CN112348638B - Activity document recommending method and device, electronic equipment and storage medium - Google Patents
Activity document recommending method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112348638B CN112348638B CN202011240904.3A CN202011240904A CN112348638B CN 112348638 B CN112348638 B CN 112348638B CN 202011240904 A CN202011240904 A CN 202011240904A CN 112348638 B CN112348638 B CN 112348638B
- Authority
- CN
- China
- Prior art keywords
- activity
- user
- target
- information
- topic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000000694 effects Effects 0.000 title claims abstract description 458
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 14
- 230000001737 promoting effect Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 230000002087 whitening effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003616 anti-epidemic effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an activity document recommending method, an activity document recommending device, electronic equipment and a storage medium, and relates to the field of data processing. The activity document recommending method comprises the following steps: acquiring a user-activity knowledge graph according to the user information table and the activity information table; matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information; obtaining a target user corresponding to the topic keyword according to the target activity scheme and the association relation corresponding to the target activity topic information; the target user is at least one interested user associated with the target activity topic information. By using the method provided by the application, the target activity topic information matched with the topic keywords can be obtained through the user-activity knowledge graph, so that the target user corresponding to the topic keywords is obtained, the manual activity prediction is avoided, and the user participation condition corresponding to the topic keywords can be predicted by combining the historical data.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a method, an apparatus, an electronic device, and a storage medium for recommending an activity document.
Background
The activity material theme refers to a corresponding document theme pushed out by each activity; for example, if a "lover's day" buys a whitening product for one, the corresponding topic is: "plot", "whiten", "giver". For operators, it is often necessary to determine whether the subject of a new activity can motivate a historic behavioural user, or to predict the population and number of motivated users.
Therefore, in order to save manpower, operators adopt activity materials to conduct topic recommendation, namely, view the activity topic of the bid, then predict the activity condition and search the historical activity document. For example, the bid pushes out a "whitening+bouquet" activity, and operators can analyze the bid with reference to the topic of the bid and ignore the situation of their own products; or, the operator may only track the current hot spot for activity theme customization.
For the prior art solutions, the following bottlenecks exist: 1, the activity of the bid product cannot be perfectly matched with the product of the bid product; 2, through bidding or hot spot customizing activities, the prediction function of the historical activities cannot be used, namely the possible excited user situation of the new activity theme cannot be predicted.
Disclosure of Invention
The purpose of the application includes, for example, providing a method, a device, an electronic device and a storage medium for recommending an activity document, which can obtain target activity topic information matched with topic keywords through a user-activity knowledge graph, further obtain target users corresponding to the topic keywords, avoid manually predicting activities, and predict user participation corresponding to the topic keywords by combining historical data.
Embodiments of the present application may be implemented as follows:
in a first aspect, the present application provides a method for event document recommendation, the method comprising:
acquiring a user-activity knowledge graph according to the user information table and the activity information table;
the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identifier; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-knowledge graph comprises an association relation between the interested user and the activity identifier, a user attribute of the interested user and an activity attribute corresponding to the activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme;
matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information;
obtaining a target user corresponding to the topic keyword according to the target activity scheme corresponding to the target activity topic information and the association relation; the target user is at least one of the interested users associated with the target activity topic information.
In an alternative embodiment, the user information table is obtained by:
judging whether a user to be determined has an interaction process with a first activity during the activity of the first activity; the first activity is any one of the at least one activity;
if yes, the user to be determined is used as a first interested user of the first activity;
and associating the first interested user with the first activity to obtain the user information table.
In an alternative embodiment, the activity information table is obtained by:
acquiring an activity scheme of the first activity; the activity scheme is characterized by a propaganda document adopted for propaganda of the first activity, and the propaganda document comprises a plurality of activity theme information;
obtaining user evaluation information of the first activity; the user evaluation information is activity evaluation of the first activity by interested users of the first activity;
and establishing a corresponding relation between the first activity and the propaganda document, and recording the propaganda document to obtain the activity information table.
In an optional embodiment, establishing a correspondence between the first activity and the propaganda document, and recording the propaganda document to obtain the activity information table, where the activity information table includes:
extracting a plurality of activity theme information in the propaganda text;
establishing a corresponding relation between the first activity and the plurality of activity theme information;
and recording the corresponding relation and the propaganda document to obtain the activity information table.
In an alternative embodiment, matching the topic keyword with the user-activity knowledge graph to obtain target activity topic information includes:
acquiring a theme keyword input by a worker, and mapping the theme keyword into a dense vector;
acquiring cosine similarity between the dense vector and each activity topic information in the user-activity knowledge graph;
taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity;
and taking the activity theme information corresponding to the target similarity as the target activity theme information.
In an alternative embodiment, the first condition is that cosine similarity is greater than or equal to a similarity threshold;
taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity, wherein the method comprises the following steps:
judging whether the first cosine similarity is larger than or equal to the similarity threshold value or not; the first cosine similarity is any one of the cosine similarities;
if yes, the first cosine similarity is taken as the target similarity.
In an optional embodiment, according to the association relationship between the target activity scheme corresponding to the target activity topic information and the target activity scheme, obtaining the target user corresponding to the topic keyword includes:
taking the activity scheme of the target activity theme information as a target activity scheme;
matching the activity identifier corresponding to the target activity scheme with the association relation to obtain a target user; the target user includes all interested users associated with the target activity scheme.
In a second aspect, the present application provides an activity document recommendation device, the device comprising:
the acquisition module is used for acquiring a user-activity knowledge graph according to the user information table and the activity information table;
the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identifier; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-knowledge graph comprises an association relation between the interested user and the activity identifier, a user attribute of the interested user and an activity attribute corresponding to the activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme;
the matching module is used for matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information;
the processing module is used for obtaining a target user corresponding to the topic keyword according to the target activity scheme corresponding to the target activity topic information and the association relation; the target user is at least one of the interested users associated with the target activity topic information.
In a third aspect, the present application provides an electronic device comprising a processor and a memory storing a computer program executable by the processor, the processor being executable to implement the method of any one of the preceding embodiments.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method according to any of the preceding embodiments.
Compared with the prior art, the application provides an activity document recommending method, an activity document recommending device, electronic equipment and a storage medium, and relates to the field of data processing. The activity document recommending method comprises the following steps: acquiring a user-activity knowledge graph according to the user information table and the activity information table; the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identifier; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-knowledge graph comprises an association relation between the interested user and the activity identifier, a user attribute of the interested user and an activity attribute corresponding to the activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme; matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information; obtaining a target user corresponding to the topic keyword according to the target activity scheme corresponding to the target activity topic information and the association relation; the target user is at least one of the interested users associated with the target activity topic information. By using the method provided by the application, the target activity topic information matched with the topic keywords can be obtained through the user-activity knowledge graph, so that the target user corresponding to the topic keywords is obtained, the manual activity prediction is avoided, and the user participation condition corresponding to the topic keywords can be predicted by combining the historical data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for recommending an activity document according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating another method for recommending an event document according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating another method for recommending an event document according to an embodiment of the present disclosure;
FIG. 4 is a flowchart illustrating another method for recommending an activity document according to an embodiment of the present application;
FIG. 5 is a flowchart illustrating another method for recommending an activity document according to an embodiment of the present application;
FIG. 6 is a flowchart illustrating another method for recommending an event document according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a user-activity knowledge graph according to an embodiment of the present application;
FIG. 8 is a schematic block diagram of an activity document recommendation apparatus according to an embodiment of the present disclosure;
fig. 9 is a block schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. In the description of the present application, it should be noted that, if the terms "upper," "lower," "inner," "outer," and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or the azimuth or the positional relationship in which the inventive product is conventionally put in use, it is merely for convenience of describing the present application and simplifying the description, and it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be configured and operated in a specific azimuth, and thus should not be construed as limiting the present application. It should be noted that, without conflict, features in embodiments of the present application may be combined with each other.
The activity material theme refers to a corresponding document theme pushed out by each activity; for example, if a "lover's day" buys a whitening product for one, the corresponding topic is: "plot", "whiten", "giver". For operators, it is often necessary to determine whether the subject of a new activity can motivate a historic behavioural user, or to predict the population and number of motivated users. Therefore, in order to save manpower, operators adopt activity materials to conduct topic recommendation, namely, view the activity topic of the bid, then predict the activity condition and search the historical activity document. For example, the bid pushes out a "whitening+bouquet" activity, and operators can analyze the bid with reference to the topic of the bid and ignore the situation of their own products; or, the operator may only track the current hot spot for activity theme customization. For the prior art solutions, the following bottlenecks exist: 1, the activity of the bid product cannot be perfectly matched with the product of the bid product; 2, through bidding or hot spot customizing activities, the prediction function of the historical activities cannot be used, namely the possible excited user situation of the new activity theme cannot be predicted.
In order to solve at least the above problems, an embodiment of the present application provides an activity document recommendation method, referring to fig. 1, fig. 1 is a flow chart of an activity document recommendation method provided in the embodiment of the present application, and the activity document recommendation method may include the following steps:
s210, acquiring a user-activity knowledge graph according to the user information table and the activity information table.
Wherein the user information table comprises correspondence of at least one activity and its interested user group comprising at least one interested user having a desire to participate in the at least one activity, each activity having an activity identification (Identity Document, ID). The activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification. The campaign approach may be a promotional document employed for a campaign, which may include a plurality of campaign topic information. For example, for a "story" campaign, its promotional document is: the meaning of the existence of the plot is to remind 'Blieveinlove', and the love never leaves, and simultaneously reminds us: love, will be called to listen. Especially in epidemic situations, so that the scenario lets us and Li Xian together ", the activity topic information of the" scenario "activity can be: li Xian, lover's day, love, epidemic situation, belive.
The user-knowledge graph may include an association relationship between an interested user and an activity identifier, a user attribute of the interested user, and an activity attribute corresponding to an activity scheme, where the activity attribute is activity topic information determined according to the activity scheme. For example, the activity attributes may also include a start time, duration of the activity, place of development of the activity, manner of holding the activity, and the like.
And S220, matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information.
For example, the target activity topic information may be one or more activity topic information having the highest similarity to the topic keyword among the plurality of activity topic information, or may be one or more activity topic information having a similarity to the topic keyword greater than or equal to a similarity threshold among the plurality of activity topic information.
S230, obtaining the target user corresponding to the topic keyword according to the target activity scheme and the association relation corresponding to the target activity topic information.
The target user is at least one interested user associated with the target activity topic information. By using the activity document recommending method provided by the embodiment of the application, the target activity topic information matched with the topic keywords can be obtained through the user-activity knowledge graph, so that the target users corresponding to the topic keywords can be obtained, the manual activity prediction is avoided, and the user participation situation corresponding to the topic keywords can be predicted by combining the historical data.
In an alternative implementation manner, a possible implementation manner is given on the basis of fig. 1 in order to obtain the above-mentioned user information table, please refer to fig. 2, fig. 2 is a schematic flow chart of another activity document recommendation method provided in this embodiment of the present application, where the above-mentioned user information table may be obtained by:
s201, it is determined whether the user to be determined has an interaction procedure with the first activity during the activity of the first activity.
The first activity is any one of the at least one activity; the interaction procedure may be a user having a participating activity during an activity of the first activity.
If it is to be determined that the user has no interaction procedure with the first activity during the activity of the first activity, S202 is performed; if it is to be determined that the user has an interaction procedure with the first activity during the activity of the first activity, S203 is performed.
S202, the user to be determined is not an interested user of the first activity.
S203, taking the user to be determined as a first interested user of the first activity.
For example, taking the WeChat ecology as an example, users who are behaving during an activity can be defined as users who are interested in the activity within the WeChat applet; other means may be used, such as forwarding information such as an activity document during an activity, defined as users interested in the activity.
S204, associating the first interested user with the first activity to obtain a user information table.
It should be understood that the above user information table may be that the user ID of the first interested user is associated with the first activity, and the user information table may further store information of the gender, the region, and the like of the first interested user.
In an alternative implementation manner, a possible implementation manner is given on the basis of fig. 1 in order to obtain the above activity information table, and referring to fig. 3, fig. 3 is a schematic flow chart of another activity document recommendation method provided in this embodiment of the present application, where the above activity information table may be obtained by:
s205, acquiring an activity scheme of the first activity.
The campaign solution characterizes a promotional document employed for promoting the first campaign, the promotional document comprising a plurality of campaign topic information.
S206, obtaining user evaluation information of the first activity.
The user rating information is an activity rating of the first activity by an interested user of the first activity.
S207, establishing a corresponding relation between the first activity and the propaganda document, and recording the propaganda document to obtain an activity information table.
For example, for each activity, there are two portions of the document that are of great concern: on one hand, the propaganda text of an operator usually has a large amount of activity theme information; another aspect is the ratings information of the active interested users. For both aspects of information, the first point may be an operational input and the second point may be manually gathered or by means of a crawler or the like.
In an alternative implementation manner, in order to obtain the activity information table, a possible implementation manner is given on the basis of fig. 3, please refer to fig. 4, fig. 5 is a schematic flow chart of another activity document recommendation method provided in this embodiment of the present application, which is directed to S207 described above: establishing a corresponding relation between a first activity and a propaganda document, and recording the propaganda document to obtain an activity information table, which can comprise the following steps:
s2071, extracting a plurality of activity theme information in the propaganda document.
In a possible implementation manner, the activity topic information may be obtained by extracting topic evaluation information through hanlp in natural language processing, where hanlp may include various topic extraction modes such as chinese word segmentation, named entity recognition, abstract keywords, dependency syntax analysis, simplified and complex pinyin conversion, intelligent recommendation, and the like.
S2072, establishing a corresponding relation between the first activity and the plurality of activity theme information.
For example, for the "scenario" activity proposed above, the activity topic information is: li Xian, lover's day, love, epidemic situation, belive; and establishing a connection between the activity ID of the first activity and the activity topic information 'Li Xian, the plot, love, epidemic situation and Belive', thereby obtaining the corresponding relation between the first activity and the activity topic information.
S2073, recording the corresponding relation and the propaganda text to obtain the activity information table.
It should be appreciated that each promotional document in the campaign information table has a correspondence to the campaign ID of its corresponding campaign, so that promotional document retrieval is performed by the campaign ID when viewing of promotional documents is required.
In an alternative implementation manner, in order to obtain the target activity topic information, a possible implementation manner is given on the basis of fig. 1, please refer to fig. 5, fig. 5 is a schematic flow chart of another activity document recommendation method provided in this embodiment of the present application, which is aimed at S220 described above: matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information, which may include:
s2201, obtaining the topic keywords input by the staff, and mapping the topic keywords into dense vectors.
For example, the topic keyword input by the staff is acquired through an input device such as a touch screen, a keyboard, a mouse and the like; mapping the subject keywords into dense vectors that characterize keywords having cosine similarity to the subject keywords greater than or equal to a predetermined similarity threshold may be performed using a pre-trained word vector technique of Neuro-programming (NLP, linguistic Programming).
S2202, obtaining cosine similarity between the dense vector and each activity topic information in the user-activity knowledge graph.
That is, the similarity between the dense vector and each activity topic information in the user-activity knowledge graph is compared, so as to obtain cosine similarity between the dense vector and each activity topic information in the user-activity knowledge graph; it should be appreciated that the higher the cosine similarity, the more similar the dense vector is to each activity topic information in the user-activity knowledge-graph. For example, 'anti-epidemic' may be matched to 'epidemic' for 'activity a'; further, the similarity may be determined by cosine similarity a. If the cosine similarity a between the new word (dense vector corresponding to the topic keyword) and the historical activity topic word (each activity topic information in the user-activity knowledge graph) is smaller than 0.5, the new word is not related to the historical activity topic word, and topic recommendation is not performed on the topic keyword.
S2203, taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity.
The first condition may be that the cosine similarity is greater than or equal to a similarity threshold. For example, for S2203 described above, it may include: judging whether the first cosine similarity is larger than or equal to a similarity threshold value or not; the first cosine similarity is any one of all cosine similarities. And if the first cosine similarity is greater than or equal to the similarity threshold, taking the first cosine similarity as the target similarity.
S2204, taking the activity theme information corresponding to the target similarity as target activity theme information.
And if the topic keyword has a plurality of target similarities meeting the first condition, taking the activity topic information corresponding to each target similarity as target activity topic information.
In an alternative implementation manner, in order to determine the target user corresponding to the topic keyword, a possible implementation manner is given on the basis of fig. 5, please refer to fig. 6, fig. 6 provides a flowchart of another activity document recommendation method according to an embodiment of the present application, which is directed to S230 described above: according to the target activity scheme and the association relation corresponding to the target activity topic information, obtaining the target user corresponding to the topic keyword, which may include:
s2301, an activity scheme to which the target activity topic information belongs is taken as a target activity scheme.
For example, if the activity scheme to which the plurality of target activity topic information belongs is activity topic information of the same activity scheme, the activity scheme is taken as a target activity scheme; and if the activity schemes to which the plurality of target activity theme information belong are the activity theme information of different activity schemes, taking each activity scheme as the target activity scheme.
S2302, matching the activity identifier corresponding to the target activity scheme with the association relationship to obtain the target user.
The target user includes all interested users associated with the target activity scheme. For example, if the activity schemes to which the plurality of target activity topic information belong are activity topic information of the same activity scheme, the interested user corresponding to the target activity scheme is taken as the target user; and if the activity schemes to which the plurality of target activity theme information belong are the activity theme information of different activity schemes, taking the interested users corresponding to each target activity scheme as target users.
In order to facilitate understanding of the activity document recommendation method provided by any one of the foregoing embodiments, please refer to fig. 7, fig. 7 is a schematic diagram of providing a user-activity knowledge graph in an embodiment of the present application, in which different labels are used to represent an activity and a user in fig. 7, a box represents the activity, a circle represents the user, and a user connected with the activity is an interested user of the activity; it should be appreciated that for the same user, it may be an interested user for multiple activities.
An operator can query and analyze the user-activity knowledge graph shown in fig. 7, and in the user-activity knowledge graph shown in fig. 7, each user is triggered to mark the information of the user's user gender, the region where the user is located, and the like.
In one possible implementation, cosine similarity a may be considered as the association of new subject words (subject keywords) with activity ABC. For a new topic, the number of interested users of the activity ABC can be multiplied by a to roughly predict the new topic word (topic keyword) collocation activity topic information corresponding to the activity ABC and the number of users possibly motivated.
In one possible implementation, irrelevant nodes may be deleted from the user-activity knowledge graph shown in fig. 7, and a graph of an activity corresponding to the topic keyword may be output. In this way, visual analysis of user assets motivated by related activities may be quickly performed.
In order to implement the activity document recommending method provided in any of the foregoing embodiments, the embodiment of the present application provides an activity document recommending apparatus, please refer to fig. 8, fig. 8 is a block schematic diagram of an activity document recommending apparatus provided in the embodiment of the present application, and the activity document recommending apparatus 40 may include: an acquisition module 41, a matching module 42 and a processing module 43.
The obtaining module 41 is configured to obtain a user-activity knowledge graph according to the user information table and the activity information table.
The user information table comprises at least one activity and a corresponding relation of interest user groups, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identification. The activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification. The user-knowledge graph comprises an association relation between an interested user and an activity identifier, user attributes of the interested user and activity attributes corresponding to an activity scheme, wherein the activity attributes are activity topic information determined according to the activity scheme.
The matching module 42 is configured to match the topic keyword with the user-activity knowledge graph to obtain the target activity topic information.
The processing module 43 is configured to obtain a target user corresponding to the topic keyword according to the target activity scheme and the association relationship corresponding to the target activity topic information. The target user is at least one interested user associated with the target activity topic information.
It should be appreciated that the obtaining module 41, the matching module 42 and the processing module 43 may cooperatively implement the activity document recommendation method and possible sub-steps thereof provided in any of the above embodiments.
An embodiment of the present application provides an electronic device, as shown in fig. 9, and fig. 9 is a schematic block diagram of the electronic device provided in the embodiment of the present application. The electronic device 60 comprises a memory 61, a processor 62 and a communication interface 63. The memory 61, the processor 62 and the communication interface 63 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 61 may be used to store software programs and modules, such as program instructions/modules corresponding to the activity document recommendation method provided in the embodiments of the present application, and the processor 62 executes the software programs and modules stored in the memory 61, thereby performing various functional applications and data processing. The communication interface 63 may be used for communication of signaling or data with other node devices. The electronic device 60 may have a plurality of communication interfaces 63 in this application.
The Memory 61 may be, but is not limited to, a random access Memory (Random Access Memory, RAM), a Read Only Memory (ROM), a programmable Read Only Memory (Programmable Read-Only Memory, PROM), an erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor 62 may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
The electronic device 60 may implement any of the activity document recommendation methods provided herein. The electronic device 60 may be, but is not limited to, a cell phone, tablet, notebook, server, or other electronic device with processing capabilities.
The present embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements an activity document recommendation method according to any of the foregoing embodiments. The computer readable storage medium may be, but is not limited to, a usb disk, a removable hard disk, ROM, RAM, PROM, EPROM, EEPROM, a magnetic disk, or an optical disk, etc. various media capable of storing program codes.
In summary, the application provides an activity document recommending method, an activity document recommending device, electronic equipment and a storage medium, and relates to the field of data processing. The activity document recommending method comprises the following steps: acquiring a user-activity knowledge graph according to the user information table and the activity information table; the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identification; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-knowledge graph comprises an association relation between an interested user and an activity identifier, a user attribute of the interested user and an activity attribute corresponding to an activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme; matching the topic keywords with the user-activity knowledge graph to obtain target activity topic information; obtaining a target user corresponding to the topic keyword according to the target activity scheme and the association relation corresponding to the target activity topic information; the target user is at least one interested user associated with the target activity topic information. By using the method provided by the application, the target activity topic information matched with the topic keywords can be obtained through the user-activity knowledge graph, so that the target user corresponding to the topic keywords is obtained, the manual activity prediction is avoided, and the user participation condition corresponding to the topic keywords can be predicted by combining the historical data.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily conceivable by those skilled in the art within the technical scope of the present application should be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (9)
1. A method of event document recommendation, the method comprising:
acquiring a user-activity knowledge graph according to the user information table and the activity information table;
the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identifier; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-activity knowledge graph comprises an association relation between the interested user and the activity identifier, a user attribute of the interested user and an activity attribute corresponding to the activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme;
acquiring a theme keyword input by a worker, and mapping the theme keyword into a dense vector;
acquiring cosine similarity between the dense vector and each activity topic information in the user-activity knowledge graph;
taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity;
taking the activity theme information corresponding to the target similarity as target activity theme information;
obtaining a target user corresponding to the topic keyword according to the target activity scheme corresponding to the target activity topic information and the association relation; the target user is at least one of the interested users associated with the target activity topic information.
2. The method of claim 1, wherein the user information table is obtained by:
judging whether a user to be determined has an interaction process with a first activity during the activity of the first activity; the first activity is any one of the at least one activity;
if yes, the user to be determined is used as a first interested user of the first activity;
and associating the first interested user with the first activity to obtain the user information table.
3. The method of claim 2, wherein the activity information table is obtained by:
acquiring an activity scheme of the first activity; the activity scheme is characterized by a propaganda document adopted for propaganda of the first activity, and the propaganda document comprises a plurality of activity theme information;
obtaining user evaluation information of the first activity; the user evaluation information is activity evaluation of the first activity by interested users of the first activity;
and establishing a corresponding relation between the first activity and the propaganda document, and recording the propaganda document to obtain the activity information table.
4. The method of claim 3, wherein establishing the correspondence between the first campaign and the promotional document and recording the promotional document to obtain the campaign information list comprises:
extracting a plurality of activity theme information in the propaganda text;
establishing a corresponding relation between the first activity and the plurality of activity theme information;
and recording the corresponding relation and the propaganda document to obtain the activity information table.
5. The method of claim 1, wherein the first condition is cosine similarity being greater than or equal to a similarity threshold;
taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity, wherein the method comprises the following steps:
judging whether the first cosine similarity is larger than or equal to the similarity threshold value or not; the first cosine similarity is any one of the cosine similarities;
if yes, the first cosine similarity is taken as the target similarity.
6. The method of claim 1, wherein obtaining the target user corresponding to the topic keyword according to the association relationship between the target activity scheme corresponding to the target activity topic information and the association relationship comprises:
taking the activity scheme of the target activity theme information as a target activity scheme;
matching the activity identifier corresponding to the target activity scheme with the association relation to obtain a target user; the target user includes all interested users associated with the target activity scheme.
7. An activity document recommendation device, the device comprising:
the acquisition module is used for acquiring a user-activity knowledge graph according to the user information table and the activity information table;
the user information table comprises at least one activity and a corresponding relation of interest user groups thereof, wherein the interest user groups comprise at least one interest user with participation expectations for the at least one activity, and each activity is provided with an activity identifier; the activity information table is the corresponding relation between the activity identification and the activity scheme corresponding to the activity identification; the user-activity knowledge graph comprises an association relation between the interested user and the activity identifier, a user attribute of the interested user and an activity attribute corresponding to the activity scheme, wherein the activity attribute is activity topic information determined according to the activity scheme;
the matching module is used for acquiring the topic keywords input by the staff and mapping the topic keywords into dense vectors; acquiring cosine similarity between the dense vector and each activity topic information in the user-activity knowledge graph; taking the cosine similarity meeting the first condition in all the cosine similarities as the target similarity; taking the activity theme information corresponding to the target similarity as target activity theme information;
the processing module is used for obtaining a target user corresponding to the topic keyword according to the target activity scheme corresponding to the target activity topic information and the association relation; the target user is at least one of the interested users associated with the target activity topic information.
8. An electronic device comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being executable to implement the method of any one of claims 1-6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011240904.3A CN112348638B (en) | 2020-11-09 | 2020-11-09 | Activity document recommending method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011240904.3A CN112348638B (en) | 2020-11-09 | 2020-11-09 | Activity document recommending method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112348638A CN112348638A (en) | 2021-02-09 |
| CN112348638B true CN112348638B (en) | 2024-02-20 |
Family
ID=74429371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011240904.3A Active CN112348638B (en) | 2020-11-09 | 2020-11-09 | Activity document recommending method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348638B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110765753A (en) * | 2019-12-27 | 2020-02-07 | 广东博智林机器人有限公司 | Method, system, computer device and storage medium for generating file |
| CN110837552A (en) * | 2019-09-30 | 2020-02-25 | 口口相传(北京)网络技术有限公司 | Diet information recommendation method and device |
| CN111177559A (en) * | 2019-12-30 | 2020-05-19 | 中国联合网络通信集团有限公司 | Text travel service recommendation method and device, electronic equipment and storage medium |
| CN111311351A (en) * | 2020-01-15 | 2020-06-19 | 上海风秩科技有限公司 | File recommendation method and device, computer equipment and readable storage medium |
| US10733236B1 (en) * | 2016-12-16 | 2020-08-04 | Veritas Technologies Llc | Systems and methods for producing message search recommendations |
| CN111488462A (en) * | 2020-04-02 | 2020-08-04 | ***通信集团江苏有限公司 | Recommendation method, device, equipment and medium based on knowledge graph |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9466071B2 (en) * | 2011-11-16 | 2016-10-11 | Yahoo! Inc. | Social media user recommendation system and method |
| CN108268619B (en) * | 2018-01-08 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| JP7051724B2 (en) * | 2019-01-21 | 2022-04-11 | 株式会社日立製作所 | How to present useful information to achieve the purpose of the computer system and the target. |
-
2020
- 2020-11-09 CN CN202011240904.3A patent/CN112348638B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10733236B1 (en) * | 2016-12-16 | 2020-08-04 | Veritas Technologies Llc | Systems and methods for producing message search recommendations |
| CN110837552A (en) * | 2019-09-30 | 2020-02-25 | 口口相传(北京)网络技术有限公司 | Diet information recommendation method and device |
| CN110765753A (en) * | 2019-12-27 | 2020-02-07 | 广东博智林机器人有限公司 | Method, system, computer device and storage medium for generating file |
| CN111177559A (en) * | 2019-12-30 | 2020-05-19 | 中国联合网络通信集团有限公司 | Text travel service recommendation method and device, electronic equipment and storage medium |
| CN111311351A (en) * | 2020-01-15 | 2020-06-19 | 上海风秩科技有限公司 | File recommendation method and device, computer equipment and readable storage medium |
| CN111488462A (en) * | 2020-04-02 | 2020-08-04 | ***通信集团江苏有限公司 | Recommendation method, device, equipment and medium based on knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112348638A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | A bibliometric analysis of topic modelling studies (2000–2017) | |
| US9767166B2 (en) | System and method for predicting user behaviors based on phrase connections | |
| CN108804450B (en) | Information pushing method and device | |
| CN105528388B (en) | Search recommendation method and device | |
| CN107526718B (en) | Method and device for generating text | |
| US20150032753A1 (en) | System and method for pushing and distributing promotion content | |
| CN112380331A (en) | Information pushing method and device | |
| US10002187B2 (en) | Method and system for performing topic creation for social data | |
| CN111552880A (en) | Data processing method, device and medium based on knowledge graph and electronic equipment | |
| CN110427453B (en) | Data similarity calculation method, device, computer equipment and storage medium | |
| CN110008396B (en) | Object information pushing method, device, equipment and computer readable storage medium | |
| Saia et al. | A semantic approach to remove incoherent items from a user profile and improve the accuracy of a recommender system | |
| CN109947903B (en) | Idiom query method and device | |
| CN111191111A (en) | Content recommendation method, device and storage medium | |
| CN111914188A (en) | Method, system, device and storage medium for selecting recommendation target user | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| Chen et al. | Wsdm cup 2018: Music recommendation and churn prediction | |
| CN112650942A (en) | Product recommendation method, device, computer system and computer-readable storage medium | |
| CN111538830A (en) | French retrieval method, French retrieval device, computer equipment and storage medium | |
| CN111125305A (en) | Hot topic determination method and device, storage medium and electronic equipment | |
| CN108470289B (en) | Virtual article issuing method and equipment based on E-commerce shopping platform | |
| CN108021713B (en) | Document clustering method and device | |
| CN110750708A (en) | Keyword recommendation method and device and electronic equipment | |
| CN112348638B (en) | Activity document recommending method and device, electronic equipment and storage medium | |
| CN113743973B (en) | Method and device for analyzing market hotspot trend |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240111 Address after: 200,030 Unit 5B03, Floor 5, Building 2, No. 277, Longlan Road, Xuhui District, Shanghai Applicant after: SHANGHAI SECOND PICKET NETWORK TECHNOLOGY CO.,LTD. Address before: Unit 5b04, 5th floor, building 2, 277 Longlan Road, Xuhui District, Shanghai 200030 Applicant before: Shanghai Fengzhi Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |