Object classification method and apparatus, device, medium, and program product

Abstract

Embodiments of the present disclosure relate to an object classification method and apparatus, a device, a medium, and a program product. The method comprises acquiring object data associated with an object of which information delivery does not exceed a predetermined duration, wherein the object data indicates at least one of the following: a profile of the object, interaction information of the object, and an attribute of information delivered by the object. The method further comprises on the basis of the object data, determining a category to which the object belongs, the category being used for determining a processing strategy associated with the object. In the embodiments of the present disclosure, a category of an object that delivers information can be determined, and a corresponding processing strategy can be determined on the basis of the category. In this way, associated appropriate resources or strategies can be provided on the basis of the category of the object, thereby improving the efficiency and experience of information delivery of objects.

Description

[0001]Method, device, equipment, medium and program product technology field The present disclosure relates to the field of computers, and more particularly, to a method, device, equipment, medium and program product for object classification. Background art With the popularity of the Internet and the increasing dependence of people on the Internet, the data on the Internet is increasing, which gradually forms a massive data resource, and it becomes more and more important to process and classify these data. With the increase of data resources, various platforms begin to appear, which can provide various data resources to different users in different categories. The platform usually provides services to push text, video, audio and other content to the user, and can also push product, article, link, plug-in and other information. Invention content Embodiments of the present disclosure provide a method, device, equipment, medium and program product for object classification. According to the disclosed first aspect, a method for object classification is provided. The method comprises obtaining object data associated with an object whose information has not exceeded a predetermined time length, wherein the object data indicates at least one of the following: profile of the object, interaction information of the object, and property of the information launched by the object. The method further comprises determining a category to which the object belongs based on the object data, the category being used to determine a processing strategy associated with the object. In the second aspect disclosed, a device for object classification is provided. The device comprises an obtaining module configured to obtain object data associated with an object whose information has not exceeded a predetermined time length, wherein the object data indicates at least one of the following: profile of the object, interaction information of the object, and property of the information launched by the object. The device further comprises a classification module configured to determine a category to which the object belongs based on the object data, the category being used to determine a processing strategy associated with the object. In the third aspect of the present disclosure, an electronic device is provided. The electronic device comprises a processor and a storage coupled with the processor, the storage having instructions stored therein, which, when executed by the processor, cause the electronic device to perform the method according to the first aspect. In the fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to the first aspect.In a fifth aspect of the disclosure, a computer program product is provided that includes computer-executable instructions that, when executed, cause a computer to perform the method according to the first aspect. The summary is provided to introduce a selection of concepts in a simplified form, which are further described in the detailed description below. The summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. The above and other features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements, in which: FIG. 1 shows a diagram of an example environment in which various embodiments of the present disclosure can be implemented; FIG. 2 shows a flowchart of a method for object classification according to some embodiments of the present disclosure; FIG. 3A shows a diagram of a scenario of determining a class to which an object belongs according to certain embodiments of the present disclosure; FIG. 3B shows a diagram of an architecture of a classification model according to certain embodiments of the present disclosure; FIG. 4 shows a diagram of a method for object classification according to certain embodiments of the present disclosure; FIG. 5 shows a diagram of a method of evaluating a classification model according to certain embodiments of the present disclosure; FIG. 6 shows a block diagram of an apparatus for object classification according to certain embodiments of the present disclosure; and FIG. 7 shows a block diagram of an electronic device according to certain embodiments of the present disclosure. Like reference numerals refer to like elements throughout the various drawings. It can be appreciated that the data involved in the present technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws and regulations and relevant regulations. In response to receiving a request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation to be performed by the user will need to acquire and use the user information. Thus, the user can autonomously choose whether to provide the user information to the software or hardware, such as an electronic device, an application program, a server, or a storage medium, etc. that performs the technical solution of the present disclosure according to the prompt information.The user interaction operation or the interaction between the user and the content, and the data related to the user operation (including but not limited to data for analysis, stored data, displayed data, etc.) in the present disclosure are recorded, collected or stored with authorization of the user or through full authorization of all parties, and the collection, use and processing of the related data need to comply with the relevant laws, regulations and standards of the country and region, and provide corresponding operation entrances for the user to select authorization or refusal. In the technical scheme of the embodiment of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of the information related to the user comply with the relevant laws and regulations and do not violate public order and good customs. The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, on the contrary, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not used to limit the protection scope of the present disclosure. In the description of the embodiments of the present disclosure, the term “comprises” and similar terms should be interpreted as open-ended inclusion, that is, “including but not limited to”. The term “based on” should be understood as “at least partially based on”. The term “one embodiment” or “the embodiment” should be understood as “at least one embodiment”. The terms “first”, “second”, etc. can refer to different or same objects, unless otherwise specified. The following can also include other explicit and implicit definitions. As mentioned earlier, some users can put information, and these information can be pushed to specific or non-specific people. In order to distinguish and describe, in the embodiments of the present disclosure, the entity or user who puts information is called the object of putting information, which is referred to as the object. In the related art, different resources and strategies can be provided for different objects based on the behavior of the previous putting information of the object. In some cases, the object has less experience in putting information, so there is a lack of relevant information about the behavior of the previous putting information of the object, and in this case, it is difficult to determine the processing strategy related to the object. Therefore, the embodiments of the present disclosure provide a method for object classification.In the method, for an object whose information placement does not exceed a predetermined time length, object data associated with the object can be obtained, the object data can include at least one of a profile of the object, interaction information of the object, or a property of information placed by the object, on the basis of the object data, a category to which the object belongs can be determined, so that the information placed by the object can be processed on the basis of the category of the object. Through the embodiments of the present disclosure, in the case that an object has little experience in placing information or has no experience in placing information, the object can also be accurately classified, so that a processing strategy associated with the object can be determined on the basis of the classification, for example, how to allocate resources to the object. In this way, objects with little experience can also obtain appropriate resources and processing, so that the experience of these objects can be improved. The processing of the object can no longer be limited to objects with rich experience, and has higher flexibility and adaptability. FIG. 1 shows a schematic diagram of an example environment 100 in which a plurality of embodiments of the present disclosure can be implemented. As shown in FIG. 1, the example environment 100 can include an object 101 placing information, a terminal device 102, a cloud server 103, a terminal device 104, and a user 105. In embodiments of the present disclosure, the terminal device can be any device capable of sending and receiving information, which can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a smart television, a personal digital assistant (PDA), a smart printer, a smart home appliance, a vehicle terminal, a wearable device (smart watch, smart bracelet, smart glasses, etc.), a virtual reality (VR) device, an augmented reality (AR) device, etc., and the present application embodiments do not limit this. The terminal device. The cloud server 103 can be a computing system, a single server, a distributed server, etc., and the cloud server 103 can be a server providing information placement and push services, and can be used to provide services for receiving and pushing content and information. The terminal device 102 and the terminal device 104 can obtain services from the cloud server.In embodiments of the present disclosure, the object 101 can post information through the terminal device 102, the cloud server 103 can receive the information posted by the object from the terminal device 102, and push it to the terminal device 104, so that the user 105 can obtain the information posted by the terminal device 102 through the terminal device 104. In some embodiments, the cloud server 103 can obtain object data associated with the object 101, determine the category to which the object 101 belongs on this basis, and then the cloud server can determine the processing strategy associated with the object 101 based on the category, for example, determine the resources allocated for the information posted by the object 101, or determine the communication strategy with the object 101. It should be understood that the architecture and functions in the example environment 100 are described for illustrative purposes only, and do not imply any limitation on the scope of the present disclosure. Embodiments of the present disclosure can also be applied to other environments with different architectures and / or functions. For example, in some embodiments, the environment 100 can also include multiple objects, and in some embodiments, the terminal device 102 and the terminal device 104 can directly communicate. The method according to embodiments of the present disclosure will be described in detail below with reference to FIGS. 2-5. For ease of understanding, the specific data mentioned in the following description are exemplary and do not serve to limit the scope of the present disclosure. It can be understood that the embodiments described below can also include additional actions not shown and / or can omit the actions shown, and the scope of the present disclosure is not limited in this respect. FIG. 2 shows a flowchart of a method 200 for object classification according to some embodiments of the present disclosure. The method 200 can be performed by a device for object classification, which can be, for example, the cloud server 103 in the environment 100, or a system configured in the cloud server, or an independent device or system. The device can be implemented in software and / or hardware. Next, the method 200 will be described illustratively taking the classification device as the execution subject. Referring to FIG. 2, the method 200 can include block 202 and block 204. In block 202, the classification device obtains object data associated with an object that has not posted information for more than a predetermined time length. Where the object has not posted information for more than a predetermined time length, it can be that the object has posted information for the first time recently, that is, the object can be a user lacking experience in posting information.In some embodiments, the object can be a new user who has not been served information before, e.g., a user who logs in the serving platform for the first time. In some embodiments, the object can be an old user who has not been served information again for another predetermined time length after being served information before, i.e., an old user with less experience of being served information. The object data associated with the object can indicate at least one of a profile of the object, interaction information of the object, and attributes of information served to the object. The profile may, for example, indicate information such as a name, an identification code, etc. of the object. The interaction information may, for example, include interaction information such as acquisition, click, etc. of the object on other information or content served or pushed. The information served to the object can be information newly served to the object, or information previously served to the object. The attributes of the information served to the object may, for example, include a type of the information served, a quantity of the information served, or other attributes of the information, etc. In some embodiments, the classification apparatus can acquire the object data in a process in which the object uses the serving platform, e.g., in a process in which the object logs in the serving platform, acquire data input by the object. In block 204, the classification apparatus determines a category to which the object belongs based on the object data, the category being used to determine a processing strategy associated with the object. In some embodiments, a plurality of categories can be predefined in the classification apparatus, and the classification apparatus can determine the category to which the object belongs. In some embodiments, the classification apparatus can determine a score of the object based on the object data, and determine the category to which the object belongs based on the score. In some embodiments, the classification apparatus can be configured with a predefined classification model, and the classification apparatus can input the object data into the classification model, and determine the category to which the object belongs through the classification model. In some embodiments, the classification apparatus can acquire object data associated with other objects and categories of the other objects, and determine the category to which the object belongs based thereon. In embodiments of the present disclosure, the processing strategy associated with the object can be directly related to the object, or can be related to information served to the object. Exemplarily, the processing strategy associated with the object can be a manner of communication between the object, or a type or quantity of resources allocated for information served to the object. Through the above method 200, the classification apparatus can determine a category of an object with less experience of being served information based on object data associated with the object, and determine a processing strategy for the object with less experience of being served information based thereon.As such, even if the object is less experienced in putting information, a suitable processing strategy can be determined to adapt to the object. As such, the flexibility and adaptability of providing resources and strategies for the information put by the object or the object can be improved, and the experience of the object can also be improved. In some embodiments, the object data associated with the object obtained in the foregoing block 202 includes data indicating the profile of the object, the interaction information of the object, and the attribute of the information put by the object. That is, the object data for determining the category of the object includes multiple data. In some embodiments, the profile of the object can include the credit data of the object, and in some embodiments, the credit data can indicate the number of times of default or the number of times of compliance of the object. In some embodiments, the object data can also indicate the satisfaction of the object to the service provided or the resource allocated. In some embodiments, the attribute of the information put by the object includes both the number of information put by the object after starting to put information and the total amount of information put by the object, which can be based on the score of the quality of the information put by the object, or the number of types of information put by the object. In some embodiments, the classification device can determine the characteristics of the object based on the profile of the object and the interaction information of the object, determine the characteristics of the information put by the object based on the attribute of the information put by the object, and input the characteristics of the object and the characteristics of the information put by the object into a predefined classification model to determine the category to which the object belongs. In some embodiments, the classification device can obtain the webpage created by the object or the webpage containing the information of the object, and identify one or more data related to the object from the webpage through a predefined identification model, such as a natural language processing model, to determine the object data associated with the object. FIG. 3A illustrates a schematic diagram of a scene 300A for determining the category to which the object belongs, taking a classification device as a classification system. In the scene 300A, the classification system 301 can obtain the profile data 302 of the object and the interaction data 303, and generate the characteristics 307 of the object on this basis, wherein the profile data 302 can include the credit data 306 of the object. The classification system 301 can obtain the information quantity data 304 and the total amount data 305 of the information put by the object, and generate the characteristics 308 of the information on this basis.The classification system 301 can input the object features 307 and the information features 308 into a predefined classification model 309, thereby generating the category 310o of the object. In some embodiments, the predefined classification model can be a classification model established based on an extreme Gradient Boosting (XGBoost) algorithm. For example, FIG. 3B shows a schematic diagram of an architecture 300B of an XGBoost classification model in some embodiments of the present disclosure. The classification model 320 included in FIG. 3B can be, for example, the classification model 309 in FIG. 3A, and the object data 330 included in FIG. 3B can include, for example, the profile data 302, the interaction data 303, the information quantity data 304, and the information total amount data 305 in FIG. 3A. o As shown in FIG. 3B, after receiving the object data 330, the classification model 320 can establish a decision tree 321 based on a predefined rule. Through the decision tree 321, a score fi(x) for classification can be obtained. Then, the classification model 320 can determine a residual error of the decision tree 321, and construct a new decision tree 322 based on the residual error and the object data 330. In this way, until the number of decision trees reaches a predefined number threshold, i.e., a decision tree 323 is constructed, or the value of the residual error no longer decreases. The classification model 320 can obtain a score for classification from each decision tree It should be understood that FIGS. 3A and 3B are merely examples of embodiments of the present disclosure and should not be taken as a limitation on the methods provided by the present disclosure. In some embodiments, the classification system can obtain more or less data, and in some embodiments, the classification model can also be other types of classification models. In some embodiments, the classification device can also input data indicative of the profile of the object, the interaction information of the object, the number of information posted by the object, and the total number of information posted by the object into a predefined classification model, respectively, which form features, respectively, on the basis of which the classification model determines the category to which the object belongs. In some embodiments, the classification model can be trained based on historical object data associated with historical objects, which include data indicative of the profile of the historical objects, the interaction information of the historical objects, and the attributes of the information posted by the historical objects, as well as data indicative of the categories to which the historical objects belong. That is, the classification model can be trained based on data associated with other objects that have been classified manually or otherwise. In some embodiments, over time, the classification device can continuously obtain new object data and train the classification model based thereon, and update the category of the object based on the classification model that is constantly updated. Exemplarily, FIG. 4 shows a schematic diagram of a method 400 for object classification in some embodiments of the present disclosure in the form of a time axis. In FIG. 4, a time axis 410 is included, the arrow of the time axis indicates the direction of time advancement, and exemplarily, the time axis can include time points tl, t2, and t3, wherein the time point tl is a time point before the time point t2, and the time point t2 is a time point before the time point t3. Referring to FIG. 4, the method 400 can include blocks 412 to 436. Among them, block 412 can occur at the time point tl, blocks 422 to 426 can occur at the time point t2, and blocks 432 to 436 can occur at the time point t3. In block 412, at the time point tl, the object starts to post information. The classification device can obtain data related to the object, thereby determining that the object starts to post information at the time point tl. In block 422, at the time point t2 after the time point tl, the classification device determines that no information is posted within a first predetermined length of time before the time point tl, and the length of time from the time point tl to the time point t2 does not exceed a second predetermined length of time.That is, the classification device determines that the object is a user without experience of putting information or a user with less experience of putting information. In block 424, the classification device obtains object data associated with the object. In block 426, the classification device determines, based on the object data and a classification model, a first category to which the object belongs at t2, where the classification model is trained based on historical object data before t2. In block 432, at t3 after t2, the classification device obtains new historical object data, which includes data associated with the historical object that is newly added during a period from t2 to t3. In block 434, the classification device trains the classification model based on the historical object data and the new historical object data, thereby obtaining an iteratively trained classification model. In block 436, the classification device determines, based on the object data associated with the object and the iteratively trained classification model, a second category to which the object belongs at t3. The second category is more time-sensitive than the first category. With the above method 400, the classification model can be iteratively trained based on data that increases over time, thereby making the determination of the type of the object by the classification model more accurate, and thereby making the type to which the object is finally determined more accurate over time. In some embodiments, the classification device can also evaluate the classification effect of the classification model. For example, after the classification device determines the category to which the object belongs based on the classification model, the classification device can evaluate the classification model based on new object data associated with the object that is newly added. For example, FIG. 5 shows a schematic diagram of a method 500 of evaluating the classification model in some embodiments of the present disclosure. In FIG. 5, a time axis 510 is included, and the arrow of the time axis indicates the direction of time advancement. For example, the time axis can include times tl, t2, and t4. The time tl is before t2, and the time t2 is before t4. Referring to FIG. 5, the method 500 can include blocks 512 to 536. For example, block 512 can occur at tl, blocks 522 to 526 can occur at t2, and blocks 532 to 536 can occur at t4. In block 512, at tl, the object starts to put information.In block 522, at a time t2 after the time tl, the classification device determines that the object has not put information in a first predetermined length of time before the time tl, and a length of time from the time tl to the time t2 does not exceed a second predetermined length of time. That is, the classification device determines that the object is an experienced user without putting information or a user with less experience of putting information. In block 524, the classification device obtains object data associated with the object. In block 526, the classification device determines a first category to which the object belongs at the time t2 based on the object data and a first classification model. In block 532, at a time t4 after the time t2 by a third predetermined length of time from the time t2, the classification device obtains new object data associated with the object during a period from the time t2 to the time t4, which can include a third category to which the object belongs, which can be determined by a classification algorithm or autonomously configured as the number of information put by the object increases. In block 534, the classification device determines the third category to which the object belongs based on the new object data. The third category can be carried in the new object data. In block 536, the classification device compares the third category with the first category determined based on the classification model at the time t2, thereby evaluating the classification effect of the classification model. For example, the classification device can score the classification model based on the size of the gap between the third category and the first category. In some embodiments, in a case where the score of the classification model is determined to be lower than a predetermined score threshold, the classification device can optimize the classification model, thereby maintaining a better classification effect at all times. FIG. 6 shows a block diagram of a device 600 for object classification according to some embodiments of the present disclosure. As shown in FIG. 6, the device 600 can include an obtaining module 602 configured to obtain object data associated with an object that has not put information for a predetermined length of time, wherein the object data indicates at least one of: a profile of the object, interaction information of the object, and attributes of information put by the object. The device 600 can also include a classification module 604 configured to determine a category to which the object belongs based on the object data, the category being used to determine a processing strategy associated with the object. In some embodiments, wherein the object data indicates the profile of the object, the interaction information of the object, and the attributes of the information put by the object, and the attributes of the information put by the object include a number of information and a total amount of information.In some embodiments, the profile of the object includes credit data of the object. In some embodiments, the classification module 604 includes a model classification unit configured to determine a category to which the object belongs based on the object data and a classification model, where the classification model is trained based on historical object data associated with historical objects, the historical object data including data indicating categories to which the historical objects belong. In some embodiments, the model classification unit includes: a first classification unit configured to determine a first category to which the object belongs at a first time based on the object data and the classification model; and a second classification unit configured to determine a second category to which the object belongs at a second time based on the object data and the classification model after iterative training, where the classification model after iterative training is the classification model trained based on the historical object data and additional historical object data, the additional historical object data being data associated with the historical objects added between the first time and the second time. In some embodiments, the model classification unit includes a third classification unit configured to determine the first category to which the object belongs at the first time based on the object data and the classification model; and the apparatus 600 further includes: an additional data obtaining unit configured to obtain additional object data of the object from the first time to a third time, the third time being a third predetermined length of time from the first time; and a fourth classification unit configured to determine a third category to which the object belongs at the third time based on the additional object data, the third category being used to evaluate the classification model. In some embodiments, the classification model includes a gradient boosting model. In some embodiments, the obtaining module 602 includes: a webpage obtaining unit configured to obtain a webpage associated with the object; and a data determining unit configured to determine at least a portion of the object data from the webpage based on a predefined recognition model. FIG. 7 shows a block diagram of an electronic device 700 according to certain embodiments of the present disclosure, which can be the device or apparatus described in embodiments of the present disclosure. As shown in FIG. 7, the device 700 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 702, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 704 or computer program instructions loaded from a storage unit 716 into a random access memory (RAM) 706.In RAM 706, various programs and data can be stored. CPU / GPU 702, ROM 704, and RAM 706 are connected to one another via bus 708. Input / output (I / O) interface 710 is also connected to bus 708. Although not shown in FIG. 7, device 700 can include a co-processor. Various components of device 700 are connected to I / O interface 710, including: input unit 712, e.g., a keyboard, mouse, etc.; output unit 714, e.g., various types of displays, speakers, etc.; storage unit 716, e.g., a disk, a memory, etc.; and communication unit 718, e.g., a network card, a modem, a wireless communication transceiver, etc. Communication unit 718 allows device 700 to exchange information / data with other devices over a computer network, e.g., the Internet, and / or various telecommunication networks. The various methods or processes described above can be performed by CPU / GPU 702. For example, in some embodiments, the methods can be implemented as a computer software program tangibly embodied in a machine-readable medium, e.g., storage unit 716. In some embodiments, some or all of the computer program can be loaded and / or installed on device 700 via ROM 704 and / or communication unit 718. When the computer program is loaded into RAM 706 and executed by CPU / GPU 702, one or more steps or actions of the methods or processes described above can be performed. In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions stored thereon for performing various aspects of the present disclosure. The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer-readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire. Computer-readable program instructions described herein can be downloaded to respective computing / processing devices from a computer-readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the respective computing / processing device. Computer-readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object-oriented programming language and conventional procedural programming languages. The computer-readable program instructions can execute entirely on the user's computing / processing device, partly on the user's computing / processing device, as a stand-alone software package, partly on the user's computing / processing device and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computing / processing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).In some embodiments, the electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), which can execute computer-readable program instructions, is customized by utilizing state information of the computer-readable program instructions to implement various aspects of the present disclosure. These computer-readable program instructions can be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer-readable program instructions can also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein comprises an article of manufacture including a manufacture that implements the functions / acts specified in the flowchart and / or block diagram block or blocks. The computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks. The flowchart and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logic functions. In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved.It is also noted that each of the individual blocks, combinations of blocks, or both, in the block diagrams and / or flow charts herein can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or can be implemented by a combination of special purpose hardware and computer instructions. Embodiments of the present disclosure have been described herein with the intent to be illustrative rather than limiting. Numerous embodiments have been described as modified examples, and still other modifications combining the specific embodiments noted in this document, can be employed as would be understood by one of ordinary skill in the art. The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. Various embodiments of hardware or software modules that can be used in implementing the described functionality can be embodied as or in one or more application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), or other hardware- or software components.

Claims

Claims 1. A method for object classification, comprising: Obtain object data associated with an object whose information delivery duration has not exceeded a predetermined time, wherein the object data indicates at least one of the following: the object's profile, the object's interaction information, and the attributes of the information delivered by the object; And based on the object data, determine the category to which the object belongs, the category being used to determine the processing strategy associated with the object.

2. The method of claim 1, wherein the object data indicates the profile of the object, the interaction information of the object, and the attributes of the information delivered by the object, and the attributes of the information delivered by the object include the quantity of the information and the total amount of the information.

3. The method of claim 2, wherein the profile of the object includes the credit data of the object.

4. The method of claim 1, wherein determining the category to which the object belongs based on the object data comprises: Based on the object data and the classification model, the category to which the object belongs is determined. The classification model is trained based on historical object data associated with historical objects, and the historical object data includes data indicating the category to which the historical object belongs.

5. The method of claim 4, wherein determining the category to which the object belongs based on the object data and the classification model comprises: Based on the object data and the classification model, determine the first category to which the object belongs at the first moment; And based on the object data and the iteratively trained classification model, determine the second category to which the object belongs at the second time point. The iteratively trained classification model is the classification model trained with newly added historical object data and the historical object data. The newly added historical object data is data associated with historical objects added between the first time point and the second time point.

6. The method of claim 4, wherein the object data and classification are based on... The model determines the category to which the object belongs by including: Based on the object data and the classification model, determine the first category to which the object belongs at the first moment; The method further includes: acquiring new object data of the object from the first time point to the third time point, wherein the third time point is a third predetermined time interval from the first time point; And based on the newly added object data, determine the third category to which the object belongs at the third time point, the third category being used to evaluate the classification model.

7. The method according to any one of claims 4 to 6, wherein the classification model comprises an extreme gradient boosting model.

8. The method of claim 1, wherein obtaining object data associated with the object comprises: Retrieve the webpage associated with the object; And based on a predefined recognition model, determine at least a portion of the object data from the webpage.

9. An apparatus for classifying objects, comprising: The acquisition module is configured to acquire object data associated with an object whose delivery information has not exceeded a predetermined duration, wherein the object data indicates at least one of the following: the object's profile, the object's interaction information, and the attributes of the information delivered by the object; And a classification module, configured to determine the category to which the object belongs based on the object data, the category being used to determine the processing strategy associated with the object.

10. An electronic device, comprising: processor; and a memory coupled to the processor, the memory having instructions stored therein, which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer-executable instructions that, when executed, cause a computer to perform the steps of the method according to any one of claims 1 to 8. 18

Images