CN109493146A - Advertisement placement method and device - Google Patents
Advertisement placement method and device Download PDFInfo
- Publication number
- CN109493146A CN109493146A CN201811448380.XA CN201811448380A CN109493146A CN 109493146 A CN109493146 A CN 109493146A CN 201811448380 A CN201811448380 A CN 201811448380A CN 109493146 A CN109493146 A CN 109493146A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- tag along
- along sort
- advertisements
- advertisements metadata
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0257—User requested
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present embodiments relate to advertisement processing technology fields, in particular to a kind of advertisement placement method and device.This method is by obtaining customer problem record and its corresponding user portrait, then customer problem is recognized, and the result based on secondary identification, user's portrait carry out matching screening to multiple advertisements to be put, finally calculate each of screening acquisition advertisement to be put estimates clicking rate, the orderly dispensing of multiple advertisements to be put is realized according to the size order for estimating clicking rate, it so, it is possible to improve the accuracy and efficiency that advertisement is launched.
Description
Technical field
The present embodiments relate to advertisement processing technology fields, in particular to a kind of advertisement placement method and device.
Background technique
With the development of internet technology, Internet advertising has many relative to traditional television advertising and entity advertisements
Advantage, such as: strong interactivity and aesthetic, spread scope popularity, flexible timeliness etc..But existing interconnection
Net advertisement dispensing technology accuracy is not high, inefficiency.
Summary of the invention
In view of this, the present invention provides a kind of advertisement placement method and devices.
The embodiment of the invention provides a kind of advertisement placement methods, are applied to electronic equipment, which comprises
It obtains customer problem record and the customer problem records corresponding user's portrait, identify the customer problem note
The first tag along sort and the second tag along sort under first tag along sort of record;
Multiple advertisements to be put are obtained, for each advertisement to be put, extract the advertisements metadata of the advertisement to be put,
Count in multiple advertisements metadatas for extracting with the matched advertisements metadata of the first tag along sort;
For each advertisements metadata that statistics obtains, it is similar to second tag along sort to calculate the advertisements metadata
Angle value, judges whether the similarity value reaches given threshold, if reaching, judges whether the advertisements metadata draws with the user
As matching, if matching, retains the advertisements metadata;
For each advertisements metadata of reservation, estimating for advertising information to be put corresponding to the advertisements metadata is calculated
Clicking rate;
According to be calculated it is multiple estimate clicking rate by the corresponding advertisement to be put of each advertisements metadata of reservation into
Row is launched.
Optionally, the first tag along sort of the customer problem record is identified and under first tag along sort
The step of second tag along sort, comprising:
At least one keyword in the customer problem record is extracted, theme letter is generated according at least one described keyword
Breath;
The first tag along sort of the customer problem record is identified based on the subject information;
Obtain at least one conjunctive word of at least one keyword;
Identify that the customer problem is recorded in based at least one described keyword and at least one described conjunctive word
The second tag along sort under first tag along sort.
Optionally, the advertisements metadata includes advertisement classification, count in the multiple advertisements metadatas extracted with it is described
The step of first tag along sort matched advertisements metadata, comprising:
For each advertisements metadata extracted, the advertisement classification in the advertisements metadata is obtained;
Judge whether the advertisement classification and first tag along sort consistent, if unanimously, determine the advertisement classification with
The first tag along sort matching, counts the advertisements metadata.
Optionally, the advertisements metadata further includes advertisement keyword, for each advertisements metadata that statistics obtains, meter
The step of calculating similarity value of the advertisements metadata with second tag along sort, comprising:
Obtain the advertisement keyword in the advertisements metadata;
Calculate the cosine similarity value of the advertisement keyword Yu second tag along sort.
Optionally, according to be calculated multiple to estimate clicking rate corresponding to be put by each advertisements metadata of reservation
The step of advertisement is launched, comprising:
According to the multiple sequencings for estimating clicking rate being calculated by each advertisements metadata of reservation it is corresponding to
Advertisement is launched successively to be launched.
The embodiment of the invention also provides a kind of advertisement delivery devices, are applied to electronic equipment, and described device includes:
Identification module records corresponding user's portrait for obtaining customer problem record and the customer problem, identifies
The first tag along sort and the second tag along sort under first tag along sort of the customer problem record;
First matching module, for each advertisement to be put, it is to be put to extract this for obtaining multiple advertisements to be put
The advertisements metadata of advertisement, count in the multiple advertisements metadatas extracted with the matched advertisement member number of first tag along sort
According to;
Second matching module, for for the obtained each advertisements metadata of statistics, calculate the advertisements metadata with it is described
The similarity value of second tag along sort, judges whether the similarity value reaches given threshold, if reaching, judges the advertisement member number
According to whether with the user portrait match, if match, retain the advertisements metadata;
Clicking rate computing module is estimated, for it is right to calculate advertisements metadata institute for each advertisements metadata retained
The advertising information to be put answered estimates clicking rate;
Advertisement putting module, for according to the multiple each advertisements metadatas pair for estimating clicking rate for reservation being calculated
The advertisement to be put answered is launched.
Optionally, the identification module identifies the first tag along sort of the customer problem record and described first
The second tag along sort under tag along sort, specifically includes:
At least one keyword in the customer problem record is extracted, theme letter is generated according at least one described keyword
Breath;
The first tag along sort of the customer problem record is identified based on the subject information;
Obtain at least one conjunctive word of at least one keyword;
Identify that the customer problem is recorded in based at least one described keyword and at least one described conjunctive word
The second tag along sort under first tag along sort.
Optionally, the advertisements metadata includes advertisement classification, and the first matching module statistics extracts multiple wide
It accuses in metadata with the matched advertisements metadata of the first tag along sort, specifically includes:
For each advertisements metadata extracted, the advertisement classification in the advertisements metadata is obtained;
Judge whether the advertisement classification and first tag along sort consistent, if unanimously, determine the advertisement classification with
The first tag along sort matching, counts the advertisements metadata.
Optionally, the advertisements metadata further includes advertisement keyword, and second matching module is obtained for statistics
Each advertisements metadata calculates the similarity value of the advertisements metadata Yu second tag along sort, specifically includes:
Obtain the advertisement keyword in the advertisements metadata;
Calculate the cosine similarity value of the advertisement keyword Yu second tag along sort.
Optionally, described to estimate clicking rate computing module according to the multiple clicking rates of estimating being calculated for each of reservation
The corresponding advertisement to be put of advertisements metadata is launched, comprising:
According to the multiple sequencings for estimating clicking rate being calculated by each advertisements metadata of reservation it is corresponding to
Advertisement is launched successively to be launched
The embodiment of the invention also provides a kind of electronic equipment, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor realize that above-mentioned advertisement is thrown when executing the computer program
Put method.
The embodiment of the invention also provides a kind of computer readable storage medium, the readable storage medium storing program for executing includes computer
Program, the electronic equipment computer program controls the readable storage medium storing program for executing when running where execute above-mentioned advertisement dispensing side
Method.
Beneficial effect
Advertisement placement method and device provided in an embodiment of the present invention can recognize that the first classification of customer problem record
Label and the second tag along sort once match multiple advertisements to be put by the first tag along sort, then pass through second
Tag along sort and user's portrait carry out Secondary Match to multiple advertisements to be put, so, it is possible to guarantee advertisement to be put and use
Family demand is utmostly agreed with, and can be improved the accuracy of advertisement dispensing, by calculating each advertisements metadata pair retained
The advertising information to be put answered estimates clicking rate, and is launched advertisement to be put based on multiple clicking rates of estimating, can
The probability that user clicks advertisement is improved, and then guarantees the efficiency that advertisement is launched.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the block diagram of a kind of electronic equipment 10 provided by the embodiment of the present invention.
Fig. 2 is a kind of flow chart of advertisement placement method provided by the embodiment of the present invention.
Fig. 3 is the schematic diagram for the sub-step that step S21 shown in Fig. 2 includes in an embodiment.
Fig. 4 is a kind of module frame chart of advertisement delivery device 20 provided by the embodiment of the present invention.
Icon:
10- electronic equipment;11- memory;12- processor;13- network module;
20- advertisement delivery device;21- identification module;The first matching module of 22-;The second matching module of 23-;24- is estimated a little
Hit rate computing module;25- advertisement putting module.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment only
It is a part of the embodiments of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings
The component of embodiment can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Inventor further investigation reveals that, existing Internet advertising launches that the most accuracy of technology is not high and inefficiency.Tool
Body, existing Internet advertising is launched technology and is mainly realized by Three models:
1) displaying amount charging mode is pressed.Firstly, this mode does not segment media content further, for matchmaker
It is situated between, the flow of popular plate is significantly larger than long-tail plate, and advertiser mainly launches advertisement in popular plate, advertisement position is failed
It makes full use of;Secondly, this mode fails effectively to draw a portrait to user, cannot be separated different according to the feature of user
Advertisement fails effectively to utilize advertisement position.
2) click volume charging mode is pressed.It is effectively drawn a portrait to user, but is difficult to meet the needs of advertiser is to displaying amount,
Indicated when one the user effectively to draw a portrait it is online after, advertisement subsystem can distribute a suitable advertisement, may cause part advertisement
Click is unsatisfactory for advertiser demand.
3) bid advertisement mode.Ad system includes user behavior data more comprehensively, richer, is more suitable for platform factory
Quotient builds big platform, but the manufacturer of the user behavior data in medium is contained only for vertical field, very difficult across click
Convert this road bank.
Defect present in the above scheme in the prior art, is that inventor is obtaining after practicing and carefully studying
As a result, therefore, the solution that the discovery procedure of the above problem and the hereinafter embodiment of the present invention are proposed regarding to the issue above
Scheme all should be the contribution that inventor makes the present invention in process of the present invention.
Based on the studies above, the embodiment of the invention provides a kind of advertisement placement method and devices, can be improved advertisement throwing
The accuracy and efficiency put.
Fig. 1 shows the block diagram of a kind of electronic equipment 10 provided by the embodiment of the present invention.The embodiment of the present invention
In electronic equipment 10 can for data storage, transmission, processing function server-side, as shown in Figure 1, electronic equipment 10 wrap
It includes: memory 11, processor 12, network module 13 and advertisement delivery device 20.
It is directly or indirectly electrically connected between memory 11, processor 12 and network module 13, to realize the biography of data
Defeated or interaction.It is electrically connected for example, these elements can be realized from each other by one or more communication bus or signal wire.
Advertisement delivery device 20 is stored in memory 11, the advertisement delivery device 20 includes at least one can be with software or firmware
(firmware) form is stored in the software function module in the memory 11, and the processor 12 is stored in by operation
The advertisement delivery device 20 in software program and module, such as the embodiment of the present invention in memory 11, thereby executing various
Functional application and data processing, i.e. advertisement placement method in the realization embodiment of the present invention.
Wherein, the memory 11 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 11 is for storing program, and the processor 12 executes described program after receiving and executing instruction.
The processor 12 may be a kind of IC chip, the processing capacity with data.Above-mentioned processor 12
It can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP) etc..It may be implemented or execute each method, step disclosed in the embodiment of the present invention and patrol
Collect block diagram.General processor can be microprocessor or the processor is also possible to any conventional processor etc..
Network module 13 is used to establish the communication connection between electronic equipment 10 and other communication terminal devices by network,
Realize the transmitting-receiving operation of network signal and data.Above-mentioned network signal may include wireless signal or wire signal.
It is appreciated that structure shown in FIG. 1 is only to illustrate, electronic equipment 10 may also include it is more than shown in Fig. 1 or
Less component, or with the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can using hardware, software or its
Combination is realized.
The embodiment of the present invention also provides a kind of computer readable storage medium, and the readable storage medium storing program for executing includes computer journey
Sequence.Electronic equipment 10 computer program controls the readable storage medium storing program for executing when running where executes following advertisement dispensing side
Method.
Fig. 2 shows a kind of flow charts of advertisement placement method provided by the embodiment of the present invention.The method is related
Method and step defined in process is applied to electronic equipment 10, can be realized by the processor 12.It below will be to shown in Fig. 2
Detailed process is described in detail:
Step S21, obtains customer problem record and the customer problem records corresponding user's portrait, identifies that user asks
The first tag along sort and the second tag along sort under the first tag along sort for inscribing record.
Fig. 3 is please referred to, is enumerated in the present embodiment by step S211, step S212, step S213 and step S214
One of implementation of step S21.
Step S211, extracts at least one keyword in customer problem record, generates theme according at least one keyword
Information.
In the present embodiment, it generates model using document subject matter the keyword in customer problem record is extracted and given birth to
At subject information, specifically, is recorded for the customer problem of long text, LAD model can be used, asked for the user of short text
Topic record, can use LAD2vec model.
Step S212 identifies the first tag along sort of customer problem record based on subject information.
Specifically, it according to subject information, can recognize that using machine learning classification method corresponding with the subject information
First tag along sort identifies the process of the first tag along sort it can be appreciated that recording the mistake classified to the customer problem
Journey.
For example, the first tag along sort can be any one in education, medical treatment, culture, game, amusement, in this implementation
In example, the first tag along sort is medical treatment.
Step S213 obtains at least one conjunctive word of at least one keyword.
For example, keyword is " cold cough ", then conjunctive word can be " rhinorrhea ", " aching all over " etc..
Step S214 identifies that customer problem is recorded in first based at least one keyword and at least one conjunctive word
The second tag along sort under tag along sort.
For example, identifying the second classification under medical tag based on " cold cough ", " rhinorrhea " and " aching all over "
Label: cold symptoms.
It is appreciated that through the above steps, can be realized the dual identification (classification) to customer problem record, after being convenient for
The accurate match of relevant advertisements.
Optionally, user's portrait can be obtained by the behavior record of user.User's portrait includes gender, the age, resides
Ground, income etc..
Step S22 obtains multiple advertisements to be put for each advertisement to be put and extracts the wide of the advertisement to be put
Accuse metadata, count in the multiple advertisements metadatas extracted with the matched advertisements metadata of the first tag along sort.
Advertisements metadata includes advertisement position ID, advertisement ID, advertiser ID, ad material ID, marketing activity ID, commercial paper
Not, advertisement major category, advertisement title, advertisement keyword etc..
In the present embodiment, it can judge whether advertisements metadata matches with the first tag along sort by advertisement classification, have
Body, extracts the advertisement classification in each advertisements metadata, judge respectively each advertisement classification whether with the first tag along sort
Unanimously, the corresponding advertisements metadata of consistent advertisement classification rope is judged to matching with the first tag along sort, is counted and first point
The matched multiple advertisements metadatas of class label.
In this way, screening by the first round, the dispensing of some inessential advertisements can be excluded to a certain extent, saved
Internet resources.
Step S23 calculates the advertisements metadata and second contingency table for each advertisements metadata that statistics obtains
The similarity value of label.
In the present embodiment, the similarity of advertisements metadata and the second tag along sort can be calculated by advertisement keyword
Value.
Specifically, for each advertisements metadata, the advertisement keyword in the advertisements metadata is extracted, calculates advertisement keyword
The cosine similarity value of word and the second tag along sort.
Step S24, judges whether similarity value reaches given threshold
Wherein, given threshold can be preset.
If similarity value is less than given threshold, step S25 is turned to.
If similarity value is more than or equal to given threshold, step S26 is turned to.
Step S25 removes the corresponding advertisements metadata of the advertisement keyword.
If being appreciated that, similarity value is less than given threshold, shows that the advertisement keyword is related to the second tag along sort
Degree is not high, can be by the corresponding advertisement member number of the advertisement keyword in order to avoid the invalid push of the not high advertisement of some degrees of correlation
It according to being removed, is no longer further analyzed and screens, so, it is possible to save certain Internet resources.
Step S26, judges whether the advertisements metadata matches with user's portrait.
It is mismatched if the advertisements metadata and user draw a portrait, turns to step S27.
If the advertisements metadata is matched with user's portrait, step S28 is turned to.
Step S27 removes the advertisements metadata.
If being appreciated that, similarity value meets, and the matching that also will do it user's portrait determines, and then ensures the advertisement member number
The user terminal of specific user's portrait can be accurately launched according to corresponding advertisement to be put, and nothing is carried out to user in this way, avoiding
The advertisement of difference is launched and push.
In the present embodiment, advertisement position ID, advertisement ID, advertiser ID, ad material ID, marketing activity ID etc. can be passed through
Realize the matching with user's portrait.
Step S28 retains the advertisements metadata.
If the advertisements metadata is matched with user's portrait, which can be retained, further to divide
Analysis.
Step S29, calculate the corresponding advertisement to be put of each advertisements metadata of reservation estimates clicking rate and according to meter
The clicking rates of estimating calculated launch the advertisement to be put of reservation more.
It is appreciated that the advertisements metadata retained may to be multiple, correspondingly, the advertisement to be put of reservation be also it is multiple,
For this purpose, can calculate each of reservation advertisement to be put first estimates clicking rate, convenient for orderly dispensing later.
Specific, for each of reservation advertisement to be put, the history point for the corresponding user terminal that can be drawn a portrait based on user
It hits record and click prediction model and Logic Regression Models calculates and estimate clicking rate.
Calculate it is multiple estimate clicking rate after, can be according to estimating the size order of clicking rate for the multiple wait throw of reservation
It puts advertisement and is successively sent to the corresponding user terminal of user's portrait.It so, it is possible accurate, the orderly dispensing of realization advertisement, on the one hand,
The accurate dispensing of advertisement can Effective selection provide targeted effective advertisement, reduce disappearing for customer flow and Internet resources
Consumption, on the other hand, the orderly of advertisement launch the efficiency that can be improved advertisement dispensing, estimate the high preferential push of clicking rate, in this way,
It can guarantee that user terminal can click advertisement, be able to ascend advertising results to the full extent.
On the basis of the above, as shown in figure 4, the embodiment of the invention provides a kind of advertisement delivery device 20, the advertisement
Delivery device 20 includes: identification module 21, the first matching module 22, the second matching module 23, estimates clicking rate computing module 24
With advertisement putting module 25.
Identification module 21 records corresponding user's portrait, identification for obtaining customer problem record and the customer problem
First tag along sort of the customer problem record and the second tag along sort under first tag along sort out.
Since identification module 21 is similar with the realization principle of step S21 in Fig. 2, do not illustrate more herein.
First matching module 22, for each advertisement to be put, extracts this wait throw for obtaining multiple advertisements to be put
The advertisements metadata for putting advertisement counts first with the matched advertisement of first tag along sort in the multiple advertisements metadatas extracted
Data.
Since the first matching module 22 is similar with the realization principle of step S22 in Fig. 2, do not illustrate more herein.
Second matching module 23, each advertisements metadata for obtaining for statistics, calculates the advertisements metadata and institute
The similarity value for stating the second tag along sort, judges whether the similarity value reaches given threshold, if reaching, judges advertisement member
Whether data match with user portrait, if matching, retains the advertisements metadata.
Since the second matching module 23 is similar with step S23~realization principle of step S28 in Fig. 2, do not make herein
More explanations.
Clicking rate computing module 24 is estimated, for calculating the advertisements metadata institute for each advertisements metadata retained
Corresponding advertising information to be put estimates clicking rate.
It is similar with the realization principle of step S29 in Fig. 2 due to estimating clicking rate computing module 24, do not make herein more
Explanation.
Advertisement putting module 25, for according to the multiple each advertisements metadatas for estimating clicking rate for reservation being calculated
Corresponding advertisement to be put is launched.
Since advertisement putting module 25 is similar with the realization principle of step S29 in Fig. 2, do not illustrate more herein.
To sum up, advertisement placement method and device provided by the embodiment of the present invention can be improved the accuracy of advertisement dispensing
And efficiency.
In several embodiments provided by the embodiment of the present invention, it should be understood that disclosed device and method, it can also
To realize by another way.Device and method embodiment described above is only schematical, for example, in attached drawing
Flow chart and block diagram show that the devices of multiple embodiments according to the present invention, method and computer program product are able to achieve
Architecture, function and operation.In this regard, each box in flowchart or block diagram can represent module, a program
A part of section or code, a part of the module, section or code include that one or more is patrolled for realizing defined
Collect the executable instruction of function.It should also be noted that in some implementations as replacement, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, electronic equipment 10 or the network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of advertisement placement method, which is characterized in that be applied to electronic equipment, which comprises
It obtains customer problem record and the customer problem records corresponding user's portrait, identify the customer problem record
First tag along sort and the second tag along sort under first tag along sort;
Multiple advertisements to be put are obtained, for each advertisement to be put, extract the advertisements metadata of the advertisement to be put, are counted
In the multiple advertisements metadatas extracted with the matched advertisements metadata of the first tag along sort;
For each advertisements metadata that statistics obtains, the similarity of the advertisements metadata Yu second tag along sort is calculated
Value, judges whether the similarity value reaches given threshold, if reaching, judges whether the advertisements metadata draws a portrait with the user
Matching, if matching, retains the advertisements metadata;
For each advertisements metadata of reservation, calculate advertising information to be put corresponding to the advertisements metadata estimates click
Rate;
It multiple estimate clicking rate according to what is be calculated and throws the corresponding advertisement to be put of each advertisements metadata of reservation
It puts.
2. advertisement placement method according to claim 1, which is characterized in that identify the first of the customer problem record
The step of tag along sort and the second tag along sort under first tag along sort, comprising:
At least one keyword in the customer problem record is extracted, subject information is generated according at least one described keyword;
The first tag along sort of the customer problem record is identified based on the subject information;
Obtain at least one conjunctive word of at least one keyword;
It is described to identify that the customer problem is recorded in based at least one described keyword and at least one described conjunctive word
The second tag along sort under first tag along sort.
3. advertisement placement method according to claim 1, which is characterized in that the advertisements metadata includes advertisement classification,
The step of counting advertisements metadata matched with first tag along sort in the multiple advertisements metadatas extracted, comprising:
For each advertisements metadata extracted, the advertisement classification in the advertisements metadata is obtained;
Judge whether the advertisement classification and first tag along sort consistent, if unanimously, determine the advertisement classification with it is described
The matching of first tag along sort, counts the advertisements metadata.
4. advertisement placement method according to claim 3, which is characterized in that the advertisements metadata further includes advertisement keyword
Word calculates the similarity value of the advertisements metadata Yu second tag along sort for each advertisements metadata that statistics obtains
The step of, comprising:
Obtain the advertisement keyword in the advertisements metadata;
Calculate the cosine similarity value of the advertisement keyword Yu second tag along sort.
5. advertisement placement method according to claim 1, which is characterized in that multiple estimate clicking rate according to what is be calculated
The step of corresponding advertisement to be put of each advertisements metadata of reservation is launched, comprising:
It is according to the multiple sequencings for estimating clicking rate being calculated that each advertisements metadata of reservation is corresponding to be put
Advertisement is successively launched.
6. a kind of advertisement delivery device, which is characterized in that be applied to electronic equipment, described device includes:
Identification module records corresponding user's portrait for obtaining customer problem record and the customer problem, identifies described
The first tag along sort and the second tag along sort under first tag along sort of customer problem record;
First matching module, for each advertisement to be put, extracts the advertisement to be put for obtaining multiple advertisements to be put
Advertisements metadata, count in the multiple advertisements metadatas extracted with the matched advertisements metadata of the first tag along sort;
Second matching module, each advertisements metadata for obtaining for statistics, calculates the advertisements metadata and described second
The similarity value of tag along sort, judges whether the similarity value reaches given threshold, if reaching, judges that the advertisements metadata is
It is no to be matched with user portrait, if matching, retains the advertisements metadata;
Clicking rate computing module is estimated, for calculating corresponding to the advertisements metadata for each advertisements metadata retained
Advertising information to be put estimates clicking rate;
Advertisement putting module, for according to be calculated multiple to estimate clicking rate corresponding by each advertisements metadata of reservation
Advertisement to be put is launched.
7. advertisement delivery device according to claim 6, which is characterized in that the identification module identifies that the user asks
The first tag along sort and the second tag along sort under first tag along sort for inscribing record, specifically include:
At least one keyword in the customer problem record is extracted, subject information is generated according at least one described keyword;
The first tag along sort of the customer problem record is identified based on the subject information;
Obtain at least one conjunctive word of at least one keyword;
It is described to identify that the customer problem is recorded in based at least one described keyword and at least one described conjunctive word
The second tag along sort under first tag along sort.
8. advertisement delivery device according to claim 6, which is characterized in that the advertisements metadata includes advertisement classification,
In multiple advertisements metadatas that first matching module statistics extracts with the matched advertisement member number of first tag along sort
According to specifically including:
For each advertisements metadata extracted, the advertisement classification in the advertisements metadata is obtained;
Judge whether the advertisement classification and first tag along sort consistent, if unanimously, determine the advertisement classification with it is described
The matching of first tag along sort, counts the advertisements metadata.
9. advertisement delivery device according to claim 8, which is characterized in that the advertisements metadata further includes advertisement keyword
Word, each advertisements metadata that second matching module is obtained for statistics, calculates the advertisements metadata and described second point
The similarity value of class label, specifically includes:
Obtain the advertisement keyword in the advertisements metadata;
Calculate the cosine similarity value of the advertisement keyword Yu second tag along sort.
10. advertisement delivery device according to claim 6, which is characterized in that it is described estimate clicking rate computing module according to
The multiple clicking rates of estimating being calculated launch the corresponding advertisement to be put of each advertisements metadata of reservation, comprising:
It is according to the multiple sequencings for estimating clicking rate being calculated that each advertisements metadata of reservation is corresponding to be put
Advertisement is successively launched.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811448380.XA CN109493146A (en) | 2018-11-29 | 2018-11-29 | Advertisement placement method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811448380.XA CN109493146A (en) | 2018-11-29 | 2018-11-29 | Advertisement placement method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493146A true CN109493146A (en) | 2019-03-19 |
Family
ID=65698710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811448380.XA Pending CN109493146A (en) | 2018-11-29 | 2018-11-29 | Advertisement placement method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493146A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110765771A (en) * | 2019-09-17 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Method and device for determining advertisement statement |
CN110782286A (en) * | 2019-10-25 | 2020-02-11 | 上海喜马拉雅科技有限公司 | Advertisement pushing method and device, server and computer readable storage medium |
CN111160953A (en) * | 2019-12-12 | 2020-05-15 | 浙江大华技术股份有限公司 | Method and device for delivering advertisement in application and storage medium |
CN111242684A (en) * | 2020-01-12 | 2020-06-05 | 浙江执御信息技术有限公司 | Advertisement putting method |
CN112396473A (en) * | 2020-12-23 | 2021-02-23 | 上海苍苔信息技术有限公司 | CPM system and method for improving CTR value |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951965A (en) * | 2015-06-26 | 2015-09-30 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method and device |
CN106021586A (en) * | 2016-06-06 | 2016-10-12 | 腾讯科技(北京)有限公司 | Information processing method and server |
CN106204156A (en) * | 2016-07-20 | 2016-12-07 | 天涯社区网络科技股份有限公司 | A kind of advertisement placement method for network forum and device |
CN106952112A (en) * | 2017-03-01 | 2017-07-14 | 心触动(武汉)文化传媒有限公司 | A kind of method for delivering advertisement accurately and system |
CN108230025A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
-
2018
- 2018-11-29 CN CN201811448380.XA patent/CN109493146A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951965A (en) * | 2015-06-26 | 2015-09-30 | 深圳市腾讯计算机系统有限公司 | Advertisement delivery method and device |
CN106021586A (en) * | 2016-06-06 | 2016-10-12 | 腾讯科技(北京)有限公司 | Information processing method and server |
CN106204156A (en) * | 2016-07-20 | 2016-12-07 | 天涯社区网络科技股份有限公司 | A kind of advertisement placement method for network forum and device |
CN106952112A (en) * | 2017-03-01 | 2017-07-14 | 心触动(武汉)文化传媒有限公司 | A kind of method for delivering advertisement accurately and system |
CN108230025A (en) * | 2017-12-29 | 2018-06-29 | 暴风集团股份有限公司 | Method and apparatus, electronic equipment, storage medium, program are recommended in advertisement |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110765771A (en) * | 2019-09-17 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Method and device for determining advertisement statement |
CN110765771B (en) * | 2019-09-17 | 2023-05-05 | 创新先进技术有限公司 | Method and device for determining advertisement sentences |
CN110782286A (en) * | 2019-10-25 | 2020-02-11 | 上海喜马拉雅科技有限公司 | Advertisement pushing method and device, server and computer readable storage medium |
CN110782286B (en) * | 2019-10-25 | 2023-08-18 | 上海喜马拉雅科技有限公司 | Advertisement pushing method, advertisement pushing device, server and computer readable storage medium |
CN111160953A (en) * | 2019-12-12 | 2020-05-15 | 浙江大华技术股份有限公司 | Method and device for delivering advertisement in application and storage medium |
CN111160953B (en) * | 2019-12-12 | 2023-11-03 | 浙江大华技术股份有限公司 | Method, device and storage medium for putting advertisement in application |
CN111242684A (en) * | 2020-01-12 | 2020-06-05 | 浙江执御信息技术有限公司 | Advertisement putting method |
CN112396473A (en) * | 2020-12-23 | 2021-02-23 | 上海苍苔信息技术有限公司 | CPM system and method for improving CTR value |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493146A (en) | Advertisement placement method and device | |
CN105160008B (en) | Method and device for positioning recommended user | |
CN108108996B (en) | Method and device for delivering advertisements in video, computer equipment and readable medium | |
WO2018072513A1 (en) | Advertisement information pushing method and apparatus, and system, server and computer readable medium | |
CN107807941B (en) | Information processing method and device | |
EP2242016A1 (en) | Touchpoint customization system | |
CN108446813A (en) | A kind of method of electric business service quality overall merit | |
CN110222975A (en) | A kind of loss customer analysis method, apparatus, electronic equipment and storage medium | |
CN105912560A (en) | Detect sports video highlights based on voice recognition | |
US11017430B2 (en) | Delivering advertisements based on user sentiment and learned behavior | |
CN110427897A (en) | Analysis method, device and the server of video highlight degree | |
CN108269122B (en) | Advertisement similarity processing method and device | |
CN107222526A (en) | Push method, device, equipment and the computer-readable storage medium of promotion message | |
CN110414856B (en) | Method and device for evaluating marketing information design quality | |
CN108256537A (en) | A kind of user gender prediction method and system | |
CN108595492A (en) | Method for pushing and device, storage medium, the electronic device of content | |
CN110428277B (en) | Touch method of recommended product, storage medium and program product | |
CN206378900U (en) | A kind of advertisement delivery effect evaluation system based on mobile terminal | |
CN113506124B (en) | Method for evaluating media advertisement putting effect in intelligent business district | |
CN106383857A (en) | Information processing method and electronic equipment | |
CN109408723A (en) | A kind of method for pushing and device | |
CN109660871A (en) | A kind of barrage Role Information determines method, device and equipment | |
US11308135B2 (en) | Data prioritization through relationship analysis mapping | |
JP2004094383A (en) | Recommendation device and advertisement distribution method | |
CN107665202A (en) | Method and device for constructing interest model and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |