CN111814034A - Information processing method, information processing apparatus, storage medium, and electronic device - Google Patents
Information processing method, information processing apparatus, storage medium, and electronic device Download PDFInfo
- Publication number
- CN111814034A CN111814034A CN201910600799.0A CN201910600799A CN111814034A CN 111814034 A CN111814034 A CN 111814034A CN 201910600799 A CN201910600799 A CN 201910600799A CN 111814034 A CN111814034 A CN 111814034A
- Authority
- CN
- China
- Prior art keywords
- recommended
- historical
- push
- document
- case
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses an information processing method, an information processing device, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring a recommended case library, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one tag; selecting at least one recommended case from a recommended case library based on the user characteristics of the target user group of the promotion activity, wherein the label of the recommended case is associated with the user characteristics of the target user group; and generating a push message based on the activity information of the promotion activity and the recommended pattern, and pushing the push message to the target user group. The information processing method selects the pushed documents from the recommended documents library based on the user characteristics of the target user groups and the labels of the pushed documents, generates and sends the pushed information to the target user groups based on the selected pushed documents and the activity information of the promotion activities, can push more appropriate pushed documents to different target user groups, realizes personalized recommendation, and is beneficial to improving the promotion effect of the promotion activities.
Description
Technical Field
The present disclosure relates to the field of information processing technologies, and in particular, to an information processing method and apparatus, a storage medium, and an electronic device.
Background
Currently, most users (drivers and passengers) take a car using a car calling APP on mobile terminals. In the operation process of APP, the purposes of attracting new customers, increasing user viscosity and the like can be achieved through different popularization activities. In the promotion activity, the document can show the creative strategy of the activity in the form of characters. The appropriate file can lead the user to generate interest in the promotion activities, and lead more users to participate in the promotion activities. In the process of pushing promotional activities to users, designing a case for each promotional activity can take a large amount of labor. And users in different regions and in different age groups have different understandings and feelings about the case. If the same file is pushed to all users, only part of the users will be interested in promoting the activity.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide an information processing method, an information processing apparatus, a storage medium, and an electronic device, so as to solve the following problems in the prior art: if the same file is pushed to all users, only part of the users will be interested in promoting the activity.
In one aspect, an embodiment of the present disclosure provides an information processing method, including:
acquiring a recommended case library, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one tag;
selecting at least one recommended case from the recommended case library based on the user characteristics of a target user group of the promotion activity, wherein the label of the recommended case is associated with the user characteristics of the target user group;
and generating a push message based on the activity information of the promotion activity and the recommended file, and pushing the push message to the target user group.
In some embodiments, the obtaining a library of recommended documents comprises:
acquiring a historical recommended case and push feedback data of the historical recommended case;
judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not;
if yes, adding at least one label for the historical recommended file, and adding the historical recommended file to the recommended file library.
In some embodiments, the determining whether the push feedback data of the historical recommended document meets a preset recommendation condition includes:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
In some embodiments, the push feedback data includes click-through rate data and/or conversion rate data.
In some embodiments, the selecting at least one of the recommended documents from the library of recommended documents based on the user characteristics of the target user group for the promotional activity, the tag of the recommended document being associated with the user characteristics of the target user group comprises:
determining user characteristics of the target user group;
matching the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm;
and acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
In some embodiments, the obtaining at least one of the tags matching the user characteristics and at least one of the recommended documents corresponding to the tags includes:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
In some embodiments, the tag comprises at least one of the following types:
user tags, function tags, theme tags.
In another aspect, an embodiment of the present disclosure provides an information processing apparatus, including:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a recommendation document library which comprises a plurality of recommendation documents with at least one label;
the selection module is used for selecting at least one recommended case from the recommended case library based on the user characteristics of a target user group of the promotion activity, and the label of the recommended case is associated with the user characteristics of the target user group;
and the pushing module is used for generating a pushing message based on the activity information of the promotion activity and the recommended document and pushing the pushing message to the target user group.
In some embodiments, the obtaining module comprises:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a historical recommended case and push feedback data of the historical recommended case;
the judging unit is used for judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not;
and the adding unit is used for adding at least one label to the historical recommended file and adding the historical recommended file to the recommended file library under the condition that the push feedback data meet the preset recommendation condition.
In some embodiments, the determining unit is specifically configured to:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
In some embodiments, the push feedback data includes click-through rate data and/or conversion rate data.
In some embodiments, the selecting module comprises:
a determining unit, configured to determine a user characteristic of the target user group;
a matching unit, configured to match the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm;
and the second acquisition unit is used for acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
In some embodiments, the second obtaining unit is specifically configured to:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
In some embodiments, the tag comprises at least one of the following types:
user tags, function tags, theme tags.
In another aspect, the present disclosure provides a storage medium storing a computer program, which when executed by a processor implements the steps of the method described above.
In another aspect, the disclosed embodiments provide an electronic device, which at least includes a memory and a processor, where the memory stores a computer program thereon, and the processor implements the steps of the method when executing the computer program on the memory.
According to the method and the device for recommending the files, the pushed files are selected from the recommended file library based on the user characteristics of the target user group and the labels of the pushed files, the pushed information is generated based on the selected pushed files and the activity information of the popularization activity, the pushed information is sent to the target user group, more appropriate pushed files can be pushed to different target user groups, personalized recommendation is achieved, users of the target user group can be more easily motivated, and the popularization effect of the popularization activity is improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present disclosure, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an information processing method provided by an embodiment of the present disclosure;
fig. 2 is a flowchart of acquiring a recommended document library in the information processing method according to the embodiment of the present disclosure;
fig. 3 is a flowchart of selecting a recommended document from the recommended document library in the information processing method according to the embodiment of the present disclosure;
fig. 4 is a block diagram of an information processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a block diagram of an acquisition module of an information processing apparatus according to an embodiment of the present disclosure;
fig. 6 is a block diagram of a selection module of an information processing apparatus according to an embodiment of the present disclosure;
fig. 7 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Reference numerals:
10-an acquisition module; 11-a first acquisition unit; 12-a determination unit; 13-an addition unit; 20-selecting a module; 21-a determination unit; 22-a matching unit; 23-a second acquisition unit; 30-pushing module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described below clearly and completely with reference to the accompanying drawings of the embodiments of the present disclosure. It is to be understood that the described embodiments are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the disclosure without any inventive step, are within the scope of protection of the disclosure.
Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
To maintain the following description of the embodiments of the present disclosure clear and concise, a detailed description of known functions and known components have been omitted from the present disclosure.
Fig. 1 is a flowchart of an information processing method according to an embodiment of the present disclosure, and referring to fig. 1, the information processing method specifically includes the following steps:
s100, a recommended case library is obtained, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one label.
Wherein, the recommended case library comprises a plurality of pre-selected push cases. The pushed documents in the recommended documents library can be high-quality pushed documents selected from historical pushed documents, and can also be new pushed documents written by editors. The push file is written for promoting brands, products, services or software and other promotion activities and is used for playing the word content of the target user group. Like 'car robbing just like a stick, people can run all things with high-heeled shoes and drip out from the beginning of a trip'. The tags can be keywords for identifying the pushed documents, one pushed document can only have one tag, and also can have a plurality of tags, and the plurality of tags can identify the pushed documents from a plurality of dimensions. For example, a push document may be labeled with "young people", "trend", etc. The obtaining of the recommended case library can be used for constructing the recommended case library, calling the recommended case library from a preset storage area, and obtaining the updated recommended case library so that the recommended case library is in a state to be inquired, and further, the recommended case can be selected at any time.
S200, based on the user characteristics of the target user group of the promotion activity, selecting at least one recommended case from the recommended case library, wherein the label of the recommended case is associated with the user characteristics of the target user group.
The promotion activity refers to that an enterprise, an individual or an organization promotes the content of brands, products, services or software and the like of the target users through creative activities. The promotion activities typically make a promotion activity plan, which typically includes user characteristics and activity information of the target user group. The target user group refers to a target group targeted by promotion activities, such as young people, middle aged people, old people, students, workers, office workers, and the like. For example, the promotional activity may be an activity that pushes the vehicle platform to a young person, and the user characteristic of the target user group is a young person.
The matched push file can be selected from the recommendation file library by matching the user characteristics and the labels of the target user group, the selected result can be one push file or a plurality of push files, and the specific number of the selected push files is not limited. For example, taking the example of pushing the car-playing platform to young people or old people, the user characteristics of "young people" or "old people" are matched with the tags in the recommended document library, and if one pushed document is marked with the "young people" tag, the pushed document is matched and acquired. For example, "live in the same alleys in villages in cities, it takes several kilometers to drive all vehicles, and the people can drip from the beginning of the trip. The calculation amount and the matching difficulty when the user characteristics of the target user group are matched with the pushed documents can be simplified by setting the tags, so that the aim of quickly selecting the pushed documents suitable for being recommended to the target user group can be fulfilled through quick matching of the user characteristics and the tags, and the user characteristics do not need to be matched with the whole pushed documents.
And S300, generating a push message based on the activity information of the promotion activity and the recommended pattern, and pushing the push message to the target user group.
The activity information may include activity subject, content, time and place, etc. The push documents are text contents capable of playing originality of the target user, but the push documents usually do not include activity information of specific promotion activities. Therefore, after the push document matching the target user group is selected, the activity information and the push document need to be combined to generate a complete push message for pushing to the target user. That is, the push message includes activity information related to the promotion activity and creative text content for motivating the target user, so that the target user is allowed to accept the promotion activity while the target user is being exercised. Taking a historical popularization activity as an example, the popularization activity is the activity of popularizing the splicing and dripping wind-mill, crossing the city and returning to home for a year in the course of the year, and then the activity information comprises the splicing and dripping wind-mill, crossing the city and returning to home for a year. The obtained push documents comprise 'door opening, namely home door', and the activity information is combined with the push documents to form complete push information 'door opening, namely home door'; the wind mill is used for splicing drops and getting home for years across cities. In actual application, the push information may be further provided with picture information. Of course, the event information may be a service provider name, discount information, or the like, or may be only one trademark capable of identifying a service or a product.
By adopting the information processing method, the pushed document is selected from the recommended document library based on the user characteristics of the target user group and the label of the pushed document, the pushed information is generated based on the selected pushed document and the activity information of the promotion activity, and then the pushed information is sent to the target user group, so that more appropriate pushed documents can be pushed to different target user groups, personalized recommendation is realized, users of the target user group can be more easily motivated, and the promotion effect of the promotion activity is further improved.
As shown in fig. 2, in some embodiments, the obtaining of the recommended document library specifically includes the following steps:
s101, obtaining a historical recommendation file and push feedback data of the historical recommendation file.
The historical recommendation documents are the recommendation documents pushed to the user. The push feedback data comprises result data of the promotion activities fed back after the historical push documents participate in the promotion activities, such as click rate, conversion rate, complaint information and other related data. The push feedback data can reflect the push effect of the historical push file.
S102, judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions.
The preset recommendation condition is a condition representing that the historical recommendation document is a high-quality recommendation document, and various methods can be used for judging whether the historical recommendation document is a high-quality recommendation document in the specific implementation process.
In one case, the determination may be based on the click rate of the historical recommendation documents. If the click rate of a historical pushed document is high, the pushed document can motivate the user, has enough attraction and is a high-quality pushed document. In this case, it is determined whether the push feedback data of the historical recommended document meets a preset recommendation condition, that is, it is determined whether the click rate of the historical pushed document is greater than a preset click rate threshold. The preset click rate threshold is used for representing whether the pushed document is a high-quality pushed document or not through the click rate, and if the click rate of the historical pushed document is greater than the preset click rate threshold, the historical pushed document is the high-quality pushed document and has the values of collection and re-pushing; if the click rate of the historical pushed document is not greater than the preset click rate threshold, the click rate of the historical pushed document is low, the user cannot be attracted to click and check the historical pushed document, and the historical pushed document is judged to be not a high-quality pushed document preliminarily.
In another case, whether the historical push documents are premium push documents may also be determined based on the conversion rate of the historical push documents. The conversion rate is the ratio of the number of target users who receive the historical pushed document and receive the promotion activities corresponding to the historical pushed document to the number of target users who receive the historical pushed document. If the user accepts the promotion activity, the historical pushed case not only attracts the user to click the historical pushed case, but also further enables the user to accept the corresponding promotion activity, and the final purpose of the promotion activity is achieved. Therefore, whether the historical push documents are high-quality push documents can be effectively judged based on the conversion rate. In this case, it is determined whether the historical recommended document meets a preset recommendation condition, that is, it is determined whether the conversion rate of the historical pushed document is greater than a preset conversion rate threshold. And when the conversion rate information of a historical pushed file is judged to be larger than the preset conversion rate threshold value, preliminarily judging that the historical pushed file is a high-quality pushed file and meets the preset recommendation condition. If the conversion rate of a historical pushed case is not greater than the preset conversion rate threshold value, the historical pushed case is preliminarily judged to be not a high-quality pushed case and not accord with the preset recommendation condition.
It should be noted that, it may also be determined whether the historical pushed document is a high-quality pushed document based on the click rate and the conversion rate, that is, it is determined that the push feedback data of the historical pushed document meets the preset recommendation condition only when the click rate of the historical pushed document meets the preset click rate threshold and the conversion rate meets the preset conversion rate threshold. Alternatively, it may be determined whether the historical pushed document is a high-quality pushed document based on other determination conditions, or the worker may manually determine whether the historical pushed document is a high-quality pushed document.
S103, if yes, adding at least one label to the historical recommended file, and adding the historical recommended file to the recommended file library.
And when the pushing feedback data of a historical pushing case is judged to meet the preset recommendation condition, preliminarily judging that the historical pushing case is a high-quality pushing case, and adding a label to the historical pushing case. In the implementation process, labels can be added to the history push file from multiple dimensions, for example, the labels can comprise a user label, a function label and a theme label. Wherein, the user label is used for marking the user group suitable for pushing of the pushing case. Target user group characteristics, such as age, location, occupation, and the like of the user, may be determined based on the user information in the obtained push feedback information that clicks on the historical push documentation. And then adding labels to the historical pushed documents based on the user characteristics of the target user group. For example, when the number of users under the age of 25 is higher among the clicking users of a history push document, a label of "young person" may be added to the history push document. If the female users account for a higher percentage of the clicking users of a history push file, a label of 'female' can be added to the history push file. The function label is used for marking the function, type, purpose and the like of the promotion activity, such as a pull-up, a retention or a silent recall and the like. For example, when the promotion activity represented by a history push document aims at adding a new user, a "pull new" tag is added to the history push document. The hashtags may be based on the linguistic style of the history-pushed case, keywords, etc. The theme label can be obtained through a keyword, a theme model and a latent semantic model. For example, if there are popular network terms in the history push document, a label of "trend" may be added to the history push document. For example, if the content of a history push document is "door is a home door when a vehicle door is opened", a label of "go home" may be added to the history push document. Through the steps, a new recommended case library can be created, and the recommended cases in the recommended case library can be continuously updated.
In the specific implementation process, there are various methods for determining the preset recommendation condition. In some embodiments, the method for determining the preset recommendation condition may specifically include the following steps:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
The push feedback data can reflect the push effect of the historical push file. The preset recommendation condition is determined based on the overall situation of all the push feedback data, and one preset recommendation condition can be relatively accurately determined, so that whether the historical push file is a high-quality push file can be accurately judged through the preset recommendation condition.
For example, in the case that it is determined whether a high-quality document is asked for the history pushed document based on the click rate, the method for determining the preset recommendation condition may specifically include: acquiring the click rate of each historical push file; and calculating the average click rate based on the click rates of all historical pushed documents, and determining the average click rate as the preset recommendation condition. The average click rate can reflect the common click rate condition of the historical push files and is easy to calculate. For example, the click rate information of 100 or 1000 historical push documents may be counted, and an average click rate is calculated based on the click rate information, and then the average click rate is set as a preset recommendation condition for preliminarily determining whether the historical push documents are good-quality push documents.
For example, in the case that it is determined whether the historical pushed documents are good-quality pushed documents based on the conversion rate, the method for determining the preset recommendation condition may specifically include: acquiring the conversion rate information of each historical pushed file; calculating the average conversion rate of a plurality of historical pushed documents based on the conversion rates of all historical pushed documents, and determining the average conversion rate as the preset recommendation condition. The average conversion rate can reflect the universal conversion condition of the historical pushing case and is easy to calculate. For example, the conversion rate information of 100, 1000 or even more historical push documents can be counted, and the average conversion rate is calculated based on the conversion rate information, and then the average conversion rate is set as a preset recommendation condition for preliminarily judging whether the historical push documents are high-quality push documents.
In some embodiments, as shown in fig. 3, the selecting at least one recommended document from the recommended document library based on the user characteristics of the target user group for the promotion activity, where the associating the tag of the recommended document with the user characteristics of the target user group includes:
s201, determining the user characteristics of the target user group.
After a promotional campaign is designed, the promotional campaign typically has a target user group, which typically has user characteristics that can characterize the group. For example, for a promotion activity of calling a car during rush hour, the target user group is a working group, and the user characteristics capable of characterizing the group can be determined as a "working group".
S202, matching the user characteristics with the labels of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm.
The collaborative filtering algorithm is to recommend information of interest to a user by using the preference of a user group with mutual interest or common experience. If the similarity degree between the user characteristics and the labels of the recommended documents can be based, the recommended documents with the labels not matched with the user characteristics in the recommended document library are filtered, and the labels matched with the user characteristics are further obtained. The association rules algorithm may filter out tags associated with a user characteristic by manually set rules, e.g., if the user characteristic is "young", then rules may be set to match the "young" tags with tags in the recommended documents library.
S203, obtaining the label matched with the user characteristic and at least one recommended file corresponding to the label.
For example, the target user characteristic may be "young people", and after the "trend" label is screened out by the collaborative filtering algorithm, one or more recommended documents marked with the "trend" label may be marked. In the actual application process, only the collaborative filtering algorithm may be adopted, only the association rule algorithm may be adopted, or both the collaborative filtering algorithm and the association rule algorithm may be applied. Of course, other recommended screening methods may also be applied.
In some embodiments, the obtaining at least one of the tags matching the user characteristics and at least one of the recommended documents corresponding to the tags includes:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
In a specific implementation process, a tag matched with the user characteristic can be selected based on, for example, a collaborative filtering algorithm, then a recommended case is obtained from a recommended case library based on the tag, a recommended case list is generated, and the recommended cases in the recommended case list are sorted according to the matching degree scores. For example, when the user features include 5 keywords, if the tags of one recommended document all hit the 5 keywords, the matching degree of the piece of recommended document is determined to be scored as 10 points, if the tags hit the 4 keywords, the scoring is performed as 8 points, and so on. And then one or more top-ranked push documents are selected from the recommended document list. The specific selection number can be determined according to the number of the target user group for the promotion activity, for example, when the number of the target user group is ten thousand, 10 push documents can be selected, and when the number of the target user group is 10 thousand, 50-100 push documents can be selected. The recommended documents selected from the recommended document list can be directly used for generating push information, and can also be manually screened again by workers to generate push information. The automatic selection does not need human participation, and is suitable for popularization activities with lower sensitivity and better universality. The manual screening is suitable for popularization activities which are sensitive, small in target user number and small in required document pushing number.
Fig. 4 is a block diagram of an information processing apparatus according to an embodiment of the disclosure, and referring to fig. 4, the information processing apparatus according to the embodiment of the disclosure may specifically include an obtaining module 10, a selecting module 20, and a pushing module 30, where:
the obtaining module 10 is configured to obtain a recommended document library, where the recommended document library includes a plurality of recommended documents, and the recommended documents have at least one tag.
Wherein, the recommended case library comprises a plurality of pre-selected push cases. The pushed documents in the recommended documents library can be high-quality pushed documents selected from historical pushed documents, and can also be new pushed documents written by editors. The push file is written for promoting brands, products, services or software and other promotion activities and is used for playing the word content of the target user group. Like 'car robbing just like a stick, people can run all things with high-heeled shoes and drip out from the beginning of a trip'. The tags can be keywords for identifying the pushed documents, one pushed document can only have one tag, and also can have a plurality of tags, and the plurality of tags can identify the pushed documents from a plurality of dimensions. For example, a push document may be labeled with "young people", "trend", etc. The obtaining module 10 may obtain the recommended document library, for example, to construct the recommended document library, to retrieve the recommended document library from a preset storage area, or to obtain an updated recommended document library, so that the recommended document library is in a state to be queried, and further, to select the recommended document from the recommended document library at any time.
And the selecting module 20 is configured to select at least one recommended document from the recommended document library based on the user characteristics of the target user group of the popularization activity, where a tag of the recommended document is associated with the user characteristics of the target user group.
The promotion activity refers to that an enterprise, an individual or an organization promotes the content of brands, products, services or software and the like of the target users through creative activities. The promotion activities typically make a promotion activity plan, which typically includes user characteristics and activity information of the target user group. The target user group refers to a target group targeted by promotion activities, such as young people, middle aged people, old people, students, workers, office workers, and the like. For example, the promotional activity may be an activity that pushes the vehicle platform to a young person, and the user characteristic of the target user group is a young person.
The selecting module 20 can select the matched push documents from the recommended document library by matching the user characteristics and the tags of the target user group, and the selected result may be one push document or a plurality of push documents, where the specific number of the selected push documents is not limited. For example, taking the example of pushing the car-playing platform to young people or old people, the user characteristics of "young people" or "old people" are matched with the tags in the recommended document library, and if one pushed document is marked with the "young people" tag, the pushed document is matched and acquired. For example, "live in the same alleys in villages in cities, it takes several kilometers to drive all vehicles, and the people can drip from the beginning of the trip. The calculation amount and the matching difficulty when the user characteristics of the target user group are matched with the pushed documents can be simplified by setting the tags, so that the aim of quickly selecting the pushed documents suitable for being recommended to the target user group can be fulfilled through quick matching of the user characteristics and the tags, and the user characteristics do not need to be matched with the whole pushed documents.
And the pushing module 30 is configured to generate a push message based on the activity information of the promotion activity and the recommended document, and push the push message to the target user group.
The activity information may include activity subject, content, time and place, etc. The push documents are text contents capable of playing originality of the target user, but the push documents usually do not include activity information of specific promotion activities. Therefore, after the push document matching the target user group is selected, the activity information and the push document need to be combined to generate a complete push message for pushing to the target user. That is, the push message includes activity information related to the promotion activity and creative text content for motivating the target user, so that the target user is allowed to accept the promotion activity while the target user is being exercised. Taking a historical popularization activity as an example, the popularization activity is the activity of popularizing the splicing and dripping wind-mill, crossing the city and returning to home for a year in the course of the year, and then the activity information comprises the splicing and dripping wind-mill, crossing the city and returning to home for a year. The obtained push documents comprise 'door opening, namely home door', and the activity information is combined with the push documents to form complete push information 'door opening, namely home door'; the wind mill is used for splicing drops and getting home for years across cities. In actual application, the push information may be further provided with picture information. Of course, the event information may include a service provider name, discount information, or the like, or may be only one trademark capable of identifying a service or a product.
By adopting the information processing device, the selection module 20 selects the pushed documents from the recommended documents library based on the user characteristics of the target user group and the labels of the pushed documents, the push module 30 generates the pushed information based on the selected pushed documents and the activity information of the promotion activities, and then sends the pushed information to the target user group, so that more appropriate pushed documents can be pushed to different target user groups, personalized recommendation is realized, users of the target user group can be more easily motivated, and the promotion effect of the promotion activities is further improved.
As shown in fig. 5, in some embodiments, the obtaining module 10 includes: a first acquiring unit 11, a judging unit 12, and an adding unit 13, wherein:
the first obtaining unit 11 is configured to obtain a history recommended case and push feedback data of the history recommended case. The historical recommendation documents are the recommendation documents pushed to the user. The push feedback data comprises result data of the promotion activities fed back after the historical push documents participate in the promotion activities, such as click rate, conversion rate, complaint information and other related data. The push feedback data can reflect the push effect of the historical push file.
The judging unit 12 is configured to judge whether the push feedback data of the historical recommended document meets a preset recommendation condition. The preset recommendation condition is a condition representing that the historical recommendation document is a high-quality recommendation document, and various methods can be used for judging whether the historical recommendation document is a high-quality recommendation document in the specific implementation process.
In one case, the determination may be based on the click rate of the historical recommendation documents. If the click rate of a historical pushed document is high, the pushed document can motivate the user, has enough attraction and is a high-quality pushed document. In this case, the determining unit 12 is specifically configured to determine whether the click rate of the historical push documents is greater than a preset click rate threshold. The preset click rate threshold is used for representing whether the pushed document is a high-quality pushed document or not through the click rate, and if the click rate of the historical pushed document is greater than the preset click rate threshold, the historical pushed document is the high-quality pushed document and has the values of collection and re-pushing; if the click rate of the historical pushed document is not greater than the preset click rate threshold, the click rate of the historical pushed document is low, the user cannot be attracted to click and check the historical pushed document, and the historical pushed document is judged to be not a high-quality pushed document preliminarily.
In another case, whether the historical push documents are premium push documents may also be determined based on the conversion rate of the historical push documents. The conversion rate is the ratio of the number of target users who receive the historical pushed document and receive the promotion activities corresponding to the historical pushed document to the number of target users who receive the historical pushed document. If the user accepts the promotion activity, the historical pushed case not only attracts the user to click the historical pushed case, but also further enables the user to accept the corresponding promotion activity, and the final purpose of the promotion activity is achieved. Therefore, whether the historical push documents are high-quality push documents can be effectively judged based on the conversion rate. In this case, the judging unit 12 is configured to judge whether the conversion rate of the history push documents is greater than a preset conversion rate threshold. And when the conversion rate information of a historical pushed file is judged to be larger than the preset conversion rate threshold value, preliminarily judging that the historical pushed file is a high-quality pushed file and meets the preset recommendation condition. If the conversion rate of a historical pushed case is not greater than the preset conversion rate threshold value, the historical pushed case is preliminarily judged to be not a high-quality pushed case and not accord with the preset recommendation condition.
It should be noted that, it may also be determined whether the historical pushed document is a high-quality pushed document based on the click rate and the conversion rate, that is, it is determined that the push feedback data of the historical pushed document meets the preset recommendation condition only when the click rate of the historical pushed document meets the preset click rate threshold and the conversion rate meets the preset conversion rate threshold. Alternatively, it may be determined whether the historical pushed document is a high-quality pushed document based on other determination conditions, or the worker may manually determine whether the historical pushed document is a high-quality pushed document.
The adding unit 13 is configured to add at least one tag to the historical recommended document and add the historical recommended document to the recommended document library when the push feedback data meets the preset recommendation condition. When the push feedback data of a historical push file is judged to meet the preset recommendation condition, the historical push file is preliminarily judged to be a high-quality push file, and a label is added to the historical push file through the adding unit 13. In the implementation process, labels can be added to the history push file from multiple dimensions, for example, the labels can comprise a user label, a function label and a theme label. Wherein, the user label is used for marking the user group suitable for pushing of the pushing case. Target user group characteristics, such as age, location, occupation, and the like of the user, may be determined based on the user information in the obtained push feedback information that clicks on the historical push documentation. And then adding labels to the historical pushed documents based on the user characteristics of the target user group. For example, when the number of users under the age of 25 is higher among the clicking users of a history push document, a label of "young person" may be added to the history push document. If the female users account for a higher percentage of the clicking users of a history push file, a label of 'female' can be added to the history push file. The function label is used for marking the function, type, purpose and the like of the promotion activity, such as a pull-up, a retention or a silent recall and the like. For example, when the promotion activity represented by a history push document aims at adding a new user, a "pull new" tag is added to the history push document. The hashtags may be based on the linguistic style of the history-pushed case, keywords, etc. The theme label can be obtained through a keyword, a theme model and a latent semantic model. For example, if there are popular network terms in the history push document, a label of "trend" may be added to the history push document. For example, if the content of a history push document is "door is a home door when a vehicle door is opened", a label of "go home" may be added to the history push document. Through the steps, a new recommended case library can be created, and the recommended cases in the recommended case library can be continuously updated.
In some embodiments, the determining unit 12 is specifically configured to:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
The push feedback data can reflect the push effect of the historical push file. The preset recommendation condition is determined based on the overall situation of all the push feedback data, and one preset recommendation condition can be relatively accurately determined, so that whether the historical push file is a high-quality push file can be accurately judged through the preset recommendation condition.
For example, in the case that it is determined whether a high-quality document is asked for the history pushed document based on the click rate, the method for determining the preset recommendation condition may specifically include: acquiring the click rate of each historical push file; and calculating the average click rate based on the click rates of all historical pushed documents, and determining the average click rate as the preset recommendation condition. The average click rate can reflect the common click rate condition of the historical push files and is easy to calculate. For example, the click rate information of 100 or 1000 historical push documents may be counted, and an average click rate is calculated based on the click rate information, and then the average click rate is set as a preset recommendation condition for preliminarily determining whether the historical push documents are good-quality push documents.
For example, in the case that it is determined whether the historical pushed documents are good-quality pushed documents based on the conversion rate, the method for determining the preset recommendation condition may specifically include: acquiring the conversion rate information of each historical pushed file; calculating the average conversion rate of a plurality of historical pushed documents based on the conversion rates of all historical pushed documents, and determining the average conversion rate as the preset recommendation condition. The average conversion rate can reflect the universal conversion condition of the historical pushing case and is easy to calculate. For example, the conversion rate information of 100, 1000 or even more historical push documents can be counted, and the average conversion rate is calculated based on the conversion rate information, and then the average conversion rate is set as a preset recommendation condition for preliminarily judging whether the historical push documents are high-quality push documents.
As shown in fig. 6, in some embodiments, the selecting module 20 includes: a determination unit 21, a matching unit 22 and a second acquisition unit 23.
The determining unit 21 is configured to determine a user characteristic of the target user group. After a promotional campaign is designed, the promotional campaign typically has a target user group, which typically has user characteristics that can characterize the group. For example, for a promotion activity of calling a car during rush hour, the target user group is a working group, and the user characteristics capable of characterizing the group can be determined as a "working group".
The matching unit 22 is configured to match the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm. The collaborative filtering algorithm is to recommend information of interest to a user by using the preference of a user group with mutual interest or common experience. If the similarity degree between the user characteristics and the labels of the recommended documents can be based, the recommended documents with the labels not matched with the user characteristics in the recommended document library are filtered, and the labels matched with the user characteristics are further obtained. The association rules algorithm may filter out tags associated with a user characteristic by manually set rules, e.g., if the user characteristic is "young", then rules may be set to match the "young" tags with tags in the recommended documents library.
The second obtaining unit 23 is configured to obtain the tag matching the user characteristic and at least one recommended document corresponding to the tag. For example, the target user characteristic may be "young people", and after the "trend" label is screened out by the collaborative filtering algorithm, one or more recommended documents marked with the "trend" label may be marked. In the actual application process, only the collaborative filtering algorithm may be adopted, only the association rule algorithm may be adopted, or both the collaborative filtering algorithm and the association rule algorithm may be applied. Of course, other recommended screening methods may also be applied.
In some embodiments, the second obtaining unit 23 is specifically configured to:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
In a specific implementation process, a tag matched with the user characteristic can be selected based on, for example, a collaborative filtering algorithm, then a recommended case is obtained from a recommended case library based on the tag, a recommended case list is generated, and the recommended cases in the recommended case list are sorted according to the matching degree scores. For example, when the user features include 5 keywords, if the tags of one recommended document all hit the 5 keywords, the matching degree of the piece of recommended document is determined to be scored as 10 points, if the tags hit the 4 keywords, the scoring is performed as 8 points, and so on. And then one or more top-ranked push documents are selected from the recommended document list. The specific selection number can be determined according to the number of the target user group for the promotion activity, for example, when the number of the target user group is ten thousand, 10 push documents can be selected, and when the number of the target user group is 10 thousand, 50-100 push documents can be selected. The recommended documents selected from the recommended document list can be directly used for generating push information, and can also be manually screened again by workers to generate push information. The automatic selection does not need human participation, and is suitable for popularization activities with lower sensitivity and better universality. The manual screening is suitable for popularization activities which are sensitive, small in target user number and small in required document pushing number.
The embodiment of the present disclosure further provides a storage medium storing a computer program, where the computer program is executed by a processor to implement the method provided in any embodiment of the present disclosure, and exemplarily includes the following steps:
s100, acquiring a recommended case library, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one tag;
s200, based on the user characteristics of a target user group of the promotion activity, selecting at least one recommended case from the recommended case library, wherein the label of the recommended case is associated with the user characteristics of the target user group;
s300, generating a push message based on the activity information of the promotion activity and the recommended pattern, and pushing the push message to the target user group.
When the computer program is executed by the processor to obtain the recommended document library, the processor specifically executes the following steps: acquiring a historical recommended case and push feedback data of the historical recommended case; judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not; if yes, adding at least one label for the historical recommended file, and adding the historical recommended file to the recommended file library.
When the computer program is executed by the processor to judge whether the push feedback data of the historical recommendation file meets the preset recommendation condition, the processor specifically executes the following steps: determining the push feedback data of each historical recommendation case; and determining the preset recommendation condition based on all the push feedback data.
The computer program is executed by a processor for determining the preset recommendation condition based on all the push feedback data, including click-through rate data and/or conversion rate data.
When the computer program is executed by the processor to the steps of selecting at least one recommended case from the recommended case library based on the user characteristics of the target user group of the promotion activity, wherein the label of the recommended case is associated with the user characteristics of the target user group, the following steps are specifically executed by the processor: determining user characteristics of the target user group; matching the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm; and acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
When the computer program is executed by the processor to obtain at least one label matched with the user characteristics and at least one recommended case corresponding to the label, the processor specifically executes the following steps: acquiring at least one label matched with the user characteristics of the target user group; acquiring a recommended case list corresponding to each label based on each label; sorting the recommended documents in all the recommended document lists according to the matching degree scores; and selecting at least one recommended case with the top ranking.
The computer program is executed by a processor to obtain a recommended case library, the recommended case library comprises a plurality of recommended cases, and the label comprises at least one of the following types: user tags, function tags, theme tags.
According to the method and the device for recommending the files, the pushed files are selected from the recommended file library based on the user characteristics of the target user group and the labels of the pushed files, the pushed information is generated based on the selected pushed files and the activity information of the popularization activity, the pushed information is sent to the target user group, more appropriate pushed files can be pushed to different target user groups, personalized recommendation is achieved, users of the target user group can be more easily motivated, and the popularization effect of the popularization activity is improved.
The storage medium may be disposed in an electronic device that at least includes a memory and a processor, and may exist in the form of a memory, and specific implementation manners are not described herein again.
The embodiment of the present disclosure provides an electronic device, as shown in fig. 7, the electronic device at least includes a memory 901 and a processor 902, the memory 901 stores a computer program, and the processor 902 implements the method provided in any embodiment of the present disclosure when executing the computer program on the memory 901, where, for example, the computer program includes the following steps:
s100, acquiring a recommended case library, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one tag;
s200, based on the user characteristics of a target user group of the promotion activity, selecting at least one recommended case from the recommended case library, wherein the label of the recommended case is associated with the user characteristics of the target user group;
s300, generating a push message based on the activity information of the promotion activity and the recommended pattern, and pushing the push message to the target user group.
When executing the computer program for acquiring the recommended document library stored in the memory 901, the processor 902 specifically executes the following computer program: acquiring a historical recommended case and push feedback data of the historical recommended case; judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not; if yes, adding at least one label for the historical recommended file, and adding the historical recommended file to the recommended file library.
When executing the computer program stored in the memory 901 for determining whether the push feedback data of the historical recommendation document meets the preset recommendation condition, the processor 902 specifically executes the following computer program: determining the push feedback data of each historical recommendation case; and determining the preset recommendation condition based on all the push feedback data.
The processor 902, when executing a computer program stored on the memory 901 that determines the push feedback data for each of the historical recommendation documents, the push feedback data includes click through rate data and/or conversion rate data.
The processor 902, when executing the computer program stored in the memory 901 and based on the user characteristics of the target user group of the promotional activities, selects at least one recommended document from the recommended document library, and the tag of the recommended document is associated with the user characteristics of the target user group, specifically executes the following computer program: determining user characteristics of the target user group; matching the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm; and acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
The processor 902 executes a computer program stored in the memory 901 to obtain a recommended document library, where the recommended document library includes a plurality of recommended documents, and when the recommended document has at least one tag, the following computer programs are specifically executed: the tag includes at least one of the following types: user tags, function tags, theme tags.
According to the method and the device for recommending the files, the pushed files are selected from the recommended file library based on the user characteristics of the target user group and the labels of the pushed files, the pushed information is generated based on the selected pushed files and the activity information of the popularization activity, the pushed information is sent to the target user group, more appropriate pushed files can be pushed to different target user groups, personalized recommendation is achieved, users of the target user group can be more easily motivated, and the popularization effect of the popularization activity is improved.
Moreover, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments based on the disclosure with equivalent elements, modifications, omissions, combinations (e.g., of various embodiments across), adaptations or alterations. The elements of the claims are to be interpreted broadly based on the language employed in the claims and not limited to examples described in the present specification or during the prosecution of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more versions thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the foregoing detailed description, various features may be grouped together to streamline the disclosure. This should not be interpreted as an intention that a disclosed feature not claimed is essential to any claim. Rather, the subject matter of the present disclosure may lie in less than all features of a particular disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with each other in various combinations or permutations. The scope of the disclosure should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are merely exemplary embodiments of the present disclosure, which is not intended to limit the present disclosure, and the scope of the present disclosure is defined by the claims. Various modifications and equivalents of the disclosure may occur to those skilled in the art within the spirit and scope of the disclosure, and such modifications and equivalents are considered to be within the scope of the disclosure.
Claims (16)
1. An information processing method characterized by comprising:
acquiring a recommended case library, wherein the recommended case library comprises a plurality of recommended cases, and each recommended case is provided with at least one tag;
selecting at least one recommended case from the recommended case library based on the user characteristics of a target user group of the promotion activity, wherein the label of the recommended case is associated with the user characteristics of the target user group;
and generating a push message based on the activity information of the promotion activity and the recommended file, and pushing the push message to the target user group.
2. The information processing method according to claim 1, wherein the acquiring of the recommended document library includes:
acquiring a historical recommended case and push feedback data of the historical recommended case;
judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not;
if yes, adding at least one label for the historical recommended file, and adding the historical recommended file to the recommended file library.
3. The information processing method of claim 2, wherein the determining whether the push feedback data of the historical recommendation document meets a preset recommendation condition comprises:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
4. The information processing method of claim 3, wherein the push feedback data comprises click-through rate data and/or conversion rate data.
5. The information processing method of claim 1, wherein the selecting at least one of the recommended documents from the recommended document library based on the user characteristics of the target user group for the promotional activity, and wherein the associating the tag of the recommended document with the user characteristics of the target user group comprises:
determining user characteristics of the target user group;
matching the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm;
and acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
6. The information processing method according to claim 5, wherein the acquiring at least one of the tag matching the user feature and at least one of the recommended document corresponding to the tag includes:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
7. The information processing method according to any one of claims 1 to 6, wherein the tag includes at least one of the following types:
user tags, function tags, theme tags.
8. An information processing apparatus characterized by comprising:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a recommendation document library which comprises a plurality of recommendation documents with at least one label;
the selection module is used for selecting at least one recommended case from the recommended case library based on the user characteristics of a target user group of the promotion activity, and the label of the recommended case is associated with the user characteristics of the target user group;
and the pushing module is used for generating a pushing message based on the activity information of the promotion activity and the recommended document and pushing the pushing message to the target user group.
9. The information processing apparatus according to claim 8, wherein the acquisition module includes:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring a historical recommended case and push feedback data of the historical recommended case;
the judging unit is used for judging whether the push feedback data of the historical recommendation file meet preset recommendation conditions or not;
and the adding unit is used for adding at least one label to the historical recommended file and adding the historical recommended file to the recommended file library under the condition that the push feedback data meet the preset recommendation condition.
10. The information processing apparatus according to claim 9, wherein the determination unit is specifically configured to:
determining the push feedback data of each historical recommendation case;
and determining the preset recommendation condition based on all the push feedback data.
11. The information processing apparatus of claim 10, wherein the push feedback data comprises click-through rate data and/or conversion rate data.
12. The information processing apparatus according to claim 8, wherein the selecting module includes:
a determining unit, configured to determine a user characteristic of the target user group;
a matching unit, configured to match the user characteristics with the tags of the recommended documents in the recommended document library through a collaborative filtering algorithm and/or an association rule algorithm;
and the second acquisition unit is used for acquiring the label matched with the user characteristics and at least one recommended file corresponding to the label.
13. The information processing apparatus according to claim 12, wherein the second acquisition unit is specifically configured to:
acquiring at least one label matched with the user characteristics of the target user group;
acquiring a recommended case list corresponding to each label based on each label;
sorting the recommended documents in all the recommended document lists according to the matching degree scores;
and selecting at least one recommended case with the top ranking.
14. The information processing apparatus according to any one of claims 8 to 13, wherein the tag includes at least one of the following types:
user tags, function tags, theme tags.
15. A storage medium storing a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 7 when executed by a processor.
16. An electronic device comprising at least a memory, a processor, the memory having a computer program stored thereon, wherein the processor, when executing the computer program on the memory, is adapted to carry out the steps of the method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910600799.0A CN111814034A (en) | 2019-07-04 | 2019-07-04 | Information processing method, information processing apparatus, storage medium, and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910600799.0A CN111814034A (en) | 2019-07-04 | 2019-07-04 | Information processing method, information processing apparatus, storage medium, and electronic device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111814034A true CN111814034A (en) | 2020-10-23 |
Family
ID=72844595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910600799.0A Pending CN111814034A (en) | 2019-07-04 | 2019-07-04 | Information processing method, information processing apparatus, storage medium, and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111814034A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113254633A (en) * | 2021-05-10 | 2021-08-13 | 中国民生银行股份有限公司 | Message pattern generation method and device |
CN115238198A (en) * | 2022-09-26 | 2022-10-25 | 江苏银承网络科技股份有限公司 | Method and device for pushing file information |
CN115277835A (en) * | 2022-08-01 | 2022-11-01 | 网易(杭州)网络有限公司 | Information pushing method and device, storage medium and electronic equipment |
CN115563397A (en) * | 2022-12-06 | 2023-01-03 | 福建慧政通信息科技有限公司 | Electronic file recommendation method and terminal |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106375797A (en) * | 2016-09-27 | 2017-02-01 | 北京赢点科技有限公司 | Media program and activity recommendation system and method |
CN107025570A (en) * | 2017-01-05 | 2017-08-08 | 李汉洙 | A kind of method in movie theatre advertisement |
CN108563753A (en) * | 2018-04-16 | 2018-09-21 | 深圳壹账通智能科技有限公司 | Message pushes generation method, device and the computer readable storage medium of official documents and correspondence |
-
2019
- 2019-07-04 CN CN201910600799.0A patent/CN111814034A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106375797A (en) * | 2016-09-27 | 2017-02-01 | 北京赢点科技有限公司 | Media program and activity recommendation system and method |
CN107025570A (en) * | 2017-01-05 | 2017-08-08 | 李汉洙 | A kind of method in movie theatre advertisement |
CN108563753A (en) * | 2018-04-16 | 2018-09-21 | 深圳壹账通智能科技有限公司 | Message pushes generation method, device and the computer readable storage medium of official documents and correspondence |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113254633A (en) * | 2021-05-10 | 2021-08-13 | 中国民生银行股份有限公司 | Message pattern generation method and device |
CN113254633B (en) * | 2021-05-10 | 2024-05-03 | 中国民生银行股份有限公司 | Message document generation method and device |
CN115277835A (en) * | 2022-08-01 | 2022-11-01 | 网易(杭州)网络有限公司 | Information pushing method and device, storage medium and electronic equipment |
CN115238198A (en) * | 2022-09-26 | 2022-10-25 | 江苏银承网络科技股份有限公司 | Method and device for pushing file information |
CN115563397A (en) * | 2022-12-06 | 2023-01-03 | 福建慧政通信息科技有限公司 | Electronic file recommendation method and terminal |
CN115563397B (en) * | 2022-12-06 | 2023-03-21 | 福建慧政通信息科技有限公司 | Electronic file recommendation method and terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111814034A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
CN105550903B (en) | Target user determination method and device | |
CN107346496B (en) | Target user orientation method and device | |
KR101324909B1 (en) | Touchpoint customization system | |
US8930412B2 (en) | Intelligence centers | |
CN101071437A (en) | User classifying method, directional advertising launching method, device and system | |
US20070192194A1 (en) | Metalevel electronic marketplace for advertising | |
US20070027901A1 (en) | Method and System for Developing and Managing A Computer-Based Marketing Campaign | |
CN104412563B (en) | method and system for online advertisement | |
Zaki et al. | Customer experience analytics: dynamic customer-centric model | |
CN102222299A (en) | Inventory management | |
WO2020147429A1 (en) | Advertisement data generation | |
EP3951621A1 (en) | Data collection method and system | |
KR102322668B1 (en) | Systme for providing multi-platform service for stimulating creative activity of contents creator | |
CN112446717A (en) | Advertisement putting method and device | |
CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
AU2010202238A1 (en) | Method and system for determining average values for displayed information items | |
JP2011054158A (en) | Object customization and management system | |
CN108595580B (en) | News recommendation method, device, server and storage medium | |
CN114266592A (en) | Distribution method, distribution device, equipment and medium of advertisement materials | |
US20230115791A1 (en) | Method and system for identifying assets and automating the creation and monetization of advertisements | |
CN108549722B (en) | Multi-platform data publishing method, system and medium | |
JP6373140B2 (en) | Extraction apparatus, extraction method, and extraction program | |
CN112734142B (en) | Resource learning path planning method and device based on deep learning | |
CN115809889A (en) | Intelligent passenger group screening method, system, medium and equipment based on marketing effect |
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 |