CN105208113A - Information pushing method and device - Google Patents
Information pushing method and device Download PDFInfo
- Publication number
- CN105208113A CN105208113A CN201510549839.5A CN201510549839A CN105208113A CN 105208113 A CN105208113 A CN 105208113A CN 201510549839 A CN201510549839 A CN 201510549839A CN 105208113 A CN105208113 A CN 105208113A
- Authority
- CN
- China
- Prior art keywords
- information
- service end
- presented
- terminal use
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012549 training Methods 0.000 claims description 41
- 239000000284 extract Substances 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 10
- 235000012054 meals Nutrition 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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
-
- 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
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses an information pushing method and device. The method comprises the following specific execution modes: receiving user identification of a terminal user sent by an application server end through a forecast server end; searching extended information of the terminal user according to the user identification, wherein the extended information is obtained from a terminal; generating a predicted value for each piece of information to be displayed based on the extended information and a pre-trained prediction model, wherein the predicted values comprise probability values for carrying out operation on each information to be displayed by the terminal user; and returning the predicted values to the application server end so as to allow the application server end to select at least one piece of information to be displayed according to the ranking result of the predicted values, and push the information to be displayed to the terminal user. The method can improve the target performance of user identification pushing.
Description
Technical field
The application relates to field of computer technology, is specifically related to Internet technical field, particularly relates to a kind of method and apparatus of information pushing.
Background technology
Information pushing, is also called " Web broadcast ", is by certain technical standard or agreement, and the information needed by pushing user on the internet reduces a technology of information overload.Information advancing technique to user by active push information, can be reduced user on network, search for institute's time spent.Information pushing may be used for display and the terminal applies of various webpage, such as web advertisement, the application of shopping Terminal Type etc.
But in more existing terminal applies, conventional information pushing mode is normally direct loads pushed information on the page, different terminals shows identical pushed information, thus there is Internet resources related data under-utilized, information pushing lacks problem targetedly.
Summary of the invention
The object of the application is the method and apparatus of the information pushing proposing a kind of improvement, solves the technical problem that above background technology part is mentioned.
On the one hand, this application provides a kind of method of information pushing, described method comprises: the user ID receiving the terminal use that application service end sends; Retrieve the extend information of described terminal use according to described user ID, wherein, described extend information obtains from terminal; Based on the forecast model of described extend information and training in advance to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Described predicted value is returned to described application service end, chooses at least one information pushing to be presented to described terminal use for described application service end group in the ranking results of each predicted value.
In certain embodiments, described method also comprises: receive the historical operation information that the history exhibition information of described application service end transmission, information to be presented and multiple terminal use carry out for described history exhibition information; Obtain the extend information of described multiple terminal use; According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
In certain embodiments, described according to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model comprise: from the extend information of described multiple terminal use, extract user characteristics respectively; According to described user characteristics and described historical operation information, generate the contribution coefficient of user characteristics for historical operation information; Generate the forecast model that the operation information to terminal use is predicted based on described user characteristics and described contribution coefficient.
In certain embodiments, describedly based on described extend information and described forecast model, each bar information to be presented generation forecast value to be comprised: from described extend information, extract user characteristics; Calculate the importance degree coefficient of each user characteristics; Based on the predicted value of the described importance degree coefficient of each user characteristics and the operation information of described contribution coefficient computing terminal user.
In certain embodiments, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
Second aspect, present invention also provides a kind of method of information pushing, described method comprises: to the user ID of prediction service end transmitting terminal user, generate the predicted value of information to be presented: the extend information retrieving described terminal use according to described user ID for prediction service end for each user ID according to following steps; Based on the forecast model of described extend information and training in advance to every bar information generation forecast to be presented value, wherein, described extend information is obtained from terminal by described prediction service end, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Receive each predicted value that described prediction service end returns; Ranking results based on each predicted value chooses at least one information pushing to be presented to described terminal use.
In certain embodiments, described method also comprises: obtain the historical operation information that multiple terminal use carries out for history exhibition information; Send described information to be presented, described history exhibition information and described historical operation information to described prediction service end, train forecast model for described prediction service end by following steps: the extend information obtaining described multiple terminal use; According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
In certain embodiments, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
The third aspect, this application provides a kind of device of information pushing, and described device comprises: receiver module, is configured for the user ID receiving the terminal use that application service end sends; Retrieval module, is configured for the extend information retrieving described terminal use according to described user ID, and wherein, described extend information obtains from terminal; Generation module, be configured for forecast model based on described extend information and training in advance to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Return module, be configured for and described predicted value is returned to described application service end, choose at least one information pushing to be presented to described terminal use for described application service end group in the ranking results of each predicted value.
In certain embodiments, described device also comprises: model information receiver module, is configured for the historical operation information that the history exhibition information receiving described application service end and send, information to be presented and multiple terminal use carry out for described history exhibition information; Acquisition module, is configured for the extend information obtaining described multiple terminal use; Model training module, is configured for according to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
In certain embodiments, described model training module comprises: feature extraction unit, is configured for and extracts user characteristics respectively from the extend information of described multiple terminal use; Contribution coefficient generation unit, is configured for according to described user characteristics and described historical operation information, generates the contribution coefficient of user characteristics for historical operation information; Forecast model generation unit, is configured for and generates the forecast model that the operation information to terminal use is predicted based on described user characteristics and described contribution coefficient.
In certain embodiments, described generation module comprises: extraction unit, is configured for and extracts user characteristics from described extend information; Coefficient calculation unit, is configured for the importance degree coefficient calculating each user characteristics; Predictor calculation unit, is configured for the predicted value based on the described importance degree coefficient of each user characteristics and the operation information of described contribution coefficient computing terminal user.
In certain embodiments, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
Fourth aspect, present invention also provides a kind of device of information pushing, and described device comprises:
Sending module, be configured for the user ID to prediction service end transmitting terminal user, generate the predicted value of information to be presented according to following steps for each user ID for prediction service end: the extend information retrieving described terminal use according to described user ID; Based on the forecast model of described extend information and training in advance to every bar information generation forecast to be presented value, wherein, described extend information is obtained from terminal by described prediction service end, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Receiver module, is configured for each predicted value receiving described prediction service end and return; Pushing module, the ranking results be configured for based on each predicted value chooses at least one information pushing to be presented to described terminal use.
In certain embodiments, described device also comprises: acquisition module, is configured for the historical operation information obtaining multiple terminal use and carry out for history exhibition information; Model information sending module, be configured for and send described information to be presented, described history exhibition information and described historical operation information to described prediction service end, train forecast model for described prediction service end by following steps: the extend information obtaining described multiple terminal use; According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
In certain embodiments, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
5th aspect, present invention also provides a kind of system of information pushing, and described system comprises terminal, prediction service end, application service end; Described application service end, is configured for the user ID from described terminal acquisition terminal use and sends to prediction service end; Described prediction service end, is configured for the user ID receiving the terminal use that described application service end sends; Retrieve the extend information of described terminal use according to described user ID, wherein, described extend information obtains from terminal; Based on the forecast model of described extend information and training in advance to each bar information generation forecast to be presented value; Described predicted value is returned to described application service end, and wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Described application service end, is also configured for each predicted value receiving described prediction service end and return; Ranking results based on each predicted value is chosen at least one information to be presented and is sent to described terminal; Described terminal, is configured at least one information pushing to be presented of described application service end transmission to described terminal use.
The method and apparatus of the information pushing that the application provides, by the user ID of application service end to prediction service end transmitting terminal user, retrieved the extend information of terminal use according to user ID by prediction service end, and based on extend information and forecast model, application service end is sent to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating, then application service end group chooses at least one information pushing to be presented to described terminal use in the ranking results of each predicted value, thus push different information according to the difference of extend information to different terminals user, achieve and be imbued with information pushing targetedly.
Accompanying drawing explanation
By reading the detailed description to non-limiting example done with reference to the following drawings, the other features, objects and advantages of the application will become more obvious:
Fig. 1 shows the exemplary system architecture can applying the embodiment of the present application;
Fig. 2 is the flow chart of an embodiment of the method for information pushing according to the application;
Fig. 3 is the effect schematic diagram of another embodiment of the method for information pushing according to the application;
Fig. 4 is the schematic diagram of an application scenarios of the method for a kind of information pushing according to the application;
Fig. 5 is the structure chart of an embodiment of the device of information pushing according to the application;
Fig. 6 is the structural representation of another embodiment of the device of information pushing according to the application;
Fig. 7 is the structural representation of the computer system be suitable for for the terminal equipment or server realizing the embodiment of the present application.
Embodiment
Below in conjunction with drawings and Examples, the application is described in further detail.Be understandable that, specific embodiment described herein is only for explaining related invention, but not the restriction to this invention.It also should be noted that, for convenience of description, in accompanying drawing, illustrate only the part relevant to Invention.
It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.Below with reference to the accompanying drawings and describe the application in detail in conjunction with the embodiments.
Fig. 1 shows the exemplary system architecture 100 can applying the embodiment of the present application.
As shown in Figure 1, system architecture 100 can comprise terminal equipment 101,102, network 103 and first server 104 (such as predicting service end) and second server 105 (such as application service end).Network 103 in order to terminal equipment 101,102, the medium of communication link is provided between first server 104 and second server 105.Network 103 can comprise various connection type, such as wired, wireless communication link or fiber optic cables etc.
It is mutual that terminal equipment 101,102 can pass through network 103 and first server 104 or second server 105, to receive or to send message etc.Terminal equipment 101,102 can be provided with the application of various telecommunication customer end, such as browser application, the application of shopping class, searching class application, map class application, social platform application, mailbox client, JICQ etc.
Terminal equipment 101, 102 can be support browser application, the various electronic equipments that shopping class application etc. is mounted thereon, include but not limited to smart mobile phone, intelligent watch, panel computer, personal digital assistant, E-book reader, MP3 player (MovingPictureExpertsGroupAudioLayerIII, dynamic image expert compression standard audio frequency aspect 3), MP4 (MovingPictureExpertsGroupAudioLayerIV, dynamic image expert compression standard audio frequency aspect 4) player, pocket computer on knee and desktop computer etc.
First server 104 and second server 105 can be to provide the server of various service.Such as first server 104 can be the background server etc. that browser application, searching class application, map class application etc. to terminal equipment 101,102 provide support; Second server 105 can be the background server etc. provided support to the shopping class application etc. of terminal equipment 101,102.The process such as server can store the data received, generation, and result is fed back to terminal equipment.
It should be noted that, the method for the information pushing that the embodiment of the present application provides can be performed by first server 104 and second server 105.Such as: first server 104 can obtain user ID and corresponding extend information, as search characteristics, access characteristic, position feature etc. from terminal equipment 101,102; Second server 105 can obtain user ID and the historical operation information etc. to the history exhibition information that second server 105 provides from terminal equipment 101,102; Then the user ID of the terminal use of acquisition, historical operation information and history exhibition information can be uploaded to first server 104 by second server 105, the extend information of the information uploaded according to second server 105 by first server 104 and the terminal use of acquisition trains forecast model, to predict operation (the such as click) information of terminal use to the information to be pushed that second server 105 provides; Then the extend information that the user ID that can upload according to second server 105 of first server 104 obtains terminal use is made prediction and will be predicted the outcome and returns to second server 105, by second server 105 according to predicting the outcome to terminal equipment 101,102 pushed information.Be appreciated that, first server 104 can be pushed information set to predicting the outcome of returning of second server 105, also can be predicted value or the ranking results that terminal use treats the possibility of the operation of exhibition information, now, choose corresponding information pushing to be presented to terminal use by second server 105 based on this ranking results, the application does not limit this.
Should be appreciated that, the number of the terminal equipment in Fig. 1, network and server is only schematic.According to realizing needs, the terminal equipment of arbitrary number, network and server can be had.
Please refer to Fig. 2, it illustrates the flow process 200 of an embodiment of the method for information pushing.The method of this information pushing is applied particularly in the electronic equipment (first server 104 of such as Fig. 1) with certain operational capability.For the ease of understanding, in the present embodiment, the cloud server terminal can collecting large data (BigData) in conjunction with the method is applied as prediction service end and illustrates.This flow process 200 comprises the following steps:
Step 201, receives the user ID of the terminal use that application service end sends.
In the present embodiment, first cloud server terminal can receive the user ID of the terminal use that application service end sends.Wherein, application service end can be the application service end (second server 105 such as shown in Fig. 1) for terminal applies provides support.Cloud server terminal can obtain the user ID of terminal use by wired connection mode or radio connection from application service end.Above-mentioned radio connection includes but not limited to 3G/4G connection, WiFi connection, bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultrawideband) connection and other radio connection developed known or future now.
Wherein, user ID is the character string for identifying user identity, such as can include but not limited to following at least one: the user name used when user connects application service end by terminal equipment, the mobile device international identity code (InternationalMobileEquipmentIdentity of terminal equipment, IMEI), the Internet protocol address (InternetProtocolAddress of terminal equipment accessing Internet, IP address), the media interviews of terminal equipment control (MediaAccessControl, MAC) address etc.
In some optional implementations of the present embodiment, application service end, except the user ID to cloud server terminal transmitting terminal user, can also send the information such as log-on message (such as age), current time, weather when user registers to application service end.
Step 202, retrieves the extend information of terminal use according to above-mentioned user ID.
In the present embodiment, cloud server terminal then can retrieve corresponding terminal use according to above-mentioned user ID, and obtains the extend information of terminal use.Here, extend information can include but not limited to following at least one item: retrieval character (such as term), access characteristic (such as the network address of institute's accession page), position feature etc.Cloud server terminal can gather the various information of all terminal uses that can collect in advance, such as various user ID and extend information.
In the various information of the terminal use that cloud server terminal gathers, the user ID of a corresponding multiple different representation of terminal use's possibility, when wherein any one user ID is identical with the user ID that application service end sends, can determine that terminal use representated by the user ID that application service end sends and this terminal use representated by any one user ID are same terminal use, cloud server terminal can retrieve the extend information of this terminal use.
Step 203, based on the forecast model of above-mentioned extend information and training in advance to each bar information generation forecast to be presented value.
In the present embodiment, cloud server terminal then can process to above-mentioned extend information the Prediction Parameters data obtained needed for forecast model, and according to Prediction Parameters data by forecast model to each bar information to be pushed generation forecast value.
Wherein, information to be presented can be the information that application service end is shown for the terminal applies supported to it.Such as, when terminal applies is applied for making a reservation, information to be presented can be the Business Information and/or dish information of serving the meals.Information to be presented can be sent to cloud server terminal in advance by application service end, and also can send to cloud server terminal together with user ID, the application does not limit this.
Here, predicted value can comprise the probable value that terminal use carries out for each bar information to be presented operating.The operation that terminal use treats exhibition information can be clicking operation, buy operation etc.For example, such as this terminal applies is application of making a reservation, and terminal use can carry out by the same businessman that serves the meals of the terminal applies of client the operation browsing, click or buy vegetable.Wherein, when terminal use opens a terminal the application page, the page presentation of the terminal applies information of the businessman that serves the meals, application service end can determine that the information of user to the businessman that serves the meals is browsed, and namely number of visits can represent with displaying number of times.Application service end may need to predict that terminal use is to the following at least one item in the above operation of this businessman that serves the meals: clicking rate (as number of clicks with show the ratio of number of times), buying rate (as Successful Transaction number of times and the ratio showing number of times) or conversion ratio (ratio as Successful Transaction number of times and number of clicks) etc., then correspondingly, predicted value can be the estimated value to clicking rate, buying rate or conversion ratio, also can be a certain terminal use determined to the click probability of this businessman that serves the meals, purchase probability or the probability that can buy after clicking, etc.The operation that terminal use carries out for exhibition information and the probable value carrying out operating can to a certain degree reflecting the preference of terminal use to exhibition information.
Forecast model can be for using at least one in the user ID obtained from application service end, information to be presented and the extend information that retrieves as input, and export the Mathematical Modeling of terminal use corresponding to user ID for the predicted value of each bar information to be presented.The historical operation information that cloud server terminal can be carried out from application service end acquisition history exhibition information, information to be presented and multiple terminal use for described history exhibition information, then the extend information obtaining them is represented according to the user of multiple terminal use, then according to information to be presented, history exhibition information, historical operation information and extend information training forecast model, such as from these information, extract user characteristics, then set up forecast model by known algorithm such as such as sorting algorithm, regression algorithm etc.For multivariate regression models, cloud server terminal can from one group of sample data, determine the relationship between each user characteristics and various operation, then various statistical test is carried out to the credibility of these relational expressions, and the impact finding out which user characteristics from all multi-user features of a certain operation of impact is remarkable, the impact of which user characteristics is not remarkable, then according to above-mentioned relational expression, the value of the probability of a certain operation is predicted according to the value of one or several user characteristics (be used for the value of characterizing consumer feature on the impact of operation information), and provide the levels of precision of this prediction.
In some optional implementations of the present embodiment, training pattern can be carried out as follows:
First, cloud server terminal can extract user characteristics respectively from the extend information of multiple terminal use.Such as, if extend information comprises search characteristics, user characteristics at least can comprise search word, can also comprise and use each search word to carry out the searching times etc. searched for; If extend information comprises access characteristic, user characteristics at least can comprise the network address of institute's accession page, can also comprise the number of times etc. of accessing each network address; If extend information comprises position feature, user characteristics can comprise user's registration terminal application time position coordinates or location name, etc.Alternatively, cloud server terminal can carry out the extraction of user characteristics according to the extend information of a nearest time period (as in three months).
Then, cloud server terminal the historical operation to each history exhibition information can set up corresponding relation according to extracted user characteristics and terminal use, to generate the contribution coefficient of each user characteristics for operation information by the study of machine end.Wherein, contribution coefficient can be used to the value of characterizing consumer feature on the impact of a certain operation information of generation.Be appreciated that, exemplarily, suppose that user characteristics comprises search word and position, the predicted value generated is needed to be the buying rate that terminal use treats exhibition information, if terminal use after having carried out searching within more short time (as in one hour) have purchased the commodity searched for, the contribution coefficient of search word is larger, the number of times using same search word to carry out searching for is more, single search is less for the impact producing the result bought, and contribution coefficient is less; If terminal use selects the number of times in the dining room of commercial circle, place more when certain position, the contribution coefficient of position feature is larger, etc.What deserves to be explained is, when predicting, every user characteristics can also have importance degree coefficient, such as search word, the number of times using a search word to carry out searching for is more, importance degree coefficient can be larger, and the time gap current time using a search word to carry out searching for is nearer, and importance degree coefficient can be larger.
Finally, the historical operation information that cloud server terminal can be carried out for history exhibition information according to user characteristics, contribution coefficient and terminal use, set up the dependence of operation and user characteristics, and by adjustment contribution coefficient, thus generate the forecast model that the operation information to terminal use is predicted based on user characteristics and contribution coefficient.When extend information comprises search characteristics, access characteristic and position feature, user characteristics can comprise search word, the network address of institute's accession page and position, and a kind of forecast model of generation can be: Y
i=β
1× i
1+ β
2× i
2+ β
3× i
3; Wherein, Y
ithe predicted value of the operation information to a certain information to be presented can be represented, β
1the contribution coefficient of the distance of the current location of terminal use and this trade company (as the trade company that serves the meals) indicated by information to be presented can be represented, i
1can represent the distance of the current location of terminal use and this trade company (as the trade company that serves the meals) indicated by information to be presented importance degree coefficient (as nearer in distance, i
1larger), β
2the contribution coefficient of the single search of search word can be represented, i
2can represent the importance degree coefficient of search word, the importance degree coefficient of search word can be directly proportional to the number of times using this search word to carry out searching for, β
3the contribution coefficient of the single reference to the page can be represented, i
3can the importance degree coefficient of representation page, the importance degree coefficient of the page can be directly proportional to the number of times of this page of access, etc.When carrying out model training, Y
iand i
1, i
2, i
3known, can solve and obtain β
1, β
2, β
3; When predicting, i can be obtained by the computation rule of importance degree coefficient
1, i
2, i
3, and solved the β obtained
1, β
2, β
3, obtain predicted value Y
i.What deserves to be explained is, search word can have multiple, therefore, for the forecast model that cloud server terminal is set up, usually also has accuracy rate.Accuracy rate can be controlled by error term, as: Y
i=β
1× i
1+ β
2× i
2+ β
3× i
3+ e; Wherein, e is error term, and error term can concentrate the predicted value predicted by forecast model to compare acquisition with the actual actual value produced in a certain operation information according to test samples.
In some optional implementations of the present embodiment, the terminal applies that application server is supported is the application of shopping class, and application service end also sends the pricing information of history exhibition information as one of historical information of training forecast model to cloud server terminal.Except user characteristics can also comprise the price feature and/or advertisement bid feature waiting to push exhibition information in the parameter of training forecast model.Now, Cloud Server can be analyzed simultaneously wait to push the price feature of exhibition information and/or advertisement bid (service of a certain exhibition information of this trade company of displaying that such as trade company provides for application service end the expense of paying, such as 1 yuan/1000 times) feature to the impact of the operation of terminal use.Such as, some terminal uses like clicking the high exhibition information of price, then the contribution degree that the exhibition information that price is higher clicks this exhibition information to this terminal use is larger; Again such as, the exhibition information that advertisement bid is higher, its importance degree coefficient is larger.
In some optional implementations of the present embodiment, for the terminal use that cloud server terminal cannot match corresponding user ID or retrieve less than extend information, cloud server terminal (can be bid higher according to the bid information generation forecast value of exhibition information, predicted value is higher) or get predicted value according to the overall probability of the historical operation of each information to be presented, average as predicted value after also can predicting each terminal use.
In some optional implementations of the present embodiment, when cloud server terminal receives the model modification request of application service end transmission, according to new Data Update model.Wherein, model modification request can comprise the historical operation information carried out for history exhibition information for the history exhibition information of current time, information to be presented and multiple terminal use.In some implementations, application service end can by the cycle (as one day) to cloud server terminal transmission pattern update request.
In some optional implementations of the present embodiment, this step can be comprised by the process of forecast model generation forecast value: from the extend information of terminal use, extract user characteristics; Calculate the importance degree coefficient of each user characteristics; Based on the predicted value of the importance degree coefficient of each user characteristics and the operation information of contribution coefficient computing terminal user.Such as, the product summation that the importance degree coefficient of each user characteristics can be multiplied with contribution coefficient by cloud server terminal, as predicted value.
Step 204, returns to application service end by above-mentioned predicted value.
In the present embodiment, the predicted value obtained by forecast model then can be returned to application service end by cloud server terminal.Application service termination can choose at least one information pushing to be presented to terminal use based on the ranking results of predicted value (as from big to small) after receiving the predicted value that cloud server terminal returns.Application service end can choose the information pushing to be presented of the forward predetermined number of sequence to terminal use, and also whole information pushing to be presented can be shown according to ranking results to terminal use, the application does not limit this.Wherein, the sequence of predicted value can be completed by cloud server terminal, also can be completed by application service end.
The embodiment that composition graphs 2 describes, the historical operation information that history exhibition information, information to be presented and multiple terminal use that cloud server terminal is sent according to application service end carry out for history exhibition information, retrieve the extend information of terminal use, according to extend information generation forecast model, and carry out according to current extensions information when predicting, improve the specific aim of pushed information.
Please refer to Fig. 3, it illustrates the flow process 300 of another embodiment of the method for information pushing.The method of this information pushing is applied particularly in the electronic equipment (application server 105 of such as Fig. 1) with certain operational capability.For the ease of understanding, in the present embodiment, be that shopping class is applied in the application service end provided support and illustrated in conjunction with this electronic equipment.This flow process 300 comprises the following steps:
Step 301, to the user ID of prediction service end transmitting terminal user.
In the present embodiment, application service end can obtain the user ID of terminal use from least one terminal equipment, and sends to prediction service end (as the first server 104 in Fig. 1, can as cloud server terminal).Here, terminal equipment can be the client device running the terminal applies that application service end is supported, the terminal equipment 101,102 of such as Fig. 1 terminal.Application service end can obtain the user ID of terminal use from terminal equipment by wired connection mode or radio connection, also can by wired connection mode or the radio connection user ID to prediction service end transmitting terminal user.
Wherein, user ID is the character string for identifying user identity, such as, can include but not limited to following at least one: the user name used when user connects application service end by terminal equipment, the mobile device international identity code IMEI, the IP address of terminal equipment accessing Internet, the MAC Address of terminal equipment etc. of terminal equipment.
In the present embodiment, after prediction service end receives the user ID of application service end transmission, the extend information of terminal use can be retrieved according to described user ID, then based on extend information and preset forecast model to every bar information generation forecast to be presented value, then each predicted value is returned.Wherein, described extend information is by predicting that service end obtains from terminal.
Step 302, receives each predicted value that prediction service end returns.
In the present embodiment, application service end can from prediction service end receive prediction service end by above-mentioned user ID obtain the extend information (such as search characteristics, position feature) of terminal use and generation, terminal use is to the predicted value of every bar information to be presented.Here, predicted value can comprise the probable value that terminal use carries out for each bar information to be presented operating.The operation that terminal use treats exhibition information can be clicking operation, buy operation etc.
Prediction service end can retrieve corresponding terminal use according to above-mentioned user ID, and obtains the extend information of terminal use, and this extend information such as can include but not limited to following at least one item: retrieval character, access characteristic, position feature etc.; Then, prediction service end using extend information as input, and can export terminal use corresponding to user ID for a certain evolutionary operator probability value of every bar information and executing to be presented by the forecast model of training in advance.Here for item can determine according to the request of application service end to model training, such as the application of shopping class, application service end may need to predict that terminal use is to the following at least one item in the above operation of this businessman that serves the meals: the clicking rate, buying rate, conversion ratio etc. of every bar information to be presented.Wherein, information to be presented can be sent when prediction service end sends forecast model by application service end, and also can send when sending user ID, the application does not limit this.
In some optional implementations of the present embodiment, application service end sends user ID with before generation forecast value to prediction service end, the solicited message of generation forecast model can also be sent, for prediction service end according to this solicited message training forecast model to prediction service end.Particularly, application service end can obtain the historical operation information that multiple terminal use carries out for history exhibition information, history exhibition information, historical operation information are sent to prediction service end together with information to be presented, for prediction service end training forecast model.Wherein, prediction service end can set up forecast model by known algorithm such as such as sorting algorithm, regression algorithm etc., and concrete training process is consistent with hereinbefore described, does not repeat them here.
Step 303, the ranking results based on each predicted value chooses at least one information pushing information to be presented to terminal use.
In the present embodiment, application service termination can choose at least one information pushing to be presented to terminal use based on the ranking results of predicted value (as from big to small) after receiving the predicted value predicting that service end returns.Application service end can choose the information pushing to be presented of the forward predetermined number of sequence to terminal use, and also whole information pushing to be presented can be shown according to ranking results to terminal use, the application does not limit this.Wherein, the sequence of predicted value can be completed by cloud server terminal, also can be completed by application service end.
The embodiment that composition graphs 3 describes, application service end, by advance to the historical operation information that prediction service end transmission history exhibition information, information to be presented and multiple terminal use carry out for history exhibition information, trains forecast model for prediction service end.After model training completes, application service end, by obtaining terminal use to the predicted value of every bar information to be presented to the user ID of prediction service end transmitting terminal user, has saved local resource.Simultaneously, the extend information of terminal use is make use of during prediction service end generation forecast value, therefore, at least one information to be presented that application service end group is chosen in the ranking results of these predicted values, other network datas of terminal use are merged, by the information pushing to be presented choosing out like this to terminal use, improve the specific aim of information pushing.
Refer to Fig. 4, it illustrates an application scenarios of the information-pushing method of the application.As shown in Figure 4, in the information-pushing method of the application, prediction service end can be cloud server terminal 430, and terminal use can connect application service end 420 and cloud server terminal 430 by the corresponding terminal application in terminal 410.Terminal 410 can be installed the terminal applies (as shopping class application etc.) that application service end 420 is supported, the various terminal applies (as searching class application, map application etc.) that cloud server terminal 430 is supported can also be installed.Wherein, cloud server terminal 430 can one straight through the various terminal applies supported of cloud server terminal 430 that step 4000 sense terminals 410 is installed, to obtain the operation information that terminal use is undertaken by terminal 410, and then preserve as the extend information of terminal use.Be appreciated that the extend information of terminal use can real-time update when terminal use has carried out new operation.
In the application scenarios of Fig. 4, mainly comprise two stages, wherein, step 4001-step 4003 is the forecast model training stage, and step 401-step 405 is the information pushing stage.Wherein, the forecast model training stage can carry out in advance, can also be undertaken by cycle (as one week or one month).The terminal applies that the information pushing stage can be supported by terminal 410 operational applications service end 420 by terminal use after the forecast model training stage terminates and triggering.In forecast model training stage and information pushing stage, cloud server terminal can transfer the expanded application of the terminal use obtained in step 4000.
In the forecast model training stage, first as shown in step 4001, application service end 420 sends to cloud server terminal 430 historical operation information and information to be presented that history exhibition information, multiple terminal use carry out for history exhibition information; Then, as shown in step 4002, cloud server terminal can obtain the extend information of this multiple terminal use, and user characteristics is extracted respectively from these extend informations, set up the dependence of user characteristics and operation (as clicked, buying), thus solve contribution coefficient (namely user characteristics is on the value of the impact of a certain operation information of generation), set up forecast model; Then, in step 4003, cloud server terminal 430 can provide the prediction interface of forecast model (as web service interface to application service end 420, WebServiceAPI), for in the information pushing stage, application service end 420 sends predictions request by this interface to cloud server terminal 430, and cloud server terminal 430 returns predicted value to application service end 420.
In the information pushing stage, first, as shown in step 401, terminal use by terminal 410 initiated connection request or inquiry request (as access application service end 420 the home page request of terminal applies supported); Then, in step 402, application service end 420 obtains the user ID of terminal use, and sends to cloud server terminal 430; Then, in step 403, cloud server terminal 430 retrieves the extend information of the terminal use obtained in step 4000 according to the user ID of terminal use, and using the input of this extend information as forecast model, calculate the predicted value (predicted value of such as clicking rate) of this terminal use to each information to be presented by forecast model; Then, in step 404, cloud server terminal 430 feeds back the predicted value obtained to application service end 420; Then, in step 405, application service end 420, based on the ranking results of predicted value, chooses one or more information to be presented, or by information to be presented according to after the ranking results sequence of predicted value, is sent to terminal 410 to be pushed to terminal use.
In the application scenarios shown in Fig. 4, if in step 403, the extend information of the terminal use that cloud server terminal 430 retrieves according to the user ID of terminal use comprises the retrieving information of nearest (before 10 minutes): how term " selects tent ", in the predicted value that then forecast model calculates, the to be presented information relevant to " tent " can have larger predicted value, and then, in step 405, application service end 420 based on predicted value ranking results can by the to be presented information arrangement relevant to " tent " at the most forward location push to terminal use, thus achieve the information pushing targetedly of terminal applies.
With further reference to Fig. 5, it illustrates the structural representation of an embodiment of the information push-delivery apparatus according to the application.As shown in Figure 5, device 500 can comprise receiver module 501, retrieval module 502, generation module 503, return module 504.Wherein, receiver module 501 can be configured for the user ID receiving the terminal use that application service end sends; Retrieval module 502 can be configured for the extend information retrieving terminal use according to user ID, and wherein, described extend information obtains from terminal; Generation module 503 can be configured for based on extend information and forecast model to each bar information generation forecast to be presented value, and wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Return module 504 can be configured for predicted value is returned to application service end, choose at least one information pushing to be presented to terminal use for application service end group in the ranking results of each predicted value.
The all modules recorded in device 500 are corresponding with each step in the method described with reference to figure 2.Thus, the operation that describes for the method for information pushing described in conjunction with Figure 2 and the feature module that is equally applicable to device 500 and wherein comprises, does not repeat them here above.
With further reference to Fig. 6, it illustrates the structural representation of an embodiment of the information push-delivery apparatus according to the application.As shown in Figure 6, device 600 can comprise sending module 601, receiver module 602, pushing module 603.Wherein, sending module 601 can be configured for the user ID to prediction service end transmitting terminal user, generates the predicted value of information to be presented: the extend information retrieving terminal use according to user ID for prediction service end for each user ID according to following steps; Based on extend information and preset forecast model to every bar information generation forecast to be presented value, wherein, extend information is by predicting that service end obtains from terminal, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Receiver module 602 can be configured for each predicted value receiving prediction service end and return; The ranking results that pushing module 603 can be configured for based on each predicted value chooses at least one information pushing to be presented to terminal use.
The all modules recorded in device 600 are corresponding with each step in the method described with reference to figure 3.Thus, the operation that describes for the method for information pushing described in conjunction with Figure 3 and the feature module that is equally applicable to device 600 and wherein comprises, does not repeat them here above.
It will be appreciated by those skilled in the art that, the device 500 of above-mentioned information pushing and device 600 also comprise some other known features, such as processor, memory etc., in order to unnecessarily fuzzy embodiment of the present disclosure, these known structures are not shown in Fig. 5, Fig. 6.
In addition, present invention also provides a kind of system of information pushing, described system comprises terminal, prediction service end, application service end.Wherein, prediction service end can comprise the device 500 shown in Fig. 5, and application service end can comprise the device 600 shown in Fig. 6.Application service end can obtain the user ID of terminal use from terminal and send to prediction service end; Prediction service end can receive the user ID of the terminal use that application service end sends, the extend information of terminal use is retrieved according to user ID, wherein, extend information obtains from terminal, and based on extend information and forecast model to each bar information generation forecast to be presented value, then predicted value is returned to application service end; Application service end can also receive each predicted value of returning of prediction service end, and chooses at least one information to be presented based on the ranking results of each predicted value and be sent to terminal; At least one information pushing to be presented that described application service end can send by terminal is to described terminal use.
Below with reference to Fig. 7, it illustrates the structural representation of the computer system 700 of terminal equipment or the server be suitable for for realizing the embodiment of the present application.
As shown in Figure 7, computer system 700 comprises CPU (CPU) 701, and it or can be loaded into the program random access storage device (RAM) 703 from storage area 708 and perform various suitable action and process according to the program be stored in read-only memory (ROM) 702.In RAM703, also store system 700 and operate required various program and data.CPU701, ROM702 and RAM703 are connected with each other by bus 704.I/O (I/O) interface 705 is also connected to bus 704.
I/O interface 705 is connected to: the importation 706 comprising keyboard, mouse etc. with lower component; Comprise the output 707 of such as cathode ray tube (CRT), liquid crystal display (LCD) etc. and loud speaker etc.; Comprise the storage area 708 of hard disk etc.; And comprise the communications portion 709 of network interface unit of such as LAN card, modulator-demodulator etc.Communications portion 709 is via the network executive communication process of such as internet.Driver 710 is also connected to I/O interface 705 as required.Detachable media 711, such as disk, CD, magneto optical disk, semiconductor memory etc., be arranged on driver 710 as required, so that the computer program read from it is mounted into storage area 708 as required.
Especially, according to embodiment of the present disclosure, the process that reference flow sheet describes above may be implemented as computer software programs.Such as, embodiment of the present disclosure comprises a kind of computer program, and it comprises the computer program visibly comprised on a machine-readable medium, and described computer program comprises the program code for the method shown in flowchart.In such embodiments, this computer program can be downloaded and installed from network by communications portion 709, and/or is mounted from detachable media 711.
Flow chart in accompanying drawing and block diagram, illustrate according to the architectural framework in the cards of the system of the various embodiment of the application, method and computer program product, function and operation.In this, each square frame in flow chart or block diagram can represent a part for module, program segment or a code, and a part for described module, program segment or code comprises one or more executable instruction for realizing the logic function specified.Also it should be noted that at some as in the realization of replacing, the function marked in square frame also can be different from occurring in sequence of marking in accompanying drawing.Such as, in fact the square frame that two adjoining lands represent can perform substantially concurrently, and they also can perform by contrary order sometimes, and this determines according to involved function.Also it should be noted that, the combination of the square frame in each square frame in block diagram and/or flow chart and block diagram and/or flow chart, can realize by the special hardware based system of the function put rules into practice or operation, or can realize with the combination of specialized hardware and computer instruction.
Unit involved in the embodiment of the present application can be realized by the mode of software, also can be realized by the mode of hardware.Described module also can be arranged within a processor, such as, can be described as: a kind of processor comprises receiver module, retrieval module, generation module and return module.Wherein, the title of these modules does not form the restriction to this module itself under certain conditions, and such as, receiver module can also be described to " being configured for the module of the user ID receiving the terminal use that application service end sends ".
As another aspect, present invention also provides a kind of non-volatile computer storage medium, this non-volatile computer storage medium can be the non-volatile computer storage medium comprised in device described in above-described embodiment; Also can be individualism, be unkitted the non-volatile computer storage medium allocated in terminal.In some implementations, above-mentioned non-volatile computer storage medium stores one or more program, when one or more program described is performed by an equipment, makes described equipment: the user ID receiving the terminal use that application service end sends; Retrieve the extend information of described terminal use according to described user ID, wherein, described extend information obtains from terminal; Based on described extend information and forecast model to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Described predicted value is returned to described application service end, chooses at least one information pushing to be presented to described terminal use for described application service end group in the ranking results of each predicted value.During in spirit, some realize, above-mentioned non-volatile computer storage medium stores one or more program, when one or more program described is performed by an equipment, make described equipment: to the user ID of prediction service end transmitting terminal user, generate the predicted value of information to be presented according to following steps for each user ID for prediction service end: the extend information retrieving described terminal use according to described user ID; Based on described extend information and preset forecast model to every bar information generation forecast to be presented value, wherein, described extend information is obtained from terminal by described prediction service end, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating; Receive each predicted value that described prediction service end returns; Ranking results based on each predicted value chooses at least one information pushing to be presented to described terminal use.
More than describe and be only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art are to be understood that, invention scope involved in the application, be not limited to the technical scheme of the particular combination of above-mentioned technical characteristic, also should be encompassed in when not departing from described inventive concept, other technical scheme of being carried out combination in any by above-mentioned technical characteristic or its equivalent feature and being formed simultaneously.The technical characteristic that such as, disclosed in above-mentioned feature and the application (but being not limited to) has similar functions is replaced mutually and the technical scheme formed.
Claims (17)
1. a method for information pushing, is characterized in that, described method comprises:
Receive the user ID of the terminal use that application service end sends;
Retrieve the extend information of described terminal use according to described user ID, wherein, described extend information obtains from terminal;
Based on the forecast model of described extend information and training in advance to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating;
Described predicted value is returned to described application service end, chooses at least one information pushing to be presented to described terminal use for described application service end group in the ranking results of each predicted value.
2. method according to claim 1, is characterized in that, described method also comprises:
Receive the historical operation information that the history exhibition information of described application service end transmission, information to be presented and multiple terminal use carry out for described history exhibition information;
Obtain the extend information of described multiple terminal use;
According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
3. method according to claim 2, is characterized in that, described according to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model comprise:
User characteristics is extracted respectively from the extend information of described multiple terminal use;
According to described user characteristics and described historical operation information, generate the contribution coefficient of user characteristics for historical operation information;
Generate the forecast model that the operation information to terminal use is predicted based on described user characteristics and described contribution coefficient.
4. method according to claim 3, is characterized in that, describedly comprises each bar information generation forecast to be presented value based on described extend information and described forecast model:
User characteristics is extracted from described extend information;
Calculate the importance degree coefficient of each user characteristics;
Based on the predicted value of the described importance degree coefficient of each user characteristics and the operation information of described contribution coefficient computing terminal user.
5., according to described method arbitrary in claim 1-4, it is characterized in that, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
6. a method for information pushing, is characterized in that, described method comprises:
To the user ID of prediction service end transmitting terminal user, generate the predicted value of information to be presented according to following steps for each user ID for prediction service end: the extend information retrieving described terminal use according to described user ID; Based on the forecast model of described extend information and training in advance to every bar information generation forecast to be presented value, wherein, described extend information is obtained from terminal by described prediction service end, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating;
Receive each predicted value that described prediction service end returns;
Ranking results based on each predicted value chooses at least one information pushing to be presented to described terminal use.
7. method according to claim 6, is characterized in that, described method also comprises:
Obtain the historical operation information that multiple terminal use carries out for history exhibition information;
Send described information to be presented, described history exhibition information and described historical operation information to described prediction service end, train forecast model for described prediction service end by following steps: the extend information obtaining described multiple terminal use; According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
8. the method according to claim 6 or 7, is characterized in that, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
9. a device for information pushing, is characterized in that, described device comprises:
Receiver module, is configured for the user ID receiving the terminal use that application service end sends;
Retrieval module, is configured for the extend information retrieving described terminal use according to described user ID, and wherein, described extend information obtains from terminal;
Generation module, be configured for forecast model based on described extend information and training in advance to each bar information generation forecast to be presented value, wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating;
Return module, be configured for and described predicted value is returned to described application service end, choose at least one information pushing to be presented to described terminal use for described application service end group in the ranking results of each predicted value.
10. device according to claim 9, is characterized in that, described device also comprises:
Model information receiver module, is configured for the historical operation information that the history exhibition information receiving described application service end and send, information to be presented and multiple terminal use carry out for described history exhibition information;
Acquisition module, is configured for the extend information obtaining described multiple terminal use;
Model training module, is configured for according to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
11. devices according to claim 10, is characterized in that, described model training module comprises:
Feature extraction unit, is configured for and extracts user characteristics respectively from the extend information of described multiple terminal use;
Contribution coefficient generation unit, is configured for according to described user characteristics and described historical operation information, generates the contribution coefficient of user characteristics for historical operation information;
Forecast model generation unit, is configured for and generates the forecast model that the operation information to terminal use is predicted based on described user characteristics and described contribution coefficient.
12. devices according to claim 11, is characterized in that, described generation module comprises:
Extraction unit, is configured for and extracts user characteristics from described extend information;
Coefficient calculation unit, is configured for the importance degree coefficient calculating each user characteristics;
Predictor calculation unit, is configured for the predicted value based on the described importance degree coefficient of each user characteristics and the operation information of described contribution coefficient computing terminal user.
13. according to described device arbitrary in claim 9-12, and it is characterized in that, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
The device of 14. 1 kinds of information pushings, is characterized in that, described device comprises:
Sending module, be configured for the user ID to prediction service end transmitting terminal user, generate the predicted value of information to be presented according to following steps for each user ID for prediction service end: the extend information retrieving described terminal use according to described user ID; Based on the forecast model of described extend information and training in advance to every bar information generation forecast to be presented value, wherein, described extend information is obtained from terminal by described prediction service end, and described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating;
Receiver module, is configured for each predicted value receiving described prediction service end and return;
Pushing module, the ranking results be configured for based on each predicted value chooses at least one information pushing to be presented to described terminal use.
15. devices according to claim 14, is characterized in that, described device also comprises:
Acquisition module, is configured for the historical operation information obtaining multiple terminal use and carry out for history exhibition information;
Model information sending module, be configured for and send described information to be presented, described history exhibition information and described historical operation information to described prediction service end, train forecast model for described prediction service end by following steps: the extend information obtaining described multiple terminal use; According to described information to be presented, described history exhibition information, described historical operation information and described extend information training forecast model.
16. devices according to claims 14 or 15, it is characterized in that, described extend information comprises following at least one item: search characteristics, access characteristic and position feature.
The system of 17. 1 kinds of information pushings, is characterized in that, described system comprises terminal, prediction service end, application service end;
Described application service end, is configured for the user ID from described terminal acquisition terminal use and sends to prediction service end;
Described prediction service end, is configured for the user ID receiving the terminal use that described application service end sends; Retrieve the extend information of described terminal use according to described user ID, wherein, described extend information obtains from terminal; Based on the forecast model of described extend information and training in advance to each bar information generation forecast to be presented value; Described predicted value is returned to described application service end, and wherein, described predicted value comprises the probable value that terminal use carries out for each bar information to be presented operating;
Described application service end, is also configured for each predicted value receiving described prediction service end and return; Ranking results based on each predicted value is chosen at least one information to be presented and is sent to described terminal;
Described terminal, is configured at least one information pushing to be presented of described application service end transmission to described terminal use.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510549839.5A CN105208113A (en) | 2015-08-31 | 2015-08-31 | Information pushing method and device |
PCT/CN2015/096233 WO2017035970A1 (en) | 2015-08-31 | 2015-12-03 | Information pushing method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510549839.5A CN105208113A (en) | 2015-08-31 | 2015-08-31 | Information pushing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105208113A true CN105208113A (en) | 2015-12-30 |
Family
ID=54955537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510549839.5A Pending CN105208113A (en) | 2015-08-31 | 2015-08-31 | Information pushing method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105208113A (en) |
WO (1) | WO2017035970A1 (en) |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106919692A (en) * | 2017-03-07 | 2017-07-04 | 广州优视网络科技有限公司 | A kind of method and apparatus of PUSH message |
CN106940703A (en) * | 2016-01-04 | 2017-07-11 | 腾讯科技(北京)有限公司 | Pushed information roughing sort method and device |
CN107229728A (en) * | 2017-06-05 | 2017-10-03 | 努比亚技术有限公司 | Searching method, equipment and storage medium based on neutral net |
CN107291921A (en) * | 2017-06-28 | 2017-10-24 | 北京京东尚科信息技术有限公司 | Information processing method and system |
CN107404577A (en) * | 2017-07-20 | 2017-11-28 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
CN107465741A (en) * | 2017-08-02 | 2017-12-12 | 北京小度信息科技有限公司 | Information-pushing method and device |
CN107767153A (en) * | 2016-08-16 | 2018-03-06 | 腾讯科技(北京)有限公司 | A kind of data processing method and device |
CN108287834A (en) * | 2017-01-09 | 2018-07-17 | 百度在线网络技术(北京)有限公司 | Method, apparatus and computing device for pushed information |
CN108415970A (en) * | 2018-02-08 | 2018-08-17 | 北京三快在线科技有限公司 | Retrieval result sort method, device, electronic equipment and storage medium |
CN109460826A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | For distributing the method, apparatus and model modification system of data |
CN109559158A (en) * | 2018-11-06 | 2019-04-02 | 北京奇虎科技有限公司 | Promotion message put-on method, device, electronic equipment and readable storage medium storing program for executing |
CN109636490A (en) * | 2019-01-25 | 2019-04-16 | 上海基分文化传播有限公司 | Real-time predicting method, the advertisement valuation method and system of ad conversion rates |
CN109845232A (en) * | 2017-08-24 | 2019-06-04 | 谷歌有限责任公司 | Digital assembly transmission |
CN110049079A (en) * | 2018-01-16 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Information push and model training method, device, equipment and storage medium |
CN110110210A (en) * | 2018-01-22 | 2019-08-09 | 腾讯科技(北京)有限公司 | The method and apparatus that push shows information |
CN110955835A (en) * | 2019-11-28 | 2020-04-03 | 重庆市科学技术研究院 | Sharing platform information publishing system based on big data technology |
CN111026959A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技(深圳)有限公司 | Prompt message pushing method, device and storage medium |
CN111104585A (en) * | 2018-10-25 | 2020-05-05 | 北京嘀嘀无限科技发展有限公司 | Question recommendation method and device |
CN111125502A (en) * | 2018-10-31 | 2020-05-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN111126649A (en) * | 2018-10-31 | 2020-05-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
CN111340265A (en) * | 2018-12-19 | 2020-06-26 | 北京嘀嘀无限科技发展有限公司 | Off-line intervention method and device for driver, electronic equipment and computer storage medium |
CN111381909A (en) * | 2018-12-27 | 2020-07-07 | 北京字节跳动网络技术有限公司 | Page display method and device, terminal equipment and storage medium |
CN111460270A (en) * | 2019-01-18 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
CN111506643A (en) * | 2019-01-31 | 2020-08-07 | 北京沃东天骏信息技术有限公司 | Method, device and system for generating information |
CN112068854A (en) * | 2019-06-10 | 2020-12-11 | 杭州海康威视数字技术股份有限公司 | Intelligent device algorithm updating system, intelligent device and platform server |
CN112398947A (en) * | 2020-11-18 | 2021-02-23 | 腾讯科技(深圳)有限公司 | Information pushing method, device and equipment and computer readable storage medium |
CN113032034A (en) * | 2019-12-06 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for controlling application program |
WO2021169424A1 (en) * | 2020-02-28 | 2021-09-02 | 深圳前海微众银行股份有限公司 | Online message processing method, apparatus and device, and readable storage medium |
CN113779455A (en) * | 2021-01-25 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Method and device for displaying information |
CN117150105A (en) * | 2023-10-27 | 2023-12-01 | 四川银亿科技有限公司 | Data acquisition method and acquisition platform based on webpage |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110147514B (en) * | 2017-09-08 | 2023-11-07 | 阿里巴巴集团控股有限公司 | Resource display method, device and equipment thereof |
CN110188908B (en) * | 2018-02-22 | 2024-07-19 | 北京京东尚科信息技术有限公司 | Method and device for predicting article receiving and sending modes of users |
CN108683990B (en) * | 2018-08-02 | 2021-01-12 | Oppo广东移动通信有限公司 | Electronic device, service subscription method of service area and related product |
CN110858377B (en) * | 2018-08-22 | 2024-04-05 | 阿里巴巴集团控股有限公司 | Information processing method, page display method, system and equipment |
CN112199187B (en) * | 2019-07-08 | 2024-06-18 | 北京字节跳动网络技术有限公司 | Content display method, device, electronic equipment and computer readable storage medium |
CN112214306A (en) * | 2019-07-11 | 2021-01-12 | 北京字节跳动网络技术有限公司 | Content display weight value calculation method and device, electronic equipment and computer readable storage medium |
CN111858922B (en) * | 2019-09-24 | 2024-09-24 | 北京嘀嘀无限科技发展有限公司 | Service side information query method and device, electronic equipment and storage medium |
CN110827138B (en) * | 2019-10-31 | 2022-07-05 | 北京芯盾时代科技有限公司 | Push information determining method and device |
CN113326454B (en) * | 2020-02-28 | 2024-05-24 | 北京沃东天骏信息技术有限公司 | Method and device for displaying labels |
CN112165514B (en) * | 2020-09-16 | 2023-11-03 | 中电信用服务有限公司 | System and method for determining display content |
CN112307966B (en) * | 2020-10-30 | 2023-09-05 | 京东方科技集团股份有限公司 | Event display method and device, storage medium and electronic equipment |
TWI786510B (en) * | 2021-01-08 | 2022-12-11 | 聚英企業管理顧問股份有限公司 | Familiarity analysis device for customers |
CN113111117B (en) * | 2021-05-13 | 2024-08-13 | 上海寻梦信息技术有限公司 | Method, system, equipment and storage medium for displaying destination address based on map |
CN113435197B (en) * | 2021-06-25 | 2023-01-03 | 平安国际智慧城市科技股份有限公司 | Data pushing method and device, pushing server and storage medium |
CN113726849B (en) * | 2021-07-20 | 2023-11-24 | 浙江吉利控股集团有限公司 | Sharing method, device and server for drinking wine making mode |
CN115712745B (en) * | 2023-01-09 | 2023-06-13 | 荣耀终端有限公司 | Method, system and electronic device for acquiring user annotation data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102279889A (en) * | 2011-08-29 | 2011-12-14 | 百度在线网络技术(北京)有限公司 | Question pushing method and system based on geographic information |
CN102831199A (en) * | 2012-08-07 | 2012-12-19 | 北京奇虎科技有限公司 | Method and device for establishing interest model |
CN102890689A (en) * | 2011-07-22 | 2013-01-23 | 北京百度网讯科技有限公司 | Method and system for building user interest model |
CN103294800A (en) * | 2013-05-27 | 2013-09-11 | 华为技术有限公司 | Method and device for pushing information |
US20140214537A1 (en) * | 2013-01-31 | 2014-07-31 | Samsung Electronics Co., Ltd. | User terminal and method and system for providing advertisement |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6981040B1 (en) * | 1999-12-28 | 2005-12-27 | Utopy, Inc. | Automatic, personalized online information and product services |
CN103166930B (en) * | 2011-12-15 | 2016-04-13 | 腾讯科技(深圳)有限公司 | The method and system of pushing network information |
CN103489117B (en) * | 2012-06-12 | 2015-07-01 | 深圳市腾讯计算机系统有限公司 | Method and system for information releasing |
-
2015
- 2015-08-31 CN CN201510549839.5A patent/CN105208113A/en active Pending
- 2015-12-03 WO PCT/CN2015/096233 patent/WO2017035970A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102890689A (en) * | 2011-07-22 | 2013-01-23 | 北京百度网讯科技有限公司 | Method and system for building user interest model |
CN102279889A (en) * | 2011-08-29 | 2011-12-14 | 百度在线网络技术(北京)有限公司 | Question pushing method and system based on geographic information |
CN102831199A (en) * | 2012-08-07 | 2012-12-19 | 北京奇虎科技有限公司 | Method and device for establishing interest model |
US20140214537A1 (en) * | 2013-01-31 | 2014-07-31 | Samsung Electronics Co., Ltd. | User terminal and method and system for providing advertisement |
CN103294800A (en) * | 2013-05-27 | 2013-09-11 | 华为技术有限公司 | Method and device for pushing information |
Cited By (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106940703A (en) * | 2016-01-04 | 2017-07-11 | 腾讯科技(北京)有限公司 | Pushed information roughing sort method and device |
CN106940703B (en) * | 2016-01-04 | 2020-09-11 | 腾讯科技(北京)有限公司 | Pushed information rough selection sorting method and device |
CN107767153A (en) * | 2016-08-16 | 2018-03-06 | 腾讯科技(北京)有限公司 | A kind of data processing method and device |
CN107767153B (en) * | 2016-08-16 | 2022-02-11 | 腾讯科技(北京)有限公司 | Data processing method and device |
CN108287834A (en) * | 2017-01-09 | 2018-07-17 | 百度在线网络技术(北京)有限公司 | Method, apparatus and computing device for pushed information |
CN106919692B (en) * | 2017-03-07 | 2021-02-19 | 阿里巴巴(中国)有限公司 | Method and device for pushing message |
WO2018161677A1 (en) * | 2017-03-07 | 2018-09-13 | 广州优视网络科技有限公司 | Message pushing method, apparatus, and storage medium |
CN106919692A (en) * | 2017-03-07 | 2017-07-04 | 广州优视网络科技有限公司 | A kind of method and apparatus of PUSH message |
CN107229728A (en) * | 2017-06-05 | 2017-10-03 | 努比亚技术有限公司 | Searching method, equipment and storage medium based on neutral net |
CN107291921B (en) * | 2017-06-28 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Information processing method and system |
CN107291921A (en) * | 2017-06-28 | 2017-10-24 | 北京京东尚科信息技术有限公司 | Information processing method and system |
CN107404577A (en) * | 2017-07-20 | 2017-11-28 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
CN107465741A (en) * | 2017-08-02 | 2017-12-12 | 北京小度信息科技有限公司 | Information-pushing method and device |
CN109845232B (en) * | 2017-08-24 | 2021-11-16 | 谷歌有限责任公司 | Method and computing system for digital component transmission |
CN109845232A (en) * | 2017-08-24 | 2019-06-04 | 谷歌有限责任公司 | Digital assembly transmission |
CN110049079A (en) * | 2018-01-16 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Information push and model training method, device, equipment and storage medium |
CN110110210B (en) * | 2018-01-22 | 2024-09-13 | 腾讯科技(北京)有限公司 | Method and device for pushing display information |
CN110110210A (en) * | 2018-01-22 | 2019-08-09 | 腾讯科技(北京)有限公司 | The method and apparatus that push shows information |
CN108415970A (en) * | 2018-02-08 | 2018-08-17 | 北京三快在线科技有限公司 | Retrieval result sort method, device, electronic equipment and storage medium |
CN111104585A (en) * | 2018-10-25 | 2020-05-05 | 北京嘀嘀无限科技发展有限公司 | Question recommendation method and device |
CN111104585B (en) * | 2018-10-25 | 2023-06-02 | 北京嘀嘀无限科技发展有限公司 | Question recommending method and device |
CN111125502B (en) * | 2018-10-31 | 2024-02-20 | 北京字节跳动网络技术有限公司 | Method and device for generating information |
CN111126649B (en) * | 2018-10-31 | 2023-08-11 | 北京字节跳动网络技术有限公司 | Method and device for generating information |
CN111125502A (en) * | 2018-10-31 | 2020-05-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN111126649A (en) * | 2018-10-31 | 2020-05-08 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN109460826A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | For distributing the method, apparatus and model modification system of data |
CN109559158A (en) * | 2018-11-06 | 2019-04-02 | 北京奇虎科技有限公司 | Promotion message put-on method, device, electronic equipment and readable storage medium storing program for executing |
CN111340265A (en) * | 2018-12-19 | 2020-06-26 | 北京嘀嘀无限科技发展有限公司 | Off-line intervention method and device for driver, electronic equipment and computer storage medium |
CN111381909A (en) * | 2018-12-27 | 2020-07-07 | 北京字节跳动网络技术有限公司 | Page display method and device, terminal equipment and storage medium |
CN111460270A (en) * | 2019-01-18 | 2020-07-28 | 北京字节跳动网络技术有限公司 | Information pushing method and device |
CN109636490A (en) * | 2019-01-25 | 2019-04-16 | 上海基分文化传播有限公司 | Real-time predicting method, the advertisement valuation method and system of ad conversion rates |
CN111506643A (en) * | 2019-01-31 | 2020-08-07 | 北京沃东天骏信息技术有限公司 | Method, device and system for generating information |
CN111506643B (en) * | 2019-01-31 | 2023-09-29 | 北京沃东天骏信息技术有限公司 | Method, device and system for generating information |
CN112068854A (en) * | 2019-06-10 | 2020-12-11 | 杭州海康威视数字技术股份有限公司 | Intelligent device algorithm updating system, intelligent device and platform server |
CN112068854B (en) * | 2019-06-10 | 2023-09-01 | 杭州海康威视数字技术股份有限公司 | Intelligent device algorithm updating system, intelligent device and platform server |
CN110955835A (en) * | 2019-11-28 | 2020-04-03 | 重庆市科学技术研究院 | Sharing platform information publishing system based on big data technology |
CN111026959A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技(深圳)有限公司 | Prompt message pushing method, device and storage medium |
CN111026959B (en) * | 2019-11-29 | 2024-07-05 | 腾讯科技(深圳)有限公司 | Prompt message pushing method, device and storage medium |
CN113032034A (en) * | 2019-12-06 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for controlling application program |
CN113032034B (en) * | 2019-12-06 | 2024-08-06 | 北京达佳互联信息技术有限公司 | Method, device, server and storage medium for controlling application program |
CN111222923A (en) * | 2020-01-13 | 2020-06-02 | 秒针信息技术有限公司 | Method and device for judging potential customer, electronic equipment and storage medium |
CN111222923B (en) * | 2020-01-13 | 2023-12-15 | 秒针信息技术有限公司 | Method and device for judging potential clients, electronic equipment and storage medium |
WO2021169424A1 (en) * | 2020-02-28 | 2021-09-02 | 深圳前海微众银行股份有限公司 | Online message processing method, apparatus and device, and readable storage medium |
CN112398947A (en) * | 2020-11-18 | 2021-02-23 | 腾讯科技(深圳)有限公司 | Information pushing method, device and equipment and computer readable storage medium |
CN113779455A (en) * | 2021-01-25 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Method and device for displaying information |
CN117150105B (en) * | 2023-10-27 | 2023-12-26 | 四川银亿科技有限公司 | Data acquisition method and acquisition platform based on webpage |
CN117150105A (en) * | 2023-10-27 | 2023-12-01 | 四川银亿科技有限公司 | Data acquisition method and acquisition platform based on webpage |
Also Published As
Publication number | Publication date |
---|---|
WO2017035970A1 (en) | 2017-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105208113A (en) | Information pushing method and device | |
CN105320766B (en) | Information-pushing method and device | |
CN110324414B (en) | Resource bit flow distribution method and device and electronic equipment | |
AU2016303436A1 (en) | Method and system for applying probabilistic topic models to content in a tax environment to improve user satisfaction with a question and answer customer support system | |
US20140188593A1 (en) | Selecting an advertisement for a traffic source | |
US20160210656A1 (en) | System for marketing touchpoint attribution bias correction | |
CA2944652C (en) | Inference model for traveler classification | |
CN104954410A (en) | Message pushing method, device thereof and server | |
US20170300939A1 (en) | Optimizing promotional offer mixes using predictive modeling | |
US11134359B2 (en) | Systems and methods for calibrated location prediction | |
US20220076320A1 (en) | Content recommendation method, device, and storage medium | |
CN107368907A (en) | Hotel information methods of exhibiting and device, electronic equipment, storage medium | |
CN106489165A (en) | Future, the conversion of self-application was mated with selected content item | |
CN109961198B (en) | Associated information generation method and device | |
US20140122221A1 (en) | Optimizing bidding with multiple campaign types | |
CN109697627A (en) | System and method for automatic bidding using deep neural language model | |
CN105117491A (en) | Page pushing method and device | |
CN105488205A (en) | Page generation method and page generation apparatus | |
CN104272336A (en) | List-based advertisement serving | |
CN108737486A (en) | Information-pushing method and device | |
CN112749323B (en) | Method and device for constructing user portrait | |
CN110827104A (en) | Method and device for recommending commodities to user | |
CN112348460A (en) | Resource limit adjusting method and device of cooperative task and electronic equipment | |
CN105488161A (en) | Information pushing method and apparatus | |
US9210222B2 (en) | Browser cookie analysis and targeted content delivery |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20151230 |