CN106940705B - A method and device for constructing user portraits - Google Patents
A method and device for constructing user portraits Download PDFInfo
- Publication number
- CN106940705B CN106940705B CN201611186477.9A CN201611186477A CN106940705B CN 106940705 B CN106940705 B CN 106940705B CN 201611186477 A CN201611186477 A CN 201611186477A CN 106940705 B CN106940705 B CN 106940705B
- Authority
- CN
- China
- Prior art keywords
- application
- user
- information
- tag information
- topic
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000013598 vector Substances 0.000 claims description 93
- 238000009434 installation Methods 0.000 claims description 63
- 230000015654 memory Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000003068 static effect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 16
- 230000008569 process Effects 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000005291 magnetic effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 230000004580 weight loss Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000003936 working memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本申请的目的是提供一种用于构建用户画像的方法与设备。与现有技术相比，本申请获取用户在用户设备上使用应用的应用使用记录信息，根据所述应用使用记录信息确定所述用户对应的一个或多个应用标签信息，然后，基于所述一个或多个应用标签信息，构建所述用户的用户画像信息；本申请所述应用使用记录信息相对于用户网页浏览记录、社交网络关系、新闻广告点击记录等用户信息而言，具有静态稳定、数据量小、信息量大的优点，因而，本申请所构建的用户画像信息能够更加精准地定义和识别用户。
The purpose of this application is to provide a method and device for constructing a user portrait. Compared with the prior art, the present application obtains the application usage record information of the application used by the user on the user equipment, determines one or more application tag information corresponding to the user according to the application usage record information, and then, based on the one or more application tag information. or multiple application tag information to construct the user portrait information of the user; the application usage record information described in this application has static stability, data stability, and data relative to user information such as user web page browsing records, social network relationships, news advertisement click records, etc. Therefore, the user portrait information constructed in this application can define and identify users more accurately.
Description
Technical Field
The present application relates to the field of communications, and more particularly, to a technique for building a user representation.
Background
User portrayal is a tool and method for objectively and accurately describing a target user. The user representation includes multi-dimensional information of the user, such as basic attributes (age, sex, region, constellation, etc.), social features (family structure, marital status, etc.), interest features (interest, content of interaction, etc.), and other behavior, consumption and purchasing power features required in different situations. In the prior art, the user portrait is mostly constructed based on different user information, such as a user call log, base station location information, a user web browsing record, a user online shopping record, a news advertisement click record, social network relationship and interest, and the like. The information is usually fast in change and unstable, such as the user browsing the web page and clicking on the news record will change all the time; meanwhile, some information collection needs to be performed after a user logs in to determine the attribution of the information, such as online shopping records, social network information and the like.
Disclosure of Invention
It is an object of the present application to provide a method and apparatus for constructing a user representation.
According to one aspect of the present application, there is provided a method for constructing a user representation, wherein the method comprises:
acquiring application use record information of an application used by a user on user equipment;
determining one or more pieces of application label information corresponding to the user according to the application use record information;
constructing user representation information for the user based on the one or more application tag information.
According to another aspect of the present application, there is provided a method for determining application tag information of a user, wherein the method includes:
acquiring application use record information of an application used by a user on user equipment;
acquiring an application theme vector corresponding to the application on the user equipment according to the application use record information;
and determining the application label information corresponding to the user according to one or more topic keywords in the application topic vector.
According to yet another aspect of the application, there is provided an apparatus for constructing a user representation, wherein the apparatus comprises:
the device comprises a first device, a second device and a third device, wherein the first device is used for acquiring application use record information of an application used by a user on user equipment;
second means for determining one or more pieces of application tag information corresponding to the user according to the application usage record information;
third means for constructing user representation information for the user based on the one or more application tag information.
According to still another aspect of the present application, there is provided an apparatus for determining application tag information of a user, wherein the apparatus includes:
fifth means for acquiring application usage record information of an application used by a user on the user equipment;
a sixth device, configured to obtain, according to the application usage record information, an application theme vector corresponding to the application on the user equipment;
and a seventh device, configured to determine, according to one or more topic keywords in the application topic vector, application tag information corresponding to the user.
According to yet another aspect of the present application, there is provided a computer-readable storage medium comprising instructions that, when executed, cause a system to:
acquiring application use record information of an application used by a user on user equipment;
determining one or more pieces of application label information corresponding to the user according to the application use record information;
constructing user representation information for the user based on the one or more application tag information.
According to yet another aspect of the present application, there is provided a computer-readable storage medium comprising instructions that, when executed, cause a system to:
acquiring application use record information of an application used by a user on user equipment;
acquiring an application theme vector corresponding to the application on the user equipment according to the application use record information;
and determining the application label information corresponding to the user according to one or more topic keywords in the application topic vector.
According to yet another aspect of the application, there is provided an apparatus for constructing a user representation, wherein the apparatus comprises:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring application use record information of an application used by a user on user equipment;
determining one or more pieces of application label information corresponding to the user according to the application use record information;
constructing user representation information for the user based on the one or more application tag information.
According to still another aspect of the present application, there is provided an apparatus for determining application tag information of a user, wherein the apparatus includes:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring application use record information of an application used by a user on user equipment;
acquiring an application theme vector corresponding to the application on the user equipment according to the application use record information;
and determining the application label information corresponding to the user according to one or more topic keywords in the application topic vector.
Compared with the prior art, the method and the device have the advantages that application use record information of the application used by the user on the user equipment is obtained, one or more pieces of application label information corresponding to the user are determined according to the application use record information, and then the user portrait information of the user is constructed based on the one or more pieces of application label information; the application uses the user information such as record information for user's web browsing record, social network relation, news advertisement click record, has static stability, the data volume is little, the information volume is big advantage, therefore, the user portrait information that this application founds can more accurately define and discern the user. Further, the application label information comprises application installation label information and/or application active label information, and the user is labeled from different dimensions, so that more accurate user portrait information is constructed. Further, the application installation label information and/or the application activity label information based on the application theme are provided, richer differentiation label information is obtained, and the applications can be better classified.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 illustrates a flow diagram of a method for constructing a user representation according to one embodiment of the present application;
FIG. 2 illustrates a flow diagram of a method for determining application tag information for a user according to another embodiment of the present application;
FIG. 3 shows a schematic diagram of an apparatus for constructing a user representation, in accordance with one embodiment of the present application;
fig. 4 shows a schematic diagram of an apparatus for determining application tag information of a user according to another embodiment of the present application.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
The present application is described in further detail below with reference to the attached figures.
In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
FIG. 1 shows a flowchart of a method for constructing a user representation, according to one embodiment of the present application, including step S11, step S12, and step S13.
Specifically, in step S11, device 1 acquires application usage record information of the application used by the user on the user device; in step S12, the device 1 determines one or more pieces of application label information corresponding to the user according to the application usage record information; in step S13, the device 1 constructs user representation information of the user based on the one or more application label information.
Here, the device 1 includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, and the like, which can perform human-computer interaction with a user through a touch panel, and the mobile electronic product may employ any operating system, such as an android operating system, an iOS operating system, and the like. The network device includes an electronic device capable of automatically performing numerical calculation and information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The network device comprises but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud formed by a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device 1 may also be a script program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network. Of course, those skilled in the art will appreciate that the above-described apparatus 1 is merely exemplary, and that other existing or future existing apparatus 1, as may be suitable for use in the present application, are also intended to be encompassed within the scope of the present application and are hereby incorporated by reference.
In step S11, the device 1 acquires application use record information of the application used by the user on the user device.
For example, the application usage record information may include the name or identification information of the application, and information of the number of times of use, the length of time of use per time, the usage consumption flow, and the like, in a period of time (one day, one week, one half month, one month, and the like). Here, the data collection may be performed through an APP installed on the user equipment to acquire the application usage record information, or the application usage record information may be acquired from a third party.
In step S12, the device 1 determines one or more pieces of application label information corresponding to the user according to the application usage record information.
In the mobile user, each user basically uses one user device independently, each user device has a unique identification (such as an imei number or a mac address), and the application use record information can reflect the real characteristics of the user relatively truly. And labeling the users with different characteristics according to the application use record information, and determining one or more pieces of application label information corresponding to the users.
Preferably, in step S12, the device 1 queries application library information according to the application usage record information, and determines one or more pieces of application tag information corresponding to the user.
Here, the application library information includes information such as category, description, price, download amount, etc. of an application, which can be obtained from a network, such as an application market (Google Play, iOS app store, etc.) can provide.
Preferably, the application tag information includes at least any one of: applying installation tag information; applying active tag information; installing tag information based on the application of the application theme; application activity tag information based on application topics.
For example, the application installation tag information is determined based on applications installed by a user, and the application active tag information is determined based on the applications installed by the user and the usage frequency (the number of usage times in a time period, the time length of each usage, the usage consumption flow, and the like) of each application. The application installation tag information comprises application installation tag information based on an application theme, and the application activity tag information comprises application activity tag information based on an application theme. The application theme is used to compare specific information that embodies the application in its entirety.
Preferably, the application installation tag information includes at least any one of: application installation tag information based on category, application installation tag information based on price; the application active tag information comprises at least any one of: category-based application activity label information, price-based application activity label information.
For example, according to the application types installed by the user, the number of the application installations of different types is counted, and one or more types of application installation label information corresponding to the user is determined according to the information, and the weight of each application is the same in the process. Suppose that user a has m mobile applications installed on the mobile phone, and belongs to k different categories: category 1, category 2 … category k, the corresponding number of applications being: c1, c2 … ck; then the category-based application installation tag information for user a may be: [ "class 1": c1, "class 2": c2, …, "class k": ck ]; alternatively, the number of applications may also use a normalized value, for example, the weight of the category 1 may be C1/C, where C is C1+ C2+ … + ck, which is the total number of installed applications.
For another example, according to price information of an application installed by a user, one or more pieces of price-based application installation tag information corresponding to the user are determined, and then the installation situation of the user on the paid application is analyzed, so that the attitude and the economic condition of the user on the paid application can be reflected to a certain extent. The price-based application installation tag information for a user may be [ "pay": c1, "free": c2, "pay for use": 0 or 1], wherein, c1 installs the number of free applications for the user, c2 installs the number of paid applications for the user, and the value of the pay label is determined to be 1 or 0 according to whether the user applies the paid applications.
For another example, according to the category/price information of the application used by the user and the corresponding usage frequency (the number of usage times in a time period, the duration of each usage, the usage consumption flow rate, etc.), one or more category/price-based application active label information corresponding to the user is determined, in the process, the weight of each application used by the user is different, and the weight value is proportional to the usage frequency of the application. Assume that user B's category-based application activity tag information may be: [ "category 1": T1, "category 2": T2, …, "category k": tk ], where "category 1" is the category of the application used by the user, and T1 is the usage traffic of the application used by the user for a period of time, where the weight may also be a normalized value T1/T, where T is T1+ T2+ … + tk. Alternatively, the category-based application activity tag information of user B may also be: [ "category 1": n1, "category 2": n2, …, "category k": nk ], where "category 1" is a category corresponding to an application used by a user, and n1 is the number of times the application of the category is used for a period of time, or takes a normalized value. In the process, different time period selections can reflect different application use interests of the user in the time period selections. A time range such as three months, half a year, etc. may be selected to obtain the long term active category label of the user, a time range such as one month, half a month, etc. may be selected to obtain the medium term active category label of the user, and a time range such as one week, one day, two days, etc. may be selected to obtain the short term active category label of the user.
More preferably, the application tag information includes application installation tag information or application active tag information based on an application theme; in step S12, the device 1 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information; and determining the application installation tag information or the application active tag information based on the application theme corresponding to the user according to one or more theme key words in the application theme vector.
With the increase of the number of applications and the abundance of application functions, it is more and more difficult for developers to classify the applications, and the specific information of the applications cannot be comprehensively reflected to a certain extent by the category information. Aiming at the possibility that the application category division and the like are inaccurate, large in roughness and small in information amount and one application may have multiple categories, the application installation label information and/or the application active label information based on the application theme are provided, and the application theme is used for comprehensively embodying the specific information of the application. For example, an application topic vector corresponding to a social-class application may be: [ "communication": 0.1, "short message": 0.15, "speech": 0.2, "video": 0.15, "chat": 0.4], an application theme vector for a motion class application may be: [ "basketball": 0.1, "running": 0.2, "calories": 0.2, "weight loss": 0.1, "sport": 0.4], the keywords (such as correspondence, basketball, etc.) are the main labels constituting the application theme, and the weights (such as 0.1, 0.2, etc.) represent the frequency of occurrence of the corresponding keywords in the application theme.
In step S13, the device 1 constructs user representation information of the user based on the one or more application label information.
For example, the user profile information of the user may be constructed based on all application tag information, or may be constructed based on some (e.g., a number of application tag information with weights greater than corresponding thresholds) of the application tag information.
Preferably, in step S13, the device 1 constructs user representation information of the user based on the target application scene of the user representation and the one or more application tag information.
For example, the target application scenarios include, but are not limited to: and (4) inspecting the scenes related to the installation of the user APP and inspecting the scenes of the preference of the user APP.
Preferably, in step S13, the device 1 constructs user representation information of the user based on a target application scene of the user representation and the one or more application tag information, wherein the user representation information includes the application tag information matching the target application scene.
For example, if the target application scenario is related to a short-term behavior of a user, the application active tag information in a time range of one week, one day, two days, etc. may be selected; if the target application scene is related to the user middle-term behavior, the application active label information in the time range of one month, half month and the like can be selected; if the target application scenario is associated with a long-term behavior of a user, the application active tag information may be selected within a time range such as three months, half a year, and the like. That is, the selected application tag information should match the target scene.
Preferably, in step S13, the device 1 constructs user representation information of the user based on a target application scene of the user representation and the one or more application tag information, wherein the application tag information matching the target application scene in the user representation information is weighted higher than other application tag information in the user representation information.
For example, when the target application scenario is a scenario related to installation of an APP of an investigation user, a relatively large weight may be given to the application installation tag information; when the target application scenario is a scenario for considering the preference of the user APP, a relatively large weight may be given to the application active tag information.
Preferably, the method further comprises: the device 1 provides application information or presentation information matching the user representation information to the user device.
For example, application information or presentation information that matches the user profile information may include application recommendation information, news, merchandise advertisement information, etc. that may be of interest to the user.
Fig. 2 shows a flowchart of a method for determining application tag information of a user according to another embodiment of the present application, the method including step S25, step S26, and step S27.
Specifically, in step S25, the device 2 acquires application usage record information of the application used by the user on the user device; in step S26, the device 2 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information; in step S27, the device 2 determines the application tag information corresponding to the user according to one or more topic keywords in the application topic vector.
Here, the device 2 includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, and the like, which can perform human-computer interaction with a user through a touch panel, and the mobile electronic product may employ any operating system, such as an android operating system, an iOS operating system, and the like. The network device includes an electronic device capable of automatically performing numerical calculation and information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The network device comprises but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud formed by a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device 2 may also be a script program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network. Of course, those skilled in the art will appreciate that the above-described apparatus 2 is merely exemplary, and that other existing or future existing apparatus 2, as may be suitable for use in the present application, are also intended to be encompassed within the scope of the present application and are hereby incorporated by reference.
In step S25, the device 2 acquires application use record information of the application used by the user on the user device.
For example, the application usage record information may include the name or identification information of the application, and information of the number of times of use, the length of time of use per time, the usage consumption flow, and the like, in a period of time (one day, one week, one half month, one month, and the like). Here, the data collection may be performed through an APP installed on the user equipment to acquire the application usage record information, or the application usage record information may be acquired from a third party.
In step S26, the device 2 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information.
Here, the application on the user equipment (i.e. the application currently installed by the user) may be determined according to the application usage record information, and then the application theme vector corresponding to the application theme vector may be obtained. For example, an application topic vector corresponding to a social-class application may be: [ "communication": 0.1, "short message": 0.15, "speech": 0.2, "video": 0.15, "chat": 0.4], an application theme vector for a motion class application may be: [ "basketball": 0.1, "running": 0.2, "calories": 0.2, "weight loss": 0.1, "sport": 0.4], the keywords (such as correspondence, basketball, etc.) are the main labels constituting the application theme, and the weights (such as 0.1, 0.2, etc.) represent the frequency of occurrence of the corresponding keywords in the application theme.
Preferably, in step S26, the device 2 obtains application description information corresponding to the application on the user equipment according to the application usage record information; and generating an application theme vector of the corresponding application according to the application description information, wherein the application theme vector comprises one or more theme keywords.
For example, the application description information may be obtained from a network, such as may be provided by an application market (Google Play, iOS app store, etc.). The application description information contains more information, including more keywords and function descriptions, relative to the category of the application.
More preferably, the generating an application theme vector of a corresponding application according to the application description information includes: performing word segmentation processing on the application description information to obtain a plurality of topic keywords; and performing a clustering algorithm on the plurality of topic keywords, and determining an application topic vector corresponding to application, wherein the application topic vector comprises one or more topic keywords.
For example, the application description information is processed, a sentence is segmented, and stop words without information, punctuation marks, website information, email addresses and the like are removed; and setting the number of topic models, wherein each topic model corresponds to one application topic vector, and clustering the topic models by adopting an LDA (Latent Dirichlet Allocation, an unsupervised machine learning technology and can be used for identifying Latent topic information in a large-scale document set or a corpus) topic model algorithm to obtain model keywords and weight.
Of course, those skilled in the art should understand that the LDA topic model algorithm described above is merely an example, and other existing or hereafter-presented algorithms, such as LSI (Latent Semantic Indexing) algorithms, as applicable to the present application, are also included within the scope of the present application and are hereby incorporated by reference.
In step S27, the device 2 determines the application tag information corresponding to the user according to one or more topic keywords in the application topic vector.
For example, the application tag information corresponding to the user may be determined according to all topic keywords in the application topic vector, or the application tag information corresponding to the user may be determined according to a plurality of preferred (for example, higher-weight) topic keywords in the application topic vector.
Preferably, in step S27, the device 2 determines, according to the application usage record information and one or more topic keywords in the application topic vector, application installation tag information and/or application active tag information corresponding to the user.
Here, the application tag information includes application installation tag information and/or application active tag information. The application installation tag information is determined based on applications installed by a user, and the application active tag information is determined based on the applications installed by the user and the use frequency (the use times in a time period, the use time length of each time, the use consumption flow and the like) of each application.
For example, the process of determining the application installation tag information may include: obtaining the topic key words of each application and the corresponding application topic vectors, selecting a threshold value k, wherein each topic only takes the k key words with the maximum weight, and one topic can be simplified as [ w [, n [ ]1:v1,w1:v1…wk:vk]Wherein w is1…kIs a keyword, v1…kIs the weight of the keyword. Tagging a user according to the keywords of the application, for example, if m applications are installed in one user a, the corresponding tags are m × k tags, and the weight of each tag is the keyword weight [ w [ ]11:v11,…w1k:v1k,w21:v21,…w2k:v2k,…wm1:vm1,…wmk:vmk]Wherein w isijFor the jth keyword, v, of the ith applicationijIs the corresponding weight; when the same keyword appears, the keywords can be combined, and the weights of the two keywords are added to be used as a new weight.
For another example, the process of determining the application active tag information may include: and adding labels to the user and calculating corresponding label weights according to the applied topic keywords and the weights based on the use flow or use times of the user application. Each topic only takes the k keywords with the maximum weight, and if one user B uses m applications in a time period, the corresponding labels have m multiplied by k, and the weight of each label is the weight [ w ] of the keywords11:v11×t1,…w1k:v1k×tk,w21:v21×t2,…w2k:v2k×t2,…wm1:vm1×tm,…wmk:vmk×tm]Wherein w isijFor the jth keyword, v, of the ith applicationijIs the corresponding weight, tiUsing the flow or number of times for the first application; when the same keywords appear, the keywords can be combined, and the weights of the two keywords are multiplied by the corresponding flow and then added to form a new weight.
FIG. 3 shows an apparatus 1 for composing a user representation according to an embodiment of the present application, said apparatus 1 comprising first means 11, second means 12 and third means 13.
Specifically, the first device 11 obtains application usage record information of an application used by a user on user equipment; the second device 12 determines one or more pieces of application tag information corresponding to the user according to the application use record information; the third means 13 constructs user representation information for the user based on the one or more application tag information.
Here, the device 1 includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, and the like, which can perform human-computer interaction with a user through a touch panel, and the mobile electronic product may employ any operating system, such as an android operating system, an iOS operating system, and the like. The network device includes an electronic device capable of automatically performing numerical calculation and information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The network device comprises but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud formed by a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device 1 may also be a script program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network. Of course, those skilled in the art will appreciate that the above-described apparatus 1 is merely exemplary, and that other existing or future existing apparatus 1, as may be suitable for use in the present application, are also intended to be encompassed within the scope of the present application and are hereby incorporated by reference.
The first device 11 obtains application usage record information of an application used by a user on a user equipment.
For example, the application usage record information may include the name or identification information of the application, and information of the number of times of use, the length of time of use per time, the usage consumption flow, and the like, in a period of time (one day, one week, one half month, one month, and the like). Here, the data collection may be performed through an APP installed on the user equipment to acquire the application usage record information, or the application usage record information may be acquired from a third party.
And the second device 12 determines one or more pieces of application tag information corresponding to the user according to the application use record information.
In the mobile user, each user basically uses one user device independently, each user device has a unique identification (such as an imei number or a mac address), and the application use record information can reflect the real characteristics of the user relatively truly. And labeling the users with different characteristics according to the application use record information, and determining one or more pieces of application label information corresponding to the users.
Preferably, the second device 12 queries application library information according to the application usage record information, and determines one or more pieces of application tag information corresponding to the user.
Here, the application library information includes information such as category, description, price, download amount, etc. of an application, which can be obtained from a network, such as an application market (Google Play, iOS app store, etc.) can provide.
Preferably, the application tag information includes at least any one of: applying installation tag information; applying active tag information; installing tag information based on the application of the application theme; application activity tag information based on application topics.
For example, the application installation tag information is determined based on applications installed by a user, and the application active tag information is determined based on the applications installed by the user and the usage frequency (the number of usage times in a time period, the time length of each usage, the usage consumption flow, and the like) of each application. The application installation tag information comprises application installation tag information based on an application theme, and the application activity tag information comprises application activity tag information based on an application theme. The application theme is used to compare specific information that embodies the application in its entirety.
Preferably, the application installation tag information includes at least any one of: application installation tag information based on category, application installation tag information based on price; the application active tag information comprises at least any one of: category-based application activity label information, price-based application activity label information.
For example, according to the application types installed by the user, the number of the application installations of different types is counted, and one or more types of application installation label information corresponding to the user is determined according to the information, and the weight of each application is the same in the process. Suppose that user a has m mobile applications installed on the mobile phone, and belongs to k different categories: category 1, category 2 … category k, the corresponding number of applications being: c1, c2 … ck; then the category-based application installation tag information for user a may be: [ "class 1": c1, "class 2": c2, …, "class k": ck ]; alternatively, the number of applications may also use a normalized value, for example, the weight of the category 1 may be C1/C, where C is C1+ C2+ … + ck, which is the total number of installed applications.
For another example, according to price information of an application installed by a user, one or more pieces of price-based application installation tag information corresponding to the user are determined, and then the installation situation of the user on the paid application is analyzed, so that the attitude and the economic condition of the user on the paid application can be reflected to a certain extent. The price-based application installation tag information for a user may be [ "pay": c1, "free": c2, "pay for use": 0 or 1], wherein, c1 installs the number of free applications for the user, c2 installs the number of paid applications for the user, and the value of the pay label is determined to be 1 or 0 according to whether the user applies the paid applications.
For another example, according to the category/price information of the application used by the user and the corresponding usage frequency (the number of usage times in a time period, the duration of each usage, the usage consumption flow rate, etc.), one or more category/price-based application active label information corresponding to the user is determined, in the process, the weight of each application used by the user is different, and the weight value is proportional to the usage frequency of the application. Assume that user B's category-based application activity tag information may be: [ "category 1": T1, "category 2": T2, …, "category k": tk ], where "category 1" is the category of the application used by the user, and T1 is the usage traffic of the application used by the user for a period of time, where the weight may also be a normalized value T1/T, where T is T1+ T2+ … + tk. Alternatively, the category-based application activity tag information of user B may also be: [ "category 1": n1, "category 2": n2, …, "category k": nk ], where "category 1" is a category corresponding to an application used by a user, and n1 is the number of times the application of the category is used for a period of time, or takes a normalized value. In the process, different time period selections can reflect different application use interests of the user in the time period selections. A time range such as three months, half a year, etc. may be selected to obtain the long term active category label of the user, a time range such as one month, half a month, etc. may be selected to obtain the medium term active category label of the user, and a time range such as one week, one day, two days, etc. may be selected to obtain the short term active category label of the user.
More preferably, the application tag information includes application installation tag information or application active tag information based on an application theme; the second device 12 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information; and determining the application installation tag information or the application active tag information based on the application theme corresponding to the user according to one or more theme key words in the application theme vector.
With the increase of the number of applications and the abundance of application functions, it is more and more difficult for developers to classify the applications, and the specific information of the applications cannot be comprehensively reflected to a certain extent by the category information. Aiming at the possibility that the application category division and the like are inaccurate, large in roughness and small in information amount and one application may have multiple categories, the application installation label information and/or the application active label information based on the application theme are provided, and the application theme is used for comprehensively embodying the specific information of the application. For example, an application topic vector corresponding to a social-class application may be: [ "communication": 0.1, "short message": 0.15, "speech": 0.2, "video": 0.15, "chat": 0.4], an application theme vector for a motion class application may be: [ "basketball": 0.1, "running": 0.2, "calories": 0.2, "weight loss": 0.1, "sport": 0.4], the keywords (such as correspondence, basketball, etc.) are the main labels constituting the application theme, and the weights (such as 0.1, 0.2, etc.) represent the frequency of occurrence of the corresponding keywords in the application theme.
The third means 13 constructs user representation information for the user based on the one or more application tag information.
For example, the user profile information of the user may be constructed based on all application tag information, or may be constructed based on some (e.g., a number of application tag information with weights greater than corresponding thresholds) of the application tag information.
Preferably, the third means 13 constructs user representation information of the user based on a target application scene of the user representation and the one or more application tag information.
For example, the target application scenarios include, but are not limited to: and (4) inspecting the scenes related to the installation of the user APP and inspecting the scenes of the preference of the user APP.
Preferably, the third means 13 constructs user representation information of the user based on a target application scene of the user representation and the one or more application tag information, wherein the user representation information comprises the application tag information matching the target application scene.
For example, if the target application scenario is related to a short-term behavior of a user, the application active tag information in a time range of one week, one day, two days, etc. may be selected; if the target application scene is related to the user middle-term behavior, the application active label information in the time range of one month, half month and the like can be selected; if the target application scenario is associated with a long-term behavior of a user, the application active tag information may be selected within a time range such as three months, half a year, and the like. That is, the selected application tag information should match the target scene.
Preferably, the third means 13 constructs user representation information of the user based on a target application scene of the user representation and the one or more application tag information, wherein the application tag information matching the target application scene in the user representation information is weighted higher than other application tag information in the user representation information.
For example, when the target application scenario is a scenario related to installation of an APP of an investigation user, a relatively large weight may be given to the application installation tag information; when the target application scenario is a scenario for considering the preference of the user APP, a relatively large weight may be given to the application active tag information.
Preferably, the apparatus 1 further comprises fourth means (not shown in the figures); the fourth device provides the application information or the presentation information matched with the user portrait information to the user equipment.
For example, application information or presentation information that matches the user profile information may include application recommendation information, news, merchandise advertisement information, etc. that may be of interest to the user.
Fig. 4 shows an apparatus 2 for determining application tag information of a user according to another embodiment of the present application, said apparatus 2 comprising fifth means 25, sixth means 26 and seventh means 27.
Specifically, the fifth device 25 obtains application usage record information of the application used by the user on the user equipment; the sixth device 26 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information; the seventh device 27 determines the application tag information corresponding to the user according to one or more topic keywords in the application topic vector.
Here, the device 2 includes, but is not limited to, a user device, a network device, or a device formed by integrating a user device and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product, such as a smart phone, a tablet computer, and the like, which can perform human-computer interaction with a user through a touch panel, and the mobile electronic product may employ any operating system, such as an android operating system, an iOS operating system, and the like. The network device includes an electronic device capable of automatically performing numerical calculation and information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The network device comprises but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud formed by a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device 2 may also be a script program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network. Of course, those skilled in the art will appreciate that the above-described apparatus 2 is merely exemplary, and that other existing or future existing apparatus 2, as may be suitable for use in the present application, are also intended to be encompassed within the scope of the present application and are hereby incorporated by reference.
The fifth means 25 obtains application usage record information of the application used by the user on the user equipment.
For example, the application usage record information may include the name or identification information of the application, and information of the number of times of use, the length of time of use per time, the usage consumption flow, and the like, in a period of time (one day, one week, one half month, one month, and the like). Here, the data collection may be performed through an APP installed on the user equipment to acquire the application usage record information, or the application usage record information may be acquired from a third party.
The sixth means 26 obtains an application theme vector corresponding to the application on the user equipment according to the application usage record information.
Here, the application on the user equipment (i.e. the application currently installed by the user) may be determined according to the application usage record information, and then the application theme vector corresponding to the application theme vector may be obtained. For example, an application topic vector corresponding to a social-class application may be: [ "communication": 0.1, "short message": 0.15, "speech": 0.2, "video": 0.15, "chat": 0.4], an application theme vector for a motion class application may be: [ "basketball": 0.1, "running": 0.2, "calories": 0.2, "weight loss": 0.1, "sport": 0.4], the keywords (such as correspondence, basketball, etc.) are the main labels constituting the application theme, and the weights (such as 0.1, 0.2, etc.) represent the frequency of occurrence of the corresponding keywords in the application theme.
Preferably, the sixth device 26 obtains the application description information corresponding to the application on the user equipment according to the application usage record information; and generating an application theme vector of the corresponding application according to the application description information, wherein the application theme vector comprises one or more theme keywords.
For example, the application description information may be obtained from a network, such as may be provided by an application market (Google Play, iOS app store, etc.). The application description information contains more information, including more keywords and function descriptions, relative to the category of the application.
More preferably, the generating an application theme vector of a corresponding application according to the application description information includes: performing word segmentation processing on the application description information to obtain a plurality of topic keywords; and performing a clustering algorithm on the plurality of topic keywords, and determining an application topic vector corresponding to application, wherein the application topic vector comprises one or more topic keywords.
For example, the application description information is processed, a sentence is segmented, and stop words without information, punctuation marks, website information, email addresses and the like are removed; and setting the number of topic models, wherein each topic model corresponds to one application topic vector, and clustering the topic models by adopting an LDA (Latent Dirichlet Allocation, an unsupervised machine learning technology and can be used for identifying Latent topic information in a large-scale document set or a corpus) topic model algorithm to obtain model keywords and weight.
Of course, those skilled in the art should understand that the LDA topic model algorithm described above is merely an example, and other existing or hereafter-presented algorithms, such as LSI (Latent Semantic Indexing) algorithms, as applicable to the present application, are also included within the scope of the present application and are hereby incorporated by reference.
The seventh device 27 determines the application tag information corresponding to the user according to one or more topic keywords in the application topic vector.
For example, the application tag information corresponding to the user may be determined according to all topic keywords in the application topic vector, or the application tag information corresponding to the user may be determined according to a plurality of preferred (for example, higher-weight) topic keywords in the application topic vector.
Preferably, the seventh device 27 determines the application installation tag information and/or the application active tag information corresponding to the user according to the application usage record information and one or more topic keywords in the application topic vector.
Here, the application tag information includes application installation tag information and/or application active tag information. The application installation tag information is determined based on applications installed by a user, and the application active tag information is determined based on the applications installed by the user and the use frequency (the use times in a time period, the use time length of each time, the use consumption flow and the like) of each application.
For example, the process of determining the application installation tag information may include: obtaining the topic key words of each application and the corresponding application topic vectors, selecting a threshold value k, wherein each topic only takes the k key words with the maximum weight, and one topic can be simplified as [ w [, n [ ]1:v1,w1:v1…wk:vk]Wherein w is1…kIs a keyword, v1…kIs the weight of the keyword. Tagging a user according to the keywords of the application, for example, if m applications are installed in one user a, the corresponding tags are m × k tags, and the weight of each tag is the keyword weight [ w [ ]11:v11,…w1k:v1k,w21:v21,…w2k:v2k,…wm1:vm1,…wmk:vmk]Wherein w isijFor the jth keyword, v, of the ith applicationijIs the corresponding weight; when the same keyword appears, the keywords can be combined, and the weights of the two keywords are added to be used as a new weight.
For another example, the process of determining the application active tag information may include: and adding labels to the user and calculating corresponding label weights according to the applied topic keywords and the weights based on the use flow or use times of the user application. Each topic only takes the k keywords with the maximum weight, and if one user B uses m applications in a time period, the corresponding labels have m multiplied by k, and the weight of each label is the weight [ w ] of the keywords11:v11×t1,…w1k:v1k×tk,w21:v21×t2,…w2k:v2k×t2,…wm1:vm1×tm,…wmk:vmk×tm]Wherein w isijFor the jth keyword, v, of the ith applicationijIs the corresponding weight, tiUsing the flow or number of times for the first application; when the same keyword appears, the keywords can be combined, and the weights of the two keywordsMultiplied by the corresponding flow rate and added as a new weight.
According to yet another aspect of the present application, there is provided a computer-readable storage medium comprising instructions that, when executed, cause a system to:
acquiring application use record information of an application used by a user on user equipment;
determining one or more pieces of application label information corresponding to the user according to the application use record information;
constructing user representation information for the user based on the one or more application tag information.
According to yet another aspect of the present application, there is provided a computer-readable storage medium comprising instructions that, when executed, cause a system to:
acquiring application use record information of an application used by a user on user equipment;
acquiring an application theme vector corresponding to the application on the user equipment according to the application use record information;
and determining the application label information corresponding to the user according to one or more topic keywords in the application topic vector.
According to yet another aspect of the application, there is provided an apparatus for constructing a user representation, wherein the apparatus comprises:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring application use record information of an application used by a user on user equipment;
determining one or more pieces of application label information corresponding to the user according to the application use record information;
constructing user representation information for the user based on the one or more application tag information.
According to still another aspect of the present application, there is provided an apparatus for determining application tag information of a user, wherein the apparatus includes:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to:
acquiring application use record information of an application used by a user on user equipment;
acquiring an application theme vector corresponding to the application on the user equipment according to the application use record information;
and determining the application label information corresponding to the user according to one or more topic keywords in the application topic vector.
Compared with the prior art, the method and the device have the advantages that application use record information of the application used by the user on the user equipment is obtained, one or more pieces of application label information corresponding to the user are determined according to the application use record information, and then the user portrait information of the user is constructed based on the one or more pieces of application label information; the application uses the user information such as record information for user's web browsing record, social network relation, news advertisement click record, has static stability, the data volume is little, the information volume is big advantage, therefore, the user portrait information that this application founds can more accurately define and discern the user. Further, the application label information comprises application installation label information and/or application active label information, and the user is labeled from different dimensions, so that more accurate user portrait information is constructed. Further, the application installation label information and/or the application activity label information based on the application theme are provided, richer differentiation label information is obtained, and the applications can be better classified.
It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Program instructions which invoke the methods of the present application may be stored on a fixed or removable recording medium and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored within a working memory of a computer device operating in accordance with the program instructions. An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or a solution according to the aforementioned embodiments of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (22)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611186477.9A CN106940705B (en) | 2016-12-20 | 2016-12-20 | A method and device for constructing user portraits |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611186477.9A CN106940705B (en) | 2016-12-20 | 2016-12-20 | A method and device for constructing user portraits |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106940705A CN106940705A (en) | 2017-07-11 |
| CN106940705B true CN106940705B (en) | 2021-01-22 |
Family
ID=59468580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611186477.9A Active CN106940705B (en) | 2016-12-20 | 2016-12-20 | A method and device for constructing user portraits |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106940705B (en) |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389138A (en) * | 2017-08-09 | 2019-02-26 | 武汉安天信息技术有限责任公司 | A kind of user's portrait method and device |
| CN107563851A (en) * | 2017-08-23 | 2018-01-09 | 广东欧珀移动通信有限公司 | Application recommended method, device, terminal and storage medium |
| CN107688639A (en) * | 2017-08-24 | 2018-02-13 | 努比亚技术有限公司 | Using recommendation method, server and computer-readable recording medium |
| CN107578292B (en) * | 2017-09-19 | 2020-10-16 | 上海财经大学 | User portrait construction system |
| CN107870986A (en) * | 2017-10-13 | 2018-04-03 | 平安科技（深圳）有限公司 | User behavior analysis method, application server and computer-readable recording medium based on reptile data |
| CN107705156B (en) * | 2017-10-16 | 2021-02-05 | 深圳大宇无限科技有限公司 | User feature analysis method and device |
| CN110019759A (en) * | 2017-10-27 | 2019-07-16 | 腾讯科技（深圳）有限公司 | Tenant group processing method, device, computer equipment and storage medium |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| CN107729560A (en) * | 2017-11-08 | 2018-02-23 | 北京奇虎科技有限公司 | User's portrait building method, device and computing device based on big data |
| CN108388572A (en) * | 2018-01-10 | 2018-08-10 | 链家网（北京）科技有限公司 | A method for fetching user portraits |
| CN108230114B (en) * | 2018-01-16 | 2021-04-23 | 平安好房（上海）电子商务有限公司 | Method, device, device and readable storage medium for selecting user feature tag |
| CN109359180B (en) * | 2018-09-20 | 2021-03-02 | 腾讯科技（深圳）有限公司 | User portrait generation method and device, electronic equipment and computer readable medium |
| CN109767300B (en) * | 2019-01-14 | 2022-02-15 | 博拉网络股份有限公司 | Big data portrait and model construction method based on user habits |
| CN110175264A (en) * | 2019-04-23 | 2019-08-27 | 深圳市傲天科技股份有限公司 | Construction method, server and the computer readable storage medium of video user portrait |
| CN113396433B (en) * | 2019-06-11 | 2023-12-26 | 深圳市欢太科技有限公司 | User portrait construction method and related products |
| CN112116368A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for labeling equipment recommending contents to crowd and processor |
| CN110457679B (en) * | 2019-07-01 | 2023-11-28 | 深圳追一科技有限公司 | User portrait construction method, device, computer equipment and storage medium |
| CN110674144A (en) * | 2019-08-14 | 2020-01-10 | 深圳壹账通智能科技有限公司 | User portrait generation method and device, computer equipment and storage medium |
| CN113051465A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Push method and device for optimization strategy, server and storage medium |
| CN113050782B (en) * | 2019-12-27 | 2023-02-28 | Oppo广东移动通信有限公司 | Portrait construction method, apparatus, terminal and storage medium |
| CN111079023B (en) * | 2019-12-30 | 2023-06-16 | Oppo广东移动通信有限公司 | Target account identification method, device, terminal and storage medium |
| CN111310009A (en) * | 2020-01-16 | 2020-06-19 | 珠海格力电器股份有限公司 | User classification method and device, storage medium and computer equipment |
| CN111260220B (en) * | 2020-01-16 | 2021-05-14 | 北京房江湖科技有限公司 | Group control equipment identification method and device, electronic equipment and storage medium |
| CN112035519B (en) * | 2020-08-28 | 2023-11-24 | 中国平安人寿保险股份有限公司 | User image drawing method, device, computer readable storage medium and terminal equipment |
| CN114546794A (en) * | 2020-11-27 | 2022-05-27 | 中国移动通信集团终端有限公司 | Application coverage rate determination method, device, equipment and storage medium |
| CN112948526A (en) * | 2021-02-01 | 2021-06-11 | 大箴(杭州)科技有限公司 | User portrait generation method and device, electronic equipment and storage medium |
| CN113157540A (en) * | 2021-03-31 | 2021-07-23 | 国家计算机网络与信息安全管理中心 | User behavior analysis method and system |
| CN114943562A (en) * | 2022-06-08 | 2022-08-26 | 中国银行股份有限公司 | A method and related device for pushing bank coupons |
| CN115061700A (en) * | 2022-06-30 | 2022-09-16 | 上海掌门科技有限公司 | Method, apparatus, medium, and program product for determining user portrait tag information |
| CN116484109B (en) * | 2023-06-21 | 2023-09-01 | 九一金融信息服务(北京)有限公司 | Customer portrait analysis system and method based on artificial intelligence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102884822A (en) * | 2010-05-11 | 2013-01-16 | 诺基亚公司 | Method and apparatus for determining user context |
| CN103530339A (en) * | 2013-10-08 | 2014-01-22 | 北京百度网讯科技有限公司 | Mobile application information push method and device |
| CN103927309A (en) * | 2013-01-14 | 2014-07-16 | 阿里巴巴集团控股有限公司 | Method and device for marking information labels for business objects |
| CN104133878A (en) * | 2014-07-25 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | User label generation method and device |
| CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
-
2016
- 2016-12-20 CN CN201611186477.9A patent/CN106940705B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102884822A (en) * | 2010-05-11 | 2013-01-16 | 诺基亚公司 | Method and apparatus for determining user context |
| CN103927309A (en) * | 2013-01-14 | 2014-07-16 | 阿里巴巴集团控股有限公司 | Method and device for marking information labels for business objects |
| CN103530339A (en) * | 2013-10-08 | 2014-01-22 | 北京百度网讯科技有限公司 | Mobile application information push method and device |
| CN104133878A (en) * | 2014-07-25 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | User label generation method and device |
| CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106940705A (en) | 2017-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106940705B (en) | A method and device for constructing user portraits | |
| US11269962B2 (en) | Inductive matrix completion and graph proximity for content item recommendation | |
| US10747771B2 (en) | Method and apparatus for determining hot event | |
| WO2018192496A1 (en) | Trend information generation method and device, storage medium and electronic device | |
| CN104899220B (en) | Application program recommendation method and system | |
| US12141212B2 (en) | Intelligent interface accelerating | |
| WO2019149145A1 (en) | Compliant report class sorting method and apparatus | |
| WO2019169978A1 (en) | Resource recommendation method and device | |
| US20150302012A1 (en) | Generating suggested search queries | |
| US11275748B2 (en) | Influence score of a social media domain | |
| CN110851710A (en) | Novel recommendation method and device | |
| US20210209624A1 (en) | Online platform for predicting consumer interest level | |
| US9767417B1 (en) | Category predictions for user behavior | |
| US10346496B2 (en) | Information category obtaining method and apparatus | |
| US10902009B1 (en) | Machine learning system and method to map keywords and records into an embedding space | |
| US20170228378A1 (en) | Extracting topics from customer review search queries | |
| US12261882B2 (en) | Identifying fraudulent requests for content | |
| CN110674404A (en) | Link information generation method, device, system, storage medium and electronic equipment | |
| US12255903B2 (en) | Identifying fraudulent requests for content | |
| CN113010795A (en) | User dynamic portrait generation method, system, storage medium and electronic device | |
| US9201967B1 (en) | Rule based product classification | |
| US20200104408A1 (en) | Determining user lookalikes in a database system | |
| US10339559B2 (en) | Associating social comments with individual assets used in a campaign | |
| US12147503B2 (en) | Debiasing training data based upon information seeking behaviors | |
| US11615245B2 (en) | Article topic alignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 80536, Shanghai Patentee after: Shanghai Zongzhang Technology Group Co.,Ltd. Country or region after: China Address before: Room 80536, Shanghai Patentee before: SHANGHAI ZHANGMEN SCIENCE AND TECHNOLOGY Co.,Ltd. Country or region before: China |