WO2013189296A1 - 一种推荐目标软件的处理方法及系统 - Google Patents
一种推荐目标软件的处理方法及系统 Download PDFInfo
- Publication number
- WO2013189296A1 WO2013189296A1 PCT/CN2013/077577 CN2013077577W WO2013189296A1 WO 2013189296 A1 WO2013189296 A1 WO 2013189296A1 CN 2013077577 W CN2013077577 W CN 2013077577W WO 2013189296 A1 WO2013189296 A1 WO 2013189296A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- software
- user
- cluster
- client
- specific user
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012545 processing Methods 0.000 title claims abstract description 28
- 238000007621 cluster analysis Methods 0.000 claims abstract description 47
- 238000013480 data collection Methods 0.000 claims description 15
- 238000009434 installation Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims 2
- 230000000875 corresponding effect Effects 0.000 description 32
- 238000010586 diagram Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 238000011900 installation process Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
- G06F16/24554—Unary operations; Data partitioning operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Definitions
- Software Management System is software that manages the software of a data processing device.
- the software managers commonly used in the industry are 360 software housekeepers and Jinshan software housekeepers.
- the main features of the current software manager include: software depot, software upgrade, software uninstallation, download management, and more.
- the software warehouse in the software management system usually integrates most of the most commonly used software in the industry for users to choose to install and upgrade.
- more and more software is supported in the software warehouse, covering instant messaging, audio and video playback, web browsing, input methods, etc., and the total number will reach thousands or even Tens of thousands.
- the software management system recommendation software mainly performs recommended installation according to the installed software and the download amount or heat of the software, and the recommended channels and methods include: a leaderboard in the software warehouse, and a special recommendation page in the software warehouse. And use the prompt box (TIPS) to push popular target software.
- TIPS prompt box
- the existing schemes for recommending target software have the following disadvantages:
- the recommended software is too poorly correlated with the specific user, and the accuracy is not high, and the target software that meets the user's usage characteristics cannot be accurately pushed.
- SUMMARY OF THE INVENTION the main object of the present invention is to provide a processing method and system for recommending target software, so as to improve the correlation between the recommended target software and a specific user, and improve the accuracy of the recommendation.
- a method for processing recommended target software comprising:
- the most relevant user cluster of the specific user; the software of the top N bits is selected and recommended to the specific user in the software list corresponding to the user cluster, and the N is a predetermined value.
- a processing system that recommends target software including:
- the clustering analysis module is configured to perform cluster analysis on the user according to the software usage information reported by the user, determine a software list corresponding to each user cluster, and sort the software in the software list according to the usage of the software;
- a recommendation module configured to determine a user cluster that is most relevant to the specific user according to the software usage information of the specific user; and select, in the software list corresponding to the user cluster, the first N-bit software recommendation to the specific user, where the N is Predetermined value.
- the present invention can fully take into account the user's software usage information, and based on this, perform user cluster analysis, and different users cluster to recommend different software lists; when specific users use, first determine The user cluster to which the specific user belongs (equivalent to the user's use feature type), and then recommend the top software from the software list corresponding to the user cluster. Therefore, the target software recommended by the present invention can be implemented with a specific user. The higher the correlation, the higher the accuracy of the recommendation.
- FIG. 1 is a schematic flowchart of a method for processing a recommended target software according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of a composition of a processing system for recommending target software according to an embodiment of the present invention
- FIG. 3 is a schematic diagram of still another composition of a processing system for recommending target software according to an embodiment of the present invention
- FIG. 1 is a schematic flowchart of a method for processing a recommended target software according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of a composition of a processing system for recommending target software according to an embodiment of the present invention
- FIG. 3 is a schematic diagram of still another composition of a processing system for recommending target software according to an embodiment of the present invention
- FIG. 1 is a schematic flowchart of a method for processing a recommended target software according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of a composition of a processing system for recommending target software according to an embodiment of the present invention
- FIG. 4a is a schematic diagram of the cluster analysis module and the recommendation module being set on the server side
- FIG. 4b is a schematic diagram of the cluster analysis module being set on the server side, and the recommendation module being set on the client side;
- FIG. 5a is a schematic diagram showing an interface of the recommended target software by an icon
- FIG. 5b is a schematic diagram showing an interface of the recommended target software after being clicked by an icon
- FIG. 5c is a schematic diagram showing an interface of the recommended target software after the download and installation is completed by an icon
- FIG. 5 is a schematic diagram of an interface for displaying an edit mode of the recommended target software by means of an icon;
- FIG. 6a is a schematic diagram of another composition of the processing system of the recommended target software according to the embodiment of the present invention.
- FIG. 6b is another schematic diagram of the composition of the processing system of the recommended target software in the embodiment of the present invention. MODE FOR CARRYING OUT THE INVENTION The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
- FIG. 1 is a schematic flow chart of a method for processing recommended target software according to the present invention. Referring to Figure 1, the method mainly includes:
- Step 101 Perform cluster analysis on the user according to the software usage information reported by the user, determine a software list corresponding to each user cluster, and sort the software in the software list according to the usage of the software;
- Step 102 When a specific user uses the software management system, determine the user cluster most relevant to the specific user according to the software usage information of the specific user; select the top N bits in the software list corresponding to the user cluster. The software is recommended to the specific user, and the N is a predetermined value.
- FIG. 2 is a schematic diagram of a composition of a processing system for recommending target software according to the present invention. The processing system is operative to perform the method of the present invention. Referring to Figure 2, the processing system includes:
- the cluster analysis module is configured to perform cluster analysis on the user according to the software usage information reported by the user, determine a software list corresponding to each user cluster, and use the software in the software list according to the usage of the software.
- Software for sorting
- a recommendation module configured to determine a user cluster that is most relevant to the specific user according to the software usage information of the specific user; and select, in the software list corresponding to the user cluster, the first N-bit software recommendation to the specific user, where the N is Predetermined value.
- the software usage information reported by the user refers to the software usage information reported by the full amount of users.
- the full amount of users does not refer to all users, but to sample users who have only uploaded their own software usage information. If the sampled user reaches a certain lower limit (which can be set according to the application requirements), then it is determined that these sampled users can represent all users.
- the sampling user refers to a user having the authority to report data.
- each user of the software management system is sent a request for agreeing to report the data of the client itself, if the user receives the request. Then the user becomes a sampling user and has the authority to report data; if the user rejects the request, there is no permission to report the data.
- the processing system of the present invention further includes a data collection module.
- the data collection module is disposed on a client of the software management system, and is configured to collect and report data.
- the software usage information of the authorized user is reported to the cluster analysis module and the recommendation module.
- the software usage information reported by the user in step 101 includes: software information of the software installed by the user client, such as information such as a software name and/or a software category. This information can be found by the data collection module through information such as the path and executable file of the installed software in the registry and configuration files of the client's own machine.
- the cluster analysis process described in step 101 will be described below.
- Cluster Analysis also known as group analysis, is a multivariate statistical analysis method that classifies sampled data according to the principle of "object-like aggregation".
- the cluster analysis requires a large amount of sampled data, which can be reasonably pressed. The characteristics of the sampled data are used for reasonable classification.
- the cluster analysis process is a process of classifying sampled data into different classes, so objects in the same cluster have great similarities, and objects between different clusters have great dissimilarity.
- the goal of cluster analysis is to classify the sampled data on a similar basis.
- the invention adopts the cluster analysis method to collect the software usage information of the full amount of users. Based on the clustering analysis of the characteristics of different user groups, the users with similar software usage characteristics are aggregated into a class of users, and the typical characteristics of the cluster users are extracted as criteria for judging the clustering of a specific user.
- the cluster analysis method to collect the software usage information of the full amount of users.
- existing mature cluster analysis methods may be used, for example: system clustering method, decomposition method, joining method, dynamic clustering method, ordered sample clustering, overlapping clustering, fuzzy clustering, etc. .
- the cluster analysis module of the present invention performs cluster analysis on the user group according to the software name and/or category information in the installed software list, and clusters the user groups having different software usage characteristics (ie, user clustering), and Each user cluster selects the corresponding software list.
- the direct data basis of the cluster analysis module is the software class of the installed software reported by each sample user. If the sampling user only reports the software name, the software category to which the software belongs is first searched from the software warehouse according to the software name, and the software category is used as a direct data basis for cluster analysis.
- the specific clustering process of the clustering analysis module for the user may be slightly different according to the recommendation requirements.
- the method for clustering the user according to the software usage information reported by the user is used in an embodiment.
- the analysis process includes:
- Step 111 Count the software quantity of each type of installed software reported by each sampling user;
- Step 112 Determine the software category with the largest number of software installed by each sampling user;
- Step 113 The software category with the largest number of installed software is similar Degree, clustering the sampling users to obtain user clustering of different software usage characteristics.
- the software category with the largest number of software installed by n sampling users is the video class. If the n is greater than the threshold of one cluster, the video user cluster is divided, and the software of the video user cluster is used.
- the features are: The video class software is installed the most.
- the software category with the largest number of software installed by the m sampling users bl ⁇ bm is a game class. If the m is greater than a clustering threshold, the game user cluster is divided, and the game user clusters software.
- the features used are: Game software is installed the most.
- step 101 after performing cluster analysis on the user, it is necessary to determine a software list corresponding to each user cluster. Specifically, the user clusters according to the clustering are selected from the software warehouse of the software management system to select a software category software list of the corresponding category, and the software in the software list is sorted according to the usage of the software. The number of software in the list of software to be recommended is also controllable. Set up according to business needs.
- the sorting of the software in the software list according to the software usage mainly refers to sorting according to the overall running heat of the software.
- the method may include: collecting network downloads of each software and starting times and running times of each software reported by the user on the user client; for each software, downloading, starting, and running the software The time is multiplied by the corresponding weight, and finally summed to obtain the overall running heat of the software, and the overall running heat of the software is used as the software; the software in the software list is performed according to the overall running heat of the software. Sort.
- k video softwares Al ⁇ Ak are selected to form a corresponding list of software to be recommended, and the k video softwares are sorted according to the overall running heat of the software.
- a game software B1-B1 is selected to form a corresponding list of software to be recommended, and the one game software is sorted according to the overall running heat of the software.
- the cluster analysis module is set on the server side in the embodiment of the present invention, and the step 101 is performed on the server end.
- step 102 when a specific user uses the software management system, it is usually determined whether the specific user has the authority to report data, which is divided into the following two cases:
- the first case if the specific user has the right to report data, the client of the specific user obtains the software usage information of the local machine, and uploads the information to the server; the server uses the software usage information reported by the specific user client. Determining a user cluster most relevant to the specific user, selecting a software of the first N bits to be sent to the client of the specific user in the software list corresponding to the user cluster; the client of the specific user will use the first N software Displayed as recommended software. For example, the icon of the recommended software can be displayed on the small Q desk, and the software is identified as a recommended software in light gray.
- the software usage information mainly includes software information installed on the machine and/or software information frequently used by the machine.
- the installed software information of the machine is an installed software category and/or name, which can be searched by the data collection module through information such as the path and executable file of the installed software in the registry and configuration files of the client's local machine. get.
- the software information frequently used by the machine is mainly a software category and/or name that is frequently used. These frequently used software are usually the operating system's quick launch bar, desktop, and/or software in the DOCK column, which can be collected by data.
- the module is obtained through the corresponding application programming interface (API) of the native operating system.
- API application programming interface
- the method further includes: the client of the specific user sending the usage information of the recommended software to the server, where the usage information of the recommended software includes at least one subsequent Kind of information, namely: the number of installations of the software, the time from the start to the end of the software, and the amount of secondary startup after the software is installed.
- the information is mainly used by the data collection module for the click operation and the running time of the specific user.
- the server obtains the usage information of the recommended software and determines the recommended heat.
- the specific determination method may be the number of installations of the software, the time from the start to the end of the software, and the software.
- the second startup amount is weighted and summed to obtain the recommended heat; then, according to the recommended heat of the recommended software, the ranking of the recommended software in the software list corresponding to the user cluster is adjusted, where, The recommended software that is recommended to have a heat greater than the specified threshold increases its ranking. For recommended software whose recommended heat is less than the specified threshold, the ranking is lowered.
- the selection dimension of the target software can be further increased for the user, the relevance of the target software to the user is further improved, and the accuracy of the recommendation is improved.
- the cluster analysis module and the recommendation module need to be set on the server side, as shown in FIG. 4a.
- the server sends the user clustering information and the corresponding sorted software list to the client of the specific user;
- the client of the specific user obtains the software usage information of the local device;
- the client of the specific user determines the user cluster most relevant to the specific user according to the software usage information of the local device, and selects in the software list corresponding to the user cluster.
- the first N bits of software are displayed as recommended software.
- the software usage information mainly includes software information installed on the machine and/or software information frequently used by the machine.
- the installed software information of the machine is an installed software category and/or name, which can be searched by the data collection module through information such as the path and executable file of the installed software in the registry and configuration files of the client's local machine. get.
- the software information frequently used by the machine is mainly a software category and/or name that is frequently used. These frequently used software are usually the operating system's quick launch bar, desktop, and/or software in the DOCK column, which can be collected by data.
- the module is obtained through the corresponding API of the native operating system.
- the cluster analysis module needs to be set on the server, and the recommendation module is set on the client.
- the clustering module is further configured to send the user clustering information and the corresponding sorted software list to the client; the recommendation module is further used to
- the data collection module of the client obtains the software usage information of the specific user of the local device, determines the user cluster most relevant to the specific user according to the software usage information of the specific user, and selects in the software list corresponding to the user cluster.
- the first N bits of software are displayed as recommended software.
- the software usage information of the specific user described in step 102 includes: software information that is installed by the specific user client and/or software information that is frequently started.
- the determining, according to the software usage information of the specific user, the user cluster that is most relevant to the user, may specifically include:
- Step 121 In each software list corresponding to the user cluster, determine the cluster correlation degree of the software and the user cluster according to the ranking of each software.
- Step 122 Determine, according to the software list corresponding to each user cluster and the cluster relevance of the software, the cluster of users to which the installed software and/or the frequently-initiated software belong in the specific user client. And determining a clustering relevance of each of the installed software and/or the frequently launched software to cluster with the user to which it belongs.
- Step 123 Add the cluster correlations of the software belonging to the same user cluster to obtain a matching score of the user cluster; further processing manner herein may include: assigning the frequently-started software to the The software adds a higher weight, and the cluster correlation degree of the software belonging to the same user cluster is weighted and added according to the software weight, and the obtained weighted sum is used as the matching score of the user cluster.
- the two related user clusters are queried, that is, the user cluster of the game class and the user cluster of the office class, and the game software is queried.
- the correlation degree of X in the user cluster of the game class is X
- the correlation degree of the game software Y in the user cluster of the game class is y
- the correlation degree of the office software Z in the user cluster of the office class is z.
- the matching score of the user cluster of the game class is x+y
- the matching score of the user cluster of the office class is z.
- Step 124 Select a user cluster with the highest matching score as the user most relevant to the user. Class.
- the software of the first N bits is recommended to the specific user in step 102, and may also be specifically:
- the recommended software list removes the software that has been installed by the specific user, and then selects the top N software from the remaining software to recommend to the specific user. This makes it possible to further improve the accuracy of the recommendation without being disturbed by the software installed by the user.
- modules in the systems of the above examples may be distributed to the devices of the examples by way of example, or may be modified to be located in one or more devices other than the present examples.
- the modules of the above examples can be combined into one module, or can be further split into multiple sub-modules.
- the processing system of the recommended target software proposed by the embodiments of the present invention can be embodied in various forms.
- a plug-in that is installed into a software management system can be written in accordance with a standard application interface, or it can be packaged as an application for users to download and use.
- When written as a plug-in it can be implemented as a variety of plug-ins such as ocx, dll, cab, etc.
- the processing system of the recommended target software proposed by the embodiments of the present invention may also be implemented by a specific technology such as a Flash plug-in, a RealPlayer plug-in, an MMS plug-in, a MIDI staff plug-in, or an ActiveX plug-in.
- a machine readable storage medium storing instructions for causing a machine to execute a processing method of the recommended target software as described herein.
- a system or apparatus equipped with a storage medium on which software program code implementing the functions of any of the above-described embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be stored Reading and executing the program code stored in the storage medium.
- the program code itself read from the storage medium can implement the functions of any of the above examples, and thus the program code and the storage medium storing the program code constitute the implementation of the above Part of the mapping management technology program.
- Storage medium embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (eg,
- the program code can be downloaded from the server computer by the communication network.
- Fig. 6a is a schematic view showing still another structure of an electronic map ranging device according to an embodiment of the present invention.
- the system can include a server and a client, the server includes a first memory, and a first processor in communication with the first memory, wherein the first memory stores The cluster analysis instruction and the recommendation instruction executed by the first processor are described.
- the cluster analysis instruction is used to indicate that the user analyzes the software according to the software usage information reported by the client, determines a software list corresponding to each user cluster, and uses the software in the software list according to the usage of the software. Sort.
- the recommendation instruction is used to indicate that the user cluster that is most relevant to the specific user is determined according to the software usage information of the client of the specific user; and the software of the first N digits is recommended to the specific user in the software list corresponding to the user cluster, N is a predetermined value.
- the client may also include a second memory and a second processor in communication with the second memory, wherein the second memory stores data acquisition instructions executable by the second processor for indicating The software usage information of the user with the authority to report data is collected and reported to the server.
- FIG. 6b is still another schematic structural diagram of an electronic map ranging device according to an embodiment of the present invention.
- the system can include a server and a client, the server includes a first memory, and a first processor in communication with the first memory, wherein the first memory stores A cluster analysis instruction executed by the first processor.
- the cluster analysis instruction is used to indicate that the user analyzes the software according to the software usage information reported by the client, determines a software list corresponding to each user cluster, and uses the software in the software list according to the usage of the software.
- the sorting is performed, and the user clustering information and the corresponding sorted software list are sent to the client.
- the client can include a second memory and a second processor in communication with the second memory, wherein the second memory stores data acquisition instructions and recommendation instructions executable by the second processor.
- the data collection instruction is used to indicate that the software usage information of the user having the authority to report the data is collected and reported to the server; or the software usage information of the user who has not authorized to report the data is collected; the recommendation instruction is used to indicate the data collection by the client local device.
- the instruction acquires software usage information of a specific user of the local machine, and instructs to determine a user cluster most relevant to the specific user according to the software usage information of the client of the specific user; select the software of the first N bits in the software list corresponding to the user cluster Displayed as recommended software, the N is a predetermined value.
- the technical solution in the embodiment of the present invention can estimate the preference of the user to use the software through a series of processes, and the software pushed according to the technical solution will improve the accuracy of the software recommendation and the user requirement, and for some excellent, But relatively small software is also easy to recommend to relevant users.
- the manner in which the recommended target software is displayed on the client there may be multiple ways.
- the recommended target software may be displayed by an icon, and the installation may be performed by clicking and executing. The way to make the entire recommendation process thinner and smoother, to simplify the process to the greatest extent, reduce the psychological pressure of users.
- Figure 5a is a schematic diagram of an interface for displaying recommended target software by means of icons.
- the target software to be pushed may be in a form different from other icons, for example, the icon of the recommended target software may be presented in the operation of the software management system in the form of a light gray icon 500 (other icons are dark).
- a lighter software startup operation panel 501 called "Small Q Desk".
- the pushing frequency of the target software may be configured in the background, for example, the basic frequency is one software per week.
- FIG. 5b is a schematic diagram showing an interface of the recommended target software after being clicked by an icon.
- clicking the light gray icon 500 triggers the download and installation process; after the download is complete, it will be silently installed; after the installation is complete, the icon lights up (ie, the light gray is removed), indicating that it can be used normally.
- FIG. 5c is a schematic diagram showing an interface of the recommended target software after the download and installation is completed by an icon Figure. As shown in Figure 5c, after the installation is complete, the software icon 500 is illuminated and can be used in the same way as the icons in other "Small Q Desk" panels.
- the light gray icon 500 can be removed in two ways.
- FIG. 5d is a schematic diagram of an interface for displaying an edit mode of the recommended target software by an icon.
- the handling of error conditions mainly includes:
- the floating window prompts "The network connection is abnormal, the download fails", and when the user clicks the light gray icon 500 again, the download target software is restarted.
- the software product is recommended in such an icon management software panel, which is in line with the user's psychological expectation. It can enrich the usefulness of such software, and expand the features recommended by the software based on the icon management.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Stored Programmes (AREA)
Abstract
本申请公开了一种推荐目标软件的处理方法和系统,包括:聚类分析模块根据用户上报的软件使用信息对用户进行聚类分析,确定每种用户聚类对应的软件列表,按照软件的使用情况对所述软件列表中的软件进行排序;推荐模块根据具体用户的软件使用信息确定与该具体用户最相关的用户聚类;在该用户聚类对应的软件列表中选择前N位的软件推荐给该具体用户,所述N为预定值。利用本发明,可以提高所推荐的目标软件与具体用户的相关性,提高推荐的准确度。
Description
一种推荐目标软件的处理方法及系统 本申请要求于 2012 年 06 月 21 日提交中国专利局、 申请号为 201210207154.9、发明名称为"一种推荐目标软件的处理方法及系统"的中国专 利申请的优先权, 其全部内容通过引用结合在本申请中。 技术领域 本申请涉及数据处理设备的软件处理技术领域, 尤其涉及一种推荐目标 软件的处理方法及系统。 发明背景 目前, 数据处理设备, 如计算机、 智能手机、 掌上电脑、 平板电脑等, 的使用越来越普及。 在数据处理设备上运行的各种软件也呈爆炸式发展。
其中对于软件的管理, 目前的主要技术方案是软件管理系统。 软件管理 系统是一种对数据处理设备的软件进行管理的软件。 目前业界比较常用的软 件管理器比如 360软件管家、 金山软件管家等。 目前的软件管理器具备的主 要功能包括: 软件仓库、 软件升级、 软件卸载、 下载管理等。
软件管理系统中的软件仓库中通常集合了目前业界大部分的优秀常用的 软件, 供用户选择安装和升级。 为了给用户提供更丰富、 更全面的软件安装 和升级, 目前软件仓库中支持的软件越来越多, 遍及即时通信、 音视频播放、 网页浏览、 输入法等各个门类, 总数会达到数千甚至上万种。 在如此众多的 软件中, 有质量的好坏优劣之分。 对于用户来讲, 往往希望软件管理系统能 为用户推荐质量较高的且针对性较强的软件。 因此目前的软件管理系统中大 部分都集成了软件推荐的功能。
现有技术中, 软件管理系统推荐软件主要是根据已经安装的软件和该软 件的下载量或热度进行推荐安装, 其推荐渠道及方式包括: 软件仓库中的排 行榜、 软件仓库中的专题推荐页、 以及利用提示框(TIPS ) 等来推送热门的 目标软件。
但是, 现有的推荐目标软件的方案存在如下的缺点:
所推荐的软件与具体用户的相关性太差, 准确度不高, 不能很准确地推 送符合用户使用特征的目标软件。 发明内容 有鉴于此, 本发明的主要目的在于提供推荐目标软件的处理方法和系统, 以提高所推荐的目标软件与具体用户的相关性, 提高推荐的准确度。
本发明的技术方案是这样实现的: 一种推荐目标软件的处理方法, 包括:
根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户聚类 对应的软件列表, 按照软件的使用情况对所述软件列表中的软件进行排序; 根据具体用户的软件使用信息确定与该具体用户最相关的用户聚类; 在 该用户聚类对应的软件列表中选择前 N位的软件推荐给该具体用户, 所述 N 为预定值。
一种推荐目标软件的处理系统, 包括:
聚类分析模块, 用于根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情况对所述软件列表中 的软件进行排序;
推荐模块, 用于根据具体用户的软件使用信息确定与该具体用户最相关 的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的软件推荐给该具 体用户, 所述 N为预定值。 与现有技术相比, 本发明可以充分考虑到用户的软件使用信息, 并以此 为依据进行用户的聚类分析, 不同的用户聚类推荐不同的软件列表; 在具体 用户使用时, 先确定该具体用户所属的用户聚类 (相当于用户的使用特征类 型), 再从该用户聚类对应的软件列表中推荐排名在前的软件, 因此, 本发明 所推荐的目标软件可以与具体用户实现较高的相关性, 推荐的准确度较高。 附图简要说明 图 1为本发明实施例中所述推荐目标软件的处理方法的一种流程示意图; 图 2为本发明实施例中所述推荐目标软件的处理系统的一种组成示意图;
图 3 为本发明实施例中所述推荐目标软件的处理系统的又一种组成示意 图;
图 4a为所述聚类分析模块和推荐模块设置在服务器端的一种示意图; 图 4b为所述聚类分析模块设置在服务器端, 推荐模块设置在客户端的一 种示意图;
图 5a为通过图标方式显示被推荐目标软件的界面示意图;
图 5b为通过图标方式显示被推荐目标软件在被点击后的界面示意图; 图 5c为通过图标方式显示被推荐目标软件在下载安装完成后的界面示意 图;
图 5d为通过图标方式显示被推荐目标软件的编辑模式的界面示意图; 图 6a为本发明实施例中所述推荐目标软件的处理系统的又一种组成示意 图;
图 6b为本发明实施例中所述推荐目标软件的处理系统的另一种组成示意 图。 实施本发明的方式 下面结合附图及具体实施例对本发明再作进一步详细的说明
图 1为本发明所述推荐目标软件的处理方法的一种流程示意图。参见图 1 , 该方法主要包括:
步骤 101、根据用户上报的软件使用信息对用户进行聚类分析, 确定每种 用户聚类对应的软件列表, 按照软件的使用情况对所述软件列表中的软件进 行排序;
步骤 102、 当一具体用户使用软件管理系统时, 才艮据该具体用户的软件使 用信息确定与该具体用户最相关的用户聚类; 在该用户聚类对应的软件列表 中选择前 N位的软件推荐给该具体用户, 所述 N为预定值。 图 2为本发明所述推荐目标软件的处理系统的一种组成示意图。 该处理 系统用于执行本发明的方法, 参见图 2, 该处理系统包括:
聚类分析模块, 用于根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情况对所述软件列表中
的软件进行排序;
推荐模块, 用于根据具体用户的软件使用信息确定与该具体用户最相关 的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的软件推荐给该具 体用户, 所述 N为预定值。 在步骤 101 中, 所述用户上报的软件使用信息是指全量用户上报的软件 使用信息。 所述全量用户并不是指全体用户, 而是只上传了自身软件使用信 息的采样用户。 如果采样用户达到了一定的数量下限(该数量下限可以根据 应用需求进行设置), 则判定这些采样用户可以代表全体用户。
所述的采样用户是指具有上报数据权限的用户, 在本发明的具体实施例 中, 预先为软件管理系统的每个用户发送一份是否同意上报自身客户端数据 的请求, 如果用户接收该请求则该用户变为采样用户, 具有上报数据的权限; 如果用户拒绝该请求则没有上报数据的权限。
为了能够采集到用户上报的软件使用信息, 本发明所述的处理系统中还 包括数据采集模块, 如图 3所示, 该数据采集模块设置在软件管理系统的客 户端, 用于采集具有上报数据权限的用户的软件使用信息, 并上报给聚类分 析模块和推荐模块。
步骤 101 中所述用户上报的软件使用信息包括: 用户客户端本机已安装 软件的软件信息, 例如具体为软件名称和 /或软件类别等信息。 这些信息可以 由所述数据采集模块通过客户端本机的注册表和配置文件中的已安装软件的 路径和可执行文件等信息查找得到。 下面说明步骤 101所述的聚类分析过程。
聚类分析 ( Cluster Analysis ) 又称群分析, 是根据 "物以类聚" 的原理, 对采样数据进行分类的一种多元统计分析方法, 聚类分析的处理对象是大量 的采样数据, 要求能合理地按采样数据的特性来进行合理的分类。
聚类分析过程是将采样数据分类到不同的类的一个过程, 所以同一个簇 中的对象有很大的相似性, 而不同簇间的对象有很大的相异性。 聚类分析的 目标就是在相似的基础上对采样的数据进行分类。
本发明就是采用聚类分析方法, 以所采集到的全量用户的软件使用信息
为基础, 聚类分析出不同用户群的特征, 将对软件使用特征相近的用户聚集 为一类用户, 并提取出该聚类用户的典型特征作为后续判断某一具体用户所 属聚类的标准。 例如:
本发明实施例中, 可以采用现有成熟的聚类分析方法, 例如: 系统聚类 法、 分解法、 加入法、 动态聚类法、 有序样品聚类、 有重叠聚类和模糊聚类 等。
本发明所述聚类分析模块根据已安装软件列表中的软件名称和 /或类别信 息对用户群进行聚类分析, 聚类出具有不同软件使用特征的用户群(即用户 聚类), 并为每种用户聚类选择对应的软件列表。
聚类分析模块的直接数据基础是各采样用户上报的已安装软件的软件类 另 ij。 如果采样用户只上报了软件名称, 则首先根据软件名称从软件仓库中查 询该软件所属的软件类别, 将该软件类别作为聚类分析的直接数据基础。
步骤 101 中, 聚类分析模块对用户进行聚类分析的具体聚类过程可以依 照推荐需求的不同会略有不同, 例如一种实施例的所述根据用户上报的软件 使用信息对用户进行聚类分析过程包括:
步骤 111、 统计各采样用户上报的各类已安装软件的软件数量; 步骤 112、 确定出各采样用户所安装软件数量最多的软件类别; 步骤 113、 以所述安装软件数量最多的软件类别为相似度, 对采样用户进 行聚类划分, 得到不同软件使用特征的用户聚类。
例如: n个采样用户 al~an所安装软件数量最多的软件类别为视频类, 如 果所述 n大于一个聚类的门限值, 则划分出视频用户聚类, 该视频用户聚类 的软件使用特征就是: 视频类的软件安装的最多。
再例如: m个采样用户 bl~bm所安装软件数量最多的软件类别为游戏类, 如果所述 m大于一个聚类的门限值, 则划分出游戏用户聚类, 该游戏用户聚 类的软件使用特征就是: 游戏类的软件安装的最多。 步骤 101 中, 在对用户进行聚类分析之后, 需要确定每种用户聚类对应 的软件列表。 具体可以为: 按照聚类划分出的用户聚类, 从软件管理系统的 软件仓库中选择对应类别的软件组成软件列表, 该软件列表中的软件按照软 件的使用情况进行排序。 所述待推荐软件列表中的软件数量也是可控的, 可
以根据业务需求进行设置。
所述按照软件使用情况对软件列表中的软件进行排序主要是指按照软件 的整体运行热度进行排序。 具体可包括: 采集各软件的网络下载量和采样用 户所上报的各软件在用户客户端本机上的启动次数和运行时间; 针对每一软 件, 将该软件的网络下载量、 启动次数和运行时间分别乘以对应的权重, 最 后再求和, 得到该软件的整体运行热度, 将该软件的整体运行热度作为该软 件的使用情况; 按照软件的整体运行热度对所述软件列表中的软件进行排序。
例如:
对于视频用户聚类, 选择 k个视频类软件 Al~Ak组成对应的待推荐软件 列表, 该 k个视频类软件按照软件整体运行热度进行排序。
对于游戏用户聚类, 选择 1个游戏类软件 B1-B1组成对应的待推荐软件 列表, 该 1个游戏类软件按照软件整体运行热度进行排序。 本发明实施例中所述聚类分析模块设置在服务器端, 所述步骤 101 在服 务器端执行。
所述步骤 102 中, 当一具体用户使用软件管理系统时, 通常要判断该具 体用户是否具有上报数据的权限, 分以下两种情况:
第一种情况: 如果所述具体用户有上报数据的权限, 则该具体用户的客 户端获得本机的软件使用信息, 并上传给服务器端; 服务器端根据该具体用 户客户端上报的软件使用信息确定与该具体用户最相关的用户聚类, 在该用 户聚类对应的软件列表中选择前 N位的软件发送给该具体用户的客户端; 该 具体用户的客户端将所述前 N位软件作为被推荐软件进行显示。 例如可以在 小 Q书桌上显示该推荐软件的图标, 并用浅灰色标识该软件为推荐软件。
所述软件使用信息主要包括本机已安装的软件信息和 /或本机经常使用的 软件信息。 所述本机已安装的软件信息为已安装的软件类别和 /或名称, 可以 由数据采集模块通过客户端本机的注册表和配置文件中的已安装软件的路径 和可执行文件等信息查找得到。 所述本机经常使用的软件信息主要是经常使 用的软件类别和 /或名称,这些经常使用的软件通常为操作系统的快速启动栏、 桌面、 和 /或 DOCK栏中的软件, 可以由数据采集模块通过本机操作系统的对 应的应用程序编程接口 ( API )得到。
并且, 如果所述具体用户有上报数据的权限, 还可以进一步包括: 所述 具体用户的客户端将所述被推荐软件的使用信息发送给服务器端, 该被推荐 软件的使用信息包括后续至少一种信息, 即: 该软件的安装次数、 该软件从 启动到结束的时间、 该软件安装完成后的二次启动量, 这些信息主要通过所 述数据采集模块对该具体用户的点击操作和运行时长进行统计得到; 服务器 端收到所述被推荐软件的使用信息后确定其被推荐热度, 具体的确定方法可 以是分别对所述该软件的安装次数、 该软件从启动到结束的时间、 该软件安 装完成后的二次启动量进行加权求和, 得到被推荐热度; 然后, 再根据被推 荐软件的被推荐热度调整对应用户聚类的软件列表中该被推荐软件的排列位 次, 其中, 对于被推荐热度大于指定阈值的被推荐软件调高其排列位次, 对 于被推荐热度小于指定阈值的被推荐软件则调低其排列位次。 通过这种调整, 可以进一步增加为用户推荐目标软件的选择维度, 进一步提高目标软件与用 户的相关性, 提高推荐的准确度。
在本发明所述的推荐目标软件的处理系统的一种实施例中, 为了执行上 述第一种情况的方法, 所述聚类分析模块和推荐模块需要设置在服务器端, 如图 4a所示。 第二种情况, 如果所述具体用户没有上报数据的权限, 则服务器端将所 述每种用户聚类信息及其对应的经过所述排序的软件列表下发给该具体用户 的客户端; 该具体用户的客户端获得本机的软件使用信息; 该具体用户的客 户端根据该本机的软件使用信息确定与该具体用户最相关的用户聚类, 在该 用户聚类对应的软件列表中选择前 N位的软件作为被推荐软件进行显示。
与所述第一种情况相同的是, 所述软件使用信息主要包括本机已安装的 软件信息和 /或本机经常使用的软件信息。 所述本机已安装的软件信息为已安 装的软件类别和 /或名称, 可以由数据采集模块通过客户端本机的注册表和配 置文件中的已安装软件的路径和可执行文件等信息查找得到。 所述本机经常 使用的软件信息主要是经常使用的软件类别和 /或名称, 这些经常使用的软件 通常为操作系统的快速启动栏、 桌面、 和 /或 DOCK栏中的软件, 可以由数据 采集模块通过本机操作系统的对应的 API得到。
在本发明所述的推荐目标软件的处理系统的一种实施例中, 为了执行上 述第二种情况的方法, 所述聚类分析模块需要设置在服务器端, 所述推荐模 块设置在客户端, 如图 4b所示; 并且所述聚类分析模块进一步用于将所述每 种用户聚类信息及其对应的经过所述排序的软件列表下发给客户端; 所述推 荐模块进一步用于从客户端本机的数据采集模块中获取本机具体用户的软件 使用信息, 根据该具体用户的软件使用信息确定与该具体用户最相关的用户 聚类, 在该用户聚类对应的软件列表中选择前 N位的软件作为被推荐软件进 行显示。 在本发明的一种实施例中, 步骤 102 中所述的具体用户的软件使用信息 包括: 该具体用户客户端本机已安装的软件信息和 /或经常启动的软件信息。
所述根据具体用户的软件使用信息确定与该用户最相关的用户聚类, 可 具体包括:
步骤 121、在每种用户聚类对应的软件列表中,按照每款软件的排序名次 确定该软件与该用户聚类的聚类相关度。
步骤 122、 根据各用户聚类对应的软件列表及其软件的所述聚类相关度, 确定所述具体用户客户端本机中的各已安装软件和 /或经常启动软件所属的用 户聚类, 以及确定所述各已安装软件和 /或经常启动软件与其所属用户聚类的 聚类相关度。
步骤 123、将属于同一用户聚类的所述软件的聚类相关度相加,得到该用 户聚类的匹配分数; 此处进一步的处理方式可包括: 为所述经常启动软件分 配比所述已安装软件更高的权值, 将属于同一用户聚类的所述软件的聚类相 关度按照所述的软件权值进行加权相加, 将得到的加权和作为该用户聚类的 匹配分数。
例如, 用户已安装软件有游戏软件 X, 游戏软件 Y, 办公软件 Z, 则查询 到两种相关的用户聚类, 即游戏类的用户聚类和办公类的用户聚类, 并查询 得到游戏软件 X在游戏类的用户聚类中的相关度为 X , 游戏软件 Y在游戏类 的用户聚类中的相关度为 y,办公软件 Z在办公类的用户聚类中的相关度为 z。 那么游戏类的用户聚类的匹配分数为 x+y ,办公类的用户聚类的匹配分数为 z。
步骤 124、 选择匹配分数最高的用户聚类作为与该用户最相关的用户聚
类。
在确定了与该具体用户最相关的用户聚类之后, 例如确定了游戏用户聚 类为与用户最相关的聚类, 则从该聚类对应的软件列表中选择排在前 N位的 软件推荐给该具体用户。 在本发明的又一种实施例中, 步骤 102 中所述在该用户聚类对应的软件 列表中选择前 N位的软件推荐给该具体用户, 还可以具体为: 在该用户聚类 的待推荐软件列表中去除该具体用户已经安装的软件, 再从剩余的软件中选 择排在前 N位的软件推荐给该具体用户。 这样就可以不受用户已安装软件的 干扰, 进一步提高推荐的准确度。
在一种优选方案中, 所述被推荐的软件个数 N=l , 即针对一个具体用户 一次只推荐一款软件, 这样可以避免一次推荐软件数量较多导致的用户选择 困难。
本领域技术人员可以理解上述实例中的系统中的模块可以按照实例描述 分布于实例的装置中, 也可以进行相应变化位于不同于本实例的一个或多个 装置中。 上述实例的模块可以合并为一个模块, 也可以进一步拆分成多个子 模块。
实际上, 可以通过多种形式来具体实施本发明实施例所提出的推荐目标 软件的处理系统。 比如, 可以遵循一定规范的应用程序接口编写为安装到软 件管理系统中的插件程序, 也可以将其封装为应用程序以供用户自行下载使 用。 当编写为插件程序时, 可以将其实施为 ocx、 dll、 cab等多种插件形式。 也可以通过 Flash插件、 RealPlayer插件、 MMS插件、 MIDI五线谱插件、 ActiveX 插件等具体技术来实施本发明实施方式所提出的推荐目标软件的处理系统。
基于上述各个实例所提供的技术方案, 这里还提出了一种机器可读的存 储介质, 存储用于使一机器执行如本文所述的推荐目标软件的处理方法的指 令。 具体地, 可以提供配有存储介质的系统或者装置, 在该存储介质上存储 着实现上述实施例中任一实施例的功能的软件程序代码, 且使该系统或者装 置的计算机(或 CPU或 MPU )读出并执行存储在存储介质中的程序代码。
在这种情况下, 从存储介质读取的程序代码本身可实现上述实例中任何 一项实例的功能, 因此程序代码和存储程序代码的存储介质构成了实现上述
映射管理技术方案的一部分。
用于提供程序代码的存储介质实施例包括软盘、硬盘、磁光盘、 光盘(如
CD-ROM、 CD-R, CD-RW、 DVD-ROM、 DVD-RAM、 DVD-RW、 DVD+RW )、 磁带、 非易失性存储卡和 ROM。 可选择地, 可以由通信网络从服务器计算机 上下载程序代码。
此外, 应该清楚的是, 不仅可以通过执行计算机所读出的程序代码, 而 且可以通过基于程序代码的指令使计算机上操作的操作系统等来完成部分或 者全部的实际操作, 从而实现上述实例中任意一项实施例的功能。
例如, 图 6a为才艮据本发明实施例的电子地图测距装置的又一个结构示意 图。 如图 6a所示, 该系统可包括一服务器端和一客户端, 该服务器端包括第 一存储器、 以及与所述第一存储器通信的第一处理器, 其中所述第一存储器 存储有可由所述第一处理器执行的聚类分析指令和推荐指令。
其中, 聚类分析指令用于指示根据用户的客户端上报的软件使用信息对 用户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情 况对所述软件列表中的软件进行排序。
推荐指令用于指示根据具体用户的客户端的软件使用信息确定与该具体 用户最相关的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的软件 推荐给该具体用户, 所述 N为预定值。
相应地, 客户端也可包括第二存储器以及与所述第二存储器通信的第二 处理器, 其中, 所述第二存储器存储有可由所述第二处理器执行的数据采集 指令, 用于指示采集具有上报数据权限的用户的软件使用信息, 并上报给服 务器。
图 6b为才艮据本发明实施例的电子地图测距装置的又一个结构示意图。 如 图 6b所示, 该系统可包括一服务器端和一客户端, 该服务器端包括第一存储 器、 以及与所述第一存储器通信的第一处理器, 其中所述第一存储器存储有 可由所述第一处理器执行的聚类分析指令。
其中, 聚类分析指令用于指示根据用户的客户端上报的软件使用信息对 用户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情 况对所述软件列表中的软件进行排序, 并将所述每种用户聚类信息及其对应 的经过所述排序的软件列表下发给客户端。
客户端可包括第二存储器以及与所述第二存储器通信的第二处理器, 其 中, 所述第二存储器存储有可由所述第二处理器执行的数据采集指令和推荐 指令。
数据采集指令用于指示采集具有上报数据权限的用户的软件使用信息, 并上报给服务器; 或指示采集没有上报数据权限的用户的软件使用信息; 推荐指令用于指示通过客户端本机的数据采集指令获取本机具体用户的 软件使用信息, 并指示根据具体用户的客户端的软件使用信息确定与该具体 用户最相关的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的软件 作为被推荐软件进行显示, 所述 N为预定值。 如上所述, 本发明实施例中的技术方案可以通过一系列处理推算出用户 使用软件的偏好, 根据该技术方案推送的软件将提高软件推荐与用户需求符 合的精准程度, 并且对于一些较出色、 但较为小众的软件也很容易被推荐给 相关用户。 至于被推荐的目标软件在客户端上的显示方式, 可以有多种方式, 例如 在本发明的一种实施例中, 可以通过图标方式显示被推荐的目标软件, 并可 以采用单击执行安装的方式, 让整个推荐流程变得比较轻薄, 顺畅, 最大程 度上简化流程, 降低用户的心理压力。
如图 5a为通过图标方式显示被推荐目标软件的界面示意图。 参见图 5a, 被推送的目标软件可以以与其它图标相区别的形式, 例如可以采用浅灰图标 500 (其它图标为深色)的形式将被推荐的目标软件的图标呈现在软件管理系 统的操作面板中, 例如此处为一种名叫 "小 Q书桌" 的较为轻盈的软件启动 操作面板 501。 其中, 当鼠标置于所述浅灰图标 500之上时, 可以显示软件的 基本信息; 所述目标软件的推送频率可以在后台进行配置, 例如基本频率为 每周一款软件。
图 5b为通过图标方式显示被推荐目标软件在被点击后的界面示意图。 参 见图 5b, 单击所述浅灰图标 500后则触发下载及安装过程; 下载完成后会静 默安装; 安装完成后, 图标点亮 (即浅灰色被去除), 表示可正常使用。
图 5c为通过图标方式显示被推荐目标软件在下载安装完成后的界面示意
图。 如图 5c所示, 在安装完成后, 所述软件图标 500点亮, 可与其它 "小 Q 书桌" 面板中的图标同样使用。
如果用户不点击所述浅灰图标 500, 可通过以下两种方式移除浅灰图标
500:
1 )常规删除操作: 进入编辑模式后, 点击右上角的减号, 删除浅灰图标。 如图 5d为通过图标方式显示被推荐目标软件的编辑模式的界面示意图。
2 ) 当推送下一款软件时, 检测到上一个浅灰图标未被安装, 则自动替换 原有图标。
对于错误情况的处理主要包括:
如果网络连接不正常, 则弹出浮窗提示 "网络连接异常, 下载失败", 用 户再次点击浅灰图标 500时, 重新触发下载目标软件。
如果下载后, 安装过程失败, 则浅灰图标 500保持浅灰色; 并弹出浮窗 提示 "安装失败, 请重试", 用户再次点击浅灰图标时, 重新触发静默安装。 如所述图 5a至图 5d所示, 在此类图标管理软件面板推荐软件产品, 较 符合用户心理预期。 可以丰富此类软件的实用性, 在图标管理的基础上扩展 出软件推荐的特性。 以上所述仅为本发明的较佳实施例而已, 并不用以限制本发明, 凡在本 发明的精神和原则之内, 所做的任何修改、 等同替换、 改进等, 均应包含在 本发明保护的范围之内。
Claims
1、 一种推荐目标软件的处理方法, 其特征在于, 包括:
根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户聚类 对应的软件列表, 按照软件的使用情况对所述软件列表中的软件进行排序; 根据具体用户的软件使用信息确定与该具体用户最相关的用户聚类; 在 该用户聚类对应的软件列表中选择前 N位的软件推荐给该具体用户, 所述 N 为预定值。
2、 根据权利要求 1所述的方法, 其特征在于, 所述用户上报的软件使用 信息包括: 用户客户端已安装软件的软件信息;
所述根据用户上报的软件使用信息对用户进行聚类分析, 具体包括: 统计各采样用户上报的各类已安装软件的软件数量;
确定出各采样用户所安装软件数量最多的软件类别;
以所述安装软件数量最多的软件类别为相似度, 对采样用户进行聚类划 分, 得到不同软件使用特征的用户聚类。
3、 根据权利要求 1所述的方法, 其特征在于, 所述按照软件的使用情况 对所述软件列表中的软件进行排序, 具体包括:
采集各软件的网络下载量和采样用户所上报的各软件在用户客户端本机 上的启动次数和运行时间;
针对每一软件, 将该软件的网络下载量、 启动次数和运行时间分别乘以 对应的权重, 最后再求和, 得到该软件的整体运行热度, 将该软件的整体运 行热度作为该软件的使用情况;
按照软件的整体运行热度对所述软件列表中的软件进行排序。
4、 根据权利要求 1所述的方法, 其特征在于, 所述具体用户的软件使用 信息包括: 该具体用户客户端本机已安装的软件信息和 /或经常启动的软件信 息;
所述根据具体用户的软件使用信息确定与该用户最相关的用户聚类, 具
体包括:
在每种用户聚类对应的软件列表中, 按照每款软件的排序名次确定该软 件与该用户聚类的聚类相关度;
根据各用户聚类对应的软件列表及其软件的所述聚类相关度, 确定所述 具体用户的客户端本机中的各已安装软件和 /或经常启动软件所属的用户聚 类, 以及确定所述各已安装软件和 /或经常启动软件与其所属用户聚类的聚类 相关度;
将属于同一用户聚类的所述软件的聚类相关度相加, 得到该用户聚类的 匹配分数;
选择匹配分数最高的用户聚类作为与该用户最相关的用户聚类。
5、 根据权利要求 4所述的方法, 其特征在于, 所述将属于同一用户聚类 的所述软件的聚类相关度相加, 得到该用户聚类的匹配分数, 具体包括: 为所述经常启动软件分配比所述已安装软件更高的权值, 将属于同一用 户聚类的所述软件的聚类相关度按照所述的软件权值进行加权相加, 将得到 的加权和作为该用户聚类的匹配分数。
6、 根据权利要求 1所述的方法, 其特征在于,
所述根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户 聚类对应的软件列表, 按照软件的使用情况对所述软件列表中的软件进行排 序的步骤, 由服务器端执行;
所述具体用户为具有上报数据权限的用户;
所述根据该具体用户的软件使用信息确定与该具体用户最相关的用户聚 类, 在该用户聚类对应的软件列表中选择前 N位的软件推荐给该具体用户, 具体包括:
该具体用户的客户端获得本机的软件使用信息, 并上传给服务器端; 服务器端根据该具体用户客户端上报的软件使用信息确定与该具体用户 最相关的用户聚类, 在该用户聚类对应的软件列表中选择前 N位的软件发送 给该具体用户的客户端;
该具体用户的客户端将所述前 N位软件作为被推荐软件进行显示。
7、 根据权利要求 6所述的方法, 其特征在于, 在所述具体用户的客户端
将所述前 N位软件作为被推荐软件进行显示之后 , 进一步包括:
所述具体用户的客户端将所述被推荐软件的使用信息发送给服务器端; 服务器端根据所述被推荐软件的使用信息确定其被推荐热度;
根据被推荐软件的被推荐热度调整对应用户聚类对应的软件列表中该被 推荐软件的排列位次, 其中, 对于被推荐热度大于指定阈值的被推荐软件调 高其排列位次, 对于被推荐热度小于指定阈值的被推荐软件则调低其排列位 次。
8、 根据权利要求 7所述的方法, 其特征在于, 所述被推荐软件的使用信 息包括以下至少一种: 该软件的安装次数、 该软件从启动到结束的时间、 该 软件安装完成后的二次启动量。
9、 根据权利要求 1所述的方法, 其特征在于,
所述根据全量用户上报的软件使用信息对用户进行聚类分析, 确定每种 用户聚类对应的软件列表, 按照软件的使用情况对所述软件列表中的软件进 行排序的步骤, 由服务器端执行;
所述具体用户为不具有上报数据权限的用户;
所述根据该具体用户的软件使用信息确定与该具体用户最相关的用户聚 类, 在该用户聚类对应的软件列表中选择前 N位的软件推荐给该具体用户, 具体包括:
服务器端将所述每种用户聚类信息及其对应的经过所述排序的软件列表 下发给该具体用户的客户端;
该具体用户的客户端获得本机的软件使用信息;
该具体用户的客户端根据该本机的软件使用信息确定与该具体用户最相 关的用户聚类, 在该用户聚类对应的软件列表中选择前 N位的软件作为被推 荐软件进行显示。
10、 根据权利要求 1至 9任一项所述的方法, 其特征在于, 所述在该用 户聚类对应的软件列表中选择前 N位的软件推荐给该具体用户, 具体包括: 在该用户聚类的待推荐软件列表中去除该具体用户已经安装的软件, 再 从剩余的软件中选择排在前 N位的软件推荐给该具体用户。
11、 根据权利要求 10所述的方法, 其特征在于, 所述 N=l。
12、 一种推荐目标软件的处理系统, 其特征在于, 包括:
聚类分析模块, 用于根据用户上报的软件使用信息对用户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情况对所述软件列表中 的软件进行排序;
推荐模块, 用于根据具体用户的软件使用信息确定与该具体用户最相关 的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的软件推荐给该具 体用户, 所述 N为预定值。
13、 根据权利要求 12所述的系统, 其特征在于, 该系统进一步包括: 数 据采集模块, 设置在客户端, 用于采集具有上报数据权限的用户的软件使用 信息, 并上报给聚类分析模块和推荐模块。
14、 根据权利要求 13所述的系统, 其特征在于, 所述聚类分析模块和推 荐模块设置在服务器端。
15、 根据权利要求 13所述的系统, 其特征在于,
所述聚类分析模块设置在服务器端, 所述推荐模块设置在客户端; 所述聚类分析模块进一步用于将所述每种用户聚类信息及其对应的经过 所述排序的软件列表下发给客户端;
所述推荐模块进一步用于从客户端本机的数据采集模块中获取本机具体 用户的软件使用信息, 根据该具体用户的软件使用信息确定与该具体用户最 相关的用户聚类, 在该用户聚类对应的软件列表中选择前 N位的软件作为被 推荐软件进行显示。
16、 根据权利要求 12所述的系统, 其特征在于,
所述用户上报的软件使用信息包括: 用户客户端本机已安装软件的软件 信息;
所述具体用户的软件使用信息包括: 该具体用户客户端本机已安装软件
的软件信息, 和 /或经常启动的软件信息。
17、 一种推荐目标软件的处理系统, 其特征在于, 包括: 一服务器端和 一客户端, 该服务器端包括第一存储器、 以及与所述第一存储器通信的第一 处理器, 其中所述第一存储器存储有可由所述第一处理器执行的聚类分析指 令和推荐指令;
所述聚类分析指令用于指示根据用户的客户端上报的软件使用信息对用 户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情况 对所述软件列表中的软件进行排序;
所述推荐指令用于指示根据具体用户的客户端的软件使用信息确定与该 具体用户最相关的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的 软件推荐给该具体用户, 所述 N为预定值。
18、 根据权利要求 17所述的系统, 其特征在于, 所述客户端包括第二存 储器以及与所述第二存储器通信的第二处理器, 其中, 所述第二存储器存储 有可由所述第二处理器执行的数据采集指令, 用于指示采集具有上报数据权 限的用户的软件使用信息, 并上报给服务器。
19、 一种推荐目标软件的处理系统, 其特征在于, 包括: 一服务器端和 一客户端, 该服务器端包括第一存储器、 以及与所述第一存储器通信的第一 处理器, 其中所述第一存储器存储有可由所述第一处理器执行的聚类分析指 令; 客户端包括第二存储器以及与所述第二存储器通信的第二处理器, 其中, 所述第二存储器存储有可由所述第二处理器执行的数据采集指令和推荐指 令;
所述聚类分析指令用于指示根据用户的客户端上报的软件使用信息对用 户进行聚类分析, 确定每种用户聚类对应的软件列表, 按照软件的使用情况 对所述软件列表中的软件进行排序, 并将所述每种用户聚类信息及其对应的 经过所述排序的软件列表下发给客户端;
所述数据采集指令用于指示采集具有上报数据权限的用户的软件使用信 息, 并上报给服务器; 或指示采集没有上报数据权限的用户的软件使用信息; 所述推荐指令用于指示通过客户端本机的数据采集指令获取本机具体用 户的软件使用信息, 并指示根据具体用户的客户端的软件使用信息确定与该 具体用户最相关的用户聚类; 在该用户聚类对应的软件列表中选择前 N位的
软件作为被推荐软件进行显示, 所述 N为预定值。
20、 一种计算机可读存储介质, 其特征在于, 其中存储有计算机程序, 该计算机程序用于执行如权利要求 1 至 11 中所述的推荐目标软件的处理方 法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
SG11201408443SA SG11201408443SA (en) | 2012-06-21 | 2013-06-20 | Method and system for processing recommended target software |
US14/576,788 US10061837B2 (en) | 2012-06-21 | 2014-12-19 | Method and system for processing recommended target software |
US16/053,697 US11048726B2 (en) | 2012-06-21 | 2018-08-02 | Method and system for processing recommended target software |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210207154.9A CN103514496B (zh) | 2012-06-21 | 2012-06-21 | 一种推荐目标软件的处理方法及系统 |
CN201210207154.9 | 2012-06-21 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/576,788 Continuation US10061837B2 (en) | 2012-06-21 | 2014-12-19 | Method and system for processing recommended target software |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013189296A1 true WO2013189296A1 (zh) | 2013-12-27 |
Family
ID=49768123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2013/077577 WO2013189296A1 (zh) | 2012-06-21 | 2013-06-20 | 一种推荐目标软件的处理方法及系统 |
Country Status (4)
Country | Link |
---|---|
US (2) | US10061837B2 (zh) |
CN (1) | CN103514496B (zh) |
SG (1) | SG11201408443SA (zh) |
WO (1) | WO2013189296A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106162348A (zh) * | 2015-04-13 | 2016-11-23 | 海信集团有限公司 | 一种个性化节目推荐方法及装置 |
CN106682196A (zh) * | 2016-12-29 | 2017-05-17 | 北京奇虎科技有限公司 | 相关软件的推荐方法和装置 |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103514496B (zh) | 2012-06-21 | 2017-05-17 | 腾讯科技(深圳)有限公司 | 一种推荐目标软件的处理方法及系统 |
CN104615452A (zh) * | 2014-09-19 | 2015-05-13 | 安一恒通(北京)科技有限公司 | 信息提供方法和装置 |
CN104360858A (zh) * | 2014-11-12 | 2015-02-18 | 华为技术有限公司 | 一种计算应用热度的方法及装置 |
CN105897801A (zh) * | 2014-12-05 | 2016-08-24 | 广西大学 | 基于云存储的手机对等免疫方法 |
CN104504149A (zh) * | 2015-01-08 | 2015-04-08 | 中国联合网络通信集团有限公司 | 一种实现应用推荐的方法及装置 |
CN104991914B (zh) * | 2015-06-23 | 2018-04-27 | 腾讯科技(深圳)有限公司 | 一种应用推荐方法及服务器 |
CN106503025B (zh) * | 2015-09-08 | 2021-02-12 | 北京搜狗科技发展有限公司 | 一种应用推荐方法和系统 |
US10402758B2 (en) * | 2015-10-14 | 2019-09-03 | Facebook, Inc. | Identifying additional applications for comparison to an application with which online system users interact |
CN107885742B (zh) * | 2016-09-29 | 2021-09-07 | 腾讯科技(深圳)有限公司 | 服务推荐方法和装置 |
CN107291446B (zh) * | 2017-05-16 | 2021-06-08 | 北京金山安全软件有限公司 | 一种桌面管理方法及装置 |
CN108984551A (zh) * | 2017-05-31 | 2018-12-11 | 广州智慧城市发展研究院 | 一种基于多类别联合软聚类的推荐方法及系统 |
CN107872535A (zh) * | 2017-12-04 | 2018-04-03 | 广东欧珀移动通信有限公司 | 应用程序推送方法、装置、服务器以及存储介质 |
CN108363804B (zh) * | 2018-03-01 | 2020-08-21 | 浙江工业大学 | 基于用户聚类的局部模型加权融合Top-N电影推荐方法 |
US10664380B2 (en) * | 2018-04-10 | 2020-05-26 | Mastercontrol, Inc. | Risk-based software validation and change control |
US11853306B2 (en) | 2018-06-03 | 2023-12-26 | Apple Inc. | Techniques for personalizing app store recommendations |
CN108510402A (zh) * | 2018-06-06 | 2018-09-07 | 中国平安人寿保险股份有限公司 | 险种信息推荐方法、装置、计算机设备及存储介质 |
CN109271303B (zh) * | 2018-09-06 | 2021-11-02 | 上海华云互越数据技术有限公司 | 一种软件配置推荐方法 |
CN110830654B (zh) * | 2019-11-07 | 2020-12-08 | 腾讯科技(深圳)有限公司 | 一种播放语音消息的方法及设备 |
CN111581366B (zh) * | 2020-05-09 | 2023-08-29 | 北京百度网讯科技有限公司 | 用户意图确定方法、装置、电子设备和可读存储介质 |
CN111672128A (zh) * | 2020-05-18 | 2020-09-18 | 苏州思酷数字科技有限公司 | 基于本地保留时长识别的游戏商城游戏推荐方法及系统 |
CN112257939B (zh) * | 2020-10-28 | 2023-02-28 | 每日互动股份有限公司 | 一种地理区域热度的处理方法、计算机设备及介质 |
CN113094087A (zh) * | 2021-04-14 | 2021-07-09 | 深圳市元征科技股份有限公司 | 软件配置方法、电子设备及存储介质 |
CN113657971B (zh) * | 2021-08-31 | 2023-12-01 | 卓尔智联(武汉)研究院有限公司 | 物品推荐方法、装置及电子设备 |
CN116401460B (zh) * | 2023-04-23 | 2024-04-05 | 中航信移动科技有限公司 | 一种提高信息推送准确性的方法、存储介质及电子设备 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090271356A1 (en) * | 2008-04-25 | 2009-10-29 | Samsung Electronics Co., Ltd. | Situation-aware thresholding for recommendation |
CN101937547A (zh) * | 2010-09-15 | 2011-01-05 | 宇龙计算机通信科技(深圳)有限公司 | 软件和/或软件信息推送方法、系统、获取装置、软件商店服务系统及移动终端 |
CN102104688A (zh) * | 2011-02-15 | 2011-06-22 | 宇龙计算机通信科技(深圳)有限公司 | 软件推荐方法和移动终端 |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7158986B1 (en) * | 1999-07-27 | 2007-01-02 | Mailfrontier, Inc. A Wholly Owned Subsidiary Of Sonicwall, Inc. | Method and system providing user with personalized recommendations by electronic-mail based upon the determined interests of the user pertain to the theme and concepts of the categorized document |
US8214264B2 (en) * | 2005-05-02 | 2012-07-03 | Cbs Interactive, Inc. | System and method for an electronic product advisor |
JP4698281B2 (ja) * | 2005-05-09 | 2011-06-08 | ソニー・エリクソン・モバイルコミュニケーションズ株式会社 | 携帯端末、情報推奨方法及びプログラム |
US8095521B2 (en) * | 2007-03-30 | 2012-01-10 | Amazon Technologies, Inc. | Recommendation system with cluster-based filtering of recommendations |
US7743059B2 (en) * | 2007-03-30 | 2010-06-22 | Amazon Technologies, Inc. | Cluster-based management of collections of items |
US10013489B2 (en) * | 2009-08-12 | 2018-07-03 | Oath Inc. | System and method for providing recommendations |
CN101867594A (zh) * | 2010-03-05 | 2010-10-20 | 宇龙计算机通信科技(深圳)有限公司 | 一种数据传输的方法、装置及系统 |
CN101887390A (zh) * | 2010-06-23 | 2010-11-17 | 宇龙计算机通信科技(深圳)有限公司 | 一种应用软件评级方法及装置 |
US9058612B2 (en) * | 2011-05-27 | 2015-06-16 | AVG Netherlands B.V. | Systems and methods for recommending software applications |
US20130085886A1 (en) * | 2011-09-29 | 2013-04-04 | Symantec Corporation | Method and system for automatic application recommendation |
CN102541590B (zh) * | 2011-12-14 | 2015-09-30 | 北京奇虎科技有限公司 | 一种软件推荐方法及推荐系统 |
CN103514496B (zh) | 2012-06-21 | 2017-05-17 | 腾讯科技(深圳)有限公司 | 一种推荐目标软件的处理方法及系统 |
US9710247B2 (en) * | 2012-06-26 | 2017-07-18 | Microsoft Technology Licensing, Llc | Identification of host-compatible downloadable applications |
US20140007070A1 (en) * | 2012-06-29 | 2014-01-02 | International Business Machines Corporation | Managing Software Product Lifecycle Across Multiple Operating System Platforms |
US20140244762A1 (en) * | 2013-02-26 | 2014-08-28 | Facebook, Inc. | Application distribution platform for rating and recommending applications |
-
2012
- 2012-06-21 CN CN201210207154.9A patent/CN103514496B/zh active Active
-
2013
- 2013-06-20 SG SG11201408443SA patent/SG11201408443SA/en unknown
- 2013-06-20 WO PCT/CN2013/077577 patent/WO2013189296A1/zh active Application Filing
-
2014
- 2014-12-19 US US14/576,788 patent/US10061837B2/en active Active
-
2018
- 2018-08-02 US US16/053,697 patent/US11048726B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090271356A1 (en) * | 2008-04-25 | 2009-10-29 | Samsung Electronics Co., Ltd. | Situation-aware thresholding for recommendation |
CN101937547A (zh) * | 2010-09-15 | 2011-01-05 | 宇龙计算机通信科技(深圳)有限公司 | 软件和/或软件信息推送方法、系统、获取装置、软件商店服务系统及移动终端 |
CN102104688A (zh) * | 2011-02-15 | 2011-06-22 | 宇龙计算机通信科技(深圳)有限公司 | 软件推荐方法和移动终端 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106162348A (zh) * | 2015-04-13 | 2016-11-23 | 海信集团有限公司 | 一种个性化节目推荐方法及装置 |
CN106682196A (zh) * | 2016-12-29 | 2017-05-17 | 北京奇虎科技有限公司 | 相关软件的推荐方法和装置 |
Also Published As
Publication number | Publication date |
---|---|
US11048726B2 (en) | 2021-06-29 |
CN103514496B (zh) | 2017-05-17 |
US20190034515A1 (en) | 2019-01-31 |
CN103514496A (zh) | 2014-01-15 |
SG11201408443SA (en) | 2015-02-27 |
US10061837B2 (en) | 2018-08-28 |
US20150120742A1 (en) | 2015-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2013189296A1 (zh) | 一种推荐目标软件的处理方法及系统 | |
US11755387B1 (en) | Updating code of an app feature based on a value of a query feature | |
US10277696B2 (en) | Method and system for processing data used by creative users to create media content | |
WO2021098648A1 (zh) | 文本推荐方法、装置、设备及介质 | |
US9317613B2 (en) | Large scale entity-specific resource classification | |
US8751518B1 (en) | Fixed phrase detection for search | |
US20090158146A1 (en) | Resizing tag representations or tag group representations to control relative importance | |
US20130318514A1 (en) | Map generator for representing interrelationships between app features forged by dynamic pointers | |
US20140358630A1 (en) | Apparatus and process for conducting social media analytics | |
CN103136228A (zh) | 一种图片搜索方法以及图片搜索装置 | |
CN101847158A (zh) | 基于上下文的视频查找器 | |
CN108304432B (zh) | 信息推送处理方法、信息推送处理装置及存储介质 | |
CN103279513A (zh) | 产生内容标签的方法、提供多媒体内容信息的方法及装置 | |
US20090089285A1 (en) | Method of detecting spam hosts based on propagating prediction labels | |
KR20050120786A (ko) | 콘텐트 항목들을 그룹화하기 위한 방법 및 장치 | |
CN111191111B (zh) | 内容推荐方法、装置及存储介质 | |
JP6457123B2 (ja) | 探索処理方法およびデバイス | |
US11423096B2 (en) | Method and apparatus for outputting information | |
CN109857901B (zh) | 信息展示方法和装置、以及用于信息搜索的方法和装置 | |
CN110290199B (zh) | 内容推送方法、装置及设备 | |
CN102402589A (zh) | 一种提供与搜索请求相关的参考搜索信息的方法与设备 | |
US20140222831A1 (en) | Method and system for personalized delivery of media content | |
WO2017136295A1 (en) | Adaptive seeded user labeling for identifying targeted content | |
US20130346385A1 (en) | System and method for a purposeful sharing environment | |
CN105574030A (zh) | 一种信息搜索方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13806359 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 27/02/2015) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13806359 Country of ref document: EP Kind code of ref document: A1 |