CN114547385A

CN114547385A - Label construction method and device, electronic equipment and storage medium

Info

Publication number: CN114547385A
Application number: CN202210183402.4A
Authority: CN
Inventors: 魏政刚; 朱建伟; 莫洋
Original assignee: Ping An Life Insurance Company of China Ltd
Current assignee: Ping An Life Insurance Company of China Ltd
Priority date: 2022-02-25
Filing date: 2022-02-25
Publication date: 2022-05-27

Abstract

The embodiment of the application discloses a label construction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring characteristic data of an object to be processed; determining the business field of the object to be processed according to the characteristic data of the object to be processed; determining a plurality of business processes related to the object to be processed according to the characteristic data of the object to be processed and the business field; performing element decomposition on each business process to obtain a plurality of preset elements; selecting part of preset elements from a plurality of preset elements corresponding to each business process to form a business object corresponding to each business process; extracting attributes of a part of preset elements contained in each business object to obtain a plurality of attributes of each business object; acquiring a transformation rule corresponding to each attribute, and performing spatial transformation on the attribute value of each attribute according to the transformation rule of each attribute to obtain a feature space of each service object; and constructing a label for the object to be processed according to the feature space of each business object.

Description

Label construction method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of tag construction technologies, and in particular, to a tag construction method and apparatus, an electronic device, and a storage medium.

Background

With the continuous development of big data and artificial intelligence technologies, more and more enterprises carry out intelligent transformation, feature mining is carried out on users, articles and business processes in businesses of the enterprises through a label technology, the features are labeled by combining business languages, business labels (such as user portrait labels and commodity labels) are formed, and effective description on the features of business objects is achieved. The label plays a very important role in service operation, for example, an enterprise performs group marketing to customers according to the label, performs user personalized recommendation according to a commodity label and a user interest label, and the like. Compared with the traditional technology, the method has the advantages that the efficiency of enterprise business operation is greatly improved and the operation cost is reduced based on the accurate description of the characteristics of the business object by the big data and artificial intelligence technology.

The current common label system construction method is a top-down construction method. Specifically, according to the service field and the service process, a tag directory tree is planned according to service requirements, and then tags are processed in different modes such as statistics, attributes or model algorithms in each type of tags. The label construction method is only constructed layer by layer from top to bottom, and the relation between nodes of each layer is not explored, so that the constructed label is low in precision.

Disclosure of Invention

The embodiment of the application provides a tag construction method and device, electronic equipment and a storage medium, and the tag construction precision is improved through business decomposition.

In a first aspect, an embodiment of the present application provides a tag construction method, including:

acquiring characteristic data of an object to be processed;

determining the service field of the object to be processed according to the characteristic data of the object to be processed;

determining a plurality of business processes related to the object to be processed according to the feature data of the object to be processed and the business field;

performing element decomposition on each business process to obtain a plurality of preset elements;

selecting part of preset elements from a plurality of preset elements corresponding to each business process to form a business object corresponding to each business process, and obtaining a plurality of business objects corresponding to the business processes;

extracting attributes of a part of preset elements contained in each business object to obtain a plurality of attributes of each business object;

obtaining a transformation rule corresponding to each attribute, and performing spatial transformation on the attribute value of each attribute according to the transformation rule of each attribute to obtain a feature space of each service object;

and constructing a label for the object to be processed according to the feature space of each business object.

In a second aspect, an embodiment of the present application provides a label building apparatus, including: an acquisition unit and a processing unit;

the acquisition unit is used for acquiring characteristic data of an object to be processed;

the processing unit is used for determining the business field of the object to be processed according to the characteristic data of the object to be processed;

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor coupled to a memory, the memory configured to store a computer program, the processor configured to execute the computer program stored in the memory to cause the electronic device to perform the method of the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, where the computer program makes a computer execute the method according to the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer being operable to cause a computer to perform the method according to the first aspect.

The embodiment of the application has the following beneficial effects:

it can be seen that, in the embodiment of the present application, a plurality of business processes related to an object to be processed are obtained by analyzing and processing feature data of the object to be processed, and a plurality of preset elements are formed by decomposing the business processes, so that the business processes are more accurately depicted. Then, part of preset elements are extracted to form a business object, a label is constructed from the perspective of the business object, namely, a plurality of elements are taken as a whole to construct the label, the label is not constructed from each element independently in consideration of the relevance among the elements, and the construction precision of the label is further improved. Furthermore, since the attributes of the elements can be transformed into the feature values by the corresponding transformation rules, the attributes can be transformed into the corresponding feature values for any type of data regardless of the type of the data, and thus the tag construction of the present application has universality.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of a label construction system provided by an embodiment of the present application;

fig. 2 is a schematic flowchart of a tag construction method according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of transformation from attribute space to feature space according to an embodiment of the present application;

FIG. 4 is a schematic view of a tag provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a directory of tags provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a directory of alternative tags provided by an embodiment of the present application;

fig. 7 is a block diagram illustrating functional units of a tag building apparatus according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

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 is obvious that the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

Referring to fig. 1, fig. 1 is a schematic diagram of a label building system according to an embodiment of the present application. The tag construction system includes a first user terminal 10, a tag construction apparatus 20, and a second user terminal 30. The second user terminal is mainly used for pushing information.

For example, the first user terminal 10 may collect feature data of an object to be processed, for example, when the object to be processed is a user, the feature data of the user may be collected through a network access behavior of the user;

further, if the second user terminal 30 has the right to access the first user terminal 10, the feature data of the object to be processed may be obtained from the first user terminal 10; then determining the service field of the object to be processed according to the characteristic data of the object to be processed; determining a plurality of business processes related to the object to be processed according to the feature data of the object to be processed and the business field; performing element decomposition on each business process according to the characteristic data of the object to be processed to obtain a plurality of preset elements; selecting part of elements from a plurality of preset elements corresponding to each business process to form a business object corresponding to each business process, and obtaining a plurality of business objects corresponding to the business processes; extracting attributes of each business object to obtain a plurality of attributes of each business object; obtaining a transformation rule corresponding to each attribute, and performing spatial transformation on each attribute according to the transformation rule of each attribute to obtain a feature space of each service object; and constructing a label for the object to be processed according to the feature space of each business object.

Accordingly, after the tags are constructed, the second user terminal 30 may obtain the tags of the respective objects to be processed from the tag construction apparatus 20, determine the information to be pushed of the respective objects to be processed based on the tags of the respective objects to be processed, and push the information to be pushed to the respective objects to be processed. For example, the object to be processed adapted to a certain product may be determined according to the label of each object to be processed, and the product information of the product may be pushed to the object to be processed.

Referring to fig. 2, fig. 2 is a schematic flowchart of a tag constructing method according to an embodiment of the present application. The method is applied to the label building apparatus 20 described above. The method includes but is not limited to the following steps:

201: and acquiring characteristic data of the object to be processed.

The object to be processed comprises three types, wherein the first type is a user which takes a person as the object to be processed; the second type is that an article is an object to be processed, for example, a commodity (e.g., an insurance product); the third category is to treat human behavior, such as browsing behavior and shopping behavior of the user.

For example, when the object to be processed is a user, the feature data is a basic feature of the user, such as the age, sex, hobbies, social relations, and the like of the user, and the constructed tag can be understood as a portrait of the user; when the object to be processed is an article, the feature data is the basic features of the article, such as the category, color, price, applicable population, sales condition and the like of the article, and the constructed label can be understood as the image of the article; when the object to be processed is a behavior of the user, the feature data is behavior feature data of the user, for example, the number of times of sharing by the user, the content of sharing, browsing records, and the like, and the constructed tag is a behavior portrait of the user. In the present application, the description will be given mainly by taking the example of constructing a behavior representation for the behavior of a user, and the other two types of representations are similar to each other and will not be described again.

For example, the feature data may be obtained in different ways for different types of objects to be processed. For example, when the object to be processed is a user, the user database may be accessed through the application program interface to obtain the feature data of the user; when the object to be processed is an article, the characteristic data of the article can be acquired by accessing a merchant platform of the article; when the data to be processed is the behavior feature data of the user, the behavior feature data of the user can be obtained by accessing the user terminal of the user.

202: and determining the business field of the object to be processed according to the characteristic data of the object to be processed.

The business domain is a general term for all business processes within a specific business boundary. Therefore, the entity extraction can be carried out on the characteristic data of the object to be processed to obtain at least one entity. For example, if the feature data is that "insurance agent shares content with client", entity extraction is performed to obtain entity "insurance", "agent" and "client"; and then, determining the industry corresponding to each entity according to the corresponding relation between the entities and the industries. For example, for "insurance", the industry corresponding to the entity is determined to be an insurance industry, for "agent", the industry corresponding to the entity is determined to be a sales industry, and for "customer", the industry corresponding to the entity is determined to be a service industry. Further, the characteristic data of the object to be processed is subjected to action recognition, and a business mode related to the object to be processed is obtained, wherein the business mode comprises an online mode or an offline mode. For example, if the feature data is "the insurance agent shares content with the client", it is recognized that the action is "share", and therefore, the service mode corresponding to the feature data is determined to be the online mode. And finally, combining at least one industry corresponding to the at least one entity and the business mode to obtain the business field of the object to be processed. Along the use example, at least one industry is respectively 'insurance industry', 'sales industry' and 'service industry', and the business mode is 'online mode', so that the business field where the object to be processed is located can be determined to be 'online insurance sales'.

203: and determining a plurality of business processes related to the object to be processed according to the characteristic data of the object to be processed and the business field.

Exemplarily, the feature data of the object to be processed is divided into sentences to obtain a plurality of sentences; and (3) performing syntax analysis on each sentence to obtain a subject, a state, a predicate and an object in each sentence, wherein the state can comprise a target state, a time state and/or a place state. Following the above example, the subject is "agent", the object is "client", the predicate is "share", and the object is "content" can be obtained. And then, combining the subject, the object, the predicate and the object in each statement to obtain a business process corresponding to each statement. Following the above example, the subject, the subjects, the predicates, and the objects are combined to obtain a business process of "the agent shares content with the client". In addition, the online insurance sales in the business field may also include other business processes, for example, user registration account, user payment order, and so on. Thus, a business domain may contain multiple business processes.

204: and performing element decomposition on each business process to obtain a plurality of preset elements.

Exemplary, the preset elements of the present application include constraints, targets, subjects, objects, relationships. Among them, Constraint is an internal and external limitation (environment or context) faced by a business process; for example, constraints may include temporal constraints and/or positional constraints, etc., which are generally characterized in the feature data by a temporal or locality status language; a goal (commit Statement) is a description of the goal that a business process needs to achieve, and is typically characterized in feature data by a goal-like language. The subject (Entity-Actor), a participant involved in a business process ("person" or "system"), is characterized in feature data by a subject. An Object (Entity-Object), a non-subject Entity involved in a business process, is generally characterized in the characteristic data by an Object; relationship (Relationship), the Relationship between an object and an object in a business process, is generally characterized by a predicate in the characteristic data.

Therefore, a subject (including a time-subject, a place-subject, and a destination-subject), a predicate, and an object of each business process are acquired, thereby decomposing each business process into a plurality of preset elements.

For example, if the feature data is "content is shared to the client for january insurance agent", the business process corresponding to the feature data is "january agent shares content to the client", and the element decomposition is performed on the business process to obtain that the subject is "agent", the object-oriented object is "client", the time-oriented object is "january", and the predicate is "share", and the subject is "content". Therefore, the main body corresponding to the business process is 'agent', the constraint is 'january', the target is 'to client', and the relation is 'share'.

205: and selecting part of the preset elements from the plurality of preset elements corresponding to each business process to form a business object corresponding to each business process, so as to obtain a plurality of business objects corresponding to the business processes.

Illustratively, some elements of the present application are a subject, an object and a relationship, that is, the subject, the object and the relationship are selected from the plurality of preset elements to form a business object corresponding to each business process. For a plurality of business processes, a plurality of business objects may be obtained.

For example, if the business process is that an agent shares content with a client, the obtained business object is { agent, client, share }.

206: and extracting attributes of part of the preset elements contained in each business object to obtain a plurality of attributes of each business object.

Exemplarily, extracting an attribute of each preset element in the service object corresponding to each service process to obtain an attribute corresponding to each preset element, wherein each preset element corresponds to one or more attributes; then, all attributes corresponding to the part of preset elements are combined to obtain a plurality of attributes corresponding to the business object.

For example, for business objects: { agent, client, sharing }, extracting attributes of a preset element main body, namely the agent, wherein the attributes comprise age, gender, department age, personal reputation, level and the like; extracting attributes aiming at a preset element object, namely a client, wherein the attributes comprise age, gender and the like; the relationship is stated for the preset elements, namely the sharing is performed with attribute extraction, and the attributes comprise sharing failure, sharing success and probability preference of sharing content.

207: and acquiring a transformation rule corresponding to each attribute, and performing spatial transformation on each attribute according to the transformation rule of each attribute to obtain a feature space of each service object.

Illustratively, the transformation rule corresponding to each attribute is selected from a plurality of preset transformation rules. Optionally, the multiple preset transformation rules in the present application mainly include three categories, specifically: mapping, statistics, and model prediction. Wherein, the statistics uses a statistical analysis method to transform the attribute values; for example, summing, averaging, maximizing, minimizing, etc. the order amount; mapping is to transform the attribute values by using a mapping rule; for example, the age indicated by the characters is mapped to the age groups corresponding to teenagers, adolescents, middle-aged people, old people and the like; the model prediction is to transform the attribute value by using a trained model; for example, probability prediction is performed on the preference of the user for sharing the content, so that the probability distribution characteristic of the user content sharing preference is obtained, namely, the probability of sharing various types of content by the user is predicted through a model.

Specifically, according to the feature data of the object to be processed, the attribute value of each attribute is obtained; if the attribute value of each attribute is characterized by a text, determining a transformation rule corresponding to each attribute as a mapping, namely an attribute value expressed by a fuzzy concept, and a corresponding change rule as a mapping, for example, if the age of the agent is teenager, the corresponding transformation rule is a mapping, and the teenager needs to be mapped to a specific age bracket; if the attribute value of each attribute is represented by a number, determining the transformation rule corresponding to each attribute as statistics, for example, counting the total number of times of sharing the content by the agent in a preset time period in a statistical manner; if the attribute value of each attribute is represented by a probability, determining a transformation rule corresponding to each attribute as model prediction, for example, for content sharing of an agent, if the attribute value has sharing preference feature distribution, the feature distribution needs to be represented by a probability, and then predicting the probability of sharing various types of content by the agent through the model.

Therefore, after the transformation rule corresponding to each attribute is obtained, the attribute value of each attribute is transformed based on the transformation rule corresponding to each attribute, and a feature value (i.e., text, numerical value, or character describing each attribute, etc.) corresponding to each attribute is obtained. Specifically, if the transformation rule of each attribute is mapping, mapping is performed according to the attribute value of each attribute to obtain a feature value corresponding to each attribute; if the transformation rule of each attribute is statistics, counting the times of occurrence of the attribute value of each attribute in a preset time period, and taking the times as the characteristic value corresponding to each attribute; and if the transformation rule of each attribute is model prediction, predicting the probability distribution under each attribute by using a trained prediction model and the attribute value of each attribute, and taking the probability distribution as the characteristic value corresponding to each attribute.

And finally, combining the characteristic values corresponding to each attribute to obtain a characteristic space corresponding to each business object.

Generally, one eigenvalue corresponding to an attribute is obtained by mapping or statistical transformation, and a plurality of eigenvalues corresponding to an attribute are obtained by model prediction transformation.

For example, still following the above example of sharing content to a client by an agent, the attribute value corresponding to each attribute is transformed, and a feature space as shown in fig. 3 can be obtained.

208: and constructing a label for the object to be processed according to the feature space of each business object.

For example, as shown in fig. 4, the feature value corresponding to each attribute is used as a label of the object to be processed, so as to obtain the label of the object to be processed.

In one embodiment of the present application, after constructing the tag for the object to be processed, the method further includes:

and constructing a tree structure, wherein the tree structure comprises a father node, a plurality of first-level child nodes and a plurality of second-level child nodes, the number of the first-level child nodes is determined by the number of all attributes corresponding to the plurality of business objects, and the number of the second-level child nodes is determined by the number of all characteristic values corresponding to all attributes corresponding to the plurality of business objects. Specifically, as shown in fig. 5, a tree structure is constructed, a plurality of first-level child nodes are constructed in the tree structure according to the number of attributes, and a plurality of second-level child nodes are constructed according to the number of feature values corresponding to each attribute; further, as shown in fig. 5, the service domain of the service object is mounted on the parent node, so as to obtain a primary directory; sequentially mounting a plurality of attributes of each business object on the plurality of primary node sub-points to obtain a secondary directory; sequentially mounting the characteristic value corresponding to each attribute in the plurality of attributes of each business object on the plurality of secondary child nodes to obtain a tertiary directory; and taking the tree structure loaded with the primary directory, the secondary directory and the tertiary directory as a directory of the label.

It should be noted that the above-mentioned structured tag directory is mainly a directory formed by performing classification management from the perspective of the target of the business process. Generally, the business field of the business object is used as a top-level directory (i.e. a first-level directory), and then, according to the goal of achieving the business process corresponding to the business object, the child nodes of each layer are designed layer by layer; and until the last layer of child nodes, each attribute is used as a first-level child node, and then the characteristic value corresponding to each attribute is mounted on a second-level node corresponding to each attribute to form a catalog of the label.

It can be seen that, a directory is constructed for the tag of the object to be processed, and the constructed tag can be added to the service field and each sub-field (i.e. each attribute) related to the service field, so that the tag of the object to be processed is adapted to the service field, and the tag information of the user is provided for the service field.

In one embodiment of the present application, after building the catalog of tags, the method further comprises:

obtaining a target attribute of the attributes of each business object, wherein the target attribute is determined by a subject, a predicate, an object and a state in the characteristic data of the object to be processed, namely, an attribute related to identity in the attributes corresponding to the subject, an attribute related to identity in the attributes corresponding to the object, an attribute related to action identification in the predicate and an attribute related to purpose identification in the state are all used as the target attribute; acquiring at least one identity corresponding to the target attribute of each business object; and associating at least one identity corresponding to the target attribute of each business object to obtain the target identity of the target attribute of each business object. And the target identity of the target attribute of each business object is used as a new characteristic value of the target attribute.

Further, as shown in fig. 6, since the target identity is a new characteristic value, and a third-level node corresponding to the characteristic value is not constructed in the original tree structure, a third-level node is newly added to the target attribute of each service object in the directory of the tag, the target identity of the target attribute is mounted on the newly added third-level node, and a target identity (characteristic value) is mounted on the third-level node corresponding to the target attribute in the tree structure.

The following describes a process of obtaining a target identity by taking an identity of an associated subject as an example.

For example, if the subject is a user, and at least one identity of the user includes a WeChat ID, an APP registration ID, and a mobile phone number of the user; then, the WeChat ID, the APP registration ID and the mobile phone number of the user are correlated to obtain a target identity of the main body, namely, the multiple identities of the user are spliced (correlated) to obtain a target identity { WeChat ID, APP registration ID and mobile phone number }.

It can be seen that, in the embodiment, the uniqueness of the identity is ensured by associating the identity, which is convenient for the accuracy of subsequently obtaining the characteristic value of each node.

Referring to fig. 7, fig. 7 is a block diagram illustrating functional units of a tag building apparatus according to an embodiment of the present application. The label building apparatus 700 includes: an acquisition unit 701 and a processing unit 702;

an obtaining unit 701, configured to obtain feature data of an object to be processed;

a processing unit 702, configured to determine, according to the feature data of the object to be processed, a service field in which the object to be processed is located;

In an embodiment of the present application, in terms of determining, according to the feature data of the object to be processed, a business field where the object to be processed is located, the processing unit 702 is specifically configured to:

carrying out entity extraction on the characteristic data of the object to be processed to obtain at least one entity;

determining industries corresponding to each entity according to corresponding relations between the industries and the entities;

performing action recognition on the feature data of the object to be processed to obtain a service mode related to the object to be processed, wherein the service mode comprises an online mode or an offline mode;

and combining at least one industry corresponding to the at least one entity and the service mode to obtain the service field of the object to be processed.

In an embodiment of the present application, in terms of determining, according to the feature data of the object to be processed and the business field, a plurality of business processes related to the object to be processed, the processing unit 702 is specifically configured to:

the characteristic data of the object to be processed is divided into sentences to obtain a plurality of sentences;

carrying out syntactic analysis on each statement to obtain a subject, an object, a predicate and an object in each statement;

combining the subject, the subjects, the predicates and the objects in each statement to obtain a business process corresponding to each statement;

and combining a plurality of business processes corresponding to the plurality of sentences to obtain the plurality of business processes.

In an embodiment of the application, in terms of obtaining a transformation rule corresponding to each attribute, the processing unit 702 is specifically configured to:

acquiring an attribute value of each attribute according to the characteristic data of the object to be processed;

if the attribute value of each attribute is represented by a text, determining a transformation rule corresponding to each attribute as mapping;

if the attribute value of each attribute is represented by a number, determining a transformation rule corresponding to each attribute as statistics;

and if the attribute value of each attribute is represented by the probability, determining a transformation rule corresponding to each attribute as model prediction.

In an embodiment of the application, in obtaining a transformation rule corresponding to each attribute, and performing spatial transformation on each attribute according to the transformation rule of each attribute to obtain a feature space of each service object, the processing unit 702 is specifically configured to:

if the transformation rule of each attribute is mapping, mapping according to the attribute value of each attribute to obtain a characteristic value corresponding to each attribute;

if the transformation rule of each attribute is statistics, counting the times of occurrence of the attribute value of each attribute in a preset time period, and taking the times as the characteristic value corresponding to each attribute;

if the transformation rule of each attribute is model prediction, predicting the probability distribution under each attribute by using a trained prediction model and the attribute value of each attribute, and taking the probability distribution as the characteristic value corresponding to each attribute;

and combining the characteristic values corresponding to the attributes to obtain the characteristic space of each business object.

In an embodiment of the present application, the processing unit 702 is further configured to construct a tree structure, where the tree structure includes a parent node, a plurality of first-level child nodes, and a plurality of second-level child nodes, where a number of the plurality of first-level child nodes is determined by a number of all attributes corresponding to the plurality of business objects, and a number of the plurality of second-level child nodes is determined by a number of all feature values corresponding to all attributes corresponding to the plurality of business objects;

mounting the service field of the service object on the father node to obtain a primary directory;

sequentially mounting a plurality of attributes of each business object on the plurality of primary node sub-points to obtain a secondary directory;

sequentially mounting the characteristic value corresponding to each attribute in the plurality of attributes of each business object on the plurality of secondary child nodes to obtain a tertiary directory;

and taking the tree structure loaded with the primary directory, the secondary directory and the tertiary directory as the directory of the label.

In an embodiment of the present application, the processing unit 702 is further configured to:

acquiring at least one identity corresponding to the target attribute of each business object;

associating at least one identity corresponding to the target attribute of each business object to obtain a target identity of the target attribute of each business object;

and newly adding a third-level node for the target attribute of each business object in the directory of the label, and mounting the target identity of the target attribute on the newly added third-level node.

Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. Connected to each other by a bus 804. The memory 803 is used to store computer programs and data, and can transfer the data stored in the memory 803 to the processor 802.

The processor 802 is configured to read the computer program in the memory 803 to perform the following operations:

the control transceiver 801 acquires characteristic data of an object to be processed;

In an embodiment of the present application, in terms of determining a business area where the object to be processed is located according to the feature data of the object to be processed, the processor 802 is specifically configured to perform the following steps:

determining industries corresponding to the entities according to corresponding relations between the industries and the entities;

In an embodiment of the present application, in terms of determining a plurality of business processes related to the object to be processed according to the feature data of the object to be processed and the business field, the processor 802 is specifically configured to perform the following steps:

In an embodiment of the present application, in obtaining the transformation rule corresponding to each attribute, the processor 802 is specifically configured to perform the following steps:

In an embodiment of the present application, in obtaining a transformation rule corresponding to each of the attributes, and performing spatial transformation on each of the attributes according to the transformation rule of each of the attributes to obtain a feature space of each of the business objects, the processor 802 is specifically configured to perform the following steps:

In one embodiment of the present application, the processor 802 is further configured to perform the following steps:

constructing a tree structure, wherein the tree structure comprises a father node, a plurality of first-level child nodes and a plurality of second-level child nodes, the number of the first-level child nodes is determined by the number of all attributes corresponding to the plurality of business objects, and the number of the second-level child nodes is determined by the number of all characteristic values corresponding to all attributes corresponding to the plurality of business objects;

Specifically, the transceiver 801 may be the obtaining unit 701 of the label building apparatus 700 according to the embodiment shown in fig. 7, and the processor 802 may be the processing unit 702 of the label building apparatus 700 according to the embodiment shown in fig. 7.

It should be understood that the electronic device in the present application may include a smart Phone (e.g., an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a Mobile Internet device MID (MID), a wearable device, or the like. The above mentioned electronic devices are only examples, not exhaustive, and include but not limited to the above mentioned electronic devices. In practical applications, the electronic device may further include: intelligent vehicle-mounted terminal, computer equipment and the like.

Embodiments of the present application also provide a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement part or all of the steps of any one of the tag constructing methods described in the above method embodiments.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the label construction methods as set forth in the above method embodiments.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that the acts and modules referred to are not necessarily required in this application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple 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 mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric 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 position, or may be distributed on multiple 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 integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.

The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including 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 method described in the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that all or part of the steps of the methods of the above embodiments may be implemented by a program, which is stored in a computer-readable memory, the memory including: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A label construction method is characterized by comprising the following steps:

acquiring characteristic data of an object to be processed;

2. The method according to claim 1, wherein the determining the service domain of the object to be processed according to the feature data of the object to be processed comprises:

3. The method according to claim 1 or 2, wherein the determining a plurality of business processes related to the object to be processed according to the feature data of the object to be processed and the business field comprises:

4. The method according to claim 1 or 2, wherein the obtaining of the transformation rule corresponding to each attribute comprises:

acquiring an attribute value of each attribute according to the feature data of the object to be processed;

5. The method according to claim 4, wherein the obtaining a transformation rule corresponding to each attribute, and performing spatial transformation on each attribute according to the transformation rule of each attribute to obtain a feature space of each service object comprises:

if the transformation rule of each attribute is statistics, counting the times of occurrence of the attribute value of each attribute in a preset time period, and taking the times as a characteristic value corresponding to each attribute;

if the transformation rule of each attribute is model prediction, predicting probability distribution under each attribute by using a trained prediction model and the attribute value of each attribute, and taking the probability distribution as a characteristic value corresponding to each attribute;

6. The method of claim 5, further comprising:

7. The method of claim 6, further comprising:

obtaining a target attribute in the plurality of attributes of each business object, wherein the target attribute is determined by a subject, a predicate, an object and a subject in the characteristic data of the object to be processed;

8. A label building apparatus, comprising: an acquisition unit and a processing unit;

9. An electronic device, comprising: a processor coupled to the memory, and a memory for storing a computer program, the processor being configured to execute the computer program stored in the memory to cause the electronic device to perform the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method according to any one of claims 1-7.