CN114996445A

CN114996445A - Object classification method and device, terminal equipment and storage medium

Info

Publication number: CN114996445A
Application number: CN202210474437.3A
Authority: CN
Inventors: 牟哓
Original assignee: Hanhai Information Technology Shanghai Co Ltd
Current assignee: Hanhai Information Technology Shanghai Co Ltd
Priority date: 2022-04-29
Filing date: 2022-04-29
Publication date: 2022-09-02

Abstract

The embodiment of the invention provides an object classification method, device terminal equipment and a storage medium, and relates to the technical field of data processing; accurate object categories can be obtained quickly. The method comprises the following steps: acquiring category information set for a target entity by each service system in a plurality of service systems matched with the functional attribute of the target entity to which a first object belongs; inquiring at least one first target preset category corresponding to the category information in a plurality of preset categories preset by a local service system storing the first object; and classifying the first objects according to the number of the category information corresponding to each first target preset category.

Description

Object classification method and device, terminal equipment and storage medium

[ technical field ] A method for producing a semiconductor device

The embodiment of the invention relates to the technical field of data processing, in particular to an object classification method, device terminal equipment and a storage medium.

[ background of the invention ]

With the development of internet economy, an internet platform adopts data and functions to express characteristics and functions of entities aiming at offline entities (such as shops, landmark buildings, public parks and the like) according to application scenes of a business system of the internet platform, so as to create and obtain objects which represent corresponding entities on line.

In an application scenario of a related business system (e.g., user searching for a store, rendering a map base map, etc.), related business functions need to be executed according to object categories. For example, the e-commerce platform recommends stores whose categories match the user search keywords; the map system renders different icons on the canvas according to the landmark building types and displays the icons on the display interface. Therefore, the accuracy of the object category is related to whether the system can bring good experience for the user.

However, in the prior art, the judgment of the object type by the service system is limited by the data related to the entity to which the object belongs, which is locally stored, and accurate object type information cannot be obtained.

[ summary of the invention ]

The embodiment of the invention provides an object classification method, an object classification device, terminal equipment and a storage medium, which can quickly obtain an accurate object class.

In a first aspect, an embodiment of the present invention provides an object classification method applied to an electronic device, where the method includes: acquiring category information set for a target entity by each service system in a plurality of service systems matched with the functional attribute of the target entity to which a first object belongs; inquiring at least one first target preset category corresponding to the category information in a plurality of preset categories preset by a local service system storing the first object; and classifying the first objects according to the number of the category information corresponding to each first target preset category.

In the method, the first target preset category represents the corresponding expression mode of the determined type of the target entity to which the first object belongs in the local system by other systems of the internet, and the larger the number of the corresponding category information of the first target preset category is, the more systems determining that the category of the first object is the first target preset category in the internet are; therefore, the embodiment of the invention introduces the category information determined by other service systems of the internet to the entity in a manner of classifying the first objects according to the number of the category information corresponding to each preset category of the first objects, so that the prediction result is more accurate, and the service systems corresponding to the internet can be traced to cover more scenes.

In one possible implementation manner, the method further includes:

acquiring the name information of the first object in the local service system;

determining at least one second target preset category corresponding to the first object in the plurality of preset categories according to the name information by using a preset classification model;

classifying the first objects according to the number of the category information corresponding to each first target preset category, wherein the classifying comprises the following steps:

and classifying the first objects according to the number of the category information corresponding to each first target preset category and the at least one second target preset category.

In one possible implementation manner, determining, by using a preset classification model according to the name information, a second target preset category corresponding to the first object in the plurality of preset categories includes:

splicing the name information and the category information set by each service system for the target entity to obtain splicing information;

inputting the splicing information into the preset classification model, and extracting category characteristics from the splicing information by using the preset classification model;

and determining a second target preset category corresponding to the first object according to the category characteristics by using the preset classification model.

In one possible implementation manner, obtaining category information set for a target entity by each of a plurality of service systems matched with a functional attribute of the target entity to which a first object belongs includes:

querying a target second object which is consistent with the target entity in the entity to which the second object belongs in a plurality of second objects stored in a specific business system; wherein the particular business system is any one of the plurality of business systems;

and extracting category texts displayed by the target second object in the specific service system as category information set by the specific service system for the target entity.

In one possible implementation manner, querying at least one first target preset category corresponding to each of the plurality of category information in a plurality of preset categories preset by a local service system storing the first object includes:

mapping any category information in the category information to a node where a related preset category with the highest similarity with the category information is located;

when the node where the associated preset category is located is a leaf node in a pre-constructed category tree, taking the associated preset category as the first target preset category; each node in the pre-constructed category tree corresponds to the plurality of preset categories one by one;

and when the associated preset category is not a leaf node in a pre-constructed category tree, taking the preset category positioned at the node subnode of the associated preset category as the first target preset category.

In one possible implementation manner, classifying the first object according to the number of the category information corresponding to each first target preset category includes:

when the number of the target category information corresponding to any first target preset category is multiple, sequentially setting the matching probability of the any first target preset category for matching the first object under each target category information dimension according to the number of the first target preset category corresponding to the service system dimension in which each target category information is located;

superposing the matching probability of each first target preset category under different target category information dimensions to obtain the aggregation probability value of each first target preset category;

and classifying the first objects according to the aggregation probability value of each first target preset category.

In one possible implementation manner, the method further includes:

acquiring the name information of the first object in the local service system;

inputting the name information into a preset classification model, and outputting the confidence probability of each preset category in the plurality of preset categories and the first object;

classifying the first objects according to the aggregate probability value of each first target preset category, wherein the classification comprises the following steps:

and classifying the first objects according to the aggregation probability value of each first target preset category and the confidence probability of each preset category.

In one possible implementation manner, classifying the first object according to the aggregation probability value of each first target preset category and the confidence probability of each preset category includes:

when the maximum value of the aggregation probability value is larger than a first preset threshold value, determining the maximum value of the aggregation probability value corresponding to a first target preset category as the category of the first object;

when the maximum value of the aggregation probability values is smaller than a first preset threshold and larger than a second preset threshold, superposing the corresponding confidence probability on each first target preset category to obtain the comprehensive probability value of each first target preset category;

determining a first target preset category corresponding to the maximum value of the comprehensive probability value as the category of the first object;

and when the maximum value of the aggregation probability value is smaller than the second preset threshold value, determining the maximum value of the confidence probability corresponding to a preset category as the category of the first object.

In a second aspect, an embodiment of the present invention provides an object classification apparatus, which is disposed in an electronic device, and includes:

the system comprises a category information acquisition module, a classification information acquisition module and a classification information acquisition module, wherein the category information acquisition module is used for acquiring category information set for a target entity by each service system in a plurality of service systems matched with the functional attribute of the target entity to which a first object belongs;

the category query module is used for querying at least one first target preset category corresponding to each of the category information in a plurality of preset categories preset by a local service system storing the first object;

and the object classification module is used for classifying the first objects according to the number of the class information corresponding to each first target preset category.

In one possible implementation manner, the apparatus further includes:

a name obtaining module, configured to obtain, at the local service system, name information of the first object;

the category determining module is used for determining at least one second target preset category corresponding to the first object in the plurality of preset categories according to the name information by using a preset classification model;

the object classification module is specifically configured to classify the first objects according to the number of the category information corresponding to each first target preset category and the at least one second target preset category.

In one possible implementation manner, the category determining module includes:

the splicing submodule is used for splicing the name information and the category information set by each service system on the target entity to obtain splicing information;

the input sub-module is used for inputting the splicing information into the preset classification model and extracting category characteristics from the splicing information by using the preset classification model;

and the category determining sub-module is used for determining a second target preset category corresponding to the first object according to the category characteristics by using the preset classification model.

In one possible implementation manner, the category information obtaining module includes:

the object query submodule is used for querying a target second object which is consistent with the target entity and belongs to the entity in a plurality of second objects stored in a specific service system; wherein the particular business system is any one of the plurality of business systems;

and the category information extracting sub-module is used for extracting a category text displayed by the target second object in the specific service system as category information set for the target entity by the specific service system.

In one possible implementation manner, the category query module includes:

the mapping sub-module is used for mapping any category information in the category information to a node where an associated preset category with the highest similarity with the category information is located;

the category obtaining sub-module is used for taking the associated preset category as the first target preset category when the node where the associated preset category is located is a leaf node in a pre-constructed category tree; each node in the pre-constructed category tree corresponds to the plurality of preset categories one by one;

and the category obtaining sub-module is further configured to, when the associated preset category is not a leaf node in a pre-constructed category tree, use the preset category located at the node child node where the associated preset category is located as the first target preset category.

In one possible implementation manner, the object classification module includes:

the probability setting submodule is used for setting the matching probability of any first target preset category for matching the first object under each target category information dimension according to the number of the first target preset categories corresponding to the service system dimension of each target category information in sequence when the number of the target category information corresponding to the any first target preset category is multiple;

the superposition submodule is used for superposing the matching probability of each first target preset category under different target category information dimensions to obtain the aggregation probability value of each first target preset category;

and the object classification submodule is used for classifying the first objects according to the aggregation probability value of each first target preset category.

In one possible implementation manner, the apparatus further includes:

a name obtaining module, configured to obtain, in the local service system, name information of the first object;

the probability obtaining module is used for inputting the name information into a preset classification model and outputting the confidence probability of each preset category in the plurality of preset categories and the first object;

the object classification submodule is specifically configured to classify the first object according to the aggregation probability value of each first target preset category and the confidence probability of each preset category.

In one possible implementation manner, the object classification sub-module is specifically configured to:

when the maximum value of the aggregation probability values is smaller than a first preset threshold and larger than a second preset threshold, overlapping the aggregation probability value and the confidence probability corresponding to each first target preset category to obtain a comprehensive probability value of each first target preset category;

In a third aspect, an embodiment of the present invention provides a terminal device, including: at least one processor; and at least one memory communicatively coupled to the processor, wherein: the memory stores program instructions executable by the processor, the processor calling the program instructions to be able to perform the method provided by the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions cause the computer to execute the method provided in the first aspect.

It should be understood that the second to fourth aspects of the embodiment of the present invention are consistent with the technical solution of the first aspect of the embodiment of the present invention, and the beneficial effects obtained by the aspects and the corresponding possible implementation manners are similar, and are not described again.

[ description of the drawings ]

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present specification, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flowchart illustrating steps of an object classification method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a category tree constructed by a local business system storing a first object according to an example of the present invention;

FIG. 3 is a flow chart illustrating steps of another object classification method according to an embodiment of the present invention;

FIG. 4 is a flow chart of an exemplary method of classifying objects in accordance with the present invention;

fig. 5 is a functional block diagram of an object classification apparatus according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.

[ detailed description ] embodiments

For better understanding of the technical solutions in the present specification, the following detailed description of the embodiments of the present invention is provided with reference to the accompanying drawings.

It should be understood that the described embodiments are only a few embodiments of the present specification, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step are within the scope of the present specification.

The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the specification. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be noted that, in the technical solution, the user data or related information are collected and processed on the basis of complying with the relevant policy and regulation and obtaining the agreement of the corresponding subject, and the data is processed and used in a big data application scenario, and cannot be identified to any natural person or generate a specific association with the privacy of the natural person.

With the development of the internet, functions and characteristics of offline entities (such as shops, landmark buildings and the like) are abstracted by an online system (such as websites, application programs and the like), the abstracted functions and characteristics of the offline entities are expressed in a function and data mode, objects are created and stored in a database of the online system, and when relevant instructions are received, the online system directly calls relevant data to be displayed on an interactive interface in response to the relevant instructions.

The information on which the object is created may deviate from the actual situation of the entity, resulting in a poor accuracy of the function and data expressing the object. With the development of the internet, the online system is also updated iteratively, and the category marked when the object is created cannot be applied to a new category architecture of the updated online system.

Even if a machine learning model is constructed, the class information of the object is recalculated by using the data stored in the system, and the accuracy of the machine learning model for judging the class information is limited by the deviation between the originally stored data of the system and the actual situation of the entity and the accuracy of the originally stored data.

Illustratively, the object is created, the catering shop A is uniformly set that the category is catering, the system adapts to the business development updating category architecture, the catering category is modified into the food category, and sub-categories are added under the food category: chinese meal, western meal, southeast Asia dish, Japanese dish, etc. The object category stored by the business system is not matched with the category architecture after the system is updated, so that the condition that the catering shop A cannot be recommended in response to the fact that the user inputs the keyword Chinese meal.

In view of the foregoing problems, an embodiment of the present invention provides an object classification method applied to an electronic device. Fig. 1 is a flowchart of steps of an object classification method according to an embodiment of the present invention, and as shown in fig. 1, the steps include:

the electronic devices may include terminals, servers, computer clusters, and the like.

Step S101: and obtaining the category information set for the target entity by each service system in the plurality of service systems matched with the functional attribute of the target entity to which the first object belongs.

The first object is an object created by a local system for a target entity, the local system is a system where an object to be classified is located, and the first object may refer to the object to be classified.

The business system may be a website, an application, etc. When the application scenario of the specific service system matches the functional attribute of the target entity, the specific service system may be considered to match the functional attribute of the target entity. For example, the target entity is a Chinese food store, the functional attributes of the target entity include restaurants, location points, and the like, the group-buying application includes an application recommending the dining store, and the group-buying application is a business system matched with the functional attributes of the Chinese food store; the map application includes an application that displays the location of the Chinese food store, and is also a business system that matches the functional attributes of the Chinese food store.

The category information set for the target entity by the existing business system can be a classification result of the target entity by collecting relevant characteristics of the target entity and according to the relevant characteristics through machine learning; the category information set by the existing service system for the target entity can also be the category information after user verification; the category information set for the target entity by the existing service system can also be the category information determined after the service system is investigated offline.

In an example of the present invention, the collected service system matching the function attribute matching of the target entity to which the first object belongs may be verified, whether the class information labeled by the service system object is accurate is verified by sampling, and when the class information set by the service system accurately indicates the object class, the service system mines the class information set for the target entity.

In an example of the present invention, a data mining tool such as a big data semantic intelligent analysis platform may be used to obtain category information of a target entity in other business systems.

Step S102: and inquiring at least one first target preset category corresponding to the category information in a plurality of preset categories preset by a local service system storing the first object.

Different service systems maintain category systems suitable for application scenarios of the different service systems, and the category systems maintained by the different service systems have different category information set for entities of the same type, so that the category information acquired from other service systems needs to be mapped to the category system maintained by the system where the first object is located, and which preset categories and category information in the service system where the first object is located correspond to entities of the same type are inquired.

In an example of the present invention, the local business system storing the first object is an online shopping platform of an electronic product, and under a category system maintained by the online shopping platform of the electronic product, the category of the electronic book is an electronic reader; a certain comprehensive e-commerce platform is used as a service system matched with the functional attributes of the e-book, and the corresponding category of the e-book is an electronic product under a maintained category system. Electronic products and e-readers refer to the same class of entities. The method comprises the steps that the category information of a target entity obtained from a certain comprehensive e-commerce platform is an electronic product, and a first target preset category corresponding to the electronic product is inquired from a plurality of preset categories preset by a local business system storing a first object and is an electronic reader.

The local business system storing the first object classifies the electronic book, the category information set by other business systems for the target entity to which the first object belongs can be directly obtained, and the category information is obtained by analyzing the target entity through other business systems, so that the first target preset category corresponding to a plurality of category information in the local business system storing the first object can represent the target entity type generally accepted by most business systems.

Step S103: and classifying the first objects according to the number of the category information corresponding to each first target preset category.

The number of the category information corresponding to the first target preset category may refer to the number of the service systems selecting the type of the target entity to which the first target preset category represents the first object.

In one example of the present invention, a business system for matching functional attributes of a target entity to which a first object belongs includes: the group buying platform, the map system, the food recommendation forum and the target entity name of the first object stored by the local business system are the Chinese restaurant of the small spread of the northdown. The category information mined from the group purchase platform, the map system and the food recommendation forum to the corresponding target entities is Chinese food, food and improved Sichuan dishes respectively, and the category information corresponds to a plurality of preset categories preset by the local business system: the first target preset categories of Chinese food, cate and improved Sichuan dish are respectively as follows: staple food, snacks. The category information corresponding to the staple food comprises Chinese food and fine food, and it can be seen that a group purchase platform and a map system in three business systems matched with the functional attributes of the target entity to which the first object belongs objectively identify that the target entity type to which the first object belongs is the staple food in a local business system for storing the first object, and most business systems matched with the functional attributes of the target entity objectively identify that the target entity type to which the first object belongs is the staple food in the local business system for storing the first object.

The embodiment of the invention realizes the classification of the first object from the dimension of the target entity to which the first object belongs. And mining the category information set for the target entity by other business systems in which the relevant data of the target entity is stored in the Internet. The method comprises the steps of mapping category information set by other business systems for a target entity to a local business system storing a first object, inquiring a first target preset category corresponding to the category information in the local business system, and selecting a category to which the target entity belongs under most business systems of the Internet according to the number of the category information corresponding to the first target preset category. According to the method, the type of the first object is rapidly determined, and the method is not influenced by the accuracy of the data adopted by the first object by the local business system storing the first object.

The object classification method provided by the embodiment of the invention is used for inquiring the class information determined by other systems of the internet to the target entity to which the first object belongs aiming at the first object to be classified in the local system to obtain the class to which the target entity belongs under the evaluation systems of other systems in the internet; the method comprises the steps that category information determined by other internet systems for a target entity is corresponded to a local system to obtain a first target preset category, and the number of the category information corresponding to the first target preset category is larger as the first target preset category represents a corresponding expression mode of the other internet systems for the target entity to which the first object belongs in the local system, so that the more the systems determining that the category of the first object is the first target preset category in the internet; according to the analysis, the first object is classified according to the number of the class information corresponding to the first target preset category, the obtained class of the first object, and the result obtained by classifying the first object from the dimension of the entity to which the first object belongs are the result of actually identifying the class of the entity to which the first object belongs objectively by most business systems, and the accurate classification result can be quickly obtained.

Another embodiment of the present invention provides an implementation manner of obtaining the category information, and step S101 includes sub-steps S201 to S202.

Step S201: querying a target second object which is consistent with the target entity in the entity to which the second object belongs in a plurality of second objects stored in a specific business system; wherein the particular business system is any one of the plurality of business systems.

Obtaining a target entity to which a first object to be classified belongs, searching a service system with an object created aiming at the target entity in the Internet, and using the service system as a specific service system in a plurality of service systems matched with the functional attribute of the target entity; and querying a second object corresponding to the target entity in the specific service system, and extracting a category text of the second object as the category information of the target entity.

In an example of the present invention, the following method may be adopted to query a target second object, which is consistent with the target entity, of the plurality of second objects stored in the specific business system: extracting text information, such as the address, name and contact information of the second object, in a window interface for displaying the second object by the specific business system, calling related data, such as the address, name and contact information of the first object, stored by a local business system for storing the first object, calculating the similarity between the text information and the related data, and judging whether an entity to which the second object belongs is consistent with a target entity to which the first object belongs. And when the entity to which the second object belongs is consistent with the target entity, determining the second object as the target second object, and screening to obtain the category text displayed in the specific service system from the text information in the window interface for extracting and displaying the second object.

In an example of the present invention, a plurality of target second objects exist in a specific business system, for example, the group buying platform system includes a scenic spot recommendation architecture and a takeout architecture, the scenic spot recommendation architecture is provided with a browse page for recommending food around the scenic spot, the browse page for recommending food is displayed with a second object a created according to the dining store a, and the takeout architecture is provided with a window for displaying a second object B created according to the dining store a. Category text spot snacks of the second object A and category text netlike meat pie snacks of the second object B can be respectively extracted to serve as category information set for the catering shop A by the group buying platform system.

Step S202: and extracting the category text displayed by the target second object in the specific service system as the category information set by the specific service system for the target entity.

The embodiment of the invention determines the specific service system with the target entity corresponding to the second object according to the text information displayed by each service system in the internet, extracts the category text displayed by the specific service system aiming at the second object, and obtains the category information set by the service system matched with the functional attribute of the target entity on the target entity.

In another embodiment of the present invention, a method for querying at least one first target preset category corresponding to each of a plurality of category information is provided, where step S102 includes substeps S301 to substep S303.

S301: and mapping any category information in the category information to a node where a related preset category with the highest similarity with the category information is located.

S302: when the node where the associated preset category is located is a leaf node in a pre-constructed category tree, taking the associated preset category as the first target preset category; and each node in the pre-constructed category tree corresponds to the plurality of preset categories one by one.

S303: and when the associated preset category is not a leaf node in a pre-constructed category tree, taking the preset category positioned at the node subnode of the associated preset category as the first target preset category.

The category tree can be constructed according to the coarse granularity of services expressed by different preset categories in the plurality of preset categories under the local service system.

Fig. 2 is a schematic structural diagram of a category tree constructed by a local business system storing a first object in an example of the present invention, as shown in fig. 2, a first-level preset category meal and shopping is used as a root node of the category tree, there is no parent node in the first-level preset category meal and shopping, a second-level preset category meal and hot pot are child nodes of the preset category meal, and a third preset category cantonese dish and chuanxiong dish are child nodes of the preset category meal. The node where the beauty makeup, the clothing and the electric appliance products are located in the second layer of preset categories is a sub-node of the node where the shopping of the preset categories is located; in the third layer of preset categories, nodes where the mobile phone, the tablet, the computer and the reader are located are child nodes of nodes where the preset category electric products are located. The preset categories of the third layer, namely Guangdong dishes, Sichuan dishes, skin care and color cosmetics, are leaf nodes of the category tree, and the preset categories positioned at the leaf nodes of the category tree are the most accurate expression modes of the first object types under the application scene of the local service system for storing the first object.

Taking the preset category of the electric product as an example, the child node of the node where the electric product is located includes: the mobile phone is located at the node, the tablet is located at the node, the reader is located at the node and the computer is located at the node. The mobile phone, the tablet, the reader and the computer can be used as subclasses of electronic products, and it can be understood that the electric products include the mobile phone, the tablet, the reader and the computer.

The sub-step S301 to the sub-step S303 are explained based on the category tree shown in fig. 2.

The business system matched with the functional attributes of the target entities in one example of the invention comprises a certain electronic mall and a certain comprehensive e-commerce platform, wherein the target entity to which the first object belongs is an e-book store, the certain electronic mall creates a second object A corresponding to the e-book store, the category information obtained by extracting the category text of the second object A is an electronic reader, the certain comprehensive e-commerce platform creates a second object B corresponding to the e-book store, and the category information obtained by extracting the category text of the second object B is a household appliance.

Querying the category tree shown in fig. 2 that the similarity between the preset category reader and the electronic reader is highest, determining that the preset category reader is the associated preset category of the category information electronic reader, and mapping the electronic reader to the node where the reader is located; the category tree shown in fig. 2 is searched for that the similarity between the preset category electric appliance product and the household electric appliance is the highest, the preset category electric appliance product is determined to be the associated preset category of the category information household electric appliance, and the household electric appliance is mapped to the node where the electric appliance product is located.

The node where the electronic reader is mapped to the reader is a leaf node of the category tree shown in fig. 2, and the node where the electronic reader is located is determined to be a first target preset category. The category information set for the second object a by a certain electronic marketplace corresponds to a preset category in the category tree shown in fig. 2, and it can be understood that, in terms of a service system of a certain electronic marketplace, the category of the target entity electronic book store to which the first object belongs in the local service system for storing the first object is determined as a reader.

The nodes where the household appliances are mapped to the electric appliance products are non-leaf nodes of the category tree shown in fig. 2, and the sub-nodes of the nodes where the electric appliance products are located are as follows: the node where the preset category mobile phone is located, the node where the preset category panel is located, the node where the preset category reader is located and the node where the preset category computer is located are the first target preset category. The category information set for the second object B by a certain integrated e-commerce platform corresponds to four preset categories in the category tree shown in fig. 2, and it can be understood that, from the perspective of a certain integrated e-commerce platform service system, the categories of the target entity e-book store to which the first object belongs in the local service system for storing the first object may be: a mobile phone, a tablet, a reader or a computer.

Counting the number of the category information corresponding to each first target preset category to obtain: the mobile phone corresponds to the category information: an electrical product; the flat plate corresponds to the category information: an electrical product; the reader corresponds to the category information: electrical products and electronic readers. The reader corresponds to two types of information of an electric product and an electronic reader, the reader is the type of the first object which is determined under the angle of two business systems of objects with electronic book stores, and the type of the target entity electronic book store to which the reader can be generally accepted by a user can be represented.

The embodiment of the invention provides another object classification method, which classifies a first object from the dimension of a target entity to which the first object belongs and the data dimension adopted by the first object from a local business system for storing the first object.

In order to more intelligently implement the object classification method proposed by the embodiment of the invention, the applicant constructs a neural network model to be trained based on a text classification network (textCNN). The method includes collecting entity samples, for example, a store, a landmark building, and the like, using names of the store and the landmark building as training samples, and labeling types of the collected entity samples as comparison samples, for example, labeling store categories according to store function attributes: clothing stores, luggage stores, jewelry stores, and the like.

According to an example of the invention, a category tree as shown in fig. 2 is constructed in advance, and a preset category which best meets the function attribute of a store can be used as an entity sample type according to the similarity between the function attribute of the store and the preset category recorded by nodes in the category tree.

And training the constructed neural network model for multiple times by adopting the training samples and the comparison samples until the model is converged to obtain a preset classification model which can perform characteristic analysis on the names of the shops or landmark buildings and output the types of the shops or landmark buildings.

Fig. 3 is a flowchart of steps of another object classification method according to an embodiment of the present invention, and as shown in fig. 3, the steps include:

step S401: and acquiring the name information of the first object in the local service system.

The name information of the first object can be obtained by extracting the text information of the local service system storing the first object for displaying the window interface of the first object.

Step S402: and determining at least one second target preset category corresponding to the first object in the plurality of preset categories according to the name information by using a preset classification model.

The textCNN extracts features in the name information by using a plurality of convolution kernels (kernel) with different sizes, captures local correlation of the name to complete a text classification task, and presets a second target class with the largest correlation with the name information in a plurality of preset classes.

Step S403: and obtaining the category information set by each service system in the plurality of service systems for the target entity, wherein the category information is matched with the functional attribute of the target entity to which the first object belongs.

Step S404: and inquiring at least one first target preset category corresponding to the category information in a plurality of preset categories preset by a local service system storing the first object.

The time for the electronic device to execute steps S401 to S402 and the time for the electronic device to execute steps S403 to S404 are not sequential, and it can be understood that the electronic device may first execute steps S401 to S402 to obtain the second target preset category; or step S403 to step S404 may be executed first to obtain a first target preset category; the related steps can also be executed simultaneously to obtain the first target preset category and the second target preset category.

The electronic equipment executes the steps S401 to S402, and obtains the type information of the first object from the data dimension adopted by the local business system for storing the first object to the first object; the electronic device executes steps S403 to S404 to obtain the type information of the first object from the dimension of the target entity to which the first object belongs.

Step S405: and classifying the first objects according to the number of the category information corresponding to each first target preset category and the at least one second target preset category.

The electronic device performs step S405, merging the data dimension adopted by the first object from the local business system storing the first object to obtain information related to the first object type, and obtaining information related to the first object type from the dimension of the target entity to which the first object belongs.

Taking the category tree shown in fig. 2 as an example, obtaining the first target preset category from the dimension of the target entity to which the first object belongs includes skin care and color makeup, where the first target preset category color makeup corresponds to two types of information, and it can be understood that: generally determining the type of a target entity to which a first object belongs by a plurality of service systems matched with the functional attributes of the target entity to which the first object belongs in the internet, wherein the makeup can better represent the type of the target entity to which the first object belongs; the second target preset category output by the preset classification model comprises makeup; and fusing the information, classifying the first object, and determining that the category of the first object is the makeup.

One example of the present invention proposes an implementation method for obtaining the second target preset class according to the name information, and step S402 includes sub-steps S501 to S503.

S501: and splicing the name information and the category information set by each service system for the target entity to obtain splicing information.

Illustratively, the extracting the first object name information as the small northdown spread, and the plurality of business systems matched with the functional attributes of the small northdown spread of the target entity to which the first object belongs includes: the system comprises a certain group purchasing platform and a certain food recommending website, wherein the category information set by the certain group purchasing platform for the small northern Tang shop is a Chinese restaurant, and the category information set by the certain food recommending website for the small northern Tang shop is a seafood porridge card-reading place. And splicing the small northern Tang shop, the Chinese restaurant and the seafood porridge in a card printing way to obtain splicing information.

The northand small shop, the chinese restaurant, the seafood porridge card-making place, etc. may be converted into a vector representation using a word2vec model, a VSM vector space model, a Neural Network Language Model (NNLM), etc., or the stitching information may be converted into a vector representation.

Step 502: inputting the splicing information into the preset classification model, and extracting category characteristics from the splicing information by using the preset classification model.

Step S503: and determining a second target preset category corresponding to the first object according to the category characteristics by using the preset classification model.

The preset classification model input vector comprises characteristics in data used by a local service system to create the first object and characteristics of classification information determined by other internet service systems on the first object. And extracting the features contained in the splicing information by a preset classification model, and fusing the features of the preset classification model and the splicing information. Even if the data used by the local service system for creating the first object has errors, the preset classification model can correct the errors according to the class information extracted from other service systems of the internet. The accuracy of the output of the preset classification model is ensured.

Another embodiment of the present invention provides that after the local system storing the first object queries at least one first target preset category corresponding to each of the plurality of category information, the matching probability of the category information mapped to each first target preset category may be set according to the number of the first target preset categories corresponding to the category information.

When the number of the target category information corresponding to any first target preset category is one, the probability of mapping from the category information to the first target preset category is set to be 100%.

When the number of the target category information corresponding to any first target preset category is multiple, the matching probability of the first target preset category matching the first object under each target category information dimension is set according to the number of the first target preset category corresponding to the service system dimension where each target category information is located.

For example, as shown in fig. 2, the category information corresponding to the first target preset category makeup includes: and the makeup, namely the skin care is further included in the first target preset category corresponding to the service system dimension to which the makeup belongs. The category information beauty makeup is other exogenous business systems except for the business system to which the category information beauty makeup belongs and the first object is stored. It can be understood that, in the business system dimension to which the category information makeup belongs, the probability of determining that the type of the first object is makeup is 50%.

And superposing the matching probability of each first target preset category under different target category information dimensions to obtain the aggregation probability value of each first target preset category.

When the service system which is inquired from the internet and matched with the functional attribute of the target entity to which the first object belongs is enough, the matching probability of each first target preset category under different target category information dimensions is superposed, and the obtained aggregate probability value can be regarded as the support rate of a website or an application program which is related to the target entity to which the first object belongs and aims at the first target preset category in the internet.

The embodiment of the invention provides that the preset classification model can output confidence probabilities that different preset categories can be determined as second target preset categories. The method comprises the following steps:

step S601: and acquiring the name information of the first object in the local service system.

Step S602: and inputting the name information into a preset classification model, and outputting the confidence probability of each preset category in the plurality of preset categories and the first object.

The preset classification model textCNN utilizes a plurality of convolution kernels (kernel) with different sizes to extract semantic features in the name information, calculates the correlation between the semantic features and each preset category, and outputs the confidence probability between each preset category and the first object according to the correlation between the semantic features and each preset category.

The confidence probability of the preset category represents the probability that the preset classification model can accurately express the type of the first object according to the related data (such as name information) of the first object.

Step S603: and classifying the first objects according to the aggregation probability value of each first target preset category and the confidence probability of each preset category.

Step S603 includes substeps S701 to step S703:

s701: and when the maximum value of the aggregation probability value is larger than a first preset threshold value, determining the maximum value of the aggregation probability value corresponding to a first target preset category as the category of the first object.

S702: when the maximum value of the aggregation probability values is smaller than a first preset threshold and larger than a second preset threshold, superposing the confidence probability corresponding to each first target preset category to obtain the comprehensive probability value of each first target preset category; and determining a first target preset category corresponding to the maximum value of the comprehensive probability value as the category of the first object.

S703: and when the maximum value of the aggregation probability value is smaller than the second preset threshold value, determining the maximum value of the confidence probability corresponding to a preset category as the category of the first object.

The method comprises the steps that a local service system classifies a first object according to related data of the first object, the confidence probability of the first object in a preset category is obtained from the dimension of the local service system, category information determined by other service systems of the Internet to an entity is introduced, the confidence probability of the first object in the preset category is obtained from the dimension of an external source system, and the comprehensive probability value of the first object in the preset category is obtained by integrating the dimension of the local service system and the determination result of the external source system to the first object. The method integrates the results of the local service system dimension and the external source system dimension, and is more reliable. The characteristics used by the textCNN model algorithm adopt general characteristics, category information in internet information is introduced, and more scenes can be covered; on the basis of the textCNN model, more visual internet category information is introduced, and the source tracing of the prediction result is easier. Due to the convenience of determining the category information of the first object by the dimension of the external source system, the optimization of the subsequent steps can be completed quickly on the basis of the stability of the model.

Fig. 4 is a flowchart illustrating an object classification method according to an embodiment of the present invention, and as shown in fig. 4, the steps include:

k11: constructing a category tree as shown in fig. 2, wherein the category tree comprises a plurality of preset categories: catering, shopping, Chinese food, chafing dish, makeup, clothing, electric products, Guangdong dish, Sichuan dish, etc.

K12: obtaining a target entity to which a first object to be classified belongs: an electronic book store. And excavating the Internet to obtain a plurality of service systems matched with the functional attributes of a certain electronic product online shopping platform, a certain comprehensive e-commerce platform and a certain map system as matching target entities.

K13: the category information of the electronic book store is extracted from an electronic product online shopping platform, a certain comprehensive e-commerce platform and a certain map system respectively. The category information set by the online shopping platform of the electronic product for the electronic book stores is an electronic reader, the category information set by a certain comprehensive e-commerce platform for the electronic book stores is a household appliance, and the category information set by a certain map system for the electronic book stores is a digital product store.

K14: the category information 1 to the category information k are respectively: the method comprises the following steps that the electronic reader, the household appliances and the digital product stores are mapped to a category tree which is constructed by a business system where a first object to be classified is located, wherein the category tree is shown in figure 2, and the step of inquiring a first target preset category corresponding to the electronic reader comprises the following steps: and the reader sets the matching probability of pointing to the first target preset category reader from the category information of the shopping platform on the certain electronic product line to be 100%.

K15: the querying of the first target preset category corresponding to the household appliance comprises the following steps: the mobile phone, the tablet, the reader and the computer are arranged, wherein the matching probability of pointing to the first target preset category reader from the category information of a certain comprehensive e-commerce platform is 25%, the matching probability of pointing to the first target preset category mobile phone from the category information of the certain comprehensive e-commerce platform is 25%, the matching probability of pointing to the first target preset category tablet from the category information of the certain comprehensive e-commerce platform is 25%, and the like.

K16: the method comprises the steps that a first target preset category corresponding to a digital product store is inquired and comprises a mobile phone, a tablet, a reader and a computer, the matching probability of pointing to the first target preset category reader from the category information of a map system is 25%, the matching probability of pointing to the first target preset category mobile phone from the category information of a certain comprehensive e-commerce platform is 25%, the matching probability of pointing to the first target preset category tablet from the category information of the certain comprehensive e-commerce platform is 25%, and the like.

K17: the local business system storing the first object extracts name information of the first object, splices the name information, the electronic reader, the household appliance and the digital product store to obtain splicing information, inputs the splicing information into a preset classification model, and outputs and inputs a confidence probability distribution between each preset category in a category tree shown in fig. 2 and the first object: [ catering-0%, shopping-0%, Chinese meal-2%, chafing dish-2%, makeup-3%, clothing-1%, electric products-0%, Guangdong dish-1%, Sichuan dish-1%, skin-care-2%, makeup-1%, mobile phone-10%, tablet-10%, computer-5% and reader-62% ].

K18: and superposing the matching probabilities calculated by K14-K16 to obtain that each first target preset category can accurately express the matching probability distribution of the first object category based on other business systems except the local business system for storing the first object: [ cell phone-50%, tablet-50%, computer-50%, reader-150% ].

K19: when the aggregate probability value: and when the reader-150% is larger than a first preset threshold value, determining the reader as the category of the first object. When the reader-150% is smaller than a first preset threshold and larger than a second preset threshold, overlapping matching probability distribution: [ cell phone-50%, tablet-50%, computer-50%, reader-150% ] and confidence probability distribution: [ catering-0%, shopping-0%, Chinese meal-2%, chafing dish-2%, makeup-3%, clothing-1%, electric products-0%, cantonese dish-1%, Sichuan dish-1%, skin care-2%, makeup-1%, mobile phone-10%, tablet-10%, computer-5% and reader-62% ] to obtain the comprehensive probability value of each first target preset category; and determining the reader corresponding to the maximum value of the comprehensive probability value as the category of the first object. And when the reader-150% is smaller than the second preset threshold, determining the maximum value of the confidence probability corresponding to the preset category as the category of the first object.

Fig. 5 is a functional block diagram of an object classifying apparatus according to an embodiment of the present invention, the object classifying apparatus is disposed in an electronic device, and as shown in fig. 5, the apparatus includes:

a category information obtaining module 51, configured to obtain category information set for a target entity by each service system in a plurality of service systems that are matched with a functional attribute of the target entity to which a first object belongs;

a category query module 52, configured to query at least one first target preset category corresponding to each of the multiple pieces of category information in multiple preset categories preset by a local service system that stores the first object;

and the object classification module 53 is configured to classify the first object according to the number of the category information corresponding to each first target preset category.

The object classification apparatus provided in the embodiment shown in fig. 5 may be used to implement the technical solutions of the method embodiments shown in fig. 1 to fig. 4 in this specification, and the implementation principles and technical effects thereof may further refer to the related descriptions in the method embodiments.

Optionally, the apparatus further comprises:

Optionally, the category determining module includes:

Optionally, the category information obtaining module includes:

the object query submodule is used for querying a target second object which is consistent with the target entity and belongs to the entity in a plurality of second objects stored in a specific business system; wherein the particular business system is any one of the plurality of business systems;

Optionally, the category query module includes:

the mapping submodule is used for mapping any category information in the category information to a node where a related preset category with the highest similarity with the category information is located;

Optionally, the object classification module comprises:

Optionally, the apparatus further comprises:

Optionally, the object classification sub-module is specifically configured to:

when the maximum value of the aggregation probability values is larger than a first preset threshold value, determining the maximum value of the aggregation probability values corresponding to a first target preset category as the category of the first object;

The apparatus provided in the above-mentioned illustrated embodiment is used to implement the technical solution of the above-mentioned illustrated method embodiment, and the implementation principle and technical effect thereof may further refer to the related description in the method embodiment, which is not described herein again.

The apparatus provided in the above-described illustrated embodiment may be, for example: a chip or a chip module. The apparatus provided in the above-described embodiment is configured to implement the technical solution of the above-described method embodiment, and the implementation principle and technical effect of the apparatus may further refer to the relevant description in the method embodiment, which is not described herein again.

Each module/unit included in each device described in the above embodiments may be a software module/unit, or may also be a hardware module/unit, or may also be a part of a software module/unit, and a part of a hardware module/unit. For example, for each device applied to or integrated in a chip, each module/unit included in the device may be implemented by hardware such as a circuit, or at least a part of the modules/units may be implemented by a software program running on a processor integrated in the chip, and the rest of the modules/units may be implemented by hardware such as a circuit; for each device applied to or integrated in the chip module, each module/unit included in the device may be implemented by using hardware such as a circuit, and different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the chip module, or at least some of the modules/units may be implemented by using a software program running on a processor integrated in the chip module, and the rest of the modules/units may be implemented by using hardware such as a circuit; for each device applied to or integrated in the electronic device, each module/unit included in the device may be implemented by using hardware such as a circuit, and different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) or different components in the electronic device, or at least part of the modules/units may be implemented by using a software program running on a processor integrated in the electronic device, and the rest (if any) part of the modules/units may be implemented by using hardware such as a circuit.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 600 includes a processor 610, a memory 611, and a computer program stored in the memory 611 and capable of being executed on the processor 610, where the processor 610 executes the computer program to implement the steps in the foregoing method embodiments, and the electronic device according to the embodiment may be used to implement the technical solution according to the foregoing method embodiment, and further reference may be made to the description in the method embodiments for implementation principles and technical effects, which are not described herein again.

Fig. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure, where as shown in fig. 7, the terminal device may include at least one processor; and at least one memory communicatively coupled to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the object classification method provided by the embodiments shown in fig. 1 to 4 in the present specification.

It is to be understood that the illustrated structure of the embodiment of the present invention does not specifically limit the terminal device 100. In other embodiments of the invention, terminal device 100 may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

As shown in fig. 7, the terminal device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a mobile communication module 150, a wireless communication module 160, an indicator 192, a camera 193, a display 194, and the like.

Processor 110 may include one or more processing units, such as: the processor 110 may include an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a video codec, a Digital Signal Processor (DSP), a baseband processor, and/or a neural-Network Processing Unit (NPU), etc. Wherein, the different processing units may be independent devices or may be integrated in one or more processors.

The controller can generate an operation control signal according to the instruction operation code and the timing signal to complete the control of instruction fetching and instruction execution.

A memory may also be provided in processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that have just been used or recycled by the processor 110. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Avoiding repeated accesses reduces the latency of the processor 110, thereby increasing the efficiency of the system.

The processor 110 executes various functional applications and data processing by executing programs stored in the internal memory 121, for example, implementing the object classification method provided by the embodiments shown in fig. 1 to 4 of the present invention.

The wireless communication function of the terminal device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, a modem processor, a baseband processor, and the like.

The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in terminal device 100 may be used to cover a single or multiple communication bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed as a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The terminal device 100 implements a display function by the GPU, the display screen 194, and the application processor. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and an application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

The display screen 194 is used to display images, video, and the like. The display screen 194 includes a display panel. The display panel may adopt a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode, AMOLED), a flexible light-emitting diode (FLED), a miniature, a Micro-oeld, a quantum dot light-emitting diode (QLED), and the like. In some embodiments, the terminal device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

The terminal device 100 may implement a shooting function through the ISP, the camera 193, the video codec, the GPU, the display screen 194, the application processor, and the like.

The ISP is used to process the data fed back by the camera 193. For example, when a photo is taken, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, the optical signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converting into an image visible to naked eyes. The ISP can also carry out algorithm optimization on the noise, brightness and skin color of the image. The ISP can also optimize parameters such as exposure, color temperature and the like of a shooting scene. In some embodiments, the ISP may be provided in camera 193.

The camera 193 is used to capture still images or video. The object generates an optical image through the lens and projects the optical image to the photosensitive element. The photosensitive element may be a Charge Coupled Device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to be converted into a digital image signal. And the ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV and other formats. In some embodiments, the terminal device 100 may include 1 or N cameras 193, N being a positive integer greater than 1.

The digital signal processor is used for processing digital signals, and can process digital image signals and other digital signals. For example, when the terminal device 100 selects a frequency point, the digital signal processor is used to perform fourier transform or the like on the frequency point energy.

Video codecs are used to compress or decompress digital video. The terminal device 100 may support one or more video codecs. In this way, the terminal device 100 can play or record video in a plurality of encoding formats, such as: moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, and the like.

The internal memory 121 may be used to store computer-executable program code, which includes instructions. The internal memory 121 may include a program storage area and a data storage area. The storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required by at least one function, and the like. The storage data area may store data (such as audio data, a phonebook, etc.) created during use of the terminal device 100, and the like. In addition, the internal memory 121 may include a high-speed random access memory, and may further include a nonvolatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (UFS), and the like. The processor 110 executes various functional applications of the terminal device 100 and data processing by executing instructions stored in the internal memory 121 and/or instructions stored in a memory provided in the processor.

An embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, where the computer instructions enable the computer to execute the object classification method provided in the embodiments shown in fig. 1 to 4 in this specification.

The computer-readable storage medium described above may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM) or flash memory, an optical fiber, a portable compact disc read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present description may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In the description of embodiments of the invention, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present specification, "a plurality" means at least two, e.g., two, three, etc., unless explicitly defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present description in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present description.

The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.

It should be noted that the terminal according to the embodiment of the present invention may include, but is not limited to, a Personal Computer (PC), a Personal Digital Assistant (PDA), a wireless handheld device, a tablet computer (tablet computer), a mobile phone, an MP3 player, an MP4 player, and the like.

In the several embodiments provided in the present specification, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, 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 mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present description 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 can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods described in the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. An object classification method applied to an electronic device, the method comprising:

obtaining category information set for a target entity by each service system in a plurality of service systems matched with the functional attribute of the target entity to which a first object belongs;

inquiring at least one first target preset category corresponding to the category information in a plurality of preset categories preset by a local service system storing the first object;

and classifying the first objects according to the number of the class information corresponding to each first target preset category.

2. The method of claim 1, further comprising:

acquiring the name information of the first object in the local service system;

3. The method of claim 2, wherein determining a second target preset category corresponding to the first object in the plurality of preset categories according to the name information by using a preset classification model comprises:

4. The method of claim 1, wherein obtaining the category information set for the target entity by each business system in the plurality of business systems matched with the functional attribute of the target entity to which the first object belongs comprises:

and extracting the category text displayed by the target second object in the specific service system as the category information set by the specific service system for the target entity.

5. The method according to claim 1, wherein querying at least one first target preset category corresponding to each of the plurality of category information from a plurality of preset categories preset by a local service system storing the first object comprises:

6. The method of claim 1, wherein classifying the first object according to the number of category information corresponding to each first target preset category comprises:

7. The method of claim 6, further comprising:

acquiring the name information of the first object in the local service system;

8. The method of claim 7, wherein classifying the first object according to the aggregate probability value of each first target preset category and the confidence probability of each preset category comprises:

9. An object classification apparatus provided in an electronic device, the apparatus comprising:

the system comprises a category information acquisition module, a category information acquisition module and a first object acquisition module, wherein the category information acquisition module is used for acquiring category information set for a target entity by each service system in a plurality of service systems matched with the functional attribute of the target entity to which a first object belongs;

and the object classification module is used for classifying the first objects according to the number of the class information corresponding to each first target preset class.

10. A terminal device, comprising:

at least one processor; and

at least one memory communicatively coupled to the processor,

the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 8.

11. A computer readable storage medium storing computer instructions, the computer instructions causing the computer to perform the method of any one of claims 1 to 8.