CN115510324A - Method and device for determining label system, electronic equipment and storage medium - Google Patents
Method and device for determining label system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115510324A CN115510324A CN202211198256.9A CN202211198256A CN115510324A CN 115510324 A CN115510324 A CN 115510324A CN 202211198256 A CN202211198256 A CN 202211198256A CN 115510324 A CN115510324 A CN 115510324A
- Authority
- CN
- China
- Prior art keywords
- tag
- research entity
- research
- feature
- label
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (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 application provides a method and a device for determining a label system, electronic equipment and a storage medium, wherein the method for determining the label system comprises the following steps: acquiring an object corresponding to each data analysis requirement in the data analysis requirements for the target service; performing fine classification processing on corresponding objects by using the service attributes corresponding to the data analysis requirements to obtain research entities corresponding to each object; and constructing a corresponding label system of each research entity according to the characteristic information for describing each research entity and the characteristic information of each research entity to obtain the label systems of all objects. By adopting the technical scheme provided by the application, the data analysis requirements under different scenes can be met, the richness of the label system is improved, and the management cost of labels of all objects and the redundancy of label system construction are reduced.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining a tag system, an electronic device, and a storage medium.
Background
The label is used for identifying the characteristics of a certain object, in order to better describe the object, the characteristics of the object can be highlighted from different dimensions, the main characteristics of the certain object are highlighted through summarizing and inducing, and the individuality and different points of the object are highlighted based on the main characteristics. The label system is a system established according to a plurality of labels, in order to carry out systematic and normative label combing on objects contained in the whole enterprise or group, the content characteristics in the platform can be better known and the user characteristics in the platform can be better known through the label system, so that the user requirements can be better met.
At present, a label system is applied to items of individuation and precision, and main application scenes comprise: making a refined operation strategy, a customer relationship system CRM, an advertisement push mode and a personalized recommendation system; for example, a short video is labeled similar to ghost animals in a short video labeling system, and classified into a ghost animal video classification, so that the short video can be specifically and specifically recommended to users who like to watch ghost animals. However, since the client tag system is built according to actual scenes such as short video recommendation, several sets of tag systems are built for several scenes, and when the number of actual scenes increases, the tag repetition rate used between the scenes increases, the tag system is built more redundantly, and the management cost of tags gradually increases. Therefore, how to construct a tag system to reduce redundancy and management cost of tag system construction becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for determining a label system based on multiple objects, which are capable of determining a research entity of each object and characteristic information of each research entity by obtaining objects of data analysis requirements, thereby obtaining label systems of all objects, satisfying data analysis requirements in different scenes, improving the richness of the label system, and reducing the management cost of labels of each object and the redundancy of label system construction.
The application mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides a method for determining a tag system, where the method includes:
acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things;
for each data analysis demand, performing fine classification processing on the corresponding object by using the service attribute corresponding to the data analysis demand to obtain a plurality of research entities corresponding to the object corresponding to the data analysis demand;
for each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity;
and constructing a target label system aiming at all the objects by utilizing the constructed corresponding label system of each research entity.
Further, the step of constructing, for each research entity, a label system corresponding to the research entity according to the characteristic information describing the research entity includes:
aiming at each research entity, acquiring a feature tag corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
classifying the feature tags based on a seven-question analysis method aiming at each feature tag, determining the category to which the feature tag belongs from a plurality of pre-constructed categories, and mounting the feature tag under the category to which the original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
for each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a service tag system corresponding to the research entity;
and combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
Further, after constructing the label system corresponding to the research entity, the determining method further comprises:
for any feature tag, responding to a first operation aiming at the feature tag, and analyzing and processing target feature information under the feature tag;
alternatively, the first and second electrodes may be,
for any feature tag, responding to a second operation aiming at the feature tag, and analyzing and processing all feature information of the feature tag; wherein the first operation is an operation of acquiring at least one but not all target feature information under the feature tag; the second operation is an operation of acquiring all target feature information under the feature tag.
Further, the step of constructing a target tag system for all objects by using the constructed tag system corresponding to each research entity includes:
and combining the label systems corresponding to the research entities according to the objects to which the research entities belong by using the constructed label systems corresponding to the research entities to construct target label systems aiming at all the objects.
Further, the categories include at least one of:
a customer identification tag, a customer base tag, a customer time tag, a customer location tag, a customer product tag, a customer event tag, a customer statistics tag, and a customer rating tag.
Further, after the target tag system for all the objects is constructed, the determining method further includes:
in response to a third operation on a target object of a plurality of objects displayed in a first display page, displaying a plurality of research entities under the target object;
in response to a fourth operation directed at a target research entity of the plurality of research entities, displaying a tag system corresponding to the target research entity to analyze the feature tags according to user requirements; wherein the label system comprises category and feature labels under the target research entity.
In a second aspect, an embodiment of the present application further provides a device for determining a label system, where the device for determining a label system includes:
the acquisition module is used for acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements aiming at the target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things;
the processing module is used for performing fine classification processing on corresponding objects by utilizing the service attributes corresponding to the data analysis requirements aiming at each data analysis requirement to obtain a plurality of research entities corresponding to the objects corresponding to the data analysis requirements;
the construction module is used for constructing a label system corresponding to each research entity according to a plurality of characteristic information for describing the research entity;
and the determining module is used for constructing a target label system aiming at all the objects by utilizing the constructed label system corresponding to each research entity.
Further, when the building module is configured to build, for each research entity, a label system corresponding to the research entity according to the feature information for describing the research entity, the building module is specifically configured to:
aiming at each research entity, acquiring a feature tag corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
classifying the feature tags based on a seven-question analysis method aiming at each feature tag, determining the category to which the feature tag belongs from a plurality of pre-constructed categories, and mounting the feature tag under the category to which the original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
for each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a service tag system corresponding to the research entity;
and combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions being executable by the processor to perform the steps of the method of determining a tag architecture as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the method for determining a label system as described above.
The embodiment of the application provides a method, a device, an electronic device and a storage medium for determining a label system, wherein the method for determining the label system comprises the following steps: acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things; for each data analysis demand, performing fine classification processing on the corresponding object by using the service attribute corresponding to the data analysis demand to obtain a plurality of research entities corresponding to the object corresponding to the data analysis demand; for each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity; and constructing a target label system aiming at all the objects by utilizing the constructed corresponding label system of each research entity.
Therefore, by adopting the technical scheme provided by the application, the research entity of each object and the characteristic information of each research entity can be determined by acquiring the object of the data analysis requirement, so that the label systems of all the objects are obtained, the data analysis requirements under different scenes are met, the richness of the label systems is improved, and the management cost of the labels of all the objects and the redundancy of the label system construction are reduced.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart illustrating a method for determining a label hierarchy according to an embodiment of the present application;
fig. 2 is a flowchart illustrating another method for determining a label system according to an embodiment of the present application;
fig. 3 is a block diagram of a determination apparatus of a label hierarchy according to an embodiment of the present application;
fig. 4 is a second block diagram of a device for determining a label system according to an embodiment of the present application;
fig. 5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not intended to limit the scope of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, as generally described and illustrated in the figures herein, could be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
To enable one of ordinary skill in the art to utilize the present disclosure, the following embodiments are presented in conjunction with a specific application scenario "determination of a label system," and it will be apparent to one of ordinary skill in the art that the general principles defined herein may be applied to other embodiments and application scenarios without departing from the spirit and scope of the present disclosure.
The following method, apparatus, electronic device or computer-readable storage medium in the embodiments of the present application may be applied to any scenario in which a tag system needs to be determined, and the embodiments of the present application do not limit a specific application scenario, and any scheme for using the method, apparatus, electronic device and storage medium for determining a tag system provided in the embodiments of the present application is within the scope of protection of the present application.
It should be noted that the tag is used to identify the characteristics of an object, and in order to better describe the object, the characteristics of the object may be highlighted from different dimensions, and through summarization and summarization, the main features of an object are highlighted, so that the personality and different points of the object are highlighted. The label system is a system established according to a plurality of labels, in order to carry out systematic and normative label combing on objects contained in an entire enterprise or group, the content characteristics in the platform can be better known and the user characteristics in the platform can be better known through the label system, so that the user requirements can be better met through more sufficient understanding.
At present, a label system is applied to items of individuation and precision, and main application scenes comprise: the method comprises the following steps of making a refined operation strategy, a customer relationship system CRM, an advertisement push mode and a personalized recommendation system; for example, a short video is labeled with ghost-like labels in a short video label system, and is classified into a category of the ghost-like videos, so that the short video can be specifically and specifically recommended to users who like watching ghost. However, since the client tag system is built according to actual scenes such as short video recommendation, several sets of tag systems are built for several scenes, and when the number of actual scenes increases, the tag repetition rate used between the scenes increases, the tag system is built more redundantly, and the management cost of tags gradually increases. Therefore, how to construct a tag system to reduce redundancy and management cost of tag system construction becomes an urgent problem to be solved.
Based on this, the application provides a method, an apparatus, an electronic device and a storage medium for determining a label system, where the method for determining includes: acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things; for each data analysis requirement, performing fine classification processing on the corresponding object by using the service attribute corresponding to the data analysis requirement to obtain a plurality of research entities corresponding to the object corresponding to the data analysis requirement; for each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity; and constructing a target label system aiming at all objects by using the constructed corresponding label system of each research entity.
Therefore, by adopting the technical scheme provided by the application, the research entity of each object and the characteristic information of each research entity can be determined by acquiring the object of the data analysis requirement, so that the label systems of all objects are obtained, the data analysis requirements under different scenes are met, the richness of the label systems is improved, and the management cost of the labels of all objects and the redundancy of the label system construction are reduced.
For the purpose of facilitating an understanding of the present application, the technical solutions provided in the present application will be described in detail below with reference to specific embodiments.
Referring to fig. 1, fig. 1 is a flowchart of a method for determining a label system according to an embodiment of the present application, as shown in fig. 1, the method for determining includes:
s101, acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service;
in this step, the object includes any one of: people, things, relationships between people and people, relationships between people and things, and relationships between things and things. The target service may be a banking service or an insurance service, which is not limited herein. Before constructing a multi-object label system, firstly, it is clear which kind of object the label system is constructed, that is, the object of each data analysis requirement in the data analysis requirements is obtained; an object is an abstraction of a research entity in the objective world, with both physical and virtual objects. A great number of objects can be abstracted in the enterprise operation process, and the objects can be divided into three categories of 'people', 'objects' and 'relations' through summarizing the construction experience of a plurality of banks and a plurality of label systems. The people often have initiative and intelligence, can actively participate in social activities, actively play a promoting role, and are often the senders of relationships. An "object" is often passive and is the recipient of a relationship. "people" and "things" are objects of entity class, i.e. objects that are seen and touched, and "relationship" belongs to a virtual object, is the definition of the relation between two physical entities, and is some kind of connection that people and things, or people and people, things and things, etc. happen at a certain time.
For example, the data analysis requirement may be "analyzing the sex ratio of the low-risk loan customer group", may be "analyzing the total sales of the popular products in three days in the near future", may also be "analyzing the number of contracts made for certain numbers per month", and the like, and the data analysis requirement is targeted at "analyzing the sex ratio of the low-risk loan customer group" and is "person"; for a data analysis requirement of "analyzing total sales of popular products for nearly three days", the object of the data analysis requirement is "substance"; for a data analysis demand of "analyzing the number of contracts made per month", the object of the data analysis demand is "relationship".
S102, aiming at each data analysis requirement, performing fine classification processing on corresponding objects by using the service attribute corresponding to the data analysis requirement to obtain a plurality of research entities corresponding to the objects corresponding to the data analysis requirement;
in this step, the research entity is a specific description of the object, and each object may be classified according to the data analysis requirement, for example, when the object is "human", the research entity includes: retail customers, public customers, and business employees, etc.; where the subject is an "object", the research entities include: products and warehouses, etc.; when the object is a "relationship," the research entities include: events and contracts, etc., each research entity corresponds to a set of label systems.
S103, aiming at each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity;
in this step, each research entity under each object has a plurality of feature information, which may be attributes for describing the research entity; for example, if the data analysis requirement is "analyzing the gender ratio of the loan low risk customer group", the object is "person", the research entity is "retail customer", and the plurality of characteristic information for the retail customer includes: the job employment status is at job or away, the external overdue flag is overdue or not, the specific amount of overdue amount, the specific number of accumulated overdue times, and the sex of the client is male or female, etc.
It should be noted that, referring to fig. 2, for each research entity, a step of constructing a label system corresponding to the research entity according to feature information for describing the research entity is shown, and fig. 2 is a flowchart of another method for determining a label system provided in an embodiment of the present application, as shown in fig. 2, for each research entity, a step of constructing a label system corresponding to the research entity according to feature information for describing the research entity includes:
s201, aiming at each research entity, acquiring a feature label corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
illustratively, when the characteristic information is that the job employment status is at work or off work, the corresponding characteristic label is the job employment status; when the characteristic information is that the external overdue mark is overdue or not overdue, the corresponding characteristic label is the external overdue mark; when the characteristic information is the specific amount of overdue amount, the corresponding characteristic label is the overdue amount; when the feature information is the specific number of accumulated overdue times, the corresponding feature label is the accumulated overdue times; when the characteristic information is that the sex of the client is male or female, the corresponding characteristic label is the sex of the client.
S202, classifying the feature tags based on a seven-question analysis method aiming at each feature tag, determining the category to which the feature tag belongs in a plurality of pre-constructed categories, and mounting the feature tag under the category to which the original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
in the step, the categories have multiple levels, the first level category is a root category, and aiming at each level category in the multiple levels of categories, the level category belongs to the upper level category of the level category; for example, when the category is three-level, the first level category has a second level category below, the second level category has a third level category below, the number of the categories of each level is not limited, there may be a plurality of first level categories, each first level category has a plurality of second level categories below, each second level category has a plurality of third level categories below, each feature tag is mounted below the category of the corresponding level until the last level category is mounted, and the mounting is completed. The first level category includes at least one of: a customer identification tag, a customer base tag, a customer time tag, a customer location tag, a customer product tag, a customer event tag, a customer statistics tag, and a customer rating tag.
Here, the signature tags are refined based on the seven-query analysis method 5W2H (Who, when, where, what, how) and the customer's five core business processes at the bank (contact, business, contract, product, transaction). For example, in the banking business, it is first necessary to acquire personal information of a bank customer (Who), split it into important identification information that can be used to identify the customer and some basic information of the customer, and record When (When time dimension, mainly record the first and last time When the customer makes a trace in the bank), where (Where position dimension, mainly record the behavior of the customer in which institutions and network channels), what is done (What is done, what contact is made, what is done, what contract is signed, what product is purchased, what transaction is done, etc.), how to do this (How is recorded, how to do this (How is measured by How values, and finally, through the above information, to insights the customer behavior, the risk management ability is improved (Who, based on the above scientific information, constructs a comprehensive and comprehensive evaluation system according to an algorithm). To sum up, the first class categories are divided into eight categories, which are: the system comprises a client identification label, a client base label, a client time label, a client position label, a client product label, a client event label, a client statistical label and a client evaluation label. Wherein, the customer identification tag: a tag for client identification (client ID-Mapping) information translation; customer base label: characteristics such as customer basic information, customer identity information and customer relationship; a client time tag: the relation between the client and the date and time, and the time dimension are used for data statistics, indexes, label derivation and the like; customer location tag: the relation between the customer and the channel and the position, and the position dimension are used for data statistics, indexes, label derivation and the like; customer product labeling: the relationship between the client and the product and the service, and the service dimension are used for data statistics, index derivation, label derivation and the like; a customer event tag: the event occurrence process of business exchange between the client or the financial institution records characters, time, positions, events and the like; customer statistical label: the fact result of business exchange between the client and the financial institution records the measurement statistics of business process events, and basically represents the quantity value; customer evaluation label: and constructing comprehensive and scientific client evaluation characteristics based on the information description and information statistics recorded by the client event or the client fact.
Illustratively, each first-level category is subdivided into a plurality of second-level categories according to the type of each characteristic information, each second-level category is subdivided into a plurality of third-level categories according to the type of each characteristic information, and so on until the last-level category; for example, a certain first-level category is "customer base label", and the second-level category under the customer base label includes: basic information, wealth information, external consultation, and the like; the third category under the basic information includes: demographics, work information, contact information, and school information, among others; one first-level category is a customer statistical label, and the second-level category under the customer statistical label comprises: asset statistics, liability statistics, and transaction statistics, among others; the third category under liability statistics includes: loan statistics and credit card statistics, etc.
For example, there are three classes, and after determining a first class, a second class under the first class, and a third class under the second class, the feature tag is mounted to the first class to which the feature tag belongs, the second class under the first class, and the third class under the second class, layer by layer. The feature tag is a carrier of the data asset and is an attribute of the research entity of the object. To implement complete depiction of an object, feature tags need to be classified and mounted under corresponding categories. The feature tag is a continuous refining process for feature information of an object, so that the key point is continuous refining and is mounted layer by layer.
S203, aiming at each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a business tag system corresponding to the research entity;
deriving a new label through a characteristic label under a system label system to construct a business label system; illustratively, the feature label is "last marketing campaign participation date", and the "last marketing campaign participation date" can be converted into "campaign participation activity degree" through the acquired end date and a specific number of days (for example, 3 days) by a preset design mode, that is, a client within 3 days from the last marketing campaign participation date to the end date is regarded as a client participating in a high activity campaign; classifying the activity participation activity degree, and mounting the activity participation activity degree under a service label class constructed in advance to construct a service label system; the design mode, such as the end date and the specific number of days, can be a rule manually configured on the page in advance by a human.
And S204, combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
In the step, a service label system is derived according to the system label system, new labels are derived by self through different label design modes according to the actual service scene requirements and based on the characteristic labels in the system label system to meet the service use scene, and the service label system is constructed through the derived new labels. Here, the label system under each research entity under each object includes a system label system and a business label system, a plurality of label systems of each object can be obtained according to a plurality of research entities of each object, and label systems of all objects can be obtained according to a plurality of objects.
It should be noted that, after constructing the tag system corresponding to the research entity, the determining method further includes:
a) For any feature tag, responding to a first operation for the feature tag, and analyzing and processing target feature information under the feature tag;
b) Or, for any feature tag, responding to a second operation for the feature tag, and analyzing and processing all feature information of the feature tag; the first operation is an operation of acquiring at least one but not all target characteristic information under the characteristic label; the second operation is an operation of acquiring all target feature information under the feature tag.
In this step, when the feature tag has different feature information, a mapping relationship between the feature tag and a plurality of feature information is established, that is, the feature tag is a threshold tag; illustratively, when the feature label is gender, the corresponding feature information (threshold label) includes female and male; when the feature label is a city, the corresponding feature information includes beijing, tianjin, and ganglian, etc.
For example, when a first operation (for example, when the number of women in a certain passenger group is analyzed, the first operation may be an operation of selecting at least one but not all target feature information under the feature tag by means of mouse click or keyboard touch), the passenger group may be filtered by the target feature information (women) of the feature tag (gender); when responding to the second operation of the feature tag (for example, when analyzing the proportion of each gender in a certain guest group, the second operation may be an operation of selecting all target feature information under the feature tag by mouse click or keyboard touch), the gender proportion in the guest group may be analyzed through each feature information (female and male) of the feature tag (gender).
And S104, constructing a target label system aiming at all objects by using the constructed label system corresponding to each research entity.
It should be noted that, the step of constructing a target tag system for all objects by using the constructed tag system corresponding to each research entity includes:
1. and combining the label systems corresponding to the research entities according to the objects to which the research entities belong by using the constructed label systems corresponding to the research entities to construct target label systems aiming at all the objects.
In the step, a label system is determined according to the top-down design of each object through the steps of object erection, entity determination, classification, label hanging and threshold marking, so that a set of label systems of single objects is constructed. Meanwhile, the function expansion of a multi-object tag system is supported. The method comprises the steps of downloading standardized templates (namely, templates corresponding to categories, feature labels and feature information) on a platform, obtaining the categories, the feature labels and the feature information of all label systems, displaying the information of all label systems by switching the label systems on the platform, and performing subsequent application based on the label systems.
It should be noted that, after the target tag system for all the objects is constructed, the determining method further includes:
1) Displaying a plurality of research entities under a target object in response to a third operation on the target object in a plurality of objects displayed in a first display page;
2) Responding to a fourth operation aiming at a target research entity in the plurality of research entities, and displaying a label system corresponding to the target research entity so as to analyze the characteristic label according to the requirement of a user; wherein the label system comprises category and feature labels under the target research entity.
Illustratively, the method includes obtaining a target object (e.g., a person) and a plurality of research entities (e.g., retail customers, business customers, and employees) under the target object by responding to a third operation (where the third operation may be an operation of selecting the target object by mouse clicking or keyboard touching among the plurality of objects displayed on the first display page) of the first display page, obtaining a second display page by displaying the plurality of research entities on the first display page, and determining a target research entity (employee) corresponding to the fourth operation in response to a fourth operation (where the fourth operation may be an operation of selecting the target research entity by mouse clicking or keyboard touching among the plurality of research entities displayed on the second display page) of the target research entity among the plurality of research entities displayed on the second display page) under the target object, and obtaining a tag system (system tag system) and a business tag system) of the target research entity (employee); if the system label system has a plurality of second-level categories, acquiring a plurality of first-level categories under the system label system in the system label system, and acquiring a plurality of second-level categories under each first-level category and a plurality of feature labels under each second-level category; acquiring a plurality of first-level categories under the service label system, a plurality of second-level categories under each first-level category and a plurality of service labels under each second-level category in the service label system; and displaying the acquired plurality of characteristic tags or service tags on a first display page so as to determine at least one characteristic tag in the plurality of characteristic tags to analyze data according to user requirements.
For example, the user requirement is that "analysis is performed on a crowd with overdue amount of employees on duty in an enterprise being less than or equal to 10000 yuan", a screening rule (the overdue amount is less than or equal to 10000 yuan) can be obtained by obtaining a preset threshold "on duty" of a feature tag "working employment state" of a third category "working information" under a second category "basic information" under a first category "customer basic tag" and a feature tag "overdue amount" of a third category "loan statistics" under the second category "liability statistics" under the first category "customer statistics tag" in a system tag system of the enterprise employees, and the screening rule can be manually configured on a page; the crowd with the overdue amount less than or equal to 10000 yuan of the on-duty employees in the enterprise is screened out, the gender proportion of the crowd can be analyzed, and the age bracket of the crowd can also be analyzed.
The operation mode of centralized management of the system label and the division and autonomy of the service label is ensured through two types of category tree construction modes and management modes, namely a system label system and a service label system, so that the aim of enabling the label to be used quickly and flexibly is fulfilled. In this embodiment, the tags are extracted based on a 5W2H seven-query analysis method (Who, when, where, what, how, and What) and five major core business processes (contact, business, contract, product, and transaction) of a customer in a bank, and the function expansion of a multi-object tag system is supported, so that the multi-object tag system is mounted, the relationship among the objects is opened, the transverse expandability of the tag system under different scene businesses of the tag system of each object is met, the richness of the tag system is improved, and the use cost of the tags of each object and the complexity of the tag system construction and development are reduced.
The embodiment of the application provides a method for determining a label system, which comprises the following steps: acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things; for each data analysis demand, performing fine classification processing on the corresponding object by using the service attribute corresponding to the data analysis demand to obtain a plurality of research entities corresponding to the object corresponding to the data analysis demand; for each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity; and constructing a target label system aiming at all objects by using the constructed corresponding label system of each research entity.
Therefore, by adopting the technical scheme provided by the application, the research entity of each object and the characteristic information of each research entity can be determined by acquiring the object of the data analysis requirement, so that the label systems of all objects are obtained, the data analysis requirements under different scenes are met, the richness of the label systems is improved, and the management cost of the labels of all objects and the redundancy of the label system construction are reduced.
Based on the same application concept, a device for determining a tag system corresponding to the method for determining a tag system provided in the foregoing embodiment is also provided in the embodiments of the present application, and since the principle of solving the problem of the device in the embodiments of the present application is similar to that of the method for determining a tag system in the foregoing embodiments of the present application, the implementation of the device may refer to the implementation of the method, and repeated details are not described here.
Referring to fig. 3 and 4, fig. 3 is a first structural diagram of a determination apparatus of a label system according to an embodiment of the present application, and fig. 4 is a second structural diagram of the determination apparatus of the label system according to the embodiment of the present application. As shown in fig. 3, the determining device 310 includes:
an obtaining module 311, configured to obtain an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things;
the processing module 312 is configured to, for each data analysis requirement, perform sub-classification processing on a corresponding object by using a service attribute corresponding to the data analysis requirement, so as to obtain a plurality of research entities corresponding to the object corresponding to the data analysis requirement;
a construction module 313, configured to construct, for each research entity, a label system corresponding to the research entity according to a plurality of feature information describing the research entity;
and the determining module 314 is configured to construct a target label system for all the objects by using the constructed corresponding label system of each research entity.
Optionally, when the building module 313 is configured to build, for each research entity, a tag system corresponding to the research entity according to the feature information for describing the research entity, the building module 313 is specifically configured to:
aiming at each research entity, acquiring a feature tag corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
classifying the feature tags based on a seven-question analysis method aiming at each feature tag, determining the category to which the feature tag belongs from a plurality of pre-constructed categories, and mounting the feature tag under the category to which the original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
for each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a service tag system corresponding to the research entity;
and combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
Optionally, as shown in fig. 4, the determining apparatus 310 further includes a first application module 315, where the first application module 315 is configured to:
for any feature tag, responding to a first operation for the feature tag, and analyzing and processing target feature information under the feature tag;
alternatively, the first and second electrodes may be,
for any feature tag, responding to a second operation aiming at the feature tag, and analyzing and processing all feature information of the feature tag; the first operation is an operation of acquiring at least one but not all target characteristic information under the characteristic label; the second operation is an operation of acquiring all target feature information under the feature tag.
Optionally, when the determining module 314 is configured to construct a target label system for all objects by using the constructed corresponding label system of each research entity, the determining module 314 is specifically configured to:
and combining the label systems corresponding to the research entities according to the objects to which the research entities belong by using the constructed label systems corresponding to the research entities to construct target label systems aiming at all the objects.
Optionally, as shown in fig. 4, the determining apparatus 310 further includes a second application module 316, where the second application module 316 is configured to:
in response to a third operation on a target object of a plurality of objects displayed in a first display page, displaying a plurality of research entities under the target object;
in response to a fourth operation on a target research entity in the plurality of research entities, displaying a label system corresponding to the target research entity to analyze the feature labels according to user requirements; wherein the label system comprises category and feature labels under the target research entity.
The embodiment of the application provides a device for determining a label system, which comprises: the acquisition module is used for acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements aiming at the target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things; the processing module is used for performing sub-classification processing on corresponding objects by utilizing the service attribute corresponding to each data analysis requirement so as to obtain a plurality of research entities corresponding to the objects corresponding to the data analysis requirements; the construction module is used for constructing a label system corresponding to each research entity according to a plurality of characteristic information for describing the research entity; and the determining module is used for constructing a target label system aiming at all the objects by utilizing the constructed label system corresponding to each research entity.
Therefore, by adopting the technical scheme provided by the application, the research entity of each object and the characteristic information of each research entity can be determined by acquiring the object of the data analysis requirement, so that the label systems of all objects are obtained, the data analysis requirements under different scenes are met, the richness of the label systems is improved, and the management cost of the labels of all objects and the redundancy of the label system construction are reduced.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.
The memory 520 stores machine-readable instructions executable by the processor 510, when the electronic device 500 runs, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps of the method for determining a tag system in the method embodiments shown in fig. 1 and fig. 2 may be performed.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the step of the method for determining a tag system in the method embodiments shown in fig. 1 and fig. 2 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some communication interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present application and are intended to be covered by the appended claims. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for determining a label system, the method comprising:
acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements for a target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things;
for each data analysis demand, performing fine classification processing on the corresponding object by using the service attribute corresponding to the data analysis demand to obtain a plurality of research entities corresponding to the object corresponding to the data analysis demand;
for each research entity, constructing a label system corresponding to the research entity according to a plurality of characteristic information for describing the research entity;
and constructing a target label system aiming at all the objects by utilizing the constructed corresponding label system of each research entity.
2. The method of claim 1, wherein the step of constructing, for each research entity, a label system corresponding to the research entity based on the characteristic information describing the research entity comprises:
aiming at each research entity, acquiring a feature tag corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
classifying each feature tag based on a seven-question analysis method, determining a category to which the feature tag belongs in a plurality of pre-constructed categories, and mounting the feature tag under the category to which an original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
for each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a service tag system corresponding to the research entity;
and combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
3. The method of claim 2, wherein after constructing the label system corresponding to the research entity, the method further comprises:
for any feature tag, responding to a first operation aiming at the feature tag, and analyzing and processing target feature information under the feature tag;
alternatively, the first and second electrodes may be,
for any feature tag, responding to a second operation aiming at the feature tag, and analyzing and processing all feature information of the feature tag; wherein the first operation is an operation of acquiring at least one but not all target feature information under the feature tag; the second operation is an operation of acquiring all target feature information under the feature tag.
4. The method of claim 1, wherein the step of constructing a target label system for all the objects using the constructed label system corresponding to each research entity comprises:
and combining the label systems corresponding to the research entities according to the objects to which the research entities belong by using the constructed label systems corresponding to the research entities to construct target label systems aiming at all the objects.
5. The determination method according to claim 2, wherein the category comprises at least one of:
a customer identification tag, a customer base tag, a customer time tag, a customer location tag, a customer product tag, a customer event tag, a customer statistics tag, and a customer rating tag.
6. The method of claim 1, wherein after building the target tag hierarchy for all objects, the method further comprises:
in response to a third operation on a target object of a plurality of objects displayed in a first display page, displaying a plurality of research entities under the target object;
in response to a fourth operation on a target research entity in the plurality of research entities, displaying a label system corresponding to the target research entity to analyze the feature labels according to user requirements; wherein the label system comprises category and feature labels under the target research entity.
7. A tag hierarchy determining apparatus, comprising:
the acquisition module is used for acquiring an object corresponding to each data analysis requirement in a plurality of data analysis requirements aiming at the target service; wherein the object comprises any one of: people, things, relationships between people and things, and relationships between things and things;
the processing module is used for performing fine classification processing on corresponding objects by utilizing the service attributes corresponding to the data analysis requirements aiming at each data analysis requirement to obtain a plurality of research entities corresponding to the objects corresponding to the data analysis requirements;
the construction module is used for constructing a label system corresponding to each research entity according to a plurality of characteristic information for describing the research entity;
and the determining module is used for constructing a target label system aiming at all the objects by utilizing the constructed label system corresponding to each research entity.
8. The apparatus according to claim 7, wherein the building module, when configured to build, for each research entity, a label system corresponding to the research entity according to the feature information describing the research entity, is specifically configured to:
aiming at each research entity, acquiring a feature tag corresponding to each feature information of the research entity based on a plurality of feature information for describing the research entity;
classifying each feature tag based on a seven-question analysis method, determining a category to which the feature tag belongs in a plurality of pre-constructed categories, and mounting the feature tag under the category to which an original tag system corresponding to the research entity belongs to obtain a system tag system corresponding to the research entity;
for each feature tag in a system tag system corresponding to the research entity, converting the feature tag according to a preset design mode to obtain a converted feature tag, and classifying the converted feature tag to obtain a service tag system corresponding to the research entity;
and combining the system label system corresponding to the research entity with the business label system corresponding to the research entity to construct the label system corresponding to the research entity.
9. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is operated, the machine-readable instructions being executable by the processor to perform the steps of the method of determining a tag architecture as claimed in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the method for determining a label architecture as claimed in any one of the claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211198256.9A CN115510324B (en) | 2022-09-29 | 2022-09-29 | Label system determining method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211198256.9A CN115510324B (en) | 2022-09-29 | 2022-09-29 | Label system determining method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115510324A true CN115510324A (en) | 2022-12-23 |
| CN115510324B CN115510324B (en) | 2023-04-28 |
Family
ID=84507644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211198256.9A Active CN115510324B (en) | 2022-09-29 | 2022-09-29 | Label system determining method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115510324B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190122260A1 (en) * | 2016-09-27 | 2019-04-25 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for generating targeted label, and storage medium |
| CN111177129A (en) * | 2019-12-16 | 2020-05-19 | 中国平安财产保险股份有限公司 | Label system construction method, device, equipment and storage medium |
| CN111382343A (en) * | 2018-12-27 | 2020-07-07 | 方正国际软件(北京)有限公司 | Label system generation method and device |
| CN113313344A (en) * | 2021-04-13 | 2021-08-27 | 武汉烽火众智数字技术有限责任公司 | Label system construction method and system fusing multiple modes |
| CN114547385A (en) * | 2022-02-25 | 2022-05-27 | 中国平安人寿保险股份有限公司 | Label construction method and device, electronic equipment and storage medium |
| CN114995903A (en) * | 2022-05-30 | 2022-09-02 | 中电金信软件有限公司 | Class label identification method and device based on pre-training language model |
-
2022
- 2022-09-29 CN CN202211198256.9A patent/CN115510324B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190122260A1 (en) * | 2016-09-27 | 2019-04-25 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for generating targeted label, and storage medium |
| CN111382343A (en) * | 2018-12-27 | 2020-07-07 | 方正国际软件(北京)有限公司 | Label system generation method and device |
| CN111177129A (en) * | 2019-12-16 | 2020-05-19 | 中国平安财产保险股份有限公司 | Label system construction method, device, equipment and storage medium |
| CN113313344A (en) * | 2021-04-13 | 2021-08-27 | 武汉烽火众智数字技术有限责任公司 | Label system construction method and system fusing multiple modes |
| CN114547385A (en) * | 2022-02-25 | 2022-05-27 | 中国平安人寿保险股份有限公司 | Label construction method and device, electronic equipment and storage medium |
| CN114995903A (en) * | 2022-05-30 | 2022-09-02 | 中电金信软件有限公司 | Class label identification method and device based on pre-training language model |
Non-Patent Citations (2)
| Title |
|---|
| 张军锋等: "铁路旅客用户画像系统设计与应用研究" * |
| 陈庆波;: "浅谈构建客户标签体系思路" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115510324B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pan et al. | Forecasting destination weekly hotel occupancy with big data | |
| CN108154401B (en) | User portrait depicting method, device, medium and computing equipment | |
| Neslin et al. | Defection detection: Measuring and understanding the predictive accuracy of customer churn models | |
| US11954577B2 (en) | Deep neural network based user segmentation | |
| Jiang et al. | Analyzing firm-specific social media and market: A stakeholder-based event analysis framework | |
| US8341101B1 (en) | Determining relationships between data items and individuals, and dynamically calculating a metric score based on groups of characteristics | |
| US20150161606A1 (en) | Method and system for assessing financial condition of a merchant | |
| Kim et al. | Reference-dependent preferences on smart phones in South Korea: Focusing on attributes with heterogeneous preference direction | |
| Arun et al. | Big data: review, classification and analysis survey | |
| US8478702B1 (en) | Tools and methods for determining semantic relationship indexes | |
| CN110019774B (en) | Label distribution method, device, storage medium and electronic device | |
| Al-Sharafi et al. | Cloud computing adoption in higher education: An integrated theoretical model | |
| Poluru et al. | Applications of Domain-Specific Predictive Analytics Applied to Big Data | |
| Sahu et al. | Mobile banking adoption: A review | |
| JP6031165B1 (en) | Promising customer prediction apparatus, promising customer prediction method, and promising customer prediction program | |
| KR20210012495A (en) | Ad recommendation techniques and methods that combine the similarity of SNS text with ad content and the fairness of advertisement impressions | |
| CN115510324B (en) | Label system determining method and device, electronic equipment and storage medium | |
| CN111125514B (en) | Method, device, electronic equipment and storage medium for analyzing user behaviors | |
| Ребязина et al. | Consumer digital trust: The main trends and research directions | |
| Verma et al. | ‘Big data’patentometrics for R&D decision-making | |
| Lackovic et al. | Framework for big data usage in risk management process in banking institutions | |
| Santonastaso et al. | An Exploratory Study of the Digital Competences of Italian Accountants: Some Preliminary Results | |
| Bellet et al. | Big Data and Wellbeing: An Economic Perspective | |
| CN115600600B (en) | Label naming method, device, electronic equipment and medium of multi-object label system | |
| WO2013119762A1 (en) | Tools and methods for determining semantic relationship indexes |
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 |