CN109636487B - Advertising push method, server, computer equipment and storage medium - Google Patents
Advertising push method, server, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109636487B CN109636487B CN201910032512.9A CN201910032512A CN109636487B CN 109636487 B CN109636487 B CN 109636487B CN 201910032512 A CN201910032512 A CN 201910032512A CN 109636487 B CN109636487 B CN 109636487B
- Authority
- CN
- China
- Prior art keywords
- user
- advertisement message
- interest
- advertisement
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides an advertisement pushing method, which comprises the following steps: pushing advertisement messages with labels to a first user terminal, acquiring a plurality of behaviors of watching the advertisement messages of the first user with first label combinations, calculating the interested degree of the advertisement messages of the first user, recombining the first label combinations to generate second label combinations, pushing the advertisement messages to a second user terminal of a second user with the second label combinations, acquiring the behaviors of watching the advertisement messages of the second user, calculating the interested degree of the advertisement messages of the second user, comparing the interested degree of the advertisement messages of the second user with the first label combinations, and selecting the users with the label combinations with high interested degree to push the advertisement. The advertisement pushing method provided by the embodiment of the invention can more accurately push the advertisement to interested users, improves the efficiency of advertisement pushing and brings higher economic benefit for advertisers.
Description
Technical Field
The embodiment of the invention relates to the field of big data, in particular to an advertisement pushing method, a server and a computer readable storage medium.
Background
With the development of internet and mobile internet technologies, more and more users use mobile terminals to view information, and meanwhile, advertisements of various industries are also accompanied, advertisements which are not interesting to users often appear on the mobile terminals of the users, so that the user experience is reduced, and meanwhile, the advertising benefits are reduced.
The existing differential evolution algorithm can enable the population to continuously evolve, keep good individuals, eliminate bad individuals and guide the optimal solution approximation of search terms. With the maturation of differential evolution algorithm technology, the application range of the differential evolution algorithm technology is wider and wider. Therefore, the invention aims to solve the problems of pushing the classified advertisements to corresponding users according to categories by utilizing a differential evolution algorithm, and further improving the pushing accuracy of the advertisements so as to improve the experience of the users and the economic benefit of advertisers.
Disclosure of Invention
In view of the foregoing, it is necessary to provide an advertisement pushing method, a server, a computer device and a computer readable storage medium, which can more accurately push advertisements to interested users, improve the efficiency of advertisement pushing, and bring higher economic benefits to advertisers.
In order to achieve the above object, an embodiment of the present invention provides an advertisement pushing method, including:
pushing the advertisement message with the tag to the first user terminal;
acquiring first behaviors of a plurality of first users with first tag combinations for watching the advertisement message through the first user terminal, wherein the first behaviors at least comprise clicking or watching;
calculating a first interest degree of the advertisement message by the first user according to the first behavior and a calculation formula of the interest degree;
recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations;
pushing the advertisement message to a second user terminal of a second user with the second tag combination;
acquiring a second behavior of the second user for watching the advertisement message through the second user terminal, wherein the second behavior at least comprises clicking or watching;
calculating a second interest degree of the advertisement message by the second user according to the second behavior and the interest degree calculation formula;
comparing the first degree of interest with the second degree of interest; and
And when the first interest degree is lower than the second interest degree, eliminating the first label combination and reserving the second label combination so as to screen out the second label combination and push the advertisement to the second user.
Further, before the step of calculating the first interest level of the advertisement message by the first user according to the first behavior and the calculation formula of the interest level, the method further includes:
acquiring a first historical click record of the first user; and
And counting a first frequency of clicking the advertisement message by the first user and a first watching duration of watching the advertisement message according to the first historical clicking record.
Further, the calculation formula is:wherein M is a constant.
Further, the step of calculating the second interest level of the advertisement message by the second user according to the second behavior and the calculation formula of the interest level further includes:
acquiring a second historical click record of the second user; and
And counting a second frequency of clicking the advertisement message by the second user and a second watching duration of watching the advertisement message according to the second historical clicking record.
Further, the step of recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations further comprises:
recombining the first tag combinations to produce third tag combinations; and
And screening the second label combination with high interest degree possibility on the advertisement message from the third label combination according to the first interest degree.
To achieve the above object, an embodiment of the present invention further provides a server, including:
the pushing module is used for pushing the advertisement message with the tag to the first user terminal;
the acquisition module is used for acquiring first behaviors of a plurality of first users with first tag combinations for watching the advertisement message through the first user terminal, wherein the first behaviors at least comprise clicking or watching;
the computing module is used for computing the first interest degree of the first user on the advertisement message according to the first behavior and the interest degree computing formula;
a combining module for recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations;
the pushing module is further configured to push the advertisement message to a second user terminal of a second user with the second tag combination;
the obtaining module is further configured to obtain, through the second user terminal, a second behavior of the second user for watching the advertisement message, where the second behavior at least includes clicking or watching;
the computing module is further configured to compute a second interest level of the advertisement message by the second user according to the second behavior and the computation formula of the interest level;
a comparison module for comparing the first degree of interest with the second degree of interest; and
And the screening module is used for eliminating the first label combination and reserving the second label combination when the first interest degree is lower than the second interest degree so as to screen the label combination and push the advertisements to the second user.
Further, the obtaining module is further configured to obtain a first historical click record of the first user, and count a first frequency of clicking the advertisement message by the first user and a first viewing duration of viewing the advertisement message according to the first historical click record.
Further, the calculation formula is:wherein M is a constant.
Further, the obtaining module is further configured to obtain a second history click record of the second user, and count a second frequency of clicking the advertisement message by the second user and a second viewing duration of viewing the advertisement message according to the second history click record.
Further, the combination module is further configured to recombine the first tag combinations to generate third tag combinations, and screen the second tag combinations with high likelihood of interest in the advertisement message from the third tag combinations according to the first interest degree.
To achieve the above object, embodiments of the present invention further provide a computer device, a memory of the computer device, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the advertisement pushing method as described above.
To achieve the above object, an embodiment of the present invention also provides a computer-readable storage medium having stored therein a computer program executable by at least one processor to cause the at least one processor to perform the steps of the advertisement pushing method as described above.
According to the advertisement pushing method, the server, the computer equipment and the computer readable storage medium, the advertisement can be more accurately pushed to interested users by optimizing the label combination of the users by utilizing the differential evolution algorithm, the advertisement pushing efficiency is improved, and meanwhile, higher economic benefits are brought to advertisers.
Drawings
FIG. 1 is a flowchart illustrating a method for pushing advertisements according to an embodiment of the present invention.
Fig. 2 is a hardware architecture diagram of a server according to a second embodiment of the invention.
FIG. 3 is a block diagram illustrating a third embodiment of an advertisement delivery system according to the present invention.
Reference numerals:
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
Example 1
Referring to fig. 1, a flowchart illustrating steps of an advertisement pushing method according to a first embodiment of the present invention is shown. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. Note that, in this embodiment, the server 2 is described as an execution main body by way of example. The method comprises the following steps:
step S100, pushing the advertisement message with the tag to the first user terminal.
Step S102, a plurality of first behaviors of watching the advertisement message, which are respectively provided with a first label combination, are obtained through the first user terminal, wherein the first behaviors at least comprise clicking or watching.
Specifically, the server 2 is preset with advertisement messages with various tag types, and the advertisement messages are provided with different tag types according to different types, for example: insurance, food, sports, make-up, and wear. Meanwhile, the server 2 is further preset with a user tag database, where the user tag database is used to store the tag types described by the user, for example: "female" loves naughty precious, "" housewives "insurance," "teenagers" basketball, "" etc.
In a preferred embodiment, when there is an advertisement message of an insurance class to be recommended to a user, a user of a tag combination of "" female "" loving baby ', "" housewife "" insurance', "teenager" "basketball" "is preset in the server 2, at this time, the server 2 pushes the advertisement message of the insurance class to the user of the tag combination of" "female" "loving baby '," "housewife" "insurance'," teenager "" basketball "," etc., and then the server 2 obtains the behaviors of clicking or viewing the advertisement message of the insurance class by the user terminal.
Step S104, according to the first behavior and the calculation formula of the interest degree, calculating the first interest degree of the advertisement message by the first user.
In a preferred embodiment, a first degree of interest of a first user in the advertisement message is calculated by obtaining a first frequency at which the first user clicks on the advertisement message and a first viewing duration for viewing the advertisement message. The higher the frequency of clicking on the advertisement message or the longer the first viewing duration of viewing the advertisement message by the first user, the higher the first user's first level of interest in the advertisement message. The first frequency of acquiring the advertisement information clicked by the first user may be the number of times the first user clicks the advertisement information according to the acquired first historical click record of the first user, or may be the ratio of the number of times the first user clicks the advertisement information to the number of times the server 2 pushes the advertisement information. Wherein, the calculation formula of the interest degree is as follows:wherein, M is a constant, and correspondingly, the calculation formula of the first interest degree is:
Step S106, the first label combination is recombined by utilizing a differential evolution algorithm to generate a second label combination.
In a preferred embodiment, if the server 2 is pre-configured with the users of the tag combinations of "female" "loving precious metal" ","' housewife "" insurance "", and "" teenager "" basketball "", are recombined to generate 2 by using the differential evolution algorithm 6 -1 tag combination (tag combination with null removed), for example: after recombination, the composition is formed into "" female "" housewife "", "" female "" insurance "", "" female "" teenager "", "" female "" basketball "", "" vain "" housewife "", "" vain "" insurance "", "" vain "" teenager "", and the composition is used for preventing and treating the skin and the skin. The third label combination of ' Ainaobao ' basketball ', ' housewife ' teenager ', ' housewife ' basketball ', ' insurance ' teenager ', ' insurance ' basketball ', ' women ' housewife ' basketball ', ' Ainaubao ' housewife ' insurance ', and the like. Then, the server 2 screens out the "loving" and "insurance" young "tag combinations, that is, the second tag combination, with" ", according to the degree of interest of the user of the" loving "and" housewife "," insurance "," and "basketball", "tag combinations of the" loving "and" young "," wherein the user of the "loving" and "insurance", "household", "and" housewife "," insurance "," tag combinations of the "loving" and "housewife", that is, the second tag combination, from the third tag combination.The users who love the combination of the "housewife," "insurance," "teenager," "women," "housewife," and the "love panobao" housewife, "" insurance, "" labels are the second users. It should be noted that the first user and the second user may be the same user group, and only the label combination given by the first user and the second user is different, so that the satisfaction degree of the labels given by the user group to the user group is different.
Step S108, pushing the advertisement message to a second user terminal of the second user with the second label combination.
In a preferred embodiment, when a new user of the tag combination (i.e. a second user of the second tag combination) is generated, the server 2 pushes advertisement messages of the insurance class to a second user terminal of the second user to count a second interest level of the advertisement messages of the insurance class for the second user.
Step S110, obtaining, by the second user terminal, a second behavior of the second user to watch the advertisement message, where the second behavior includes at least clicking or watching.
Step S112, calculating a second interest level of the advertisement message by the second user according to the second behavior and the calculation formula of the interest level.
In a preferred embodiment, a second user's second level of interest in the advertisement message is calculated by obtaining a second frequency at which the second user clicks on the advertisement message and a second viewing duration for viewing the advertisement message. The higher the frequency of clicking on the advertisement message or the longer the second viewing duration of viewing the advertisement message by the second user, the higher the second user's second level of interest in the advertisement message. The second frequency of obtaining the advertisement information clicked by the second user may be the number of times the second user clicks the advertisement information according to the obtained second historical click record of the second user, or may be the ratio of the number of times the second user clicks the advertisement information to the number of times the server 2 pushes the advertisement information. Wherein, the calculation formula of the interest degree is that：Wherein, M is a constant, and correspondingly, the calculation formula of the second interest degree is:
Step S114, comparing the first degree of interest with the second degree of interest.
And step S116, when the first interest degree is lower than the second interest degree, eliminating the first label combination and reserving the second label combination so as to screen out the second label combination and push advertisements to the second user.
In another preferred embodiment, if the selected tag combination users have a degree of interest in the advertisement message lower than a preset value, the newly generated tag combination users are recombined to generate new tag combination users, and the degree of interest in the advertisement message by the new tag combination users is calculated respectively.
It should be noted that, in the embodiment of the present invention, the first tag combination is recombined by using the differential evolution algorithm, and only different tags are regarded as vectors in a certain sense, by freely combining the tags, for example, there are 1000 original tags, and in the combination, by giving an original tag 0 or 1, whether there are the original tags in the combination is represented, and in this way, 2 total tags are obtained 1000 And (3) selecting a combination mode, and then screening out a label combination with high possibility of preset data so as to perform further screening and further generate a new label combination.
According to the embodiment of the invention, the label combination of the user is optimized by utilizing the differential evolution algorithm, so that the advertisement can be more accurately pushed to the interested user, the advertisement pushing efficiency is improved, and meanwhile, higher economic benefits are brought to advertisers.
Example two
Referring to fig. 2, a hardware architecture diagram of a server according to a second embodiment of the invention is shown. The server 2 includes, but is not limited to, memory 21, processing 22, and network interface 23, which are communicatively coupled to each other via a system bus, with fig. 2 only showing the server 2 having components 21-23, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may alternatively be implemented.
The memory 21 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 21 may be an internal storage unit of the server 2, such as a hard disk or a memory of the server 2. In other embodiments, the memory may also be an external storage device of the server 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the server 2. Of course, the memory 21 may also comprise both an internal memory unit of the server 2 and an external memory device. In this embodiment, the memory 21 is generally used to store an operating system and various application software installed on the server 2, such as program codes of the advertisement push system 20. Further, the memory 21 may be used to temporarily store various types of data that have been output or are to be output.
The processor 22 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the server 2. In this embodiment, the processor 22 is configured to execute the program code or process data stored in the memory 21, for example, to execute the advertisement pushing system 20.
The network interface 23 may comprise a wireless network interface or a wired network interface, which network interface 23 is typically used for establishing a communication connection between the server 2 and other electronic devices. For example, the network interface 23 is used to connect the server 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the server 2 and the external terminal, and the like. The network may be an Intranet (Intranet), the Internet (Internet), a global system for mobile communications (Global System of Mobile communication, GSM), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or other wireless or wired network.
Example III
Referring to fig. 3, a program module diagram of an advertisement push system according to a third embodiment of the present invention is shown. In this embodiment, the advertisement pushing system 20 may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention and implement the advertisement pushing method described above. Program modules in accordance with embodiments of the present invention refer to a series of computer program instruction segments capable of performing particular functions, which are more suitable than the program itself for describing the execution of the advertisement delivery system 20 in a storage medium. The following description will specifically describe functions of each program module of the present embodiment:
a pushing module 201, configured to push the advertisement message with the tag to the first user terminal.
The obtaining module 202 is configured to obtain, by the first user terminal, a first behavior of viewing the advertisement message by a plurality of first users each having a first tag combination, where the first behavior includes at least clicking or viewing.
Specifically, the memory 21 of the server 2 is preset with advertisement messages of various tag types, and the advertisement messages are provided with different tag types according to types, for example: insurance, food, sports, make-up, and wear. Meanwhile, a user tag database is also preset in the memory 21 of the server 2, where the user tag database is used to store the tag types described by the user, for example: "female" loves naughty precious, "" housewives "insurance," "teenagers" basketball, "" etc.
In a preferred embodiment, when there is an advertisement message of an insurance class to be recommended to the user, a user of a tag combination of "female" "loving baby '," "housewife" "insurance'," teenager "" basketball "" is preset in the memory 21 of the server 2, and the pushing module 201 pushes the advertisement message of the insurance class to the user of the tag combination of "" female "" loving baby ', "" housewife "" insurance', "teenager" "basketball", "tag, and then the obtaining module 202 obtains the behaviors of the user of the tag combination of" "female", "loving baby '," "housewife" "insurance'," teenager "" basketball "," tag clicking or viewing the advertisement message of the insurance class through the user terminal.
The calculating module 203 is configured to calculate a first interest level of the advertisement message for the first user according to the first behavior and a calculation formula of the interest level.
In a preferred embodiment, the obtaining module 202 obtains a first frequency of clicking the advertisement message by the first user and a first viewing duration for viewing the advertisement message, and the calculating module 203 calculates a first interest level of the advertisement message by the first user according to the first frequency and the first viewing duration. The higher the frequency of clicking on the advertisement message or the longer the first viewing duration of viewing the advertisement message by the first user, the higher the first user's first level of interest in the advertisement message. The first frequency of the advertisement message clicked by the first user obtained by the obtaining module 202 may be the number of times the advertisement message is clicked by the first user in the obtained first historical click record of the first user, or may be a ratio of the number of times the advertisement message is clicked by the first user to the number of times the advertisement message is pushed by the server. Wherein, the calculation formula of the interest degree is as follows:wherein M is a constant, and correspondingly, the firstA calculation formula of the interest degree is as follows:
A combining module 204, configured to recombine the first tag combinations using a differential evolution algorithm to generate second tag combinations.
In a preferred embodiment, if the memory 21 of the server 2 is pre-configured with the users of the tag combinations of "" female "" loving precious, "" housewife "" insurance, "" and "" teenager "" basketball, "" the combination module 204 uses the differential evolution algorithm to re-combine the users of the tag combinations of "" female "" loving precious, "" housewife "" insurance, "" and "" teenager "" basketball, "" to generate 2 6 -1 tag combination (tag combination with null removed), for example: after recombination, the composition is formed into "" female "" housewife "", "" female "" insurance "", "" female "" teenager "", "" female "" basketball "", "" vain "" housewife "", "" vain "" insurance "", "" vain "" teenager "", and the composition is used for preventing and treating the skin and the skin. The third label combination of ' Ainaobao ' basketball ', ' housewife ' teenager ', ' housewife ' basketball ', ' insurance ' teenager ', ' insurance ' basketball ', ' women ' housewife ' basketball ', ' Ainaubao ' housewife ' insurance ', and the like. The combination module 204 then screens out the "naughty" housewife "," insurance "teenager", "women" housewife "," insurance "label combinations with a high likelihood of interest from the third label combination based on the user's interest in the advertisement message in the" naughty "label combinations, wherein the label combination of the' loving baby 'housewife', 'insurance' teenager ',' female 'housewife', 'loving baby' housewife 'insurance', and 'loving baby' housewife 'insurance', namely the second label combination, is provided with the 'loving baby'.The user of the label combination of ' housewife ', ' insurance ' teenager ', ' women ' housewife ', ' archer ' and ' archer ' insurance ', i.e. the second user. It should be noted that the first user and the second user may be the same user group, and only the label combination given by the first user and the second user is different, so that the satisfaction degree of the labels given by the user group to the user group is different.
The pushing module 201 is further configured to push the advertisement message to a second user terminal of the second user with the second tag combination.
In a preferred embodiment, when the combination result of the combination module 204 generates a new user of the tag combination (i.e., a second user of the second tag combination), the pushing module 201 pushes the advertisement message of the insurance class to the second user terminal of the second user to count the second interest level of the advertisement message of the insurance class for the second user.
The obtaining module 202 is further configured to obtain, through the second user terminal, a second behavior of the second user to watch the advertisement message, where the second behavior includes at least clicking or watching.
The calculating module 203 is further configured to calculate a second interest level of the advertisement message for the second user according to the second behavior and the calculation formula of the interest level.
In a preferred embodiment, the obtaining module 202 obtains a second frequency of clicking the advertisement message by the second user and a second viewing duration for viewing the advertisement message, and the calculating module 203 calculates a second interest level of the advertisement message by the second user according to the second frequency and the second viewing duration. The higher the frequency of clicking on the advertisement message or the longer the second viewing duration of viewing the advertisement message by the second user, the higher the second user's second level of interest in the advertisement message. The second frequency of clicking the advertisement message by the second user acquired by the acquisition module 202 may be according to the second history of clicking the second userThe number of times the user clicks the advertisement information may be the ratio of the number of times the second user clicks the advertisement information to the number of times the server pushes the advertisement information. Wherein, the calculation formula of the interest degree is as follows:wherein, M is a constant, and correspondingly, the calculation formula of the second interest degree is:
A comparison module 205, configured to compare the first degree of interest with the second degree of interest.
And the screening module 206 is configured to eliminate the first tag combination and reserve the second tag combination when the first interest level is lower than the second interest level, so as to screen the second tag combination and push the advertisement to the second user.
In another preferred embodiment, if the selected tag combination users have a degree of interest in the advertisement message lower than a preset value, the newly generated tag combination users are recombined to generate new tag combination users, and the degree of interest in the advertisement message by the new tag combination users is calculated respectively.
It should be noted that, in the embodiment of the present invention, the first tag combination is recombined by using the differential evolution algorithm, and only different tags are regarded as vectors in a certain sense, by freely combining the tags, for example, there are 1000 original tags, and in the combination, by giving an original tag 0 or 1, whether there are the original tags in the combination is represented, and in this way, 2 total tags are obtained 1000 And (3) selecting a combination mode, and then screening out a label combination with high possibility of preset data so as to perform further screening and further generate a new label combination.
According to the embodiment of the invention, the label combination of the user is optimized by utilizing the differential evolution algorithm, so that the advertisement can be more accurately pushed to the interested user, the advertisement pushing efficiency is improved, and meanwhile, higher economic benefits are brought to advertisers.
The invention also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server or a cabinet server (comprising independent servers or a server cluster formed by a plurality of servers) and the like which can execute programs. The computer device of the present embodiment includes at least, but is not limited to: memory, processors, etc. that may be communicatively coupled to each other via a system bus.
The present embodiment also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs the corresponding functions. The computer readable storage medium of the present embodiment is used to store the advertisement pushing system 20, and when executed by a processor, implements the advertisement pushing method of the first embodiment.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. An advertisement pushing method, characterized in that the method comprises the steps of:
pushing the advertisement message with the tag to the first user terminal;
acquiring first behaviors of a plurality of first users with first tag combinations for watching the advertisement message through the first user terminal, wherein the first behaviors at least comprise clicking or watching;
calculating a first interest degree of the advertisement message by the first user according to the first behavior and a calculation formula of the interest degree;
recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations;
pushing the advertisement message to a second user terminal of a second user with the second tag combination;
acquiring a second behavior of the second user for watching the advertisement message through the second user terminal, wherein the second behavior at least comprises clicking or watching;
calculating a second interest degree of the advertisement message by the second user according to the second behavior and the interest degree calculation formula;
comparing the first degree of interest with the second degree of interest; and
When the first interest degree is lower than the second interest degree, eliminating the first label combination and reserving the second label combination so as to screen out the second label combination and push advertisements to the second user;
wherein, the calculation formula of the interest degree is as follows:the M is a constant.
2. The advertisement pushing method as set forth in claim 1, wherein before the step of calculating the first interest level of the advertisement message by the first user according to the first behavior and the calculation formula of the interest level, further comprising:
acquiring a first historical click record of the first user; and
And counting a first click frequency of clicking the advertisement message by the first user and a first watching duration for watching the advertisement message according to the first historical click record.
3. The advertisement pushing method of claim 1, wherein the step of calculating a second degree of interest of the second user in the advertisement message according to the second behavior and the calculation formula of the degree of interest further comprises:
acquiring a second historical click record of the second user; and
And according to the second historical click record, counting a second click frequency of clicking the advertisement message by the second user and a second watching time length for watching the advertisement message.
4. The advertisement pushing method of claim 1, wherein the step of recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations further comprises:
recombining the first tag combinations to produce third tag combinations; and
And screening the second label combination with high interest degree possibility on the advertisement message from the third label combination according to the first interest degree.
5. A server, comprising:
the pushing module is used for pushing the advertisement message with the tag to the first user terminal;
the acquisition module is used for acquiring first behaviors of a plurality of first users with first tag combinations for watching the advertisement message through the first user terminal, wherein the first behaviors at least comprise clicking or watching;
the computing module is used for computing the first interest degree of the first user on the advertisement message according to the first behavior and the interest degree computing formula;
a combining module for recombining the first tag combinations using a differential evolution algorithm to produce second tag combinations;
the pushing module is further configured to push the advertisement message to a second user terminal of a second user with the second tag combination;
the obtaining module is further configured to obtain, through the second user terminal, a second behavior of the second user for watching the advertisement message, where the second behavior at least includes clicking or watching;
the computing module is further configured to compute a second interest level of the advertisement message by the second user according to the second behavior and the computation formula of the interest level;
a comparison module for comparing the first degree of interest with the second degree of interest; and
The screening module is used for eliminating the first label combination and reserving the second label combination when the first interest degree is lower than the second interest degree so as to screen the second label combination and push advertisements to the second user;
wherein, the calculation formula of the interest degree is as follows:the M is a constant.
6. The server according to claim 5, further comprising:
the combination module is further configured to recombine the first tag combinations to generate a third tag combination; and
The screening module is further configured to screen the second tag combination with high likelihood of interest degree for the advertisement message from the third tag combination according to the first interest degree.
7. A computer device, characterized in that the computer device memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when being executed by the processor, implements the steps of the advertisement pushing method according to any of the claims 1-4.
8. A computer-readable storage medium, in which a computer program is stored, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of the advertisement pushing method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910032512.9A CN109636487B (en) | 2019-01-14 | 2019-01-14 | Advertising push method, server, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910032512.9A CN109636487B (en) | 2019-01-14 | 2019-01-14 | Advertising push method, server, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636487A CN109636487A (en) | 2019-04-16 |
| CN109636487B true CN109636487B (en) | 2023-09-29 |
Family
ID=66060765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910032512.9A Active CN109636487B (en) | 2019-01-14 | 2019-01-14 | Advertising push method, server, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636487B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111447492B (en) * | 2019-10-25 | 2020-11-06 | 苏州博高睿华生物科技有限公司 | Targeted advertisement strategy customizing device and method |
| CN110751526A (en) * | 2019-10-25 | 2020-02-04 | 广州凌鑫达实业有限公司 | Advertisement pushing method and device, computer equipment and storage medium |
| CN111260391B (en) * | 2019-12-12 | 2021-09-07 | 上海钧正网络科技有限公司 | Advertising push method, apparatus, computer equipment and readable storage medium |
| CN111127092B (en) * | 2019-12-20 | 2023-07-14 | 中富通集团股份有限公司 | Method for improving click rate of intelligent device application advertisement and storage medium |
| CN111242693B (en) * | 2020-01-16 | 2023-08-25 | 秒针信息技术有限公司 | Device identification determining method and device, electronic device and storage medium |
| US11393203B2 (en) * | 2020-12-14 | 2022-07-19 | Snap Inc. | Visual tag emerging pattern detection |
| CN115442321B (en) * | 2021-06-04 | 2023-08-18 | 中国移动通信集团浙江有限公司 | Message delivery method, device, equipment and computer program product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014195782A2 (en) * | 2013-06-03 | 2014-12-11 | Tata Consultancy Services Limited | Differential evolution-based feature selection |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN108446735A (en) * | 2018-03-06 | 2018-08-24 | 宁波大学 | A kind of feature selection approach optimizing neighbour's constituent analysis based on differential evolution |
| CN109034864A (en) * | 2018-06-11 | 2018-12-18 | 广东因特利信息科技股份有限公司 | Improve method, apparatus, electronic equipment and storage medium that precision is launched in advertisement |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7716240B2 (en) * | 2005-12-29 | 2010-05-11 | Nextlabs, Inc. | Techniques and system to deploy policies intelligently |
| US7789758B2 (en) * | 2006-03-10 | 2010-09-07 | Electronic Arts, Inc. | Video game with simulated evolution |
-
2019
- 2019-01-14 CN CN201910032512.9A patent/CN109636487B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014195782A2 (en) * | 2013-06-03 | 2014-12-11 | Tata Consultancy Services Limited | Differential evolution-based feature selection |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN108446735A (en) * | 2018-03-06 | 2018-08-24 | 宁波大学 | A kind of feature selection approach optimizing neighbour's constituent analysis based on differential evolution |
| CN109034864A (en) * | 2018-06-11 | 2018-12-18 | 广东因特利信息科技股份有限公司 | Improve method, apparatus, electronic equipment and storage medium that precision is launched in advertisement |
Non-Patent Citations (1)
| Title |
|---|
| "Web文本分类中的标签权重自动优化研究";钟旭东;《小型微型计算机系统》;第37卷(第5期);890-894 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636487A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636487B (en) | Advertising push method, server, computer equipment and storage medium | |
| CN106372961A (en) | Commodity recommendation method and device | |
| CN113412608B (en) | Content pushing method and device, server and storage medium | |
| US12267557B2 (en) | Video content recommendation method and apparatus, and computer device | |
| CN111078742B (en) | User classification model training method, user classification method and device | |
| CN113225580B (en) | Live broadcast data processing method and device, electronic equipment and medium | |
| CN112650921B (en) | Object recommendation method, device, equipment and storage medium | |
| CN110807050B (en) | Performance analysis method, device, computer equipment and storage medium | |
| CN113434762A (en) | Association pushing method, device and equipment based on user information and storage medium | |
| CN113360756A (en) | Resource recommendation method and device, electronic equipment and medium | |
| JP2011227721A (en) | Interest extraction device, interest extraction method, and interest extraction program | |
| CN110110206A (en) | Relation excavation and recommended method, device, calculating equipment, storage medium between article | |
| CN112015986A (en) | Data pushing method and device, electronic equipment and computer readable storage medium | |
| CN111723210A (en) | Method and device for storing data table, computer equipment and readable storage medium | |
| CN110535910B (en) | Method and device for recalling breakpoint user and storage medium | |
| CN106257507B (en) | Risk assessment method and device for user behavior | |
| CN111401959B (en) | Risk group prediction method, apparatus, computer device and storage medium | |
| CN110503507B (en) | Insurance product data pushing method and system based on big data and computer equipment | |
| CN116362841A (en) | Recommendation method and device for financial products, computer equipment and readable storage medium | |
| CN112882758B (en) | iOS device identifier generation method and system | |
| CN110796500B (en) | Information monitoring method and device, electronic equipment and storage medium | |
| CN110557351A (en) | Method and apparatus for generating information | |
| CN108512744B (en) | Advertisement short message identification method, electronic device, terminal equipment and storage medium | |
| CN109241417B (en) | User awakening method and device, computing equipment and storage medium | |
| CN113468235A (en) | Information acquisition method, device, server 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 |