CN104090894A - Method for online parallel computing of recommended information, device for online parallel computing of recommended information, and server for online parallel computing of recommended information - Google Patents
Method for online parallel computing of recommended information, device for online parallel computing of recommended information, and server for online parallel computing of recommended information Download PDFInfo
- Publication number
- CN104090894A CN104090894A CN201310698031.4A CN201310698031A CN104090894A CN 104090894 A CN104090894 A CN 104090894A CN 201310698031 A CN201310698031 A CN 201310698031A CN 104090894 A CN104090894 A CN 104090894A
- Authority
- CN
- China
- Prior art keywords
- information
- recommended
- user
- real time
- historical data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of Internet, and discloses a method for online parallel computing of recommended information, a device for online parallel computing of the recommended information, and a server for online parallel computing of the recommended information. The method for online parallel computing of the recommended information comprises the following steps: obtaining an application ID and information bit IDs of a first user in a current application, and obtaining an information list corresponding to each information bit ID; obtaining real-time data corresponding to the application ID in a real-time and online manner, pulling historical data corresponding to the application ID, and carrying out parallel computing of estimated weights of information to be recommended in each information list according to the real-time data and the historical data; screening the information to be recommended in each information list according to each estimated weight of each piece of information to be recommended; determining the information to be recommended that has been screened from each information list to be the recommended information of an information bit identified by the information bit ID corresponding to each information list. The invention has the advantages that the real-time data which is obtained in a real-time and online manner and the pulled historical data are used for the parallel computing of the estimated weights of the information to be recommended, and the recommended information is determined according to the estimated weights, so that the determined recommended information is more accurate.
Description
Technical field
The present invention relates to Internet technical field, particularly a kind of method of online parallel computation recommendation information, device and server.
Background technology
Along with the high speed development of internet and perfect, than these traditional three large propagation media of newspaper, broadcast and TV, the network media becomes the grand strategy ingredient of communications media gradually because it has the powerful advantage such as real-time, dirigibility.Wherein, when information is propagated in network, circulation way, except the tradition formula of casting net is thrown in, is more that the data that adopt a kind of basis to collect are determined recommendation information, then the method that definite recommendation information is recommended.Because information adopts definite method of different recommendation informations can bring different benefits in the time propagating, therefore, need to select the more reasonably computing method of recommendation information according to actual conditions.
A kind of computing method of recommendation information are provided in correlation technique, and in the method, in the time that terminal detects that user surfs the Net, terminal is obtained this user in current application identities and at least one information bit mark making under application, and obtains user's related data.Afterwards, terminal is sent to server by the application identities getting, each information bit mark and this user's related data again.Server is according to this user's of correlation data calculation of this user concern type, and obtain each information bit and identify after corresponding information list, according to this user's concern type, the information that can throw in information list is screened, thereby the information that user is paid close attention to is defined as the information that each information bit is recommended.Wherein, user's related data is the data that get after terminal accumulates a period of time under off-line case.
Realizing in process of the present invention, inventor finds that said method at least exists following problem:
Because user's related data is the data that get after terminal accumulates a period of time under off-line case, thereby the real-time of the data that get is poor, thereby make server cannot reflect truly user's concern situation according to the definite user's of user's related data concern type, cause the mode of the information that can throw in information list being screened according to user's concern type more coarse, fineness is inadequate, thereby definite recommendation information is accurate not.
Summary of the invention
In order to solve the problem of correlation technique, the embodiment of the present invention provides a kind of method, device and server of online parallel computation recommendation information.Described technical scheme is as follows:
On the one hand, provide a kind of method of online parallel computation recommendation information, described method comprises:
Obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in described information list, comprise at least one information to be recommended;
Real-time online obtains real time data corresponding to described application identities, pull historical data corresponding to described application identities, and according at least one prediction weight of the information to be recommended in the described real time data getting and the each information list of historical data parallel computation that pulls, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
According to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
The information to be recommended filtering out in each information list is defined as to the recommendation information of the information bit that information bit that each information list is corresponding identifies.
On the other hand, provide a kind of device of online parallel computation recommendation information, described device comprises:
The first acquisition module, for obtaining first user in current application identities and at least one information bit mark making under application;
The second acquisition module, identifies corresponding information list for obtaining each information bit, comprises at least one information to be recommended in described information list;
The 3rd acquisition module, obtains real time data corresponding to described application identities for real-time online, pulls historical data corresponding to described application identities;
Computing module, at least one prediction weight of the information to be recommended of the real time data of getting described in basis and the each information list of historical data parallel computation pulling, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
Screening module, screens the information to be recommended of each information list for every kind of prediction weight according to each information to be recommended, obtains the information to be recommended filtering out in each information list;
Determination module, is defined as the recommendation information of the information bit that information bit that each information list is corresponding identifies for the information to be recommended that each information list is filtered out.
A kind of server is also provided, described server includes storer, and one or more than one program, one of them or more than one program are stored in storer, and be configured to be carried out by one or more than one processor, described one or more than one routine package are containing for carrying out the instruction of following operation:
Obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in described information list, comprise at least one information to be recommended;
Real-time online obtains real time data corresponding to described application identities, pull historical data corresponding to described application identities, and according at least one prediction weight of the information to be recommended in the described real time data getting and the each information list of historical data parallel computation that pulls, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
According to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
The information to be recommended filtering out in each information list is defined as to the recommendation information of the information bit that information bit that each information list is corresponding identifies.
The beneficial effect of the technical scheme that the embodiment of the present invention provides is:
Identify corresponding information list by obtaining each information bit, real-time online obtains current real time data corresponding to application identities making under application of user, pull historical data corresponding to application identities, make the data that get have more real-time, and according to the prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, more accurate according to the recommendation information that every kind of prediction weight of each information to be recommended is definite, and improved computing velocity.
Brief description of the drawings
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing of required use during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the method flow diagram of a kind of online parallel computation recommendation information that provides of the embodiment of the present invention one;
Fig. 2 is the method flow diagram of a kind of online parallel computation recommendation information that provides of the embodiment of the present invention two;
Fig. 3 is the schematic flow sheet of the online parallel computation recommendation information of the first that provides of the embodiment of the present invention two;
Fig. 4 is the schematic flow sheet of the online parallel computation recommendation information of the second that provides of the embodiment of the present invention two;
Fig. 5 is the schematic flow sheet of the third online parallel computation recommendation information of providing of the embodiment of the present invention two;
Fig. 6 is the apparatus structure schematic diagram of a kind of online parallel computation recommendation information that provides of the embodiment of the present invention three;
Fig. 7 is the structural representation of a kind of the 3rd acquisition module of providing of the embodiment of the present invention three;
Fig. 8 is the structural representation of a kind of server of providing of the embodiment of the present invention four.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Embodiment mono-
Because existing correlation technique is in the time determining recommendation information, the data that the user's who uses related data gets accumulate a period of time under off-line case after for terminal, therefore, cause the real-time of the data that get poor, thereby make server cannot reflect truly user's concern situation according to the definite user's of user's related data concern type, cause the mode of the information in information list being screened according to user's concern type more coarse, fineness is inadequate, thereby makes definite recommendation information accurate not.
In order to prevent above-mentioned situation, the embodiment of the present invention provides a kind of method of online parallel computation recommendation information, and the method can be applicable to server, referring to Fig. 1, take server as example as executive agent, and the method flow that the present embodiment provides comprises:
101: obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in information list, comprise at least one information to be recommended;
102: real-time online obtains real time data corresponding to application identities, pull historical data corresponding to application identities, and at least one prediction weight of information to be recommended in the real time data getting according to real-time online and the each information list of historical data parallel computation that pulls, prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
Wherein, according at least one prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, include but not limited to:
According to the prediction weight of the information to be recommended in the real time data getting and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the real time data getting and the same information list of historical data parallel computation that pulls;
Wherein, prediction weight at least comprises the one in clicking rate and probability of transaction.
Wherein, real-time online obtains real time data corresponding to application identities, pulls historical data corresponding to application identities, includes but not limited to:
Obtain the real time data of first user and pull the historical data of first user according to application identities real-time online, and the current place of definite first user group;
Obtain the real time data of each the second user in the group of the current place of first user according to application identities real-time online, and pull the historical data of each the second user in the group of the current place of first user;
According to the real time data corresponding to Real time data acquisition application identities of each second user and first user, and obtain historical data corresponding to application identities according to the historical data of each second user and first user.
Wherein, determine the current place of first user group, include but not limited to:
Determine the current place of first user group according to the historical data of first user and real time data;
Or, determine the current place of first user group according to application identities.
103: according to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
104: the recommendation information that the information to be recommended filtering out in each information list is defined as to the information bit that information bit that each information list is corresponding identifies.
As a kind of preferred embodiment, the method also comprises:
Exceed Preset Time threshold value if calculate the time of at least one prediction weight of the information to be recommended in each information list according to the real time data getting and the historical data that pulls, stop calculating operation, and obtain the prediction weight of the each information to be recommended in each information list according to current result of calculation.
The method that the present embodiment provides, identify corresponding information list by obtaining each information bit, real-time online obtains current real time data corresponding to application identities making under application of user, pull historical data corresponding to application identities, make the data that get have more real-time, and according to the prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, more accurate according to the recommendation information that every kind of prediction weight of each information to be recommended is definite, and improved computing velocity.
Embodiment bis-
The embodiment of the present invention provides a kind of method of online parallel computation recommendation information, and in conjunction with the content of above-described embodiment one, the present embodiment is example taking executive agent as server, and the method that the present embodiment is provided is illustrated.Referring to Fig. 2, the method flow that the present embodiment provides comprises:
201: obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list;
The present embodiment is not done concrete restriction to obtaining first user at current application identities under application and the obtain manner of at least one information bit mark of making, and includes but not limited to: the first user being got by terminal that server receiving terminal sends identifies application identities and at least one information bit under application current.Terminal is obtained first user and is made application identities under application and at least one information bit when mark current, the application process that can use by detecting current first user, obtains information bit mark corresponding to information bit under application identities and this application process of this application correspondence according to definite application process.Wherein, the corresponding application identities of each application process, the corresponding information bit mark of each information bit, information bit is designated at least one.For example, terminal detects that the current application process using of user is QICQ.exe, terminal is obtained the database file of application process QICQ.exe in this locality storage, from database file, obtain information bit mark corresponding to information bit under application identities and this application process that application process QICQ.exe is corresponding, as the application identities getting is QICQ_ID, gets two information bits marks and be respectively Table_ID1 and Table_ID2.
Terminal gets after the current application identities and information bit mark making under application of user, schematic flow sheet shown in Figure 3, the access distribution that the application identities getting and information bit mark is sent to server by terminal gathers layer, realize the application identities getting and information bit mark are sent to server, identified by server reception application identities and information bit.Server gets after application identities and information bit mark, can identify the information list that obtaining information bit-identify is corresponding according to information bit.Wherein, server can pre-stored each information bit identify corresponding information list in this locality, in the time of the list of needs obtaining information, can directly be identified at this locality according to information bit and retrieve and extract.Certainly, server can also adopt information list corresponding to alternate manner obtaining information bit-identify, and the present embodiment is not done concrete restriction to this.It should be noted that, in the time that server gets multiple information bit mark, need the information bit list that repeatedly obtaining information bit-identify is corresponding, get each information bit and identify and in corresponding information list, at least comprise an information to be recommended, the present embodiment is not done concrete restriction to the number of the information to be recommended comprising in information list.In addition, the information order that server can provide according to advertiser, calculates each information bit and identifies corresponding information list.For example, the information order of certain classification is sorted according to price, the information in the information order of first 100 of getting is as the information to be recommended in information list corresponding to one of them message identification.Certainly, can also adopt the list of alternate manner obtaining information, the present embodiment is not done concrete restriction yet to this.
Further, convenient for subsequent calculations, server, in the time of obtaining information list, can calculate every kind of customer group, the information list of each information bit.For example, customer group is divided into unmarried crowd, three kinds of customer groups of married crowd and mother and baby crowd, calculate respectively the information list of each information bit for every kind of customer group.Certainly, also customer group can be done to divide further according to actual conditions, the present embodiment is not done concrete restriction to this.Because number and the position of information bit under an application are all fixed, therefore, information bit mark corresponding to information bit also fixed.Server can precompute under each customer group, different information bits identify corresponding information list, as in the time browsing a webpage, on this webpage, there are two fixing information bits, corresponding information bit mark is respectively Table_ID1 and Table_ID2, in the time that unmarried crowd browses this webpage, server can precompute these two information bits and identify the information list of corresponding information bit for unmarried crowd; In the time that married crowd browses this webpage, server can precompute these two information bits and identify the information list of corresponding information bit for married crowd; In the time that mother and baby crowd browses this webpage, server can precompute these two information bits and identify the information list of corresponding information bit for mother and baby crowd.For example,, for comprising the information that more amusement is relevant in unmarried crowd's information list, as digital product information etc.For comprising the information that more household is relevant in married crowd's information list, as different furniture information etc.For comprising the product information that more infant is relevant in mother and baby crowd's information list, as care product information etc.
Can identify corresponding information list to each information bit by above-mentioned steps and do preliminary screening, remove redundant information, thereby make the needs that information to be recommended in information list can properer user, and can save the time of subsequent calculations cost.Certainly, according to actual conditions, this step can be done further and optimize, and the present embodiment is not done concrete restriction to the implementation procedure of this step.
202: real-time online obtains real time data corresponding to application identities, pull historical data corresponding to application identities;
The present embodiment does not obtain real time data corresponding to application identities to real-time online and does concrete restriction, also the mode that pulls that pulls historical data corresponding to application identities is not done to concrete restriction, include but not limited to: obtain the real time data of first user and pull the historical data of first user according to application identities real-time online, and the current place of definite first user group; Obtain the real time data of each the second user in the group of the current place of first user according to application identities real-time online, and pull the historical data of each the second user in the group of the current place of first user; According to the real time data corresponding to Real time data acquisition application identities of each second user and first user, and obtain historical data corresponding to application identities according to the historical data of each second user and first user.
Wherein, determine that the current place of first user group can adopt following two kinds of modes:
First kind of way: determine the current place of first user group according to application identities.
Server can be divided to corresponding group by first user mark in advance, owing to can comprising the user ID that first user is corresponding in application identities, when getting after the user ID that first user in application identities is corresponding, can directly determine the current place of first user group according to user ID corresponding to first user.
The second way: determine the current place of first user group according to the historical data of first user and real time data.
The historical data of first user corresponding to this user ID that if server is pre-stored, as the behavioral data of user in the time using this application and the portrait data of first user input, in the time that server gets application identities, can be according to the user ID in application identities, pull behavioral data and the portrait data of first user corresponding to this user ID, and then can determine the current place of first user group according to behavioral data and portrait data two item numbers certificates.
For example, server is divided into user unmarried man group, unmarried female group, married man group and married Nv Qunsige group in advance, and server is pre-stored, and portrait data that first user inputs are " sex: man " " marital status: unmarried ".Now, server gets after application identities, can get the portrait data of first user according to the user ID of first user in application identities, can determine that according to the portrait data of first user first user belongs to unmarried male group this group.Certainly, determine that according to application identities the current place of first user group can also adopt alternate manner, the present embodiment is not done concrete restriction to this.
Certainly, historical data can also comprise other more content, and the present embodiment is not done concrete restriction to this.
In the time pulling user's historical data, in order to accelerate to pull the speed of historical data, server can arrange a L2 cache, and this buffer memory reading speed is faster compared with internal memory.Therefore, the historical data using recently often can be deposited in this L2 cache, when in L2 cache, pull less than needs historical data time, can be pulling from internal memory, and upgrade the historical data of storing in L2 cache simultaneously.Certainly, for concrete application scenario, three grades of buffer memorys or alternate manner can also be set accelerate to pull the speed of historical data, the present embodiment is not done concrete restriction to this.It should be noted that, the historical data of having stored by server constantly accumulation obtain, as the behavioral data of the user in historical data, server can be collected user and surf the Net the keyword of input as one in user's behavioral data at every turn.
Due to when first user is for the first time when access server system, server may not stored first user and identify the historical data of corresponding first user in advance, now, can determine the current place of first user group according to the real time data of first user.The data of the current generation of application that real time data can used for first user, as currently in user watching a video, the video information of this video can be current real time data, and user is browsing commodity, and the design parameter information of these commodity can be also current real time data.Certainly, real time data also can be other content, and the present embodiment is not done concrete restriction yet to this.Server is getting after user's real time data, can carry out equally calculated off-line, becomes a certain content in historical data with the real time data that this is got, and the present embodiment is not done concrete restriction yet to this.
The mode of determining the current place of first user group according to the real time data of first user can, with reference to the mode of determining the current place of first user group according to historical data, repeat no more herein.Certainly, can also adopt other method according to actual conditions, the present embodiment is not done concrete restriction to this.
Wherein, can determine the current place of first user group by above-mentioned steps, the second user refers to other users in the group of first user place.The real time data of each the second user in real-time online obtains the current place of first user group, and while pulling the historical data of each the second user in the group of the current place of first user, can obtain the real time data of first user and pull the method for the historical data of first user with reference to real-time online, repeat no more herein.Certainly, can also adopt other method real-time online to obtain the real time data of each the second user in the group of the current place of first user and pull the historical data of each the second user in the group of the current place of first user, the present embodiment is not done concrete restriction to this, referring to the step of query caching Cache data Layer in Fig. 3.
When after definite real time data of each the second user and the real time data and historical data of historical data and first user, preferably, owing to having unavoidably redundant data in any data, therefore, can screen real time data and the historical data of each the second user's real time data and historical data and first user, the present embodiment does not limit concrete screening mode herein, includes but not limited to according to the time, time data screening excessively of a specified duration be fallen etc.Certainly, according to actual conditions, can also adopt other screening modes, the present embodiment is not done concrete restriction to this.
203: according at least one prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
The present embodiment not account form of at least one the prediction weight to the information to be recommended in the real time data getting according to real-time online and the each information list of historical data parallel computation that pulls is done concrete restriction, include but not limited to: according to the prediction weight of the information to be recommended in the real time data getting and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the real time data getting and the same information list of historical data parallel computation that pulls.
For the ease of understanding, now for example above-mentioned computing method are explained, concrete explaination is as follows:
Server gets each information bit and identifies after corresponding information list, can split into multiple calculation tasks according to information bit mark, as identified Table_ID1 and Table_ID2 according to 2 information bits, split into respectively 2 calculation task Task1 and Task2, each calculation task is used for calculating an information bit and identifies the prediction weight of the information to be recommended in corresponding information list.Preferably, in order to save time, multiple calculation tasks of fractionation can parallel computation, and calculation task Task1 and Task2 can executed in parallel, and this example is not done concrete restriction to this.Wherein, prediction weight is worth for the recommendation of weighing each information to be recommended, prediction weight can be divided into polytype as required, include but not limited to Information rate, probability of transaction and the degree of correlation etc., the present embodiment is not done concrete restriction to the kind of prediction weight, also the content of prediction weight is not done to concrete restriction.
Further, in order to simplify subsequent calculations task, before every kind of prediction weight of information to be recommended that can be in the each information list of parallel computation, the real time data getting according to real-time online and the historical data pulling are screened the information to be recommended in information list.For example, drawing a portrait data or user behavior data etc. according to the user in historical data screens the information to be recommended in information list, or, according to user's real time data, the information to be recommended in information list is screened, this screening process can be done the step of filtering distribution as access distribution in Fig. 3 gathers layer query filter condition user data etc., the information to be recommended in information list is screened.
Due to difference prediction weight corresponding different algorithm respectively, therefore, calculation task need to be done to split further according to algorithm.For example, to predict that weight is as Information rate and the degree of correlation are as example, two kinds of algorithms corresponding to prediction weight are respectively Alg1 and Alg2.Therefore, calculation task Task1 can be split as two computing unit task task 1_Alg1, Task1_Alg2 according to two kinds of algorithms.Similarly, calculation task Task2 also can be split as two computing unit task task 2_Alg1, Task2_Alg2 according to two kinds of algorithms.For the ease of understanding, now carry out relevant explanation explanation as an example of computing unit task task 1_Alg1 example, what computing unit task task 1_Alg1 calculated is the Information rate of all information to be recommended in the information list that information bit mark Table_ID1 is corresponding.Preferably, in order to save time, the multiple computing unit tasks that split according to algorithm can parallel computation, and computing unit task task 2_Alg1 and Task2_Alg2 also can executed in parallel, and this example is not done concrete restriction to this.
Owing at least comprising an information to be recommended in an information list, therefore, computing unit task also can split further according to the number of information to be recommended in algorithm information list.For example, taking computing unit task task 1_Alg1 as example, if include three information to be recommended in information list, now computing unit task task 1_Alg1 can be split as three computing unit subtask Task1_Alg1_1, Task1_Alg1_2, Task1_Alg1_3 according to the number of information to be recommended.Similarly, computing unit task task 1_Alg2, Task2_Alg1, Task2_Alg2 also can be split as several computing unit subtasks according to the number of information to be recommended in corresponding informance list.The step that this process can be distributed by information to be recommended as shown in Figure 3.For the ease of understanding, now carry out relevant explanation explanation as an example of computing unit subtask Task1_Alg1_1 example, what computing unit subtask Task1_Alg1_1 calculated is the Information rate of first information to be recommended in the information list that information bit mark Table_ID1 is corresponding.Preferably, in order to save time, the multiple computing units subtask splitting into according to the number of information in information list can parallel computation, be that computing unit subtask Task1_Alg1_1, Task1_Alg1_2, Task1_Alg1_3 equally can executed in parallel, the present embodiment is not done concrete restriction to this.
It should be noted that, the split process of parallel computation can be with reference to the content in figure 5, in Fig. 5, split in the split process principle of flow process and this step consistent, actual in the time carrying out parallel computation, splitting flow process or method for splitting can determine according to server arrangement, and the present embodiment is not done concrete restriction to this.
For the ease of understanding, taking the prediction weight calculated as computing information clicking rate is as example, referring to the step of the prediction weight of computing information in Fig. 3, the process of the Information rate of calculating an information to be recommended is explained below:
In the real time data getting due to real-time online and the historical data pulling, can comprise user and click feedback data.The total degree that an information that what wherein, user clicked that feedback data represents is is exposed in information bit and user click the total degree of this information.User clicks total degree * 100% that the total degree/information of this information exposes in information bit and is the Information rate of this information.For example, having the cumulative exposure total degree on an advertisement position of advertisement is first 1000 times, and user is in the process of this advertisement exposure, and the number of times of clicking altogether this advertisement is 100 times, now, click feedback data according to user and can determine that the ad click rate of this advertisement is 100/1000*100%=10%.
Certainly, including above-mentioned Information rate, in the process of prediction weight being calculated in reality, can be according to actual conditions, adopt different algorithms to calculate prediction weight, the present embodiment is not done concrete restriction to the computing method of prediction weight.
Further, in order to determine quickly recommendation information, do not allow user wait for the long period, when every kind of prediction weight of the information to be recommended in the real time data getting according to real-time online and the each information list of historical data parallel computation that pulls, can set in advance a time threshold.When concrete enforcement, carry out at first timing from computation process, when the computing time of accumulation is when overtime threshold value, now, if do not complete calculation task, using the prediction weight of complete as calculated information to be recommended as result of calculation.Do not calculate any result if cause for some reason, now can be using the information in the information recommendation list of acquiescence as definite recommendation information.If do not set in advance the information recommendation list of acquiescence, now illustrate that information bit that information bit that this information list is corresponding identifies may lose the value of impression information, now, can select this information bit undercarriage from application corresponding to application identities.Certainly, in actual conditions, can also do to process further according to concrete situation, the present embodiment not be done concrete restriction to this.
204: according to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
Calculate after every kind of prediction weight of each information to be recommended, can screen the information to be recommended in each information list according to every kind of prediction weight of each information to be recommended.In the process of wherein, screening, can adopt with the following method:
For every kind of prediction weight arranges a weighted value, for example, Information rate weighted value is 60% in advance.Probability of transaction weighted value is 40% etc., every kind of each information to be recommended prediction weighted value is multiplied by the numerical value that corresponding weighted value obtains to superpose, obtain a fractional value, according to the fractional value of each information to be recommended, information to be recommended in each information list is screened.
For example, to predict that weight is as Information rate and probability of transaction, the weighted value that Information rate accounts for is 40%, and the weighted value that probability of transaction accounts for is 60% for example.In information list, include three information to be recommended, the Information rate of first information to be recommended is 40%, probability of transaction is 20%, the Information rate that the Information rate of second information to be recommended is 90%, probability of transaction is 10%, the three information to be recommended is 20%, probability of transaction is 80%.For the ease of calculating, the Information rate of each information to be recommended and probability of transaction can be converted to the form of fractional value.Taking first information to be recommended as example, Information rate mark is that 40%*100=40 divides, and probability of transaction mark is that 20%*100=20 divides.Every kind of each information to be recommended prediction weight is multiplied by the numerical value that corresponding weighted value obtains and superposes, obtain a final fractional value.For example, the fractional value of first information to be recommended is that 40*40%+20*60%=28 divides, and the fractional value of second information to be recommended is that 90*40%+10*60%=42 divides, and the fractional value of the 3rd information to be recommended is that 20*40%+80*60%=56 divides.
Determining after the fractional value of each information to be recommended, can screen the information to be recommended in each information list according to the fractional value of each information to be recommended.For example, can sort according to fractional value, filter out the information to be recommended of fractional value maximum, as above-mentioned example mid-score value is 56 points to the maximum, i.e. the third corresponding information to be recommended.Or, can also filter out first three information to be recommended of fractional value rank, the present embodiment is not done concrete restriction to the process of screening according to fractional value.
Further, for definite recommendation information more humane, after the information in information list being screened by said method, the user behavior data in the real time data that can also get according to real-time online and the historical data pulling does classification equalization operation and redirect operation to the information in the information list after screening.For the ease of understanding, be illustrated taking recommendation information as advertisement below.
For example, server can determine that by user behavior data user is browsing Mobile phone recently, but a user is in the time buying mobile phone, also may buy the marginal-product that mobile phone is relevant simultaneously, as sticking film for mobile phone, and mobile phone shell etc.Therefore,, in order to make the demand of the properer user of advertisement in the advertising listing after screening, can do classification equalization operation to the advertisement in advertising listing.In said circumstances, if there is no the relevant advertisements of sticking film for mobile phone in the advertising listing after screening, add the advertisement of at least one sticking film for mobile phone in can the advertising listing after screening.Again because a user is in the time preparing to buy commodity, in the process of screening commodity, browse often after commodity, the of a sort similar commodity of these commodity of removal search, the price and the design parameter that contrast similar commodity are determined the final commodity of buying again, in the process of contrast, the commodity of before browsing are browsed possibly again.Based on above-mentioned principle, browse custom for what make the properer user of advertisement in the advertising listing after screening, can do redirect operation to the advertisement in advertising listing, in the advertising listing after screening, add the advertisement that at least one user browses recently.
Certainly, except above-mentioned screening technique, can also adopt other method according to every kind of prediction weight of each information to be recommended, information to be recommended in each information list to be screened, the present embodiment is not done concrete restriction to the screening technique information to be recommended in each information list being screened according to every kind of prediction weight of each information to be recommended.And after the information in information list being screened by said method, can also do some other Optimum Operation, the present embodiment is not done concrete restriction to the content of optimizing, also the method for optimizing and subsequent step are not done to concrete restriction.
205: the recommendation information that the information to be recommended filtering out in each information list is defined as to the information bit that information bit that each information list is corresponding identifies.
After server is defined as the information to be recommended filtering out in each information list the recommendation information of the information bit that information bit that each information list is corresponding identifies, application identities, information bit mark and corresponding recommendation information can be sent to terminal.
Further, terminal is receiving after the recommendation information of the application identities of server transmission, information bit mark and correspondence, can determine corresponding application according to application identities, determine information bit according to information bit mark, recommendation information is shown in corresponding information bit.Have when multiple when an information bit identifies corresponding recommendation information, multiple recommendation informations can also be shown at the enterprising road wheel stream of information bit.Certainly, can also have other operation, the subsequent step of the recommendation information of the information bit that the present embodiment does not identify definite information bit corresponding to each information list is done concrete restriction.
It should be noted that, the steps flow chart of above-mentioned execution can be with reference to figure 3 or Fig. 4.Wherein, Fig. 3 is while determining recommendation information, after first user operates terminal, and the interaction flow of terminal and server.Fig. 4 is while determining recommendation information, the inner treatment scheme of determining recommendation information of server.The method that Fig. 3, Fig. 4 provide with the present embodiment is consistent on principle and step framework, in the process of implementing in reality, can be with reference to any one in the method in figure 3, Fig. 4 or the present embodiment, and the present embodiment is not done concrete restriction to this.
The method that the present embodiment provides, identify corresponding information list by obtaining each information bit, real-time online obtains current real time data corresponding to application identities making under application of user, pull historical data corresponding to application identities, make the data that get have more real-time, and according to the prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, more accurate according to the recommendation information that every kind of prediction weight of each information to be recommended is definite, and improved computing velocity.
Embodiment tri-
The embodiment of the present invention provides a kind of device of online parallel computation recommendation information, the method that this device provides for carrying out above-described embodiment one or embodiment bis-.Referring to Fig. 6, this device comprises:
The first acquisition module 601, for obtaining first user in current application identities and at least one information bit mark making under application;
The second acquisition module 602, identifies corresponding information list for obtaining each information bit, comprises at least one information to be recommended in information list;
The 3rd acquisition module 603, obtains real time data corresponding to application identities for real-time online, pulls historical data corresponding to application identities;
Computing module 604, at least one prediction weight of the information to be recommended of the real time data getting for basis and the each information list of historical data parallel computation pulling, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
Screening module 605, screens the information to be recommended of each information list for every kind of prediction weight according to each information to be recommended, obtains the information to be recommended filtering out in each information list;
Determination module 606, is defined as the recommendation information of the information bit that information bit that each information list is corresponding identifies for the information to be recommended that each information list is filtered out.
As a kind of preferred embodiment, computing module 604, for according to the prediction weight of the information to be recommended of the real time data that gets and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the real time data getting and the same information list of historical data parallel computation that pulls; Wherein, prediction weight at least comprises the one in clicking rate and probability of transaction.
As a kind of preferred embodiment, computing module 604, also for when calculating the time of at least one prediction weight of the information to be recommended of each information list according to the real time data that gets and the historical data that pulls while exceeding Preset Time threshold value, stop calculating operation, and obtain the prediction weight of the each information to be recommended in each information list according to current result of calculation.
As a kind of preferred embodiment, referring to Fig. 7, the 3rd acquisition module 603, includes but not limited to:
The first acquiring unit 6031, for obtaining the real time data of first user and pulling the historical data of first user according to application identities real-time online;
Determining unit 6032, for determining the current place of first user group;
Second acquisition unit 6033, obtains the real time data of each the second user in the group of the current place of first user for real-time online, and pulls the historical data of each the second user in the group of the current place of first user;
The 3rd acquiring unit 6034, for according to the real time data corresponding to Real time data acquisition application identities of each second user and first user, and obtains historical data corresponding to application identities according to the historical data of each second user and first user.
As a kind of preferred embodiment, determining unit 6032, for determining the current place of first user group according to the real time data of first user and historical data, or, determine the current place of first user group according to application identities.
The device that the present embodiment provides, identify corresponding information list by obtaining each information bit, real-time online obtains current real time data corresponding to application identities making under application of user, pull historical data corresponding to application identities, make the data that get have more real-time, and according to the prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, more accurate according to the recommendation information that every kind of prediction weight of each information to be recommended is definite, and improved computing velocity.
Embodiment tetra-
The present embodiment provides a kind of server, and this server can be for the method for the online parallel computation recommendation information providing in above-described embodiment be provided.Referring to Fig. 8, this server 800 comprises:
Server 800 can because of configuration or performance is different produces larger difference, can comprise one or more central processing units (central processing units, CPU) 1122(for example, one or more processors) and storer 1132, for example one or more mass memory units of storage medium 1130(of one or more storage application programs 1142 or data 1144).Wherein, storer 1132 and storage medium 1130 can be of short duration storage or storage lastingly.The program that is stored in storage medium 1130 can comprise one or more modules (diagram does not mark), and each module can comprise a series of command operatings in server.Further, central processing unit 1122 can be set to communicate by letter with storage medium 1130, carries out a series of command operatings in storage medium 1130 on server 800.
Server 800 can also comprise one or more power supplys 1126, one or more wired or wireless network interfaces 1150, one or more IO interface 1158, and/or, one or more operating systems 1141, for example Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc.
More than one or one program is stored in storer, and is configured to be carried out by more than one or one processor, and described more than one or one routine package contains for carrying out the instruction of following operation:
Obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in information list, comprise at least one information to be recommended;
Real-time online obtains real time data corresponding to described application identities, pull historical data corresponding to application identities, and according at least one prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
According to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
The information to be recommended filtering out in each information list is defined as to the recommendation information of the information bit that information bit that each information list is corresponding identifies.
Supposing above-mentioned is the possible embodiment of the first,, in the possible embodiment of the first embodiment possible as the second basic and that provide, in the storer of server, also comprises the instruction for carrying out following operation:
According to the prediction weight of the information to be recommended in the real time data getting and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the real time data getting and the same information list of historical data parallel computation that pulls;
Wherein, prediction weight at least comprises the one in clicking rate and probability of transaction.
In the third the possible embodiment providing as basis at any embodiment of the first or the possible embodiment of the second, in the storer of server, also comprise the instruction for carrying out following operation:
Exceed Preset Time threshold value if calculate the time of at least one prediction weight of the information to be recommended in each information list according to the real time data getting and the historical data that pulls, stop calculating operation, and obtain the prediction weight of the each information to be recommended in each information list according to current result of calculation.
In the 4th kind of possible embodiment providing as basis at any embodiment of the first or the possible embodiment of the second, in the storer of server, also comprise the instruction for carrying out following operation:
Obtain the real time data of described first user and pull the historical data of first user according to application identities real-time online, and determine the current place of described first user group;
Obtain the real time data of each the second user in the group of the current place of first user according to application identities real-time online, and pull the historical data of each the second user in the group of the current place of first user;
According to the real time data corresponding to Real time data acquisition application identities of each second user and first user, and obtain historical data corresponding to application identities according to the historical data of each second user and first user.
In the 5th kind of possible embodiment providing as basis at the 4th kind of possible embodiment, in the storer of server, also comprise the instruction for carrying out following operation:
Determine the current place of first user group according to the historical data of first user and real time data;
Or, determine the current place of first user group according to application identities.
Server provided by the invention, identify corresponding information list by obtaining each information bit, real-time online obtains current real time data corresponding to application identities making under application of user, pull historical data corresponding to application identities, make the data that get have more real-time, and according to the prediction weight of the information to be recommended in the real time data getting and the each information list of historical data parallel computation that pulls, more accurate according to the recommendation information that every kind of prediction weight of each information to be recommended is definite, and improved computing velocity.
It should be noted that: the device of the online parallel computation recommendation information that above-described embodiment provides is in the time of calculated recommendation information, only be illustrated with the division of above-mentioned each functional module, in practical application, can above-mentioned functions be distributed and completed by different functional modules as required, be divided into different functional modules by the inner structure of device, to complete all or part of function described above.In addition, the device of the online parallel computation recommendation information that above-described embodiment provides, the server of online parallel computation recommendation information belong to same design with the embodiment of the method for online parallel computation recommendation information, its specific implementation process refers to embodiment of the method, repeats no more here.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that all or part of step that realizes above-described embodiment can complete by hardware, also can carry out the hardware that instruction is relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any amendment of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (11)
1. a method for online parallel computation recommendation information, is characterized in that, described method comprises:
Obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in described information list, comprise at least one information to be recommended;
Real-time online obtains real time data corresponding to described application identities, pull historical data corresponding to described application identities, and according at least one prediction weight of the information to be recommended in the described real time data getting and the each information list of historical data parallel computation that pulls, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
According to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
The information to be recommended filtering out in each information list is defined as to the recommendation information of the information bit that information bit that each information list is corresponding identifies.
2. method according to claim 1, is characterized in that, at least one prediction weight of the information to be recommended in the real time data getting described in described basis and the each information list of historical data parallel computation pulling, comprising:
According to the prediction weight of the information to be recommended in the described real time data getting and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the described real time data getting and the same information list of historical data parallel computation that pulls;
Wherein, described prediction weight at least comprises the one in clicking rate and probability of transaction.
3. method according to claim 1 and 2, is characterized in that, described method also comprises:
Exceed Preset Time threshold value if calculate the time of at least one prediction weight of the information to be recommended in each information list according to the described real time data getting and the historical data that pulls, stop calculating operation, and obtain the prediction weight of the each information to be recommended in each information list according to current result of calculation.
4. method according to claim 1 and 2, is characterized in that, described real-time online obtains real time data corresponding to described application identities, pulls historical data corresponding to described application identities, comprising:
Obtain the real time data of described first user and pull the historical data of described first user according to described application identities real-time online, and determine the current place of described first user group;
Obtain the real time data of each the second user in the group of the current place of described first user according to described application identities real-time online, and pull the historical data of each the second user in the group of the current place of described first user;
According to real time data corresponding to application identities described in the Real time data acquisition of each the second user and described first user, and obtain historical data corresponding to described application identities according to the historical data of each the second user and described first user.
5. method according to claim 4, is characterized in that, the current place of described definite described first user group, comprising:
Determine the current place of described first user group according to the historical data of described first user and real time data;
Or, determine the current place of described first user group according to described application identities.
6. a device for online parallel computation recommendation information, is characterized in that, described device comprises:
The first acquisition module, for obtaining first user in current application identities and at least one information bit mark making under application;
The second acquisition module, identifies corresponding information list for obtaining each information bit, comprises at least one information to be recommended in described information list;
The 3rd acquisition module, obtains real time data corresponding to described application identities for real-time online, pulls historical data corresponding to described application identities;
Computing module, at least one prediction weight of the information to be recommended of the real time data getting described in basis and the each information list of historical data parallel computation pulling, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
Screening module, screens the information to be recommended of each information list for every kind of prediction weight according to each information to be recommended, obtains the information to be recommended filtering out in each information list;
Determination module, is defined as the recommendation information of the information bit that information bit that each information list is corresponding identifies for the information to be recommended that each information list is filtered out.
7. device according to claim 6, it is characterized in that, described computing module, for according to described in the prediction weight of information to be recommended of the real time data that gets and each information list of historical data parallel computation of pulling, and according to every kind of prediction weight of the information to be recommended in the described real time data getting and the same information list of historical data parallel computation that pulls; Wherein, described prediction weight at least comprises the one in clicking rate and probability of transaction.
8. according to the device described in claim 6 or 7, it is characterized in that, described computing module, also for when according to described in the real time data that gets and the historical data that pulls time of calculating at least one prediction weight of the information to be recommended of each information list while exceeding Preset Time threshold value, stop calculating operation, and obtain the prediction weight of the each information to be recommended in each information list according to current result of calculation.
9. according to the device described in claim 6 or 7, it is characterized in that, described the 3rd acquisition module, comprising:
The first acquiring unit, for obtaining the real time data of described first user according to described application identities real-time online and pulling the historical data of described first user;
Determining unit, for determining the current place of described first user group;
Second acquisition unit, obtains the real time data of each the second user in the group of the current place of described first user for real-time online, and pulls the historical data of each the second user in the group of the current place of described first user;
The 3rd acquiring unit, be used for according to real time data corresponding to application identities described in the Real time data acquisition of each the second user and described first user, and obtain historical data corresponding to described application identities according to the historical data of each the second user and described first user.
10. device according to claim 9, it is characterized in that, described determining unit, for determining the current place of described first user group according to the real time data of described first user and historical data, or, determine the current place of described first user group according to described application identities.
11. 1 kinds of servers, it is characterized in that, described server includes storer, and one or more than one program, one of them or more than one program are stored in storer, and be configured to be carried out by one or more than one processor, described one or more than one routine package are containing for carrying out the instruction of following operation:
Obtain first user in current application identities and at least one information bit mark making under application, obtain each information bit and identify corresponding information list, in described information list, comprise at least one information to be recommended;
Real-time online obtains real time data corresponding to described application identities, pull historical data corresponding to described application identities, and according at least one prediction weight of the information to be recommended in the described real time data getting and the each information list of historical data parallel computation that pulls, described prediction weight is for weighing the recommendation rate of specific gravity of each information to be recommended;
According to every kind of prediction weight of each information to be recommended, information to be recommended in each information list is screened, obtain the information to be recommended filtering out in each information list;
The information to be recommended filtering out in each information list is defined as to the recommendation information of the information bit that information bit that each information list is corresponding identifies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310698031.4A CN104090894B (en) | 2013-12-18 | 2013-12-18 | The method of online parallel computation recommendation information, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310698031.4A CN104090894B (en) | 2013-12-18 | 2013-12-18 | The method of online parallel computation recommendation information, device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104090894A true CN104090894A (en) | 2014-10-08 |
| CN104090894B CN104090894B (en) | 2015-10-21 |
Family
ID=51638610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310698031.4A Active CN104090894B (en) | 2013-12-18 | 2013-12-18 | The method of online parallel computation recommendation information, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104090894B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104867492A (en) * | 2015-05-07 | 2015-08-26 | 科大讯飞股份有限公司 | Intelligent interaction system and method |
| CN105630852A (en) * | 2014-11-28 | 2016-06-01 | 北京奇立软件技术有限公司 | Information inquiry method and server |
| CN105654341A (en) * | 2015-12-28 | 2016-06-08 | 中国民航信息网络股份有限公司 | Aviation product recommendation system and aviation product recommendation method based on cloud service |
| CN105955969A (en) * | 2015-11-12 | 2016-09-21 | ***股份有限公司 | User behavior data ranking method and device |
| CN105959374A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Data recommendation method and data recommendation equipment |
| CN106033419A (en) * | 2015-03-10 | 2016-10-19 | 深圳市腾讯计算机***有限公司 | An information real-time push method, device and system |
| CN106570006A (en) * | 2015-10-08 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Multimedia file recommendation system and releasing information storage method |
| CN107038213A (en) * | 2017-02-28 | 2017-08-11 | 华为技术有限公司 | A kind of method and device of video recommendations |
| CN108810056A (en) * | 2017-05-04 | 2018-11-13 | 腾讯科技（北京）有限公司 | Information-pushing method and device |
| CN110245990A (en) * | 2019-06-19 | 2019-09-17 | 北京达佳互联信息技术有限公司 | Advertisement recommended method, device, electronic equipment and storage medium |
| CN112541119A (en) * | 2020-12-08 | 2021-03-23 | 厦门诚创网络股份有限公司 | Efficient and energy-saving small recommendation system |
| CN113254772A (en) * | 2021-05-31 | 2021-08-13 | 温州行动者网络科技有限公司 | Information pushing method based on big data |
| CN113961792A (en) * | 2020-07-15 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Resource recommendation system, method, electronic device and storage medium |
| CN114443967A (en) * | 2022-04-08 | 2022-05-06 | 北京并行科技股份有限公司 | Similar application recommendation method, computing device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030015351A1 (en) * | 1996-03-25 | 2003-01-23 | Halliburton Energy Services, Inc. | Method and system for predicting performance of a drilling system of a given formation |
| CN101546484A (en) * | 2009-04-30 | 2009-09-30 | 南京航空航天大学 | Flight delay conformance analysis and forecast system based on SOA and operation method thereof |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
-
2013
- 2013-12-18 CN CN201310698031.4A patent/CN104090894B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030015351A1 (en) * | 1996-03-25 | 2003-01-23 | Halliburton Energy Services, Inc. | Method and system for predicting performance of a drilling system of a given formation |
| CN101546484A (en) * | 2009-04-30 | 2009-09-30 | 南京航空航天大学 | Flight delay conformance analysis and forecast system based on SOA and operation method thereof |
| CN102088626A (en) * | 2009-12-02 | 2011-06-08 | Tcl集团股份有限公司 | On-line video recommendation method and video portal service system |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630852A (en) * | 2014-11-28 | 2016-06-01 | 北京奇立软件技术有限公司 | Information inquiry method and server |
| CN106033419A (en) * | 2015-03-10 | 2016-10-19 | 深圳市腾讯计算机***有限公司 | An information real-time push method, device and system |
| CN106033419B (en) * | 2015-03-10 | 2020-11-06 | 深圳市腾讯计算机***有限公司 | Method, device and system for pushing messages in real time |
| CN104867492A (en) * | 2015-05-07 | 2015-08-26 | 科大讯飞股份有限公司 | Intelligent interaction system and method |
| CN106570006A (en) * | 2015-10-08 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Multimedia file recommendation system and releasing information storage method |
| CN106570006B (en) * | 2015-10-08 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Multimedia file recommendation system and delivery information storage method |
| CN105955969A (en) * | 2015-11-12 | 2016-09-21 | ***股份有限公司 | User behavior data ranking method and device |
| CN105955969B (en) * | 2015-11-12 | 2019-08-13 | ***股份有限公司 | A kind of user behavior data arrangement method and device |
| CN105654341A (en) * | 2015-12-28 | 2016-06-08 | 中国民航信息网络股份有限公司 | Aviation product recommendation system and aviation product recommendation method based on cloud service |
| CN105959374A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Data recommendation method and data recommendation equipment |
| WO2017193897A1 (en) * | 2016-05-12 | 2017-11-16 | 腾讯科技（深圳）有限公司 | Data recommendation method and device therefor, and storage medium |
| CN105959374B (en) * | 2016-05-12 | 2019-05-03 | 腾讯科技（深圳）有限公司 | A kind of data recommendation method and its equipment |
| US10706363B2 (en) | 2016-05-12 | 2020-07-07 | Tencent Technology (Shenzhen) Company Limited | Data recommendation method and device, and storage medium |
| CN107038213B (en) * | 2017-02-28 | 2021-06-15 | 华为技术有限公司 | Video recommendation method and device |
| CN107038213A (en) * | 2017-02-28 | 2017-08-11 | 华为技术有限公司 | A kind of method and device of video recommendations |
| CN108810056A (en) * | 2017-05-04 | 2018-11-13 | 腾讯科技（北京）有限公司 | Information-pushing method and device |
| CN108810056B (en) * | 2017-05-04 | 2021-05-14 | 腾讯科技（北京）有限公司 | Information pushing method and device |
| CN110245990A (en) * | 2019-06-19 | 2019-09-17 | 北京达佳互联信息技术有限公司 | Advertisement recommended method, device, electronic equipment and storage medium |
| CN113961792A (en) * | 2020-07-15 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Resource recommendation system, method, electronic device and storage medium |
| CN113961792B (en) * | 2020-07-15 | 2024-07-09 | 北京达佳互联信息技术有限公司 | Resource recommendation system, method, electronic equipment and storage medium |
| CN112541119A (en) * | 2020-12-08 | 2021-03-23 | 厦门诚创网络股份有限公司 | Efficient and energy-saving small recommendation system |
| CN112541119B (en) * | 2020-12-08 | 2022-07-05 | 厦门诚创网络股份有限公司 | Efficient and energy-saving small recommendation system |
| CN113254772A (en) * | 2021-05-31 | 2021-08-13 | 温州行动者网络科技有限公司 | Information pushing method based on big data |
| CN113254772B (en) * | 2021-05-31 | 2022-01-11 | 山东远桥信息科技有限公司 | Information pushing method based on big data |
| CN114443967A (en) * | 2022-04-08 | 2022-05-06 | 北京并行科技股份有限公司 | Similar application recommendation method, computing device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104090894B (en) | 2015-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104090894B (en) | The method of online parallel computation recommendation information, device and server | |
| CN105872629B (en) | Content recommendation method, apparatus and system | |
| US20210044674A1 (en) | Method and Apparatus for Real-Time Personalization | |
| US9015128B2 (en) | Method and system for measuring social influence and receptivity of users | |
| US8306858B2 (en) | Consolidated content item request for multiple environments | |
| TWI603273B (en) | Method and device for placing information search | |
| CN104035926B (en) | A kind of dispensing of internet information and system | |
| CN110796477A (en) | Advertisement display method and device, electronic equipment and readable storage medium | |
| US20110029382A1 (en) | Automated Targeting of Information to a Website Visitor | |
| US10262339B2 (en) | Externality-based advertisement bid and budget allocation adjustment | |
| CN110532468B (en) | Website resource recommendation method and device and computing equipment | |
| CN102750320B (en) | Method, device and system for calculating network video real-time attention | |
| US20160092933A1 (en) | Advertisement opportunity bidding | |
| CN109325179A (en) | A kind of method and device that content is promoted | |
| CN108632311A (en) | Information-pushing method and device | |
| CN106815254A (en) | A kind of data processing method and device | |
| CN103795697A (en) | Network medium information release effect simulation method and system | |
| CN105184616A (en) | Method and device for targeted delivery of business object | |
| CN102902775A (en) | Internet real-time computing method and internet real-time computing system | |
| US20160267521A1 (en) | Systems and methods for electronically monitoring audience attentiveness and receptiveness | |
| CN110191171A (en) | Weather information transmission method | |
| CN110659404A (en) | Information recommendation method and device and storage medium | |
| CN111428143A (en) | Commodity recommendation method and system, server and storage medium | |
| Zhang et al. | Optimizing video caching at the edge: A hybrid multi-point process approach | |
| CN106021391A (en) | Product comment information real-time collection method based on Storm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |