CN105183882A

CN105183882A - Application software recommending method and device

Info

Publication number: CN105183882A
Application number: CN201510612729.9A
Authority: CN
Inventors: 刘海涛
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Baidu Online Network Technology Beijing Co Ltd; Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2015-09-23
Filing date: 2015-09-23
Publication date: 2015-12-23
Also published as: WO2017049792A1

Abstract

The invention provides an application software recommending method and device. The method comprises the steps that user feature information is obtained according to the application software recommending request received from a client side; the user feature information serving as input parameters is provided for an application software recommending model, and the application software recommending model is obtained on the basis of studying historical data for attention paid to all pieces of application software; recommending data of the application software are formed according to the recommended application software information output by the application software recommending model, and the data are issued to the client side. According to the technical scheme, the application software recommended data issued to the client side can contain the application software in which users are interested, and the situation that the application software in which the users are interested can not be displayed to the users in a highlighted mode, and the application software recommended information which does not conform to the interest of the users occupies network resources can be avoided to a certain degree.

Description

A kind of application software recommend method and device

Technical field

The present invention relates to network technology, especially relate to a kind of application software recommend method and application software recommendation apparatus.

Background technology

Along with the quick fast development of internet especially mobile Internet, application software (ApplicationSoftware) has become a part indispensable in people's routine work life gradually.At present, application software especially for the kind of the APP (Application, application program) of mobile terminal device and quantity all in continual increase.

Inventor is realizing finding in process of the present invention, for the developer of application software, owing to having dropped into certain human and material resources and financial resources in the performance history of application software, therefore, developer often wish its application software developed use by more users, but the application software that developer develops often is submerged among application software numerous at present, what can not be highlighted is presented in face of this interesting user group.For user, in numerous application software, must some application software be interested to user, but, the interested application software of user is also often submerged in application software numerous at present, and what can not be highlighted represents in front of the user.

Summary of the invention

The object of this invention is to provide a kind of application software recommend method and device.

According to one of them aspect of the present invention, a kind of application software recommend method is provided, and said method comprising the steps of: according to the application software recommendation request received from client, obtain user's characteristic information; Described user's characteristic information is supplied to application software recommended models as input parameter, and described application software recommended models learns to obtain based on the historical data be concerned each application software; Form application software recommending data according to the recommended application software information that application software recommended models exports, and issue to client.

According to wherein another aspect of the present invention, a kind of application software recommend method is provided, and said method comprising the steps of: client generates application software recommendation request based on user to the operation of application software, and sends this application software recommendation request to network-side; Client receives the application software recommending data formed based on recommended application software information that network-side issues, and shows described application software recommending data; Wherein, described recommended application software information is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and described application software recommended models network-side learns to obtain based on the historical data be concerned each application software.

According to wherein another aspect of the present invention, provide a kind of application software recommendation apparatus, and described device comprising: acquisition module, being suitable for the application software recommendation request according to receiving from client, obtain user's characteristic information; Load module, be suitable for described user's characteristic information to be supplied to application software recommended models as input parameter, described application software recommended models learns to obtain based on the historical data be concerned each application software; Recommending data forms module, and the recommended application software information being suitable for exporting according to application software recommended models forms application software recommending data; And issue module, be suitable for formed application software recommending data to be handed down to client.

According to wherein another aspect of the present invention, provide a kind of application software recommendation apparatus, and described device comprises: request generation module, be suitable for generating application software recommendation request based on user to the operation of application software; Sending module, is suitable for sending to network-side the application software recommendation request generated; Receiver module, is suitable for the application software recommending data generated in response to described application software recommendation request that reception network-side issues; Display module, is suitable for showing described application software recommending data; Wherein, described application software recommending data is that network-side generates based on recommended application software information, described recommended application software information is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and described application software recommended models network-side learns to obtain based on the historical data be concerned each application software.

Compared with prior art, the present invention has the following advantages: the present invention arranges application software recommended models by the historical data utilizing each application software and be concerned, on basis application software recommended models being based upon add up large data mining, because the historical data be concerned each application software carries out learning obtaining the same application software that the different user with same characteristic features pays close attention to jointly, therefore, the application software recommended models that the present invention obtains by learning historical data can embody the different application software that the user with different characteristic pays close attention to, thus when user's characteristic information is supplied to application software recommended models as input parameter, the recommended application software information that application software recommended models exports can be formed for particular user and meet the application software recommending data of particular user interest as far as possible, it can thus be appreciated that, technical scheme provided by the invention can make to include the interested application software of user in the application software recommending data issued to client by data mining statistics as far as possible, and the application software recommendation information representing in front of the user and do not meet user interest avoiding that the interested application software of user can not be highlighted to a certain extent takies the phenomenon of Internet resources.

Accompanying drawing explanation

By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:

Fig. 1 is the process flow diagram of the application software recommend method of the embodiment of the present invention one;

Fig. 2 is the process flow diagram of the application software recommend method of the embodiment of the present invention two;

Fig. 3 is that the network-side of the embodiment of the present invention two is to first picture corresponding to photos and sending messages under client;

Fig. 4 is that the network-side of the embodiment of the present invention two is to second picture corresponding to photos and sending messages under client;

Fig. 5 is that the network-side of the embodiment of the present invention two is to the 3rd picture corresponding to photos and sending messages under client;

Fig. 6 is that the network-side of the embodiment of the present invention two is to the 4th picture corresponding to photos and sending messages under client;

Fig. 7 is the application software recommend method process flow diagram of the embodiment of the present invention three;

Fig. 8 is the application software recommend method process flow diagram of the embodiment of the present invention four;

Fig. 9 is the application software recommendation apparatus schematic diagram of the embodiment of the present invention five;

Figure 10 is the application software recommendation apparatus schematic diagram of the embodiment of the present invention six.

In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.

Embodiment

Before in further detail exemplary embodiment being discussed, it should be mentioned that some exemplary embodiments are described as the process or method described as process flow diagram.Although operations is described as the process of order by process flow diagram, many operations wherein can be implemented concurrently, concomitantly or simultaneously.In addition, the execution sequence of operations can be rearranged.When its operation is complete, described process can be terminated, but can also have the additional step do not comprised in the accompanying drawings.Described process can correspond to method, function, code, subroutine, subroutine etc.

Alleged within a context " computer equipment " also can be called " computer " etc., refer to the intelligent electronic device that can be performed the predetermined process such as numerical evaluation and/or logical calculated process by operation preset program or instruction, it can comprise processor and storer, the programmed instruction that prestores in memory is performed to perform predetermined process process by processor, or perform predetermined process process by the hardware such as ASIC, FPGA, DSP, or combined by said two devices and realize.Computer equipment includes but not limited to server, PC and notebook computer etc.

Described computer equipment comprises subscriber equipment and the network equipment.Wherein, described subscriber equipment includes but not limited to PC and notebook computer etc.; The described network equipment includes but not limited to the server group that single network server, multiple webserver form or the cloud be made up of a large amount of computing machine or the webserver based on cloud computing (CloudComputing), wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection.Wherein, described computer equipment isolated operation can realize the present invention, also accessible network by realizing the present invention with the interactive operation of other computer equipments in network.Wherein, the network residing for described computer equipment includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN etc.

It should be noted that; described subscriber equipment, the network equipment and network etc. are only citing; other computer equipments that are existing or that may occur from now on or network, as being applicable to the present invention, within also should being included in scope, and are contained in this with way of reference.

The method (some of them are illustrated by process flow diagram) discussed in following literary composition can be implemented by hardware, software, firmware, middleware, microcode, hardware description language or its combination in any.When implementing by software, firmware, middleware or microcode, program code or code segment in order to implement necessary task can be stored in machine or computer-readable medium (such as storage medium).(one or more) processor can implement necessary task.

Concrete structure disclosed herein and function detail are only representational, and are the objects for describing exemplary embodiment of the present invention.But the present invention can carry out specific implementation by many replacement forms, and should not be construed as only being limited to the embodiments set forth herein.

Should be understood that, although may have been used term " first ", " second " etc. here to describe unit, these unit should not limit by these terms.These terms are used to be only used to a unit and another unit to distinguish.For example, when not deviating from exemplary embodiment scope, first module can be called as second unit, and second unit can be called as first module similarly.Here used term "and/or" comprise one of them or more any and all combinations of listed associated item.

Should be understood that, when a unit is called as " connection " or " coupling " to another unit, it can directly connect or be coupled to another unit described, or can there is temporary location.On the other hand, " when being directly connected " or " directly coupled " to another unit, then there is not temporary location when a unit is called as.Should explain in a comparable manner the relation be used between description unit other words (such as " and be in ... between " compared to " and be directly in ... between ", " with ... contiguous " compared to " and with ... be directly close to " etc.).

Here used term is only used to describe specific embodiment and be not intended to limit exemplary embodiment.Unless context refers else clearly, otherwise singulative used here " ", " one " are also intended to comprise plural number.It is to be further understood that, the existence of the feature that term used here " comprises " and/or " comprising " specifies to state, integer, step, operation, unit and/or assembly, and do not get rid of and there is or add other features one or more, integer, step, operation, unit, assembly and/or its combination.

Also it should be mentioned that and to replace in implementation at some, the function/action mentioned can according to being different from occurring in sequence of indicating in accompanying drawing.For example, depend on involved function/action, in fact the two width figure in succession illustrated can perform simultaneously or sometimes can perform according to contrary order substantially.

Below in conjunction with accompanying drawing, the present invention is described in further detail.

Embodiment one, application software recommend method.

Fig. 1 is the process flow diagram of the application software recommend method of the present embodiment, and the method shown in Fig. 1 mainly comprises step S100, step S110 and step S120.Method described in the present embodiment is performed in network-side, and the method described in the present embodiment can perform in computer equipment, as performed by the computer equipment in network-side.Below each step in Fig. 1 is described respectively.

The application software recommendation request that S100, basis receive from client, obtains user's characteristic information.

Concrete, client in the present embodiment is arranged in subscriber terminal equipment usually, here subscriber terminal equipment is generally mobile terminal device as intelligent mobile phone or panel computer etc., certainly, this subscriber terminal equipment also can for desk-top computer or mobile computer etc. can access network and user can be made freely to download and install the intelligent electronic device of application software.Application software in the present embodiment is generally the APP etc. that can be installed in intelligent mobile phone or panel computer, and certainly, this application software also can for being installed on the application software in desk-top computer or mobile computer.In addition, the client in the present embodiment is generally and is arranged in subscriber terminal equipment and the application software that to a certain degree can manage subscriber terminal equipment, as Baidu mobile phone assistant etc.The present embodiment not limited subscriber terminal device, application software and be arranged at the concrete manifestation form of the client in subscriber terminal equipment.

Exemplarily, the application software recommendation request from client that network termination receives is generally user when performing certain operation on its subscriber terminal equipment, the application software recommendation request that the client of installing in this subscriber terminal equipment is triggered by this operation and generates; A concrete example: client is knowing that user is when searching for certain APP (as inputted APP title and click search button in browser or APP market), generates application software recommendation request, and sends; Another concrete example: client is knowing that user is when browsing certain APP (as checking the user comment etc. of certain APP), generates application software recommendation request and sends; Another concrete example: client, when knowing certain APP of user installation (the installation button as certain APP is clicked), generates application software recommendation request and sends; Destination address (as chained address etc.) in application software recommendation request is normally pre-set in client.

Exemplarily, the application software recommendation request in the present embodiment can be specially the message based on HTTP (HyperTextTransferProtocol, HTML (Hypertext Markup Language)).The present embodiment does not limit the agreement and message format etc. that application software recommendation request adopts.

Exemplarily, user's characteristic information is carried in application software recommendation request in the present embodiment, network-side only can obtain user's characteristic information from application software recommendation request, network-side also can obtain user's characteristic information from application software recommendation request and the local data stored, namely network-side can from application software recommendation request fetching portion user's characteristic information, and obtain other certain customers' characteristic informations from its local data stored.In addition, the present embodiment does not get rid of network-side after receiving application software recommendation request yet, to the implementation of client-requested user's characteristic information.

Exemplarily, the user's characteristic information in the present embodiment can comprise usually: the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user ask the application software information browsed and user ask in the application software information of installation any one or multiple.

Wherein, subscriber terminal apparatus information self available resource information (processing speed etc. as free memory size and processor) that can be specially the brand message of subscriber terminal equipment, type information and subscriber terminal equipment etc.Network-side locally when it gets subscriber terminal apparatus information can store this subscriber terminal apparatus information, so that during subsequently received application software recommendation request, the data that network-side can store from this locality, obtain the geographical location information at subscriber terminal equipment place.

Wherein, the geographical location information at subscriber terminal equipment place can be specially province or the city at subscriber terminal equipment place, also can be specially province and the city at subscriber terminal equipment place, can also be province city and district or the small towns etc. at subscriber terminal equipment place more specifically.Certainly, the geographical location information at subscriber terminal equipment place also can use longitude and latitude to represent.Network-side locally when it gets the geographical location information at active user's terminal device place can store this geographical location information, so that during subsequently received application software recommendation request, from the data that this locality stores, obtain the geographical location information at subscriber terminal equipment place.

S110, user's characteristic information is supplied to application software recommended models as input parameter, application software recommended models learns to obtain based on the historical data be concerned each application software.

Concrete, application software recommended models is previously provided with in the network-side of the present embodiment, this application software recommended models is mainly used in prediction user concern/interested application software, namely input the parameter needed for it to application software recommended models, the result that this application software recommended models can learn in advance according to it exports corresponding information.

All user's characteristic information all can be supplied to application software recommended models as input parameter by the present embodiment, when user's characteristic information includes the unwanted information of application software recommended models, certain customers' characteristic information also can be supplied to application software recommended models as input parameter by the present embodiment.

In addition, when only including the part input parameter needed for application software recommended models in user's characteristic information, application software recommended models in the present embodiment when its input parameter is not provided completely, can export corresponding recommended application software information.Also have, the present embodiment can arrange the information of the application software of not wishing appearance or in input parameter, arrange the number of times recommended for this client and this user's characteristic information in input parameter, thus when client can be made to wish to obtain new recommended application software information after receiving recommended application software information, application software recommended models does not export the recommended application software information (namely exporting new recommended application software information) of repetition as far as possible.

The application software recommended models pre-set in the network-side of the present embodiment can be one, also can be multiple.When application software recommended models is one, the application software recommended models arranged in network-side can for the application software recommended models (this application software recommended models can be called " see and see application software recommended models ") obtained based on learning the associated historical data browsed of application software, or can for the application software recommended models (this application software recommended models can be called " filling and dress application software recommended models ") to obtain based on learning the historical data of the associated installation of application software, or can for learning based on the geographic location history data of the subscriber terminal equipment be concerned application software and the application software recommended models (this application software recommended models can be called " region relative application software recommended models ") etc. obtained.When application software recommended models is multiple, the application software recommended models arranged in network-side can comprise any two or three in above-mentioned three application software recommended models.

Associated the browsing of above-mentioned application software refers to that user is after having browsed an application software, browse again Another application software, now two methods software is browsed by user-association, utilizes the relevant information of this two methods software can form the associated historical data browsed of application software.

The associated installation of above-mentioned application software refers to that user is after having installed an application software, Another application software has been installed again, now two methods software is installed by user-association, utilizes the relevant information of this two methods software can form the historical data of the associated installation of application software.

Above-mentioned application software be concerned can for searched, the application software of application software be mounted and application software viewed in any one or multiple.

In addition, it should be noted that, although three the application software recommended models exemplified above-mentioned can independently exist separately, but the present embodiment does not get rid of above-mentioned any two methods software recommend model or three application software recommended models are synthesized the possibility being set to an application software recommended models.

Exemplarily, when being provided with multiple application software recommended models in network-side, user's characteristic information can be supplied to all application software recommended models by network-side respectively, thus obtains the recommended application software information that each application software recommended models exports respectively; The particular content of the user's characteristic information that network-side also can obtain according to it determines user's characteristic information to be only supplied to certain applications software recommend model, thus obtains the recommended application software information of part application software recommended models output; A concrete example, the information of carrying of network-side in the application software recommendation request come according to client transmissions judges that user is when installing a certain application software, then network-side can determine user's characteristic information to be supplied to respectively " fill and dress application software recommended models " and " region relative application software recommended models "; Another concrete example, the information that network-side carries in the application software recommendation request come according to client transmissions judges that user is when searching for a certain application software, then can to determine user's characteristic information to be supplied to respectively " see and see application software recommended models " and " region relative application software recommended models " certain for network-side, and network-side also can determine user's characteristic information to be supplied to respectively " see see application software recommended models not only ", " fill but also dress application software recommended models " and " region relative application software recommended models ".The present embodiment not limiting network end, after receiving the application software recommendation request from client, judges to utilize part or all application software recommended models to carry out the specific implementation of application software recommendation.

Application software recommended models in the present embodiment normally network-side utilizes a large amount of historical datas including various dimensions information and constantly learns to obtain based on intelligent machine learning art, as network-side utilizes a large amount of historical datas including various dimensions information to make support vector machine carry out self study process, support vector machine finally can make network-side obtain application software recommended models by carrying out the process operations such as cluster analysis to a large amount of historical datas.Network-side is after obtaining application software recommended models for the first time, also should continue to safeguard accordingly current application software recommended models, improve current application software recommended models constantly to revise, thus the application software that raising application software recommended models is recommended meets the degree of user intention.After network-side can collect the new historical data of some in the use procedure of application software recommended models, these new historical data are utilized to make the intelligent machine learning arts such as support vector machine proceed learning manipulation.It can thus be appreciated that the application software recommended models in the present embodiment adopts data mining technology to arrange.

No matter application software recommended models in the present embodiment is in the first learning process arranged, or perfectly safeguards in learning process follow-up, the mode of learning that can adopt the mode of learning of self study or have tutor to supervise; In addition, the technological means that the learning process of application software recommended models can also adopt external forced to intervene, to force to revise the deviation existed in learning process.The present embodiment is not restricted to and arranges application software recommended models and the historical data that the concrete mode of learning adopted and study the adopt particular content and data dimension etc. that comprise.

Can comprise for carrying out improving the new historical data safeguarded to application software recommend model in the present embodiment: client after receiving application software recommending data that network-side issues and show user, user based on this display picture performed by the information (namely user is based on the associative operation information performed by application software recommending data) of corresponding operating.That is, the operation performed by application software that the present embodiment can utilize user to recommend based on application software recommended models is further revised application software recommend model.

S120, the recommended application software information formation application software recommending data exported according to application software recommended models, and issue to client.

Concrete, the recommended application software information of an application software recommended models output can be one or more application software information, when being provided with multiple application software recommended models in network-side, the quantity of the recommended application software information obtained can be more; The present embodiment can utilize obtained all recommended application software information to form application software recommending data, and the recommended application software information of obtained part also can be utilized to form application software recommending data.Because the application software recommending data in the present embodiment is by can symbolizing the user characteristic data of user characteristics and being obtained by the application software recommended models that data mining technology is set up; therefore; the present embodiment usually can be distinct for the application software recommending data that the user with different point of interest generates, thus the application software recommending data in the present embodiment can be called application software personalized recommendation data.

A concrete example, network-side is when the quantity a predetermined level is exceeded of the application software information that it obtains, can from all recommended application software information obtained the application software information of random selecting predetermined quantity, and utilize the application software information of the predetermined quantity of random selecting to form application software recommending data.

Another concrete example, network-side is when the quantity a predetermined level is exceeded of the application software information that it obtains, the priority corresponding according to each application software recommended models can choose the recommended application software information of predetermined quantity from all recommended application software information, and utilize the recommended application software information chosen based on priority to form application software recommending data.Priority corresponding to each application software recommended models can be arranged according to actual conditions, as being provided with in network-side when " see see application software recommended models not only ", " fill but also dress application software recommended models " and " region relative application software recommended models ", the priority that the priority that network-side can be arranged " fill not only dress application software recommended models " higher than the priority of " see but also see application software recommended models ", and is arranged " see and see application software recommended models " is higher than the priority of " region relative application software recommended models ".

In order to avoid the application software of recommending to user by user the generation of this phenomenon is installed, the network-side of the present embodiment can utilize the relevant information of the mounted application software of the subscriber terminal equipment at client place to filter the recommended application software information that application software recommend model exports, with comprise in the recommended application software information of filtering by the relevant information of the application software of user installation, afterwards, the recommended application software information after network-side can utilize filtration forms application software recommending data.

Network-side in the present embodiment can be previously stored with the relevant information (title and version etc. as application software) of current the installed application software of each subscriber terminal equipment, namely the relevant information of network-side to application software mounted in each subscriber terminal equipment is safeguarded, and network-side can by realizing with the information interaction of client to the maintenance of the relevant information of application software mounted in each subscriber terminal equipment; Like this, after network termination receives application software recommendation request, the relevant information of current the installed application software of the subscriber terminal equipment at client place can be obtained from the information that it prestores.In addition, network-side in the present embodiment also can adopt additive method to the relevant information of current the installed application software of the subscriber terminal equipment obtaining client place, such as, network-side after receiving application software recommendation request, by obtaining the relevant information of current the installed application software of the subscriber terminal equipment at client place with the information interaction of client.The present embodiment not limiting network end obtains the specific implementation of the relevant information of current the installed application software of the subscriber terminal equipment at client place; In addition, network-side also can not be filtered the recommended application software information that application software recommend model exports, and this filter operation can have been come by client.

In addition, the network-side of the present embodiment is in the process forming application software recommending data, the recommended application software information that can not only utilize application software recommended models to export is to form application software recommending data, and the recommended application software information that application software recommended models can also be utilized to export and other recommendation informations form application software recommending data together.

A concrete example, the recommended application software information that network-side can export according to application software recommended models and the operation project information preset form application software recommending data.Here operation project information can refer to the relevant information of the popularization activity of the respective item that network-side is carried out according to the operation demand of its reality, as operation cooperation application software information and the thematic project information of operation activity at least one; The thematic project information of above-mentioned operation activity is usually not relevant to application software, and the thematic project information of operation activity corresponding can have the program (as video frequency program) etc. of serial feature.In addition, the network-side of the present embodiment can by the priority of the recommended application software information higher than the output of application software recommended models of priority setting corresponding for operation project information, as priority corresponding for operation project information is set to limit priority, to be conducive to the popularization of respective item.

Embodiment two, application software recommend method.

Be intelligent mobile phone below with subscriber terminal equipment, application software be the APP be installed in intelligent mobile phone is example, the method for 2-6 to the present embodiment is described by reference to the accompanying drawings.

Setting network end (the large data mining service end as in network-side) obtains " see see application software recommended models not only ", " fill but also dress application software recommended models " and " region relative application software recommended models " three recommended models by the study of historical data, and network-side is after obtaining three recommended models, also constantly can collect historical data, and constantly utilize the historical data collected to carry out continuing the learning process of recommended models.The method flow of the present embodiment as shown in Figure 2.

In Fig. 2, S200, network-side (the data request service end as in network-side) receive the application software recommendation request from client.

S210, network-side (the data request service end as in network-side) obtain user's characteristic information from application software recommendation request, as the brand of intelligent mobile phone, model, free memory and user ask the APP information etc. of checking/installing.

S220, network-side (the data request service end as in network-side) judge whether to need to recommend to install the high APP of the degree of correlation to this client, not only judge whether to have needed utilization to fill but dress application software recommended models to obtain recommended APP, if need to recommend to install the high APP of the degree of correlation to client, then arrive step S221, otherwise, to step S230.

S221, network-side (the large data mining service end as in network-side) determine the input information of " filling and dress application software recommended models " according to user's characteristic information, and be supplied to " filling and dress application software recommended models ", the recommended APP information that " fill and dress application software recommended models " exports can return to data request service end by large data mining service end.Afterwards, to step S230.

S230, network-side (the data request service end as in network-side) judge whether to need to recommend to check the APP that the degree of correlation is high to this client, not only judge whether to have needed utilization to see but also seen that application software recommended models is to obtain recommended APP, if need to recommend to check the APP that the degree of correlation is high to client, then arrive step S231, otherwise, to step S240.

S231, network-side (the large data mining service end as in network-side) determine the input information of " see and see application software recommended models " according to user's characteristic information, and being supplied to " see and see application software recommended models ", the recommended APP information that " see and see application software recommended models " exports can return to data request service end by large data mining service end.Afterwards, to step S240.

S240, network-side (the data request service end as in network-side) judge whether to need to recommend to this client the APP that the region degree of correlation is high, namely judge whether to need to utilize region relative application software recommended models to obtain recommended APP, if need to recommend to client the APP that the region degree of correlation is high, then arrive step S241, otherwise, to step S250.

S251, network-side (the large data mining service end as in network-side) determine the input information of " region relative application software recommended models " according to user's characteristic information, and be supplied to " region relative application software recommended models ", the recommended APP information that " region relative application software recommended models " exports can return to data request service end by large data mining service end.Afterwards, to step S260.

260, network-side (the data request service end as in network-side) judges whether to need to recommend to run the APP information cooperated to this client, if need the APP information of recommending operation cooperation to client, then arrive step S261, otherwise, to step S270.

S261, network-side (the large data mining service end as in network-side) return corresponding information according to the APP information of the operation cooperation pre-set to data request service end.Afterwards, to step S270.

270, network-side (the data request service end as in network-side) judges whether to need to recommend operation activity thematic information to this client, if need to recommend operation activity thematic information to client, then arrives step S271, otherwise, to step S280.

S271, network-side (the large data mining service end as in network-side) return corresponding information according to the operation activity thematic information pre-set to data request service end.Afterwards, to step S280.

S280, network-side (the data request service end as in network-side) according to the intelligent mobile phone at client place current the APP information of installing filtration treatment is carried out to the recommended APP information that each model exports, during APP information a predetermined level is exceeded after filtration, therefrom can choose the APP information of predetermined quantity.When there is APP information and/or the operation activity thematic information of operation cooperation, forming application software recommending data together with the APP information cooperate the APP information finally determined and operation and/or operation activity thematic information, and issuing to client.When there is not APP information and/or the operation activity thematic information of operation cooperation, utilizing the APP information finally determined to form application software recommending data, and issuing to client.

Install in the application scenarios of the APP of Baidu in its intelligent mobile phone user, the method for the present embodiment issues to client the displaying picture that application software recommending data formed can be as shown in Figure 3.Check in its intelligent mobile phone in the application scenarios of a certain APP user, the method of the present embodiment issues to client the displaying picture that application software recommending data formed can be as shown in Figure 4, " changing " in Fig. 4 can change the recommended application software information of showing in picture, when as stored the recommended application software information of surplus in the client, the recommended application software information of the surplus that client stores according to this locality carries out frame updating displaying; For another example, client continues to network-side request, and network-side issues new recommended application software information according to the request of client to client, and client shows the recommended application software information newly issued.At current existence operation activity special topic, and user installs in the application scenarios of the APP of clan's war in its intelligent mobile phone, the method of the present embodiment issues to client displaying picture that application software recommending data formed can as shown in Figure 5, China on the tip of the tongue in Fig. 5 and like that strange skill video is current operation activity special topic.At the current APP that there is operation cooperation, and user downloads in the application scenarios of a certain APP in its intelligent mobile phone, the method of the present embodiment issues to client the displaying picture that application software recommending data formed can as shown in Figure 6, and the APP of the Baidu in Fig. 6 is the APP of current operation cooperation.

Embodiment three, application software recommend method.

Fig. 7 is the process flow diagram of the application software recommend method of the present embodiment, and the method shown in Fig. 7 mainly comprises step S700 and step S710.The executive agent of the method described in the present embodiment can be called as client, and the method described in the present embodiment can perform in subscriber terminal equipment, as by the execution such as intelligent mobile phone or panel computer.Below each step in Fig. 7 is described respectively.

S700, client generate application software recommendation request based on user to the operation of application software, and send this application software recommendation request to network-side.

Concrete, when user performs certain operation on its subscriber terminal equipment, the client of installing in this subscriber terminal equipment is triggered by this operation and generates application software recommendation request; A concrete example: client is knowing that user is when searching for certain APP (as inputted APP title and click search button in browser or APP market), generates application software recommendation request, and sends to network-side; Another concrete example: client is knowing that user is when browsing certain APP (as checking the user comment etc. of certain APP), generates application software recommendation request and sends to network-side; Another concrete example: client, when knowing certain APP of user installation (the installation button as certain APP is clicked), generates application software recommendation request and sends to network-side; Destination address (as chained address etc.) in application software recommendation request is normally pre-set in client.

Exemplarily, the application software recommendation request in the present embodiment can be specially the message based on HTTP.The present embodiment does not limit the agreement and message format etc. that application software recommendation request adopts.

Exemplarily, user's characteristic information can be carried in application software recommendation request by the client in the present embodiment.This user's characteristic information can comprise usually: the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user ask the application software information browsed and user ask in the application software information of installation any one or multiple; The content that the geographical location information at the content that subscriber terminal apparatus information wherein comprises, subscriber terminal equipment place comprises see the description in above-described embodiment one, can not be repeated.

S710, client receive the application software recommending data formed based on recommended application software information that network-side issues, and show application software recommending data.

Concrete, recommended application software information in the present embodiment is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and the application software recommended models network-side in the present embodiment learns to obtain based on the historical data be concerned each application software.About application software recommended models refers to the description in above-described embodiment one, be not repeated.

Also may include operation project information in the application software recommending data that client receives, this operation project information can comprise at least one in the application software information and the thematic project information of operation activity of runing cooperation.In addition, when including recommended application software information, the application software information of operation cooperation and priority corresponding to the thematic project information of operation activity in application software recommending data, client can consider this priority setting information in the process of showing picture to user, and namely client should preferentially show the content with high priority.Also have, when client has self-determined priority to arrange authority, the application software recommending data that client can receive based on it independently determines its content of preferentially showing, as preferentially shown the application software information that operation is cooperated or the thematic project information of operation activity etc., when user closes the picture of the application software information of the preferential operation cooperation shown or the thematic project information of operation activity, then show recommended application software information.

In order to avoid the recommended application software of showing to user by user the generation of this phenomenon is installed, the client of the present embodiment can utilize the relevant information of the mounted application software of its place subscriber terminal equipment to filter the recommended application software information received, with comprise in the recommended application software information of filtering by the relevant information of the application software of user installation, afterwards, the recommended application software information after client can utilize filtration shows corresponding picture to user.

Embodiment four, application software recommend method.The method flow process as shown in Figure 8.

In Fig. 8, S800, client send application software recommendation request to network-side (the data request service end as in network-side), and this application software recommendation request can carry user's characteristic information.

S810, client judge that whether this request is successful, as according to the response message that network-side returns, client judges that whether this request is successful, if unsuccessful, then arrive step S811; If success, then arrive step S820.

S811, unsuccessfully to process accordingly for request, as carried out the compatible fault-tolerant processing of the clients such as data fault-tolerant process and Network Abnormal.

S820, client judge whether include operation project information in the application software recommending data that network-side issues, if include operation project information, then arrive step S821, otherwise, to step S830.

S821, client carry out data fault-tolerant inspection to operation project information, and carry out displaying process to operation project information.Afterwards, to step S822.

S822, client judge whether to need the recommended application software information in application software recommend data to show, if need to show, then arrive step S830, otherwise the processing procedure of this method terminate.

S830, client carry out data fault-tolerant inspection to the recommended application software information in application software recommend data, arrive step S840 afterwards.

S840, client utilize the relevant information of the mounted application software of its place subscriber terminal equipment to filter the recommended application software information received, with comprise in the recommended application software information of filtering by the relevant information of the application software of user installation, arrive step S850 afterwards.

S850, client carry out sequence process according to priority corresponding to each recommended application software information to each recommended application software information, arrive step S860 afterwards.

S860, client carry out picture exhibition and interactive function process to the recommended application software information after sequence process, as formed the picture shown to user according to data type and page setup demand etc.

Embodiment five, application software recommendation apparatus.

The device of the present embodiment can be arranged in the computer equipment of network-side, and the primary structure of this device as shown in Figure 9.

In Fig. 9, application software recommendation apparatus mainly comprises: acquisition module 900, load module 910, application software recommended models 920, recommending data form module 930 and issue module 940, and this device can also optionally comprise: the first filtering module 950, choose in module 960 and study module 970 arbitrary one or more.

Acquisition module 900 is mainly suitable for the application software recommendation request according to receiving from client, obtains user's characteristic information.

Concrete, the application software recommendation request received from client is generally when user performs certain operation at its subscriber terminal equipment, the application software recommendation request that the client of installing in this subscriber terminal equipment is triggered by this operation and generates.The message based on HTTP can be specially from the application software recommendation request of client reception.

Exemplarily, user's characteristic information is carried from the application software recommendation request that client receives, acquisition module 900 only can obtain user's characteristic information from application software recommendation request, acquisition module 900 also can obtain user's characteristic information from application software recommendation request and the local data stored, namely acquisition module 900 can from application software recommendation request fetching portion user's characteristic information, and from network-side this locality store data obtain other certain customers' characteristic informations.In addition, the present embodiment does not get rid of acquisition module 900 after acquisition application software recommendation request yet, to the implementation of client-requested user's characteristic information.

Exemplarily, the user's characteristic information that acquisition module 900 gets can comprise usually: the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user ask the application software information browsed and user ask in the application software information of installation any one or multiple; The geographical location information at subscriber terminal apparatus information wherein and subscriber terminal equipment place is concrete as the description in above-described embodiment one, is not repeated.

Load module 910 is mainly suitable for user's characteristic information to be supplied to application software recommended models 920 as input parameter, and this application software recommended models 920 learns to obtain based on the historical data be concerned each application software.

Concrete, application software recommended models 920 is previously provided with in the network-side of the present embodiment, this application software recommended models 920 is mainly used in prediction user concern/interested application software, namely load module 910 inputs parameter needed for it to application software recommended models 920, and the result that this application software recommended models 920 can learn in advance according to it exports corresponding information.

All user's characteristic information all can be supplied to application software recommended models 920 as input parameter by load module 910, when user's characteristic information includes application software recommended models 920 unwanted information, certain customers' characteristic information also can be supplied to application software recommended models 920 as input parameter by load module 910.

In addition, when only including the part input parameter needed for application software recommended models 920 in user's characteristic information, application software recommended models 920 in the present embodiment when its input parameter is not provided completely, can export corresponding recommended application software information.

The application software recommended models 920 pre-set in the network-side of the present embodiment can be one, also can be multiple.When application software recommended models 920 is one, the application software recommended models 920 arranged in network-side can for the application software recommended models 920 obtained based on learning the associated historical data browsed of application software, or can for the application software recommended models 920 obtained based on learning the historical data of the associated installation of application software, or can for learning based on the geographic location history data of the subscriber terminal equipment be concerned application software and the application software recommended models 920 etc. obtained.When application software recommended models 920 is multiple, the application software recommended models 920 arranged in network-side can comprise any two or three in above-mentioned three application software recommended models 920.

In addition, it should be noted that, although three the application software recommended models 920 exemplified above-mentioned can independently exist separately, but the present embodiment does not get rid of above-mentioned any two methods software recommend model 920 or three application software recommended models 920 are synthesized the possibility being set to an application software recommended models 920.

Exemplarily, when being provided with multiple application software recommended models 920 in network-side, user's characteristic information can be supplied to all application software recommended models 920 by load module 910 respectively, thus obtains the recommended application software information that each application software recommended models 920 exports respectively, the particular content of the user's characteristic information that load module 910 also can obtain according to it determines user's characteristic information to be only supplied to certain applications software recommend model 920, thus obtains the recommended application software information of part application software recommended models 920 output, a concrete example, the information of carrying of load module 910 in the application software recommendation request come according to client transmissions judges that user is when installing a certain application software, then load module 910 can determine user's characteristic information to be supplied to respectively " fill and dress application software recommended models " and " region relative application software recommended models ", another concrete example, the information of the carrying of load module 910 in the application software recommendation request come according to client transmissions judges that user is when searching for a certain application software, then can to determine user's characteristic information to be supplied to respectively " see and see application software recommended models " and " region relative application software recommended models " certain for load module 910, load module 910 also can determine user's characteristic information to be supplied to respectively " see and see application software recommended models ", " fill and dress application software recommended models " and " region relative application software recommended models ".The present embodiment does not limit load module 910 after receiving the application software recommendation request from client, judges to utilize part or all application software recommended models 920 to carry out the specific implementation of application software recommendation.

Application software recommended models 920 in the present embodiment normally study module 970 utilization includes the historical data of various dimensions information and constantly learns to obtain based on intelligent machine learning art, as study module 970 utilizes the historical data including various dimensions information to make support vector machine carry out self study process, support vector machine finally can make network-side obtain application software recommended models 920 by carrying out the process operations such as cluster analysis to a large amount of historical datas.Study module 970 is after obtaining application software recommended models 920 for the first time, what also should continue safeguards accordingly to current application software recommended models 920, improve current application software recommended models 920 constantly to revise, thus the application software that raising application software recommended models 920 is recommended meets the degree of user intention.After study module 970 can collect the new historical data of some in the use procedure of application software recommended models 920, these new historical data are utilized to make the intelligent machine learning arts such as support vector machine proceed learning manipulation.

No matter study module 970 in the present embodiment is in the learning process of the first setting of application software recommended models 920, or in the learning process of follow-up perfect maintenance, the mode of learning that can adopt the mode of learning of self study or have tutor to supervise; In addition, the technological means that study module 970 can also adopt external forced to intervene in the learning process of application software recommended models 920, to force to revise the deviation existed in learning process.The present embodiment is not restricted to study module 970 arranges application software recommended models 920 and the concrete mode of learning that adopts and the historical data that adopts of study comprise particular content and data dimension etc.

Can comprise for carrying out improving the new historical data safeguarded to application software recommend model 920 in the present embodiment: client after receiving application software recommending data that network-side issues and show user, user based on this display picture performed by the information (namely user is based on the associative operation information performed by application software recommending data) of corresponding operating.That is, the operation performed by application software that study module 970 can utilize user to recommend based on application software recommended models 920 is further revised application software recommend model 920.

Recommending data forms the recommended application software information formation application software recommending data that module 930 is mainly suitable for exporting according to application software recommended models 920.

Issue module 940 to be mainly suitable for issuing to client the application software recommending data that recommending data forms module 930 formation.

First filtering module 950 is mainly suitable for filtering the recommended application software information that application software recommend model 920 exports according to the subscriber terminal equipment at client place mounted application software information.

Choose the priority that module 960 is mainly suitable for according to each application software recommended models 920 correspondence, from recommended application software information, choose the recommended application software information of predetermined quantity.

Concrete, the recommended application software information of application software recommended models 920 output can be one or more application software information, when being provided with multiple application software recommended models 920 in network-side, the quantity of the recommended application software information obtained can be more; The all recommended application software information that recommending data formation module 930 can utilize application software recommended models 920 to export is to form application software recommending data, and the recommended application software information of the part that also application software recommended models 920 can be utilized to export is to form application software recommending data.

A concrete example, recommending data forms module 930 when the quantity a predetermined level is exceeded of the application software information that application software recommended models 920 exports, can from all recommended application software information obtained the application software information of random selecting predetermined quantity, and utilize the application software information of the predetermined quantity of random selecting to form application software recommending data.

Another concrete example, when the quantity a predetermined level is exceeded of the application software information that application software recommended models 920 exports, choose module 960 can choose predetermined quantity from all recommended application software information recommended application software information according to the priority of each application software recommended models 920 correspondence, recommending data forms module 930 and utilizes the recommended application software information chosen based on priority to form application software recommending data.Priority corresponding to each application software recommended models 920 can be arranged according to actual conditions, as being provided with in network-side " see and see application software recommended models ", " fill and dress application software recommended models " and " region relative application software recommended models " when, priority arranges priority that module (not shown) can arrange " fill the not only dress application software recommended models " priority higher than " see but also see application software recommended models ", and the priority of priority higher than " region relative application software recommended models " of " see and see application software recommended models " is set.

In order to avoid the application software of recommending to user by user the generation of this phenomenon is installed, first filtering module 950 can utilize the relevant information of the mounted application software of the subscriber terminal equipment at client place to filter the recommended application software information that application software recommend model 920 exports, with comprise in the recommended application software information of filtering by the relevant information of the application software of user installation, afterwards, the recommended application software information after recommending data formation module 930 can utilize filtration forms application software recommending data.

The first filtering module 950 in the present embodiment can be previously stored with the relevant information (title and version etc. as application software) of current the installed application software of each subscriber terminal equipment, namely the relevant information of the first filtering module 950 to application software mounted in each subscriber terminal equipment is safeguarded, and the first filtering module 950 can by realizing with the information interaction of client to the maintenance of the relevant information of application software mounted in each subscriber terminal equipment; Like this, after acquisition module 900 gets application software recommendation request, the first filtering module 950 can obtain the relevant information of current the installed application software of the subscriber terminal equipment at client place from the information that it prestores.In addition, first filtering module 950 also can adopt additive method to the relevant information of current the installed application software of the subscriber terminal equipment obtaining client place, such as, acquisition module 900 is after getting application software recommendation request, and the first filtering module 950 is by obtaining the relevant information of current the installed application software of the subscriber terminal equipment at client place with the information interaction of client.The present embodiment does not limit the specific implementation that the first filtering module 950 obtains the relevant information of current the installed application software of the subscriber terminal equipment at client place; In addition, the device of the present embodiment also can not filter the recommended application software information that application software recommend model 920 exports, and this filter operation can have been come by client.

In addition, the recommending data of the present embodiment forms module 930 in the process forming application software recommending data, the recommended application software information that can not only utilize application software recommended models 920 to export is to form application software recommending data, and the recommended application software information that application software recommended models 920 can also be utilized to export and other recommendation informations form application software recommending data together.

A concrete example, recommending data forms the recommended application software information that module 930 can export according to application software recommended models 920 and the operation project information preset forms application software recommending data.Here operation project information can refer to the relevant information of the popularization activity of the respective item that network-side is carried out according to the operation demand of its reality, as operation cooperation application software information and the thematic project information of operation activity at least one; The thematic project information of above-mentioned operation activity is usually not relevant to application software, and the thematic project information of operation activity corresponding can have the program (as video frequency program) etc. of serial feature.In addition, the priority of the recommended application software information exported higher than application software recommended models 920 that recommending data forms that priority corresponding to operation project information can arrange by module 930, as recommending data forms module 930, priority corresponding for operation project information is set to limit priority, to be conducive to the popularization of respective item.(procurator replys: priority is not here aforementioned priority, and operation project information etc. does not need through application software recommended models 920, and aforementioned priority is for application software recommended models 920)

Embodiment six, application software recommendation apparatus.

The device of the present embodiment can be arranged in subscriber terminal equipment, and as being arranged in the client in subscriber terminal equipment, the primary structure of this device as shown in Figure 10.

In Figure 10, application software recommendation apparatus mainly comprises: request generation module 1000, sending module 1010, receiver module 1020 and display module 1030.

Request generation module 1000 is mainly suitable for generating application software recommendation request based on user to the operation of application software; And sending module 1010 is mainly suitable for sending request to network-side the application software recommendation request that generation module 1000 generates.

Concrete, when user performs certain operation on its subscriber terminal equipment, request generation module 1000 is triggered by this operation and generates application software recommendation request; A concrete example: request generation module 1000 is knowing that user is when searching for certain APP (as inputted APP title and click search button in browser or APP market), generate application software recommendation request, sending module 1010 sends this application software recommendation request to network-side; Another concrete example: request generation module 1000 is knowing that user is when browsing certain APP (as checking the user comment etc. of certain APP), generate application software recommendation request, sending module 1010 sends this application software recommendation request to network-side; Another concrete example: request generation module 1000 is when knowing certain APP of user installation (the installation button as certain APP is clicked), generate application software recommendation request, sending module 1010 sends this application software recommendation request to network-side; Destination address (as chained address etc.) in application software recommendation request is normally pre-set in request generation module 1000.

Exemplarily, the application software recommendation request of asking generation module 1000 to generate can be specially the message based on HTTP.The present embodiment does not limit the agreement and message format etc. that application software recommendation request adopts.

Exemplarily, generation module 1000 is asked user's characteristic information can be carried in application software recommendation request.This user's characteristic information can comprise usually: the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user ask the application software information browsed and user ask in the application software information of installation any one or multiple; The content that the geographical location information at the content that subscriber terminal apparatus information wherein comprises, subscriber terminal equipment place comprises see the description in above-described embodiment one, can not be repeated.

Receiver module 1020 is mainly suitable for the application software recommending data generated in response to this application software recommendation request that reception network-side issues; And display module 1030 is mainly suitable for the application software recommending data that displaying receiver module 1020 receives.

Concrete, the recommended application software information that receiver module 1020 receives is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and above-mentioned application software recommended models network-side learns to obtain based on the historical data be concerned each application software.About application software recommended models refers to the description in above-described embodiment one and embodiment five, be not repeated.

Also may include operation project information in the application software recommending data that receiver module 1020 receives, this operation project information can comprise at least one in the application software information and the thematic project information of operation activity of runing cooperation.In addition, when including recommended application software information, the application software information of operation cooperation and priority corresponding to the thematic project information of operation activity in application software recommending data, display module 1030 can consider this priority setting information in the process of showing picture to user, and namely display module 1030 should preferentially show the content with high priority.Also have, when display module 1030 has self-determined priority to arrange authority, the application software recommending data that display module 1030 can receive based on it independently determines its content of preferentially showing, as preferentially shown the application software information that operation is cooperated or the thematic project information of operation activity etc., when user closes the picture of the application software information of the preferential operation cooperation shown or the thematic project information of operation activity, display module 1030 shows recommended application software information again.

Second filtering module 1040 is mainly suitable for, according to the mounted application software information of the subscriber terminal equipment at its place, filtering the application software recommending data that receiver module 1020 receives.

In order to avoid the recommended application software of showing to user by user the generation of this phenomenon is installed, second filtering module 1040 can utilize the relevant information of the mounted application software of its place subscriber terminal equipment to filter the recommended application software information that receiver module 1020 receives, with comprise in the recommended application software information of filtering by the relevant information of the application software of user installation, afterwards, the recommended application software information after display module 1030 can utilize filtration shows corresponding picture to user.

It should be noted that the present invention can be implemented in the assembly of software and/or software restraint, such as, each device of the present invention can adopt special IC (ASIC) or any other similar hardware device to realize.In one embodiment, software program of the present invention can perform to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, such as, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, such as, as coordinating with processor thus performing the circuit of each step or function.

To those skilled in the art, obviously, the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from the viewpoint of which, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, therefore, all changes be intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.The word such as first and second is used for representing title, and does not represent any particular order.

Although show and describe exemplary embodiment especially above, it will be appreciated by those skilled in the art that when not deviating from the spirit and scope of claims, can change to some extent in its form and details.Here sought protection is set forth in the dependent claims.Define in following numbering clause each embodiment these and other in:

1, an application software recommend method, wherein, the method comprises the following steps:

According to the application software recommendation request received from client, obtain user's characteristic information;

Described user's characteristic information is supplied to application software recommended models as input parameter, and described application software recommended models learns to obtain based on the historical data be concerned each application software;

Form application software recommending data according to the recommended application software information that application software recommended models exports, and issue to client.

2, the method according to clause 1, wherein, described user's characteristic information comprises: the application software information that the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user asks to browse, user ask at least one in the application software information of installation.

3, the method according to clause 1, wherein, described application software recommended models comprise following at least one:

The application software recommended models obtained based on learning the associated historical data browsed of application software;

The application software recommended models obtained based on learning the historical data of the associated installation of application software;

The application software recommended models that geographic location history data based on the subscriber terminal equipment be concerned application software learn and obtain.

4, the method according to clause 1, wherein, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

According to the subscriber terminal equipment at client place mounted application software information, the recommended application software information that application software recommend model exports is filtered, and utilize the recommended application software information after filtering to form application software recommending data.

5, the method according to clause 1 or 2 or 3 or 4, wherein, when described application software recommended models is multiple, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

The priority corresponding according to each application software recommended models chooses the recommended application software information of predetermined quantity from recommended application software information, and the recommended application software information chosen described in utilizing forms application software recommending data.

6, the method according to clause 1 or 2 or 3 or 4, wherein, described method also comprises:

Receive and store the next user of client transmissions based on the associative operation information performed by application software recommending data, and described associative operation information is used for the learning process of described application software recommended models.

7, the method according to clause 1 or 2 or 3 or 4, wherein, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

The recommended application software information exported according to application software recommended models and the operation project information preset form application software recommending data.

8, the method according to clause 7, wherein, described operation project information comprises: at least one in the application software information of operation cooperation and the thematic project information of operation activity, and the priority of recommended application software information that priority corresponding to described operation project information exports higher than application software recommended models.

9, an application software recommend method, wherein, the method comprises the following steps:

Client generates application software recommendation request based on user to the operation of application software, and sends this application software recommendation request to network-side;

Client receives the application software recommending data formed based on recommended application software information that network-side issues, and shows described application software recommending data;

Wherein, described recommended application software information is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and described application software recommended models network-side learns to obtain based on the historical data be concerned each application software.

10, the method according to clause 9, wherein, described client receives the application software recommending data formed based on recommended application software information that network-side issues, and shows that described application software recommending data comprises:

Recommended application software information in the application software recommending data that client receives according to the subscriber terminal equipment at its place mounted application software information butt joint is filtered, and shows the application software recommending data of the recommended application software information after including filtration.

11, an application software recommendation apparatus, wherein, comprising:

Acquisition module, is suitable for the application software recommendation request according to receiving from client, obtains user's characteristic information;

Load module, be suitable for described user's characteristic information to be supplied to application software recommended models as input parameter, described application software recommended models learns to obtain based on the historical data be concerned each application software;

Recommending data forms module, and the recommended application software information being suitable for exporting according to application software recommended models forms application software recommending data; And

Issue module, be suitable for formed application software recommending data to be handed down to client.

12, the device according to clause 11, wherein, described user's characteristic information comprises: the application software information that the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user asks to browse, user ask at least one in the application software information of installation.

13, the device according to clause 11, wherein, described application software recommended models comprise following at least one:

14, the device according to clause 11, wherein, described device also comprises:

First filtering module, is suitable for filtering the recommended application software information that application software recommend model exports according to the subscriber terminal equipment at client place mounted application software information, and

Described recommending data forms module and is suitable for utilizing the recommended application software information after filtering to form application software recommending data.

15, the device according to clause 11 or 12 or 13 or 14, wherein, when described application software recommended models is multiple, described device also comprises:

Choose module, for the priority corresponding according to each application software recommended models, from recommended application software information, choose the recommended application software information of predetermined quantity, and

Described recommending data forms the recommended application software information formation application software recommending data that module is suitable for choosing described in utilization.

16, the device according to clause 11 or 12 or 13 or 14, wherein, described device also comprises:

Study module, is suitable for utilizing user based on the associative operation information performed by application software recommending data, carries out the learning process of described application software recommended models.

17, the device according to clause 11 or 12 or 13 or 14, wherein, described recommending data forms module and is specifically suitable for:

18, the device according to clause 17, wherein, described operation project information comprises: at least one in the application software information of operation cooperation and the thematic project information of operation activity, and the priority of recommended application software information that priority corresponding to described operation project information exports higher than application software recommended models.

19, an application software recommendation apparatus, is arranged in client, and wherein, this device comprises:

Request generation module, is suitable for generating application software recommendation request based on user to the operation of application software;

Sending module, is suitable for sending to network-side the application software recommendation request generated;

Receiver module, is suitable for the application software recommending data generated in response to described application software recommendation request that reception network-side issues;

Display module, is suitable for showing described application software recommending data;

Wherein, described application software recommending data is that network-side generates based on recommended application software information, described recommended application software information is that its user's characteristic information obtained according to application software recommendation request is supplied to application software recommended models as input parameter by network-side, and exported by application software recommended models, and described application software recommended models network-side learns to obtain based on the historical data be concerned each application software.

20, the device according to clause 19, wherein, described device also comprises:

Second filtering module, is suitable for, according to the mounted application software information of the subscriber terminal equipment at its place, filtering the application software recommending data received, and

Described display module is suitable for showing the application software recommending data after filtering.

Claims

1. an application software recommend method, wherein, the method comprises the following steps:

2. method according to claim 1, wherein, described user's characteristic information comprises: the application software information that the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user asks to browse, user ask at least one in the application software information of installation.

3. method according to claim 1, wherein, described application software recommended models comprise following at least one:

4. method according to claim 1, wherein, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

5. the method according to claim 1 or 2 or 3 or 4, wherein, when described application software recommended models is multiple, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

6. the method according to claim 1 or 2 or 3 or 4, wherein, described method also comprises:

7. the method according to claim 1 or 2 or 3 or 4, wherein, the described recommended application software information exported according to application software recommended models forms application software recommending data and comprises:

8. method according to claim 7, wherein, described operation project information comprises: at least one in the application software information of operation cooperation and the thematic project information of operation activity, and the priority of recommended application software information that priority corresponding to described operation project information exports higher than application software recommended models.

9. an application software recommend method, wherein, the method comprises the following steps:

10. method according to claim 9, wherein, described client receives the application software recommending data formed based on recommended application software information that network-side issues, and shows that described application software recommending data comprises:

11. 1 kinds of application software recommendation apparatus, wherein, comprising:

12. devices according to claim 11, wherein, described user's characteristic information comprises: the application software information that the application software information that subscriber terminal apparatus information, the geographical location information at subscriber terminal equipment place, user ask to search for, user asks to browse, user ask at least one in the application software information of installation.

13. devices according to claim 11, wherein, described application software recommended models comprise following at least one:

14. devices according to claim 11, wherein, described device also comprises:

15. devices according to claim 11 or 12 or 13 or 14, wherein, when described application software recommended models is multiple, described device also comprises:

Choose module, be suitable for the priority corresponding according to each application software recommended models, from recommended application software information, choose the recommended application software information of predetermined quantity, and

16. devices according to claim 11 or 12 or 13 or 14, wherein, described device also comprises:

17. devices according to claim 11 or 12 or 13 or 14, wherein, described recommending data forms module and is specifically suitable for:

18. devices according to claim 17, wherein, described operation project information comprises: at least one in the application software information of operation cooperation and the thematic project information of operation activity, and the priority of recommended application software information that priority corresponding to described operation project information exports higher than application software recommended models.

19. 1 kinds of application software recommendation apparatus, are arranged in client, and wherein, this device comprises:

20. devices according to claim 19, wherein, described device also comprises: