IDF of the suspicious keyword t t Wherein D is n Is a third value, N t Is the second value, and n is the number of suspicious keywords in the suspicious keyword set.
Optionally, the matching degree calculating module 202 is configured to:
and inputting the initial keyword and each word data in the preset word data table into a preset character string matching algorithm to obtain the matching degree output by the preset character string matching algorithm, wherein the matching degree represents the correlation degree of the initial keyword and each word data in the preset word data table.
Optionally, the message pushing module 206 is configured to:
the usage period in the terminal usage data is read.
And judging whether the pushing time of the message to be pushed is in the use time period, if so, pushing the message to be pushed to the target mobile terminal.
An embodiment of the present invention further provides a message push server, as shown in fig. 3, where the message push server includes:
a processor 301;
a memory 302 for storing instructions executable by the processor 301.
Wherein the processor 301 is configured to execute instructions to implement the message push method as described in any of the above.
Embodiments of the present invention further provide a computer-readable storage medium, where instructions of the computer-readable storage medium, when executed by a processor of a message push server, enable the message push server to execute the message push method as described in any one of the above.
The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
Claims (10)
1. A message pushing method is characterized by comprising the following steps:
receiving a message pushing request sent by a target mobile terminal, wherein the message pushing request comprises an initial key phrase;
for each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table;
screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group comprises a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold;
for each suspicious keyword: calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm;
determining each suspicious keyword of which the associated parameter is greater than a second preset threshold as an alternative keyword, wherein the first preset threshold is different from the second preset threshold;
and determining a message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal.
2. The message pushing method according to claim 1, wherein the calculating, by using a predetermined false positive check algorithm, the association parameter of the suspicious keyword according to the word type of the suspicious keyword includes:
determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword;
and performing product operation on the word frequency and the inverse document frequency by using the preset misjudgment check algorithm, and determining an operation result as the associated parameter of the suspicious keyword.
3. The message pushing method according to claim 2, wherein the determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword comprises:
determining a first numerical value according to the word type of the suspicious keyword, wherein the first numerical value is the number of the suspicious keywords which are consistent with the word type of the suspicious keyword in the suspicious keyword group;
determining the number of times of the suspicious keyword appearing in the first numerical value as a second numerical value;
and dividing the second numerical value by the quotient of the first numerical value by using the preset misjudgment check algorithm to determine the word frequency of the suspicious keyword.
4. The message pushing method according to claim 3, further comprising:
determining the total number of the suspicious keywords in the suspicious keyword group as a third numerical value;
by the formula:
IDF t ＝lg(D n /N t )，
calculating the inverse document frequency IDF of the suspicious keyword t t Wherein, the D is n Is said third value, said N t Is the second value, and n is the number of the suspicious keywords in the suspicious keyword group.
5. The message pushing method according to claim 1, wherein the calculating the matching degree of the initial keyword based on the preset word data table comprises:
and inputting the initial keyword and each word data in the preset word data table into a preset character string matching algorithm to obtain the matching degree output by the preset character string matching algorithm, wherein the matching degree represents the association degree of the initial keyword and each word data in the preset word data table.
6. The message pushing method according to claim 1, wherein the message pushing request further includes terminal usage data of the mobile terminal, and the pushing the message to be pushed to the target mobile terminal includes:
reading the use time period in the terminal use data;
and judging whether the pushing time of the message to be pushed is in the use time period, if so, pushing the message to be pushed to the target mobile terminal.
7. A message push server, characterized in that the message push server comprises:
the data receiving module is used for receiving a message pushing request sent by a target mobile terminal, wherein the message pushing request comprises an initial key phrase;
a matching degree calculation module, configured to perform, on each initial keyword in the initial keyword group: determining the word type of the initial keyword, calling a preset word data table corresponding to the word type, and calculating the matching degree of the initial keyword based on the preset word data table;
the first data screening module is used for screening each initial keyword based on the matching degree to obtain a keyword group and a suspicious keyword group, wherein the suspicious keyword group comprises a plurality of suspicious keywords, and the matching degree of the suspicious keywords is smaller than a first preset threshold value;
the misjudgment inspection module is used for carrying out the following steps on each suspicious keyword: calculating the associated parameters of the suspicious keywords according to the word types of the suspicious keywords by using a preset misjudgment checking algorithm;
the second data screening module is used for determining each suspicious keyword of which the associated parameter is greater than a second preset threshold as an alternative keyword, wherein the first preset threshold is different from the second preset threshold;
and the message pushing module is used for determining a message to be pushed according to the keyword group and each alternative keyword, and pushing the message to be pushed to the target mobile terminal.
8. The message push server according to claim 7, wherein the misjudgment checking module is configured to:
determining the word frequency and the inverse document frequency of the suspicious keyword according to the word type of the suspicious keyword;
and performing product operation on the word frequency and the inverse document frequency by using the preset misjudgment check algorithm, and determining an operation result as the associated parameter of the suspicious keyword.
9. A message push server, characterized in that the message push server comprises:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the message pushing method of any one of claims 1 to 6.
10. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of a message push server, enable the message push server to perform the message push method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210843062.3A CN115208946B (en) | 2022-07-18 | 2022-07-18 | Message pushing method, message pushing server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210843062.3A CN115208946B (en) | 2022-07-18 | 2022-07-18 | Message pushing method, message pushing server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115208946A true CN115208946A (en) | 2022-10-18 |
| CN115208946B CN115208946B (en) | 2024-03-01 |
Family
ID=83581685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210843062.3A Active CN115208946B (en) | 2022-07-18 | 2022-07-18 | Message pushing method, message pushing server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115208946B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| CN108616444A (en) * | 2018-03-30 | 2018-10-02 | 平安科技（深圳）有限公司 | A kind of PUSH message processing method, computer readable storage medium and terminal device |
| CN109325182A (en) * | 2018-10-12 | 2019-02-12 | 平安科技（深圳）有限公司 | Dialogue-based information-pushing method, device, computer equipment and storage medium |
| US20200081977A1 (en) * | 2017-10-20 | 2020-03-12 | Tencent Technology (Shenzhen) Company Limited | Keyword extraction method and apparatus, storage medium, and electronic apparatus |
-
2022
- 2022-07-18 CN CN202210843062.3A patent/CN115208946B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868377A (en) * | 2016-03-31 | 2016-08-17 | 北京奇艺世纪科技有限公司 | Method and device for pushing information |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107220386A (en) * | 2017-06-29 | 2017-09-29 | 北京百度网讯科技有限公司 | Information-pushing method and device |
| US20200081977A1 (en) * | 2017-10-20 | 2020-03-12 | Tencent Technology (Shenzhen) Company Limited | Keyword extraction method and apparatus, storage medium, and electronic apparatus |
| CN108616444A (en) * | 2018-03-30 | 2018-10-02 | 平安科技（深圳）有限公司 | A kind of PUSH message processing method, computer readable storage medium and terminal device |
| CN109325182A (en) * | 2018-10-12 | 2019-02-12 | 平安科技（深圳）有限公司 | Dialogue-based information-pushing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115208946B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11973799B2 (en) | Domain name processing systems and methods | |
| CN108319630B (en) | Information processing method, information processing device, storage medium and computer equipment | |
| US11455301B1 (en) | Method and system for identifying entities | |
| CN110457302B (en) | Intelligent structured data cleaning method | |
| CN103546446B (en) | Phishing website detection method, device and terminal | |
| CN108319628B (en) | User interest determination method and device | |
| CN111224923B (en) | Detection method, device and system for counterfeit websites | |
| CN110738562A (en) | Method, device and equipment for generating risk reminding information | |
| JP2015130136A (en) | Information processing system, information processing apparatus, control method of the same, and control program | |
| CN110443291B (en) | Model training method, device and equipment | |
| CN110020205B (en) | Method and system for screening data information | |
| CN115208946B (en) | Message pushing method, message pushing server and storage medium | |
| US20160285905A1 (en) | System and method for detecting mobile cyber incident | |
| CN111949916B (en) | Webpage analysis method, device, equipment and storage medium | |
| CN114661859A (en) | Sensitive keyword retrieval method, device, medium and product based on system index | |
| CN113674083A (en) | Internet financial platform credit risk monitoring method, device and computer system | |
| CN113254800A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN105574023A (en) | Information filtering method and apparatus | |
| US20180174019A1 (en) | Artificial intelligence analysis service | |
| CN114500261B (en) | Network asset identification method and device, electronic equipment and storage medium | |
| CN113609391B (en) | Event recognition method and device, electronic equipment, medium and program | |
| CN114143286B (en) | Method and device for positioning target object and electronic equipment | |
| WO2024089859A1 (en) | Collection device, collection method, and collection program | |
| CN107103033B (en) | Preference prediction method and device for cold-start user | |
| CN114385643A (en) | Data storage method and device, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |