CN109241417B - User awakening method and device, computing equipment and storage medium - Google Patents
User awakening method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN109241417B CN109241417B CN201810960826.0A CN201810960826A CN109241417B CN 109241417 B CN109241417 B CN 109241417B CN 201810960826 A CN201810960826 A CN 201810960826A CN 109241417 B CN109241417 B CN 109241417B
- Authority
- CN
- China
- Prior art keywords
- behavior
- interest
- user
- wake
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure relates to a user wake method and apparatus, a computing device, and a storage medium. The user awakening method comprises the following steps: for a user to be awakened of an application, analyzing the behavior of the user on the application to obtain an interest tag of the user; and determining wake-up content for pushing to the user to wake up the user according to the interest tag of the user. User wake-up apparatus, computing devices and storage media are also provided. According to the method and the device for obtaining the interest labels of the user to be awakened, the interest labels of the user to be awakened can be obtained according to the massive data of the historical behaviors of the user, and awakening contents conforming to the interest points of the user to be awakened are pushed to the user according to the interest labels of the user to be awakened, so that the awakening success rate is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a user wake-up method and apparatus, a computing device, and a storage medium.
Background
Many service providers now offer their own services to users for use in the form of client applications. After a user installs a client application on a terminal device such as a computer and a mobile phone, various rich service products provided by manufacturers can be used through an interface provided by the client application. However, after a period of use of the service, the user may lose interest in continued use and gradually lose use of the client application. These users who do not use the client application for a long time are often referred to as silent users.
If the user is always silent, this tends to result in loss of the user, which is undesirable for the service provider, and therefore, it is necessary to wake up the silent user.
However, in the prior art, the wake-up mode of the silent user is that all silent users are woken up through a unified activity mode, for example, the client application pushes the same preferential activity to all silent users, and the wake-up effect of the method on the silent users is poor.
Disclosure of Invention
To solve one or more of the above problems, embodiments of the present invention provide a user wake-up method and apparatus, a computing device, and a storage medium.
According to a first aspect of the present disclosure, there is provided a user wake-up method, comprising:
for a user to be awakened of an application, analyzing the behavior of the user on the application to obtain an interest tag of the user; and
and determining wake-up content which is used for pushing the interest tag to the user to wake up the interest tag.
According to an exemplary embodiment, the analyzing the behavior of the user on the application to obtain the interest tag of the user comprises:
acquiring behavior data of the user on the application within a preset time period before the last active behavior;
According to the types of the behavior objects and the types of the behaviors, distributing behavior object labels and behavior type labels for each piece of behavior data, wherein the behavior object labels and the behavior type labels are selected from a preset behavior object label set and a preset behavior type label set;
for behaviors with the same behavior object label and behavior type label, counting the occurrence frequency and occurrence time of the behaviors;
for each assigned behavior object tag, calculating an interest score thereof according to one or more of a behavior type tag, a frequency of occurrence and a time of occurrence of behavior data to which the assigned behavior object tag belongs; and
and selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as the interest labels of the users.
According to an exemplary embodiment, the determining wake-up content for pushing to the user to wake up according to the interest tag of the user includes:
acquiring attribute tags of each content in a content set to compare with interest tags of the users;
determining the content of which the attribute tag is matched with the interest tag from the content set according to a preset matching rule; and
One or more of the matched contents are selected as the wake-up contents.
According to an exemplary embodiment, said selecting one or more of the matched content as the wake-up content comprises at least one of:
selecting one content with highest historical wake-up rate or a plurality of contents with higher historical wake-up rates from the matched contents as the wake-up content;
selecting one content with highest popularity rate from the matched contents or selecting a plurality of contents with higher popularity rates as the awakening content;
one content having the highest weighted sum of the historic wake up rate and the popularity rate or a plurality of contents having the higher weighted sum of the historic wake up rate and the popularity rate are selected from the matched contents as the wake up contents.
According to an exemplary embodiment, for each assigned behavior object tag, the calculating the interest score according to the behavior type tag, the occurrence frequency and the occurrence time of the behavior data, includes:
for each behavior object label, three initial interest scores of the behavior object label are calculated according to the behavior type label, the occurrence frequency and the occurrence time of the behavior;
Multiplying the three initial interest scores by the weight values of the three initial interest scores and summing, and taking the obtained result as a weighted sum interest score of the behavior object label; and
and taking the highest weighted sum interest score among the weighted sum interest scores obtained by the behavior object tag as the interest score of the behavior object tag.
According to an exemplary embodiment, for each assigned behavior object tag, the calculating the interest score according to the behavior type tag, the occurrence frequency and the occurrence time of the behavior data, includes:
and when the behavior type label is a first behavior type label, giving the highest interest score to the behavior object label.
According to an exemplary embodiment, the user wake-up method further comprises:
in the case that more than a predetermined number of the behavior object tags of the user have the highest interest score:
the first interest scores of the behavior object labels with the number larger than the preset number are reapplied according to the sequence of the occurrence time of the behaviors from the new to the old; or alternatively
The second interest scores from high to low are reapplied to the behavior object labels with the number larger than the preset number according to the sequence of the occurrence frequency of the behaviors from high to low; or alternatively
For each of the greater than predetermined number of behavioral object tags, a weighted sum of the first interest score and the second interest score is calculated as its final interest score.
According to a second aspect of the present disclosure, there is provided a user wake-up device comprising:
an interest tag determination module configured to: for a user to be awakened of an application, analyzing the behavior of the user on the application to obtain an interest tag of the user; and
a wake content determination module configured to: and determining wake-up content which is used for pushing the interest tag to the user to wake up the interest tag.
According to an exemplary embodiment, the interest tag determination module further comprises:
a behavioral data acquisition module configured to: acquiring behavior data of the user on the application within a preset time period before the last active behavior;
a label distribution module configured to: according to the types of the behavior objects and the types of the behaviors, distributing behavior object labels and behavior type labels for each piece of behavior data, wherein the behavior object labels and the behavior type labels are selected from a preset behavior object label set and a preset behavior type label set;
A statistics module configured to: for behaviors with the same behavior object label and behavior type label, counting the occurrence frequency and occurrence time of the behaviors;
an interest score calculation module configured to: for each assigned behavior object tag, calculating an interest score thereof according to one or more of a behavior type tag, a frequency of occurrence and a time of occurrence of behavior data to which the assigned behavior object tag belongs; and
an interest tag determination module configured to: and selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as the interest labels of the users.
According to an exemplary embodiment, the wake content determination module further comprises:
an attribute tag acquisition module configured to: acquiring attribute tags of each content in a content set to compare with interest tags of the users;
a matching module configured to: determining the content of which the attribute tag is matched with the interest tag from the content set according to a preset matching rule; and
a selection module configured to: one or more of the matched contents are selected as the wake-up contents.
According to a third aspect of the present disclosure there is provided a computing device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform any of the method embodiments described above.
According to a fourth aspect of the present disclosure there is provided a storage medium having stored thereon a computer program which, when executed by one or more processors, implements any of the method embodiments described above.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
through the embodiments of the disclosure as described above and below, the wake-up content for pushing to the user to wake up the user can be determined for the interest point (interest tag) of the user to be woken up, and the wake-up success rate is higher because the wake-up content is determined for the interest point of the user and has more accurate pertinence. In addition, in some embodiments, the occurrence frequency and the occurrence time of the behavior are counted for the combination of the behavior object tag and the behavior type tag of the behavior data, and the interest score of the behavior object tag is calculated according to the behavior type tag, the occurrence frequency and the occurrence time, so that the interest tag of the user is determined according to the interest score, and the interest tag of the user can be determined more accurately. In addition, in some embodiments, the content with attribute tags matching the interest tags of the user is ranked according to the historical wake-up rate, the popularity rate or the weighted sum of the historical wake-up rate and the popularity rate, so that one or more matched content with highest ranking or higher ranking is selected as wake-up content, and the wake-up rate can be further improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Fig. 1 is a flow chart illustrating a user wake-up method according to an exemplary embodiment.
Fig. 2 is a schematic flow chart of an exemplary specific implementation of step S110 in the user wake-up method according to the corresponding embodiment of fig. 1.
Fig. 3 is a schematic flow chart of an exemplary specific implementation of step S240 in the user wake-up method according to the corresponding embodiment of fig. 2.
Fig. 4 is a schematic flow chart of another exemplary specific implementation of step S240 in the user wake-up method according to the corresponding embodiment of fig. 2.
Fig. 5 is a schematic flow chart of an exemplary specific implementation of step S120 in the user wake-up method according to the corresponding embodiment of fig. 1.
Fig. 6 is a schematic block diagram of a user wake-up device 601, shown according to an exemplary embodiment.
Fig. 7 is a schematic block diagram of an interest tag determination module 610 in the user wake-up device according to the corresponding embodiment of fig. 6.
Fig. 8 is a schematic block diagram of the wake-up content determination module 620 in the user wake-up device according to the corresponding embodiment of fig. 6.
FIG. 9 is a schematic block diagram of a computing device 901, shown in accordance with an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flow chart illustrating a user wake-up method according to an exemplary embodiment. As shown in fig. 1, the example user wake-up method includes the steps of:
s110, for the user to be awakened of the application, analyzing the behavior of the user on the application to obtain the interest tag of the user.
By "user of an application to wake up" is meant a user where no active actions have occurred on the application for a predetermined period. To determine a user to wake up, an example user wake up method may include the steps of: and counting the time when the user does not have active action on the application, and considering the user as the user to be awakened under the condition that the time when the user does not have active action on the application exceeds a preset period. "active behavior" may refer to the behavior of a user logging in on the application, or the behavior of generating behavior data, etc. The predetermined period may be referred to as a "customer churn period" and indicates a time when the user does not perform active actions, for example, the customer churn period may be defined as 80 days, and the user corresponding to the customer churn period needs to wake up, so that it is referred to as a "user to wake up".
Unlike the prior art where the same item activity or activities are pushed to all users to be awakened in a unified manner, the example user awakening method performs customized awakening on users according to characteristics of each user, such as interest tags of the users, so as to improve the awakening rate. Accordingly, in step S110, the user 'S interest tag is obtained by analyzing the user' S behavior on the application, and then the process proceeds to step S120.
S120, determining wake-up content which is used for pushing the interest tag to the user to wake up the interest tag.
The wake-up content for waking up the user may be plural, and the wake-up rate can be greatly improved by determining the content conforming to the interest points of the user according to the interest tags of the user as the wake-up content customized for the user, so that the user's requirement can be met more accurately.
With respect to the specific implementation of "analyze user behavior on application to get user interest tags" described in step S110, an example is given in fig. 2. As shown in fig. 2, step S110 of fig. 1 may include the steps of:
s210, acquiring behavior data of the user on the application in a preset time period before the last active behavior.
Typically, historical behavior data of a user for an application is stored in a database of the application. To analyze the user's interest tags, in this example, behavior data of the user on the application for a predetermined period of time before the last active behavior is obtained from a database. The last active action may be, for example, last logging into the application, last generating action data on the application, etc. The predetermined period of time may be any period of time as long as the data amount of the user behavior data within the period of time is sufficient to determine the interest tags thereof, for example, the predetermined period of time is 6 months.
S220, according to the types of the behavior objects and the types of the behaviors, a behavior object tag and a behavior type tag are allocated to each piece of behavior data, wherein the behavior object tag and the behavior type tag are selected from a preset behavior object tag set and a preset behavior type tag set.
One behavior may generally include two attributes, namely a behavior object and a behavior category (i.e., what behavior), determining points of interest to a user refers to determining which behavior object or objects the user is interested in. To facilitate mining and reuse of behavior data of a user, a set of tags may be generally predetermined for objects and behavior categories of the behavior data. For example, the set of behavioral object tags may include insurance, financial, life, health, etc., representing that the behavioral object of the user is a commodity, activity, advertisement, etc., of the type insurance, financial, life, health, etc. For example, the behavior category tab set may include purchase, participation, click, browse, etc., indicating that the user performed such behavior for the behavior object. For each piece of behavior data, a behavior object tag and a behavior category tag, which are respectively selected from a predetermined behavior object tag set and behavior category tag set, may be assigned thereto. For example, for a piece of behavior data that records that a user purchased an unexpected risk at a certain time, it may be assigned a behavior object tag "insurance" and a behavior category tag "purchase"; for behavior data recorded that a user browses household appliance goods at a certain time, a behavior object tag "life" and a behavior category tag "browse" may be assigned thereto.
S230, for the behaviors having the same behavior object tag and behavior type tag, statistics is made of the occurrence frequency and occurrence time of the behaviors.
After the label is assigned to each piece of behavior data, the occurrence frequency and the occurrence time of the behavior having such a label combination can be counted according to the combination of the behavior object label and the behavior type label. The frequency of occurrence may refer to the total number of times the behavior is generated in the acquired behavior data, or may refer to the number of times the behavior is generated in a unit time (for example, one day, one week, one month). The latest occurrence time of the behavior of the same label combination is defined as the occurrence time of the behavior of the label combination. Through statistics, a table can be obtained, for example, in the form of:
table 1: behavior data statistics table
S240, for each of the assigned behavior object tags, calculating an interest score thereof from one or more of a behavior type tag, a frequency of occurrence, and a time of occurrence of the behavior data to which it belongs.
The interest score of each behavior object tag is related to the corresponding behavior category tag, the occurrence frequency and the occurrence time of the behavior. In one example, the interest score for each type of behavior is buy > engage > click > browse, with higher interest scores for higher frequency of occurrence of the behavior and higher interest scores for closer time of occurrence. The interest score of the behavior object tag may be calculated from one or more of the behavior category tag, the occurrence frequency of the behavior, and the occurrence time. For other specific examples of how to calculate the interest score, please refer to the description with reference to fig. 3-4.
S250, selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as the interest labels of the users.
The higher the interest score, the more interesting the user is to the behavioral object tag, which can be determined as the user's interest tag. One or more interest tags may be determined for each user based on the interest scores.
Fig. 3 is a schematic flow chart of an exemplary specific implementation of step S240 in the user wake-up method according to the corresponding embodiment of fig. 2. As shown in fig. 3, step S240 may include the steps of:
s310, for each behavior object label, three initial interest scores of the behavior object label are calculated according to the behavior type label, the occurrence frequency and the occurrence time of the behavior.
The full score of the interest score can be set to be 100 points, and different interest scores are given to the behavior object labels according to different behavior type labels, occurrence frequency and occurrence time. As described above, it can be predetermined that the interest score of each type of behavior is purchase > participation > click > browsing, and the higher the occurrence frequency of the behavior, the higher the interest score, and the closer the occurrence time, the higher the interest score.
According to the example shown in table 1, the initial interest score shown in table 2 below can be obtained through the process of step S310.
S320, multiplying the three initial interest scores by the weight values of the three initial interest scores and summing the three initial interest scores, and taking the obtained result as the weighted sum interest score of the behavior object label.
The weight values corresponding to the three dimensions of behavior category label, frequency of occurrence of behavior, and time of occurrence can be determined based on statistics of reasonable speculation and/or wake-up rates. For example, in the example shown in table 2, the weight value of the initial interest score corresponding to the behavior type tag is set to 60%, the weight value of the initial interest score corresponding to the occurrence frequency is set to 20%, and the weight value of the initial interest score corresponding to the occurrence time is set to 20%.
Table 2: initial interest score and weighted sum interest score calculation
S330, taking the highest weighted sum interest score among the weighted sum interest scores obtained by the behavior object label as the interest score of the behavior object label.
The number of weighted sum interest scores (including interest scores of 0) available for each behavior object tag is equal to the number of combinations with behavior class tags. As shown in the example of table 2, each behavioral object tag gets four weighted sum interest scores, choosing the highest one as its final interest score, as shown in table 3 below:
Table 3: final interest score results
As can be seen from table 3, the interest scores of the four behavior object tags are arranged in order from high to low: financial > insurance > life > health. In one example, "financial" with highest interest score may be selected as the user's interest tag, and the first two "financial" and "insurance" with higher interest score may be selected as the user's interest tag.
Fig. 4 is a schematic flow chart of another exemplary specific implementation of step S240 in the user wake-up method according to the corresponding embodiment of fig. 2. As shown in fig. 4, step S240 may include the steps of:
s410, when the behavior type tag is the first behavior type tag, the highest interest score is given to the behavior object tag.
That is, whenever a case in which a behavior object tag is combined with a first behavior type tag occurs in behavior data, the behavior object tag is given the highest interest score (for example, 100 points full), regardless of the occurrence frequency and occurrence time thereof.
The first behavior type tag may be one or more behavior type tags in the behavior type tag set, which can more accurately reflect the user interest point. For example, if a user purchases a product, it may be inferred that the user must have a greater interest in that product. Therefore, the behavior category label "purchase" may be used as the first behavior category, and the highest interest score may be given to a behavior object label of a user as long as the user purchases the behavior object. For example, in the example of table 1, where a user purchased two types of products, "insurance" and "financial", the highest interest score of 100 points may be assigned to both the behavioral object tags "insurance" and "financial".
In one example, if only one behavioral object tag is found to have the highest interest score according to the above method, that behavioral object tag may be determined to be the user's interest tag. In another example, if only less than a predetermined number (the predetermined number may be, for example, a number between 2-10) of behavioral object tags are found to have the highest interest score according to the above method, some or all of these behavioral object tags may be determined to be interest tags of the user. In yet another example, if a behavioral object tag greater than a predetermined number (which may be, for example, a number between 2-10) is found to have the highest interest score according to the above method, further processing is performed in step S420.
S420, in a case where more than a predetermined number of the behavior object tags of the user have the highest interest score (for example, in the example shown in table 1, according to S410, both the behavior object tags "insurance" and "financial" have the highest interest score of 100 points, and further processing is required assuming that the predetermined number here is 1), any one of the following (1) to (3) is performed:
(1) And re-assigning the first interest scores from high to low to the behavior object labels with the number larger than the preset number according to the order of the occurrence time of the behaviors from new to old.
Taking table 1 as an example, the behavior data of the combination of the behavior object label "insurance" and "financial" and the first behavior type label "purchase" are the first row and the second row data in table 1, where the occurrence time corresponding to the behavior object label "insurance" is "2018, 3 months, 2 days", and the occurrence time corresponding to the behavior object label "financial" is "2018, 4 months, 14 days". Reassigning the behavior object tags "insurance" and "financial" with the first interest score according to the morning and evening of the respective occurrence time, e.g., the first interest score S of the behavior object tag "insurance I1 Setting 80 points, namely a first interest score S of a behavior object label of financial F1 Set to 90 minutes.
In one example, the first interest score may be taken as the final interest score of the behavioral object tag. Since the first behavior category label is set to correspond to the highest initial interest score, it may be determined that the resulting final interest score of the behavior object label combined with other behavior category labels is lower than all of the first interest scores. Thus, it may be determined that those behavioral object tags having the first interest score are those of the user's overall behavioral object tags that have a higher final interest score. In one example, one or more behavioral object tags with the highest or higher final interest score may be selected from those behavioral object tags with the first interest score as the user's interest tag.
(2) And re-assigning the second interest scores from high to low to the behavior object labels with the number larger than the preset number according to the sequence of the occurrence frequency of the behaviors from high to low.
Taking table 1 as an example, the behavior data of the combination of the behavior object label "insurance" and "financial" and the first behavior type label "purchase" is the first row and the second row data in table 1, where the occurrence frequency corresponding to the behavior object label "insurance" is "2", and the occurrence frequency corresponding to the behavior object label "financial" is "1". Reassigning the behavior object tags "insurance" and "financial" with the second interest score according to the respective occurrence frequency, e.g., the second interest score S of the behavior object tag "insurance I2 Setting 90 points, and setting a second interest score S of the behavior object label financial F2 Set to 80 minutes.
In one example, the second interest score may be taken as the final interest score of the behavioral object tag. Since the first behavior category label is set to correspond to the highest initial interest score, it may be determined that the resulting final interest score of the behavior object label combined with the other behavior category labels is lower than all of the second interest scores. Thus, it may be determined that those behavioral object tags having the second interest score are those of the user's all behavioral object tags that have a higher final interest score. In one example, one or more behavioral object tags with the highest or higher final interest score may be selected from those behavioral object tags with the second interest score as the user's interest tag.
(3) For each of the greater than predetermined number of behavioral object tags, a weighted sum of the first interest score and the second interest score is calculated as its final interest score.
Alternatively, a weighted sum of the first interest score and the second interest score may be calculated as the final interest scoreDividing into two parts. The respective weight values of the first interest score and the second interest score may be determined based on a reasonably inferred and/or statistical wake-up rate, e.g., if the more recent the occurrence time is perceived to be reflecting the user's point of interest and the less frequent occurrence is not as important as the former, the weight value of the first interest score may be set to be greater than the weight value of the second interest score. For example, the weight values of the first interest score and the second interest score may be set to 70% and 30%, respectively. Taking the example of Table 1 as an example, the final interest score for the behavior object tag "insurance" is: s is S I ＝S I1 *70％+S I2 *30% = 83, the final interest score of the behavioral object tag "financial" is: s is S F ＝S F1 *70％+S F2 *30% = 87. It can be seen that the final interest score of the behavior object tag "financial" is greater than the final interest score of the behavior object tag "insurance".
Through the embodiments of fig. 2-4, the user's points of interest may be more accurately determined, thereby more accurately matching the wake-up content.
Fig. 5 is a schematic flow chart of an exemplary specific implementation of step S120 in the user wake-up method according to the corresponding embodiment of fig. 1. As shown in fig. 5, step S120 may include the steps of:
s510, acquiring attribute tags of each content in the content set to compare with interest tags of the users.
By "content" is meant items that may be pushed to a user to wake up the user (i.e., cause the user to resume active behavior on the application), such as advertisements for merchandise and/or purchase links, offers, rewards, and the like. The content collection includes one or more content, each content has an attribute tag identifying an attribute or keyword of the content, and the attribute tag may include a tag identifying an object to which the content is directed, such as "insurance," "financial," "life," "health," or "fund," "unexpected danger," "household," etc., and may include a tag representing other attributes of the content, such as "rewards," "offers," "cashback," etc. Content collection data including an attribute tag for each content may be obtained from a database and then the attribute tags compared to interest tags for the user.
And S520, determining the content with the attribute label matched with the interest label from the content set according to a preset matching rule.
The purpose of comparing the attribute tag with the interest tag is to see whether the attribute tag and the interest tag are matched, if the attribute tag and the interest tag meet a preset matching rule, the attribute tag and the interest tag are judged to be matched, otherwise, the attribute tag and the interest tag are not matched. The predetermined matching rules may include one or more of the following (1) - (3):
(1) And if the attribute tag is identical to the interest tag, judging that the attribute tag is matched with the interest tag.
For example, if "insurance" is included in the user's interest tag and "insurance" is also included in the attribute tag of the content, it is determined that the two match.
(2) If the attribute tag and the interest tag belong to the same or similar category, the attribute tag and the interest tag are judged to be matched.
For example, if the user's interest tag includes "insurance", and the attribute tag of the content includes "unexpected risk", it is determined that the "unexpected risk" belongs to the "insurance" category, and it is determined that the two match.
(3) If the attribute tag and the interest tag are found to be matched items in the matching list by searching a preset matching list, the attribute tag and the interest tag are judged to be matched.
The preset matching list may be a list that is sorted and pre-saved according to experience, historical matching results, and/or reasoning, in which it is listed which attribute tags match which interest tags.
And S530, selecting one or more pieces of matched content as the awakening content.
The content of which the attribute tags match the user's interest tags may be more than one, from which one or more pushes may be selected for the user. In one example, one content having the highest historical wake up rate or a plurality of contents having higher historical wake up rates are selected from the matched contents as the wake up content. In another example, one content with the highest popularity rate is selected from the matched contents or a plurality of contents with higher popularity rates are selected as the wake-up contents. In yet another example, one content having the highest weighted sum of the historical wake up rate and the popularity rate or a plurality of contents having the higher weighted sum of the historical wake up rate and the popularity rate are selected as wake up contents from the matched contents.
After determining the wake-up content for the user to be woken up, the wake-up content needs to be pushed to the user to be woken up. In one example, the application pushes to the user through a contact (e.g., cell phone, mailbox, etc.) registered at the time of user registration by obtaining the contact, such as by automatically sending mail, text messages, weChat, etc. In another example, the application obtains a telephone contact of the user, and sends the user information including the telephone contact and the determined wake-up content to the selected active salesman, and sends a push task to the active salesman, and then the active salesman calls the user through the telephone contact to push the determined wake-up content, informing the user to log in the application for learning, purchasing or participating. In selecting an activated salesman, the activated salesman most familiar with the wake content (e.g., wake content is a promotional item, and the activated salesman selected is the promoter of the item), the activated salesman with the highest wake rate or the most popular activated salesman, etc. may be selected.
The foregoing is various embodiments of a user wake-up method, and in accordance with another aspect of the present disclosure, apparatus embodiments are also provided. Fig. 6 shows a schematic block diagram of a user wake-up device 601 according to an exemplary embodiment. The user wake-up device 601 is used to perform embodiments of the user wake-up method as described above, wherein the application is run on the user wake-up device 601. As shown in the example of fig. 6, the user wake-up device 601 may include an interest tag determination module 610 and a wake-up content determination module 620, wherein:
the interest tag determination module 610 is configured to: for a user to be awakened of the application, analyzing the behavior of the user on the application to obtain an interest tag of the user; and
the wake content determination module 620 is configured to: and determining wake-up content for pushing to the user to wake up the user according to the interest tag of the user.
Fig. 7 shows a schematic block diagram of the fun tag determination module 610 in the user wake-up device of the embodiment of fig. 6. As shown in fig. 7, the interest tag determination module 610 may further include:
a behavioral data acquisition module 710 configured to: acquiring behavior data of a user on an application in a preset time period before the last active behavior;
A tag assignment module 720 configured to: according to the types of the behavior objects and the types of the behaviors, distributing behavior object labels and behavior type labels for each piece of behavior data, wherein the behavior object labels and the behavior type labels are selected from a preset behavior object label set and a preset behavior type label set;
a statistics module 730 configured to: for behaviors with the same behavior object label and behavior type label, counting the occurrence frequency and occurrence time of the behaviors;
an interest score calculation module 740 configured to: for each assigned behavior object tag, calculating an interest score thereof according to one or more of a behavior type tag, a frequency of occurrence and a time of occurrence of behavior data to which the assigned behavior object tag belongs; and
an interest tag determination module 750 configured to: and selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as interest labels of users.
Fig. 8 shows a schematic block diagram of the wake-up content determination module 620 in the user wake-up device of the embodiment of fig. 6. As shown in fig. 8, the wake content determination module 620 may further include:
An attribute tag acquisition module 810 configured to: acquiring attribute tags of each content in a content set to compare with interest tags of the users;
a matching module 820 configured to: determining the content of which the attribute tag is matched with the interest tag from the content set according to a preset matching rule; and
a selection module 830 configured to: one or more of the matched contents are selected as the wake-up contents.
The implementation process of the functions and roles of each unit/module in the above device and the relevant details are specifically detailed in the implementation process of the corresponding steps in the above user wake-up method, which are not repeated here.
The user wake-up means in the above embodiments may be implemented by hardware, software, firmware or a combination thereof, and may be implemented as a single apparatus or as a logic integrated system in which constituent units/modules are dispersed in one or more computing devices and perform corresponding functions, respectively.
The units/modules constituting the user wake-up device in the above embodiments are divided according to logic functions, they may be re-divided according to logic functions, and the data processing user wake-up device may be implemented by more or fewer units/modules, for example. These constituent units/modules may be implemented by hardware, software, firmware or a combination thereof, and they may be separate independent components or may be integrated units/modules where a plurality of components are combined to perform corresponding logic functions. The means for hardware, software, firmware, or a combination thereof may include: separate hardware components, functional modules implemented by programming, functional modules implemented by programmable logic devices, or the like, or a combination thereof.
According to one exemplary embodiment, the user wake-up device may be implemented as a computing device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform any of the embodiments of the user wake-up method as described above, i.e. the computer program, when executed by the processor, causes the computing device to perform the functions performed by the constituent elements/modules of the embodiments of the user wake-up device as described above. The computing device may be a server or a terminal device. The application is deployed/run on the computing device, and a user can directly use the service provided by the application through the computing device, or can use the service provided by the application through a terminal device (for example, a mobile phone, a computer, a tablet computer, etc.) installed with a client APP of the application and communicating with the computing device through a network.
The processor described in the above embodiments may refer to a single processing unit, such as a central processing unit CPU, or may be a distributed processor system comprising a plurality of discrete processing units.
The memory described in the above embodiments may include one or more memories, which may be internal memory of the computing device, such as various memories, transient or non-transient, or external storage connected to the computing device through a memory interface.
Fig. 9 illustrates a schematic block diagram of one exemplary embodiment of such a computing device 901. As shown in fig. 9, a computing device 901 may include: processor 910, communication interface 920, memory 930, and bus 940. The memory 930 stores a computer program executable by the processor 910. The processor 910, when executing the computer program, implements the functions of the user wake-up method and the user wake-up device in the above embodiments. The number of memories 930 and processors 910, respectively, may be one or more. The communication interface 920 is used for communication between the processor 910 and external devices.
The processor 910 may be a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various exemplary flow steps, functional units/modules and/or circuits described in connection with this disclosure. The processor may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, digital signal processors, or the like.
Memory 930 may include volatile memory and/or nonvolatile memory such as nonvolatile dynamic random access memory, phase change random access memory, magnetoresistive random access memory, magnetic disk memory, electrically erasable programmable read only memory, flash memory devices, semiconductor devices (e.g., solid state disks), and the like. Memory 930 may also optionally be an external remote storage device.
Bus 940 may be an industry standard architecture (ISA, industry Standard Architecture) bus, a peripheral component interconnect (PCI, peripheral Component) bus, or an extended industry standard architecture (EISA, extended Industry Standard Component) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus. Alternatively, if the memory 930, the processor 910, and the communication interface 920 are integrated on a single chip, the memory 930, the processor 910, and the communication interface 920 may communicate with each other through internal interfaces.
The above method and apparatus embodiments may also be implemented in the form of a computer program, stored on a storage medium, and distributed. Thus, according to another aspect of the present disclosure, there is also provided a storage medium having stored thereon a computer program executable by a processor, which when executed by the processor, implements any of the method and apparatus embodiments described above.
The storage medium may be any tangible device that can hold and store instructions that can be used by an instruction execution device. For example, it may be, but is not limited to being, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the storage medium include: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing.
The computer program/computer instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions described in this disclosure may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. It will be apparent to those skilled in the art that the above embodiments may be used alone or in combination with one another as desired. In addition, for the device embodiment, since it corresponds to the method embodiment, description is relatively simple, and reference should be made to the description of the corresponding part of the method embodiment for relevant points.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. A method of waking up a user, comprising:
for a user to be awakened of an application, acquiring behavior data of the user on the application in a preset time period before the last active behavior;
According to the types of the behavior objects and the types of the behaviors, distributing behavior object labels and behavior type labels for each piece of behavior data, wherein the behavior object labels and the behavior type labels are selected from a preset behavior object label set and a preset behavior type label set;
for behaviors with the same behavior object label and behavior type label, counting the occurrence frequency and occurrence time of the behaviors;
for each distributed behavior object label, calculating interest scores according to the behavior type label, the occurrence frequency and the occurrence time of behaviors of the behavior data to which the distributed behavior object label belongs;
selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as the interest labels of the users;
determining wake-up content for pushing to the user to wake up the user according to the interest tag of the user;
wherein, for each assigned behavior object tag, calculating an interest score according to a behavior type tag, a frequency of occurrence and a time of occurrence of the behavior data to which the assigned behavior object tag belongs, including:
for each behavior object label, three initial interest scores of the behavior object label are calculated according to the behavior type label, the occurrence frequency of the behavior and the occurrence time, wherein the initial interest scores are higher when the occurrence time is closer;
Multiplying the three initial interest scores by the weight values of the three initial interest scores and summing, and taking the obtained result as a weighted sum interest score of the behavior object label;
and taking the highest weighted sum interest score among the weighted sum interest scores obtained by the behavior object tag as the interest score of the behavior object tag.
2. The user wake-up method of any of claims 1, wherein the determining wake-up content for pushing to the user to wake up it based on the user's interest tag comprises:
acquiring attribute tags of each content in a content set to compare with interest tags of the users;
determining the content of which the attribute tag is matched with the interest tag from the content set according to a preset matching rule; and
one or more of the matched contents are selected as the wake-up contents.
3. The user wake-up method of claim 2, wherein the selecting one or more of the matched content as the wake-up content comprises at least one of:
selecting one content with highest historical wake-up rate or a plurality of contents with higher historical wake-up rates from the matched contents as the wake-up content;
Selecting one content with highest popularity rate from the matched contents or selecting a plurality of contents with higher popularity rates as the awakening content;
one content having the highest weighted sum of the historic wake up rate and the popularity rate or a plurality of contents having the higher weighted sum of the historic wake up rate and the popularity rate are selected from the matched contents as the wake up contents.
4. The user wake-up method of claim 1, wherein for each of the assigned behavior object tags, calculating an interest score thereof based on a behavior category tag of behavior data to which it belongs, an occurrence frequency of the behavior, and an occurrence time, comprises:
and when the behavior type label is a first behavior type label, giving the highest interest score to the behavior object label.
5. The user wake-up method of claim 4, further comprising:
in the case that more than a predetermined number of the behavior object tags of the user have the highest interest score:
the first interest scores of the behavior object labels with the number larger than the preset number are reapplied according to the sequence of the occurrence time of the behaviors from the new to the old; or alternatively
The second interest scores from high to low are reapplied to the behavior object labels with the number larger than the preset number according to the sequence of the occurrence frequency of the behaviors from high to low; or alternatively
For each of the greater than predetermined number of behavioral object tags, a weighted sum of the first interest score and the second interest score is calculated as its final interest score.
6. A user wake-up device, comprising:
an interest tag determination module configured to: for a user to be awakened of an application, acquiring behavior data of the user on the application in a preset time period before the last active behavior; according to the types of the behavior objects and the types of the behaviors, distributing behavior object labels and behavior type labels for each piece of behavior data, wherein the behavior object labels and the behavior type labels are selected from a preset behavior object label set and a preset behavior type label set; for behaviors with the same behavior object label and behavior type label, counting the occurrence frequency and occurrence time of the behaviors; for each distributed behavior object label, calculating interest scores according to the behavior type label, the occurrence frequency and the occurrence time of behaviors of the behavior data to which the distributed behavior object label belongs; selecting one behavior object label with highest interest score from the distributed behavior object labels or selecting a plurality of behavior object labels with higher interest scores as the interest labels of the users; wherein, for each assigned behavior object tag, calculating an interest score according to a behavior type tag, a frequency of occurrence and a time of occurrence of the behavior data to which the assigned behavior object tag belongs, including: for each behavior object label, three initial interest scores of the behavior object label are calculated according to the behavior type label, the occurrence frequency of the behavior and the occurrence time, wherein the initial interest scores are higher when the occurrence time is closer; multiplying the three initial interest scores by the weight values of the three initial interest scores and summing, and taking the obtained result as a weighted sum interest score of the behavior object label; taking the highest weighted sum interest score among the weighted sum interest scores obtained by the behavior object tag as the interest score of the behavior object tag;
A wake content determination module configured to: and determining wake-up content which is used for pushing the interest tag to the user to wake up the interest tag.
7. A computing device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the method of any of claims 1 to 5.
8. A storage medium having stored thereon a computer program which, when executed by one or more processors, implements the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810960826.0A CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810960826.0A CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109241417A CN109241417A (en) | 2019-01-18 |
| CN109241417B true CN109241417B (en) | 2023-07-25 |
Family
ID=65068364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810960826.0A Active CN109241417B (en) | 2018-08-22 | 2018-08-22 | User awakening method and device, computing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241417B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144935A (en) * | 2019-12-17 | 2020-05-12 | 武汉海云健康科技股份有限公司 | Big data-based sleep member awakening method and system, server and medium |
| CN112950266B (en) * | 2021-02-26 | 2024-05-03 | 北京达佳互联信息技术有限公司 | Media resource display method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103378976A (en) * | 2012-04-19 | 2013-10-30 | 深圳市快播科技有限公司 | Method of waking up sound asleep user and system |
| CN104933134A (en) * | 2015-06-12 | 2015-09-23 | 海信集团有限公司 | User feature analysis method and user feature analysis device |
| CN105718184A (en) * | 2014-12-05 | 2016-06-29 | 北京搜狗科技发展有限公司 | Data processing method and apparatus |
| CN106055617A (en) * | 2016-05-26 | 2016-10-26 | 乐视控股（北京）有限公司 | Data pushing method and device |
-
2018
- 2018-08-22 CN CN201810960826.0A patent/CN109241417B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103378976A (en) * | 2012-04-19 | 2013-10-30 | 深圳市快播科技有限公司 | Method of waking up sound asleep user and system |
| CN105718184A (en) * | 2014-12-05 | 2016-06-29 | 北京搜狗科技发展有限公司 | Data processing method and apparatus |
| CN104933134A (en) * | 2015-06-12 | 2015-09-23 | 海信集团有限公司 | User feature analysis method and user feature analysis device |
| CN106055617A (en) * | 2016-05-26 | 2016-10-26 | 乐视控股（北京）有限公司 | Data pushing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109241417A (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11587116B2 (en) | Predictive recommendation system | |
| CN107369075B (en) | Commodity display method and device and electronic equipment | |
| US11556877B2 (en) | Generation of engagement and support recommendations for content creators | |
| US20160379268A1 (en) | User behavior data analysis method and device | |
| CN106940705A (en) | A kind of method and apparatus for being used to build user's portrait | |
| CN109299356B (en) | Activity recommendation method and device based on big data, electronic equipment and storage medium | |
| CN110392155B (en) | Notification message display and processing method, device and equipment | |
| US11887156B2 (en) | Dynamically varying remarketing based on evolving user interests | |
| CA2822077A1 (en) | Method and apparatus for segmenting a customer base and interacting with customers of the segmented customer base | |
| US20160232548A1 (en) | Adaptive pricing analytics | |
| CN111242709A (en) | Message pushing method and device, equipment and storage medium thereof | |
| US9460163B1 (en) | Configurable extractions in social media | |
| CN110751509A (en) | Display method and device for application popup window and electronic equipment | |
| CN109241417B (en) | User awakening method and device, computing equipment and storage medium | |
| CN108694174B (en) | Content delivery data analysis method and device | |
| CN110764667B (en) | Popup window display method and device and electronic equipment | |
| CN108710656B (en) | Content pushing method and device | |
| US20190087852A1 (en) | Re-messaging with alternative content items in an online remarketing campaign | |
| CN113434063A (en) | Information display method, device and equipment | |
| CN113743968A (en) | Information delivery method, device and equipment | |
| CN115809889A (en) | Intelligent passenger group screening method, system, medium and equipment based on marketing effect | |
| CN114119168A (en) | Information pushing method and device | |
| EP3449454A1 (en) | Emphasizing communication based on past interaction related to promoted items | |
| CN110780941A (en) | Application pendant display method and device and electronic equipment | |
| CN111241382A (en) | Data processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |