CN106777354A - Promotion message freshness determines method and device - Google Patents
Promotion message freshness determines method and device Download PDFInfo
- Publication number
- CN106777354A CN106777354A CN201710036301.3A CN201710036301A CN106777354A CN 106777354 A CN106777354 A CN 106777354A CN 201710036301 A CN201710036301 A CN 201710036301A CN 106777354 A CN106777354 A CN 106777354A
- Authority
- CN
- China
- Prior art keywords
- determining
- memory
- promotion information
- freshness
- user
- 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 37
- 230000015654 memory Effects 0.000 claims abstract description 227
- 230000000694 effects Effects 0.000 abstract description 13
- 238000004364 calculation method Methods 0.000 description 15
- 230000001737 promoting effect Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000002596 correlated effect Effects 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008655 medium-term memory Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000012360 testing method Methods 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
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
Determine method and device the embodiment of the invention discloses a kind of freshness of promotion message, be related to areas of information technology, method to include：Obtain the historical data that user checks promotion message；According to the historical data, the memory intensity of the first promotion message is determined, wherein, first promotion message is associated with the second promotion message in predetermined dimension；Second promotion message is current information to be promoted；First promotion message is the promotion message that user has checked；The memory intensity is used for the intensity for indicating the user to remember first promotion message；According to the memory intensity, freshness of second promotion message in the predetermined dimension is determined, wherein, the freshness is used to indicate the strange degree of second promotion message.Whether technical scheme provided in an embodiment of the present invention, by the calculating of freshness, can realize that being accurately positioned for promotion message sends and lifted promotion message and have effect spread to send promotion message to client and provides foundation.
Description
Technical Field
The invention relates to the technical field of information, in particular to a method and a device for determining the freshness of popularization information.
Background
The promotion information is content actively pushed to a user for watching or searching, and common promotion information can comprise advertisements, government announcements, activity introduction information and the like.
In the prior art, usually, one piece of popularization information is repeatedly pushed to the same user for watching, or similar popularization information may be pushed to one or more users for watching in a concentrated manner, but the popularization effect of the promotion information pushing method is not good, and obviously, the effective spreading rate of the information is low. In addition, the repeated pushing of the same promotion information or similar promotion information to the same or same type of users may cause user dissatisfaction and even cause complaints, or close and delete some applications, thereby causing a problem of user loss.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide a method and an apparatus for determining freshness of promotion information, so as to improve promotion effects of promotion information and user satisfaction of receiving and/or viewing promotion information.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a first aspect of an embodiment of the present invention provides a method for determining freshness of promotion information, including:
acquiring historical data of user viewing promotion information;
determining the memory strength of first promotion information according to the historical data, wherein the first promotion information is related to the second promotion information in a preset dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
according to the memory intensity, determining the freshness of the second promotion information on the preset dimensionality, wherein the freshness is used for indicating the strangeness degree of the second promotion information.
Based on the above scheme, the determining the freshness of the second promotion information in the predetermined dimension according to the memory strength includes:
and determining the freshness of the second promotion information on the preset dimension according to the memory intensity and the attenuation factor.
Based on the above scheme, the determining the freshness of the second promotion information in the predetermined dimension according to the memory strength and the attenuation factor includes:
the freshness freshsore in the predetermined dimension is calculated according to the following formula,
wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is an attenuation factor.
Based on the above scheme, the determining the memory strength of the first promotion information according to the historical data includes:
determining whether the first promotion information is checked within a preset time range or not according to the historical data;
and when the first promotion information is not checked in the preset time range, the memory intensity is a specified value.
Based on the above scheme, the determining the memory strength of the user for memorizing the first popularization information according to the historical data includes:
when the first promotion information is checked in the preset time range, determining checking time and checking times of the first promotion information in the preset time range;
and determining the memory intensity according to the viewing times and the viewing time.
Based on the above scheme, the determining the memory strength according to the viewing times and the viewing time includes:
determining the memory quality parameter of the user;
and determining the memory strength according to the checking times, the checking time and the memory quality parameters.
Based on the above scheme, the determining the memory quality parameter of the user includes:
acquiring the user attribute of the user;
and determining the memory quality parameter according to the user attribute.
Based on the above scheme, the determining the memory strength according to the viewing times and the viewing time includes:
determining the single memory intensity of single viewing according to the time difference between the viewing time and the current time;
determining the overall memory intensity according to the single memory intensity;
determining an attenuation factor in the preset time range according to the checking times;
and determining the memory intensity by combining the overall memory intensity and the attenuation factor.
Based on the above scheme, the method further comprises:
and determining comprehensive freshness according to the freshness of the plurality of preset dimensions.
Based on the above scheme, said determining the integrated freshness according to the freshness of a plurality of said predetermined dimensions comprises:
the integrated freshness FreshScore is calculated according to the following formula:
FreshScore＝∑wi×FreshScorei
wherein the FreshScoreiFreshness for the ith said predetermined dimension; said wiThe weight value of the ith preset dimension is obtained; wherein the value of i is an integer not less than 1.
A second aspect of an embodiment of the present invention provides an apparatus for determining freshness of promotion information, including:
the acquisition unit is used for acquiring historical data of the popularization information checked by the user;
the first determining unit is used for determining the memory intensity of first promotion information according to the historical data, wherein the first promotion information is related to the second promotion information in a preset dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
the second determining unit is used for determining the freshness of the second promotion information on the preset dimensionality according to the memory strength, wherein the freshness is used for indicating the strangeness degree of the second promotion information.
Based on the above scheme, the second determining unit is configured to determine the freshness of the second popularization information in the predetermined dimension according to the memory strength and the attenuation factor.
Based on the above scheme, the second determining unit is specifically configured to calculate the freshness freshsore in the predetermined dimension according to the following formula,
wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is an attenuation factor.
Based on the above scheme, the first determining unit is configured to determine whether the first popularization information is checked within a predetermined time range according to the historical data; and when the first promotion information is not checked in the preset time range, the memory intensity is a specified value.
Based on the above scheme, the first determining unit is specifically configured to determine, when the first popularization information is checked within the predetermined time range, checking time and checking times for checking the first popularization information within the predetermined time range; and determining the memory intensity according to the viewing times and the viewing time.
Based on the above scheme, the second determining unit is configured to determine a memory quality parameter of the user; and determining the memory strength according to the checking times, the checking time and the memory quality parameters.
Based on the above scheme, the second determining unit is configured to obtain the user attribute of the user; and determining the memory quality parameter according to the user attribute.
Based on the above scheme, the second determining unit is configured to determine a single memory strength of a single check according to a time difference between the check time and the current time; determining the overall memory intensity according to the single memory intensity; determining an attenuation factor within the preset time range according to the checking times; and determining the memory intensity by combining the overall memory intensity and the attenuation factor.
Based on the above scheme, the apparatus further comprises:
and the third determining unit is used for determining the comprehensive freshness according to the freshness of the preset dimensions.
Based on the above scheme, the third determining unit is configured to calculate the integrated freshness FreshScore according to the following formula:
FreshScore＝∑wi×FreshScorei
wherein the FreshScoreiFreshness for the ith said predetermined dimension; said wiThe weight value of the ith preset dimension is obtained; wherein the value of i is an integer not less than 1.
According to the method and the device for determining the freshness of the promotion information, provided by the embodiment of the invention, the historical data of the promotion information checked by a user can be obtained, the memory strength of the first promotion information which is associated with the second promotion information to be promoted at present can be determined according to the historical data, the freshness of the second promotion information in a preset dimension can be obtained according to the memory strength and the attenuation factor, the freshness can be used as a parameter for screening and sending the second promotion information to the user, and through calculation of the freshness, compared with the method and the device for randomly sending the promotion information to the user or sending the promotion information to the user without screening, the problems of poor promotion effect and low user satisfaction caused by repeatedly sending the same information or the same type of information to the same user can be reduced, and the promotion effect and the user satisfaction are improved.
Drawings
Fig. 1 is a flowchart illustrating a first method for determining freshness of promotion information according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a freshness determination apparatus for providing first promotion information according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a second method for determining freshness of promotion information according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a corresponding relationship between a predetermined dimension and a memory content according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a freshness determination apparatus for providing a second promotion information according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a promotion information system according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the drawings and the specific embodiments of the specification.
As shown in fig. 1, the present embodiment provides a method for determining freshness of promotion information, including:
step S110: acquiring historical data of user viewing promotion information;
step S120: determining the memory strength of first promotion information according to the historical data, wherein the first promotion information is related to the second promotion information in a preset dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
step S130: according to the memory intensity, determining the freshness of the second promotion information on the preset dimensionality, wherein the freshness is used for indicating the strangeness degree of the second promotion information.
The freshness determination method described in this embodiment may be an information processing method applied to various electronic devices with information processing functions, for example, an information processing method applied to an advertisement promotion platform. The promotional information may include advertisements, various types of announcements or events, and the like, where advertisements may include commercial advertisements and non-commercial advertisements. The non-commercial advertisements may typically include charitable advertisements, and the like.
The freshness may be a basis for determining whether to push the second promotion information to the user, for example, when the value of the freshness is within a specified range, the second promotion information is sent to the user, otherwise, the second promotion information is not sent. In this embodiment, the freshness may be a parameter related to a receiving condition of the first promotion information received by the client where the user is located. The receiving condition information may include parameters such as the receiving times, the receiving frequency and/or the receiving time of the first promotion information. Of course, the freshness may be display condition information of whether the client where the user is located has displayed the first promotion information, where the display condition information may include information such as display times, display time, and/or display frequency.
The historical data is the historical data of the popularization information checked by the user, and the historical data can comprise various parameters of the information name of the popularization information checked by the user, the popularization object and the source of the popularization information, materials related to the popularization information, checking time, checking duration, checking times and the like. The material may include various data constituting the promotion information, such as pictures, texts, and/or videos used in the promotion information.
In a specific implementation, the history data may further include a display duration and a display frequency of the first promotion information on the user terminal, and a user operation accompanying the first promotion information viewed by the user. The user operation can comprise other user operations besides simple viewing, such as a forwarding operation, a clicking operation, a collection operation of collecting to a collection catalogue, a recommendation operation or a copying operation recommended to a friend, and the like.
These user operations can enhance the memory of the user and can improve the memory strength of the user. Therefore, in the embodiment, when determining the memory strength, the memory strength is determined not only according to the parameters such as whether to check, the number of times of checking, the duration of checking, and the like, but also according to the user operation accompanying in the checking process. If the user operation occurs, the memory strength can be recalculated by using the enhancement coefficient according to the enhancement coefficient corresponding to the user operation except the viewing operation on the basis of the memory strength obtained by the viewing operation, so that the memory strength obtained by recalculation is increased. The enhancement factor may be a positive number greater than 1.
When the user watches a certain promotion information, the longer the watching time point is away from the current time point, the lower the memory intensity of the user on the promotion information is, the fewer the watching times are, and the lower the memory intensity is.
In this embodiment, the memory strength may represent a memory degree of a certain promotion information by a user, for example, a memory percentage or a memory definition of a certain promotion information memorized by the user may be included. For example, an advertisement includes M words, where the strength of memory may include the total number of words that the user remembers, and/or, the correct total number of words is remembered. For example, if the user remembers N1 words, the memory ratio can be N1/M; if the user remembers the correct total number of words N2, the memory resolution may be N2/M. In this embodiment, the memory strength may be represented by the memory ratio, the memory clarity, the memory duration, or a combination of the memory ratio and/or the memory clarity, so as to obtain a comprehensive memory strength. The comprehensive memory strength can be the product of the memory proportion and the proportion weight and the product of the memory definition and the definition proportion weight. In summary, there are many ways to characterize the memory strength, and this is not exemplified in this embodiment.
In this embodiment, the memory strength may be between 0 and 1. In the present embodiment, the freshness is a parameter that is negatively related to the memory strength, for example, the freshness is equal to the inverse of the memory strength.
The freshness calculated in this embodiment may be used to determine whether to send the second promotional information to a user, or when to send the promotional information to the first user. For example, the calculated freshness at the current time is low, which indicates that the user may have just seen the promotion information, and it may be determined according to the freshness that the second promotion information is not sent to the user at the current time, and it may also be used to calculate that the second promotion information is pushed to the user at a certain time after the current time.
In this embodiment, the second promotion information and the first promotion information are two promotion information having relevance, and the first promotion information is promotion information that a user can know and see according to historical data of the user. In this embodiment, the second promotion information and the first promotion information have relevance, and these relevance may be embodied in these aspects:
in a first aspect: the relevance may be embodied in that the attributes of the second promotional information and the first promotional information in the predetermined dimension are the same. For example, the second promotion information and the first promotion information relate to the same industry, for example, both are automobile advertisements or mobile phone advertisements, or the same brand or advertiser. For another example, the second promotion information is a mobile phone advertisement of apple, and the first promotion information is a tablet personal computer advertisement of apple. As a specific example, the first promotion information may include the second promotion information itself. For example, when there is currently an advertisement a, and the user has just promoted the advertisement a for the first two days, and the user also views the advertisement a, the viewing record of the advertisement a will be presented in the history data. Therefore, in this embodiment, when the second popularization information is to be sent to the user again, the freshness of the second popularization information by the user may be determined according to the history data of the second popularization information sent to the user before, and then whether to continue sending the second popularization information to the user and/or when to send the second popularization information to the user may be determined according to the calculated freshness.
In a second aspect:
the second promotion information and the first promotion information have relevance, and the similarity between the second promotion information and the first promotion information in a preset dimension is also embodied. For example, the material used in advertisement a and advertisement B has similarity. For example, advertisement a and advertisement B use similar pictures and/or background music, etc.
In this embodiment, the user may be represented by various user identifiers, for example, in a social application, a user may be characterized by a social account of the social application. Here, sending the second popularization information to the user may be immediately sending the second popularization information to the social account corresponding to the user, and then the popularization information may be seen on an application interface of the social account of the user.
In the embodiment, by calculating the freshness, which popularization information is sent or not sent to the user can be determined, and the problems of poor popularization effect, poor effective propagation rate and low user satisfaction of the popularization information caused by repeatedly sending the same or similar popularization information to the user are avoided, so that the popularization effect, the effective propagation rate and the user satisfaction of the popularization information are improved.
In the embodiment, when the freshness is calculated, an attenuation factor is also introduced, wherein the attenuation factor is used for indicating the memory attenuation degree of the user migration along with the time, and generally, the attenuation factor is in negative correlation with the duration from the viewing time to the current time. That is, the greater the duration, the smaller the attenuation factor, indicating that the greater the memory intensity attenuation, the greater the freshness. Therefore, the step S130 may include: and determining the freshness of the second promotion information on the preset dimension according to the memory intensity and the attenuation factor.
By introducing an attenuation factor, the freshness can be calculated more accurately.
There are various implementation manners of the step S130, and the following provides an optional manner:
the determining the freshness of the second promotion information on the predetermined dimension according to the memory strength and the attenuation factor includes:
the freshness freshsore in the predetermined dimension is calculated according to the following formula,
wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is an attenuation factor.
In this way, firstly, the embodiment provides a freshness degree calculation method, and secondly, quantification of freshness degree is achieved, so that various electronic devices can conveniently determine whether to push the second promotion information to a user according to quantified parameters.
In some embodiments, the step S120 may include:
determining whether the first promotion information is checked by the user within a preset time range or not according to the historical data;
and when the first promotion information is not checked in the preset time range, the memory intensity is a designated value.
The predetermined time range may correspond to a time window ending with the current time. For example, if the duration of the time window is 1 month, the predetermined time window may be one month before the current time. Of course, in this embodiment, if the periodic statistics are performed, the predetermined time range may be the previous period.
In this embodiment, first, it is determined whether the first promotion information associated with the second promotion information in a predetermined dimension has been checked within a predetermined time range. If it is found by querying the historical data, the user does not view the first promotion information associated with the second promotion information in the predetermined dimension within the predetermined time range, so the memory strength is a designated value in this embodiment, the designated value may be 0 or a positive real number not within the predetermined value range in this embodiment, which indicates that the user does not view the first promotion information, and obviously, even if the memory is not available, the memory strength is not involved, or the user may view the first promotion information in other scenes, so the designated value may be given in advance, or a value may be randomly selected from the predetermined value range as the designated value. If the second information is viewed, the memory intensity can be calculated according to a preset functional relation.
In the embodiment, the memory strength is positively correlated with the number of times of watching the first promotion information, and is negatively correlated with the time length of the watching time point from the current time point; functions that satisfy this relationship can be used to calculate the memory strength.
In some embodiments, the step S120 may include:
when the first promotion information is checked within the preset time range, checking times and each checking time are determined;
and determining the memory intensity according to the viewing times and the viewing time.
For example, if the client displays one piece of the first promotion information at time a within a predetermined time range, the time a is the viewing time.
Further, the method further comprises:
determining a frequency attenuation factor according to the checking frequency;
the step S130 may include:
and determining the freshness according to the memory intensity and the number attenuation factor.
In some embodiments, the aforementioned attenuation factor may be a comprehensive memory attenuation factor, which may be any parameter negatively correlated to the time length between the viewing time and the current time, and may be a statically set value, and when the method is used in a specific application, the time length is used as a query index and is determined by looking up a table. In this embodiment the attenuation factor is a number attenuation factor. A specific functional relationship may be employed for the calculation. One calculated functional relationship for the degree attenuation factor is provided below, and is not limited to the following functional relationship when used specifically:
wherein, the CalDesc (x) is a calculated function value and is the memory attenuation factor; and x is the number of times of watching the first promotion information in the preset time range.
In some embodiments, the determining the memory strength according to the number of viewing times and the viewing time includes:
determining the memory quality parameter of the user;
and determining the memory strength according to the checking times, the checking time and the memory quality parameters.
The memory quality parameter here is a parameter that reflects the strength of the user's memory, and may represent, for example, the duration of time for which a piece of information is memorized after being viewed. Generally, the better the memory of a person, the larger the memory goodness parameter.
During calculation, through big data analysis, all users adopt a unified default value, for example, in this embodiment, a default value may be a value 60 representing a parameter of memory merits of a common person.
But in some embodiments to accurately calculate the freshness, the memory goodness parameter will be determined on a targeted basis based on user attributes. For example, the memory quality parameter is dynamically determined according to reference factors such as the gender and/or age and/or education degree of the user. For example, the age may be divided into different age groups, each of which is assigned a memory goodness parameter, e.g., a 20 to 30 year old user may have a greater memory goodness parameter relative to a 50 to 60 year old user. For gender, the memory quality parameter of the female user may be set to be greater than the memory quality parameter of the male user. For the education level, the memory quality parameter of the user with high education level can be made larger than the memory quality parameter of the user with low education level. Of course, the above is only roughly classified according to the user attributes to determine the memory quality parameter.
In particular implementation, the memory quality parameter can be dynamically determined according to personal characteristics of each user. For example, some users can determine that the memory of the user is stronger than that of a common user through social activities or games participated by the users and some intelligent tests, and specific memory quality parameters can be given according to the memory strength of the user, rather than obtaining the memory quality parameters through other attribute analysis of the user.
Therefore, the memory quality parameter can be a uniformly distributed uniform value, or different values for different users, or a static value or a dynamically determined value.
For example, the determining the memory goodness parameter of the user includes: acquiring the user attribute of the user; and determining the memory quality parameter according to the user attribute. The user attributes may include the age, gender, occupation, education level, preferences, or personal behavior habits. The user's preferences may also determine how well the user remembers a certain message. For example, a user may be interested in information a, and may have a memory that is continuously higher than information B that is not interested in it. Although some users of the personal behavior habits have strong memory, the memory can be automatically shielded in some cases, and active memory can be realized in some cases to generate an effect of forgetting, so that the memory quality parameter can be determined according to the personal behavior habits in the embodiment.
Of course, in some embodiments, the memory goodness parameter is also related to the time point of memory generation, for example, some users have a memory in the morning that is significantly better than the memory in the afternoon, so the value of the memory goodness parameter may depend not only on the user attribute but also on the occurrence time of the memory. Therefore, the memory quality parameter can also be determined according to the occurrence time of the memory and/or the user attribute.
In some embodiments, the method further comprises:
determining an integrated freshness according to the freshness of the plurality of predetermined dimensions, wherein optionally the integrated freshness is at least used for determining whether to send the second promotion information to the user.
Carry out from the multidimension degree in this embodiment the calculation of new freshness to confirm comprehensive new freshness, thereby realize more accurate new freshness calculation, and promote the accurate popularization of information.
The predetermined dimension may include various information such as the promotion information itself, the source of the promotion information, the promotion objects related to the promotion information, the industry or brand related to the promotion information, and the materials included in the promotion information.
And respectively calculating the freshness of at least two preset dimensions, combining the freshness of each preset dimension to obtain a comprehensive freshness, and finally determining whether to send the second promotion information to the user and/or when to send the second promotion information to the user according to the comprehensive freshness.
For example, the determining an integrated freshness based on the freshness of the plurality of predetermined dimensions includes:
calculating the integrated freshness FreshScore according to the following formula
FreshScore＝∑wi×FreshScorei
Wherein the FreshScoreiFreshness for the ith said predetermined dimension; said wiThe weight value of the ith preset dimension is obtained; wherein the value of i is an integer not less than 1.
And if the weights of different preset dimensions are different, the influence degree of the freshness of the preset dimension on the comprehensive freshness is represented. Usually, the weight value is a preset static value. The static value can be an influence value which can reflect the degree of strangeness of the dimension to a certain promotion information of the user and is determined according to big data statistics or simulation or experience summary.
For example, the predetermined dimensions corresponding to an advertisement may include both dimensions of an advertiser and a promotion. In general, the advertiser may not have a high degree of interest in the user, and the advertiser may set a weight value lower than the weight value of the promotion when calculating the integrated freshness. In short, the value of the weight in this embodiment may be positively correlated with the attention of the user to the dimension. The value of i starts from 1, and the maximum value is the total preset dimension number M.
In some embodiments, determining the memory strength according to the number of viewing times and the viewing time includes:
determining the single memory intensity of single viewing according to the time difference between the viewing time and the current time;
determining the overall memory intensity according to the single memory intensity;
determining an attenuation factor within the preset time range according to the checking times;
and determining the memory intensity by combining the overall memory intensity and the attenuation factor. A specific method for calculating the memory strength is provided below, but it should be noted that the specific implementation is not limited to this algorithm.
CalMemory(t,impressCount)＝CalTimeFactor(t)×CalCountFactor(impressCount)
If impressCount ≠ 0, then calcountfactor (impressCount) is 1, otherwise calcountfactor (impressCount) is 0;
the t is the viewing time; the impressCount is the number of times that the user checks the first promotion information at time t, and the value is 0 or 1 or an integer greater than 1; and s is the memory quality parameter. The callmemory (T, impressCount) is the memory strength of the viewing time T, that is, the memory strength of the user at the current time T after viewing the first promotion information at the time T. During specific calculation, the memory intensity of each time point needs to be combined to obtain the overall memory intensity within the preset time range. For example, the overall memory strength can be calculated using the following functional relationship:
and T is the current moment. If the T1 is the earliest time point in the predetermined time range, the T2 is the latest time point in the predetermined time range, and if the T2 is the earliest time point in the predetermined time range, the T1 is the latest time point in the predetermined time range.
In some embodiments, the step S130 may include:
calculate the freshness FreshScore of the ith according to the following formulai
Wherein, the alpha is a fitting coefficient, and the Calmemory is the overall memory intensity; the beta is a memory attenuation factor.
In this embodiment, β may be calculated by the following functional relationship:
the definition of each parameter herein can be referred to the parameters represented by the corresponding symbols of the previous embodiments.
As shown in fig. 2, the present embodiment provides a freshness degree determination apparatus of promotion information, including:
an obtaining unit 110, configured to obtain historical data of popularization information viewed by a user;
a first determining unit 120, configured to determine, according to the historical data, a memory strength of first promotional information, where the first promotional information is associated with second promotional information in a predetermined dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
a second determining unit 130, configured to determine freshness of the second popularization information in the predetermined dimension according to the memory strength, where the freshness is used to indicate a degree of strangeness of the second popularization information.
The freshness degree determination device provided by the embodiment can be applied to various promotion information providing servers or search servers or push servers or promotion information processing platforms.
The obtaining unit 110 may correspond to a processor or a processing circuit, may read the history data from a local storage medium of the device, and may also correspond to a communication interface, receive or query the history data from an external device, for example, query or receive the history data from a network platform such as a cloud platform.
The first determining unit 120 and the second determining unit 130 correspond to a processor or a processing circuit. The processor may include a central processing unit, digital signal processor, application processor, microprocessor, application processor, or programmable array, or the like. The processing circuit may comprise an application specific integrated circuit.
The processor or processing circuit may implement the operations of the first and second determining units 120 and 130 through the execution of predetermined codes.
The first determining unit 120 and the second determining unit 130 may correspond to the same processor or processing circuit, or may correspond to different processors or processing circuits.
The second determining unit 130 is configured to determine the freshness of the second popularization information in the predetermined dimension according to the memory strength and the attenuation factor.
In a word, the new freshness degree determination device that this embodiment provided can be used to calculate the new freshness degree of the second popularization information of treating the popularization to a certain or a plurality of users, makes things convenient for follow-up popularization server or promotion information's providing server according to the new freshness degree selectivity sends the popularization information to the user, promotes the popularization effect of popularization information and user's information and looks up the satisfaction.
In some embodiments, the apparatus further comprises:
a third determining unit, configured to determine an integrated freshness according to the freshness degrees of the plurality of predetermined dimensions, where the integrated freshness is at least used to determine whether to send the second promotion information to the user.
In this embodiment, a third determining unit is further introduced, and a specific structure of the third determining unit is the same as or similar to the structures of the first determining unit 120 and the second determining unit 130, but the third determining unit is a comprehensive calculating unit for freshness of a plurality of predetermined dimensions, and can combine the freshness of the plurality of predetermined dimensions to obtain a comprehensive freshness, which is used as a selection basis for sending promotion information to a user.
In some embodiments, the third determining unit is specifically configured to calculate the integrated freshness FreshScore according to the following formula:
FreshScore＝∑wi×FreshScorei
wherein the FreshScoreiFreshness for the ith said predetermined dimension; said wiThe weight value of the ith preset dimension is obtained; wherein the value of i is an integer not less than 1.
The third determination unit may correspond to a calculator or a processor having a calculation function in the present embodiment. The third determining unit calculates the comprehensive freshness by using the functional relationship, so that the popularization information suitable for being sent to the current user can be conveniently selected from a plurality of dimensions, on one hand, the accurate determination of the user receiving the popularization information is ensured, the popularization effect is further improved, and on the other hand, the satisfaction degree of the user receiving and/or checking the popularization information can be ensured.
In some embodiments, the first determining unit 120 is configured to determine whether the first promotion information has been viewed by the user within a predetermined time range according to the historical data; and when the first promotion information is not checked in the preset time range, the memory intensity is a designated value.
In this embodiment, the first determining unit 120 first determines the memory strength according to a viewing record of the first promotion information related to the second promotion information in a certain predetermined dimension within a defined predetermined time range.
In this embodiment, reference may be made to the foregoing embodiment for the correlation between the second popularization information and the first popularization information in a predetermined dimension, which is not repeated here.
In some embodiments, the first determining unit 120 is further configured to determine, when the first popularization information is viewed within the predetermined time range, the number of viewing times; and determining the memory intensity according to the checking times and the checking time.
In this embodiment, the number of viewing times of the first popularization information within the predetermined time range is determined, and the memory strength of the first popularization information is determined according to the number of viewing times and the viewing time. The memory strength can be expressed in parameters such as memory ratio and/or memory clarity.
In some embodiments, the apparatus further comprises:
a fourth determining unit, configured to determine a number attenuation factor according to the number of views;
the second determining unit 130 is configured to determine the freshness according to the memory strength and the number attenuation factor.
In this embodiment, a fourth determining unit is further included, and a specific hardware structure of the fourth determining unit may correspond to a processor or a processing circuit, similar to the structure of the first determining unit 120, the second determining unit 130, and/or the third determining unit.
In this embodiment, the decay factor is a degree decay factor, and in specific implementations, the decay factor may also be a decay factor of single memory strength that is not related to degree.
The fourth determination unit may calculate the number attenuation factor through the function in the foregoing embodiment, may calculate the freshness of each predetermined dimension, and may further obtain the integrated freshness based on the freshness of each predetermined dimension.
In some embodiments, the second determining unit 130 is configured to determine a memory quality parameter of the user; and determining the memory strength according to the checking times, the checking time and the memory quality parameters.
In this embodiment, the second determining unit 130 may determine the memory strength by looking up the table or the functional relationship with the number of times of viewing, the viewing time, and the memory quality parameter as input parameters.
In some embodiments, the second determining unit 130 is configured to obtain a user attribute of the user; and determining the memory quality parameter according to the user attribute.
In this embodiment, the memory quality parameter is based on the memory quality parameter of the user determines the memory strength of different users, so that the sent popularization information can be screened according to the personal characteristics of the user, accurate pushing is realized, the popularization effect is improved, and the user satisfaction can be improved.
In some embodiments, the second determining unit 130 is configured to determine a single memory strength of a single viewing according to a time difference between the viewing time and a current time; determining the overall memory intensity according to the single memory intensity; determining an attenuation factor within the preset time range according to the checking times; and determining the memory intensity by combining the overall memory intensity and the attenuation factor.
In some embodiments, the second determining unit 130 is specifically configured to calculate the freshness freshsore of the ith predetermined dimension according to the following formulai
Wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is a memory attenuation factor.
In the present embodiment, the freshness can be accurately and easily calculated by using the above functional relationship.
Several specific examples are provided below in connection with the above embodiments:
example one:
the final freshness score FreshScore is formed by fusing freshness degrees of a plurality of preset dimensions, and the scores of all freshness dimensions are fused in a linear weighting mode:
FreshScore＝∑wi×FreshScorei
wherein:
wieach dimension weight satisfies ∑ wi＝1，wi≧ 0, the weight can be specified by human or machine learning.
FreshScorei: freshness value of each dimension, satisfying FreshScorei∈[0，1]
For each dimension, the freshness value is calculated as shown in the following equation:
α: the fitting coefficient is 0.1 as a default value and can be adjusted according to actual needs
Beta: and (4) a value range [0,1], and the user repeatedly receives advertisements with the same dimension and additionally punishs freshness scores.
Calmemory: and the value range [0,1] represents the memory degree of the memory content of the dimension for the user.
Freshness calculation for each dimension
Taking the industry dimension as an example, we calculate the freshness of each advertisement in the candidate advertisement list of the user by using the following process:
for a candidate advertisement of a user (user), assuming that the industry is industry, the industry freshness calculation formula is as follows:
if lastImpressTime is less than 60 x 24 x N, FreshScoreindustry(user, index) ═ 0, otherwise,
wherein:
lastImpressTime: how much time has elapsed since the last view of the business advertisement;
n: regularly set the interval days for the user to pull the advertisements in the same industry;
t: viewing the time;
the time difference between T1 and T2 may be a predetermined prescribed value, for example, 30 days or 15 days or 10 days, etc.
α: the fitting coefficient, default value is 0.1.
The degree attenuation factor is calculated using the following formula:
and the x users receive the viewing times of the advertisements in the same industry.
And then the following formula is used for calculation:
CalMemory(t,impressCount)＝CalTimeFactor(t)×CalCountFactor(impressCount)
if impressCount ≠ 0, then calcountfactor (impressCount) is equal to 1, otherwise calcountfactor (impressCount) is equal to 0;
calmemory (t, impressCount): the calculation method is a calculation function of the memory strength and comprises the following steps:
wherein:
an Ebinghaos forgetting curve is used, and the default value of the memory quality parameter is set to be 60.
The impressCount in calcountfactor (impressCount) is the time t that the user receives the advertisement of the industry for several times, and the impressCount takes the value of 0 or 1 or an integer greater than 1.
The Ebinghaos forgetting curve is a curve for expressing the forgetting rate of the middle-and long-term memory in the memory. This curve was originally developed by the psychologist Hellman Erbingois through his own experiments. In this experiment, Ebinghaos used some meaningless letter combinations. This curve is obtained by memorizing these letter combinations and checking the forgetting rate after a series of time intervals. Therefore, this curve is called Ebinghaos forgetting curve.
The standard form of forgetting curve is typically:
wherein: r represents the memorized strength; s is a memory quality parameter; t is the viewing time and T is the current time. It can be seen from the above formula that the higher the memory strength, the slower the decay of the memorized content with time. The longer the memory time, the lower the content to be memorized.
It is worth noting that: the Ebinghaos forgetting curve can be replaced by other functional forms, not necessarilySuch a form may be approximated by using other functions such as a polynomial or a power function. The attenuation factor may be selected for use according to the actual situation, depending on the degree of protection of the user experience.
The memory strength calculation may also be simplified by using only the time when the content was last viewed. Compared to using the sum of all the "memory contents" that have seen the contents for a period of time in the past.
After the freshness scores of the dimensions are calculated, the global freshness score can be obtained according to the weight of each dimension.
The above is the industry as the predetermined dimension, and when the predetermined dimension is implemented, the predetermined dimension is many, and is not limited to the above industry.
Fig. 4 shows a list of predetermined dimensions and memory contents. The predetermined dimensions include advertisements, advertisers, advertising, industries, materials, and the like. Fig. 4 illustrates an advertisement of the mobile phone a as an example.
In particular implementations, the subject matter of the advertisement may include an advertising service in addition to the advertisement. The advertisement generally corresponds to a physical object, and the advertisement service may be various services that do not involve a physical object, such as a cleaning service, etc.
Example two:
in the present embodiment, an advertisement is taken as promotion information and an industry dimension is taken as an example for explanation. As shown in fig. 3, this example provides a method for sending promotional information, including:
step S1: a request to pull an advertisement;
step S2: acquiring a candidate advertisement list;
step S3: judging whether the candidate advertisement list contains the advertisement with the non-calculated freshness, if not, ending the process, and if so, entering the step S4;
step S4: selecting a candidate advertisement with uncomputed freshness;
step S5: historical data of the advertisement viewed by the user is extracted, wherein the historical data can comprise industries related to the advertisement viewed by the user.
Step S6.1: calculating the attenuation of times;
step S6.2: calculating the memory intensity of the user;
step S7: and calculating the industry freshness.
Example three
As shown in fig. 5, this example provides an alternative hardware configuration diagram of the freshness degree determination apparatus for promotion information, which includes a processor 11, an input/output interface 13 (e.g., a display screen, a touch screen, a speaker), a storage medium 14, and a network interface 12, and the components can be connected and communicated via a system bus 15. Accordingly, the storage media 14 each have stored therein an executable instruction for performing the freshness determination method for promotion information described in the embodiments of the present invention. The hardware modules shown in fig. 5 may be partially implemented, fully implemented or other hardware modules may be implemented as required, the number of each type of hardware module may be one or more, the hardware modules may be implemented in the same geographical location, or distributed in different geographical locations, and may be used to perform at least one of the above-described methods for determining freshness of promotional information shown in fig. 1 or fig. 3.
Example four:
as shown in fig. 6, this example illustrates an advertisement as promotion information, and provides an advertisement promotion system.
The advertisement system includes:
the advertisement request terminal can correspond to the user or the user terminal and can be used for sending an advertisement request;
the access server cluster can be used for accessing the advertisement request terminal;
the retrieval server cluster is connected with the access server cluster and can receive retrieval parameters provided by the access server cluster according to the advertisement request;
and the retrieval server cluster is used for acquiring historical data from the storage server cluster, performing freshness calculation according to the historical data, retrieving advertisements according to the freshness and retrieval parameters, and returning the retrieved advertisements to the advertisement request end through the access server cluster in the manner of advertisement data.
In this example the cluster is a cluster comprising at least a plurality of servers.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (15)
1. A method for determining freshness of promotion information is characterized by comprising the following steps:
acquiring historical data of user viewing promotion information;
determining the memory strength of first promotion information according to the historical data, wherein the first promotion information is related to the second promotion information in a preset dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
according to the memory intensity, determining the freshness of the second promotion information on the preset dimensionality, wherein the freshness is used for indicating the strangeness degree of the second promotion information.
2. The method of claim 1,
the determining the freshness of the second promotion information on the predetermined dimension according to the memory strength includes:
and determining the freshness of the second promotion information on the preset dimension according to the memory intensity and the attenuation factor.
3. The method of claim 2,
the determining the freshness of the second promotion information on the predetermined dimension according to the memory strength and the attenuation factor includes:
the freshness freshsore in the predetermined dimension is calculated according to the following formula,
wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is an attenuation factor.
4. The method according to any one of claims 1 to 3,
the determining the memory strength of the first promotion information according to the historical data comprises:
determining whether the first promotion information is checked within a preset time range or not according to the historical data;
when the first promotion information is not checked in the preset time range, the memory intensity is a designated value;
or,
when the first promotion information is checked in the preset time range, determining checking time and checking times of the first promotion information in the preset time range;
and determining the memory intensity according to the viewing times and the viewing time.
5. The method of claim 4,
the determining the memory strength according to the viewing times and the viewing time comprises:
determining the memory quality parameter of the user;
determining the memory strength according to the checking times, the checking time and the memory quality parameters;
or,
determining the single memory intensity of single viewing according to the time difference between the viewing time and the current time;
determining the overall memory intensity according to the single memory intensity;
determining an attenuation factor within the preset time range according to the checking times;
and determining the memory intensity by combining the overall memory intensity and the attenuation factor.
6. The method of claim 5,
the determining of the memory quality parameter of the user comprises:
acquiring the user attribute of the user;
and determining the memory quality parameter according to the user attribute.
7. The method according to any one of claims 1 to 3,
the method further comprises the following steps:
and determining comprehensive freshness according to the freshness of the plurality of preset dimensions.
8. The method of claim 7,
said determining an integrated freshness based on a plurality of said predetermined dimensions of freshness comprises:
the integrated freshness FreshScore is calculated according to the following formula:
FreshScore＝∑wi×FreshScorei
wherein the FreshScoreiFreshness for the ith said predetermined dimension; said wiThe weight value of the ith preset dimension is obtained; wherein the value of i is an integer not less than 1.
9. A freshness determination device of promotion information, comprising:
the acquisition unit is used for acquiring historical data of the popularization information checked by the user;
the first determining unit is used for determining the memory intensity of first promotion information according to the historical data, wherein the first promotion information is related to the second promotion information in a preset dimension; the second promotion information is information to be promoted currently; the first promotion information is promotion information which is checked by a user; the memory strength is used for indicating the strength of the user for memorizing the first promotion information;
the second determining unit is used for determining the freshness of the second promotion information on the preset dimensionality according to the memory strength, wherein the freshness is used for indicating the strangeness degree of the second promotion information.
10. The apparatus of claim 9,
the second determining unit is configured to determine freshness of the second popularization information in the predetermined dimension according to the memory strength and the attenuation factor.
11. The apparatus of claim 10,
the second determination unit is used for calculating the freshness FreshScore on the preset dimension according to the following formula,
wherein, the alpha is a fitting coefficient, and the Calmemory is the memory strength; the beta is an attenuation factor.
12. The apparatus according to any one of claims 9 to 11,
the first determining unit is used for determining whether the first promotion information is checked in a preset time range according to the historical data; when the first promotion information is not checked in the preset time range, the memory intensity is a designated value; or,
the first determining unit is used for determining the viewing time and the viewing times of viewing the first promotion information in the preset time range when the first promotion information is viewed in the preset time range; and determining the memory intensity according to the viewing times and the viewing time.
13. The apparatus of claim 12,
the second determining unit is used for determining the memory quality parameter of the user; determining the memory strength according to the checking times, the checking time and the memory quality parameters;
or,
the second determining unit is used for determining the single memory strength of single viewing according to the time difference between the viewing time and the current time; determining the overall memory intensity according to the single memory intensity; determining an attenuation factor within the preset time range according to the checking times; and determining the memory intensity by combining the overall memory intensity and the attenuation factor.
14. The apparatus of claim 13,
the second determining unit is used for acquiring the user attribute of the user; and determining the memory quality parameter according to the user attribute.
15. The apparatus according to any one of claims 9 to 11,
the device further comprises:
and the third determining unit is used for determining the comprehensive freshness according to the freshness of the preset dimensions.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710036301.3A CN106777354A (en) | 2017-01-17 | 2017-01-17 | Promotion message freshness determines method and device |
| PCT/CN2017/114633 WO2018133566A1 (en) | 2017-01-17 | 2017-12-05 | Method and device for determining freshness of promotional information, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710036301.3A CN106777354A (en) | 2017-01-17 | 2017-01-17 | Promotion message freshness determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106777354A true CN106777354A (en) | 2017-05-31 |
Family
ID=58944486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710036301.3A Pending CN106777354A (en) | 2017-01-17 | 2017-01-17 | Promotion message freshness determines method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106777354A (en) |
| WO (1) | WO2018133566A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018133566A1 (en) * | 2017-01-17 | 2018-07-26 | 腾讯科技（深圳）有限公司 | Method and device for determining freshness of promotional information, electronic device, and storage medium |
| CN110147803A (en) * | 2018-02-08 | 2019-08-20 | 北大方正集团有限公司 | Customer churn early-warning processing method and device |
| CN110389801A (en) * | 2019-06-05 | 2019-10-29 | 北京梧桐车联科技有限责任公司 | A kind of information processing method, device, mobile unit and storage medium |
| CN111062734A (en) * | 2018-10-16 | 2020-04-24 | 北京字节跳动网络技术有限公司 | Method and device for reordering release information, electronic equipment and readable medium |
| CN112291297A (en) * | 2020-09-04 | 2021-01-29 | 腾讯科技（深圳）有限公司 | Information data processing method, device, storage medium and electronic equipment |
| CN108596711B (en) * | 2018-03-28 | 2021-04-23 | 阿里巴巴（中国）有限公司 | Application recommendation method and device and electronic equipment |
| CN117235380A (en) * | 2023-10-07 | 2023-12-15 | 广州禧闻信息技术有限公司 | Cultural relic digital cloud exhibition whole-network popularity analysis system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003067555A1 (en) * | 2002-02-06 | 2003-08-14 | Mintel Learning Technologies, Inc. | A system and method to optimize human associative memory and to enhance human memory |
| CN102779310A (en) * | 2012-06-25 | 2012-11-14 | 亿赞普(北京)科技有限公司 | Method and system for playing advertisements |
| CN103368992A (en) * | 2012-03-28 | 2013-10-23 | 阿里巴巴集团控股有限公司 | Message push method and device |
| US20130297447A1 (en) * | 2012-02-09 | 2013-11-07 | Panasonic Corporation | Recommended content providing apparatus, recommended content providing program and recommended content providing method |
| CN103853965A (en) * | 2014-03-11 | 2014-06-11 | 广州杰赛科技股份有限公司 | Fingerprint certification-based entertainment system |
| CN105827510A (en) * | 2016-03-31 | 2016-08-03 | 维沃移动通信有限公司 | Push message processing method for mobile terminal, and mobile terminal |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105099866B (en) * | 2014-05-23 | 2019-04-12 | 腾讯科技（北京）有限公司 | The control method and device that data are shown |
| CN105005582B (en) * | 2015-06-17 | 2017-09-15 | 深圳市腾讯计算机系统有限公司 | The recommendation method and device of multimedia messages |
| CN105787061B (en) * | 2016-02-29 | 2019-09-20 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Information-pushing method |
| CN105843902A (en) * | 2016-03-23 | 2016-08-10 | 乐视网信息技术（北京）股份有限公司 | Interaction information sorting method and apparatus |
| CN106777354A (en) * | 2017-01-17 | 2017-05-31 | 腾讯科技（深圳）有限公司 | Promotion message freshness determines method and device |
-
2017
- 2017-01-17 CN CN201710036301.3A patent/CN106777354A/en active Pending
- 2017-12-05 WO PCT/CN2017/114633 patent/WO2018133566A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003067555A1 (en) * | 2002-02-06 | 2003-08-14 | Mintel Learning Technologies, Inc. | A system and method to optimize human associative memory and to enhance human memory |
| US20130297447A1 (en) * | 2012-02-09 | 2013-11-07 | Panasonic Corporation | Recommended content providing apparatus, recommended content providing program and recommended content providing method |
| CN103368992A (en) * | 2012-03-28 | 2013-10-23 | 阿里巴巴集团控股有限公司 | Message push method and device |
| CN102779310A (en) * | 2012-06-25 | 2012-11-14 | 亿赞普(北京)科技有限公司 | Method and system for playing advertisements |
| CN103853965A (en) * | 2014-03-11 | 2014-06-11 | 广州杰赛科技股份有限公司 | Fingerprint certification-based entertainment system |
| CN105827510A (en) * | 2016-03-31 | 2016-08-03 | 维沃移动通信有限公司 | Push message processing method for mobile terminal, and mobile terminal |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018133566A1 (en) * | 2017-01-17 | 2018-07-26 | 腾讯科技（深圳）有限公司 | Method and device for determining freshness of promotional information, electronic device, and storage medium |
| CN110147803A (en) * | 2018-02-08 | 2019-08-20 | 北大方正集团有限公司 | Customer churn early-warning processing method and device |
| CN108596711B (en) * | 2018-03-28 | 2021-04-23 | 阿里巴巴（中国）有限公司 | Application recommendation method and device and electronic equipment |
| CN111062734A (en) * | 2018-10-16 | 2020-04-24 | 北京字节跳动网络技术有限公司 | Method and device for reordering release information, electronic equipment and readable medium |
| CN111062734B (en) * | 2018-10-16 | 2023-08-25 | 北京字节跳动网络技术有限公司 | Method and device for reordering delivery information, electronic equipment and readable medium |
| CN110389801A (en) * | 2019-06-05 | 2019-10-29 | 北京梧桐车联科技有限责任公司 | A kind of information processing method, device, mobile unit and storage medium |
| CN110389801B (en) * | 2019-06-05 | 2022-08-30 | 北京梧桐车联科技有限责任公司 | Information processing method and device, vehicle-mounted equipment and storage medium |
| CN112291297A (en) * | 2020-09-04 | 2021-01-29 | 腾讯科技（深圳）有限公司 | Information data processing method, device, storage medium and electronic equipment |
| CN117235380A (en) * | 2023-10-07 | 2023-12-15 | 广州禧闻信息技术有限公司 | Cultural relic digital cloud exhibition whole-network popularity analysis system |
| CN117235380B (en) * | 2023-10-07 | 2024-05-14 | 广州禧闻信息技术有限公司 | Cultural relic digital cloud exhibition whole-network popularity analysis system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018133566A1 (en) | 2018-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210110428A1 (en) | Click-Through Prediction for Targeted Content | |
| CN106777354A (en) | Promotion message freshness determines method and device | |
| US9589025B2 (en) | Correlated information recommendation | |
| CN105550903B (en) | Target user determination method and device | |
| CN107426328B (en) | Information pushing method and device | |
| CN110298716B (en) | Information pushing method and device | |
| WO2011069073A1 (en) | Measuring advertising effectiveness without control group | |
| JP6154963B2 (en) | Information processing apparatus, information processing method, and information processing program | |
| US10565180B2 (en) | Automated social message stream population | |
| KR101960872B1 (en) | Determining whether to send a call-out to a bidder in an online content auction | |
| CN108540508B (en) | Method, device and equipment for pushing information | |
| JP2018536937A (en) | Push information coarse selection sorting method, device, and computer storage medium | |
| CN105095465B (en) | Information recommendation method, system and device | |
| CN107103028A (en) | A kind of information processing method and device | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN110866040A (en) | User portrait generation method, device and system | |
| US11270334B2 (en) | Systems and methods for generating adjustment(s) for distributing content variations to target entities for performance of an associated action | |
| US20130238974A1 (en) | Online polling methodologies and platforms | |
| JP5813052B2 (en) | Information processing apparatus, method, and program | |
| CN108710656B (en) | Content pushing method and device | |
| CN113704630B (en) | Information pushing method and device, readable storage medium and electronic equipment | |
| CN113158032B (en) | Information pushing method and device | |
| Sakshaug et al. | Recent Advances in Data Integration | |
| CN111784091B (en) | Method and device for processing information | |
| CN111882360A (en) | User group expansion method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |