CN101334792A - Personalized service recommendation system and method - Google Patents
Personalized service recommendation system and method Download PDFInfo
- Publication number
- CN101334792A CN101334792A CNA2008101164770A CN200810116477A CN101334792A CN 101334792 A CN101334792 A CN 101334792A CN A2008101164770 A CNA2008101164770 A CN A2008101164770A CN 200810116477 A CN200810116477 A CN 200810116477A CN 101334792 A CN101334792 A CN 101334792A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- recommendation
- database
- personalized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses an individualized service recommendation system and a corresponding method including the following steps: various operation information existing on a terminal is monitored by a user information collector and after a pre-processing the operation information is stored in a user information database; and if the user information database is updated, a user behavior analyzer is started for analysis; the user behavior analyzer scans the user information database and extracts the new user information and stores the new information in a resource information database, and then new recommendation strategies are computed and stored in a recommendation strategy database; a context sensing processor senses the present context of the user and sends out the present context description information and an individualized recommendation processor is started; the individualized recommendation processor acquires the present context information after receiving the information from the context sensing processor and also acquires a matched optimal recommendation strategy by searching the recommendation strategy database and then matches the proper resource information according to the optimal recommendation strategy and by searching the resource information database so as to generate the individualized recommendation service in real time.
Description
Technical field
The present invention relates to the Computer Applied Technology field, particularly relate to a kind of personalized service recommendation system and method.
Background technology
Personalized recommendation system is used to help the user to seek interested content in a large amount of information, and " personalization " service that it embodies is more and more accepted by various fields such as business web site, library automations at present, becomes their important function.The personalized service technology provides different services for different users, to meet the different needs.Personalized service is learnt user's interest and behavior by Collection and analysis user profile, thereby realizes the initiatively purpose of recommendation.Have many individuation service systems at present, they have proposed various thinkings to realize personalized service.Can be divided into two kinds according to the recommended technology that it adopted: rule-based system and information filtering system.Information filtering system can be divided into the system and the collaborative filtering system of content-based filtration again.
In order to realize personalized service, at first need to follow the tracks of and learn user's interest and behavior, and design a kind of proper means of expression.In order to give the user resource recommendation, must organize resource, choose the feature of resource, and adopt the suitable way of recommendation.In addition, also the architecture of necessary taking into account system is considered the pros and cons that realize at server end, client and agent side.
General, personalized recommendation system need pass through user modeling, project coupling and recommend the output three phases to realize personalized recommendation.The process of the user modeling knowledge that to be acquiring and maintaining relevant with user interest, demand or custom, its result will produce a user model of representing the peculiar background knowledge of user or interest, demand.The project matching stage will be a foundation with this model, use various recommended technologies to seek out the project that is complementary with it, recommend output stage that these projects are presented to the user with predicted value, Top-N recommendation or other forms then.
User's description document of different individuation service systems respectively has its characteristics, user's description document can be divided on the content based on interest and based on two types of behavior.User's description document based on interest can be expressed as weight vectors model, type hierarchy structural model, weighting semantic net model, bookmark and bibliographic structure etc.User's description document based on behavior can be expressed as user's browse mode or access module.User's description document can be organized with file, also can organize with relational database or other databases.
When the user used individuation service system the 1st time, system can require the user to register oneself essential information and interested content, and user profile also can implicitly be collected by system.After what a user's description document of customization, system can allow the user independently revise, and also can be revised by system self-adaption ground.System wants adaptive modification user profile, must analyze active user's behavior according to the information source of study, thereby adjusts the weight of user interest or adjust the user interest hierarchical structure.According to the information source of study, the method for usertracking can be divided into two kinds: explicit tracking and implicit expression are followed the tracks of.Explicit tracking is meant that the system requirements user feeds back the resource of recommending and estimates, thereby reaches the destination of study.Implicit expression follows the tracks of not require what information the user provides, and all tracking are all finished automatically by system, and implicit expression is followed the tracks of can be divided into behavior tracking and daily record excavation again.
The description of resource and user's description are closely related, and general way is to express user and resource with same mechanism, can represent with content-based method with based on the method for classification.Content-based method is to represent resource from the extraction information of resource own, for example weighting keyword vector.Method based on classification is to utilize classification to represent resource, and document resources is classified to be helped document is recommended the document users interest.The method of text classification has multiple, naive Bayesian for example, k arest neighbors method and support vector machine.
Personalized recommendation can adopt the technology and the collaborative filter techniques of rule-based technology, content-based filtration.
There are much relations the position that distributes based on the personalized service architecture of Web and user's description document.Existing personalized service recommendation system and method can leave server end, client, agent side in for the user's description document that relates to user privacy information.
User's description document of most of individuation service system all leaves server end in.Advantage is to avoid the transmission of user's description document, except supporting content-based filtration, can also support collaborative filtering.Shortcoming is that user's description document can not be shared between different Web uses.
The advantage that user's description document is stored on the agency is not only can support content-based filtration and collaborative filtering, also supports user's description document sharing between different Web use, and shortcoming is possible need the transmission user description document.
The advantage that user's description document is stored in client is that user's description document can be shared between different application, and shortcoming is to carry out content-based filtration, has limited the recommendation ability.
Summary of the invention
The object of the present invention is to provide a kind of personalized service recommendation system and method, it can keep the recommendation ability suitable with existing commending system under the prerequisite of the privacy information of protecting the terminal user effectively, and has expanded the scope of service recommendation.
The invention provides a kind of personalized service recommendation system, comprise at least one terminal, described terminal comprises: user information collection device, User Information Database, user behavior analysis device, resource information database, recommendation policy database, context-aware processor and personalized recommendation processor, wherein:
Described user information collection device, be used for the various actions that supervisory user takes place on terminal, original user data with collection terminal, this original user data is carried out obtaining user profile after the pre-service, deposit described user profile in User Information Database, and according to circumstances send triggering message to the user behavior analysis device;
Described User Information Database is used to deposit the user profile clauses and subclauses by described user information collection device output, carries out user behavior analysis for the user behavior analysis device;
Described user behavior analysis device is used for scanning described User Information Database after receiving described triggering message, therefrom extracts new resource information, charges to resource information database, calculates new recommendation strategy, charges to the recommendation policy database;
Described resource information database is used to deposit the resource information that is produced by described user behavior analysis device analysis;
Described recommendation policy database is used to deposit the recommendation strategy that is generated by described user behavior analysis device, and should recommend strategy to be used for personalized recommendation processor generation recommendation service;
Described context-aware processor, the current context that is used for the perception user, the timing scan User Information Database, the record clauses and subclauses and the newly-increased record clauses and subclauses of therefrom inquiring about two class special users' latest update, and according to circumstances send triggering message to the personalized recommendation processor;
Described personalized recommendation processor, after being used to receive triggering message from the context-aware processor, obtain current contextual information, recommend policy database by retrieval, the optimum that obtains coupling is recommended strategy, and tactful according to the optimum recommendation by the retrieve resources information database, the coupling adequate resources generates the personalized recommendation service in real time.
Described personalized service recommendation system also comprises and shares information server and user control interface, wherein:
Described shared information server is used for for based on the information sharing of the mode of sharing information server the time, deposits the resource information that the terminal user allows and upload and recommends strategy, for the other-end user search and download use;
Described user control interface is used for adjust recommending strategy and the information sharing manager is configured and manages, and control information Sharing Management device.
The information sharing of described information sharing manager realizes by following dual mode: a kind of is the P2P mode, can be point-to-point shared between user terminal; Another kind is based on the mode of sharing information server, and the user will share information stores to sharing on the information server, use for other user inquirings.
Described personalized recommendation processor can be supported the rule-based filtration in the personalized service recommendation, content-based filtration and collaborative filtering simultaneously.
Described user information collection device and context-aware processor are as independently program or program module are moved simultaneously.
The present invention also provides a kind of personalized service recommendation method, comprises step:
Steps A. the various operation informations that the monitoring of user information collection device is carried out on terminal, original user data with collection terminal, described original user data is carried out obtaining user profile after the pre-service, deposit described user profile in User Information Database, if User Information Database upgrades, then start the user behavior analysis device and analyze;
Step B, user behavior analysis device scanning User Information Database therefrom extracts new user profile and charges to resource information database, calculates new recommendation strategy and charges to the recommendation policy database;
Step C, context-aware processor perception user's current context, from User Information Database information extraction in real time, current context-descriptive information is exported in the variation of analysis context, starts the personalized recommendation processor;
Step D, the personalized recommendation processor, after being used to receive current context-descriptive information from the context-aware processor, obtain current contextual information, recommend policy database by this locality or the retrieval of information sharing manager, the optimum that obtains coupling is recommended strategy, and according to recommending strategy by this locality or information sharing manager retrieve resources information database, the coupling adequate resources generates the personalized recommendation service in real time.
Described step D comprises step:
Step D1, personalized recommendation processor with current context-descriptive information as input, and the retrieval local terminal first recommend policy database, if find the recommendation strategy of coupling, then, retrieve first resource information database of local terminal, find the resource information of coupling according to strategy;
Step D2, if it fails to match, the personalized recommendation processor sends query requests, wait-for-response to the information sharing manager;
Step D3, the information sharing manager sends query requests to attachable second terminal or shared information server, and wait-for-response;
Step D4, the information sharing manager of attachable second terminal or shared information server is accepted query requests, and as input, retrieval and coupling are recommended strategy and resource information with current context-descriptive information;
Step D5, local information sharing manager receives response message, upgrades resource information database and recommends policy database, and trigger message to one of personalized recommendation processor transmission, start the operation of personalized recommendation processor, generate the personalized recommendation service in real time.
Described personalized service recommendation method also comprises step:
Step e, the local terminal user, optimizes and recommends strategy by user control interface according to recommendation effect, promotes recommendation effect;
Step F, the terminal user is according to result of use, and the acquisition strategy of configuration information sharing policy and shared information promotes recommendation effect.
The invention has the beneficial effects as follows: personalized service recommendation system of the present invention and method, it can effectively be protected user privacy information, can support the rule-based filtration in the personalized service recommendation, content-based filtration and collaborative filtering again simultaneously; Its recommendable service range is not limited only to the Web resource, also comprises the local resource of terminal and the resource on every side of terminal; Further, the user can not be subjected to anyly restrictedly to use existing various personalized recommendation to serve when using recommendation service provided by the present invention.
Description of drawings
Fig. 1 is the structural drawing of personalized service recommendation system embodiment of the present invention;
Fig. 2 is the process flow diagram of personalized service recommendation method embodiment of the present invention;
Fig. 3 is the transmission diagram of data among the personalized service recommendation method embodiment of the present invention.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer,, a kind of personalized service recommendation system of the present invention and method are further elaborated below in conjunction with drawings and Examples.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
Problem to be solved by this invention is to provide a kind of personalized service recommendation system and method based on terminal.Can under the prerequisite of the privacy information of effectively protecting the terminal user, keep the recommendation ability suitable, and expand the scope of service recommendation with existing commending system.
Fig. 1 is the structural drawing of personalized service recommendation system embodiment of the present invention, and with reference to Fig. 1, a kind of personalized service recommendation system of the present invention comprises at least one terminal.
Described terminal can be the terminal of arbitrary form, includes but not limited to PC, mobile phone, embedded handhold equipment etc., but is not limited to these terminal forms, as long as have certain computing power.
Personalized service recommendation system of the present invention is made up of a plurality of independently modules and data storage, realizes contact and cooperation between each standalone module by sharing message exchange and message.
Wherein user information collection device and the parallel running of context-aware processor, other modules are moved by message trigger.
As shown in Figure 1, described terminal of the present invention comprises user information collection device, User Information Database, user behavior analysis device, resource information database, recommendation policy database, context-aware processor, personalized recommendation processor, information sharing manager, user control interface, wherein:
Described user information collection device, be used for the various actions that supervisory user takes place on terminal, original user data with collection terminal, this original user data is carried out obtaining user profile after the pre-service, deposit user profile in User Information Database, and according to circumstances send triggering message to the user behavior analysis device;
If User Information Database upgrades, the user information collection device starts the user behavior analysis device and analyzes by message trigger.
The Data Source of described user information collection device mainly comprises: operating system level logs, web browser access record, user's operation behavior record.The memory location of operating system level logs and Web browser Visitor Logs is open and fixing, and the user information collection device can obtain raw data by regularly reading these data storage files.
User's operation behavior record is different with above-mentioned two kinds of raw data, do not have the Data Source that can directly use, and different operating system need adopt diverse ways to obtain.At class Unix system, there is a group system order can obtain the relevant information of user operation, for example, w order inquiry utmp file also shows each user in the current system and progress information that it moves.The user information collection device can be carried out these orders by the exec system call, and obtains execution result by pipeline or socket communication, thereby obtains user's operation behavior record.Simpler method directly reads the operated log file of these orders, but need understand its memory location in advance.At the Windows system, one of method is MSAA (the Microsoft Active Accessibility) technology that adopts Microsoft to provide.This technology is used to provide interactive online help, and operations that can the captured in real time user is as long as realize that according to standard its client-side program just can realize real-time user's operation behavior record that obtains.
Described original user data includes but not limited to following content: user totem information, user's operation information, user operate the resource that start time, user manipulate.
The data pre-service that described user data collection device carries out, be meant that the raw data that will collect is organized into the data entries with following meaning of one's words: what application program what user uses carried out what resource of what action need between when and obtains what result, and deposits these clauses and subclauses in User Information Database.
Described User Information Database is used to deposit the user profile clauses and subclauses by the output of user information collection device, and this user profile is used for user behavior analysis.
Described User Information Database can be a logical storage, does not limit the specific implementation type, can be relevant database, also can be file.Its main field is:
Sequence number: be used to identify every record, major key;
User ID: be used to identify each user, adopt system's login name of user;
The last time of origin: the minute book bar writes down the time of the last time appearance of described information;
Application name: the application name that recording user uses;
Action name: recording user action name at this moment;
The result of operation: the reflection that operation causes, for example startup of new process;
Cumulative number: the multiplicity of the described information of this record;
Updating mark: whether this record with respect to preceding renewal has taken place once;
Correlated resources: mainly comprise document resources, device resource and Internet resources, this field is a compound field, and the sub-table structure that comprises is:
Resource name: the title of record resource;
The reference address of resource: the accessible address of record resource;
The access rights of resource: the access rights of record resource;
Described user behavior analysis device, receive trigger message after, the scanning User Information Database therefrom extracts new resource information, charges to resource information database, calculates new recommendation strategy, charges to the recommendation policy database.
Described recommendation strategy includes but not limited to correlation rule.
Described user behavior analysis device at first carries out whole scan to User Information Database, selects record that upgraded and the record that increases newly.Obtain extracting the correlated resources field of main field in the described User Information Database after these records, obtain resource information, resource information includes but not limited to equipment class resource, document class resource, program class resource etc.Resource information is deposited in resource information database after classifying.Main classification includes but not limited to: equipment class resource, document class resource, program class resource etc.Above-mentioned classification also can be divided multi-level subclass.Finish after the resource information extraction, the user behavior analysis device carries out association rule mining to User Information Database, can use the association rules mining algorithm of present main flow herein, does not do concrete qualification.The correlation rule that generates deposits the recommendation policy database in.Correlation rule adopts the IF-THAN structure representation.For example: IF (Open a file with MSWORD) THEN (Using a printer).
Described resource information database is used to deposit the resource information that is produced by the analysis of user behavior analysis device.Its field mainly comprises:
Sequence number: major key;
Resource class code: identifying resource classification;
Resource name: the title of resource;
The reference address of resource: the accessible address of record resource;
The access rights of resource: the access rights of record resource;
Described database is a logical storage, does not limit the specific implementation type, can be relevant database, also can be file.
Described recommendation policy database is used to deposit the recommendation strategy that is generated by the user behavior analysis device, and should recommend strategy to be used for personalized recommendation processor generation recommendation service, and its main field comprises:
Sequence number: major key;
Former piece: the precondition of strategy;
Consequent: the content recommendation of strategy;
Weights: degneracy, represent the credibility of this strategy;
Described context-aware processor is used for perception user's current context.Context-aware processor timing scan User Information Database, therefrom inquire about the record clauses and subclauses and the newly-increased record clauses and subclauses of two class special users' latest update, come perception user's current context, and according to circumstances send triggering message to the personalized recommendation processor.
Described context is meant the real-time feature description information of terminal self software and hardware state and the real-time feature description information of terminal surrounding ambient condition.
Two class special users comprise virtual system representative of consumer and virtual environment representative of consumer.This two class special user's user profile is collected by the user information collection device, and method and domestic consumer are just the same.But on the meaning of one's words of information difference is arranged.What the virtual system representative of consumer was represented is the terminal hardware environment, and what the virtual environment representative of consumer was represented is the surrounding environment of terminal.The representative of its every user profile record be the contextual variation of terminal.For example following two records:
(" virtual system representative of consumer ", " 200801011224 ", " device loads deletion ", " disconnection of wireless network ", " successfully disconnecting ", " 1 ", " renewal ", " ");
(" virtual environment representative of consumer ", " 200801011224 ", " location aware ", " handoff environment ", " switching is finished ", " 1 ", " renewal ", " ");
The context-aware processor can obtain a current contextual high-rise meaning of one's words by the as above record of two User Information Databases: environment switches, and wireless network lost efficacy.Obtain after this contextual information, it is added trigger message, send to the personalized recommendation processor.
Described personalized recommendation processor, after being used to receive message from the context-aware processor, obtain current contextual information, recommend policy database by retrieval, the optimum that obtains coupling is recommended strategy, and tactful according to the optimum recommendation by the retrieve resources information database, the coupling adequate resources generates the personalized recommendation service in real time.
The input of described personalized recommendation processor is from the contextual information of resource information database, recommendation policy database and the output of context-aware processor, and it is output as recommendation service tabulation and executive plan;
The personalized recommendation processor can be supported the rule-based filtration in the existing personalized service recommendation, content-based filtration and collaborative filtering simultaneously among the present invention.
At first use content-based filter algorithm to select available recommendation strategy.If fail, then pass through the method for the recommendation strategy of acquisition other-end or shared information server, carry out collaborative filtering.Obtain recommending carrying out rule-based filtration after the strategy, finish recommendation process.
The recommendation service tabulation and the executive plan of described output can be to present to the user with predicted value, Top-N recommendation or other forms.
Described user control interface is used for adjust recommending strategy and the information sharing manager is configured and manages, and control information Sharing Management device.
User control interface is the passage that the terminal user interferes the terminal works activity, i.e. the interface of system of the present invention.The terminal user recommends strategy by the user control interface adjustment and the information sharing manager is configured and manages, and control information Sharing Management device.Mainly comprise following operation: the recommendation strategy that appointment can be shared, switch P 2P sharing mode, switch are based on the sharing mode of central server, shared local information.
Preferably, the configuration of information sharing and management are fully by user control interface control, and more preferably, described information sharing could be shared information through the explicit permission of user control interface, and the risk of pointing out the user to bring.
Described information sharing manager is used to make shared resource information and recommendation strategy between the different terminals, and obtains resources shared information and recommend strategy.The terminal that needs that had by each that it was both passive is visited by the mode of authorizing, and the resource that self is allowed be shared initiatively is distributed to a terminal again.
The information sharing of described information sharing manager realizes by following dual mode: a kind of is the P2P mode, can be point-to-point shared between user terminal; Another kind is based on the mode of sharing information server, and the user will share information stores to sharing on the information server, use for other user inquirings.
As a kind of embodiment, in information sharing, if based on the mode of sharing information server, personalized service recommendation system then of the present invention, also comprise shared information server, be used to deposit resource information and the recommendation strategy that the terminal user allows and uploads, also download for the other-end user search and use.
The user information collection device can be used as independently program module or independently software module run on the user terminal.The various operations that user information collection device supervisory user is carried out on terminal, the source of user's operation information comprise interface or the data buffer that user's operation information is obtained in possible being used to that the application program of operating system daily record, application log and other operating systems provides.This user information collection device is adjusted according to the operating system of terminal and main application environment self.
Preferably, this user information collection device is collected after the raw information of user operation, increase without limitation in order not make database, if identical operations is arranged, and update time then, and cumulative number increased 1.
The user profile that the user information collection device generates includes but not limited to time, action type, operating resource type, resource access address, resource access mode, resource access authority, resource use start time, resource use concluding time, cumulative number etc.
The user profile of this generation deposits User Information Database in by the user information collection device.
The user information collection device sends a message to the user behavior analysis device after each update user information database, start the user behavior analysis device and analyze; User behavior analysis device scanning User Information Database therefrom extracts new resource information and deposits resource information database in, calculates new recommendation strategy simultaneously, if there is new recommendation strategy to generate, then upgrades and recommends policy database.
The context-aware processor is as independently program module or software module operation, from User Information Database information extraction in real time, the variation of analysis context; If variation has taken place context, then upgrade contextual information, and send a message initiated personalized recommendation processor.
The personalized recommendation processor receives after the message from the context-aware processor, at first obtains current contextual information; Based on context information retrieval is recommended policy database then, and the optimum that obtains coupling is recommended strategy; Obtain recommending after the strategy, the personalized recommendation processor is according to recommending tactful retrieve resources information database, the coupling adequate resources, and carry out adequate resources according to contextual information and recommend, for example start next step local resource that will use in advance, perhaps provide a resource of using possibly to connect tabulation.
The information sharing manager is accepted user's direct control as independent program module or independent software module operation by user control interface.The information sharing manager has two kinds of functions: 1, share local information; 2, obtain the shared information of other-end.There is dual mode to realize at these two kinds of functions: 1, P2P mode; 2, based on the central server mode.
Fig. 2 is the process flow diagram of personalized service recommendation method embodiment of the present invention, and Fig. 3 is the transmission diagram of data among the personalized service recommendation method embodiment of the present invention, and with reference to Fig. 2, Fig. 3, a kind of personalized service recommendation method of the present invention comprises the following steps:
Steps A, the various operation informations that the monitoring of user information collection device is carried out on terminal, original user data with collection terminal, this original user data is carried out obtaining user profile after the pre-service, deposit described user profile in User Information Database, and judge whether User Information Database upgrades, if then start the user behavior analysis device and analyze;
The user information collection device is collection terminal user's various information in real time, and executable operations 1 deposits the information after handling in User Information Database; If User Information Database upgrades, then produce one and trigger message, executable operations 2 starts the user behavior analysis device;
Described User Information Database upgrades, be divided into two kinds of situations again: a kind of is newly-increased data, another kind is that the number of times of some operation informations of repeating on terminal of user arrives certain threshold value, under the both of these case, thinks that all renewal has taken place User Information Database.
For the former, User Information Database directly upgrades, and will increase one to the cumulative frequency of the user profile that should increase newly, and produces one and trigger message, starts the user behavior analysis device;
For the latter, during the certain threshold value of number of times no show of the some operation informations that on terminal, repeat as the user, User Information Database upgrades original users information time corresponding, and will increase one to cumulative frequency that should original users information, and does not start the user behavior analysis device; And has only the number of times of the some operation informations that on terminal, repeat as the user, promptly to cumulative frequency that should original users information, when arriving certain threshold value, illustrate that this operation information is often used this moment, need the user behavior analysis device to analyze, so that recommend, User Information Database just produces one and triggers message so, starts the user behavior analysis device.
Described threshold value is set according to concrete operations information.Different operating information corresponding threshold difference.
Step B, user behavior analysis device scanning User Information Database therefrom extracts new user profile and charges to resource information database, calculates new recommendation strategy and charges to the recommendation policy database;
Step C, context-aware processor perception user's current context extracts user profile in real time from User Information Database, and current context-descriptive information is exported in the variation of analysis context, starts the personalized recommendation processor;
Step D, the personalized recommendation processor, after being used to receive current context-descriptive information from the context-aware processor, obtain current contextual information, recommend policy database by this locality or the retrieval of information sharing manager, the optimum that obtains coupling is recommended strategy, and according to recommending strategy by this locality or information sharing manager retrieve resources information database, coupling adequate resources information generates the personalized recommendation service in real time.
Policy database is recommended in described retrieval, both can only retrieve local recommendation policy database, can retrieve long-range shared recommendation policy database by the information sharing manager again.
The personalized recommendation processor, be used to receive message from the context-aware processor after, executable operations 11, obtain contextual information, executable operations 14,16 is recommended policy database by this locality or the retrieval of information sharing manager, executable operations 10, the optimum that obtains coupling is recommended strategy; Executable operations 15,16 then, and according to recommending strategy by this locality or information sharing manager retrieve resources information database, executable operations 9 is mated adequate resources, generates the personalized recommendation service in real time.
Specifically further, described step D comprises the following steps:
Step D1, personalized recommendation processor with current context-descriptive information as input, and the retrieval local terminal first recommend policy database, if find the recommendation strategy of coupling, then, retrieve first resource information database of local terminal, find the resource of coupling according to strategy;
Step D2, if it fails to match, the personalized recommendation processor sends query requests, wait-for-response to the information sharing manager;
Step D3, the information sharing manager sends query requests to attachable second terminal or shared information server, and wait-for-response;
Step D4, the information sharing manager of attachable second terminal or shared information server is accepted query requests, and as input, retrieval and coupling are recommended strategy and resource information with current context-descriptive information;
Step D5, local information sharing manager receives response message, upgrades resource information database and recommends policy database, and trigger message to one of personalized recommendation processor transmission, start the operation of personalized recommendation processor, generate the personalized recommendation service in real time.
Among the described step D4, the information sharing manager carries out match retrieval, comprises dual mode: 1, P2P mode; 2, based on shared information server mode.
The implementation procedure of step D4 is described respectively according to these two kinds of implementations below:
1, P2P mode
Under the P2P mode, information sharing manager executable operations 17 is carried out direct communication with other information sharing managers (being external information Sharing Management device) that can be connected user terminal, and exchange resource information and recommendation strategy are realized collaborative filtering.
The detailed process of retrieval is as follows:
The second terminal information Sharing Management device receives after the query requests, if exist second terminal to allow the recommendation strategy of sharing, then retrieve second of second terminal and recommend policy database, if find the recommendation strategy of coupling, then according to strategy, retrieve second resource information database of second terminal, find the resource of coupling, the resource results of recommending strategy and coupling is returned to the initiation terminal of inquiry;
2, based on shared information server mode
Under based on shared information server mode, the information sharing manager executable operations 18 of local terminal, the information sharing manager of sharing information server with the center directly is connected, upload or retrieve shared information, the shared information of uploading is specified by control interface by the user, and is finished by user control and to upload.The detailed process of retrieval is as follows:
The information sharing manager of sharing information server receives after the query requests, share the recommendation strategy that the information server permission is shared if exist, then retrieve second of this shared information server and recommend policy database, if find the recommendation strategy of coupling, then according to strategy, second resource of information server is shared in retrieval
Information database finds the resource of coupling, will recommend the resource results of strategy and coupling to return to the initiation terminal of inquiry.
Preferably, personalized service recommendation method of the present invention also comprises the following steps
Step e, the local terminal user, optimizes and recommends strategy by user control interface according to recommendation effect, promotes recommendation effect;
The local terminal user is according to recommendation effect, and executable operations 12 by user control interface, is optimized and recommended strategy, promotes recommendation effect.
Step F, the terminal user is according to result of use, and the acquisition strategy of configuration information sharing policy and shared information promotes recommendation effect.
The terminal user is according to result of use, executable operations 13, and by user control interface, the acquisition strategy of configuration information sharing policy and shared information promotes recommendation effect.
Personalized service recommendation system of the present invention and method are compared with method with existing personalized service recommendation system, mainly have following advantage:
1. existing personalized service recommendation system and method have three kinds of deposit positions for the user's description document that relates to user privacy information: client, server and agency.Leave user's description document in client, can effectively protect user privacy information, and user's description document can share between different application, but can only carry out content-based filtration, limit the recommendation ability.Other two kinds of methods all need to leave user's description document in beyond the user terminal position, and user's privacy information has been constituted potential threat.System and method of the present invention can address the above problem.On the one hand, user profile, resource information and recommendation strategy only are stored in user terminal, can avoid leaking of user privacy information.On the other hand, can share recommendation strategy and resource information in the mode of P2P or server, thereby realize content-based filtration and collaborative filtering simultaneously by explicit control between the user.
2. existing personalized service recommendation system and method are all used at Web, generally based on the B/S computation schema, can only carry out personalized recommendation to Web service.Personalized service recommendation system and method based on terminal of the present invention, at terminal applies,, not only can include Web service in recommended range based on local computation schema, and can all include local service and service on every side in recommended range, expanded recommended range.
3. existing personalized service recommendation system and method can not be subjected to being applied in the system of the present invention of any restriction, because local browser is included the recommended range of system of the present invention in as a kind of local resource.For example,, will start browser, and the search engine that often uses of the user that is dynamically connected certainly, Google for example, thereby the personalized recommendation service that the user can use it to provide when detecting the user web search will be carried out the time.
More than specific embodiments of the invention are described and illustrate it is exemplary that these embodiment should be considered to it, and be not used in and limit the invention, the present invention should make an explanation according to appended claim.
Claims (8)
1, a kind of personalized service recommendation system, comprise at least one terminal, it is characterized in that, described terminal comprises: user information collection device, User Information Database, user behavior analysis device, resource information database, recommendation policy database, context-aware processor and personalized recommendation processor, wherein:
Described user information collection device, be used for the various actions that supervisory user takes place on terminal, original user data with collection terminal, this original user data is carried out obtaining user profile after the pre-service, deposit described user profile in User Information Database, and according to circumstances send triggering message to the user behavior analysis device;
Described User Information Database is used to deposit the user profile by described user information collection device output, carries out user behavior analysis for the user behavior analysis device;
Described user behavior analysis device is used for scanning described User Information Database after receiving described triggering message, therefrom extracts new resource information, charges to resource information database, calculates new recommendation strategy, charges to the recommendation policy database;
Described resource information database is used to deposit the resource information that is produced by described user behavior analysis device analysis;
Described recommendation policy database is used to deposit the recommendation strategy that is generated by described user behavior analysis device, and should recommend strategy to be used for personalized recommendation processor generation recommendation service;
Described context-aware processor, the current context that is used for the perception user, the timing scan User Information Database, the record clauses and subclauses and the newly-increased record clauses and subclauses of therefrom inquiring about two class special users' latest update, and according to circumstances send triggering message to the personalized recommendation processor;
Described personalized recommendation processor, after being used to receive triggering message from the context-aware processor, obtain current contextual information, recommend policy database by retrieval, the optimum that obtains coupling is recommended strategy, and tactful according to the optimum recommendation by the retrieve resources information database, the coupling adequate resources generates the personalized recommendation service in real time.
2, personalized service recommendation system according to claim 1 is characterized in that, also comprise sharing information server and user control interface, wherein:
Described shared information server is used for for based on the information sharing of the mode of sharing information server the time, deposits the resource information that the terminal user allows and upload and recommends strategy, for the other-end user search and download use;
Described user control interface is used for adjust recommending strategy and the information sharing manager is configured and manages, and control information Sharing Management device.
3, personalized service recommendation system according to claim 2 is characterized in that, the information sharing of described information sharing manager realizes by following dual mode: a kind of is the P2P mode, point-to-point sharing between user terminal; Another kind is based on the mode of sharing information server, and the user will share information stores to sharing on the information server, use for other user inquirings.
4, personalized service recommendation system according to claim 1 is characterized in that, described personalized recommendation processor can be supported the rule-based filtration in the personalized service recommendation, content-based filtration and collaborative filtering simultaneously.
5, personalized service recommendation system according to claim 1 is characterized in that, described user information collection device and context-aware processor are as independently program or program module are moved simultaneously.
6, a kind of personalized service recommendation method is characterized in that, comprises step:
The various operation informations that steps A, the monitoring of user information collection device are carried out on terminal, original user data with collection terminal, described original user data is carried out obtaining user profile after the pre-service, deposit described user profile in User Information Database, if User Information Database upgrades, then start the user behavior analysis device and analyze;
Step B, user behavior analysis device scanning User Information Database therefrom extract new user profile and charge to resource information database, calculate new recommendation strategy and charge to the recommendation policy database;
Step C, context-aware processor perception user's current context extracts user profile in real time from User Information Database, and current context-descriptive information is exported in the variation of analysis context, starts the personalized recommendation processor;
Step D, personalized recommendation processor, after being used to receive current context-descriptive information from the context-aware processor, obtain current contextual information, recommend policy database by this locality or the retrieval of information sharing manager, the optimum that obtains coupling is recommended strategy, and according to recommending strategy by this locality or information sharing manager retrieve resources information database, coupling adequate resources information generates the personalized recommendation service in real time.
7, personalized service recommendation system according to claim 6 is characterized in that, described step D comprises step:
Step D1, personalized recommendation processor with current context-descriptive information as input, and the first recommendation policy database of retrieval local terminal, if find the recommendation strategy of coupling, then according to strategy, retrieve first resource information database of local terminal, find the resource information of coupling;
Step D2, if it fails to match, the personalized recommendation processor sends query requests, wait-for-response to the information sharing manager;
Step D3, information sharing manager send query requests to attachable second terminal or shared information server, and wait-for-response;
The information sharing manager of step D4, attachable second terminal or shared information server is accepted query requests, and as input, retrieval and coupling are recommended strategy and resource information with current context-descriptive information;
Step D5, local information sharing manager receive response message, upgrade resource information database and recommend policy database, and, start the operation of personalized recommendation processor to a triggering of personalized recommendation processor transmission message, generate the personalized recommendation service in real time.
8, personalized service recommendation system according to claim 6 is characterized in that, also comprises step:
Step e, local terminal user, optimize and recommend strategy by user control interface according to recommendation effect, promote recommendation effect;
Step F, terminal user are according to result of use, and the acquisition strategy of configuration information sharing policy and shared information promotes recommendation effect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101164770A CN101334792B (en) | 2008-07-10 | 2008-07-10 | Personalized service recommendation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101164770A CN101334792B (en) | 2008-07-10 | 2008-07-10 | Personalized service recommendation system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101334792A true CN101334792A (en) | 2008-12-31 |
| CN101334792B CN101334792B (en) | 2011-01-12 |
Family
ID=40197390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008101164770A Active CN101334792B (en) | 2008-07-10 | 2008-07-10 | Personalized service recommendation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101334792B (en) |
Cited By (57)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101883107A (en) * | 2010-06-18 | 2010-11-10 | 华为技术有限公司 | Method and related device for realizing context perception service application |
| CN101895547A (en) * | 2010-07-16 | 2010-11-24 | 浙江大学 | Uncertain service-based recommender system and method |
| CN102063453A (en) * | 2010-05-31 | 2011-05-18 | 百度在线网络技术（北京）有限公司 | Method and device for searching based on demands of user |
| CN102194183A (en) * | 2010-03-04 | 2011-09-21 | 深圳市腾讯计算机系统有限公司 | Service promotion system and method for supporting cooperative implementation of a plurality of promotional activities |
| CN102223608A (en) * | 2010-04-15 | 2011-10-19 | 宏达国际电子股份有限公司 | Personalized information service method and information platform |
| CN102279851A (en) * | 2010-06-12 | 2011-12-14 | 阿里巴巴集团控股有限公司 | Intelligent navigation method, device and system |
| CN102298650A (en) * | 2011-10-18 | 2011-12-28 | 东莞市巨细信息科技有限公司 | Distributed recommendation method of massive digital information |
| WO2012037725A1 (en) * | 2010-09-21 | 2012-03-29 | Nokia Corporation | Method and apparatus for collaborative context recognition |
| CN102439582A (en) * | 2009-03-20 | 2012-05-02 | 剥离技术公司 | Device-based control system |
| CN102521754A (en) * | 2010-10-18 | 2012-06-27 | 微软公司 | Capability-based application recommendation |
| CN102546973A (en) * | 2011-01-04 | 2012-07-04 | 中兴通讯股份有限公司 | Context information application method and device adopting same |
| CN102573102A (en) * | 2010-12-30 | 2012-07-11 | 上海博泰悦臻电子设备制造有限公司 | Supplying method and device of behavioral characteristic data |
| CN102609460A (en) * | 2012-01-13 | 2012-07-25 | 中国科学院计算技术研究所 | Method and system for microblog data acquisition |
| CN102663019A (en) * | 2012-03-21 | 2012-09-12 | 北京英孚斯迈特信息技术有限公司 | Instant recommendation system |
| CN102681886A (en) * | 2011-04-14 | 2012-09-19 | 天脉聚源(北京)传媒科技有限公司 | Method and system for tracking user behaviors on mobile equipment |
| CN102708455A (en) * | 2012-05-15 | 2012-10-03 | 深圳供电局有限公司 | Management system and management method for correction and prevention problems |
| WO2012145931A1 (en) * | 2011-04-29 | 2012-11-01 | Nokia Corporation | Method and apparatus for context-aware role modeling and recommendation |
| CN102801817A (en) * | 2012-09-07 | 2012-11-28 | 深圳市学之泉集团有限公司 | Subscriber context-based pushing method and device |
| WO2013033964A1 (en) * | 2011-09-06 | 2013-03-14 | 海尔集团公司 | Cbr privacy policy generation method and system in pervasive computing environment |
| CN103220289A (en) * | 2013-04-15 | 2013-07-24 | 北京京东尚科信息技术有限公司 | Resource verification system and resource verification method based on web application |
| CN103226774A (en) * | 2013-04-25 | 2013-07-31 | 中国科学技术大学 | Information exchange system |
| CN103258284A (en) * | 2012-02-15 | 2013-08-21 | 株式会社OPTiM | Business sales promotion server, business sales promotion method, and business sales promotion program |
| CN103260061A (en) * | 2013-05-24 | 2013-08-21 | 华东师范大学 | Context-perceptive IPTV program recommending method |
| CN103457840A (en) * | 2013-09-09 | 2013-12-18 | 中国农业银行股份有限公司 | Information sharing system and information sharing method |
| CN103559197A (en) * | 2013-09-23 | 2014-02-05 | 浙江大学 | Real-time music recommendation method based on context pre-filtering |
| CN103632278A (en) * | 2012-08-21 | 2014-03-12 | 镇江雅迅软件有限责任公司 | Multi-strategy commodity recommendation system based on context information |
| CN103810202A (en) * | 2012-11-13 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Data collection method and data collection system |
| CN103955359A (en) * | 2014-03-25 | 2014-07-30 | 西安乾易企业管理咨询有限公司 | Automatic pushing method for mobile terminal application and information and system thereof |
| CN104809107A (en) * | 2015-05-18 | 2015-07-29 | 中国科学院自动化研究所 | Recommending method and system based on context conversion vector model |
| CN105045792A (en) * | 2014-04-30 | 2015-11-11 | 三星电子株式会社 | Apparatus and method for integrated management of data in mobile device, and mobile device |
| CN105095781A (en) * | 2014-05-12 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Application program access permission reminding system and method |
| CN105159366A (en) * | 2015-09-21 | 2015-12-16 | 北京农业信息技术研究中心 | Greenhouse environment monitoring system and user behavior acquisition method |
| CN105608121A (en) * | 2015-12-14 | 2016-05-25 | 东软集团股份有限公司 | Personalized recommendation method and apparatus |
| CN105897676A (en) * | 2015-12-01 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | User resource access behavior processing method and device |
| CN106227900A (en) * | 2016-09-06 | 2016-12-14 | 北京易游华成科技有限公司 | Recommending scenery spot equipment, method and system |
| CN106503073A (en) * | 2016-09-30 | 2017-03-15 | 刘兴兵 | Task processing method, Task Processing Unit and mobile intelligent terminal |
| CN106603601A (en) * | 2015-10-15 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Service processing method, device and system, and terminal equipment |
| US9680886B2 (en) | 2010-03-22 | 2017-06-13 | Peel Technologies, Inc. | Internet enabled universal remote control system |
| CN107038051A (en) * | 2017-04-27 | 2017-08-11 | 紫光华山信息技术有限公司 | A kind of BIOS configuration items recommend method and device |
| WO2018068514A1 (en) * | 2016-10-13 | 2018-04-19 | 深圳市中兴微电子技术有限公司 | Method, device and system for analyzing user operation behaviors, and computer storage medium |
| US9984048B2 (en) | 2010-06-09 | 2018-05-29 | Alibaba Group Holding Limited | Selecting a navigation hierarchical structure diagram for website navigation |
| CN108121770A (en) * | 2017-11-30 | 2018-06-05 | 南京南邮信息产业技术研究院有限公司 | A kind of information sorting device based on mobile terminal big data |
| CN108170462A (en) * | 2017-12-26 | 2018-06-15 | 深圳豪客互联网有限公司 | A kind of function recommendation tables group maintenance method and system |
| CN109597945A (en) * | 2011-07-20 | 2019-04-09 | 电子湾有限公司 | Real-time location-aware is recommended |
| CN109740017A (en) * | 2018-12-14 | 2019-05-10 | 北京字节跳动网络技术有限公司 | The immediate feedback method and device of recommendation information |
| CN110321479A (en) * | 2019-05-27 | 2019-10-11 | 哈尔滨工业大学（深圳） | A kind of secret protection Information Mobile Service recommended method and client, recommender system |
| CN110348958A (en) * | 2019-06-28 | 2019-10-18 | 中信百信银行股份有限公司 | A kind of personalized recommendation method and system |
| CN110462610A (en) * | 2017-08-05 | 2019-11-15 | 辟博股份有限公司 | The system and method for being used to form the network with integrated management position and task arrangement |
| CN110929086A (en) * | 2019-12-20 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Audio and video recommendation method and device and storage medium |
| US10657161B2 (en) | 2012-01-19 | 2020-05-19 | Alibaba Group Holding Limited | Intelligent navigation of a category system |
| CN111274481A (en) * | 2020-01-19 | 2020-06-12 | 咪咕视讯科技有限公司 | Personalized environment scene providing method and device, electronic equipment and storage medium |
| CN111439268A (en) * | 2020-03-31 | 2020-07-24 | 重庆长安汽车股份有限公司 | Method and device for actively providing personalized service, cloud server and automobile |
| WO2020200199A1 (en) * | 2019-04-03 | 2020-10-08 | 华为技术有限公司 | Personalized recommendation method, terminal apparatus and system |
| CN112417310A (en) * | 2019-08-21 | 2021-02-26 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
| CN113469704A (en) * | 2021-06-10 | 2021-10-01 | 云南电网有限责任公司 | System and method for automatically recommending customer service strategy |
| CN114338814A (en) * | 2022-03-03 | 2022-04-12 | 广州卓远虚拟现实科技有限公司 | Data sharing processing method and system based on block chain |
| WO2023226947A1 (en) * | 2022-05-23 | 2023-11-30 | 阿里巴巴达摩院(杭州)科技有限公司 | Terminal-cloud collaborative recommendation system and method, and electronic device |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202339B (en) * | 2014-09-24 | 2018-01-05 | 广西大学 | A kind of across cloud authentication service method based on user behavior |
| CN105630989A (en) * | 2015-12-25 | 2016-06-01 | 北京东方长盈信息技术有限责任公司 | Finance product universal recommendation system |
-
2008
- 2008-07-10 CN CN2008101164770A patent/CN101334792B/en active Active
Cited By (80)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102439582A (en) * | 2009-03-20 | 2012-05-02 | 剥离技术公司 | Device-based control system |
| CN102194183B (en) * | 2010-03-04 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Support service promotion system and the method for multiple popularization activity coordinated implementation |
| CN102194183A (en) * | 2010-03-04 | 2011-09-21 | 深圳市腾讯计算机系统有限公司 | Service promotion system and method for supporting cooperative implementation of a plurality of promotional activities |
| US9680886B2 (en) | 2010-03-22 | 2017-06-13 | Peel Technologies, Inc. | Internet enabled universal remote control system |
| CN102223608A (en) * | 2010-04-15 | 2011-10-19 | 宏达国际电子股份有限公司 | Personalized information service method and information platform |
| CN102063453A (en) * | 2010-05-31 | 2011-05-18 | 百度在线网络技术（北京）有限公司 | Method and device for searching based on demands of user |
| US9984048B2 (en) | 2010-06-09 | 2018-05-29 | Alibaba Group Holding Limited | Selecting a navigation hierarchical structure diagram for website navigation |
| CN102279851A (en) * | 2010-06-12 | 2011-12-14 | 阿里巴巴集团控股有限公司 | Intelligent navigation method, device and system |
| US9519720B2 (en) | 2010-06-12 | 2016-12-13 | Alibaba Group Holding Limited | Method, apparatus and system of intelligent navigation |
| CN102279851B (en) * | 2010-06-12 | 2017-05-03 | 阿里巴巴集团控股有限公司 | Intelligent navigation method, device and system |
| CN101883107A (en) * | 2010-06-18 | 2010-11-10 | 华为技术有限公司 | Method and related device for realizing context perception service application |
| US8990233B2 (en) | 2010-06-18 | 2015-03-24 | Huawei Technologies Co., Ltd. | Method for implementing context aware service application and related apparatus |
| CN101883107B (en) * | 2010-06-18 | 2014-06-04 | 华为技术有限公司 | Method and related device for realizing context perception service application |
| CN101895547A (en) * | 2010-07-16 | 2010-11-24 | 浙江大学 | Uncertain service-based recommender system and method |
| WO2012037725A1 (en) * | 2010-09-21 | 2012-03-29 | Nokia Corporation | Method and apparatus for collaborative context recognition |
| CN102521754A (en) * | 2010-10-18 | 2012-06-27 | 微软公司 | Capability-based application recommendation |
| CN102573102A (en) * | 2010-12-30 | 2012-07-11 | 上海博泰悦臻电子设备制造有限公司 | Supplying method and device of behavioral characteristic data |
| CN102546973A (en) * | 2011-01-04 | 2012-07-04 | 中兴通讯股份有限公司 | Context information application method and device adopting same |
| CN102681886A (en) * | 2011-04-14 | 2012-09-19 | 天脉聚源(北京)传媒科技有限公司 | Method and system for tracking user behaviors on mobile equipment |
| US9881092B2 (en) | 2011-04-29 | 2018-01-30 | Wsou Investments, Llc | Method and apparatus for content-aware role modeling and recommendation |
| WO2012145931A1 (en) * | 2011-04-29 | 2012-11-01 | Nokia Corporation | Method and apparatus for context-aware role modeling and recommendation |
| CN109597945B (en) * | 2011-07-20 | 2023-05-02 | 电子湾有限公司 | Method for generating location-aware recommendations |
| CN109597945A (en) * | 2011-07-20 | 2019-04-09 | 电子湾有限公司 | Real-time location-aware is recommended |
| WO2013033964A1 (en) * | 2011-09-06 | 2013-03-14 | 海尔集团公司 | Cbr privacy policy generation method and system in pervasive computing environment |
| CN102298650A (en) * | 2011-10-18 | 2011-12-28 | 东莞市巨细信息科技有限公司 | Distributed recommendation method of massive digital information |
| CN102609460B (en) * | 2012-01-13 | 2015-02-04 | 中国科学院计算技术研究所 | Method and system for microblog data acquisition |
| CN102609460A (en) * | 2012-01-13 | 2012-07-25 | 中国科学院计算技术研究所 | Method and system for microblog data acquisition |
| US10657161B2 (en) | 2012-01-19 | 2020-05-19 | Alibaba Group Holding Limited | Intelligent navigation of a category system |
| CN103258284A (en) * | 2012-02-15 | 2013-08-21 | 株式会社OPTiM | Business sales promotion server, business sales promotion method, and business sales promotion program |
| CN102663019A (en) * | 2012-03-21 | 2012-09-12 | 北京英孚斯迈特信息技术有限公司 | Instant recommendation system |
| CN102708455A (en) * | 2012-05-15 | 2012-10-03 | 深圳供电局有限公司 | Management system and management method for correction and prevention problems |
| CN103632278A (en) * | 2012-08-21 | 2014-03-12 | 镇江雅迅软件有限责任公司 | Multi-strategy commodity recommendation system based on context information |
| CN102801817B (en) * | 2012-09-07 | 2015-07-15 | 深圳市学之泉集团有限公司 | Subscriber context-based pushing method and device |
| CN102801817A (en) * | 2012-09-07 | 2012-11-28 | 深圳市学之泉集团有限公司 | Subscriber context-based pushing method and device |
| CN103810202A (en) * | 2012-11-13 | 2014-05-21 | 腾讯科技（深圳）有限公司 | Data collection method and data collection system |
| CN103810202B (en) * | 2012-11-13 | 2016-03-30 | 腾讯科技（深圳）有限公司 | Method of data capture and data gathering system |
| CN103220289A (en) * | 2013-04-15 | 2013-07-24 | 北京京东尚科信息技术有限公司 | Resource verification system and resource verification method based on web application |
| CN103226774A (en) * | 2013-04-25 | 2013-07-31 | 中国科学技术大学 | Information exchange system |
| CN103260061B (en) * | 2013-05-24 | 2015-11-18 | 华东师范大学 | A kind of IPTV program commending method of context-aware |
| CN103260061A (en) * | 2013-05-24 | 2013-08-21 | 华东师范大学 | Context-perceptive IPTV program recommending method |
| CN103457840A (en) * | 2013-09-09 | 2013-12-18 | 中国农业银行股份有限公司 | Information sharing system and information sharing method |
| CN103457840B (en) * | 2013-09-09 | 2017-01-11 | 中国农业银行股份有限公司 | Information sharing system and information sharing method |
| CN103559197A (en) * | 2013-09-23 | 2014-02-05 | 浙江大学 | Real-time music recommendation method based on context pre-filtering |
| CN103955359A (en) * | 2014-03-25 | 2014-07-30 | 西安乾易企业管理咨询有限公司 | Automatic pushing method for mobile terminal application and information and system thereof |
| US11403322B2 (en) | 2014-04-30 | 2022-08-02 | Samsung Electronics Co., Ltd. | Apparatus and method for integrated management of data in mobile device, and mobile device |
| CN105045792A (en) * | 2014-04-30 | 2015-11-11 | 三星电子株式会社 | Apparatus and method for integrated management of data in mobile device, and mobile device |
| CN105095781A (en) * | 2014-05-12 | 2015-11-25 | 宇龙计算机通信科技(深圳)有限公司 | Application program access permission reminding system and method |
| CN105095781B (en) * | 2014-05-12 | 2018-07-24 | 宇龙计算机通信科技(深圳)有限公司 | A kind of application program access rights system for prompting and method |
| CN104809107A (en) * | 2015-05-18 | 2015-07-29 | 中国科学院自动化研究所 | Recommending method and system based on context conversion vector model |
| CN105159366A (en) * | 2015-09-21 | 2015-12-16 | 北京农业信息技术研究中心 | Greenhouse environment monitoring system and user behavior acquisition method |
| CN106603601A (en) * | 2015-10-15 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Service processing method, device and system, and terminal equipment |
| CN105897676A (en) * | 2015-12-01 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | User resource access behavior processing method and device |
| CN105608121B (en) * | 2015-12-14 | 2020-09-25 | 东软集团股份有限公司 | Personalized recommendation method and device |
| CN105608121A (en) * | 2015-12-14 | 2016-05-25 | 东软集团股份有限公司 | Personalized recommendation method and apparatus |
| CN106227900A (en) * | 2016-09-06 | 2016-12-14 | 北京易游华成科技有限公司 | Recommending scenery spot equipment, method and system |
| CN106503073A (en) * | 2016-09-30 | 2017-03-15 | 刘兴兵 | Task processing method, Task Processing Unit and mobile intelligent terminal |
| WO2018068514A1 (en) * | 2016-10-13 | 2018-04-19 | 深圳市中兴微电子技术有限公司 | Method, device and system for analyzing user operation behaviors, and computer storage medium |
| CN107038051A (en) * | 2017-04-27 | 2017-08-11 | 紫光华山信息技术有限公司 | A kind of BIOS configuration items recommend method and device |
| CN107038051B (en) * | 2017-04-27 | 2020-08-04 | 新华三信息技术有限公司 | BIOS configuration item recommendation method and device |
| CN110462610B (en) * | 2017-08-05 | 2022-12-27 | 辟博股份有限公司 | Professional service recommendation system |
| CN110462610A (en) * | 2017-08-05 | 2019-11-15 | 辟博股份有限公司 | The system and method for being used to form the network with integrated management position and task arrangement |
| CN108121770A (en) * | 2017-11-30 | 2018-06-05 | 南京南邮信息产业技术研究院有限公司 | A kind of information sorting device based on mobile terminal big data |
| CN108121770B (en) * | 2017-11-30 | 2021-09-14 | 南京南邮信息产业技术研究院有限公司 | Information classification device based on mobile terminal big data |
| CN108170462A (en) * | 2017-12-26 | 2018-06-15 | 深圳豪客互联网有限公司 | A kind of function recommendation tables group maintenance method and system |
| CN108170462B (en) * | 2017-12-26 | 2020-09-22 | 深圳豪客互联网有限公司 | Function recommendation table group maintenance method and system |
| CN109740017A (en) * | 2018-12-14 | 2019-05-10 | 北京字节跳动网络技术有限公司 | The immediate feedback method and device of recommendation information |
| US11843651B2 (en) | 2019-04-03 | 2023-12-12 | Huawei Technologies Co., Ltd. | Personalized recommendation method and system, and terminal device |
| WO2020200199A1 (en) * | 2019-04-03 | 2020-10-08 | 华为技术有限公司 | Personalized recommendation method, terminal apparatus and system |
| CN110321479A (en) * | 2019-05-27 | 2019-10-11 | 哈尔滨工业大学（深圳） | A kind of secret protection Information Mobile Service recommended method and client, recommender system |
| CN110321479B (en) * | 2019-05-27 | 2021-07-20 | 哈尔滨工业大学（深圳） | Privacy protection mobile service recommendation method, client and recommendation system |
| CN110348958A (en) * | 2019-06-28 | 2019-10-18 | 中信百信银行股份有限公司 | A kind of personalized recommendation method and system |
| CN112417310B (en) * | 2019-08-21 | 2023-10-03 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
| CN112417310A (en) * | 2019-08-21 | 2021-02-26 | 上海掌门科技有限公司 | Method for establishing intelligent service index and recommending intelligent service |
| CN110929086A (en) * | 2019-12-20 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Audio and video recommendation method and device and storage medium |
| CN111274481A (en) * | 2020-01-19 | 2020-06-12 | 咪咕视讯科技有限公司 | Personalized environment scene providing method and device, electronic equipment and storage medium |
| CN111439268B (en) * | 2020-03-31 | 2023-03-14 | 重庆长安汽车股份有限公司 | Method and device for actively providing personalized service, cloud server and automobile |
| CN111439268A (en) * | 2020-03-31 | 2020-07-24 | 重庆长安汽车股份有限公司 | Method and device for actively providing personalized service, cloud server and automobile |
| CN113469704A (en) * | 2021-06-10 | 2021-10-01 | 云南电网有限责任公司 | System and method for automatically recommending customer service strategy |
| CN114338814A (en) * | 2022-03-03 | 2022-04-12 | 广州卓远虚拟现实科技有限公司 | Data sharing processing method and system based on block chain |
| WO2023226947A1 (en) * | 2022-05-23 | 2023-11-30 | 阿里巴巴达摩院(杭州)科技有限公司 | Terminal-cloud collaborative recommendation system and method, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101334792B (en) | 2011-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101334792B (en) | Personalized service recommendation system and method | |
| CN110462604B (en) | Data processing system and method based on device use associated internet device | |
| US6434548B1 (en) | Distributed metadata searching system and method | |
| CN101652777B (en) | Query generation using environment configuration | |
| Tran et al. | Searching the web of things: State of the art, challenges, and solutions | |
| US20170249392A1 (en) | Adaptable real-time feed for site population | |
| CN101957857B (en) | Automatic information push method and server | |
| CN102224520B (en) | Providing suggested sites associated with target sites | |
| US20110087644A1 (en) | Enterprise node rank engine | |
| CN101808102B (en) | Operating record tracing system and method based on cloud computing | |
| CN101796752A (en) | Unwired enterprise platform | |
| CN101124576A (en) | Search system and methods with integration of user annotations from a trust network | |
| CN103428076A (en) | Method and device for transmitting information to multi-type terminals or applications | |
| CN104137094A (en) | Content pre-fetching for computing devices | |
| US20130283274A1 (en) | Method and system for discovering and activating an application in a computer device | |
| WO2011115471A1 (en) | Integrated service delivery platform system and method thereof | |
| AlZu'bi et al. | A multi-levels geo-location based crawling method for social media platforms | |
| KR100714504B1 (en) | System and method for searching contents in personal terminals using wired and wireless internet | |
| JP2010537324A (en) | Targeted distribution of search index fragments over wireless communication networks | |
| CN104348628A (en) | Method and device for obtaining local Root authority | |
| Lu et al. | Mining mobile application usage pattern for demand prediction by considering spatial and temporal relations | |
| Li et al. | Cultural distance-aware service recommendation approach in mobile edge computing | |
| Tamilselvi et al. | Handling high web access utility mining using intelligent hybrid hill climbing algorithm based tree construction | |
| Ling-ping et al. | Application of Three-dimensional Digital Model in Digital Archive Ubiquitous Intelligent Service | |
| Tran | A reference architecture and a software platform for engineering internet of things search engines |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |