CN-116861297-B - Object recognition method, device and storage medium

CN116861297BCN 116861297 BCN116861297 BCN 116861297BCN-116861297-B

Abstract

The application provides an object identification method, an object identification device and a storage medium, relates to the technical field of communication, and aims to solve the technical problems of low efficiency and low accuracy in the general technology. The method comprises the steps of obtaining service data of a first object, wherein the service data comprise service usage data and service signaling data, inputting the service data into a target classification model for classification processing to obtain a classification result of the first object, wherein the classification result comprises a service type or a common type, and determining potential objects of communication service corresponding to the service type from a plurality of second objects with call records with the first object when the first object is the service type.

Inventors

PENG JIALI
Zheng Xiayan
WU ZHENGGUANG
SHI YU

Assignees

中国联合网络通信集团有限公司

Dates

Publication Date: 20260512
Application Date: 20230717

Claims (6)

1. An object recognition method, comprising: acquiring service data of a first object, wherein the service data comprises service use data and service signaling data; the business data is input into a target classification model for classification processing to obtain a classification result of the first object, wherein the classification result comprises a service type or a common type, and the service type comprises a logistics service type or a customer service type or a training service type; determining a potential object of a communication service corresponding to the service type from a plurality of second objects with call records of the first object under the condition that the first object is the service type; the method further comprises the steps of: Acquiring a plurality of first candidate data, wherein the first candidate data comprises a type tag of the service type; Determining the first candidate data meeting a second preset condition as first sample data to obtain a plurality of first sample data, wherein the first sample data is used for representing service data of the objects of the service type, and the second preset condition comprises that the number of the corresponding called objects in a second preset time period is larger than a preset object number threshold, the average outbound time period in the second preset time period is smaller than or equal to a second time period threshold, the number of access network devices based on outbound calls in the second preset time period is smaller than or equal to a preset device number threshold, and/or the weighted scores of the number of the call objects, the number of the called objects, the average outbound time period and the number of the access network devices are larger than a preset score threshold; acquiring a plurality of second sample data, wherein the second sample data is used for representing service data of the common type of object; Training an initial classification model based on the first sample data and the second sample data to obtain the target classification model.
2. The method of claim 1, wherein determining a potential object of the communication traffic corresponding to the service type from a plurality of second objects having call records with the first object comprises: And determining a second object which accords with a first preset condition in the plurality of second objects as the potential object, wherein the first preset condition comprises that the number of times of communication with the first object in a first preset time period is larger than a preset time threshold value, the average duration of communication with the first object in the first preset time period is smaller than a first time period threshold value, and the communication network which is different from the communication network to which the first object belongs.
3. An object recognition device is characterized by comprising an acquisition unit, a processing unit and a determination unit; The acquisition unit is used for acquiring service data of the first object, wherein the service data comprises service use data and service signaling data; The processing unit is used for inputting the business data acquired by the acquisition unit into a target classification model for classification processing to obtain a classification result of the first object, wherein the classification result comprises a service type or a common type; The determining unit is configured to determine, when the first object is the service type, a potential object of a communication service corresponding to the service type from a plurality of second objects having call records with the first object; the acquisition unit is further used for acquiring a plurality of first candidate data, wherein the first candidate data comprises a type tag of the service type; The determining unit is further configured to determine the first candidate data meeting a second preset condition as first sample data to obtain a plurality of first sample data, where the first sample data is used to represent service data of objects of the service type, and the second preset condition includes that a number of called objects corresponding to the second preset duration is greater than a preset object number threshold, an average outbound duration in the second preset duration is less than or equal to a second duration threshold, a number of access network devices based on which outbound calls in the second preset duration are performed is less than or equal to a preset device number threshold, and/or a weighted score of a number of call objects, a number of called objects, a number of average outbound durations and a number of access network devices is greater than a preset score threshold; the acquisition unit is also used for acquiring a plurality of second sample data, wherein the second sample data is used for representing the service data of the common type object; the processing unit is further configured to train an initial classification model based on the plurality of first sample data and the plurality of second sample data, to obtain the target classification model.
4. An object recognition device according to claim 3, characterized in that the determining unit is adapted to: And determining a second object which accords with a first preset condition in the plurality of second objects as the potential object, wherein the first preset condition comprises that the number of times of communication with the first object in a first preset time period is larger than a preset time threshold value, the average duration of communication with the first object in the first preset time period is smaller than a first time period threshold value, and the communication network which is different from the communication network to which the first object belongs.
5. An object recognition device comprising a memory for storing computer-executable instructions and a processor coupled to the memory via a bus, the processor executing the computer-executable instructions stored in the memory when the object recognition device is in operation to cause the object recognition device to perform the object recognition method of any one of claims 1-2.
6. A computer readable storage medium comprising computer executable instructions which, when run on a computer, cause the computer to perform the object recognition method according to any one of claims 1-2.

Description

Object recognition method, device and storage medium Technical Field The present application belongs to the field of communication technology, and in particular, relates to an object identification method, an object identification device, and a storage medium. Background With the continuous development of big data technology, communication operators have applied data mining and other technologies to perform data analysis in communication services to identify potential customers. At present, data analysis may be generally performed using rule-based methods to identify potential customers. When the method is implemented, whether the client is a potential client is generally identified by judging whether the client data accords with the prefabrication rules of dimensions such as age groups, income situations, living positions and the like. Since rules are formulated by relying on manual extensive investigation, the referenced dimensions are highly limited. Thus, this approach tends to be inefficient and difficult to accurately identify potential customers. Disclosure of Invention The application provides an object identification method, an object identification device and a storage medium, which are used for solving the technical problems of lower efficiency and lower accuracy in the general technology. In order to achieve the above purpose, the application adopts the following technical scheme: The object identification method comprises the steps of obtaining service data of a first object, wherein the service data comprise service usage data and service signaling data, inputting the service data into a target classification model to conduct classification processing to obtain a classification result of the first object, wherein the classification result comprises a service type or a common type, and determining potential objects of communication services corresponding to the service type from a plurality of second objects with call records corresponding to the first object when the first object is the service type. Optionally, the method for determining the potential object of the communication business corresponding to the service type from a plurality of second objects with call records corresponding to the first object specifically comprises the following steps: And determining a second object which accords with a first preset condition in the plurality of second objects as a potential object, wherein the first preset condition comprises that the number of times of the conversation with the first object in a first preset time period is larger than a preset time threshold value, the average conversation time with the first object in the first preset time period is smaller than the first time period threshold value, and the communication network which is different from the communication network to which the first object belongs. Optionally, the object identification method further comprises the steps of obtaining a plurality of first sample data and a plurality of second sample data, wherein the first sample data is used for representing service data of objects of a service type, the second sample data is used for representing service data of objects of a common type, and training the initial classification model based on the plurality of first sample data and the plurality of second sample data to obtain a target classification model. Optionally, the first sample data meets a second preset condition; the second preset condition comprises that the number of the called objects corresponding to the second preset time length is larger than a preset object number threshold, the average outbound time length in the second preset time length is smaller than or equal to a second time length threshold, the number of access network devices based on which outbound calls in the second preset time length are performed is smaller than or equal to a preset device number threshold, and/or the weighted scores of the number of call objects, the number of the called objects, the average outbound time length and the number of the access network devices are larger than a preset score threshold: acquiring a plurality of first candidate data, wherein the first candidate data comprises a type tag of a service type; and determining the first candidate data meeting the second preset condition as first sample data to obtain a plurality of first sample data. Optionally, the service type includes a logistical service type or a customer service type or a training service type. In a second aspect, there is provided an object recognition apparatus including an acquisition unit, a processing unit, and a determination unit; The system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring service data of a first object, wherein the service data comprises service use data and service signaling data; The processing unit is used for inputting the service data acquired by the a