CN105005587A - User portrait updating method, apparatus and system - Google Patents
User portrait updating method, apparatus and system Download PDFInfo
- Publication number
- CN105005587A CN105005587A CN201510362402.0A CN201510362402A CN105005587A CN 105005587 A CN105005587 A CN 105005587A CN 201510362402 A CN201510362402 A CN 201510362402A CN 105005587 A CN105005587 A CN 105005587A
- Authority
- CN
- China
- Prior art keywords
- user
- interest tag
- interest
- tag
- updating
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000002238 attenuated effect Effects 0.000 claims description 31
- 230000000694 effects Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 7
- 230000006399 behavior Effects 0.000 description 139
- 238000005562 fading Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003796 beauty Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation 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
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/1734—Details of monitoring file system events, e.g. by the use of hooks, filter drivers, logs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/1737—Details of further file system functions for reducing power consumption or coping with limited storage space, e.g. in mobile devices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An embodiment of the invention discloses a user portrait updating method, apparatus and system. According to the embodiment of the invention, the method comprises the steps of: obtaining a current user behavior log; obtaining a corresponding first interest label according to interest identifiers carried in the user behavior log; determining the user behavior type according to the user behavior log; obtaining a user portrait updated most recently according to the interest identifiers in the user behavior log; and updating the user portrait according to the first interest label, the behavior type and a second interest label carried in the user portrait. According to the technical scheme, the user portrait can be updated in real time, the consumption of stored resources can be reduced, the calculated amount is reduced, and the processing efficiency is improved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method, a device and a system for updating a user portrait.
Background
User portrayal, also called user role (Persona), is an effective tool for delineating target users and connecting user appeal and design direction, and is widely applied in various fields. For example, in particular implementations, the user representation may be a set of tags (tags) used to characterize the user, such as basic attributes including age, gender, and/or academic calendar, as well as interest features of the user, such as dress and/or dress. The determination and updating of the user representation is of great significance for the targeted dissemination of subsequent information, such as targeted delivery of advertisements.
The existing user portrait is updated mainly by means of off-line calculation, for example, a user behavior log can be stored, then, in a certain time window, all the user behavior logs are traversed, and the user behavior logs are calculated according to a certain time weight decay function, so that the current latest user portrait can be obtained. The size of the time window needs to be determined in advance, the reference standard mainly depends on manual experience and some statistical results, for example, the size of the time window is generally set to be more than one week.
In the process of research and practice of the prior art, the inventor of the present invention finds that, because the prior art needs to keep the user behavior logs in a longer time range, more storage resources are needed, and because all the user behavior logs need to be traversed and calculated in batches each time the user portrait is updated, the calculation amount is also large, which results in low processing efficiency and untimely update.
Disclosure of Invention
The embodiment of the invention provides a method, a device and a system for updating a user portrait, which can reduce the consumption of storage resources, reduce the calculation amount and improve the processing efficiency while realizing timely updating.
The embodiment of the invention provides a user portrait updating method, which comprises the following steps:
acquiring a current user behavior log, wherein the user behavior log carries a user identifier and an interest identifier;
acquiring a corresponding first interest tag according to the interest identifier;
determining the behavior type of the user according to the user behavior log;
obtaining a user portrait updated by the user last time according to the user identification, wherein the user portrait comprises at least one second interest tag;
and updating the user portrait according to the first interest tag, the behavior type and the second interest tag.
Correspondingly, the embodiment of the invention also provides a user portrait updating device, which comprises:
the log obtaining unit is used for obtaining a current user behavior log, and the user behavior log carries a user identifier and an interest identifier;
the tag obtaining unit is used for obtaining a corresponding first interest tag according to the interest identifier;
the determining unit is used for determining the behavior type of the user according to the user behavior log;
the portrait acquisition unit is used for acquiring a user portrait which is updated last time by a user according to the user identification, wherein the user portrait comprises at least one second interest tag;
and the updating unit is used for updating the user portrait according to the first interest tag, the behavior type and the second interest tag.
In addition, the embodiment of the invention also provides a user portrait updating system which comprises any user portrait updating device provided by the embodiment of the invention.
The method comprises the steps of obtaining a current user behavior log, determining the latest interest tag, namely a first interest tag, of a user according to the user behavior log, determining the behavior type of the user, obtaining a user portrait updated by the user last time, obtaining a previous interest tag, namely a second interest tag, of the user, and then updating the user portrait based on the first interest tag, the behavior type and the second interest tag; because the scheme can take into account the past interest and the current interest of the user when the user portrait is updated every time, the problem that the updating is not timely due to too long updating interval in the prior art can be solved, the risk that only the current interest is used as the user portrait in the prior art can be solved, and the updating effect is improved while the user portrait is updated in time; in addition, because the scheme adopts an incremental calculation mode (namely, a user portrait updated by a user last time is taken as a reference standard) during updating, the storage space and the calculation resources can be reduced to a great extent, and the processing efficiency is greatly improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1a is a schematic view of a scenario of a method for updating a user portrait according to an embodiment of the present invention;
FIG. 1b is a flowchart of a method for updating a user representation according to an embodiment of the present invention;
FIG. 2 is another flow chart of a method for updating a user representation according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an apparatus for updating a user portrait according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method, a device and a system for updating a user portrait.
Referring to FIG. 1a, the user representation updating system may include a server, which may integrate any one of the user representation updating apparatuses provided by the embodiments of the present invention; the user representation updating system may further comprise other devices, such as a user terminal.
The server may obtain a current user behavior log in real time from the user terminal, where the user behavior log may carry information such as a user identifier and an interest identifier, then obtain a latest interest tag, i.e., a first interest tag, of a user according to the interest identifier, determine a behavior type of the user according to the user behavior log, obtain a user portrait of the user updated most recently according to the user identifier, then update the user portrait according to the first interest tag, the behavior type, and a past interest tag (i.e., a second interest tag) carried in the user portrait, for example, perform attenuation calculation on the second interest tag to obtain an attenuated second interest tag, perform weighting calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag, and then, and adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait, and the like.
The details will be described below separately.
The first embodiment,
The present embodiment will be described from the perspective of a user representation updating apparatus, which may be specifically integrated in a server or the like.
A method of updating a user representation, comprising: acquiring a current user behavior log, wherein the user behavior log carries a user identifier and an interest identifier; acquiring a corresponding first interest tag according to the interest identifier; determining the behavior type of the user according to the user behavior log; acquiring a user portrait updated by the user last time according to the user identification; the user representation is updated based on the first interest tag, the behavior type, and a second interest tag carried in the user representation.
As shown in FIG. 1b, the specific flow of the method for updating a user portrait may be as follows:
101. and acquiring a current user behavior log.
For example, the user behavior log may be actively obtained from the terminal, for example, when it is determined that the user behavior log is updated, the current user behavior log is obtained from the terminal; alternatively, the user behavior log may be passively received, such as when the user behavior log is updated, the receiving terminal reports the current user behavior log, and so on.
The user behavior log can carry information such as user identification, interest identification and the like; the user identifier refers to an identifier that can be used to identify the user identity, and may include, for example, a user name, a user account number, and/or a mailbox address of the user; the interest identifier refers to an identifier that can be used to identify an interest tag, and may also be referred to as an item identifier (item ID, item Identification), such as a name of the interest tag, or a number or a code number of the interest tag, and so on. The interest tag is also referred to as "tag" description of item ID, and refers to an abstract description of "item", for example, tag may be category information of item in e-commerce, tag may be type information of item in video, tag may be a keyword obtained by performing word segmentation extraction on news name and abstract in news, and so on.
102. And acquiring a corresponding first interest tag according to the interest identifier.
For example, an interest identifier may be specifically extracted from a user behavior log, and then a corresponding interest tag is obtained according to the interest identifier.
Because the first interest tag is obtained according to the current latest user behavior log, the current latest interest of the user can be reflected to a certain extent by the first interest tag.
103. And determining the behavior type of the user according to the user behavior log.
For example, what kind of behavior the user performs may be determined from the content in the user behavior log, such as if browsing, its behavior type may be determined as "browsing behavior", if purchasing, its behavior type may be determined as "purchasing behavior", and so on.
The types of the behavior types can be set according to the requirements of practical application, and are not described herein again.
104. And acquiring a user portrait updated by the user last time according to the user identification, wherein the user portrait comprises at least one interest tag, and for convenience of description, in the embodiment of the invention, the interest tag carried by the user portrait is called a second interest tag.
Since the second interest tag is carried in the previous user image of the user, the second interest tag can reflect the past interest of the user to a certain extent.
105. The user representation is updated based on the first interest tag, the behavior type, and the second interest tag. For example, the following may be specifically mentioned:
(1) performing attenuation calculation on the second interest tag to obtain an attenuated second interest tag;
for example, the updating time of the latest user portrait and the current time may be determined, a time interval between the updating time of the latest user portrait and the current time may be calculated, a decay factor may be determined according to the time interval, then, the weight of the second interest tag may be determined, and the weight of the second interest tag may be multiplied by the decay factor to obtain the second interest tag after decay.
It can be seen that the attenuation factor is a function of the time interval, the specific form may be determined according to the service, and the general principle is that the larger the time interval is, the stronger the attenuation factor is; the smaller the spacing, the weaker the attenuation factor. For convenience of subsequent calculation, the attenuation factor can be reduced to a decimal number between [0 and 1 ].
By the attenuation factor, the degree of interest attenuation of the user can be reflected, and the degree of interest attenuation refers to that the interest labels obtained based on the user behaviors are weakened along with the time. For example, 10 days ago the user watched a horror movie, at which time the user was tagged with a "horror" label. In the last 10 days, the user has no any watching action on the 'horror' movie, the interest of the user on the 'horror movie' should be attenuated, and the attenuation degree can be expressed by an attenuation factor.
The weight of the second interest tag may be preset according to the requirements of the actual application, for example, the weight of "beauty" may be set to 0.1, and the weight of "reading" may be set to 0.4, and so on.
(2) And performing weighted calculation on the first interest tag according to the behavior type to obtain the weighted first interest tag.
For example, the first interest label may be obtained by calculating a behavior weight according to the behavior type, determining a weight of the first interest label, and multiplying the weight of the first interest label by the corresponding behavior weight.
The behavior weight is different according to the behavior type, and may specifically depend on the requirement of the actual application, for example, the weight of the purchasing behavior may be set to be higher than that of the browsing behavior, and so on.
Similarly, the weight of the first interest tag may be preset according to the requirement of the actual application, for example, the weight of "movie" may be set to 0.2, and the weight of "music" may be set to 0.1, and so on.
(3) And adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait.
The preset update ratio may be calculated according to the service, and the general principle is that the larger the time interval is, the smaller the ratio is, for example, the ratio may be represented by "1-attenuation factor". The step of adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait may specifically be as follows:
calculating a difference value of 1 minus the attenuation factor, and taking the difference value as a first proportion; and adding the weighted first interest tag into the attenuated second interest tag according to the first proportion to obtain an updated user portrait.
As can be seen from the above, in the embodiment, the current user behavior log is obtained, the latest interest tag, i.e., the first interest tag, of the user is determined according to the user behavior log, the behavior type of the user is determined, the user portrait updated by the user last time is obtained, so as to obtain the previous interest tag, i.e., the second interest tag, of the user, and then the user portrait is updated based on the first interest tag, the behavior type, and the second interest tag; because the scheme can take into account the past interest and the current interest of the user when the user portrait is updated every time, the problem that the updating is not timely due to too long updating interval in the prior art can be solved, the risk that only the current interest is used as the user portrait in the prior art can be solved, and the updating effect is improved while the user portrait is updated in time; in addition, because the scheme adopts an incremental calculation mode (namely, a user portrait updated by a user last time is taken as a reference standard) during updating, the storage space and the calculation resources can be reduced to a great extent, and the processing efficiency is greatly improved.
Example II,
The method described in the first embodiment is further illustrated by way of example.
In this embodiment, an example will be described in which an updating apparatus for a user image is specifically integrated in a server.
As shown in fig. 2, a specific process of the method for updating a user portrait may be as follows:
201. the server acquires a current user behavior log, wherein the user behavior log can carry information such as user identification and interest identification.
For example, when it is determined that the user behavior log is updated, the current user behavior log may be obtained from the terminal; or, the receiving terminal reports the current user behavior log when the user behavior log is updated, and the like.
The user identifier may include a user name, a user account and/or a mailbox address of the user; the interest identifier may be a name of the interest tag, or may also be a number or code number of the interest tag, etc.
202. And the server acquires the first interest tag according to the interest identifier.
For example, if the interest label is set as the name of the interest label, for example, the interest label corresponding to the interest label "movie" is "movie", the interest label corresponding to the interest label "music" is "music", the interest label corresponding to the interest label "reading" is "reading", the interest label corresponding to the interest label "cartoon" is "cartoon", and so on. Then:
if the interest identifications carried in the user behavior log are cartoon and music, the server can acquire corresponding first interest labels, namely cartoon and music, so that the latest current interest of the user is cartoon and music, and the like.
203. And the server determines the behavior type of the user according to the user behavior log.
For example, what kind of behavior the user performs may be determined from the content in the user behavior log, such as if browsing, its behavior type may be determined as "browsing behavior", if purchasing, its behavior type may be determined as "purchasing behavior", and so on.
For example, taking "cartoon" as an example, if the user purchases "X sunshine shortage", the behavior type of the user behavior corresponding to the first interest tag "cartoon" may be determined as "purchase". And if the user just reads the night tomb pen X and the Huatian XX history, the behavior type of the user behavior corresponding to the first interest tag cartoon can be determined as reading, and so on.
The types of the behavior types can be set according to the requirements of practical application, and are not described herein again.
204. The server obtains a user portrait updated by the user last time according to the user identification, wherein the user portrait comprises at least one second interest tag.
Since the second interest tag is carried in the previous user image of the user, the second interest tag may reflect the past interest of the user to some extent, for example, taking the second interest tag as "movie" and "cartoon" as examples, the previous interest of the user in the movie and the cartoon may be reflected to some extent, and so on.
The steps 202, 203 and 204 may not be executed sequentially.
205. And the server performs attenuation calculation on the second interest label to obtain the attenuated second interest label.
For example, the update time of the latest user portrait and the current time may be determined, a time interval between the update time of the latest user portrait and the current time may be calculated, a decay factor may be determined according to the time interval, then, the weight of the second interest tag may be determined, and the weight of the second interest tag may be multiplied by the decay factor to obtain a second interest tag after decay.
The attenuation factor is a function of the time interval, the specific form can be determined according to the service, and the general principle is that the larger the time interval is, the stronger the attenuation factor is; the smaller the spacing, the weaker the attenuation factor. For convenience of subsequent calculation, the attenuation factor can be reduced to a decimal number between [0 and 1 ].
For example, if the calculation shows that the attenuation factor is "0.3", and the weight of the second interest tag, such as "movie" is "10000", the weight of the attenuated second interest tag "movie" can be "3000".
For another example, if the calculation finds that the attenuation factor is "0.3", and the weight of the second interest tag, such as "cartoon", is "20000", it can be found that the weight of the attenuated second interest tag "cartoon" is "6000", and so on.
It should be noted that, in the embodiment of the present invention, the attenuated second interest tag refers to the weight of the attenuated second interest tag.
206. And the server performs weighted calculation on the first interest tag according to the behavior type to obtain the weighted first interest tag.
For example, a behavior weight may be calculated according to the behavior type, and then, a weight of the first interest tag is determined, and the weight of the first interest tag is multiplied by the corresponding behavior weight, so as to obtain a weighted first interest tag.
For example, if it is calculated that the weight of the behavior with the behavior type "purchase" is "0.2" and the weight of the first interest tag "caricature" is determined to be "20000", it can be obtained that the weight of the weighted first interest tag "caricature" is "4000".
For another example, if it is calculated that the weight of the behavior with the behavior type "download" is "0.3" and the weight of the first interest tag "music" is determined to be "30000", it can be obtained that the weight of the weighted first interest tag "music" is "9000".
The behavior weight is different according to the behavior type, and may specifically depend on the requirement of the actual application, for example, the weight of the purchasing behavior may be set to be higher than that of the browsing behavior, and so on.
It should be noted that, in the embodiment of the present invention, the weighted first interest tag refers to a weighted weight of the first interest tag.
207. And the server adds the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait.
The preset update ratio may be calculated according to the service, and the general principle is that the larger the time interval is, the smaller the ratio is, for example, the ratio may be represented by "1-attenuation factor", for example, if the attenuation factor is calculated to be "0.3" in step 205, the ratio may be determined to be "0.7".
For example, taking this ratio as "0.7" as an example, if in the previous step:
the weight of the second interest tag "movie" after decay is "3000";
the weight of the second interest tag "caricature" after attenuation is "6000";
the weighted first interest tag cartoon has a weight of 4000;
the weighted first interest tag "music" is weighted by "9000".
The weight of the latest interest tag may be calculated using "weight of interest tag in updated user representation — weighted first interest tag 0.7+ attenuated second interest tag" as follows:
the weight of the interest tag "movie" may be updated as: 0 x 0.7+3000 ═ 3000;
the weight of the interest tag "caricature" may be updated as: 4000 x 0.7+6000 ═ 8800;
the weight of the interest tag "music" may be updated as: 9000 × 0.7+0 ═ 6300.
Since the tag "movie" does not exist in the first interest tag, the weight of the first interest tag "movie" after weighting is 0, and similarly, since the tag "music" does not exist in the second interest tag after fading, it indicates that the interest tag is newly added and does not exist in the past, and the weight of the second interest tag "music" after fading is 0.
Thus, it may be appreciated that the interest tags in the updated user image may include "movies," "caricatures," and "music," where "movies" have a weight of 3000, "caricatures" have a weight of 8800, and "music" have a weight of 6300.
As can be seen from the above, in the embodiment, the current user behavior log is obtained, the latest interest tag, i.e., the first interest tag, of the user is determined according to the user behavior log, the behavior type of the user is determined, the user portrait updated by the user last time is obtained, so as to obtain the previous interest tag, i.e., the second interest tag, of the user, and then the user portrait is updated based on the first interest tag, the behavior type, and the second interest tag; because the scheme can take into account the past interest and the current interest of the user when the user portrait is updated every time, the problem that the updating is not timely due to too long updating interval in the prior art can be solved, the risk that only the current interest is used as the user portrait in the prior art can be solved, and the updating effect is improved while the user portrait is updated in time; in addition, because the scheme adopts an incremental calculation mode (namely, a user portrait updated by a user last time is taken as a reference standard) during updating, the storage space and the calculation resources can be reduced to a great extent, and the processing efficiency is greatly improved.
Example III,
In order to better implement the above method, an embodiment of the present invention further provides a user portrait updating apparatus, as shown in fig. 3, which may include a log acquiring unit 301, a tag acquiring unit 302, a determining unit 303, a portrait acquiring unit 304, and an updating unit 305, as follows:
a log obtaining unit 301, configured to obtain a current user behavior log.
For example, the log obtaining unit 301 may actively obtain the user behavior log from the terminal, for example, when it is determined that the user behavior log is updated, obtain the current user behavior log from the terminal; alternatively, the log obtaining unit 301 may also passively receive the user behavior log, such as a current user behavior log reported by the receiving terminal when the user behavior log is updated, and so on.
The user behavior log can carry information such as user identification, interest identification and the like; the user identification may include a user name, a user account and/or a mailbox address of the user; the interest identifier may be a name of the interest tag, or may also be a number or code number of the interest tag, etc.
A tag obtaining unit 302, configured to obtain a corresponding first interest tag according to the interest identifier.
For example, the tag obtaining unit 302 may specifically extract an interest identifier from the user behavior log, and then obtain a corresponding first interest tag according to the interest identifier.
Because the first interest tag is obtained according to the current latest user behavior log, the current latest interest of the user can be reflected to a certain extent by the first interest tag.
A determining unit 303, configured to determine a behavior type of the user according to the user behavior log.
For example, what kind of behavior the user performs may be determined from the content in the user behavior log, such as if browsing, its behavior type may be determined as "browsing behavior", if purchasing, its behavior type may be determined as "purchasing behavior", and so on.
The types of the behavior types can be set according to the requirements of practical application, and are not described herein again.
A representation obtaining unit 304, configured to obtain a user representation that is updated last time by the user according to the user identifier, where the user representation includes at least one second interest tag.
Since the second interest tag is carried in the previous user image of the user, the second interest tag can reflect the past interest of the user to a certain extent.
An update unit 305 for updating the user representation according to the first interest tag, the behavior type and the second interest tag.
For example, the update unit 305 may include an attenuation subunit, a weighting subunit, and an update subunit, as follows:
(1) an attenuator subunit;
and the attenuation subunit is used for performing attenuation calculation on the second interest tag to obtain the attenuated second interest tag.
The attenuation calculation may be performed in various ways, for example, as follows:
the decay subunit may be specifically configured to determine an update time and a current time of a latest user portrait, calculate a time interval between the update time and the current time of the latest user portrait, determine a decay factor according to the time interval, then determine a weight of the second interest tag, and multiply the weight of the second interest tag by the decay factor to obtain a second interest tag after decay.
It can be seen that the attenuation factor is a function of the time interval, the specific form may be determined according to the service, and the general principle is that the larger the time interval is, the stronger the attenuation factor is; the smaller the spacing, the weaker the attenuation factor. For convenience of subsequent calculation, the attenuation factor can be reduced to a decimal number between [0 and 1 ].
By the attenuation factor, the degree of interest attenuation of the user can be reflected, and the degree of interest attenuation refers to that the interest labels obtained based on the user behaviors are weakened along with the time. For example, 10 days ago the user watched a horror movie, at which time the user was tagged with a "horror" label. In the last 10 days, the user has no any watching action on the 'horror' movie, the interest of the user on the 'horror movie' should be attenuated, and the attenuation degree can be expressed by an attenuation factor.
The weight of the second interest tag may be preset according to the requirements of the actual application, for example, the weight of "beauty" may be set to 0.1, and the weight of "reading" may be set to 0.4, and so on.
(2) A weighting subunit;
and the weighting subunit is configured to perform weighting calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag.
The weighting method may be various, and for example, the following may be used:
the weighting subunit may be specifically configured to calculate a behavior weight according to the behavior type, determine a weight of the first interest tag, and multiply the weight of the first interest tag by the corresponding behavior weight to obtain a weighted first interest tag.
The behavior weight is different according to the behavior type, and may specifically depend on the requirement of the actual application, for example, the weight of the purchasing behavior may be set to be higher than that of the browsing behavior, and so on.
Similarly, the weight of the first interest tag may be preset according to the requirement of the actual application, for example, the weight of "movie" may be set to 0.2, and the weight of "music" may be set to 0.1, and so on.
(3) Updating the subunit;
and the updating subunit is configured to add the weighted first interest tag to the attenuated second interest tag according to a preset updating ratio, so as to obtain an updated user portrait.
The preset update ratio may be calculated according to the service, and the general principle is that the larger the time interval is, the smaller the ratio is, for example, the ratio may be represented by "1-attenuation factor". Namely:
the updating subunit is specifically configured to calculate a difference obtained by subtracting the attenuation factor from 1, and use the difference as a first ratio; and adding the weighted first interest tag into the attenuated second interest tag according to the first proportion to obtain an updated user portrait.
For example, taking this ratio as "0.7" as an example, if in the previous step:
the weight of the second interest tag "movie" after decay is "3000";
the weight of the second interest tag "caricature" after attenuation is "6000";
the weighted first interest tag cartoon has a weight of 4000;
the weighted first interest tag "music" is weighted by "9000".
The weight of the latest interest tag may be calculated using "weight of interest tag in updated user representation — weighted first interest tag 0.7+ attenuated second interest tag" as follows:
the weight of the interest tag "movie" may be updated as: 0 x 0.7+3000 ═ 3000;
the weight of the interest tag "caricature" may be updated as: 4000 x 0.7+6000 ═ 8800;
the weight of the interest tag "music" may be updated as: 9000 × 0.7+0 ═ 6300.
Since the tag "movie" does not exist in the first interest tag, the weight of the first interest tag "movie" after weighting is 0, and similarly, since the tag "music" does not exist in the second interest tag after fading, it indicates that the interest tag is newly added and does not exist in the past, and the weight of the second interest tag "music" after fading is 0.
Thus, it may be appreciated that the interest tags in the updated user image may include "movies," "caricatures," and "music," where "movies" have a weight of 3000, "caricatures" have a weight of 8800, and "music" have a weight of 6300.
The user representation updating apparatus may be integrated into a device such as a server.
In a specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and the specific implementation of the above units may refer to the foregoing method embodiments, which are not described herein again.
As can be seen from the above, the log obtaining unit 301 of the user portrait updating apparatus of the present embodiment may obtain the current user behavior log, then the tag obtaining unit 302, the determining unit 303, and the portrait obtaining unit 304 respectively determine the latest interest tag, i.e. the first interest tag, of the user and determine the behavior type of the user according to the user behavior log, and obtain the user portrait updated last time by the user to obtain the previous interest tag, i.e. the second interest tag, of the user, and then the updating unit 305 updates the user portrait based on the first interest tag, the behavior type, and the second interest tag; because the scheme can take into account the past interest and the current interest of the user when the user portrait is updated every time, the problem that the updating is not timely due to too long updating interval in the prior art can be solved, the risk that only the current interest is used as the user portrait in the prior art can be solved, and the updating effect is improved while the user portrait is updated in time; in addition, because the scheme adopts an incremental calculation mode (namely, a user portrait updated by a user last time is taken as a reference standard) during updating, the storage space and the calculation resources can be reduced to a great extent, and the processing efficiency is greatly improved.
Example four,
Accordingly, an embodiment of the present invention further provides a system for updating a user portrait, including any one of the apparatus for updating a user portrait provided in the embodiments of the present invention, specifically, see embodiment three, where the apparatus for updating a user portrait may be integrated in a server, and for example, may be as follows:
the server is used for acquiring a current user behavior log, and the user behavior log carries a user identifier and an interest identifier; acquiring a corresponding first interest tag according to the interest identifier; determining the behavior type of the user according to the user behavior log; acquiring a user portrait updated by the user last time according to the user identification; the user representation is updated based on the first interest tag, the behavior type, and a second interest tag carried in the user representation.
For example, the server may be specifically configured to perform attenuation calculation on the second interest tag to obtain an attenuated second interest tag; performing weighted calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag; and adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait.
For attenuation calculation, weighting calculation, etc., reference may be made to the foregoing embodiments, and details are not described herein.
In addition, the user representation updating system may further include other devices, such as a user terminal, as follows:
and the user terminal is used for providing the current user behavior log to the server.
The user image updating system may include any user image updating device provided in the embodiments of the present invention, so that the beneficial effects of any user image updating device provided in the embodiments of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
The method, apparatus, and system for updating a user portrait according to the embodiments of the present invention are described in detail above, and the principles and embodiments of the present invention are described herein by applying specific examples, and the description of the above embodiments is only used to help understand the method and core ideas of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (12)
1. A method for updating a user representation, comprising:
acquiring a current user behavior log, wherein the user behavior log carries a user identifier and an interest identifier;
acquiring a corresponding first interest tag according to the interest identifier;
determining the behavior type of the user according to the user behavior log;
obtaining a user portrait updated by the user last time according to the user identification, wherein the user portrait comprises at least one second interest tag;
and updating the user portrait according to the first interest tag, the behavior type and the second interest tag.
2. The method of claim 1, wherein said updating the user representation based on the first interest tag, the type of activity, and the second interest tag comprises:
performing attenuation calculation on the second interest tag to obtain an attenuated second interest tag;
performing weighted calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag;
and adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait.
3. The method of claim 2, wherein the performing attenuation calculation on the second interest tag to obtain an attenuated second interest tag comprises:
determining the updating time and the current time of the latest user portrait, and calculating the time interval between the updating time and the current time of the latest user portrait;
determining an attenuation factor from the time interval;
and determining the weight of the second interest tag, and multiplying the weight of the second interest tag by the attenuation factor to obtain the attenuated second interest tag.
4. The method of claim 3, wherein adding the weighted first interest tag to the attenuated second interest tag according to a preset update ratio to obtain an updated user profile comprises:
calculating a difference of 1 minus the attenuation factor, the difference being taken as a first proportion;
and adding the weighted first interest tag into the attenuated second interest tag according to the first proportion to obtain an updated user portrait.
5. The method according to any one of claims 2 to 4, wherein the performing a weighted calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag comprises:
calculating a behavior weight according to the behavior type;
and determining the weight of the first interest label, and multiplying the weight of the first interest label by the corresponding behavior weight to obtain the weighted first interest label.
6. The method of any one of claims 1 to 4, wherein the obtaining a current user behavior log comprises:
when the user behavior log is determined to be updated, acquiring the current user behavior log from a user terminal; or,
and receiving the current user behavior log reported by the user terminal when the user behavior log is updated.
7. An apparatus for updating a user representation, comprising:
the log obtaining unit is used for obtaining a current user behavior log, and the user behavior log carries a user identifier and an interest identifier;
the tag obtaining unit is used for obtaining a corresponding first interest tag according to the interest identifier;
the determining unit is used for determining the behavior type of the user according to the user behavior log;
the portrait acquisition unit is used for acquiring a user portrait which is updated last time by a user according to the user identification, wherein the user portrait comprises at least one second interest tag;
and the updating unit is used for updating the user portrait according to the first interest tag, the behavior type and the second interest tag.
8. The apparatus of claim 7, wherein the update unit comprises an attenuation subunit, a weighting subunit, and an update subunit;
the attenuation subunit is configured to perform attenuation calculation on the second interest tag to obtain an attenuated second interest tag;
the weighting subunit is configured to perform weighting calculation on the first interest tag according to the behavior type to obtain a weighted first interest tag;
and the updating subunit is used for adding the weighted first interest tag into the attenuated second interest tag according to a preset updating proportion to obtain an updated user portrait.
9. The apparatus of claim 8,
the attenuation subunit is specifically configured to determine an update time and a current time of a latest user portrait, and calculate a time interval between the update time and the current time of the latest user portrait; determining an attenuation factor from the time interval; and determining the weight of the second interest tag, and multiplying the weight of the second interest tag by the attenuation factor to obtain the attenuated second interest tag.
10. The apparatus of claim 9,
the updating subunit is specifically configured to calculate a difference obtained by subtracting the attenuation factor from 1, and use the difference as a first proportion; and adding the weighted first interest tag into the attenuated second interest tag according to the first proportion to obtain an updated user portrait.
11. The apparatus according to any one of claims 8 to 10,
the weighting subunit is specifically configured to calculate a behavior weight according to the behavior type, determine a weight of the first interest tag, and multiply the weight of the first interest tag by the corresponding behavior weight to obtain a weighted first interest tag.
12. A user representation updating system, comprising the user representation updating apparatus of any one of claims 7 to 11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510362402.0A CN105005587A (en) | 2015-06-26 | 2015-06-26 | User portrait updating method, apparatus and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510362402.0A CN105005587A (en) | 2015-06-26 | 2015-06-26 | User portrait updating method, apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105005587A true CN105005587A (en) | 2015-10-28 |
Family
ID=54378263
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510362402.0A Pending CN105005587A (en) | 2015-06-26 | 2015-06-26 | User portrait updating method, apparatus and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105005587A (en) |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105589956A (en) * | 2015-12-21 | 2016-05-18 | 东软集团股份有限公司 | User portraying method and device |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
CN105657003A (en) * | 2015-12-28 | 2016-06-08 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN105677867A (en) * | 2016-01-08 | 2016-06-15 | 浪潮软件集团有限公司 | User label generation method and device |
CN105893407A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Individual user portraying method and system |
CN105893406A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Group user profiling method and system |
CN106250705A (en) * | 2016-08-10 | 2016-12-21 | 深圳市衣信互联网科技有限公司 | A kind of big data collection analysis system and method based on cloud service |
CN106489159A (en) * | 2016-06-29 | 2017-03-08 | 深圳狗尾草智能科技有限公司 | A kind of user's portrait based on deep neural network represents learning system and method |
CN106599060A (en) * | 2016-11-16 | 2017-04-26 | 竹间智能科技(上海)有限公司 | Method and system for obtaining user portrait |
CN106815738A (en) * | 2015-12-01 | 2017-06-09 | 中国电信股份有限公司 | A kind of method and apparatus for obtaining user's portrait |
CN106874435A (en) * | 2017-01-25 | 2017-06-20 | 北京航空航天大学 | User portrait construction method and device |
CN107203602A (en) * | 2017-05-15 | 2017-09-26 | 竹间智能科技(上海)有限公司 | User model belief updating method and device based on chat memory |
CN108021673A (en) * | 2017-12-06 | 2018-05-11 | 北京拉勾科技有限公司 | A kind of user interest model generation method, position recommend method and computing device |
CN108073716A (en) * | 2017-12-27 | 2018-05-25 | 北京诸葛找房信息技术有限公司 | Online active user portrait generation method |
CN108268547A (en) * | 2016-12-29 | 2018-07-10 | 北京国双科技有限公司 | User's portrait generation method and device |
CN109145197A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | Generation method, the device and system of user's portrait label |
CN109146539A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | The update method and device of user's portrait |
CN109213771A (en) * | 2018-06-28 | 2019-01-15 | 深圳市彬讯科技有限公司 | Update the method and apparatus of portrait label |
CN109254812A (en) * | 2018-08-08 | 2019-01-22 | 连尚(新昌)网络科技有限公司 | A kind of method, system, terminal and server updating Shipping Options Page |
CN109408735A (en) * | 2018-10-11 | 2019-03-01 | 杭州飞弛网络科技有限公司 | A kind of generation method and system of stranger's social activity user portrait |
CN109496302A (en) * | 2018-05-31 | 2019-03-19 | 优视科技新加坡有限公司 | A kind of user's characteristic information collection method, device and equipment/terminal/server |
CN109657138A (en) * | 2018-12-10 | 2019-04-19 | 深圳墨世科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
CN109684554A (en) * | 2018-12-26 | 2019-04-26 | 腾讯科技(深圳)有限公司 | The determination method and news push method of the potential user of news |
CN109727077A (en) * | 2019-01-22 | 2019-05-07 | 深圳魔数智擎科技有限公司 | User's future draws a portrait generation method, computer storage medium and computer equipment |
CN109766913A (en) * | 2018-12-11 | 2019-05-17 | 东软集团股份有限公司 | Tenant group method, apparatus, computer readable storage medium and electronic equipment |
CN110097388A (en) * | 2018-01-31 | 2019-08-06 | 上海甚术网络科技有限公司 | A kind of web advertisement data analysing method |
CN110659921A (en) * | 2018-06-28 | 2020-01-07 | 上海传漾广告有限公司 | Method and system for analyzing correlation between network advertisement audience behaviors and audience interests |
CN111178950A (en) * | 2019-12-19 | 2020-05-19 | 车智互联(北京)科技有限公司 | User portrait construction method and device and computing equipment |
CN111240562A (en) * | 2018-11-28 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Data processing method and device, terminal equipment and computer storage medium |
CN111523026A (en) * | 2020-04-15 | 2020-08-11 | 咪咕文化科技有限公司 | User portrait updating method, system, network equipment and storage medium |
CN111767290A (en) * | 2019-04-01 | 2020-10-13 | 北京百度网讯科技有限公司 | Method and apparatus for updating a user representation |
CN112131465A (en) * | 2020-09-14 | 2020-12-25 | 绿瘦健康产业集团有限公司 | Activity information matching method, device, medium and terminal equipment |
CN112287208A (en) * | 2019-09-30 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | User portrait generation method and device, electronic equipment and storage medium |
CN112988774A (en) * | 2021-03-23 | 2021-06-18 | 汪威 | User information updating method based on big data acquisition and information server |
CN113010536A (en) * | 2021-04-21 | 2021-06-22 | 中国平安人寿保险股份有限公司 | User label obtaining method and device based on streaming data processing |
CN113177780A (en) * | 2021-05-12 | 2021-07-27 | 中移智行网络科技有限公司 | Data processing method and device, network equipment and readable storage medium |
CN114153716A (en) * | 2022-02-08 | 2022-03-08 | 中国电子科技集团公司第五十四研究所 | Real-time portrait generation method for people and nobody objects under semantic information exchange network |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7451210B2 (en) * | 2003-11-24 | 2008-11-11 | International Business Machines Corporation | Hybrid method for event prediction and system control |
CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
CN102890689A (en) * | 2011-07-22 | 2013-01-23 | 北京百度网讯科技有限公司 | Method and system for building user interest model |
CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技(深圳)有限公司 | Method and device for generating tags for user |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104602042A (en) * | 2014-12-31 | 2015-05-06 | 合一网络技术(北京)有限公司 | User behavior based label setting method |
-
2015
- 2015-06-26 CN CN201510362402.0A patent/CN105005587A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7451210B2 (en) * | 2003-11-24 | 2008-11-11 | International Business Machines Corporation | Hybrid method for event prediction and system control |
CN101901450A (en) * | 2010-07-14 | 2010-12-01 | 中兴通讯股份有限公司 | Media content recommendation method and media content recommendation system |
CN102890689A (en) * | 2011-07-22 | 2013-01-23 | 北京百度网讯科技有限公司 | Method and system for building user interest model |
CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技(深圳)有限公司 | Method and device for generating tags for user |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104602042A (en) * | 2014-12-31 | 2015-05-06 | 合一网络技术(北京)有限公司 | User behavior based label setting method |
Cited By (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893407A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Individual user portraying method and system |
CN105893406A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Group user profiling method and system |
CN106815738A (en) * | 2015-12-01 | 2017-06-09 | 中国电信股份有限公司 | A kind of method and apparatus for obtaining user's portrait |
CN105589956B (en) * | 2015-12-21 | 2018-11-27 | 东软集团股份有限公司 | A kind of method and device of user's portrait |
CN105589956A (en) * | 2015-12-21 | 2016-05-18 | 东软集团股份有限公司 | User portraying method and device |
CN105608171A (en) * | 2015-12-22 | 2016-05-25 | 青岛海贝易通信息技术有限公司 | User portrait construction method |
CN105608171B (en) * | 2015-12-22 | 2018-12-11 | 青岛海贝易通信息技术有限公司 | User's portrait construction method |
CN105657003A (en) * | 2015-12-28 | 2016-06-08 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN105657003B (en) * | 2015-12-28 | 2020-01-10 | 腾讯科技(深圳)有限公司 | Information processing method and server |
CN105677867A (en) * | 2016-01-08 | 2016-06-15 | 浪潮软件集团有限公司 | User label generation method and device |
CN106489159A (en) * | 2016-06-29 | 2017-03-08 | 深圳狗尾草智能科技有限公司 | A kind of user's portrait based on deep neural network represents learning system and method |
CN106250705A (en) * | 2016-08-10 | 2016-12-21 | 深圳市衣信互联网科技有限公司 | A kind of big data collection analysis system and method based on cloud service |
CN106599060A (en) * | 2016-11-16 | 2017-04-26 | 竹间智能科技(上海)有限公司 | Method and system for obtaining user portrait |
CN106599060B (en) * | 2016-11-16 | 2020-04-07 | 竹间智能科技(上海)有限公司 | Method and system for acquiring user portrait |
CN108268547A (en) * | 2016-12-29 | 2018-07-10 | 北京国双科技有限公司 | User's portrait generation method and device |
CN106874435B (en) * | 2017-01-25 | 2020-02-14 | 北京航空航天大学 | User portrait construction method and device |
CN106874435A (en) * | 2017-01-25 | 2017-06-20 | 北京航空航天大学 | User portrait construction method and device |
CN107203602A (en) * | 2017-05-15 | 2017-09-26 | 竹间智能科技(上海)有限公司 | User model belief updating method and device based on chat memory |
CN108021673A (en) * | 2017-12-06 | 2018-05-11 | 北京拉勾科技有限公司 | A kind of user interest model generation method, position recommend method and computing device |
CN108073716A (en) * | 2017-12-27 | 2018-05-25 | 北京诸葛找房信息技术有限公司 | Online active user portrait generation method |
CN110097388A (en) * | 2018-01-31 | 2019-08-06 | 上海甚术网络科技有限公司 | A kind of web advertisement data analysing method |
CN109496302A (en) * | 2018-05-31 | 2019-03-19 | 优视科技新加坡有限公司 | A kind of user's characteristic information collection method, device and equipment/terminal/server |
CN110659921A (en) * | 2018-06-28 | 2020-01-07 | 上海传漾广告有限公司 | Method and system for analyzing correlation between network advertisement audience behaviors and audience interests |
CN109145197B (en) * | 2018-06-28 | 2022-10-04 | 土巴兔集团股份有限公司 | User portrait label generation method, device and system |
CN109213771A (en) * | 2018-06-28 | 2019-01-15 | 深圳市彬讯科技有限公司 | Update the method and apparatus of portrait label |
CN109146539A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | The update method and device of user's portrait |
CN109145197A (en) * | 2018-06-28 | 2019-01-04 | 深圳市彬讯科技有限公司 | Generation method, the device and system of user's portrait label |
CN109254812A (en) * | 2018-08-08 | 2019-01-22 | 连尚(新昌)网络科技有限公司 | A kind of method, system, terminal and server updating Shipping Options Page |
CN109408735A (en) * | 2018-10-11 | 2019-03-01 | 杭州飞弛网络科技有限公司 | A kind of generation method and system of stranger's social activity user portrait |
CN109408735B (en) * | 2018-10-11 | 2021-06-25 | 杭州飞弛网络科技有限公司 | Stranger social user portrait generation method and system |
CN111240562B (en) * | 2018-11-28 | 2023-04-25 | 阿里巴巴集团控股有限公司 | Data processing method, device, terminal equipment and computer storage medium |
CN111240562A (en) * | 2018-11-28 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Data processing method and device, terminal equipment and computer storage medium |
CN109657138A (en) * | 2018-12-10 | 2019-04-19 | 深圳墨世科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
CN109657138B (en) * | 2018-12-10 | 2021-02-26 | 深圳大宇无限科技有限公司 | Video recommendation method and device, electronic equipment and storage medium |
CN109766913A (en) * | 2018-12-11 | 2019-05-17 | 东软集团股份有限公司 | Tenant group method, apparatus, computer readable storage medium and electronic equipment |
CN109684554A (en) * | 2018-12-26 | 2019-04-26 | 腾讯科技(深圳)有限公司 | The determination method and news push method of the potential user of news |
CN109727077A (en) * | 2019-01-22 | 2019-05-07 | 深圳魔数智擎科技有限公司 | User's future draws a portrait generation method, computer storage medium and computer equipment |
CN111767290A (en) * | 2019-04-01 | 2020-10-13 | 北京百度网讯科技有限公司 | Method and apparatus for updating a user representation |
CN111767290B (en) * | 2019-04-01 | 2024-04-19 | 北京百度网讯科技有限公司 | Method and apparatus for updating user portraits |
CN112287208A (en) * | 2019-09-30 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | User portrait generation method and device, electronic equipment and storage medium |
CN112287208B (en) * | 2019-09-30 | 2024-03-01 | 北京沃东天骏信息技术有限公司 | User portrait generation method, device, electronic equipment and storage medium |
CN111178950A (en) * | 2019-12-19 | 2020-05-19 | 车智互联(北京)科技有限公司 | User portrait construction method and device and computing equipment |
CN111178950B (en) * | 2019-12-19 | 2023-08-29 | 车智互联(北京)科技有限公司 | User portrait construction method and device and computing equipment |
CN111523026A (en) * | 2020-04-15 | 2020-08-11 | 咪咕文化科技有限公司 | User portrait updating method, system, network equipment and storage medium |
CN111523026B (en) * | 2020-04-15 | 2023-10-17 | 咪咕文化科技有限公司 | User portrait updating method, system, network equipment and storage medium |
CN112131465A (en) * | 2020-09-14 | 2020-12-25 | 绿瘦健康产业集团有限公司 | Activity information matching method, device, medium and terminal equipment |
CN112988774A (en) * | 2021-03-23 | 2021-06-18 | 汪威 | User information updating method based on big data acquisition and information server |
CN113010536B (en) * | 2021-04-21 | 2024-02-06 | 中国平安人寿保险股份有限公司 | User tag acquisition method and device based on stream data processing |
CN113010536A (en) * | 2021-04-21 | 2021-06-22 | 中国平安人寿保险股份有限公司 | User label obtaining method and device based on streaming data processing |
CN113177780A (en) * | 2021-05-12 | 2021-07-27 | 中移智行网络科技有限公司 | Data processing method and device, network equipment and readable storage medium |
CN114153716B (en) * | 2022-02-08 | 2022-05-06 | 中国电子科技集团公司第五十四研究所 | Real-time portrait generation method for people and nobody objects under semantic information exchange network |
CN114153716A (en) * | 2022-02-08 | 2022-03-08 | 中国电子科技集团公司第五十四研究所 | Real-time portrait generation method for people and nobody objects under semantic information exchange network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105005587A (en) | User portrait updating method, apparatus and system | |
US11038975B2 (en) | Information pushing method and device | |
CN109325179B (en) | Content promotion method and device | |
CN110135895B (en) | Advertisement putting method, device, equipment and storage medium | |
CN104537000B (en) | A kind of method and apparatus for pushed information | |
CN104954410A (en) | Message pushing method, device thereof and server | |
CN104239545B (en) | Multi-label page preview method and device | |
CN111147431B (en) | Method and apparatus for generating information | |
CN109003146B (en) | Business data popularization method, device, terminal and computer readable storage medium | |
CN104065672A (en) | Advertisement pushing method, client and advertisement pushing system | |
CN108540508B (en) | Method, device and equipment for pushing information | |
CN108737486B (en) | Information pushing method and device | |
CN106777354A (en) | Promotion message freshness determines method and device | |
CN105989107A (en) | Application recommendation method and device | |
CN104484482A (en) | Webpage information updating method and system of network platform | |
CN107633426A (en) | Advertising message method for implantation and system based on environmental data | |
CN104967690A (en) | Information push method and device | |
CN107967626A (en) | APP advertisement sending methods and its system | |
CN108038714B (en) | Advertisement promotion processing method and device | |
CN107257358A (en) | A kind of information-pushing method, terminal and server | |
US11070518B2 (en) | Method and system for assigning number for routing call from electronic device | |
CN103246501A (en) | Method and client-side for sharing application | |
CN108549722B (en) | Multi-platform data publishing method, system and medium | |
CN110335073A (en) | A kind of accurate method for pushing of Instant Ads excavated based on user behavior data | |
CN110557351A (en) | Method and apparatus for generating information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151028 |