CN116304236A - User portrait generation method and device, electronic equipment and storage medium - Google Patents
User portrait generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116304236A CN116304236A CN202310280091.8A CN202310280091A CN116304236A CN 116304236 A CN116304236 A CN 116304236A CN 202310280091 A CN202310280091 A CN 202310280091A CN 116304236 A CN116304236 A CN 116304236A
- Authority
- CN
- China
- Prior art keywords
- rule
- user
- data
- label
- tag
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 21
- 230000006399 behavior Effects 0.000 claims description 39
- 238000004590 computer program Methods 0.000 claims description 20
- 238000007654 immersion Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a user portrait generation method, a user portrait generation device, electronic equipment and a storage medium. The method comprises the following steps: determining portrayal rule terms based on historical user data of at least two applications; configuring each portrait rule item to a rule engine to obtain a label rule; and responding to the user portrait request, acquiring user data of at least one source end, and calling a label rule in a rule engine to process the user data into the user portrait. According to the embodiment of the invention, the portrait rule items are generated through the historical user data of a plurality of applications, and each portrait rule item is configured to the rule engine to obtain the tag rule, so that when a user is imaged, the tag rule can be called at any time by the user data under different applications to process the user data into the user portrait, the suitability of the corresponding application can be improved, the user portrait is more accurate, the tag rule is more flexible, and the data processing is more efficiently performed under the condition that the service is stably operated without stopping.
Description
Technical Field
The present invention relates to the field of big data processing technologies, and in particular, to a user portrait generating method, apparatus, electronic device, and storage medium.
Background
User portrayal, also known as user role, or virtual user representation, is an effective tool to delineate target users, contact user appeal and design direction. With the rapid development of big data and cloud services, user portraits are widely applied in various fields. As a virtual representation of an actual user, the user image is formed in a user character that is not built off the product and market, and the formed user character is required to have a primary audience and target group representing the performance representative product.
In the age background of big data, user data is spread over a network, each specific data of a user is abstracted into labels, and the user image is materialized by using the labels, so that the provision of targeted suggestions for service operation is the current mainstream research direction. However, in the prior art, in the process of processing user data to obtain a user tag and processing the tag, the user is mostly tagged based on manual screening, and the rule corresponding to the tag is not formulated, and when the tag rule needs to be changed, the user needs to be stopped for changing, so that the workload is large, the tag rule is inflexible, and the processing efficiency of the user data is low.
Disclosure of Invention
In view of the above, the invention provides a user portrait generating method, a device, an electronic device and a storage medium, which can improve the adaptability of corresponding applications, so that the user portrait is more accurate, the label rule is more flexible, and the data processing is more efficiently performed under the condition that the service stably runs without stopping.
According to one aspect of the present invention, an embodiment of the present invention provides a user portrait generating method, including:
determining portrayal rule terms based on historical user data of at least two applications;
configuring each portrait rule item to a rule engine to obtain a label rule; wherein the tag rule corresponds to corresponding tag information;
and responding to the user portrait request, acquiring user data of at least one source end, and calling the label rule in the rule engine to process the user data into the user portrait.
According to another aspect of the present invention, an embodiment of the present invention further provides a user portrait generating device, including:
a rule item determination module for determining portrayal rule items based on historical user data of at least two applications;
the rule determining module is used for configuring each portrait rule item to a rule engine to obtain a label rule; wherein the tag rule corresponds to corresponding tag information;
And the portrait determining module is used for responding to a user portrait request, acquiring user data of at least one source end, and calling the label rule in the rule engine to process the user data into a user portrait.
According to another aspect of the present invention, an embodiment of the present invention further provides an electronic device, where the terminal device includes:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the user portrait creation method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, an embodiment of the present invention further provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause a processor to implement the user portrait generating method according to any one of the embodiments of the present invention.
According to the embodiment of the invention, the portrait rule items are determined through at least two applied historical user data, and each portrait rule item is configured to the rule engine to obtain the label rule, so that when a user is portrait, the user data is processed into the user portrait according to different user data and the label rule in the rule engine is called, the label rule can be adjusted at any time under the conditions that the service is stably operated without stopping and the data processing is efficient, and therefore, the service is ensured to be stably operated when the user portrait analysis is carried out, and the label rule is more flexible.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a user portrait creation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a user portrait creation method according to another embodiment of the present invention;
FIG. 3 is a flowchart of another user portrait creation method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a system framework for user portrait creation according to an embodiment of the present invention;
FIG. 5 is a block diagram of a user portrait creating apparatus according to an embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the term "first" and the like in the description and the claims of the present invention and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In an embodiment, fig. 1 is a flowchart of a user portrait generating method according to an embodiment of the present invention, where the embodiment may be applicable to a case when a user is labeled based on big data to generate a user portrait. The method may be performed by a user portrayal generating device, which may be implemented in hardware and/or software, the user portrayal generating device being configurable in an electronic device.
As shown in fig. 1, the specific steps include:
s110, determining portrait rule items based on at least two applied historical user data.
The historical user data may be understood as the composition of user behavior data and user service data generated by the user history, and may include historical user data of one or more users under different applications. Portrayal rule terms may be understood as rule terms forming a user portrayal, which portrayal rule terms may comprise at least two rule terms. By way of example, portrait rule items may include a length of time a user takes while listening to a lesson, whether a listening state is completed, etc., which is not limited herein.
In this embodiment, at least two rule items may be set on the custom tab page by the historical user behavior data and the historical user business data of the user on at least two applications to form the portrait rule item, and of course, the historical user behavior data may include, but is not limited to, behavior data generated by the user browsing web pages in a historical manner, learning on a website in a historical manner, and related data generated on a front-end page by whether the user purchases a course on the website or not. The historical user service data can include, but is not limited to, basic information data of the user, namely personal information data set as public for the user, data in a back-end database and the like; in some embodiments, the portrait rules items may also be determined by preferences and/or needs of multiple users for knowledge data, which is not limited herein.
S120, configuring each portrait rule item to a rule engine to obtain a label rule; wherein the tag rule corresponds to corresponding tag information.
The rule engine may be called a business rule management system, and may be understood as separating business decisions and/or business rules from application programs, writing business decisions and/or business rules by using predefined semantic modules, and configuring and managing the business decisions and/or business rules when needed. The label rule may be understood as a label rule corresponding to labeling the user, and of course, the label rule may include a plurality of portrait rule items.
In this embodiment, according to the type corresponding to each portrait rule item, a tag rule is set on a custom page, and the valid and/or dead time corresponding to the tag information corresponding to the tag rule is set, and each portrait rule item in the valid time is freely combined to obtain the tag rule; in some embodiments, the basic attribute labels of the users corresponding to the channels can be determined firstly, the basic attribute labels of the channels are determined based on the basic attribute labels of the users, and the rule labels are determined based on the basic attribute labels of the users according to the preference of the users to the corresponding channels and the behavior track labels of the users; in addition, the label system can be set from multiple dimensions, and portrait rule items can be classified based on each label in the label system, so that label rules can be configured according to classification results.
It should be noted that, the configured tag rules correspond to the corresponding tag information, which may be understood that the tag rule and the corresponding tag information are in a one-to-one correspondence relationship, or may be that one tag information corresponds to the corresponding tag rule. Of course, the configured tag rule may be stored in a rule base or a knowledge base, the tag rule is loaded into a rule engine to supply system call, and service personnel manage the configured tag rule like management data through the rule engine, which may include but is not limited to querying, adding, updating, etc. the tag rule.
S130, responding to the user portrait request, acquiring user data of at least one source end, and calling a label rule in a rule engine to process the user data into the user portrait.
The user data may include user behavior data and user service data, and of course, the user behavior data may include, but is not limited to, behavior data generated by a user browsing a web page, learning on a web site, and the like, where the behavior data is related data generated on a front page. The user traffic data may include, but is not limited to, basic information data of the user, data in a back-end database, and the like. The user portraits can be understood as the user portraits obtained by tagging the user through analysis of certain behavioral data and business data of the user.
In this embodiment, user behavior data and user service data may be collected through different service platforms and methods, so that when a user portrait request is received, tag rules in a rule engine are matched with the user behavior data and the user service data, so that tag information corresponding to the tag rules is marked to a target user according to a rule matching result; in some embodiments, the user portrait is finally formed by searching the keywords in the user data and inputting the keywords into the named entity recognition model to obtain the corresponding entities, and obtaining the labels of the users according to the entities.
According to the technical scheme, the portrait rule items are determined through at least two applied historical user data, each portrait rule item is configured to the rule engine to obtain the label rule, so that when a user is portrait, the user data is processed into the user portrait according to different user data and the label rule in the rule engine, the suitability of the corresponding application can be improved, the user portrait is more accurate, the label rule is more flexible, and the data processing is performed more efficiently under the condition that the service is stably operated without stopping.
In an embodiment, the method further comprises:
acquiring a label rule and a management instruction of label information input by a user, and managing the label rule and the label information according to the management instruction;
the method for managing the tag rule and the tag information at least comprises one of the following steps:
and carrying out rule adjustment on the tag rule, wherein the adjustment comprises the following steps: modifying parameter information of the tag rule; modifying the tag information; setting effective and/or dead time for the tag information; and adding and/or deleting the label to the label rule and the label information.
The parameter information refers to relevant parameter information of the tag rule, and may include duration, learning type, purchase state, and the like.
In this embodiment, a management instruction of a tag rule and tag information input by a user is obtained in real time, and the tag rule and the tag information are managed according to the management instruction input by the user. In this embodiment, the manner of managing the tag rule and the tag information at least includes one of the following: and carrying out rule adjustment on the tag rule, wherein the adjustment comprises the following steps: modifying parameter information of the tag rule; modifying the tag information; setting effective and/or dead time for the tag information; the label rule and the label information are added and/or deleted, and the label rule can be adjusted at any time under the conditions that the service is stable to operate without stopping and the data processing is efficient, so that the service is stable to operate and the label rule is more flexible when user portrait analysis is performed. It can be understood that, the user can use the tag information on the line or lower limit the tag at any time by clicking or touching, and because each tag information corresponds to a corresponding validation time and a corresponding expiration time, the user can set the corresponding validation time and expiration time for each tag at any time, for example, the tag information corresponding to the tag rule is high in learning immersion, the tag information sets the validation time to 2023, 2, 8, 00, and the expiration time to 2023, 2, 15, 24, 00, and the tag information can be validated within the time period, and the time can be limited after the expiration of the time. Another example is: the edited tag information corresponds to a corresponding tag rule, and the tag rule can be adjusted and/or modified in real time, for example, a previously set learning preset time threshold is 30min, and the time threshold is adjusted to 50min at present.
In one embodiment, fig. 2 is a flowchart of still another user portrait creation method according to an embodiment of the present invention, where, on the basis of the above embodiments, a label rule is obtained for configuring each portrait rule item to a rule engine; and responding to the user portrait request, acquiring user data of at least one source end, and calling a label rule in a rule engine to process the user data into the user portrait for further refinement.
As shown in fig. 2, the user portrait creation method in this embodiment may specifically include the following steps:
s210, determining portrait rule items based on at least two applied historical user data.
S220, setting a tag rule and corresponding effective and/or dead time of tag information on the custom page according to the types of the portrait rule items.
In this embodiment, according to the type of each portrait rule item, a tag rule and a valid and/or dead time corresponding to tag information may be set in the custom page. It should be noted that the types of portrait rule items may include, but are not limited to, learning duration, job completion status, morning reading status, accumulated total learning duration, accumulated number of learning times, and the like. The learning time length may include a learning time length corresponding to live broadcast, a class listening time length corresponding to recorded broadcast, a job completion time length, a morning reading time length, and the like.
S230, freely combining the image rule items in the effective time to obtain a label rule.
In this embodiment, the business personnel selects the required rule on the page by clicking or touching, and the image rule items in the effective time are freely combined to generate the tag rule. Specifically, at least two rule items can be formed on the custom tag page according to historical user data and/or user requirements of at least two applications, and the at least two rule items are freely combined to obtain a tag rule; wherein the tag rule may be multi-layer rule set. For example, 1 ten thousand users exist, a class-listening time threshold can be found according to class-listening data of the 1 ten thousand users, and if class-listening time of 100 users in the 1 ten thousand users is more than 30 minutes, the class-listening time threshold can be set to be 30 minutes as a rule; another example is: the user learns the corresponding online time length in the live state, sets a first preset time threshold value as a formulated label rule, and the label information corresponding to the label rule is low in learning immersion degree; when the user learns the corresponding online time period to be greater than the first pre-time threshold value in the live state, the rule is defined as a label.
S240, responding to the user portrait request, collecting the user service data through the flink-cdc, and placing the user service data into the Kafka message queue.
In this embodiment, the link-cdc is a resource component capable of directly reading full data and incremental change data from a database such as MySQL, postgreSQL, and when receiving a user portrait request, the link-cdc may collect user service data, and put the user service data into a Kafka high throughput message queue, where Kafka provides a streaming function, and may asynchronously write in Kafka according to topics such as source data, indexes, and models, without affecting index calculation.
S250, responding to the user portrait request, acquiring user behavior data through the enterprise platform application, and placing the user behavior data into a Kafka message queue.
In this embodiment, in response to the user portrait request, the front end may also perform user behavior data collection from the enterprise platform application, and put the user behavior data into the Kafka high throughput message queue. The Kafka in this embodiment also provides a streaming function, and may be written asynchronously according to the subject of source data, index, model, etc.
S260, obtaining user service data and user behavior data from the Kafka message queue to form user data.
In this embodiment, user service data collected through a flink-cdc is obtained from a Kafka message queue, user behavior data collected through an enterprise platform application is obtained, the user behavior data includes but is not limited to behaviors in aspects of watching live lectures, recording and playing lectures, writing operations, reading books and the like, and the obtained user service data and the user behavior data are combined into user data so as to obtain a user portrait through processing the user data. It should be noted that, the embodiment of the invention can also correct unqualified user data so as to improve the accuracy of the big data analysis system.
In one embodiment, before invoking the tag rule within the rules engine to process the user data into a user representation, further comprising:
carrying out data preprocessing on user data; wherein the user data at least comprises user business data and user behavior data; wherein, the data preprocessing process at least comprises one of the following steps: corresponding supplementing and correcting the null value, the missing value and the abnormal value in the user data; deleting redundant characters and data in the user data, and cleaning the format content to integrate the data sources; carrying out normalization data processing on the user data, and carrying out data pre-aggregation operation on the user data after normalization processing; encrypting the user data to form an encrypted data signal; the validity of the user data is checked.
In this embodiment, after obtaining user data of at least one source end, data preprocessing needs to be performed on the collected user behavior data and user service data, where the data preprocessing process at least includes one of the following: corresponding supplementing and correcting the null value, the missing value and the abnormal value in the user data; deleting redundant characters and data in the user data, and cleaning the format content to integrate the data sources; carrying out normalization data processing on the user data, and carrying out data pre-aggregation operation on the user data after normalization processing; encrypting the user data to form an encrypted data signal; the validity of the user data is checked.
S270, searching a tag rule matched with the user data in a rule engine; wherein the user data at least comprises: user behavior data and user traffic data.
In this embodiment, the tag rule matching the user behavior data and the user service data may be searched in the rule engine, so as to find the matching tag rule by performing logic judgment of the tag rule on the user behavior data and the user service data. The pre-defined label rule is that the class listening time threshold is set to be 30 minutes, the operation completion state is completed within 5 minutes, and the corresponding label information is that the learning immersion degree is high; and analyzing the user data, searching for a target user of the tag rule, and marking the user matched with the tag rule as tag information with high learning immersion degree.
S280, determining label information corresponding to the label rule, and marking the label information to a target user according to the rule matching result to form a user portrait.
In this embodiment, the tag information is marked to the target user by determining tag information corresponding to the tag rule and performing the result of rule matching to form a user portrait. Specifically, the historical user data of at least two applications can be read from the database, and the corresponding tag rule and the tag information corresponding to the tag rule are determined according to the comparison between the relevant learning duration in the historical user data of at least two applications and a plurality of preset duration thresholds.
In one embodiment, determining tag information corresponding to a tag rule includes:
reading historical user data of at least two applications from a database; the historical user data at least comprises user historical live broadcast learning information and time length, recorded broadcast learning information and time length, job completion state information and completion time length and morning reading condition;
under the condition that the learning time length in the historical user data is longer than a first threshold time length, determining a label rule as a first label rule, wherein a label corresponding to the first label rule is low in learning immersion degree;
Under the condition that the learning time length in the historical user data is longer than a second threshold time length, determining the label rule as a second label rule, wherein the label corresponding to the second label rule is in learning immersion;
and under the condition that the learning time length in the historical user data is longer than a third threshold time length, determining the label rule as a third label rule, and determining the label corresponding to the second label rule as high in learning immersion degree, wherein the first threshold time length is shorter than the second threshold time length and shorter than the third threshold time length.
The first threshold duration, the second threshold duration and the third threshold duration are respectively preset duration thresholds, and the duration thresholds can be set by themselves through experience, human requirements and the like, so that the embodiment is not limited herein. It should be noted that, in order to facilitate understanding the tag rule and the tag information corresponding to each duration, the first threshold duration is set to be smaller than the second threshold duration and smaller than the third threshold duration. For example, the first threshold duration is 5 minutes, the second threshold duration is 20 minutes, and the first threshold duration is 40 minutes.
In this embodiment, historical user data of at least two applications may be read from a database; the historical user data at least comprises user historical live broadcast learning information and time length, recorded broadcast learning information and time length, job completion state information and completion time length and morning reading condition; under the condition that the learning time length in the historical user data is longer than a first threshold time length, determining a label rule as a first label rule, wherein a label corresponding to the first label rule is low in learning immersion degree; under the condition that the learning time length in the historical user data is longer than a second threshold time length, determining the label rule as a second label rule, wherein the label corresponding to the second label rule is in learning immersion; and under the condition that the learning time length in the historical user data is longer than a third threshold time length, determining the label rule as a third label rule, and determining the label corresponding to the second label rule as high in learning immersion degree, wherein the first threshold time length is shorter than the second threshold time length and shorter than the third threshold time length.
In this embodiment, the tag information corresponding to the tag rule may be determined to be tagged to the target user according to the result of the rule matching to form the user portrait. Specifically, marking the tag information to the target user according to the rule matching result may include: under the condition that the learning duration reaches a first threshold duration, marking the label with low learning immersion degree on a target user; under the condition that the learning duration reaches a second threshold duration, marking the labels in the learning immersion degree on the target user; and under the condition that the learning duration reaches a third threshold duration, marking the label with high learning immersion degree on the target user, and marking the label corresponding to the label rule on the target user as the user portrait of the target user.
According to the technical scheme, through determining portrait rule items based on at least two applied historical user data, tag rules and corresponding effective and/or failure time of tag information are set on a custom page according to types of portrait rule items; freely combining all image rule items in the effective time to obtain a label rule, and searching the label rule matched with the user data in a rule engine; the label information corresponding to the label rule is determined, and the label information is marked for the target user according to the rule matching result to form a user portrait, so that the suitability of the corresponding application can be further improved, the user portrait is more accurate, the label rule is more flexible, and the data processing is performed more efficiently under the condition that the service stably runs without stopping.
In an embodiment, in order to better understand a user portrait generating method, fig. 3 is a schematic flow diagram of another user portrait generating method according to an embodiment of the present invention, where in the embodiment of the present invention, an operation of managing the tag rule and tag information according to a management instruction may be adjusted at any time according to a user requirement, etc., and a portrait rule item is determined based on historical user data of at least two applications; the label rule is obtained by configuring each portrait rule item to a rule engine, and a user can adjust the label rule at any time under the condition that service stably runs without stopping. Therefore, when user label analysis is carried out, stable operation of service is guaranteed, and label rules are more flexible. It can be appreciated that the above method improves the flexibility of the user tag scenario.
As shown in fig. 3, the user portrait creation method includes the steps of:
s310, setting at least two rule items on the custom tag page according to historical user data and/or user requirements under at least two applications.
S320, freely combining at least two rule items to obtain a label rule; wherein the tag rule may be multi-layer rule set.
S330, acquiring a management instruction of the tag rule and the tag information input by a user, and managing the tag rule and the tag information according to the management instruction.
Wherein, the management at least comprises: modifying parameter information of the tag rule; setting effective and/or dead time for the tag information; and adding and/or deleting the label to the label rule and the label information.
S340, user business data are collected through a flink-cdc in response to the user portrait request, and user behavior data are collected through an enterprise platform application.
S350, performing data preprocessing on the user data to obtain the user data after the data preprocessing.
S360, searching a tag rule matched with the user data after data preprocessing in a rule engine.
And S370, determining the label information corresponding to the label rule, and marking the label information to the target user according to the rule matching result to form a user portrait.
S380, accessing the user portrait into each department so that each department can mine and use the user portrait.
In one embodiment, to facilitate a better understanding of the system framework of user portrayal generation, FIG. 4 is a schematic diagram of a system framework of user portrayal generation in accordance with one embodiment of the present invention.
As shown in fig. 4, a user portrait creation method included in a system frame diagram for user portrait creation according to an embodiment of the present invention includes:
a1, setting at least two rule items on a custom tag page according to historical user data and/or user requirements; and freely combining the at least two rule items to obtain tag rules, wherein each tag rule corresponds to a corresponding tag, and the tag rule can be input by a user in a front-end service page custom tag page to generate tag information.
a2, managing related labels: modifying parameter information of the tag rule, and setting effective and/or dead time for the tag information; and adding and/or deleting the label to the label rule and the label information.
a3, accessing data of an enterprise platform; the method specifically comprises the steps of user behavior data and business related data of enterprises: 1) The enterprise platform application performs front-end user behavior data acquisition, the data is acquired into a Kafka high-throughput message queue, and the preprocessed user data is loaded into a data storage platform of a batch processing layer; 2) And collecting the service data into a Kafka high-throughput message queue by using a flink cdc.
and a4, cleaning the acquired data, and performing operations such as data pre-aggregation.
and a5, searching a tag rule matched with the user data in a rule engine for the preprocessed user data.
and a6, determining label information corresponding to the label rule, and marking the label information to the target user according to the rule matching result to form a user portrait.
and a7, accessing the user portrait corresponding to the label information to the front end so as to mine and utilize the user portrait.
In one embodiment, fig. 5 is a block diagram of a user portrait generating device according to an embodiment of the present invention, where the device is suitable for use in labeling a user based on big data to generate a user portrait, and the device may be implemented by hardware/software. The user portrait generating method can be configured in the electronic equipment to realize the user portrait generating method in the embodiment of the invention. As shown in fig. 5, the apparatus includes: a rule term determination module 510, a rule determination module 520, and a representation determination module 530.
Wherein the rule term determining module 510 is configured to determine portrait rule terms based on historical user data of at least two applications;
a rule determining module 520, configured to configure each of the portrait rule items to a rule engine to obtain a tag rule; wherein the tag rule corresponds to corresponding tag information;
And the portrait determination module 530 is used for responding to a user portrait request, acquiring user data of at least one source end, and calling the label rule in the rule engine to process the user data into a user portrait.
According to the embodiment of the invention, the rule items are determined, the portrait rule items are determined through historical user data, the rule determining module configures each portrait rule item to the rule engine to obtain the label rule, and the portrait determining module is used for processing the user data into the user portrait according to different user data and calling the label rule in the rule engine when the user is portrait, so that the suitability of corresponding application can be improved, the user portrait is more accurate, the label rule is more flexible, and the data processing is more efficiently performed under the condition that the service is stably operated and is not stopped.
In an embodiment, the apparatus further comprises:
the management module is used for acquiring the label rule and the management instruction of the label information input by a user, and managing the label rule and the label information according to the management instruction;
the method for managing the tag rule and the tag information at least comprises one of the following steps:
Performing rule adjustment on the tag rule, wherein the adjustment comprises: modifying the parameter information of the label rule; modifying the tag information;
setting effective and/or dead time for the tag information;
and carrying out label new addition and/or deletion on the label rule and the label information.
In one embodiment, the rule determination module 520 includes:
the setting unit is used for setting the tag rule and the corresponding effective time and/or the corresponding dead time of the tag information on the custom page according to the type of each portrait rule item;
and the determining unit is used for freely combining all the portrait rule items in the effective time to obtain a label rule.
In one embodiment, representation determination module 530 includes:
the service data acquisition unit is used for acquiring user service data through a link-cdc and placing the user service data into a Kafka message queue;
the behavior data acquisition unit is used for acquiring user behavior data through an enterprise platform application and placing the user behavior data into the Kafka message queue;
and the composing unit is used for acquiring the user service data and the user behavior data from the Kafka message queue so as to compose user data.
In one embodiment, portrait determination module 530 further includes:
a matching unit, configured to search the rule engine for the tag rule that matches the user data; wherein the user data at least comprises: user behavior data and user business data;
and the portrait determining unit is used for determining label information corresponding to the label rule and marking the label information to a target user according to the rule matching result so as to form the portrait of the user.
In one embodiment, the image determining unit includes:
a reading subunit, configured to read historical user data of at least two applications from the database; the history user data at least comprises user history live broadcast learning information and time length, recorded broadcast learning information and time length, job completion state information and completion time length and morning reading condition;
the first determining subunit is configured to determine, when the learning time period in the historical user data is longer than a first threshold time period, that the tag rule is a first tag rule, and that the tag corresponding to the first tag rule is low in learning immersion;
the second determining subunit is configured to determine, when the learning time period in the historical user data is longer than a second threshold time period, that the tag rule is a second tag rule, where a tag corresponding to the second tag rule is in learning immersion;
And the third determining subunit is configured to determine that the tag rule is a third tag rule when the learning time period in the historical user data is longer than a third threshold time period, and the tag corresponding to the second tag rule is high in learning immersion, where the first threshold time period is less than the second threshold time period and is less than the third threshold time period.
In an embodiment, the apparatus further comprises:
the preprocessing unit is used for preprocessing the user data before the label rule in the rule engine is called to process the user data into a user portrait; wherein the user data at least comprises user business data and user behavior data; wherein, the data preprocessing process at least comprises one of the following steps:
corresponding supplementing and correcting the null value, the missing value and the abnormal value in the user data;
deleting redundant characters and data in the user data, and cleaning the format content to integrate the data sources;
carrying out normalized data processing on the user data, and carrying out data pre-aggregation operation on the normalized user data;
encrypting the user data to form an encrypted data signal;
And checking the validity of the user data.
In an embodiment, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Terminal devices may also represent various forms of mobile devices such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), 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 inventions described and/or claimed herein.
As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the terminal device 10 can also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the terminal device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the user portrayal generation method.
In some embodiments, the user portrayal generation method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the terminal device 10 via the ROM 12 and/or the communication unit 19. One or more of the steps of the user portrayal generation method described above may be performed when a computer program is loaded into RAM 13 and executed by processor 11. Alternatively, in other embodiments, processor 11 may be configured to perform the user portrayal generation method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), 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.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable user portrayal generating device, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a terminal device 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 a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the terminal device. 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), blockchain networks, and the internet.
The computing system may include clients and servers. 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 that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
In an embodiment, the present invention further comprises a computer program product comprising a computer program which, when executed by a processor, implements the user portrait generation method according to any of the embodiments of the present invention.
Computer program product in the implementation, the computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
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 invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. 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 invention should be included in the scope of the present invention.
Claims (10)
1. A user portrait creation method, comprising:
determining portrayal rule terms based on historical user data of at least two applications;
configuring each portrait rule item to a rule engine to obtain a label rule; wherein the tag rule corresponds to corresponding tag information;
and responding to the user portrait request, acquiring user data of at least one source end, and calling the label rule in the rule engine to process the user data into the user portrait.
2. The method according to claim 1, characterized in that the method further comprises:
acquiring the label rule and the management instruction of the label information input by a user, and managing the label rule and the label information according to the management instruction;
the method for managing the tag rule and the tag information at least comprises one of the following steps:
performing rule adjustment on the tag rule, wherein the adjustment comprises: modifying the parameter information of the label rule; modifying the tag information;
setting effective and/or dead time for the tag information;
and carrying out label new addition and/or deletion on the label rule and the label information.
3. The method of claim 1, wherein said configuring each of said portrait rule items to a rules engine results in at least two label rules, comprising:
setting the tag rule and the effective and/or dead time corresponding to the tag information respectively on a custom page according to the type of each portrait rule item;
and freely combining all the portrait rule items in the effective time to obtain a label rule.
4. The method of claim 1, wherein the obtaining user data of at least one source comprises
Collecting user service data through a flink-cdc, and putting the user service data into a Kafka message queue;
collecting user behavior data through enterprise platform application, and placing the user behavior data into the Kafka message queue;
and acquiring the user service data and the user behavior data from the Kafka message queue to form user data.
5. The method of claim 1, wherein said invoking the tag rule within the rules engine processes user data as a user representation comprises:
searching the tag rule matched with the user data in the rule engine; wherein the user data at least comprises: user behavior data and user business data;
and determining label information corresponding to the label rule, and marking the label information to a target user according to the rule matching result so as to form the user portrait.
6. The method of claim 5, wherein the determining tag information corresponding to the tag rule comprises:
Reading historical user data of at least two applications from a database; the history user data at least comprises user history live broadcast learning information and time length, recorded broadcast learning information and time length, job completion state information and completion time length and morning reading condition;
under the condition that the learning time length in the historical user data is longer than a first threshold time length, determining the label rule as a first label rule, wherein the label corresponding to the first label rule is low in learning immersion;
under the condition that the learning time length in the historical user data is longer than a second threshold time length, determining the label rule as a second label rule, wherein the label corresponding to the second label rule is in learning immersion;
and under the condition that the learning time length in the historical user data is longer than a third threshold time length, determining the label rule as a third label rule, and determining the label corresponding to the second label rule as high in learning immersion, wherein the first threshold time length is smaller than the second threshold time length and smaller than the third threshold time length.
7. The method of claim 1, further comprising, prior to said invoking the tag rule within the rules engine to process user data into a user representation:
Performing data preprocessing on the user data; wherein the user data at least comprises user business data and user behavior data; wherein, the data preprocessing process at least comprises one of the following steps:
corresponding supplementing and correcting the null value, the missing value and the abnormal value in the user data;
deleting redundant characters and data in the user data, and cleaning the format content to integrate the data sources;
carrying out normalized data processing on the user data, and carrying out data pre-aggregation operation on the normalized user data;
encrypting the user data to form an encrypted data signal;
and checking the validity of the user data.
8. A user tag generation apparatus, comprising:
a rule item determination module for determining portrayal rule items based on historical user data of at least two applications;
the rule determining module is used for configuring each portrait rule item to a rule engine to obtain a label rule; wherein the tag rule corresponds to corresponding tag information;
and the portrait determining module is used for responding to a user portrait request, acquiring user data of at least one source end, and calling the label rule in the rule engine to process the user data into a user portrait.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the user representation generation method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the user representation generation method of any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280091.8A CN116304236A (en) | 2023-03-14 | 2023-03-14 | User portrait generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310280091.8A CN116304236A (en) | 2023-03-14 | 2023-03-14 | User portrait generation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304236A true CN116304236A (en) | 2023-06-23 |
Family
ID=86797521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310280091.8A Pending CN116304236A (en) | 2023-03-14 | 2023-03-14 | User portrait generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304236A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150362A (en) * | 2023-09-11 | 2023-12-01 | 北京三维天地科技股份有限公司 | Main data tag marking method and system based on rule engine |
-
2023
- 2023-03-14 CN CN202310280091.8A patent/CN116304236A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150362A (en) * | 2023-09-11 | 2023-12-01 | 北京三维天地科技股份有限公司 | Main data tag marking method and system based on rule engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| CN110968695A (en) | Intelligent labeling method, device and platform based on active learning of weak supervision technology | |
| WO2020037917A1 (en) | User behavior data recommendation method, server and computer readable medium | |
| CN113239275B (en) | Information pushing method, device, electronic equipment and storage medium | |
| CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
| CN109189931A (en) | A kind of screening technique and device of object statement | |
| CN114090601B (en) | Data screening method, device, equipment and storage medium | |
| CN116304236A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN116049379A (en) | Knowledge recommendation method, knowledge recommendation device, electronic equipment and storage medium | |
| CN110674404A (en) | Link information generation method, device, system, storage medium and electronic equipment | |
| CN108021713B (en) | Document clustering method and device | |
| CN116823410B (en) | Data processing method, object processing method, recommending method and computing device | |
| CN115248890A (en) | User interest portrait generation method and device, electronic equipment and storage medium | |
| CN114358879A (en) | Real-time price monitoring method and system based on big data | |
| US11120204B2 (en) | Comment-based article augmentation | |
| CN114003567A (en) | Data acquisition method and related device | |
| CN111191142B (en) | Electronic resource recommendation method and device and readable medium | |
| CN113076254A (en) | Test case set generation method and device | |
| CN113327145A (en) | Article recommendation method and device | |
| CN114021788B (en) | Prediction method, prediction device, electronic equipment and storage medium | |
| CN115630170B (en) | Document recommendation method, system, terminal and storage medium | |
| US11907508B1 (en) | Content analytics as part of content creation | |
| CN111507366B (en) | Training method of recommendation probability model, intelligent completion method and related device | |
| CN111782949A (en) | Method and apparatus for generating information | |
| CN117421207A (en) | Intelligent evaluation influence point test method, intelligent evaluation influence point test device, computer equipment and storage medium |
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 |