CN112101012B - Interactive domain determining method and device, electronic equipment and storage medium - Google Patents
Interactive domain determining method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112101012B CN112101012B CN202011027147.1A CN202011027147A CN112101012B CN 112101012 B CN112101012 B CN 112101012B CN 202011027147 A CN202011027147 A CN 202011027147A CN 112101012 B CN112101012 B CN 112101012B
- Authority
- CN
- China
- Prior art keywords
- target
- interaction
- candidate
- categories
- field
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000002452 interceptive effect Effects 0.000 title description 5
- 230000003993 interaction Effects 0.000 claims abstract description 420
- 230000006399 behavior Effects 0.000 claims abstract description 129
- 230000015654 memory Effects 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 abstract description 22
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses an interaction field determining method, an interaction field determining device, electronic equipment and a storage medium, and relates to the fields of big data processing and the like. The specific implementation scheme is as follows: acquiring text information corresponding to N interaction behaviors of a target user respectively; wherein N is an integer greater than or equal to 1; based on the text information respectively corresponding to the N interaction behaviors, determining candidate interaction field categories and candidate keywords respectively corresponding to the N interaction behaviors; and generating target interaction field information of the target user based on the candidate interaction field category and the candidate keyword which are respectively corresponding to the N interaction behaviors.
Description
Technical Field
The present disclosure relates to the field of computer technology. The present disclosure relates in particular to the field of big data processing.
Background
The user's behavior on the internet can reflect the user's interest preferences. And it makes sense to distinguish between the interactive behavior and browsing behavior of the user. A part of interest points of the user are reflected in the preference of browsing information on the internet; another part of the points of interest are reflected in the enjoyment of discussion or interaction with other users on the web. The degree and field of these two points of interest are different and require a distinguishing process.
However, in the prior art, most of user text information is collected as much as possible to perform interest point classification scoring, and no division of interaction fields is performed for users, so that description of user features cannot be performed abundantly and comprehensively.
Disclosure of Invention
The disclosure provides an interaction field determining method, an interaction field determining device, electronic equipment and a storage medium.
According to an aspect of the present disclosure, there is provided an interaction field determining method, including:
Acquiring text information corresponding to N interaction behaviors of a target user respectively; wherein N is an integer greater than or equal to 1;
Based on the text information respectively corresponding to the N interaction behaviors, determining candidate interaction field categories and candidate keywords respectively corresponding to the N interaction behaviors;
And generating target interaction field information of the target user based on the candidate interaction field category and the candidate keyword which are respectively corresponding to the N interaction behaviors.
According to another aspect of the present disclosure, there is provided an interaction field determining apparatus, including:
the acquisition module is used for acquiring text information corresponding to N interaction behaviors of the target user respectively; wherein N is an integer greater than or equal to 1;
The text analysis module is used for determining candidate interaction field categories and candidate keywords corresponding to the N interaction behaviors respectively based on the text information corresponding to the N interaction behaviors respectively;
And the interaction domain information generation module is used for generating target interaction domain information of the target user based on the candidate interaction domain categories and the candidate keywords respectively corresponding to the N interaction behaviors.
According to an aspect of the present disclosure, there is provided an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the aforementioned method.
According to an aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the aforementioned method.
According to an aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described above.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow chart of an interaction domain determining method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an interaction domain information composition according to an embodiment of the present disclosure;
FIG. 3 is a second schematic diagram of the composition of interaction domain information according to an embodiment of the disclosure;
FIG. 4 is a second flowchart of an interaction domain determination method according to an embodiment of the disclosure;
FIG. 5 is a schematic diagram of an interaction domain determining apparatus according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram II of an interaction domain determining apparatus according to an embodiment of the present disclosure;
Fig. 7 is a block diagram of an electronic device for implementing an interaction domain determining method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The embodiment of the disclosure provides an interaction field determining method, as shown in fig. 1, including:
s101: acquiring text information corresponding to N interaction behaviors of a target user respectively; wherein N is an integer greater than or equal to 1;
S102: based on the text information respectively corresponding to the N interaction behaviors, determining candidate interaction field categories and candidate keywords respectively corresponding to the N interaction behaviors;
s103: and generating target interaction field information of the target user based on the candidate interaction field category and the candidate keyword which are respectively corresponding to the N interaction behaviors.
The text information corresponding to the N interaction behaviors of the target user may be: and acquiring text information corresponding to the N interaction behaviors of the target user respectively within a preset duration.
The preset duration may be set according to actual situations, for example, the interaction behavior of the target user within 1 day may be obtained, and the number of times of all the interaction behaviors of the target user within 1 day is recorded as N times. It should be understood that the number of interactions performed by the target user per day may be different, and accordingly, N may be different when the foregoing steps are performed at different times. For example, the interaction behavior of the target user on day 1 is 1, N is 1, the interaction behavior of the target user on day 2 is 10, and N is 10.
The method for acquiring the interaction behavior of the target user specifically may be: and acquiring interaction behaviors between the target user and other users from the user relationship network.
Wherein, the user relation network may be: and a relationship network constructed by taking the users as nodes and taking the interaction behavior between the users as edges. When a user is a node, the node may include attributes of the user, such as a base attribute of the user, where the base attribute may be a gender, an age, and the like of the user. The interaction behavior may be an interaction generated between one user and one or more other users, for example, if the target user performs any of forwarding, commenting, focusing, etc. on the information published by the user a in an application of the internet, then the interaction behavior exists between the target user and the user a.
Further, the interaction behavior between the target user and one or more other users may have corresponding text information, for example, the target user reviews the information posted by the user a, and the review information is the text information corresponding to the one-time interaction behavior; or the target user forwards the information published by the user B, and the information forwarded by the target user can be text information of one interaction behavior.
That is, the interaction behavior of the target user may correspond to different one or more other users, or the interaction behavior of the target user may include the interaction behavior generated by the target user and the same other user. It should be understood that, in this embodiment, the interaction behavior between the target user and the other user is not distinguished, and only the target user is used as a reference, all the interaction behaviors of the target user within a preset duration are obtained, and then corresponding text information is respectively obtained based on all the interaction behaviors of the target user within the preset duration.
Based on the text information corresponding to the N interaction behaviors, determining the candidate interaction domain category and the candidate keyword corresponding to the N interaction behaviors may be: and analyzing the text information corresponding to each interaction behavior to obtain candidate keywords corresponding to the text information of each interaction behavior, and determining candidate interaction field categories corresponding to each interaction behavior based on the candidate keywords.
It should be understood that the candidate keywords corresponding to the text information corresponding to the same interaction behavior may be one or more. For example: the text information corresponding to the user interaction behavior comprises 'I like A and also like B', and the keywords corresponding to the text information can comprise 'A' and 'B'. Accordingly, the same text message may correspond to one or more interaction domain categories, and the description is continued with the above example, for example, the keyword a and the keyword B belong to different preset categories, and then the text message may correspond to two interaction domain categories.
Further, generating target interaction field information of the target user based on the candidate interaction field categories and the candidate keywords respectively corresponding to the N interaction behaviors; the target interaction field information may be an interaction field tag of the target user. It should be noted that the finally generated target interaction field information may include a target interaction field category and a target keyword, where the target interaction field category may be obtained by summarizing candidate interaction field categories corresponding to N interaction behaviors respectively.
In this way, text information in the interaction behavior of the target user can be extracted, the candidate interaction field category and the candidate keyword corresponding to each text information can be determined based on one or more text information, and the target interaction field information of the target user can be determined based on the candidate interaction field category and the candidate keyword corresponding to all text information of the target user. Therefore, the relevant information about the interaction field can be added in the characteristics of the target user, and the characteristic dimension of the target user is increased, so that the characteristics of the target user are ensured to be acquired more accurately and comprehensively.
The determining, based on the text information respectively corresponding to the N interaction behaviors, the candidate interaction domain category and the candidate keyword respectively corresponding to the N interaction behaviors includes:
word segmentation is carried out on text information corresponding to the ith interaction action of the N interaction actions of the target user, and word segmentation results of the text information of the ith interaction action are obtained; wherein i is an integer of 1 or more and N or less;
Determining candidate keywords corresponding to the ith interaction behavior based on word segmentation results of the text information of the ith interaction behavior and preset keywords contained in an interest system; and determining a candidate first-level category and a candidate second-level category corresponding to the ith interaction behavior in the interest system based on the candidate keyword, and taking the candidate first-level category and the candidate second-level category as candidate interaction field categories corresponding to the ith interaction behavior.
Here, the text information of the ith interaction behavior may be any one of the text information of the N interaction behaviors, that is, the text information for each interaction behavior may be processed as described above, which is not described in detail.
The text information corresponding to the ith interaction behavior of the N interaction behaviors of the target user is segmented to obtain a segmentation result of the text information of the ith interaction behavior, punctuation marks in the text information of the ith interaction behavior can be removed, and the rest characters are split according to semantics to obtain one or more segmented words after being split as a segmentation result. For example, the text information of the user's interaction behavior includes "I like A-! The word segmentation result may include "me", "like", "a".
The interest system can be pre-constructed, and comprises preset categories and preset keywords; one or more preset first-level categories may be included in the preset categories, and one or more preset second-level categories may be included in each preset first-level category. And, each preset second-level category in the interest system may be preconfigured with one or more preset keywords.
For example, there are 2 preset first-level categories in the interest system, which are respectively preset first-level categories 1 and 2; the preset first-level category 1 comprises preset second-level categories 11 and 12, the preset second-level category 11 comprises preset keywords a1 and a2, and the preset second-level category 12 comprises preset keywords b; the preset first-level category 2 includes preset second-level categories 21 and 22, wherein the preset second-level category 21 includes preset keywords c1, c2 and c3, and the preset second-level category 22 includes preset keywords d1 and d2.
Correspondingly, each word segmentation in the word segmentation result of each text message can be matched with each preset keyword in the interest system, and one or more matched candidate keywords can be obtained; and each candidate keyword in the one or more candidate keywords can correspond to a preset second-level category, and the preset second-level category corresponds to a preset first-level category, and then each preset second-level category and the preset first-level category matched with each candidate keyword are used as a candidate second-level category and a candidate first-level category corresponding to each candidate keyword.
For example, if a certain text message matches the keyword a1, it may be determined that the text message corresponds to a preset second-level category 11 under the preset first-level category 1, where the preset first-level category 1 is used as a candidate first-level category, and the preset second-level category 11 is used as a candidate second-level category.
Further, the candidate first-level category and the candidate second-level category are used as candidate interaction field categories corresponding to the ith interaction behavior.
It should be noted that the ith interaction behavior may correspond to a plurality of candidate first-level categories and a plurality of second-level categories, and finally the candidate interaction domain categories of the ith interaction behavior may be divided based on the candidate second-level categories. For example, the ith interaction may correspond to two second-level categories, and the two second-level categories (candidate second-level categories 1 and 2 respectively) may belong to the same first-level category (referred to as candidate first-level category 1), and then the ith interaction may have two candidate interaction domain categories, namely candidate first-level category 1+candidate second-level category 1 and candidate first-level category 1+candidate second-level category 2. It should be noted that, the multiple second-level categories of the ith interaction behavior may belong to the same first-level category, or respectively belong to different first-level categories, or part of the second-level categories belong to the same first-level category, and the other part of the second-level categories respectively belong to other different first-level categories, which is not exhaustive in this embodiment.
Therefore, through the processing, the candidate first-level category and the candidate second-level category corresponding to the text information of each interaction behavior can be determined, and the candidate keywords of the candidate second-level category are obtained, so that the interaction field category corresponding to the target user is comprehensively obtained, and further, the determination of the target interaction field information aiming at the target user can be ensured to be more accurate and comprehensive.
Based on the above processing, candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors may be obtained, and further, in an embodiment, the generating the target interaction domain information of the target user based on the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors includes:
Collecting candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively to obtain a target interaction domain category comprising a target first-level category and a target second-level category and a target keyword; and taking the target interaction field category and the target keyword as target interaction field information of the target user.
Here, the collecting the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors respectively may include merging or deduplication, for example, merging if two or more interaction behaviors in the N interaction behaviors correspond to the same candidate interaction domain category; similarly, if two or more candidate keywords corresponding to the interaction behaviors are the same in the N interaction behaviors, merging or deduplication can be performed.
The same candidate interaction field category refers to the candidate first-level category and the candidate second-level category which are the same.
Through the processing, one or more collected candidate interaction domain categories and one or more candidate keywords can be obtained, the collected one or more candidate interaction domain categories are used as target interaction domain categories of the target user, and the collected one or more candidate keywords are used as target keywords of the target user.
That is, the target interaction field category may be one or more, and the target keyword may be one or more.
In this embodiment, the target interaction domain category and the target keyword are not associated, so that all target keywords of the target user and all target interaction domain categories can be obtained; and correlating all target keywords and target interaction field categories with the identification of the target user to obtain target interaction field information of the target user, or can be called as target interaction field labels of the target user.
The identification of the target user may be an identification number of the target user in the relational network, for example, a userID (user identification number) of the user.
For example, referring to fig. 2, in one example of the target interaction field information of the target user, the identification of the target user is associated with the target keywords collected by the target user, where the target keywords may include a target keyword 1-a target keyword 8; in addition, the target user's identification also associates target interaction field categories, each consisting of a target first level category and a target second level category, such as, for example, first level category 1/second level category 1, first level category 2/second level category 2, and first level category 3/second level category 3, as shown in fig. 2.
In another example, when the candidate first-level category and the candidate second-level category are used as the candidate interaction domain category corresponding to the ith interaction behavior, the method further includes:
determining the score of the candidate interaction field category corresponding to the ith interaction action and the score of the candidate keyword corresponding to the ith interaction action;
correspondingly, the method further comprises the steps of:
Determining target scores corresponding to the target interaction domain categories based on scores of candidate interaction domain categories corresponding to the N interaction behaviors respectively, and determining target scores of the target keywords based on scores of candidate keywords corresponding to the N interaction behaviors respectively.
In the process of determining the scores of the target interaction field categories, the scores of all candidate interaction field categories may be added to obtain a sum; collecting the same candidate interaction field category to obtain a target interaction field category, and adding the scores of the same candidate interaction field category to obtain sub-scores of the target interaction field category; dividing the sub-score of each target interaction field category by the sum to obtain the target score of each target interaction field category.
Similarly, in the process of determining the target score of the target keyword, the scores of all candidate keywords may be added to obtain a sum; collecting the same candidate keyword to obtain a target keyword, and adding the scores of the same candidate keyword to obtain a sub-score of the target keyword; dividing the sub-score of each target keyword by the sum to obtain the target score of each target keyword.
Further, in the determining of the target interaction field information, determining a target score of each target keyword and a target score of each target interaction field category may be further included. For example, referring to fig. 3, fig. 3 increases the target score of each target keyword based on fig. 2, and increases the target score of each target interaction domain category, which is not described in detail.
Therefore, through the processing, the target keywords and the target interaction field categories of each target user can be obtained, the target keywords and the target interaction field categories are combined to serve as target interaction field information of the target users, and the target interaction field labels of the target users can be set, so that user portraits can be more comprehensively carried out, information of interaction field dimensions corresponding to the users is obtained, more comprehensive information reference content is provided for subsequent processing, and the comprehensiveness and accuracy of subsequent processing are improved.
Further, in another embodiment, the generating the target interaction domain information of the target user based on the candidate interaction domain category and the candidate keyword corresponding to the N interaction behaviors respectively includes:
Collecting candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively to obtain M target interaction domain categories comprising a target first-level category and a target second-level category, and target keywords corresponding to the M target interaction domain categories respectively; wherein M is an integer greater than or equal to 1; the second-level target categories contained in different target interaction field categories in the M target interaction field categories are different;
And determining target interaction field information of the target user based on the M target interaction field categories and target keywords respectively corresponding to the M target interaction field categories.
The difference from the foregoing embodiment is that, in this embodiment, after the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors are collected, the obtained target keywords are associated with the target interaction domain categories, that is, different target interaction domain categories may correspond to different target keywords.
In addition, in the process of collecting, the target second-level category is used as a standard, and the M finally obtained target interaction field categories comprise different target second-level categories. It should also be noted that different target interaction field categories may include the same target first level category.
Here, the M target interaction domain categories and the target keywords corresponding to the M target interaction domain categories may be stored as M target interaction domain information of the target user or M target interaction domain labels called the target user.
Therefore, each target interaction field category and the corresponding target keyword can be associated, so that the content contained in the target interaction field information of the target user is divided more clearly, the subsequent searching or field recommending processing is facilitated, different keywords in different interaction field information can be more efficiently searched, and the subsequent processing efficiency can be further improved.
Based on the above embodiment, further, the determining the target interaction field information of the target user based on the M target interaction field categories and the target keywords corresponding to the M target interaction field categories includes the following two processing manners:
The processing mode 1 is that the M target interaction field categories and the target keywords corresponding to the M target interaction field categories are used as M target interaction field information of the target user;
Or alternatively
Processing mode 2, namely using the L target interaction field categories with the highest target scores among the M target interaction field categories and the target keywords corresponding to the L target interaction field categories as L target interaction field information of the target user; l is an integer of 1 or more and less than M.
In the processing mode 1, the M target interaction domain categories and the target keywords corresponding to the M target interaction domain categories are used as the M target interaction domain information of the target user, or may be M target interaction domain labels of the target user. Each target interaction field information (or target interaction field label) comprises an information four-tuple, and the information four-tuple can comprise: the identification of the target user, the target first level category, the target second level category, and one or more target keywords.
In the processing mode 2, the L target interaction field categories with the highest target scores in the M target interaction field categories and the target keywords corresponding to the L target interaction field categories are used as L target interaction field information of the target user; l is an integer of 1 or more and less than M.
The difference from the processing mode 1 is that the processing mode 1 stores or displays all the target interaction field information of the target user. The processing mode 2 only stores part of all the target interaction field information, specifically, the first L target interaction field categories with the highest target scores and the target keywords corresponding to the first L target interaction field categories can be stored, so as to obtain L target interaction field information of the target user.
For example, the target user finally gathers M target interaction domain categories, where M may be 100; sorting is performed based on the target scores of the M target interaction domain categories, the first L target interaction domain categories can be the first 50 target interaction domain categories serving as target users, the 50 target interaction domain categories and one or more target keywords corresponding to the 50 target interaction domain categories respectively are generated, and 50 target interaction domain information is stored or displayed.
Still further, when the candidate first-level category and the candidate second-level category are used as the candidate interaction domain category corresponding to the ith interaction behavior, the method further includes:
determining the score of the candidate interaction field category corresponding to the ith interaction behavior;
Correspondingly, when the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors are collected to obtain M target interaction domain categories including a target first-level category and a target second-level category, the method further includes:
and determining the target scores corresponding to the M target interaction domain categories based on the scores of the candidate interaction domain categories corresponding to the N interaction behaviors respectively.
The specific manner of determining the target score is the same as that of the foregoing embodiment, and will not be described here again.
In this way, each target interaction field category and corresponding target keywords can be associated, part of target interaction field categories with higher scores and corresponding target keywords can be selected from the target interaction field categories, and multiple target interaction field information of the target user is generated, so that the content contained in the target interaction field information of the target user is more clearly divided, the follow-up sub-field recommendation processing is facilitated, different keywords in different interaction field information can be more efficiently found, and the follow-up processing efficiency can be further improved; in addition, as the part of the target interaction field classification with the highest target score of the interaction field classification is selected, the characteristics of the preference of the interaction field with the preference of the target users can be obtained, the characteristics of the target users can be more accurately represented by combining the characteristics of the preference, and the degree of distinction among the target users is increased.
In still another embodiment of the present application, the method may further include: and recommending information for the target user based on the target interaction field information of the target user.
Here, the information recommendation may include: and determining one or more interaction fields with the highest attention of the target user according to the interaction field information of the target user, and further determining the recommended product for the target user based on the one or more interaction fields with the highest attention. For example, if the target user has the highest target score in the interaction domain information in a period of time, and the target interaction domain category is basketball of sports, then a court closest to the target user may be recommended, or shoes most suitable for playing basketball may be recommended for the user, which is not exhaustive.
Therefore, by acquiring the characteristics of the target interaction field information for the target user, more accurate recommended content can be provided for the user when the information recommendation is performed for the user later, so that more comprehensive information meeting personalized requirements is provided for the user.
An example illustration is provided in connection with fig. 4, comprising:
S41: establishing an interest system; here, the interest system may be pre-constructed, where the interest system includes a preset category and a preset keyword; one or more preset first-level categories may be included in the preset categories, and one or more preset second-level categories may be included in each preset first-level category. And, each preset second-level category in the interest system may be preconfigured with one or more preset keywords.
S42: respectively extracting text information in N interaction behaviors aiming at N interaction behaviors of a user; wherein N is an integer greater than or equal to 1.
For example, the text information in the interactive behavior may include a post Title, comment text, and the like.
S43: and respectively segmenting the text information in the N interaction behaviors, classifying and scoring the interest system based on the segmentation results respectively corresponding to the N interaction behaviors to obtain candidate interaction field categories, and obtaining candidate keywords. The candidate interaction field category may include a candidate first-level category and a candidate second-level category.
S44: and collecting each candidate interaction field category and each candidate keyword of the user, and generating target interaction field information of the user.
In one example, the target interaction area information may be expressed in the form of a quadruple, which may include an identification of the user, a target first-level category, a target second-level category, and a target keyword, such as expressed as: < user (or userID), cate (target first level category), cate2 (target second level category), social words >; the social word is the target keyword.
The above step S41 may be performed only once, and the target interaction area information of each user may be obtained by performing the steps S42 to S44 for each user based on the interest system constructed in step S41 in the specific process.
In still another embodiment of the present application, an apparatus for determining an interaction field is provided, as shown in fig. 5, including:
the acquiring module 51 is configured to acquire text information corresponding to N interaction behaviors of the target user respectively; wherein N is an integer greater than or equal to 1;
The text analysis module 52 is configured to determine candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively, based on the text information corresponding to the N interaction behaviors respectively;
The interaction domain information generating module 53 is configured to generate target interaction domain information of the target user based on the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors respectively.
The text analysis module 52 is configured to segment text information corresponding to an ith interaction behavior of the N interaction behaviors of the target user, and obtain a word segmentation result of the text information of the ith interaction behavior; wherein i is an integer of 1 or more and N or less;
Determining candidate keywords corresponding to the ith interaction behavior based on word segmentation results of the text information of the ith interaction behavior and preset keywords contained in an interest system; and determining a candidate first-level category and a candidate second-level category corresponding to the ith interaction behavior in the interest system based on the candidate keyword, and taking the candidate first-level category and the candidate second-level category as candidate interaction field categories corresponding to the ith interaction behavior.
The interaction domain information generating module 53 is configured to aggregate the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors respectively, so as to obtain a target interaction domain category including a target first-level category and a target second-level category, and a target keyword; and taking the target interaction field category and the target keyword as target interaction field information of the target user.
The interaction domain information generating module 53 is configured to aggregate, based on the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors, to obtain M target interaction domain categories including a target first-level category and a target second-level category, and target keywords corresponding to the M target interaction domain categories respectively; wherein M is an integer greater than or equal to 1; the second-level target categories contained in different target interaction field categories in the M target interaction field categories are different; and determining target interaction field information of the target user based on the M target interaction field categories and target keywords respectively corresponding to the M target interaction field categories.
The interaction domain information generating module 53 is configured to use the M target interaction domain categories and target keywords corresponding to the M target interaction domain categories as M target interaction domain information of the target user;
Or alternatively
The L target interaction field categories with the highest target scores in the M target interaction field categories and the target keywords corresponding to the L target interaction field categories are used as L target interaction field information of the target user; l is an integer of 1 or more and less than M.
Based on fig. 5, the apparatus provided in this embodiment, as shown in fig. 6, further includes:
And the recommending module 54 is configured to recommend information to the target user based on the target interaction field information of the target user.
According to embodiments of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.
Fig. 7 is a block diagram of an electronic device according to an interactive field determination method according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.
As shown in fig. 7, the electronic device includes: one or more processors 701, memory 702, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 701 is illustrated in fig. 7.
Memory 702 is a non-transitory computer readable storage medium provided by the present application. The memory stores instructions executable by the at least one processor to cause the at least one processor to perform the interaction field determination method provided by the present application. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to execute the interaction field determination method provided by the present application.
The memory 702 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the interaction domain determining method in the embodiment of the present application (e.g., the obtaining module 51, the text analysis module 52, the interaction domain information generating module 53, and the recommending module 54 shown in fig. 6). The processor 701 executes various functional applications of the server and data processing, i.e., implements the interaction field determination method in the above-described method embodiments, by running non-transitory software programs, instructions, and modules stored in the memory 702.
Memory 702 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the electronic device of the interaction area determination method, and the like. In addition, the memory 702 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 702 may optionally include memory remotely located with respect to the processor 701, which may be connected to the electronic device of the interaction area determination method via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the interaction field determining method may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or otherwise, in fig. 7 by way of example.
The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, trackpad, touchpad, pointer stick, one or more mouse buttons, trackball, joystick, and like input devices. The output device 704 may include a display apparatus, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service. The server may also be a server of a distributed system or a server that incorporates a blockchain.
According to the technical scheme of the embodiment of the application, the text information in the interaction behavior of the target user is extracted, the candidate interaction field category and the candidate keyword corresponding to each text information are determined based on one or more text information, and finally the target interaction field information of the target user is determined based on the candidate interaction field category and the candidate keyword corresponding to all the text information of the target user. Therefore, the relevant information about the interaction field can be added in the characteristics of the target user, and the characteristic dimension of the target user is increased, so that the characteristics of the target user are ensured to be acquired more accurately and comprehensively.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.
Claims (13)
1. An interaction field determination method, comprising:
Acquiring text information corresponding to N interaction behaviors of a target user respectively; wherein N is an integer greater than or equal to 1;
Based on the text information respectively corresponding to the N interaction behaviors, determining candidate interaction field categories and candidate keywords respectively corresponding to the N interaction behaviors;
generating target interaction field information of the target user based on the candidate interaction field categories and the candidate keywords respectively corresponding to the N interaction behaviors;
the determining, based on the text information corresponding to the N interaction behaviors, the candidate interaction domain category and the candidate keyword corresponding to the N interaction behaviors respectively includes:
word segmentation is carried out on text information corresponding to the ith interaction action of the N interaction actions of the target user, and word segmentation results of the text information of the ith interaction action are obtained; wherein i is an integer of 1 or more and N or less;
Determining candidate keywords corresponding to the ith interaction behavior based on word segmentation results of the text information of the ith interaction behavior and preset keywords contained in an interest system; and determining a candidate first-level category and a candidate second-level category corresponding to the ith interaction behavior in the interest system based on the candidate keyword, and taking the candidate first-level category and the candidate second-level category as candidate interaction field categories corresponding to the ith interaction behavior.
2. The method of claim 1, wherein the generating the target interaction field information of the target user based on the candidate interaction field category and the candidate keyword respectively corresponding to the N interaction behaviors includes:
Collecting candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively to obtain a target interaction domain category comprising a target first-level category and a target second-level category and a target keyword; and taking the target interaction field category and the target keyword as target interaction field information of the target user.
3. The method of claim 1, wherein the generating the target interaction field information of the target user based on the candidate interaction field category and the candidate keyword respectively corresponding to the N interaction behaviors includes:
Collecting candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively to obtain M target interaction domain categories comprising a target first-level category and a target second-level category, and target keywords corresponding to the M target interaction domain categories respectively; wherein M is an integer greater than or equal to 1; the second-level target categories contained in different target interaction field categories in the M target interaction field categories are different;
And determining target interaction field information of the target user based on the M target interaction field categories and target keywords respectively corresponding to the M target interaction field categories.
4. The method of claim 3, wherein the determining the target interaction field information of the target user based on the M target interaction field categories and the target keywords corresponding to the M target interaction field categories, respectively, comprises:
Taking the M target interaction field categories and the target keywords corresponding to the M target interaction field categories as M target interaction field information of the target user;
Or alternatively
The L target interaction field categories with the highest target scores in the M target interaction field categories and the target keywords corresponding to the L target interaction field categories are used as L target interaction field information of the target user; l is an integer of 1 or more and less than M.
5. The method of any of claims 1-4, wherein the method further comprises:
and recommending information for the target user based on the target interaction field information of the target user.
6. An interaction field determining apparatus, comprising:
the acquisition module is used for acquiring text information corresponding to N interaction behaviors of the target user respectively; wherein N is an integer greater than or equal to 1;
The text analysis module is used for determining candidate interaction field categories and candidate keywords corresponding to the N interaction behaviors respectively based on the text information corresponding to the N interaction behaviors respectively;
The interaction domain information generation module is used for generating target interaction domain information of the target user based on the candidate interaction domain categories and the candidate keywords which correspond to the N interaction behaviors respectively;
The text analysis module is used for word segmentation of text information corresponding to the ith interaction action of the N interaction actions of the target user, and a word segmentation result of the text information of the ith interaction action is obtained; wherein i is an integer of 1 or more and N or less; determining candidate keywords corresponding to the ith interaction behavior based on word segmentation results of the text information of the ith interaction behavior and preset keywords contained in an interest system; and determining a candidate first-level category and a candidate second-level category corresponding to the ith interaction behavior in the interest system based on the candidate keyword, and taking the candidate first-level category and the candidate second-level category as candidate interaction field categories corresponding to the ith interaction behavior.
7. The device of claim 6, wherein the interaction domain information generating module is configured to aggregate the candidate interaction domain categories and the candidate keywords corresponding to the N interaction behaviors respectively, so as to obtain a target interaction domain category including a target first-level category and a target second-level category, and a target keyword; and taking the target interaction field category and the target keyword as target interaction field information of the target user.
8. The device of claim 6, wherein the interaction domain information generating module is configured to aggregate candidate interaction domain categories and candidate keywords corresponding to the N interaction behaviors respectively, so as to obtain M target interaction domain categories including a target first-level category and a target second-level category, and target keywords corresponding to the M target interaction domain categories respectively; wherein M is an integer greater than or equal to 1; the second-level target categories contained in different target interaction field categories in the M target interaction field categories are different; and determining target interaction field information of the target user based on the M target interaction field categories and target keywords respectively corresponding to the M target interaction field categories.
9. The device of claim 8, wherein the interaction domain information generating module is configured to use the M target interaction domain categories and the target keywords corresponding to the M target interaction domain categories as M target interaction domain information of the target user;
Or alternatively
The L target interaction field categories with the highest target scores in the M target interaction field categories and the target keywords corresponding to the L target interaction field categories are used as L target interaction field information of the target user; l is an integer of 1 or more and less than M.
10. The apparatus according to any one of claims 6-9, wherein the apparatus further comprises:
and the recommending module is used for recommending information for the target user based on the target interaction field information of the target user.
11. An electronic device, comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.
13. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027147.1A CN112101012B (en) | 2020-09-25 | 2020-09-25 | Interactive domain determining method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011027147.1A CN112101012B (en) | 2020-09-25 | 2020-09-25 | Interactive domain determining method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112101012A CN112101012A (en) | 2020-12-18 |
| CN112101012B true CN112101012B (en) | 2024-04-26 |
Family
ID=73756536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011027147.1A Active CN112101012B (en) | 2020-09-25 | 2020-09-25 | Interactive domain determining method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101012B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468376B (en) * | 2021-05-31 | 2024-02-02 | 北京达佳互联信息技术有限公司 | Platform activity participation method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491463A (en) * | 2018-03-05 | 2018-09-04 | 科大讯飞股份有限公司 | Label determines method and device |
| WO2018176764A1 (en) * | 2017-03-30 | 2018-10-04 | 联想(北京)有限公司 | Data processing method and apparatus, and electronic device |
| WO2019041521A1 (en) * | 2017-08-29 | 2019-03-07 | 平安科技（深圳）有限公司 | Apparatus and method for extracting user keyword, and computer-readable storage medium |
| CN110113634A (en) * | 2019-03-22 | 2019-08-09 | 厦门理工学院 | A kind of information interaction method, device, equipment and storage medium |
| CN110569349A (en) * | 2019-07-30 | 2019-12-13 | 平安科技（深圳）有限公司 | Big data-based method, system, equipment and storage medium for pushing articles for education |
| CN110597988A (en) * | 2019-08-28 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Text classification method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220386B (en) * | 2017-06-29 | 2020-10-02 | 北京百度网讯科技有限公司 | Information pushing method and device |
-
2020
- 2020-09-25 CN CN202011027147.1A patent/CN112101012B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018176764A1 (en) * | 2017-03-30 | 2018-10-04 | 联想(北京)有限公司 | Data processing method and apparatus, and electronic device |
| WO2019041521A1 (en) * | 2017-08-29 | 2019-03-07 | 平安科技（深圳）有限公司 | Apparatus and method for extracting user keyword, and computer-readable storage medium |
| CN108491463A (en) * | 2018-03-05 | 2018-09-04 | 科大讯飞股份有限公司 | Label determines method and device |
| CN110113634A (en) * | 2019-03-22 | 2019-08-09 | 厦门理工学院 | A kind of information interaction method, device, equipment and storage medium |
| CN110569349A (en) * | 2019-07-30 | 2019-12-13 | 平安科技（深圳）有限公司 | Big data-based method, system, equipment and storage medium for pushing articles for education |
| CN110597988A (en) * | 2019-08-28 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Text classification method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于多特征的视频关联文本关键词提取方法;王万良;潘蒙;;浙江工业大学学报;20170225(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112101012A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11714816B2 (en) | Information search method and apparatus, device and storage medium | |
| CN111522967B (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN111125435B (en) | Video tag determination method and device and computer equipment | |
| CN111966890B (en) | Text-based event pushing method and device, electronic equipment and storage medium | |
| CN111782977B (en) | Point-of-interest processing method, device, equipment and computer readable storage medium | |
| CN111967262A (en) | Method and device for determining entity tag | |
| CN111522994A (en) | Method and apparatus for generating information | |
| CN112650907A (en) | Search word recommendation method, target model training method, device and equipment | |
| CN112541359B (en) | Document content identification method, device, electronic equipment and medium | |
| CN112380847B (en) | Point-of-interest processing method and device, electronic equipment and storage medium | |
| CN111858905B (en) | Model training method, information identification device, electronic equipment and storage medium | |
| CN112084150B (en) | Model training and data retrieval method, device, equipment and storage medium | |
| CN112052397B (en) | User characteristic generation method and device, electronic equipment and storage medium | |
| CN111563198B (en) | Material recall method, device, equipment and storage medium | |
| CN113516491B (en) | Popularization information display method and device, electronic equipment and storage medium | |
| CN113127669B (en) | Advertisement mapping method, device, equipment and storage medium | |
| CN111291192B (en) | Method and device for calculating triplet confidence in knowledge graph | |
| CN111090991A (en) | Scene error correction method and device, electronic equipment and storage medium | |
| CN111310058B (en) | Information theme recommendation method, device, terminal and storage medium | |
| CN112650919A (en) | Entity information analysis method, apparatus, device and storage medium | |
| CN111666417A (en) | Method and device for generating synonyms, electronic equipment and readable storage medium | |
| CN112101012B (en) | Interactive domain determining method and device, electronic equipment and storage medium | |
| CN111125445B (en) | Community theme generation method and device, electronic equipment and storage medium | |
| CN112100454A (en) | Searching method, searching device, electronic equipment and readable storage medium | |
| CN111931524A (en) | Method, apparatus, device and storage medium for outputting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |