CN113396414A

CN113396414A - Brushing amount user identification method and related product

Info

Publication number: CN113396414A
Application number: CN201980091215.XA
Authority: CN
Inventors: 石露
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2019-06-24
Filing date: 2019-06-24
Publication date: 2021-09-14
Also published as: WO2020257988A1

Abstract

The embodiment of the application discloses a brushing amount user identification method and a related product, wherein the method comprises the following steps: the method comprises the steps of obtaining a plurality of characteristic sample sets by obtaining a characteristic sample set of each reference object in a plurality of reference objects, calculating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount recognition model, carrying out characteristic extraction on the target object to obtain a target characteristic set, inputting the target characteristic set into the target brushing amount recognition model to carry out calculation to obtain a recognition result of whether the target object is a brushing amount user or not, training the target brushing amount recognition model based on the characteristic sample sets of the plurality of reference objects, and recognizing whether the target object belongs to the brushing amount user or not according to the target brushing amount recognition model, so that the brushing amount user can be recognized more accurately.

Description

Brushing amount user identification method and related product

Technical Field

The application relates to the technical field of electronics, in particular to a brushing user identification method and a related product.

Background

With the widespread use of electronic devices (such as mobile phones, tablet computers, etc.), the electronic devices have more and more applications and more powerful functions, and the electronic devices are developed towards diversification and personalization, and become indispensable electronic products in the life of users. For example, many different applications may be installed in the electronic device, different use experiences are achieved through applications with different functions, and generally, when installing the applications, a user may prefer top-ranked applications or applications with a high download amount in an application store.

At present, in order to improve ranking and click rate, a plurality of users who do not exist can be fictitious to brush the number in many applications, and the fairness of a network service platform can be damaged by the existence of the user who brushes the number, so that the user who brushes the number needs to be identified, and the accuracy and the fairness of ranking and click rate statistics are ensured.

Disclosure of Invention

The embodiment of the application provides a method for identifying a user of a brush amount and a related product, which can identify the user of the brush amount more accurately.

In a first aspect, an embodiment of the present application provides a method for identifying a brush amount user, where the method includes:

obtaining a characteristic sample set of each reference object in a plurality of reference objects to obtain a plurality of characteristic sample sets;

calculating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount identification model;

carrying out feature extraction on the target object to obtain a target feature set;

and inputting the target feature set into the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user.

In a second aspect, an embodiment of the present application provides a device for identifying a user of a brush amount, where the device for identifying a user of a brush amount includes:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a characteristic sample set of each reference object in a plurality of reference objects to obtain a plurality of characteristic sample sets;

the operation unit is used for operating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount identification model;

the extraction unit is used for extracting the features of the target object to obtain a target feature set;

the operation unit is further configured to input the target feature set to the target brushing amount identification model for operation, so as to obtain an identification result of whether the target object is a brushing amount user.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program enables a computer to perform some or all of the steps described in the first aspect of the embodiment of the present application.

In a fifth aspect, embodiments of the present application provide a computer program product, where the computer program product includes a non-transitory computer-readable storage medium storing a computer program, where the computer program is operable to cause a computer to perform some or all of the steps as described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

Drawings

Reference will now be made in brief to the drawings that are needed in describing embodiments or prior art.

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

Fig. 1A is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;

fig. 1B is a schematic flowchart of a method for identifying a user by means of a brush amount according to an embodiment of the present application;

FIG. 2 is a flow chart illustrating another method for identifying a user by means of a brush amount according to an embodiment of the present disclosure;

FIG. 3 is a flow chart illustrating another method for identifying a user based on a brushing amount according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of another electronic device disclosed in the embodiments of the present application;

fig. 5 is a schematic structural diagram of a brushing amount user identification device disclosed in an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

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

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

The electronic devices involved in the embodiments of the present application may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to a wireless modem with wireless communication functions, as well as various forms of User Equipment (UE), Mobile Stations (MS), terminal devices (terminal device), servers, and so on. For convenience of description, the above-mentioned devices are collectively referred to as electronic devices. The following describes embodiments of the present application in detail.

Referring to fig. 1A, fig. 1A is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application, and the electronic device 100 may include a control circuit, which may include a storage and processing circuit 110. The storage and processing circuitry 110 may be a memory, such as a hard drive memory, a non-volatile memory (e.g., flash memory or other electronically programmable read-only memory used to form a solid state drive, etc.), a volatile memory (e.g., static or dynamic random access memory, etc.), etc., and the embodiments of the present application are not limited thereto. Processing circuitry in storage and processing circuitry 110 may be used to control the operation of electronic device 100. The processing circuit may be implemented based on one or more microprocessors, microcontrollers, digital master-slave headphone switch controllers, baseband processors, power management units, audio codec chips, application specific integrated circuits, display driver integrated circuits, and the like.

The storage and processing circuitry 110 may be used to run software in the electronic device 100, such as an internet browsing application, a Voice Over Internet Protocol (VOIP) telephone call application, an email application, a media playing application, operating system functions, and so forth. Such software may be used to perform control operations such as, for example, camera-based image capture, ambient light measurement based on an ambient light sensor, proximity sensor measurement based on a proximity sensor, information display functionality based on status indicators such as status indicator lights of light emitting diodes, touch event detection based on a touch sensor, functionality associated with displaying information on multiple (e.g., layered) displays, operations associated with performing wireless communication functions, operations associated with collecting and generating audio signals, control operations associated with collecting and processing button press event data, and other functions in the electronic device 100, and the like, without limitation.

The electronic device 100 may also include input-output circuitry 150. The input-output circuit 150 may be used to enable the electronic device 100 to input and output data, i.e., to allow the electronic device 100 to receive data from an external device and also to allow the electronic device 100 to output data from the electronic device 100 to the external device. The input-output circuit 150 may further include a sensor 170. The sensors 170 may include ambient light sensors, proximity sensors based on light and capacitance, touch sensors (e.g., based on optical touch sensors and/or capacitive touch sensors, where the touch sensors may be part of a touch display screen or used independently as a touch sensor structure), acceleration sensors, gravity sensors, and other sensors, among others.

Input-output circuitry 150 may also include one or more displays, such as display 130. Display 130 may include one or a combination of liquid crystal displays, organic light emitting diode displays, electronic ink displays, plasma displays, displays using other display technologies. Display 130 may include an array of touch sensors (i.e., display 130 may be a touch display screen). The touch sensor may be a capacitive touch sensor formed by a transparent touch sensor electrode (e.g., an Indium Tin Oxide (ITO) electrode) array, or may be a touch sensor formed using other touch technologies, such as acoustic wave touch, pressure sensitive touch, resistive touch, optical touch, and the like, and the embodiments of the present application are not limited thereto.

The audio component 140 may be used to provide audio input and output functionality for the electronic device 100. The audio components 140 in the electronic device 100 may include a speaker, a microphone, a buzzer, a tone generator, and other components for generating and detecting sound.

The communication circuit 120 may be used to provide the electronic device 100 with the capability to communicate with external devices. The communication circuit 120 may include analog and digital input-output interface circuits, and wireless communication circuits based on radio frequency signals and/or optical signals. The wireless communication circuitry in communication circuitry 120 may include radio-frequency transceiver circuitry, power amplifier circuitry, low noise amplifiers, switches, filters, and antennas. For example, the wireless communication circuitry in communication circuitry 120 may include circuitry to support Near Field Communication (NFC) by transmitting and receiving near field coupled electromagnetic signals. For example, the communication circuit 120 may include a near field communication antenna and a near field communication transceiver. The communications circuitry 120 may also include a cellular telephone transceiver and antenna, a wireless local area network transceiver circuitry and antenna, and so forth.

The electronic device 100 may further include a battery, power management circuitry, and other input-output units 160. The input-output unit 160 may include buttons, joysticks, click wheels, scroll wheels, touch pads, keypads, keyboards, cameras, light emitting diodes and other status indicators, and the like.

A user may input commands through input-output circuitry 150 to control the operation of electronic device 100, and may use output data of input-output circuitry 150 to enable receipt of status information and other outputs from electronic device 100.

Referring to fig. 1B, fig. 1B is a schematic flow chart of a method for identifying a user with a brush amount according to an embodiment of the present disclosure, where the method for identifying a user with a brush amount described in the present embodiment includes:

101. and acquiring a feature sample set of each reference object in the plurality of reference objects to obtain a plurality of feature sample sets.

The multiple reference objects refer to users or user accounts appearing in a preset time period. The preset time period may be, for example, the last month, or the last 3 months, etc., and is not limited herein.

In the embodiment of the application, the use data of each reference object using the electronic device in the multiple reference objects can be obtained to obtain the multiple use data, and then, the feature extraction is performed on the use data of each reference object to obtain the feature sample set corresponding to each reference object, so that the multiple feature sample sets corresponding to the multiple reference objects can be obtained. Wherein each feature sample set comprises a plurality of feature samples of a plurality of dimensions.

Wherein the usage data of the electronic device used by the reference object may include at least one of: the reference object uses the temporal distribution of all applications in the electronic device, the reference object uses application data of a specific application, the application data may comprise at least one of: a frequency of using the specific application, a length of time of using the specific application each time, a time period of using the specific application each time, a geographic location of using the specific application each time, an IP address of using the specific application each time, etc., a specific operational behavior in the electronic device, wherein the specific operational behavior may include at least one of: the call operation behavior includes, for example, an incoming call record, a short message receiving behavior, a mail receiving behavior, an alarm clock reminding behavior, and the like.

The specific application refers to an application in which the frequency of use of the application by a user exceeds a preset frequency within a preset time period, and may be an application installed on the electronic device, and the specific application may include any one of the following: a browser application, a payment application, a chat application, a mail application, a riding application, a navigation application, a reading application, a video playback application, a music playback application, a learning application, such as an english learning application, a professional exam learning application, a shopping application, a fitness application, a courier application, a work application, and the like, without limitation.

102. And calculating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount recognition model.

The preset algorithm may include at least one of the following: the method comprises the following steps of presetting classification rules, a preset supervision algorithm and a preset unsupervised classification algorithm, wherein the preset classification rules can comprise: for example, one account logs in to a plurality of electronic devices, and one electronic device has a plurality of accounts to log in, so that it can be determined that there is a user with a credit, and for example, a location aggregates a plurality of devices, and a location may be the same IP location or the same geographical location. For another example, when the operation behaviors of the plurality of reference objects have consistency, there are many mechanical operation behaviors or sequence operation behaviors, and whether the plurality of brush users belong to the sample brush amount group can also be determined by using the similarity judgment of the time sequence used by the application. The predetermined supervision algorithm may comprise at least one of: a Neighbor (KNN) algorithm, a Logistic Regression (LR) algorithm, a Support Vector Machine (SVM) algorithm, an eXtreme Gradient Boosting (XGboost) algorithm, or a random forest algorithm. The predetermined unsupervised classification algorithm may include at least one of: a mean-value (Kmeans) algorithm, a Density-Based Clustering of Applications with Noise (DBscan), and an Isolation Forest algorithm.

In the embodiment of the application, the multiple preset algorithms can be fused, specifically, each feature sample set in the multiple feature sample sets can be operated according to the preset algorithms, whether the reference object corresponding to each feature sample set belongs to the brushing amount user or not is determined, so that the multiple reference objects can be divided into multiple positive samples and multiple negative samples, then training and learning are performed according to the multiple positive samples and the multiple negative samples, and a target brushing amount recognition model is obtained.

Optionally, in the step 102, the calculating the plurality of feature sample sets according to a preset algorithm to obtain the target brushing amount recognition model may include the following steps:

21. dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, wherein the first reference objects are reference objects determined to belong to the brush amount users, and the second reference objects are reference objects not determined to belong to the brush amount users;

22. determining a plurality of third reference objects which are determined to be the brush amount users in the plurality of second reference objects according to a preset classification supervision algorithm and a plurality of feature sample sets corresponding to the plurality of second reference objects;

23. and taking a plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects as positive samples, and taking other second reference objects except the plurality of third reference objects in the plurality of second reference objects as negative samples to learn to obtain the target brushing amount identification model.

In the embodiment of the application, which of the multiple reference objects belongs to the user with the brushing amount can be determined according to a preset classification rule, for example, for any reference object, according to time distribution of all applications in the electronic device used by the reference object, a specific application with the reference object use frequency exceeding a preset frequency and a non-specific application with a small use frequency can be determined, if the duration of the reference object using a certain non-specific application is suddenly increased, it can be determined that an abnormality exists, and then it can be determined that the reference object belongs to the user with the brushing amount. Through a preset rule, a plurality of first reference objects which are determined to belong to the brush amount users in the plurality of reference objects and a plurality of second reference objects which are not determined to belong to the brush amount users can be determined.

The brushing amount users in all the reference objects are difficult to identify through a preset rule, and the brushing amount users which cannot be identified by the preset rule may exist in the second reference objects. Therefore, a plurality of third reference objects belonging to the brushing volume user in the plurality of second reference objects can be further determined through a preset supervision algorithm.

Optionally, in the step 21, each of the feature sample sets includes a plurality of feature samples with a plurality of dimensions, and the classification rule includes a plurality of feature rules corresponding to the plurality of dimensions; the dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to the preset classification rules and the plurality of feature sample sets may include:

a1, determining a feature rule corresponding to a feature sample with the highest priority contained in each feature sample set in the plurality of feature sample sets according to a preset priority sequence to obtain a plurality of feature rules, wherein the priority sequence is the preset priority sequence of the plurality of feature samples with the plurality of dimensions, and the plurality of feature rules are in one-to-one correspondence with the plurality of feature sample sets;

a2, determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to each feature rule in the feature rules, and obtaining a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the reference objects.

In the embodiment of the application, corresponding feature rules can be preset for a plurality of feature samples of a plurality of dimensions to obtain a plurality of feature rules, each dimension corresponds to one feature rule, and the priority order of the plurality of feature samples of the plurality of dimensions is preset. Therefore, the feature rule corresponding to the feature sample with the highest priority contained in each feature sample set in the plurality of feature sample sets can be determined according to the preset priority sequence to obtain a plurality of feature rules, and then whether the reference object to which the corresponding feature sample set belongs to the brush amount user or not is determined according to each feature rule in the plurality of feature rules to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.

Optionally, in step 21, the classification rule includes a geographic location rule or an application usage rule; the dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to the preset classification rules and the plurality of feature sample sets may include:

a3, determining whether the reference object to which the corresponding feature sample set belongs to the brush measurement user according to the geographic position rule and the position feature samples contained in each feature sample set in the plurality of feature sample sets, and obtaining a plurality of first reference objects belonging to the brush measurement user and a plurality of second reference objects not belonging to the brush measurement user in the plurality of reference objects.

Alternatively, the first and second electrodes may be,

and A4, determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to the application use rule and the application use feature sample in each feature sample set in the plurality of feature sample sets, and obtaining a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.

The feature rules may be set in advance for some feature samples in the feature sample sets, specifically, the geographical location rules may be set for the geographical location features, and if the feature sample set corresponding to any reference object includes the geographical location features, it may be determined whether the reference object belongs to the measurement user according to the geographical location rules and the geographical location features.

Optionally, the application usage rule may also be set for the application usage feature, so that the application usage rule may be set according to the application usage feature, and if the feature sample set corresponding to any reference object includes the application usage feature, it may be determined whether the reference object belongs to the user with a brush amount according to the application usage rule and the application usage feature.

Thus, a plurality of first reference objects belonging to the brush amount user among the plurality of reference objects and a plurality of second reference objects belonging to the brush amount user are not determined according to the above-described feature rule.

24. clustering the plurality of reference objects according to a preset unsupervised classification algorithm and the plurality of feature sample sets to obtain a plurality of sample brushing amount groups, wherein each sample brushing amount group comprises a plurality of reference objects in the same cluster;

25. and training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brushing amount group in the plurality of sample brushing amount groups to obtain the target brushing amount identification model.

The method comprises the steps of clustering a plurality of characteristic sample sets through a preset unsupervised classification algorithm, specifically, clustering the characteristic sample sets with similar characteristic samples, and attributing a plurality of reference objects corresponding to the plurality of characteristic sample sets belonging to the same class to a sample brushing amount group, so that a plurality of sample brushing amount groups are obtained. Further, training and learning a plurality of feature sample sets of a plurality of reference objects of each sample brush volume group in the plurality of sample brush volume groups to obtain a target brush volume identification model, wherein each sample brush volume group corresponds to one group feature set, and the group feature set comprises a plurality of features which are the same as the sample brush volume group.

103. And performing feature extraction on the target object to obtain a target feature set.

In the embodiment of the application, the target object refers to a new user or a new user account. When a new target object is found, target use data of the target object using the electronic device can be acquired, and then feature extraction is performed on the target use data to obtain a target feature set.

104. And inputting the target feature set into the target brushing amount identification model for operation to obtain an identification result of whether the target object is a brushing amount user.

The target feature set is input into the target brush amount identification model for operation, so that an identification result of whether the target object belongs to a brush amount user or not can be obtained, and in addition, whether the target object belongs to a single brush amount user or a group brush amount user in a certain sample brush amount group can be determined. The single-brushing-amount user refers to that the behavior of brushing amount of the target object belongs to personal behavior; the group brushing amount user means that the brushing amount behavior of the target object belongs to the group brushing amount behavior.

Optionally, in the step 104, inputting the target feature set to the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user, which may include the following steps:

41. inputting the target feature set of the target object into the target brushing amount recognition model to obtain a probability value of the target object belonging to a brushing amount user;

42. and if the probability value exceeds a preset probability value, determining that the target object is a volume brushing user.

In order to determine whether the target object belongs to a single-reading user, the target feature set can be input into a target reading identification model, the probability value that the target object belongs to the reading user is determined according to the target reading identification model, if the probability value exceeds a preset probability value, the target object is determined to be the reading user, and if the probability value does not exceed the preset probability value, an identification result that the target object does not belong to the reading user is obtained.

Optionally, whether the target object is a user with a brush amount may be determined according to the classification rule or the classification supervision algorithm, specifically, whether the target object belongs to the user with a brush amount may be determined by a preset classification rule, and if it is not determined that the target object belongs to the user with a brush amount, whether the target object belongs to the user with a brush amount may be further determined by the classification supervision algorithm.

43. inputting the target feature set into the target brush amount identification model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount identification model, wherein the association degrees are in one-to-one correspondence with the sample brush amount groups;

44. and if the maximum association degree in the association degrees exceeds a preset association degree, determining that the target object belongs to a brush amount user in a target sample brush amount group corresponding to the maximum association degree.

Specifically, the association degree between the target object and each sample brush volume group can be determined according to the target feature set and the group feature set corresponding to each sample brush volume group in the plurality of sample brush volume groups in the target brush volume identification model, so that a plurality of association degrees are obtained. And then determining the maximum relevance degree in the relevance degrees, and if the maximum relevance degree exceeds the preset relevance degree, determining that the target object belongs to the brush amount user in the target sample brush amount group corresponding to the maximum relevance degree.

Optionally, in the step 43, the inputting the target feature set into the target brushing amount recognition model to obtain a plurality of association degrees between the target object and a plurality of sample brushing amount groups in the target brushing amount recognition model may include the following steps:

b1, determining the number of similar feature pairs of the target feature set and the similar feature pairs contained in the group feature set corresponding to each sample brush amount population in the plurality of sample brush amount populations in the target brush amount identification model respectively to obtain a plurality of similar feature pair numbers;

and B2, determining the relevance degree corresponding to each similar feature pair number in the plurality of similar feature pair numbers according to the corresponding relation between the preset similar feature pair number and the relevance degree, and obtaining a plurality of relevance degrees.

The number of similar feature pairs included in the group feature set corresponding to the target feature set and each sample brush volume population in the plurality of sample brush volume populations can be determined, wherein the similar feature pairs can include the same features. For example, if the first group feature set of the target feature set corresponding to the first sample brush size group includes 5 similar feature pairs, the number of the similar feature pairs of the target feature set corresponding to the first sample brush size group is 5. Thus, a number of pairs of similar features corresponding between the target feature set and a plurality of sample brush size populations, which correspond one-to-one to the number of pairs of similar features, may be determined.

In the embodiment of the present application, a corresponding relationship between the number of similar feature pairs and the degree of association may also be preset, so that the degree of association corresponding to each number of similar feature pairs in the number of similar feature pairs may be determined according to the corresponding relationship, and a plurality of degrees of association may be obtained.

Optionally, in the step B1, determining the number of similar feature pairs included in the group feature set corresponding to each sample brush amount population in the plurality of sample brush amount populations in the target brush amount recognition model respectively to obtain a plurality of similar feature pair numbers may include the following steps:

b11, matching the plurality of target features in the target feature set with a plurality of population features in a population feature set corresponding to each sample brush amount population in a plurality of sample brush amount populations in the target brush amount identification model respectively to obtain a plurality of matching values;

and B12, determining the target features and the population features corresponding to the target matching values exceeding the preset matching value in the multiple matching values as similar feature pairs, and counting the number of the similar feature pairs contained in the population feature set corresponding to each sample brush amount population in the multiple sample brush amount populations in the target brush amount recognition model respectively by the target feature set to obtain the number of the multiple similar feature pairs.

Specifically, for any one of the target features in the target feature set, the target feature may be respectively matched with a plurality of population features in the population feature set corresponding to each sample brush amount population in the sample brush amount populations, and each matched target feature and population feature corresponds to one matching value, so that a plurality of matching values may be obtained. Then, the target features and the population features of which the matching values exceed the preset matching values are determined to be similar feature pairs, so that the number of the similar feature pairs included in the population feature set corresponding to each sample brush amount population in the target feature set and the plurality of sample brush amount populations can be determined, and further, the number of the similar feature pairs included in the population feature set corresponding to each sample brush amount population in the target brush amount identification model and the target feature set respectively can be counted to obtain the number of the plurality of similar feature pairs.

It can be seen that, in the method for identifying a brush amount user described in the embodiment of the present application, a plurality of feature sample sets are obtained by obtaining a feature sample set of each of a plurality of reference objects, a target brush amount identification model is obtained by performing operation on the plurality of feature sample sets according to a preset algorithm, a target feature set is obtained by performing feature extraction on a target object, and the target feature set is input to the target brush amount identification model for performing operation to obtain an identification result of whether the target object is a brush amount user.

In accordance with the above, please refer to fig. 2, where fig. 2 is a schematic flowchart of another method for identifying a user with a brush amount according to an embodiment of the present disclosure, and the method for identifying a user with a brush amount described in the embodiment is applied to an electronic device, and the method may include the following steps:

201. and acquiring a feature sample set of each reference object in the plurality of reference objects to obtain a plurality of feature sample sets.

202. And dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, wherein the first reference objects are reference objects determined to belong to the brush amount users, and the second reference objects are reference objects not determined to belong to the brush amount users.

203. And determining a plurality of third reference objects which are determined to be the brush amount users in the plurality of second reference objects according to a preset classification supervision algorithm and a plurality of feature sample sets corresponding to the plurality of second reference objects.

204. And taking a plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects as positive samples, and taking other second reference objects except the plurality of third reference objects in the plurality of second reference objects as negative samples to learn to obtain the target brushing amount identification model.

205. And performing feature extraction on the target object to obtain a target feature set.

206. And inputting the target feature set of the target object into the target brushing amount recognition model to obtain the probability value of the target object belonging to the brushing amount user.

207. And if the probability value exceeds a preset probability value, determining that the target object is a volume brushing user.

The specific implementation process of the steps 201-206 can refer to the corresponding description in the method shown in fig. 1B, and will not be described herein again.

It can be seen that, in the method for identifying a brush amount user described in this embodiment of the present application, a plurality of feature sample sets are obtained by obtaining a feature sample set of each reference object in a plurality of reference objects, the plurality of reference objects are divided into a plurality of first reference objects and a plurality of second reference objects according to a preset classification rule and the plurality of feature sample sets, a plurality of third reference objects determined as a brush amount user in the plurality of second reference objects are determined according to a preset classification supervision algorithm and the plurality of feature sample sets corresponding to the plurality of second reference objects, the plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects are used as positive samples, other second reference objects except the plurality of third reference objects in the plurality of second reference objects are used as negative samples, and a target brush amount identification model is obtained by learning, the method comprises the steps of extracting features of a target object to obtain a target feature set, inputting the target feature set of the target object into a target brushing amount recognition model to obtain a probability value that the target object belongs to a brushing amount user, and determining that the target object is the brushing amount user if the probability value exceeds a preset probability value.

In accordance with the above, please refer to fig. 3, which is a schematic flow chart of another method for identifying a user with a brush amount according to an embodiment of the present application, where the method for identifying a user with a brush amount described in the embodiment includes the following steps:

301. and acquiring a feature sample set of each reference object in the plurality of reference objects to obtain a plurality of feature sample sets.

302. Clustering the plurality of reference objects according to a preset unsupervised classification algorithm and the plurality of feature sample sets to obtain a plurality of sample brushing amount groups, wherein each sample brushing amount group comprises a plurality of reference objects in the same cluster.

303. And training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brushing amount group in the plurality of sample brushing amount groups to obtain the target brushing amount identification model.

304. And performing feature extraction on the target object to obtain a target feature set.

305. And inputting the target feature set into the target brush amount identification model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount identification model, wherein the association degrees are in one-to-one correspondence with the sample brush amount groups.

306. And if the maximum association degree in the association degrees exceeds a preset association degree, determining that the target object belongs to a brush amount user in a target sample brush amount group corresponding to the maximum association degree.

The specific implementation process of the steps 301-306 can refer to the corresponding description in the method shown in fig. 1B, and will not be described herein again.

According to the method for identifying the brush amount user, a plurality of characteristic sample sets are obtained by obtaining the characteristic sample set of each reference object in a plurality of reference objects, and the plurality of reference objects are clustered according to a preset unsupervised classification algorithm and the plurality of characteristic sample sets to obtain a plurality of sample brush amount groups; the method comprises the steps of training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brush amount group in a plurality of sample brush amount groups to obtain a target brush amount identification model, extracting characteristics of a target object to obtain a target characteristic set, inputting the target characteristic set into the target brush amount identification model to obtain a plurality of association degrees between the target object and the plurality of sample brush amount groups in the target brush amount identification model, and determining that the target object belongs to a brush amount user in the target sample brush amount group corresponding to the maximum association degree if the maximum association degree in the association degrees exceeds a preset association degree.

In accordance with the above, please refer to fig. 4, in which fig. 4 is an electronic device 400 according to an embodiment of the present disclosure, including: a processor 410, a memory 420, a communication interface 430, and one or more programs 421, the one or more programs 421 stored in the memory 420 and configured to be executed by the processor 410, the programs comprising instructions for:

In one possible example, in terms of the operation on the feature sample sets according to the preset algorithm to obtain the target brushing amount recognition model, the program 421 includes instructions for performing the following steps:

dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, wherein the first reference objects are reference objects determined to belong to the brush amount users, and the second reference objects are reference objects not determined to belong to the brush amount users;

determining a plurality of third reference objects which are determined to be the brush amount users in the plurality of second reference objects according to a preset classification supervision algorithm and a plurality of feature sample sets corresponding to the plurality of second reference objects;

and taking a plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects as positive samples, and taking other second reference objects except the plurality of third reference objects in the plurality of second reference objects as negative samples to learn to obtain the target brushing amount identification model.

In one possible example, each of the plurality of feature sample sets contains a plurality of feature samples in a plurality of dimensions, and the classification rule includes a plurality of feature rules corresponding to the plurality of dimensions; in the aspect of dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to the preset classification rules and the plurality of feature sample sets, the program 421 includes instructions for:

determining a feature rule corresponding to a feature sample with the highest priority contained in each feature sample set in the plurality of feature sample sets according to a preset priority sequence to obtain a plurality of feature rules, wherein the priority sequence is the preset priority sequence of the plurality of feature samples with the plurality of dimensions, and the plurality of feature rules are in one-to-one correspondence with the plurality of feature sample sets;

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to each feature rule in the plurality of feature rules to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.

In one possible example, the classification rules include geographical location rules or application usage rules, and in terms of dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, the program 421 includes instructions for performing the steps of:

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to the geographic position rule and the position feature sample contained in each feature sample set in the plurality of feature sample sets, so as to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.

Alternatively, the first and second electrodes may be,

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to the application use rule and the application use feature sample in each feature sample set in the plurality of feature sample sets, and obtaining a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.

In one possible example, in terms of the input of the target feature set to the target brushing amount recognition model for operation to obtain the recognition result of whether the target object is a brushing amount user, the program 421 includes instructions for performing the following steps:

inputting the target feature set of the target object into the target brushing amount recognition model to obtain a probability value of the target object belonging to a brushing amount user;

and if the probability value exceeds a preset probability value, determining that the target object is a volume brushing user.

clustering the plurality of reference objects according to a preset unsupervised classification algorithm and the plurality of feature sample sets to obtain a plurality of sample brushing amount groups, wherein each sample brushing amount group comprises a plurality of reference objects in the same cluster;

and training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brushing amount group in the plurality of sample brushing amount groups to obtain the target brushing amount identification model.

inputting the target feature set into the target brush amount identification model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount identification model, wherein the association degrees are in one-to-one correspondence with the sample brush amount groups;

and if the maximum association degree in the association degrees exceeds a preset association degree, determining that the target object belongs to a brush amount user in a target sample brush amount group corresponding to the maximum association degree.

In one possible example, in the inputting the target feature set into the target brush amount recognition model, a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount recognition model are obtained, the program 421 includes instructions for performing the following steps:

determining the number of similar feature pairs of the group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount identification model, and obtaining a plurality of similar feature pairs;

and determining the relevance degree corresponding to each similar feature pair number in the plurality of similar feature pair numbers according to the preset corresponding relation between the similar feature pair numbers and the relevance degrees to obtain a plurality of relevance degrees.

In one possible example, in the aspect of determining the number of similar feature pairs included in the group feature set respectively corresponding to each sample brush amount population in the plurality of sample brush amount populations in the target brush amount recognition model to obtain a plurality of similar feature pair numbers, the program 421 further includes instructions for performing the following steps:

matching the plurality of target features in the target feature set with a plurality of group features in a group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount identification model respectively to obtain a plurality of matching values;

and determining the target features and the group features corresponding to the target matching values exceeding the preset matching value in the matching values as similar feature pairs, and counting the number of the similar feature pairs contained in the group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount recognition model respectively by the target feature set to obtain the number of the similar feature pairs.

Referring to fig. 5, fig. 5 is a schematic structural diagram of a device for identifying a user by brushing amount according to the present embodiment. The device for identifying the user of the brush amount is applied to the electronic equipment shown in fig. 1A, and comprises an acquisition unit 501, an arithmetic unit 502 and an extraction unit 503, wherein,

the obtaining unit 501 is configured to obtain a feature sample set of each of a plurality of reference objects, so as to obtain a plurality of feature sample sets;

the operation unit 502 is configured to perform operation on the plurality of feature sample sets according to a preset algorithm to obtain a target brushing amount identification model;

the extracting unit 503 is configured to perform feature extraction on the target object to obtain a target feature set;

the operation unit 502 is further configured to input the target feature set to the target brushing amount identification model for operation, so as to obtain an identification result of whether the target object is a brushing amount user.

Optionally, in terms of obtaining the target brushing amount recognition model by performing an operation on the plurality of feature sample sets according to a preset algorithm, the operation unit is specifically configured to:

Optionally, each feature sample set in the plurality of feature sample sets includes a plurality of feature samples of a plurality of dimensions, and the classification rule includes a plurality of feature rules corresponding to the plurality of dimensions; in the aspect that the plurality of reference objects are divided into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, the operation unit is specifically configured to:

Optionally, the classification rule includes a geographical location rule or an application usage rule, and in terms of dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to a preset classification rule and the plurality of feature sample sets, the operation unit is specifically configured to:

Alternatively, the first and second electrodes may be,

Optionally, in terms of inputting the target feature set to the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user, the operation unit 502 is specifically configured to:

Optionally, in terms of obtaining the target brushing amount recognition model by performing an operation on the plurality of feature sample sets according to a preset algorithm, the operation unit 502 is specifically configured to:

Optionally, in the aspect that the target feature set is input into the target brush amount recognition model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount recognition model, the operation unit is specifically configured to:

Optionally, in the aspect of determining the number of similar feature pairs included in the group feature set corresponding to each sample brush size population in the plurality of sample brush size populations in the target brush size recognition model respectively to obtain a plurality of similar feature pairs, the operation unit 502 is specifically configured to:

It can be seen that, in the brushing amount user identification apparatus described in the embodiment of the present application, a plurality of feature sample sets are obtained by obtaining a feature sample set of each of a plurality of reference objects, a target brushing amount identification model is obtained by performing operation on the plurality of feature sample sets according to a preset algorithm, a target feature set is obtained by performing feature extraction on a target object, and the target feature set is input to the target brushing amount identification model for performing operation to obtain an identification result of whether the target object is a brushing amount user.

It can be understood that the functions of each program module of the brushing amount user identification apparatus in this embodiment may be specifically implemented according to the method in the foregoing method embodiment, and the specific implementation process may refer to the related description of the foregoing method embodiment, which is not described herein again.

Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the brush user identification methods as described in the above method embodiments.

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

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

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

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.

The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a read-only memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and the like.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash disk, ROM, RAM, magnetic or optical disk, and the like.

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

Claims

A method for identifying a user of a brushstroke, the method comprising:

obtaining a characteristic sample set of each reference object in a plurality of reference objects to obtain a plurality of characteristic sample sets;

calculating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount identification model;

carrying out feature extraction on the target object to obtain a target feature set;

and inputting the target feature set into the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user.
The method according to claim 1, wherein the operating the plurality of feature sample sets according to a preset algorithm to obtain a target brushing amount recognition model comprises:

dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, wherein the first reference objects are reference objects determined to belong to the brush amount users, and the second reference objects are reference objects not determined to belong to the brush amount users;

determining a plurality of third reference objects which are determined to be the brush amount users in the plurality of second reference objects according to a preset classification supervision algorithm and a plurality of feature sample sets corresponding to the plurality of second reference objects;

and taking a plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects as positive samples, and taking other second reference objects except the plurality of third reference objects in the plurality of second reference objects as negative samples to learn to obtain the target brushing amount identification model.
The method of claim 2, wherein each feature sample set of the plurality of feature sample sets includes a plurality of feature samples for a plurality of dimensions, and wherein the classification rule comprises a plurality of feature rules for the plurality of dimensions; the dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets includes:

determining a feature rule corresponding to a feature sample with the highest priority contained in each feature sample set in the plurality of feature sample sets according to a preset priority sequence to obtain a plurality of feature rules, wherein the priority sequence is the preset priority sequence of the plurality of feature samples with the plurality of dimensions, and the plurality of feature rules are in one-to-one correspondence with the plurality of feature sample sets;

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to each feature rule in the plurality of feature rules to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.
The method of claim 2, wherein the classification rule comprises a geo-location rule or an application usage rule, and the dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to a preset classification rule and the plurality of feature sample sets comprises:

determining whether a reference object to which a corresponding feature sample set belongs to a brush amount user according to the geographic position rule and a position feature sample contained in each feature sample set in the plurality of feature sample sets to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects;

alternatively, the first and second electrodes may be,

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to the application use rule and the application use feature sample in each feature sample set in the plurality of feature sample sets, and obtaining a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.
The method according to any one of claims 2 to 4, wherein the inputting the target feature set into the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user comprises:

inputting the target feature set of the target object into the target brushing amount recognition model to obtain a probability value of the target object belonging to a brushing amount user;

and if the probability value exceeds a preset probability value, determining that the target object is a volume brushing user.
The method according to claim 1, wherein the operating the plurality of feature sample sets according to a preset algorithm to obtain a target brushing amount recognition model comprises:

clustering the plurality of reference objects according to a preset unsupervised classification algorithm and the plurality of feature sample sets to obtain a plurality of sample brushing amount groups, wherein each sample brushing amount group comprises the reference objects of the same class;

and training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brushing amount group in the plurality of sample brushing amount groups to obtain the target brushing amount identification model.
The method according to claim 6, wherein the inputting the target feature set into the target brushing amount recognition model for operation to obtain a recognition result of whether the target object is a brushing amount user comprises:

inputting the target feature set into the target brush amount identification model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount identification model, wherein the association degrees are in one-to-one correspondence with the sample brush amount groups;

and if the maximum association degree in the association degrees exceeds a preset association degree, determining that the target object belongs to a brush amount user in a target sample brush amount group corresponding to the maximum association degree.
The method of claim 7, wherein inputting the target feature set into the target brush amount recognition model to obtain a plurality of degrees of association between the target object and a plurality of sample brush amount populations in the target brush amount recognition model comprises:

determining the number of similar feature pairs of the group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount identification model, and obtaining a plurality of similar feature pairs;

and determining the relevance degree corresponding to each similar feature pair number in the plurality of similar feature pair numbers according to the preset corresponding relation between the similar feature pair numbers and the relevance degrees to obtain a plurality of relevance degrees.
The method according to claim 8, wherein the determining the number of similar feature pairs of the group feature set respectively corresponding to each sample brush amount population in the plurality of sample brush amount populations in the target brush amount recognition model to obtain a plurality of similar feature pair numbers comprises:

matching the plurality of target features in the target feature set with a plurality of group features in a group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount identification model respectively to obtain a plurality of matching values;

and determining the target features and the group features corresponding to the target matching values exceeding the preset matching value in the matching values as similar feature pairs, and counting the number of the similar feature pairs contained in the group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount recognition model respectively by the target feature set to obtain the number of the similar feature pairs.
A device for identifying a user of a brushamount, the device comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a characteristic sample set of each reference object in a plurality of reference objects to obtain a plurality of characteristic sample sets;

the operation unit is used for operating the plurality of characteristic sample sets according to a preset algorithm to obtain a target brushing amount identification model;

the extraction unit is used for extracting the features of the target object to obtain a target feature set;

the operation unit is further configured to input the target feature set to the target brushing amount identification model for operation, so as to obtain an identification result of whether the target object is a brushing amount user.
The apparatus according to claim 10, wherein in terms of obtaining the target brushing amount recognition model by performing the operation on the plurality of feature sample sets according to a preset algorithm, the operation unit is specifically configured to:

dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, wherein the first reference objects are reference objects determined to belong to the brush amount users, and the second reference objects are reference objects not determined to belong to the brush amount users;

determining a plurality of third reference objects which are determined to be the brush amount users in the plurality of second reference objects according to a preset classification supervision algorithm and a plurality of feature sample sets corresponding to the plurality of second reference objects;

and taking a plurality of feature sample sets corresponding to the plurality of first reference objects and the plurality of third reference objects as positive samples, and taking other second reference objects except the plurality of third reference objects in the plurality of second reference objects as negative samples to learn to obtain the target brushing amount identification model.
The apparatus of claim 11, wherein each feature sample set of the plurality of feature sample sets includes a plurality of feature samples for a plurality of dimensions, and wherein the classification rule comprises a plurality of feature rules for the plurality of dimensions; in the aspect that the plurality of reference objects are divided into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets, the operation unit is specifically configured to:

determining a feature rule corresponding to a feature sample with the highest priority contained in each feature sample set in the plurality of feature sample sets according to a preset priority sequence to obtain a plurality of feature rules, wherein the priority sequence is the preset priority sequence of the plurality of feature samples with the plurality of dimensions, and the plurality of feature rules are in one-to-one correspondence with the plurality of feature sample sets;

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to each feature rule in the plurality of feature rules to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.
The apparatus according to claim 11, wherein the classification rules comprise geographical location rules or application usage rules, and wherein the arithmetic unit is specifically configured to, in terms of dividing the plurality of reference objects into a plurality of first reference objects and a plurality of second reference objects according to preset classification rules and the plurality of feature sample sets:

determining whether a reference object to which a corresponding feature sample set belongs to a brush amount user according to the geographic position rule and a position feature sample contained in each feature sample set in the plurality of feature sample sets to obtain a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects;

alternatively, the first and second electrodes may be,

and determining whether the reference object to which the corresponding feature sample set belongs to the brush amount user according to the application use rule and the application use feature sample in each feature sample set in the plurality of feature sample sets, and obtaining a plurality of first reference objects belonging to the brush amount user and a plurality of second reference objects not belonging to the brush amount user in the plurality of reference objects.
The apparatus according to any one of claims 11 to 13, wherein in the aspect that the target feature set is input to the target brushing amount recognition model for performing the operation to obtain the recognition result of whether the target object is a brushing amount user, the operation unit is specifically configured to:

inputting the target feature set of the target object into the target brushing amount recognition model to obtain a probability value of the target object belonging to a brushing amount user;

and if the probability value exceeds a preset probability value, determining that the target object is a volume brushing user.
The apparatus according to claim 10, wherein in terms of performing an operation on the plurality of feature sample sets according to a preset algorithm to obtain a target brushing amount recognition model, the operation unit is specifically configured to:

clustering the plurality of reference objects according to a preset unsupervised classification algorithm and the plurality of feature sample sets to obtain a plurality of sample brushing amount groups, wherein each sample brushing amount group comprises a plurality of reference objects in the same cluster;

and training and learning a plurality of characteristic sample sets of a plurality of reference objects of each sample brushing amount group in the plurality of sample brushing amount groups to obtain the target brushing amount identification model.
The apparatus according to claim 15, wherein in terms of the target feature set being input to the target brushing amount recognition model for performing the operation to obtain the recognition result of whether the target object is a brushing amount user, the operation unit is specifically configured to:

inputting the target feature set into the target brush amount identification model to obtain a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount identification model, wherein the association degrees are in one-to-one correspondence with the sample brush amount groups;

and if the maximum association degree in the association degrees exceeds a preset association degree, determining that the target object belongs to a brush amount user in a target sample brush amount group corresponding to the maximum association degree.
The apparatus according to claim 16, wherein in the inputting of the target feature set into the target brush amount recognition model, a plurality of association degrees between the target object and a plurality of sample brush amount groups in the target brush amount recognition model are obtained, and the operation unit is specifically configured to:

determining the number of similar feature pairs of the group feature set corresponding to each sample brush amount group in a plurality of sample brush amount groups in the target brush amount identification model, and obtaining a plurality of similar feature pairs;

and determining the relevance degree corresponding to each similar feature pair number in the plurality of similar feature pair numbers according to the preset corresponding relation between the similar feature pair numbers and the relevance degrees to obtain a plurality of relevance degrees.
An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-9.
A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-9.
A computer program product, characterized in that the computer program product comprises a computer-readable storage medium having stored thereon a computer program for causing a computer to perform the method according to any one of claims 1-9.