CN114329048A

CN114329048A - Material determination method and device and electronic equipment

Info

Publication number: CN114329048A
Application number: CN202011063123.1A
Authority: CN
Inventors: 梁路伟; 徐晓明
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-09-30
Filing date: 2020-09-30
Publication date: 2022-04-12

Abstract

The disclosure relates to a material determination method, a material determination device and electronic equipment, wherein the method comprises the following steps: determining a plurality of candidate materials in a resource library of a content playing platform, wherein the candidate materials are determined at least based on historical display results of the materials; inputting the candidate materials into a ranking model, and outputting ranking results of the candidate materials, wherein the ranking model is obtained by training based on a training sample, and the training sample is determined at least based on historical display results of the materials; and determining target materials from the candidate materials based on the sorting result. Therefore, the screening efficiency of the materials can be effectively improved.

Description

Material determination method and device and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a material, and an electronic device.

Background

In the related art, materials are generally selected from a plurality of network resources in a manual screening mode. For example, the content of the video resources on the short video platform is obtained by browsing and viewing to determine whether there are video resources suitable as the material. Therefore, the problem of low screening efficiency exists in the existing material screening mode.

Disclosure of Invention

The disclosure provides a material determination method and device and electronic equipment, and aims to at least solve the problem that an existing material screening mode is low in screening efficiency. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a material determination method, including:

determining a plurality of candidate materials in a resource library of a content playing platform, wherein the candidate materials are determined at least based on historical display results of the materials;

inputting the candidate materials into a ranking model, and outputting ranking results of the candidate materials, wherein the ranking model is obtained by training based on a training sample, and the training sample is determined at least based on historical display results of the materials;

and determining target materials from the candidate materials based on the sorting result.

Optionally, the step of determining a plurality of candidate materials includes:

determining a target account from content publishing accounts of the content playing platform, wherein the target account is determined at least based on social relations and/or historical display information of materials;

and determining the content resources associated with the target account as candidate materials.

Optionally, the step of determining a target account from content distribution accounts of the platform includes:

screening accounts with the number of passive association relations larger than the preset relation number from the content publishing accounts, and determining the accounts as the target accounts, wherein the social relations comprise passive association relations; and/or the presence of a gas in the gas,

and screening accounts with the historical display quantity of the materials larger than the preset display quantity from the content publishing accounts, and determining the accounts as the target accounts, wherein the historical display information of the materials comprises the historical display quantity.

determining a screening category, wherein the screening category is determined based on attributes of the material;

and screening candidate materials which accord with the screening category from the resource library.

Optionally, the screening categories include:

a category determined based on at least two of the content tags, the release account category, and the material content events of the material, the attributes of the material including prime content tags, release account category, material content events; or the like, or, alternatively,

the historical display results of the materials conform to the category of the preset results.

Optionally, the displaying result of the material meeting the predetermined result includes: and after the material is displayed on the terminal equipment, the material is in a state of a preset operation.

Optionally, before the step of inputting the candidate materials into the ranking model and outputting the ranking result of the candidate materials, the method further includes:

generating a training sample of a sequencing model, wherein the training sample comprises a release result sample, and the release result sample is generated based on part of material information of which the release result accords with an expected release result and the release result does not accord with the expected release result in the historical release process;

training the ranking model based on the training samples.

According to a second aspect of the embodiments of the present disclosure, there is provided a material determination apparatus including:

a first determination module configured to execute in a repository of a content playback platform to determine a plurality of candidate materials, wherein the plurality of candidate materials are determined based on at least historical presentation results of the materials;

the output module is configured to input the candidate materials into a ranking model and output ranking results of the candidate materials, wherein the ranking model is trained on training samples, and the training samples are determined at least based on historical display results of the materials;

a second determining module configured to perform determining a target material from the plurality of candidate materials based on the ranking result.

Optionally, the first determining module includes:

the content playing platform comprises a first determining unit and a second determining unit, wherein the first determining unit is configured to determine a target account from content publishing accounts of the content playing platform, and the target account is determined at least based on social relations and/or historical display information of materials;

a second determination unit configured to perform a determination of a content asset associated with the target account as a candidate material.

Optionally, the first determining unit is configured to perform screening of accounts, of which the number of passive association relationships is greater than a predetermined relationship number, from the content publishing accounts, and determine that the accounts are the target account, where the social relationship includes a passive association relationship; and/or the presence of a gas in the gas,

and the account is configured to perform screening of the content publishing account for the content, wherein the historical display amount of the material is larger than the preset display amount, and the account is determined as the target account, and the historical display information of the material comprises the historical display amount.

Optionally, the first determining module includes:

a third determination unit configured to perform determination of a filtering category, wherein the filtering category is determined based on an attribute of the material;

and the screening unit is configured to screen out candidate materials which accord with the screening category from the resource library.

Optionally, the screening categories include:

Optionally, the apparatus further comprises:

the generating module is configured to execute training samples for generating a ranking model, wherein the training samples comprise release result samples, and the release result samples are generated based on part of material information of which the release results accord with the expected release results and the release results do not accord with the expected release results in the historical release process;

a training module configured to perform training the ranking model based on the training samples.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the material determination method of any one of the first aspect.

According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the material determination method of any one of the first aspects.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising: executable instructions which, when run on a computer, enable the computer to perform the material determination method of any one of the first aspects.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

a plurality of candidate materials are determined from a resource library of the content playing platform based on historical display results of the materials, and compared with a manual screening mode, the screening efficiency of the materials can be effectively improved; and the plurality of candidate materials are input into the sorting model to obtain a sorting result, and the sorting result can be used for displaying the expected exposure of each candidate material, so that the candidate material with higher expected exposure is selected from the plurality of candidate materials and determined as the target material, and the screening accuracy of the target material is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a flow diagram illustrating a method of material determination according to an exemplary embodiment.

FIG. 2 is a block diagram illustrating a material determination model according to an exemplary embodiment.

FIG. 3 is one of the block diagrams of a material ranking model shown in accordance with an exemplary embodiment.

FIG. 4 is a second block diagram illustrating a material ranking model according to an exemplary embodiment.

Fig. 5 is a block diagram illustrating a material determination apparatus according to an exemplary embodiment.

FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Fig. 1 is a flowchart illustrating a material determination method according to an exemplary embodiment, and referring to fig. 1, the material determination method according to the exemplary embodiment may be applied to an electronic device such as a mobile phone or a tablet computer, and includes the following steps:

step 101, determining a plurality of candidate materials in a resource library of a content playing platform.

In this step, a plurality of candidate materials may be determined based on the historical display result of the material, for example, content resources of the same author as the material with a good delivery effect in the historical display result may be selected from the resource library as the candidate materials, or content resources of the same type as the material with a good delivery effect in the historical display result may be selected as the candidate materials.

For example, a certain content publisher has a large number of followers, that is, content assets published by the content publisher all have a large number of followers to pay attention, so that the content assets published by the content publisher can be used as candidate materials, and the attention degree of the candidate materials is improved.

The candidate materials can also be content resources released by a certain public character or content resources related to recent hot matters, so that the attention degree of the candidate materials is improved, and the exposure of the materials determined based on the candidate materials is further improved.

The content playing platform may be a video playing platform, a short video playing platform, and the like, and the candidate material may be video content, text content, picture content, and the like in a resource library of the content playing platform.

And 102, inputting the candidate materials into a sorting model, and outputting sorting results of the candidate materials.

In the step, the candidate materials are sorted, and the corresponding sorting result is output, so that the most suitable material is selected from the candidate materials, the exposure of the material is improved, and the purpose of improving the material throwing effect is achieved.

Wherein the ranking model may be derived based on training samples, which may be determined based on historical presentation of the material.

For example, a ranking model may be trained based on historical presentation of material. Specifically, the ranking model can be generated by performing comparative analysis on the exposure of each material, such as the time period of delivery, the content of the material, and the like.

For example, the plurality of candidate materials include food content resources, game content resources, and integrated art content resources, but the historical display results of the materials show that the game content resources have the highest attention degree and the food content resources have the lowest attention degree, and the training model determined based on the historical display results is biased toward the game content resources in the ranking, that is, the obtained ranking results are likely to be the game content resources, the integrated art content resources, and the food content resources.

And 103, determining target materials from the candidate materials based on the sorting result.

In this step, the sorting result may be a sorting relation of expected exposure of a plurality of candidate materials, so that a candidate material with a higher expected exposure is selected as a target material, the exposure of the target material is increased, and the purpose of improving the material throwing effect is achieved.

Therefore, a plurality of candidate materials are determined from the resource library of the content playing platform based on the historical display results of the materials, and compared with a manual screening mode, the screening efficiency of the materials can be effectively improved; and the plurality of candidate materials are input into the sorting model to obtain a sorting result, and the sorting result can be used for displaying the expected exposure of each candidate material, so that the candidate material with higher expected exposure is selected from the plurality of candidate materials and determined as the target material, and the screening accuracy of the target material is improved.

Optionally, the step of determining a plurality of candidate materials includes: determining a target account from content publishing accounts of the content playing platform, wherein the target account is determined at least based on social relations and/or historical display information of materials; and determining the content resources associated with the target account as candidate materials.

In this embodiment, the social relationship may be the number of fans and the number of followers in the content publishing account; the historical display information of the material may be exposure information of the material, for example, if the exposure of the material is high in a certain period of time, a content publishing account for publishing the material may be determined as a target account.

Optionally, the step of determining a target account from content distribution accounts of the platform includes: screening accounts with the number of passive association relations larger than the preset relation number from the content publishing accounts, and determining the accounts as the target accounts, wherein the social relations comprise passive association relations; and/or screening accounts with the historical display quantity of the materials larger than the preset display quantity from the content publishing accounts, and determining the accounts as the target accounts, wherein the historical display information of the materials comprises the historical display quantity.

In this embodiment, the passive association relationship may be a relationship for establishing a concern, for example, a fan or a concern of the content distribution account has a passive association relationship with the content distribution account; and the historical presentation quantity may be the exposure of the material.

For example, if a certain content publishing account has ten thousand fans, it indicates that a passive association relationship is established between the ten thousand fans and the content publishing account; correspondingly, for a content resource issued by a certain content issuing account, if one thousand accounts watch the content resource, it indicates that an active association relationship exists between the one thousand accounts and the content resource issued by the content issuing account. It should be noted that the passive association relationship and the active association relationship include, but are not limited to, the above manners.

It can be understood that the target account may be a content distribution account with a large number of fans or a large number of followers, and the content resources distributed by the target account are concerned by a large number of people due to the large number of fans and followers, so that the exposure of the candidate materials can be increased by taking the distributed content resources as candidate materials.

In addition, the target account can also be a content release account of a material with high exposure, the content resource released by the account may have high exposure, and the content resource with high exposure released by the account can be used as a candidate element, so that the purpose of improving the exposure of the candidate material is achieved.

Optionally, the step of determining a plurality of candidate materials includes: determining a screening category, wherein the screening category is determined based on attributes of the material; and screening candidate materials which accord with the screening category from the resource library.

In the embodiment, the screening category can be determined, so that the candidate materials meeting the screening category can be selected from the resource library, and the purpose of improving the screening efficiency of the candidate materials is achieved.

The screening type can be determined based on the attribute of the material, namely the screening type is associated with the attribute of the material, namely the candidate material associated with the attribute of the material can be screened from the resource library, so that the accuracy and the screening efficiency of the candidate material are improved.

Wherein the screening categories include: a category determined based on at least two of the content tags, the release account category, and the material content events of the material, the attributes of the material including prime content tags, release account category, material content events; or the historical display result of the material accords with the category of the preset result.

For example, for food materials, content tags such as food and gourmet can be used as candidate material screening categories. Correspondingly, for a content resource issued by a certain account or a certain specific content event, the corresponding category can be used as the screening category of the candidate material.

Wherein the filtering category may be a category determined based on at least one or at least two of a content tag, a distribution account category, and a material content event of the material.

When the screening type is determined by at least two of the content tag of the material, the release account type and the material content event, the relevance between the candidate material and the material can be improved, namely the screening accuracy and the screening efficiency of the candidate material can be improved.

In addition, the step of displaying the material according with the preset result comprises the following steps: and after the material is displayed on the terminal equipment, the material is in a state of a preset operation.

In this embodiment, the occurrence of the predetermined operation state of the material may be a state in which the material is played/browsed and the distribution account information of the material is viewed.

Compared with the resource content which is approved and clicked, the resource content is played/browsed and the publishing account information of the resource content is viewed, so that the real interest of the user can be accurately reflected, namely the user is interested in the resource content, and when the resource content is used as a candidate material, the resource content can be more truly reflected to be used as the expected exposure of the candidate material according to the state of the preset operation of the resource content, namely the probability that the resource content is viewed and enters an author detail page, so that the screening efficiency of the candidate material can be improved.

Optionally, before the step of inputting the candidate materials into the ranking model and outputting the ranking result of the candidate materials, the method further includes: generating a training sample of a sequencing model, wherein the training sample comprises a release result sample, and the release result sample is generated based on part of material information of which the release result accords with an expected release result and the release result does not accord with the expected release result in the historical release process; training the ranking model based on the training samples.

In the embodiment, by adding the material of which the release result does not conform to the expected release result into the training sample for generating the ranking model, the training sample can be prevented from being distributed more and more specifically under long-term iteration and falling into a local optimal solution, so that the objectivity and the accuracy of the ranking model are influenced.

The materials which do not accord with the expected release result can be random materials, namely random flow, and the materials which do not accord with the expected release result are added into the training sample which generates the sequencing model, namely the random materials are added, so that the stability of the distribution of the training sample can be maintained to a certain degree, and the sample distribution is prevented from becoming more and more extreme.

Moreover, the materials which do not accord with the expected release result can reflect the whole change of the sequencing model, namely the whole change of the putting environment, and a dynamic time sequence index is provided for the measurement of the updating effect of the sequencing model.

Fig. 2 is a block diagram illustrating a material determination model according to an exemplary embodiment, referring to fig. 2, the determination model includes a recall ranking 201, a material warehousing and creative production 202, and an effect monitoring 203, wherein the recall ranking 201 mainly includes three parts, namely, an exploratory recall 2011, a posterior recall 2012, and a model ranking 2013.

The exploratory recall 2011 mainly aims to discover new materials, new workers and new directions, and can be subdivided into topic mining and index class exploration, wherein the topic mining is mainly recall of specific class materials, for example, recall of target classes can be determined by adopting content tags of the materials, release account classes, material content events and other modes; the index exploration is mainly based on recall of one or more in-station operation indexes, for example, the state that a material is played/browsed and the release account information of the material is viewed can be used as an exploration index, and compared with indexes that the material is approved, clicked and the like, the index exploration can reflect the real interest of a user.

The posterior recall 2012 is an automated recall made according to the existing release effect, and aims to improve the exposure of material release as timely as possible, and may include two types of accounts, namely a content release account with a large number of fans and a content release account with potential. Aiming at the content publishing account with a large number of fans, the content resources published by the content publishing account can be recalled automatically; for a potential content publishing account, the content resources with high exposure published by the content publishing account can be recalled automatically.

The method and the system have the advantages that creative production can be carried out on the warehoused materials, so that the warehoused materials become advertisements capable of being launched, and the exposure of the launched advertisements can be monitored, so that the launched advertisements can be managed.

Specifically, for the effect data returned after delivery, the material can be managed according to the exposure of the material, for example, a recall source/content publishing account with poor recent performance can be closed/reduced, and a recall source/content publisher with better recent performance is stimulated to realize the update and feedback of the recall strategy.

The model sorting 2013 mainly inputs recalled materials into a sorting model so as to sort the recalled materials, selects the materials from the sorting as warehoused materials and realizes the screening of the materials.

FIG. 3 is one of the block diagrams of a material ranking model shown in accordance with an exemplary embodiment, with reference to FIG. 3, the ranking model including a fixed category recall 301, a model ranking 302, and an effects monitoring 303; the fixed category recall 301 can be determined in a searchlighting recall mode, and then recalled materials are input into a sequencing model to sequence the recalled materials; and finally, monitoring the putting effect of the selected materials, and optimizing the sequencing model according to the monitored effect.

FIG. 4 is a second block diagram illustrating a material ranking model according to an exemplary embodiment, referring to FIG. 4, including ranked material 401, random traffic 402, and effects monitoring 403; the sequencing materials 401 are used for training the sequencing model, the random traffic 402 can be random materials, and the random traffic 402 is added in the process of training the sequencing model by using the sequencing materials 401, so that the sequencing model can be prevented from falling into a local optimal solution in the training process.

The random flow 402 may reflect the overall change of the dosing environment to a certain extent, and provide a dynamic time-series target for the measurement of the update effect of the ranking model.

The material determining method provided by the embodiment of the disclosure determines a plurality of candidate materials in a resource library of a content playing platform, wherein the candidate materials are determined at least based on a historical display result of the materials; inputting the candidate materials into a ranking model, and outputting ranking results of the candidate materials, wherein the ranking model is obtained by training based on a training sample, and the training sample is determined at least based on historical display results of the materials; and determining target materials from the candidate materials based on the sorting result. Therefore, a plurality of candidate materials are determined from the resource library of the content playing platform based on the historical display results of the materials, and compared with a manual screening mode, the screening efficiency of the materials can be effectively improved; and the plurality of candidate materials are input into the sorting model to obtain a sorting result, and the sorting result can be used for displaying the expected exposure of each candidate material, so that the candidate material with higher expected exposure is selected from the plurality of candidate materials and determined as the target material, and the screening accuracy of the target material is improved.

Fig. 5 is a block diagram illustrating a material determination apparatus according to an exemplary embodiment. Referring to fig. 5, the apparatus 500 includes a first determining module 501, an output module 502, and a second determining module 503, wherein:

a first determining module 501, configured to execute in a repository of a content playing platform, and determine a plurality of candidate materials, where the plurality of candidate materials are determined based on at least a historical display result of the materials;

an output module 502 configured to perform inputting the candidate materials into a ranking model, and outputting ranking results of the candidate materials, wherein the ranking model is trained based on a training sample, and the training sample is determined based on at least historical display results of the materials;

a second determining module 503 configured to determine a target material from the plurality of candidate materials based on the ranking result.

Optionally, the first determining module 501 includes:

Optionally, the screening categories include:

Optionally, the apparatus 500 further includes:

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

FIG. 6 is a block diagram illustrating a method for an electronic device according to an example embodiment. For example, the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 6, electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an interface to input/output (I/O) 612, a sensor component 614, and a communication component 616.

The processing component 602 generally controls overall operation of the electronic device 600, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 602 can include one or more modules that facilitate interaction between the processing component 602 and other components. For example, the processing component 602 can include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

The memory 604 is configured to store various types of data to support operation at the device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 604 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power supply component 606 provides power to the various components of electronic device 600. The power components 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 600.

The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 600 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 610 is configured to output and/or input audio signals. For example, the audio component 610 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 600 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 604 or transmitted via the communication component 616. In some embodiments, audio component 610 further includes a speaker for outputting audio signals.

The I/O interface 612 provides an interface between the processing component 602 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 614 includes one or more sensors for providing status assessment of various aspects of the electronic device 600. For example, the sensor component 614 may detect an open/closed state of the device 600, the relative positioning of components, such as a display and keypad of the electronic device 600, the sensor component 614 may also detect a change in the position of the electronic device 600 or a component of the electronic device 600, the presence or absence of user contact with the electronic device 600, orientation or acceleration/deceleration of the electronic device 600, and a change in the temperature of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 616 is configured to facilitate communications between the electronic device 600 and other devices in a wired or wireless manner. The electronic device 600 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 6G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 616 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a storage medium comprising instructions, such as the memory 604 comprising instructions, executable by the processor 620 of the electronic device 600 to perform the above-described method is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining material, comprising:

2. The method of claim 1, wherein the step of determining a plurality of candidate materials comprises:

3. The method of claim 2, wherein the step of determining the target account from the content distribution accounts of the platform comprises:

4. The method of claim 1, wherein the step of determining a plurality of candidate materials comprises:

5. The method of claim 4, wherein the screening categories comprise:

6. The method of claim 5, wherein the showing of the material in compliance with the predetermined result comprises: and after the material is displayed on the terminal equipment, the material is in a state of a preset operation.

7. The method of claim 1, wherein prior to the step of inputting the plurality of candidate materials into a ranking model and outputting a ranking result for the plurality of candidate materials, the method further comprises:

training the ranking model based on the training samples.

8. A material determination apparatus, comprising:

9. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the material determination method of any one of claims 1 to 7.

10. A storage medium in which instructions are executable by a processor of an electronic device to enable the electronic device to perform the material determination method of any one of claims 1 to 7.