CN114979275A - Resource request processing method, electronic device and storage medium - Google Patents

Resource request processing method, electronic device and storage medium Download PDF

Info

Publication number
CN114979275A
CN114979275A CN202210418300.6A CN202210418300A CN114979275A CN 114979275 A CN114979275 A CN 114979275A CN 202210418300 A CN202210418300 A CN 202210418300A CN 114979275 A CN114979275 A CN 114979275A
Authority
CN
China
Prior art keywords
resource
filling rate
user
preset
difference value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210418300.6A
Other languages
Chinese (zh)
Inventor
高云龙
戴军
蔡东海
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhangyue Technology Co Ltd
Original Assignee
Zhangyue Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhangyue Technology Co Ltd filed Critical Zhangyue Technology Co Ltd
Priority to CN202210418300.6A priority Critical patent/CN114979275A/en
Publication of CN114979275A publication Critical patent/CN114979275A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure relates to a resource request processing method, an electronic device and a storage medium, wherein the method comprises the following steps: predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end; selecting at least one target resource end with a resource filling rate larger than or equal to a preset filling rate threshold value from the plurality of preset resource ends; and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end. According to the method and the device, the resource filling rates of a plurality of preset resource ends are predicted according to feedback data of historical resource requests of the user end, the resource ends with the resource filling rates larger than or equal to a preset filling rate threshold value are selected as target resource ends, so that the user end sends the resource requests to the target resource ends, the sending of invalid resource requests caused by the fact that the resource ends do not fill resources is reduced, the bandwidth occupation is reduced, and the actual resource filling rate is improved.

Description

Resource request processing method, electronic device and storage medium
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to a resource request processing method, an electronic device, and a storage medium.
Background
The internet accelerates the information exchange and is a good advertisement carrier, so that online advertisements appear. The concept of programmed purchase, namely programming the whole delivery process from an advertiser to media, is promoted in the evolution process of online advertisements.
In order to improve the trading efficiency, the market needs to integrate a large amount of media resources so that the buyer and the seller can interface, so ADX (Ad Exchange, advertisement trading Platform) appears, and meanwhile, the advertisement source Side needs to manage various delivery strategies for ADX traffic, so DSP (Demand-Side Platform) exists. When a user accesses a page where a media advertisement position is located, a media sends an advertisement request, an advertisement source party needs to bid on a DSP in real time to purchase traffic to display the delivered advertisements, ADX returns the advertisements of the advertisement source party according to the advertisement request of the media, and the media can select whether to display the advertisements or select which advertisement to display. In practical situations, it may happen that the advertisement platform does not find an advertisement suitable for the user, or the advertisement provided by the platform does not meet the requirements of the media party, so the return amount is far less than the request amount, and the filling rate may represent the situation, i.e. the return amount/the request amount. Thus, increasing the fill rate may, on the one hand, increase the revenue of the media.
In the current commercial system, an Application Programming Interface (API) is used for interfacing with an advertisement source, the request volume sent by a media party is huge, the bandwidth cost is high, the advertisement return volume of the advertisement source party is small, the filling rate is low, the media party profit is small, and the bandwidth is occupied in most of time, which affects the effective request and response of the advertisement source party.
Disclosure of Invention
To solve the technical problem or at least partially solve the technical problem, the present disclosure provides a method for processing a resource request, an electronic device, and a storage medium.
In a first aspect, the present disclosure provides a method for processing a resource request, including:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate greater than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
In a second aspect, the present disclosure provides an electronic device comprising a processor and a memory, the memory for storing executable instructions that cause the processor to:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate greater than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
In a third aspect, the present disclosure provides a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to carry out the method of the first aspect.
Compared with the prior art, the technical scheme provided by the disclosure has the following advantages:
according to the resource request processing method, the electronic device and the storage medium, the resource filling rates of the plurality of preset resource ends to the user end are predicted, the resource end with the predicted resource filling rate larger than or equal to the preset filling rate threshold value is selected as the target resource end, then the identifier of the target resource end is sent to the user end, so that the user end sends the resource request to the target resource end, the resource request is sent to the resource end with the high predicted filling rate selectively, the sending of invalid resource requests caused by the fact that the resource end does not fill the resources is reduced, the bandwidth occupation is reduced, and the actual resource filling rate is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.
Fig. 1 is a flowchart of a method for processing a resource request according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model according to the embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
In order to make the sending of the resource request more effective and thus improve the profit, the embodiments of the present disclosure provide a method for processing a resource request, an electronic device, and a storage medium.
Fig. 1 is a flowchart of a method for processing a resource request according to an embodiment of the present disclosure.
In some embodiments of the present disclosure, the processing method of the resource request shown in fig. 1 may be executed by an electronic device, for example, a server or a terminal, and the terminal may specifically include, but is not limited to, a mobile terminal such as a smartphone, a laptop, a Personal Digital Assistant (PDA), a tablet computer (PAD), a vehicle-mounted terminal (e.g., a vehicle-mounted navigation terminal), a wearable device, and the like.
As shown in fig. 1, the method for processing the resource request may include the following steps.
S101, predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end.
Taking the advertisement resource as an example, the resource end may be an advertisement resource end, that is, a client needing to put an advertisement for promotion, wherein the resource filling rate is determined by a request amount of the client sending an advertisement request to the advertisement resource end and a return amount of the advertisement resource end returning an advertisement to the client, so that different advertisement resource ends have different resource filling rates relative to the client.
The user side may be all client side channels under the media platform, for example, a certain electronic book platform has other client side channels besides its own client side, and then its own client side and other client sides may be the user sides of the electronic book platform.
The feedback data of the historical resource request of the user side comprises: the client sends a request amount of advertisement requests to all the advertisement resource sources, and the advertisement resource sources return different return amounts of advertisements to the client. Therefore, the platform server can calculate the predicted resource filling rate according to the feedback data of the historical resource requests of the user sides under the platform flags.
S102, selecting at least one target resource end with the resource filling rate larger than or equal to a preset filling rate threshold value from a plurality of preset resource ends.
For example, when a user uses a user side of the e-book platform, the user side enters an advertisement bar page of the e-book user side, and at this time, the user side needs to send an advertisement resource request to make the advertisement resource source return an advertisement so as to fill the advertisement bar page.
The platform server can select the plurality of advertisement resource ends according to the resource filling rates predicted by the plurality of preset advertisement resource ends, select the advertisement resource ends of which the resource filling rates are larger than or equal to a preset filling rate threshold value, and use the advertisement resource ends as target resource ends, so that the user end can selectively send an advertisement request to the target resource ends in the subsequent steps.
S103, sending the identification of at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
Illustratively, the platform server sends the identifier of the selected target resource end to the user end according to the target resource end selected in S102, so that the user end sends the advertisement resource request to the target resource end.
According to the method, the device and the system, the resource filling rates of the plurality of preset resource ends to the user end are predicted, the resource end of which the predicted resource filling rate is larger than or equal to the preset filling rate threshold is selected as the target resource end, then the identification of the target resource end is sent to the user end, so that the user end sends the resource request to the target resource end, the resource request is sent to the resource end with the high predicted filling rate selectively, the sending of invalid resource requests caused by the fact that the resource end does not fill the resources is reduced, the bandwidth occupation is reduced, and the actual resource filling rate is improved.
On the basis of the above embodiment, a preset traffic proportion is sent to the user side, so that the user side sends a resource request to a plurality of preset resource ends or at least one target resource end based on the traffic proportion selection.
Illustratively, in the process of using the user terminal, the user browses to the page loaded with the advertisement, that is, generates advertisement traffic, and at this time, needs to send an advertisement request to enable the advertisement resource terminal to return the advertisement, and consumes the advertisement traffic, thereby obtaining revenue.
For example, the preset traffic proportion may be 1%, the platform server sends the preset traffic proportion to the user side, so that when the user side sends an advertisement request, the user side sends the advertisement request that needs to be sent with 1% of the advertisement traffic to the plurality of preset resource sources, that is, the advertisement request that needs to be sent with 1% of the advertisement traffic is not sent according to the resource filling rate predicted by the resource source. And the advertisement requests which need to be sent when 99% of the advertisement flow is left are selectively sent to the target resource end meeting the requirements according to the resource filling rate predicted by the resource end.
The method and the device for sending the advertisement requests send the resource requests to the plurality of preset resource ends or the at least one target resource end based on the flow proportion by sending the preset flow proportion to the user end, and the advertisement requests sent to the plurality of preset resource ends in the preset flow proportion are used as reference for comparison and cold start, so that the bandwidth is reasonably utilized, the actual filling rate is improved, meanwhile, some zero-base resource ends can be developed, and the resource ends with low predicted resource filling rate are prevented from being missed.
On the basis of the above embodiment, the feedback data of the historical resource request includes: data related to the resource side and data related to the user side; predicting the resource filling rate of a plurality of preset resource ends based on the feedback data of the historical resource requests of the user ends, wherein the method comprises the following steps: performing characteristic processing on feedback data of the historical resource request based on the data related to the resource end and the data related to the user end to obtain a resource filling rate characteristic related to the resource end and a resource filling rate characteristic related to the user end; and predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends.
Illustratively, the data related to the resource end may be, for example, an ID of the resource end, the number of times the resource end returns the resource, and the like, and the data related to the user end may be, for example, a user ID, the number of times the user end sends the request resource message, and the like. The data is processed, for example, by smoothing, the number of requests is added to a corresponding value, and the number of returns is added to a corresponding value, so as to obtain the resource filling rate characteristic related to the resource end and the resource filling rate characteristic related to the user end, for example, the resource filling rate of the whole resource end ID, or the resource filling rate of the user end of the user ID by the resource end ID, or the resource filling rate of the whole user end of the user ID. According to the characteristics, the resource filling rates of a plurality of preset resource ends are predicted.
Correspondingly, predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends comprises: and processing the resource filling rate characteristics related to the resource end and the resource filling rate characteristics related to the user end through a pre-trained logistic regression model, and outputting the resource filling rate of the preset resource end through the logistic regression model.
After the characteristics related to the resource filling rate are obtained, in order to facilitate the calculation of the predicted filling rate, for example, logarithmic processing can be performed, and then the processed characteristic data is input into a pre-trained logistic regression model, for example, the logistic regression model can be a continuous characteristic feedback type logistic regression model, and the resource filling rate at the preset resource end is output after calculation is performed through model weight, and the resource filling rate is the resource filling rate predicted by the preset resource end.
In the embodiment of the disclosure, the feedback data of the historical resource request is subjected to feature processing to obtain features related to the resource filling rate, the obtained feature prediction is processed by using a pre-trained logistic regression model, the resource filling rates of a plurality of preset resource ends are output to obtain the predicted resource filling rate, and the accuracy of the predicted resource filling rate can be improved.
On the basis of the foregoing embodiment, the data related to the resource end includes a resource end identifier, and the data related to the user end includes: user group identification, user new and old identification and user region identification.
Taking advertisement as an example, the resource identifier may be an advertisement source ID, that is, an advertisement placement ID, which is an ID of a client who needs to display an advertisement on the platform for promotion when placing the advertisement. The user group identifier may be, for example, the age stage of the user, the tendency of the user to the advertisement type, the new and old identifiers of the user, i.e., the time when the user uses the user side of the platform, whether the user is a new user or an old user of the platform, and the user region identifier, i.e., the area where the user is currently located, such as provinces, or provinces and urban areas.
Correspondingly, the resource filling rate characteristic related to the resource end includes: every other first preset duration, the resource end identifies a corresponding first resource filling rate; and identifying a corresponding second resource filling rate at the resource end every second preset duration; the first preset time length is less than the second preset time length; the resource fill rate characteristics associated with the user side include: the resource end identifies a third resource filling rate aiming at the user group identification; identifying a fourth resource filling rate of the user group in different resource request frequency intervals; a fifth resource filling rate corresponding to the new and old identifiers of the user; and the sixth resource filling rate corresponding to the user region identification.
For example, in the resource filling rate feature related to the resource end, the first preset duration may be one hour, and the first resource filling rate corresponding to the resource end identifier may be a first resource filling rate corresponding to an advertisement source ID calculated by receiving an advertisement resource request sent to the advertisement source ID and the number of times of receiving the advertisement resource returned by the advertisement source ID.
Correspondingly, the second preset duration may be one day, and the second resource filling rate corresponding to the advertisement source ID in the time of one day is obtained.
In the resource filling rate characteristics related to the user side, for example, when the user group identifier of the user side is an age group, and an advertisement that a certain advertisement source ID wants to deliver is a game advertisement, at this time, if the user group identifier is an old person, the advertisement source ID generally does not deliver the advertisement to the user side identified by the user group identifier, that is, different advertisement source IDs have different tendencies of delivering advertisements to different user groups, so that the resource filling rates of the advertisement source IDs for the user group identifiers are different, and therefore, a third resource filling rate of the preset resource end identifier for different user group identifiers can be obtained, and the third resource filling rate can reflect the influence of different user identifiers on the return of the advertisement source ID to the advertisement resource.
The fourth resource filling rate of the user group identifier in different resource request time intervals may be, for example: when different users use the user terminal, the resource request times for different advertisement source IDs are different, the request times of different user group identifications for different advertisement source IDs are divided into different intervals, for example, the request times of the user A relative to the advertisement source B in one day is 10, namely, the request times are recorded in the interval of 1-50 times, and the resource filling rate of the user A relative to the advertisement source B in the interval of 1-50 times is calculated, so that the fourth resource filling rate can be obtained, and the fourth resource filling rate can reflect the influence of the request times of different users on the return of the advertisement resources to the advertisement source IDs.
The fifth resource filling rate corresponding to the new and old user identifiers may be, for example, a resource filling rate of the advertisement source ID for advertisement delivery of the new user, and a resource filling rate of the advertisement source ID for advertisement delivery of the old user, and the fifth resource filling rate may reflect an influence of the new and old user identifiers on return of the advertisement resource to the advertisement source ID.
The sixth resource filling rate corresponding to the user region identifier may be, for example, a resource filling rate of the advertisement source ID for advertisement released by users of different provinces, and the sixth resource filling rate may reflect an influence of the region identifier on the return of the advertisement resource to the advertisement source ID.
According to the method and the device, the related resource filling rate is calculated for the plurality of preset resource end identifications and is used as the resource filling rate characteristic related to the resource end, different user end identifications are divided, the related resource filling rate is calculated and is used as the resource filling rate characteristic related to the user end, the effectiveness of the characteristic can be improved, and therefore the accuracy of the resource filling rate predicted by a subsequent model is improved.
On the basis of the foregoing embodiment, predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends further includes: processing the resource filling rate characteristic related to the resource end, the resource filling rate characteristic related to the user end and the resource filling rate characteristic determined based on the feedback data of the historical resource request through a pre-trained neural network model, and outputting the resource filling rates of a plurality of preset resource ends by the neural network model; and performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model, so that the difference value between the resource filling rate after the disturbance control and the resource filling rate output by the logistic regression model is in a preset difference value interval, and taking the resource filling rate after the disturbance control as the predicted resource filling rate.
In the embodiment of the disclosure, the feedback data of the historical resource requests are updated in real time, predicting the resource filling rates of a plurality of preset resource sources based on the feedback data of the historical resource requests is a highly challenging task, and meanwhile, in order to reduce the influence of the feedback data of the historical resource requests on the resource filling rate output by the model, which is formed according to the resource requests sent by the predicted resource filling rates, a continuous characteristic feedback type logistic regression model with extremely strong interpretability and rapid problem troubleshooting is selected as the main model.
In addition, in order to fully utilize the feedback data of the historical resource request and enable the predicted resource filling rate to be more accurate, the predicted resource filling rate can be obtained through a pre-trained neural network model. The feedback data based on the historical resource request may include, for example: the type of the terminal used by the user is, for example, a mobile phone or a computer, and further, may be, for example, a brand of the mobile phone used by the user or a model of the mobile phone used by the user.
Accordingly, the resource fill-rate characteristic determined based on the feedback data of the historical resource requests may be, for example, a resource fill-rate characteristic in which the advertisement source ID is specific to the model of the cell phone used by the user. The relevance of these features to the predicted resource fill rate is lower than that described in the above embodiments and can therefore be processed by the input neural network model. Processing the resource filling rate characteristic related to the resource end, the resource filling rate characteristic related to the user side and the resource filling rate characteristic determined based on the feedback data of the historical resource request by the neural network model, outputting the resource filling rates of a plurality of preset resource ends, performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model so that the difference value between the resource filling rate after disturbance control and the resource filling rate output by the logistic regression model is within a preset difference value interval, and taking the resource filling rate after disturbance control as the predicted resource filling rate.
In this case, referring to fig. 2, the disturbance control of the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model specifically includes the following steps:
s210, calculating a first difference value between the resource filling rate output by the neural network model and the resource filling rate output by the logistic regression model.
S220, judging whether the first difference value is within a preset difference value interval or not; and the difference interval is an interval determined based on the resource filling rate output by the logistic regression model.
If not, go to S231.
S231, weighting the first difference value to obtain a second difference value, so that the second difference value is within the difference value interval.
And S232, adding the second difference value and the resource filling rate output by the logistic regression model to obtain the resource filling rate after disturbance control.
If the first difference is within the preset difference interval, S240 is performed.
And S240, adding the first difference value and the resource filling rate output by the logistic regression model to obtain the resource filling rate after disturbance control.
For example, the preset difference interval may be 20% of the resource filling rate output by the logistic regression model, the preset percentage range of the resource filling rate output by the logistic regression model is taken to determine the difference interval, and the difference is added to the resource filling rate output by the logistic regression model and controlled within the preset difference interval, so that the resource filling rate output by the logistic regression model is controlled within the preset percentage range in a disturbance manner, the neural network model is prevented from excessively interfering with the resource filling rate output by the logistic regression model, and the accuracy of the predicted resource filling rate is improved by using the neural network model.
According to the method and the device, the resource filling rate characteristics related to the resource end, the resource filling rate characteristics related to the user side and the resource filling rate characteristics determined by feedback data of other historical resource requests are processed through the neural network model, the resource filling rates of a plurality of preset resource ends are output, the resource filling rate output by the logistic regression model is subjected to disturbance control according to the resource filling rate output by the neural network model, and the filling rate after disturbance control is used as the predicted resource filling rate. The feedback data of the historical resource requests can be more comprehensively utilized to predict the resource filling rates of a plurality of preset resource ends, and the accuracy of the predicted resource filling rates is improved.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
The electronic devices provided by the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as smart phones, notebook computers, PDAs, PADs, PMPs, in-vehicle terminals (e.g., car navigation terminals), wearable devices, and the like, and fixed terminals such as digital TVs, desktop computers, smart home devices, and the like.
It should be noted that the electronic device 310 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiment of the present invention.
The electronic device 310 conventionally includes a processor 310 and a computer program product or computer-readable medium in the form of a memory 320. The memory 320 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 320 has storage space 321 of executable instructions (or program code) 3211 for performing any of the method steps in the method of processing a resource request described above. For example, the storage space 321 for executable instructions may include respective executable instructions 3211 for implementing various steps in the above method of processing a resource request, respectively. The executable instructions may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit. The memory unit may have memory segments or memory spaces or the like arranged similarly to the memory 320 in the electronic device 310 of fig. 3. The executable instructions may be compressed, for example, in a suitable form. Generally, the memory unit comprises executable instructions for performing the steps of the processing method of the resource request according to the present invention, i.e. codes readable by a processor, such as the processor 310, for example, which when run by the electronic device 310, cause the electronic device 310 to perform the steps of the processing method of the resource request described above.
Of course, for simplicity, only some of the components of the electronic device 310 relevant to the present invention are shown in fig. 3, and components such as buses, input/output interfaces, input devices, output devices, and the like are omitted. In addition, the electronic device 310 may include any other suitable components depending on the particular application.
Embodiments of the present invention further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the method for processing the resource request provided in the embodiments of the present invention.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
In an embodiment of the present invention, program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The invention discloses:
A1. a resource request processing method comprises the following steps:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate greater than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
A2. The method of claim a1, wherein the method further comprises:
and sending a preset flow proportion to the user side so that the user side can select to send a resource request to the plurality of preset resource ends or the at least one target resource end based on the flow proportion.
A3. The method of claim a1, wherein the feedback data for the historical resource requests includes: data related to the resource side and data related to the user side;
the predicting the resource filling rates of a plurality of preset resource ends based on the feedback data of the historical resource requests of the user ends comprises the following steps:
performing feature processing on the feedback data of the historical resource request based on the data related to the resource end and the data related to the user end to obtain a resource filling rate feature related to the resource end and a resource filling rate feature related to the user end;
and predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends.
A4. The method of claim a3, wherein the predicting the resource filling rates of the preset resource ends based on the resource filling rate characteristic related to the resource end and the resource filling rate characteristic related to the user end comprises:
and processing the resource filling rate characteristics related to the resource end and the resource filling rate characteristics related to the user end through a pre-trained logistic regression model, and outputting the resource filling rates of a plurality of preset resource ends through the logistic regression model.
A5. The method of claim A3 or A4,
the data associated with the resource comprises a resource end identification;
the data related to the user terminal comprises: user group identification, user new and old identification and user region identification.
A6. The method of claim A5, wherein,
the resource filling rate characteristic related to the resource end comprises: every other first preset duration, the resource end identifies a corresponding first resource filling rate; and identifying a corresponding second resource filling rate at the resource end every second preset duration; the first preset time length is less than the second preset time length;
the resource filling rate characteristics related to the user terminal include: the resource end identifies a third resource filling rate aiming at the user group identification; identifying a fourth resource filling rate of the user group in different resource request frequency intervals; a fifth resource filling rate corresponding to the new and old identifiers of the user; and the sixth resource filling rate corresponding to the user region identification.
A7. The method of claim a4, wherein the predicting resource filling rates of a plurality of preset resource sources based on the resource filling rate characteristics associated with the resource side and the resource filling rate characteristics associated with the user side further comprises:
processing the resource filling rate characteristic related to the resource end, the resource filling rate characteristic related to the user side and the resource filling rate characteristic determined based on the feedback data of the historical resource request through a pre-trained neural network model, and outputting the resource filling rates of a plurality of preset resource ends by the neural network model;
and performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model, so that the difference value between the resource filling rate after the disturbance control and the resource filling rate output by the logistic regression model is in a preset difference value interval, and taking the resource filling rate after the disturbance control as the predicted resource filling rate.
A8. The method of claim a7, wherein the perturbation controlling the resource filling rate of the logistic regression model output based on the resource filling rate of the neural network model output comprises:
calculating a first difference value between the resource filling rate output by the neural network model and the resource filling rate output by the logistic regression model;
judging whether the first difference value is within a preset difference value interval or not; the difference interval is an interval determined based on the resource filling rate output by the logistic regression model;
if the difference value is not within the preset difference value interval, weighting the first difference value to obtain a second difference value so that the second difference value is within the difference value interval;
and adding the second difference value and the resource filling rate output by the logistic regression model to obtain the resource filling rate after the disturbance control.
A9. The method of claim A8, wherein the method further comprises:
and if the first difference is within a preset difference interval, adding the first difference and the resource filling rate output by the logistic regression model to obtain the resource filling rate after the disturbance control.
B10. An electronic device comprising a processor and a memory, the memory to store executable instructions that cause the processor to:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate greater than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
B11. The electronic device of claim B10, wherein the executable instructions further cause the processor to perform:
and sending a preset flow proportion to the user side so that the user side can select to send resource requests to the preset resource ends or the at least one target resource end based on the flow proportion.
B12. The electronic device of claim B10, wherein the feedback data for historical resource requests includes: data related to the resource side and data related to the user side;
when predicting the resource filling rates of a plurality of preset resource sources based on the feedback data of the historical resource requests of the user side, the executable instructions specifically cause the processor to execute:
performing feature processing on the feedback data of the historical resource request based on the data related to the resource end and the data related to the user end to obtain a resource filling rate feature related to the resource end and a resource filling rate feature related to the user end;
and predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends.
B13. The electronic device of claim B12, wherein in predicting the resource fill rates of a plurality of predetermined resource sources based on the resource fill rate characteristic associated with the resource end and the resource fill rate characteristic associated with the user end, the executable instructions specifically cause the processor to:
and processing the resource filling rate characteristics related to the resource end and the resource filling rate characteristics related to the user end through a pre-trained logistic regression model, and outputting the resource filling rates of a plurality of preset resource ends through the logistic regression model.
B14. The electronic device of claim B12 or B13,
the data associated with the resource comprises a resource end identification;
the data related to the user terminal comprises: user group identification, user new and old identification and user region identification.
B15. The electronic device of claim B14, wherein,
the resource filling rate characteristic related to the resource end includes: every other first preset duration, the resource end identifies a corresponding first resource filling rate; and identifying a corresponding second resource filling rate at the resource end every second preset duration; the first preset time length is less than the second preset time length;
the resource filling rate characteristics related to the user terminal include: the resource end identifies a third resource filling rate aiming at the user group identification; identifying a fourth resource filling rate of the user group in different resource request frequency intervals; a fifth resource filling rate corresponding to the new and old identifiers of the user; and the sixth resource filling rate corresponding to the user region identification.
B16. The electronic device of claim B13, wherein when predicting the resource fill rates of a plurality of predetermined resource sources based on the resource fill rate characteristics associated with the resource terminals and the resource fill rate characteristics associated with the user terminals, the executable instructions further cause the processor to:
processing the resource filling rate characteristic related to the resource end, the resource filling rate characteristic related to the user end and the resource filling rate characteristic determined based on the feedback data of the historical resource request through a pre-trained neural network model, and outputting the resource filling rates of a plurality of preset resource ends by the neural network model;
and performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model, so that the difference value between the resource filling rate after the disturbance control and the resource filling rate output by the logistic regression model is in a preset difference value interval, and taking the resource filling rate after the disturbance control as the predicted resource filling rate.
B17. The method of claim B16, wherein executable instructions, when the perturbation control is performed on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model, specifically cause the processor to perform:
calculating a first difference value between the resource filling rate output by the neural network model and the resource filling rate output by the logistic regression model;
judging whether the first difference value is within a preset difference value interval or not; the difference interval is an interval determined based on the resource filling rate output by the logistic regression model;
if not, weighting the first difference value to obtain a second difference value so as to enable the second difference value to be within the difference value interval;
and adding the second difference value and the resource filling rate output by the logistic regression model to obtain the resource filling rate after the disturbance control.
B18. The electronic device of claim B16, wherein the executable instructions further cause the processor to:
and if the first difference is within a preset difference interval, adding the first difference and the resource filling rate output by the logistic regression model to obtain the resource filling rate after the disturbance control.
C19. A computer-readable storage medium, wherein the storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method of processing a resource request of any of the preceding claims 1-9.
Various component embodiments of the invention may be implemented in whole or in part in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an electronic device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
The foregoing description is only exemplary of the preferred embodiments of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents is encompassed without departing from the spirit of the disclosure. For example, the above features and (but not limited to) features having similar functions disclosed in the present invention are mutually replaced to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the invention. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims (10)

1. A method for processing resource requests is characterized by comprising the following steps:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate greater than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
2. The method of claim 1, further comprising:
and sending a preset flow proportion to the user side so that the user side can select to send resource requests to the preset resource ends or the at least one target resource end based on the flow proportion.
3. The method of claim 1, wherein the feedback data of the historical resource requests comprises: data related to the resource side and data related to the user side;
the method for predicting the resource filling rates of a plurality of preset resource ends based on the feedback data of the historical resource requests of the user ends comprises the following steps:
performing feature processing on the feedback data of the historical resource request based on the data related to the resource end and the data related to the user end to obtain a resource filling rate feature related to the resource end and a resource filling rate feature related to the user end;
and predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristics related to the resource ends and the resource filling rate characteristics related to the user ends.
4. The method of claim 3, wherein predicting the resource filling rates of a plurality of preset resource ends based on the resource filling rate characteristic related to the resource ends and the resource filling rate characteristic related to the user ends comprises:
and processing the resource filling rate characteristics related to the resource end and the resource filling rate characteristics related to the user end through a pre-trained logistic regression model, and outputting the resource filling rates of a plurality of preset resource ends through the logistic regression model.
5. The method according to claim 3 or 4,
the data associated with the resource comprises a resource end identification;
the data related to the user terminal comprises: user group identification, user new and old identification and user region identification.
6. The method of claim 5,
the resource filling rate characteristic related to the resource end comprises: every other first preset duration, the resource end identifies a corresponding first resource filling rate; and identifying a corresponding second resource filling rate at the resource end every second preset duration; the first preset time length is less than the second preset time length;
the resource filling rate characteristics related to the user terminal include: the resource end identifies a third resource filling rate aiming at the user group identification; identifying a fourth resource filling rate of the user group in different resource request frequency intervals; a fifth resource filling rate corresponding to the new and old identifiers of the user; and the sixth resource filling rate corresponding to the user region identification.
7. The method according to claim 4, wherein the predicting the resource filling rates of the plurality of predetermined resource sources based on the resource filling rate characteristic related to the resource end and the resource filling rate characteristic related to the user end further comprises:
processing the resource filling rate characteristic related to the resource end, the resource filling rate characteristic related to the user end and the resource filling rate characteristic determined based on the feedback data of the historical resource request through a pre-trained neural network model, and outputting the resource filling rates of a plurality of preset resource ends by the neural network model;
and performing disturbance control on the resource filling rate output by the logistic regression model based on the resource filling rate output by the neural network model, so that the difference value between the resource filling rate after the disturbance control and the resource filling rate output by the logistic regression model is in a preset difference value interval, and taking the resource filling rate after the disturbance control as the predicted resource filling rate.
8. The method of claim 7, wherein the perturbation controlling the resource filling rate of the logistic regression model output based on the resource filling rate of the neural network model output comprises:
calculating a first difference between the resource filling rate output by the neural network model and the resource filling rate output by the logistic regression model;
judging whether the first difference value is within a preset difference value interval or not; the difference interval is an interval determined based on the resource filling rate output by the logistic regression model;
if the difference value is not within the preset difference value interval, weighting the first difference value to obtain a second difference value so that the second difference value is within the difference value interval;
and adding the second difference value and the resource filling rate output by the logistic regression model to obtain the resource filling rate after the disturbance control.
9. An electronic device comprising a processor and a memory, the memory to store executable instructions that cause the processor to:
predicting resource filling rates of a plurality of preset resource ends based on feedback data of historical resource requests of a user end;
selecting at least one target resource end with a resource filling rate larger than or equal to a preset filling rate threshold value from the plurality of preset resource ends;
and sending the identifier of the at least one target resource end to the user end so that the user end sends a resource request to the at least one target resource end.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method of processing a resource request of any of the preceding claims 1-8.
CN202210418300.6A 2022-04-20 2022-04-20 Resource request processing method, electronic device and storage medium Pending CN114979275A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210418300.6A CN114979275A (en) 2022-04-20 2022-04-20 Resource request processing method, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210418300.6A CN114979275A (en) 2022-04-20 2022-04-20 Resource request processing method, electronic device and storage medium

Publications (1)

Publication Number Publication Date
CN114979275A true CN114979275A (en) 2022-08-30

Family

ID=82978117

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210418300.6A Pending CN114979275A (en) 2022-04-20 2022-04-20 Resource request processing method, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN114979275A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150339728A1 (en) * 2014-05-20 2015-11-26 Pubmatic, Inc. Ad serving and intelligent impression throttling techniques implemented in electronic data networks
CN108229987A (en) * 2016-12-14 2018-06-29 腾讯科技（深圳）有限公司 A kind of advertisement inventory evaluation method and device
CN108694608A (en) * 2018-05-14 2018-10-23 广州至真信息科技有限公司 A kind of ad trafficking system and advertisement method of commerce
CN110009404A (en) * 2019-03-20 2019-07-12 深圳新度博望科技有限公司 Advertisement demonstration method, device, computer equipment and storage medium
CN111143738A (en) * 2019-11-27 2020-05-12 北京三快在线科技有限公司 Resource display method and device, electronic equipment and storage medium
CN112308579A (en) * 2019-07-24 2021-02-02 腾讯科技（深圳）有限公司 Information delivery method and device and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150339728A1 (en) * 2014-05-20 2015-11-26 Pubmatic, Inc. Ad serving and intelligent impression throttling techniques implemented in electronic data networks
CN108229987A (en) * 2016-12-14 2018-06-29 腾讯科技（深圳）有限公司 A kind of advertisement inventory evaluation method and device
CN108694608A (en) * 2018-05-14 2018-10-23 广州至真信息科技有限公司 A kind of ad trafficking system and advertisement method of commerce
CN110009404A (en) * 2019-03-20 2019-07-12 深圳新度博望科技有限公司 Advertisement demonstration method, device, computer equipment and storage medium
CN112308579A (en) * 2019-07-24 2021-02-02 腾讯科技（深圳）有限公司 Information delivery method and device and storage medium
CN111143738A (en) * 2019-11-27 2020-05-12 北京三快在线科技有限公司 Resource display method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
US20210166320A1 (en) System and method for obtaining and/or maintaining insurance coverage
KR102368327B1 (en) Differential reward method and apparatus therefor
US20140358694A1 (en) Social media pricing engine
US20120215652A1 (en) Marketplace for sensor data from mobile devices and its abstractions
US10846743B2 (en) Displaying content items based on user's level of interest in obtaining content
US20150100438A1 (en) Selecting among advertisements competing for a slot associated with electronic content delivered over a network based upon predicted latency
CN110738436A (en) method and device for determining available stock
CN111932314A (en) Method, device and equipment for pushing recommended content and readable storage medium
CN112036945A (en) Incentive method and device based on alliance chain, electronic equipment and storage medium
WO2018003630A1 (en) Message distribution method, information processing device, and recording medium having program recorded therein
JP2017049730A (en) Notification program, notification method and notification system
CN113139826A (en) Method and device for determining distribution authority of advertisement space and computer equipment
CN113487370A (en) Advertisement putting method and device, computer equipment and storage medium
CN110956490A (en) Method and device for improving advertisement putting completion rate
CN114979275A (en) Resource request processing method, electronic device and storage medium
CN115936764A (en) Product promotion method and device
JP2005135209A (en) Distribution processing service mediation system and its method
CN112348612B (en) Order generation method and device
CN114445128A (en) Card ticket management method and device, electronic equipment and computer readable medium
US20130054342A1 (en) Advertising bonus system
CN113971245A (en) Information pushing method, device and system
KR20210118791A (en) The method and program for continual advertisement by friends in online service
US20160104208A1 (en) Ad slot ownership for persistent creatives
CN113378043A (en) User screening method and device
CN113011908A (en) Advertisement space display method and device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination