CN114118446A - Object processing method, device and equipment - Google Patents

Object processing method, device and equipment Download PDF

Info

Publication number
CN114118446A
CN114118446A CN202111467076.1A CN202111467076A CN114118446A CN 114118446 A CN114118446 A CN 114118446A CN 202111467076 A CN202111467076 A CN 202111467076A CN 114118446 A CN114118446 A CN 114118446A
Authority
CN
China
Prior art keywords
determining
objects
participant
allocation information
duration
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
CN202111467076.1A
Other languages
Chinese (zh)
Inventor
张二毛
孙曼
孙超
李鑫
吴磊
谢丹力
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.)
CCB Finetech Co Ltd
Original Assignee
CCB Finetech 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 CCB Finetech Co Ltd filed Critical CCB Finetech Co Ltd
Priority to CN202111467076.1A priority Critical patent/CN114118446A/en
Publication of CN114118446A publication Critical patent/CN114118446A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the application provides an object processing method, device and equipment. The method comprises the following steps: determining a total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning; acquiring object distribution duration and object attenuation in a preset database, wherein the object distribution duration comprises a plurality of unit durations, and the object attenuation is an attenuation proportion of the number of objects distributed to a first participant in two adjacent unit durations; determining a plurality of object allocation information according to the total amount of the target objects, the object allocation duration and the object attenuation, wherein the object allocation information comprises the number of the objects, the object state and the object effective time period; a plurality of object assignment information is sent to the device of the first participant. The flexibility of object allocation is improved.

Description

Object processing method, device and equipment
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to an object processing method, device and equipment.
Background
In most industries, data cannot be simply integrated due to privacy security of the data, and the data exists in an island form. To address the islanding problem of data, a solution is proposed, called federal learning.
In the related art, there are usually a plurality of participants participating in federal learning, and objects for motivation may be allocated to the participants according to their contribution to the federal learning. However, after determining the object to assign to the participant, the object is typically assigned to the participant at once, resulting in less flexibility in object assignment.
Disclosure of Invention
The embodiment of the application provides an object processing method, device and equipment, which are used for improving the flexibility of object allocation.
In a first aspect, an embodiment of the present application provides an object processing method, including:
determining a total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning;
acquiring object distribution duration and object attenuation in a preset database, wherein the object distribution duration comprises a plurality of unit durations, and the object attenuation is an attenuation proportion of the number of objects distributed to the first party in two adjacent unit durations;
determining a plurality of object allocation information according to the total target object amount, the object allocation duration and the object attenuation amount, wherein the object allocation information comprises the object number, the object state and the object effective time period;
in one possible embodiment, determining a total amount of target objects to be allocated to the first participant comprises:
sending object confirmation requests to devices of a plurality of second parties, wherein the object confirmation requests comprise the identification of the first party and the first object total amount, and the second parties are parties of the federal learning;
receiving a plurality of object acknowledgement responses sent by the devices of the plurality of second participants;
and determining the total amount of the target object according to the plurality of object confirmation responses. .
In one possible embodiment, determining the total number of target objects according to the plurality of object confirmation responses includes:
determining a first object confirmation response among the plurality of object confirmation responses, the first object confirmation response indicating an object agreeing to allocate the first object total for the first participant;
and if the number of the first object confirmation responses is greater than or equal to a preset threshold value, determining the total amount of the first objects as the total amount of the target objects.
In one possible embodiment, determining a plurality of object allocation information according to the target total object amount, the object allocation duration and the object attenuation amount includes:
determining the information quantity N of the object allocation information according to the object allocation duration and the unit duration, wherein N is an integer greater than 1;
and determining N pieces of object distribution information according to the total target object amount, the N and the object attenuation amount.
In a possible embodiment, determining N object assignment information according to the total target object amount, the N and the object attenuation amount includes:
determining the number of objects included in the first object allocation information according to the total target object amount, the N and the object attenuation amount;
determining the number of objects in N-1 object allocation information according to the object attenuation amount and the number of objects included in the first object allocation information, wherein N-1 is other object allocation information except the first object allocation information in the N object allocation information;
determining that the object state in the first object allocation information is an available state and determining that the object state in the N-1 object allocation information is an unavailable state;
and determining the effective time period corresponding to each object distribution information according to the object distribution duration and the unit duration.
In a possible implementation manner, determining an effective time period corresponding to each object allocation information according to the object allocation duration and the unit duration includes:
determining an effective time period corresponding to the ith object distribution information as a time period after the ith time, wherein the ith time is the time after i-1 unit time from the current time;
wherein i is an integer greater than or equal to 1 and less than or equal to N.
In one possible embodiment, the method further comprises:
and sending the objects with the number of the target objects and the object distribution information to third-party equipment so that the third-party equipment stores the objects with the number of the target objects, and distributing the objects to the first participant according to the object distribution information.
In a second aspect, an embodiment of the present application provides an object processing apparatus, including: a first determining module, an obtaining module, a second determining module and a sending module, wherein,
the first determining module is used for determining the total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning;
the obtaining module is configured to obtain an object allocation duration and an object attenuation amount in a preset database, where the object allocation duration includes multiple unit durations, and the object attenuation amount is an attenuation ratio of the number of objects allocated to the first participant in two adjacent unit durations;
the second determining module is configured to determine a plurality of object allocation information according to the total target object amount, the object allocation duration, and the object attenuation amount, where the object allocation information includes an object number, an object state, and an object effective period;
the sending module is configured to send the plurality of object allocation information to the device of the first party.
In one possible implementation, the first determining module is configured to:
sending object confirmation requests to devices of a plurality of second parties, wherein the object confirmation requests comprise the identification of the first party and the first object total amount, and the second parties are parties of the federal learning;
receiving a plurality of object acknowledgement responses sent by the devices of the plurality of second participants;
and determining the total amount of the target object according to the plurality of object confirmation responses.
In one possible implementation, the first determining module is configured to:
determining a first object confirmation response among the plurality of object confirmation responses, the first object confirmation response indicating an object agreeing to allocate the first object total for the first participant;
and if the number of the first object confirmation responses is greater than or equal to a preset threshold value, determining the total amount of the first objects as the total amount of the target objects.
In one possible implementation, the second determining module is configured to:
determining the information quantity N of the object allocation information according to the object allocation duration and the unit duration, wherein N is an integer greater than 1;
and determining N pieces of object distribution information according to the total target object amount, the N and the object attenuation amount.
In one possible implementation, the second determining module is configured to:
determining the number of objects included in the first object allocation information according to the total target object amount, the N and the object attenuation amount;
determining the number of objects in N-1 object allocation information according to the object attenuation amount and the number of objects included in the first object allocation information, wherein N-1 is other object allocation information except the first object allocation information in the N object allocation information;
determining that the object state in the first object allocation information is an available state and determining that the object state in the N-1 object allocation information is an unavailable state;
and determining the effective time period corresponding to each object distribution information according to the object distribution duration and the unit duration.
In one possible implementation, the second determining module is configured to:
determining an effective time period corresponding to the ith object distribution information as a time period after the ith time, wherein the ith time is the time after i-1 unit time from the current time;
wherein i is an integer greater than or equal to 1 and less than or equal to N.
In one possible implementation, the sending module is configured to:
and sending the objects with the number of the target objects and the object distribution information to third-party equipment so that the third-party equipment stores the objects with the number of the target objects, and distributing the objects to the first participant according to the object distribution information.
In a third aspect, an embodiment of the present application provides an object processing apparatus, including: a processor and a memory;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory, so that the processor performs the object processing method of any one of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the object processing method according to any one of the first aspect.
In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the object processing method shown in any one of the first aspect.
The object processing method, device and equipment provided by the embodiment of the application comprise the steps that the object processing equipment can determine the total amount of the target objects distributed to a first participant according to the contribution degree of the first participant, and sends an object confirmation request to the equipment of a second participant. The object processing device may receive the object confirmation response sent by the device of the second party, determine the first object response and the total amount of the target objects according to the object confirmation response, and send the number of the objects to the device of the first party in batches according to the object allocation duration and the object attenuation amount until the total amount of the target objects is allocated, thereby improving the flexibility of object allocation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application;
fig. 2 is a schematic flowchart of an object processing method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another object processing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an object processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an object processing apparatus according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present application. Referring to fig. 1, a plurality of participant apparatuses 101 and an object processing apparatus 102 are included. The participant device 101 is a device of a participant in federal learning, and the participant device 101 may train a model using local data and send the trained model parameters to the object processing device 102. The object processing device 102 may receive the model parameters sent by the multiple participant devices 101, aggregate the model parameters, and determine the total amount of the target objects and the object allocation information sent to the participant devices 101 according to the contribution degrees of the participants, so as to allocate the objects to the participant objects according to the object allocation information.
In the related art, there are usually a plurality of participants participating in federal learning, and objects for motivation may be allocated to the participants according to their contribution to the federal learning. However, after determining the object to assign to the participant, the object is typically assigned to the participant at once, resulting in less flexibility in object assignment.
In the embodiment of the application, the object processing device may determine the total amount of the target object allocated to each participant according to the contribution degree of each participant, and allocate the total amount of the target object to the first participant in a plurality of times according to the object allocation duration and the object attenuation amount, so that the flexibility of object allocation is improved.
The technical means shown in the present application will be described in detail below with reference to specific examples. It should be noted that the following embodiments may exist alone or in combination with each other, and description of the same or similar contents is not repeated in different embodiments.
Fig. 2 is a schematic flowchart of an object processing method according to an embodiment of the present application. Referring to fig. 2, the method may include:
s201, the object processing equipment determines the total amount of the target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning.
The execution subject of the embodiment of the present application may be an object processing apparatus, or may be an object processing device provided in the object processing apparatus. The object processing means may be implemented by software, or by a combination of software and hardware. The object processing means may be a processor in the object processing device. For ease of understanding, the following description will be given taking an execution subject as an example of the processing apparatus.
The object processing device is a data processing device, and may be a data processing device of any one of the participants, or may be a data processing device independent of each of the participants. For example, the object processing device may be a data server. If there are 10 participants participating in the federal study, the object processing device may be a data server of the participant 1, or may be a data server independent of 10 participants.
The first participant refers to any one participant that participates in federal learning. For example, if there are 10 different banks participating in federal learning, the first party may be bank 1.
The target object total amount refers to the amount of the award allocated to the first participant. The object processing device may determine a target object total amount for the first participant based on the contribution degree of the first participant. For example, the target object total amount may be points, earnings, and the like established in federal learning, and the object processing apparatus may award 9000 ten thousand points to the first participant according to the degree of contribution of the first participant.
The target total amount may be determined by: sending object confirmation requests to a plurality of devices of second participants, wherein the object confirmation requests comprise the identification of the first participants and the total amount of the first objects, and the second participants are participants of federal learning; receiving a plurality of object acknowledgement responses sent by the devices of the plurality of second participants; and determining the total amount of the target object according to the plurality of object confirmation responses.
The second party refers to the other parties in federal learning except the first party. For example, if there are 10 different banks participating in federal learning, the first participant could be bank 1, and the other 9 banks would be second participants.
The object confirmation request is a confirmation request sent by the object processing device to the device of the second party. The object confirmation request is for confirming the amount of the award to be distributed to the first participant. The object confirmation request may include an identification of the first participant and a first object total. For example, if there are 10 banks participating in federal learning, the first participant may be bank 1, and the first object total may be the bonus points 9000 ten thousand, the object processing device may send an object confirmation request, which may be "bank 1-bonus points 9000 ten thousand", to the remaining 9 banks.
The object confirmation response is response information that the device of the second participant sends to the object processing device. The object confirmation response is used to indicate whether the amount of the award to be allocated to the first participant is agreed upon. The object confirmation response may include information such as whether to agree, an identification of the first participant, and a total amount of the first object. For example, the subject confirmation response may be "agree-bank 1-bonus point 9000 ten thousand" or may be "disagree-bank 1-bonus point 9000 ten thousand".
The object processing device may send object confirmation requests to the devices of the plurality of second participants, receive object confirmation responses sent by the devices of the plurality of second participants, and determine a total amount of the target objects to be allocated to the first participant according to the plurality of object confirmation responses.
The target object total may be determined from the plurality of object confirmation responses by: determining a first object confirmation response among the plurality of object confirmation responses, the first object confirmation response indicating an object for which the first participant is entitled to allocate a first total amount of objects; and if the number of the first object confirmation responses is greater than or equal to a preset threshold value, determining the total amount of the first objects as the total amount of the target objects.
A first portion of the plurality of object validation responses is used to indicate objects for which the first participant is entitled to the first amount of objects, and a second portion of the plurality of object validation responses is used to indicate objects for which the first participant is not entitled to the first amount of objects. The first partial object confirmation response may be determined as the first object confirmation response.
For example, if 10 banks participate in federal study, the bank 1 is a first participant, the remaining 9 banks are second participants, and the object processing device receives object confirmation responses sent by the 9 banks, wherein the object confirmation responses sent by the 7 banks are 'agree-bank 1-reward points 9000 ten thousand', and are the first part of object confirmation responses; the object confirmation responses sent by the 2 banks are "not agree-bank 1-bonus points 9000 ten thousand" and the second part of object confirmation responses. The first part of object confirmation responses may be determined as the first object confirmation responses, the first object confirmation responses may be determined as "consent-bank 1-bonus points 9000 ten thousand", and the total amount of the first objects therein may be determined as 9000 ten thousand.
The preset threshold refers to the minimum number of first object confirmation responses. For example, if 10 banks participate in federal learning, the bank 1 is a first participant, the remaining 9 banks are second participants, the preset threshold may be 2/3 corresponding to the number of the second participants, and the preset threshold may be 6, which means that at least 6 second participants send first object confirmation responses to the object processing device in the federal learning, so that the first object total amount may be determined as the target object total amount.
The object processing apparatus may determine a first object total amount allocated to the first participant according to the plurality of object confirmation responses, and determine the first object total amount as the target object total amount when the number of second participants who transmit the first object confirmation responses is greater than or equal to a preset threshold.
For example, if 10 banks participate in federal learning, the bank 1 is a first participant, the remaining 9 banks are second participants, and the preset threshold is 6. The object processing device receives 9 bank-sent object confirmation responses, wherein 7 bank-sent object confirmation responses are 'agree-bank 1-bonus point 9000 ten thousand' and 2 bank-sent object confirmation responses are 'disagree-bank 1-bonus point 9000 ten thousand'. The object processing device may determine that the first object confirmation responses are "agree-bank 1-bonus points 9000 ten thousand", the number of the first object confirmation responses is 7, which is greater than a preset threshold value, and may determine that the first object total amount is 9000 ten thousand, and confirm 9000 ten thousand as the target object total amount.
S202, the object processing equipment acquires the object distribution duration and the object attenuation amount in a preset database.
The preset database may be a database existing in the object processing apparatus, or may be a database of a server independent from the object processing apparatus. The preset database can store information such as the object allocation duration and the object attenuation amount.
The object allocation duration refers to a time during which the object processing apparatus allocates the total amount of the target object. The object allocation duration may include a plurality of unit durations. For example, the object processing apparatus may allocate a target total amount of objects (9000 ten thousand) continuously for 12 years, where the unit duration is month, and the object allocation duration is 12 years, including 144 months.
The object attenuation amount is an attenuation proportion of the number of objects allocated to the first party for two adjacent unit durations. For example, if the object decay amount is 1.6% of the monthly decay value, i.e., objects allocated per month decay proportionally to 1.6%, and the number of objects allocated to the first participant for the first month is 1596 ten thousand, the number of objects allocated to the first participant for the second month is 1596 × (1-1.6%) ≈ 1571 ten thousand.
The object processing device may obtain the object allocation duration and the object attenuation amount in the allocation for the first participant in the preset database.
S203, the object processing equipment determines a plurality of object distribution information according to the total amount of the target objects, the object distribution duration and the object attenuation amount, wherein the object distribution information comprises the number of the objects, the object state and the object effective time period.
The plurality of object allocation information may be determined by: determining the information quantity N of the object distribution information according to the object distribution duration and the unit duration, wherein N is an integer greater than 1; and determining N pieces of object distribution information according to the total target object amount, N and the object attenuation amount.
The object processing apparatus may determine the information amount N of the object allocation information according to the object allocation duration and the unit duration. For example, if the object allocation duration is 12 years, the unit duration is a month, the object allocation duration 12 years includes 144 months, and allocation is required every month, the information amount of the object allocation information may be determined to be 144.
The N object allocation information may be determined by: determining the number of objects included in the first object allocation information according to the total number of the target objects, N and the object attenuation amount; determining the number of objects in the N-1 object allocation information according to the object attenuation amount and the number of objects included in the first object allocation information, wherein N-1 is other object allocation information except the first object allocation information in the N object allocation information; determining the object state in the first object allocation information as an available state and determining the object state in the N-1 object allocation information as an unavailable state; and determining the effective time period corresponding to each object allocation information according to the object allocation duration and the unit duration.
Specifically, the number of objects included in the first object allocation information may be determined by formula calculation: total target object amount MtotalThe number of objects M in the first object assignment information can be obtained by solving the following formula (1) by the information amount N and the object attenuation amount r of the object assignment informationfirst。
Figure BDA0003388458330000101
For example, if the total target object amount is 9000 ten thousand points, the object allocation duration is 12 years, the information amount N of the object allocation information is 144, and the monthly decrement is 1.6%, the parameters are substituted into the formula (1) to obtain:
Figure BDA0003388458330000102
obtaining the number of objects included in the first object allocation information by solving: 1596 ten thousand.
The object processing apparatus may determine the number of objects in the N-1 object allocation information from the object attenuation amount and the number of objects included in the first object allocation information, and N-1 is other object allocation information than the first object allocation information among the N object allocation information.
Specifically, the number of objects included in the nth object allocation information may be determined by formula calculation: total target object amount MtotalNumber of objects in the object assignment information, N, number of objects in the object assignment information, r, MfirstThen, the number M of objects in the nth object allocation information can be obtained by solving the following formula (2)n。
Mn＝Mfirst*(1-r)n-1..
For example, if the total target object amount is 9000 ten thousand points, the object allocation duration is 12 years, the information amount N of the object allocation information is 144, the monthly decrement amount is 1.6%, the number of objects in the first object allocation information is 1596 ten thousand, and the number of objects in the other 143 object allocation information may be determined. Substituting the parameters into equation (2) yields:
Mn＝1596*(1-1.6％)n-1
the number of objects in each object allocation information can be obtained by calculation, specifically as shown in table 1:
TABLE 1
Object allocation information Number of objects Object state Object validation period
1 st one 1596 Ten thousand Can be used After 1 month
2 nd (a) 1571 million Is not available After month 2
3 rd one 1546 million Is not available After month 3
… … … …
144 th one 160 ten thousand Is not available After 144 months
The object processing apparatus may determine that the object state in the first object allocation information is an available state and determine that the object state in the N-1 object allocation information is an unavailable state. For example, the object processing apparatus may determine that the object state in the 1 st object allocation information is an available state, and the object states in the remaining 143 object allocation information are unavailable states.
The object processing device may determine an effective period corresponding to each object allocation information according to the object allocation duration and the unit duration. For example, if the unit duration is a month, the object processing device may calculate an effective period corresponding to each object allocation information by month.
The object processing device may update the object state according to the effective time period in the object allocation information, and update the corresponding object state to the available state according to the effective time period when the nth object allocation information takes effect according to the effective time period.
The object processing equipment determines that the effective time period corresponding to the ith object distribution information is a time period after the ith time, and the ith time is the time when i-1 unit time length elapses from the current time; wherein i is an integer greater than or equal to 1 and less than or equal to N.
For example, if the unit duration is month, the object processing device determines the effective time period corresponding to the second object allocation information, and the effective time period is a time period after the 2 nd month, and a duration of 1 month elapses from the current time. The object processing apparatus may determine that the effective time period of the first object information is a time period after 2021/10/1, the current time is 2021/10/1, and the time period after 2021/10/1 is referred to as a time period after 1 month, and may determine that the effective time period of the second object allocation information is a time period after 2 months, that is, the effective time period is 1 month long from the current time 2021/10/1 and is a time period after 2021/11/1, and the corresponding object status is updated from 2021/11/1 to a usable status; the validation period and object status of each object allocation information may be confirmed in turn, … …, until the 144 th object allocation information is confirmed to be a period after 2033/10/1, the corresponding object status is updated from 2033/10/1 to a usable status, and so on.
S204, the object processing device sends a plurality of object allocation information to the first participant device.
After determining each object allocation information, the object processing device may send the number of objects of the target object and the object allocation information to the third party device, so that the third party device stores the number of objects of the target object, and allocates the objects to the first participant according to the object allocation information. For example, the object processing device may transmit 1596 ten thousand points and first object allocation information as "number of objects (1596 ten thousand) -object status (available) -object validation period (after first month)" to the third party device.
The object handling device may send all allocation information to the third party device. For example, the object processing device may send 144 object assignment information and a corresponding target object number of objects to the third party device.
The third party device is a device that can store data. For example, the third party device may be a database server.
The third party device receives each object allocation information sent by the object processing device, may store each object allocation information, and allocate the object to the first participant according to the validation period in the object allocation information, for use by the first participant. For example, the third party device may store 1596 ten thousand points and first object allocation information as "number of objects (1596 ten thousand) -object status (available) -object validation period (after the first month)". If the distribution duration of the total amount of the target objects is 12 years and the distribution needs to be performed every month, the number of the target objects is 144. The object processing device may send 144 object quantities and object allocation information to the third party device, and the third party device may store 144 object allocation information and corresponding target object quantities of objects, and allocate the objects to the first participant according to the validation period in the object allocation information, so as to be used by the first participant.
In this embodiment, the object processing device may determine, according to the contribution degree of the first party, a total amount of the target object to be allocated to the first party, and send an object confirmation request to the device of the second party. The object processing device can receive the object confirmation response sent by the device of the second party, determine the first object confirmation response and the total target object amount according to the object confirmation response, and send the total target object amount to the device of the first party in batches according to the object distribution time length and the object attenuation amount, so that the flexibility of object distribution is improved.
In addition to the embodiment shown in fig. 2, the object processing method will be described in further detail below with reference to fig. 3. Fig. 3 is a schematic flowchart of another object processing method according to an embodiment of the present application. Referring to fig. 3, the method may include:
s301, the object processing device sends a plurality of object confirmation requests to a plurality of devices of the second party.
The object processing device may send a plurality of object confirmation requests to the device of the second participant over the wireless network. The object confirmation request may include an identification of the first participant and a first object total. For example, the object confirmation request may be "Bank 1-reward points 9000 ten thousand".
S302, the device of the second participant sends a plurality of object confirmation responses to the object processing device.
The object acknowledgement requests may be received by the devices of the second plurality of participants and an object acknowledgement response may be sent to the object processing device via the wireless network. The object confirmation response may include information such as whether to agree, an identification of the first participant, and a total amount of the first object. For example, the subject confirmation response may be "agree-bank 1-bonus point 9000 ten thousand" or may be "disagree-bank 1-bonus point 9000 ten thousand".
S303, determining a first object confirmation response among the plurality of object confirmation responses.
The first object confirmation response is response information agreeing to allocate the first object amount to the first participant.
The object handling device may determine the first object acknowledgement response from a plurality of object acknowledgement responses sent by the devices of the plurality of second participants.
For example, if 10 banks participate in federal learning, the object confirmation responses sent by the devices of the plurality of second participants may include an agreement-bank 1-bonus point 9000 ten thousand and a disagreement-bank 1-bonus point 9000 ten thousand, and the first object confirmation response may be determined to be "agreement-bank 1-bonus point 9000 ten thousand".
S304, the object processing apparatus confirms whether the number of the first object confirmation responses is greater than or equal to a preset threshold.
If not, updating the object confirmation request, and executing S301;
if yes, S305 is performed.
The preset threshold is a preset threshold referring to a minimum number of first object confirmation responses for representing a minimum number of second participants who have agreed to be the object confirmation request.
If the number of the confirmation responses of the first object is smaller than the preset threshold, which indicates that the number of the second participants agreeing to the object confirmation request is smaller than the preset threshold, S301 is executed, and the object processing device may resend the updated object confirmation request to the device of the second participant. The total amount of the target objects in the object confirmation request can be reduced by a preset value, and the updated object confirmation request is obtained. If the number of confirmation responses of the first object is greater than or equal to the preset threshold, which indicates that the number of second participants agreeing to the object confirmation request is greater than or equal to the preset threshold, S305 is performed.
The preset value is a fixed value used for updating the target total amount, for example, the preset value may be 1000 ten thousand, and if the target total amount is 9000 ten thousand, the target total amount is updated to 8000 ten thousand after the preset value is subtracted.
For example, if 10 banks participate in federal learning, the bank 1 is a first participant, the remaining 9 banks are second participants, the object request information is "bank 1-bonus point 9000 ten thousand", the preset value is 1000 ten thousand, the preset threshold may be 2/3 of the number of the second participants, and the preset threshold may be 6, which means that at least 6 second participants agree to the object confirmation request in the federal learning. If the number of the first object confirmation responses is 2 and is less than the preset threshold 6, it indicates that only 2 second participants agree to the object confirmation request, and the object confirmation request does not pass, the preset value (1000 ten thousand) is subtracted from the total target object amount (9000 ten thousand) to obtain an updated total target object amount of 8000 ten thousand, the updated object request information is determined to be "bank 1-8000 ten thousand bonus points", and the object processing device may transmit the updated object request information to the devices of the plurality of second participants, and perform S301 again. If the number of the first object confirmation responses is 7 and is greater than the preset threshold 6, it indicates that there are 7 second participants who agree with the object confirmation request, and the object confirmation request is passed, then S305 is performed.
S305, the object processing apparatus determines the first object total amount as the target object total amount.
And if the number of the first object confirmation responses is larger than a preset threshold value, determining the total amount of the first objects as the total amount of the target objects. For example, if the first object confirmation response is "bank 1-bonus points 9000 ten thousand", where the first object total amount is 9000 ten thousand, it may be determined that the target object total amount is 9000 ten thousand.
S306, the object processing equipment acquires the object distribution duration and the object attenuation amount in a preset database.
The object processing device can obtain the corresponding object allocation duration and the object attenuation amount in the preset database according to the identification of the participant.
The identification of a participant is used to refer to a unique one of the participants. For example, the identity of the party may be the name, account number, etc. of the party.
For example, the object processing device may obtain the object allocation duration of 12 years and the object attenuation amount of 1.6% in the preset database according to the participant 1.
S307, the object processing equipment determines a plurality of object distribution information according to the total target object amount, the object distribution duration and the object attenuation amount.
The object processing device can determine the number of objects included in the first object allocation information according to the total number of the target objects, the number of object information N, the object allocation duration and the object attenuation amount; and sequentially determining N-1 pieces of object allocation information according to the object attenuation amount and the number of the objects included in the first object allocation information, wherein the number of the corresponding objects, the object attenuation amount, the effective time period, the object state and the like are included.
For example, if the total target object amount is 9000 ten thousand, the object attenuation amount is 1.6%, the object allocation duration is 12 years, and the allocation is performed monthly, the information amount N is 144. The number of objects in the first month may be calculated to be 1596 ten thousand, and the number of objects in the second month may be calculated to be 1571 ten thousand, 1546 ten thousand in the 3 rd month, and the like in turn.
The object processing apparatus may determine that the object state in the first object allocation information is an available state and determine that the object state in the N-1 object allocation information is an unavailable state. For example, if there are 144 pieces of object allocation information, the object processing apparatus may determine that the object state in the 1 st piece of object allocation information is an available state, and the object states in the remaining 143 pieces of object allocation information are unavailable states.
The object processing device may determine an effective period corresponding to each object allocation information according to the object allocation duration and the unit duration. For example, if the unit duration is a month, the object processing device may calculate an effective period corresponding to each object allocation information by month.
S308, the object processing device determines the effective period corresponding to each object allocation information.
The object processing device may determine that an effective time period corresponding to the ith object allocation information is a time period after the ith time, and the ith time is a time that is i-1 unit duration from the current time; wherein i is an integer greater than or equal to 1 and less than or equal to N.
And when the effective time period of the object distribution information takes effect according to time, the corresponding object state is updated to be an available state.
For example, if the unit duration is month, the object processing device determines the effective time period corresponding to the second object allocation information, and the effective time period is a time period after the 2 nd month, and a duration of 1 month elapses from the current time. The object processing apparatus may determine that the validation period of the first object information is a period after 2021/10/1, the current time is 2021/10/1, and the period after 2021/10/1 is referred to as a period after 1 month, and may determine that the validation period of the second object allocation information is a period after 2 months, that is, the duration of 1 month elapses since the current time 2021/10/1, and the period after 2021/11/1, and update the object state of the first object information from 2021/11/1 to the available state; the validation period of each object allocation information may be sequentially confirmed, … …, until the 144 th object allocation information is confirmed to be a period after 2033/10/1, the object status of the first object information is updated from 2033/10/1 to a usable status.
S309, the object processing device sends a plurality of object allocation information to the third-party device.
After the object processing device determines each object allocation information, the object processing device may send the number of objects of the target object and the object allocation information to the third party device through the wireless network, so that the third party device stores the number of objects of the target object. For example, the object processing device may transmit the first object assignment information as "object decrement (1.6%) -object validation period (after the first month) -object status (available)" and the corresponding number of objects to the third party device is 1596 ten thousand. If the distribution duration of the total amount of the target objects is 12 years and the distribution needs to be performed every month, the number of the target objects is 144. The object handling device may send 144 object assignment information and the corresponding target object number objects to the third party device.
S310, the third-party device sends object distribution information to the first participant device.
The third party device receives each object allocation information sent by the object processing device, may store each object allocation information, and allocate the object to the first participant according to the validation period in the object allocation information, for use by the first participant. For example, the third party device may store 1596 ten thousand points and first object allocation information as "number of objects (1596 ten thousand) -object status (available) -object validation period (after the first month)". . If the distribution duration of the total amount of the target objects is 12 years, the distribution needs to be performed every month, the third-party device may store 144 object distribution information and the corresponding target object number objects sent by the object processing device, and distribute the objects to the first participant according to the effective time period in the object distribution information, so as to be used by the first participant.
In this embodiment, the object processing device may determine, according to the contribution degree of the first party, a total amount of the target object allocated to the first party, and send an object confirmation request to the device of the second party. The object processing device may receive the object confirmation response sent by the device of the second party, determine the first object response and the total amount of the target objects according to the object confirmation response, and send the number of the objects to the device of the first party in batches according to the object allocation duration and the object attenuation amount until the total amount of the target objects is allocated, thereby improving the flexibility of object allocation.
Fig. 4 is a schematic structural diagram of an object processing apparatus according to an embodiment of the present application, please refer to fig. 4, where the object processing apparatus 10 may include: a first determining module 11, an obtaining module 12, a second determining module 13 and a sending module 14, wherein,
the first determining module is used for determining the total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning;
the obtaining module is configured to obtain an object allocation duration and an object attenuation amount in a preset database, where the object allocation duration includes multiple unit durations, and the object attenuation amount is an attenuation ratio of the number of objects allocated to the first participant in two adjacent unit durations;
the second determining module is configured to determine a plurality of object allocation information according to the total target object amount, the object allocation duration, and the object attenuation amount, where the object allocation information includes an object number, an object state, and an object effective period;
the sending module is configured to send the plurality of object allocation information to the device of the first party.
The object processing apparatus provided in the embodiment of the present application may execute the technical solutions shown in the foregoing method embodiments, and the implementation principles and beneficial effects thereof are similar and will not be described herein again.
In a possible implementation, the first determining module 11 is specifically configured to:
sending object confirmation requests to devices of a plurality of second parties, wherein the object confirmation requests comprise the identification of the first party and the first object total amount, and the second parties are parties of the federal learning;
receiving a plurality of object acknowledgement responses sent by the devices of the plurality of second participants;
and determining the total amount of the target object according to the plurality of object confirmation responses.
In a possible implementation, the first determining module 11 is specifically configured to:
determining a first object confirmation response among the plurality of object confirmation responses, the first object confirmation response indicating an object agreeing to allocate the first object total for the first participant;
and if the number of the first object confirmation responses is greater than or equal to a preset threshold value, determining the total amount of the first objects as the total amount of the target objects.
In a possible implementation manner, the second determining module 13 is specifically configured to:
determining the information quantity N of the object allocation information according to the object allocation duration and the unit duration, wherein N is an integer greater than 1;
and determining N pieces of object distribution information according to the total target object amount, the N and the object attenuation amount.
In a possible implementation manner, the second determining module 13 is specifically configured to:
determining the number of objects included in the first object allocation information according to the total target object amount, the N and the object attenuation amount;
determining the number of objects in N-1 object allocation information according to the object attenuation amount and the number of objects included in the first object allocation information, wherein N-1 is other object allocation information except the first object allocation information in the N object allocation information;
determining that the object state in the first object allocation information is an available state and determining that the object state in the N-1 object allocation information is an unavailable state;
and determining the effective time period corresponding to each object distribution information according to the object distribution duration and the unit duration.
In a possible implementation manner, the second determining module 13 is specifically configured to:
determining an effective time period corresponding to the ith object distribution information as a time period after the ith time, wherein the ith time is the time after i-1 unit time from the current time;
wherein i is an integer greater than or equal to 1 and less than or equal to N.
In a possible implementation, the sending module 14 is specifically configured to:
and sending the objects with the number of the target objects and the object distribution information to third-party equipment so that the third-party equipment stores the objects with the number of the target objects, and distributing the objects to the first participant according to the object distribution information.
The object processing apparatus provided in the embodiment of the present application may execute the technical solutions shown in the foregoing method embodiments, and the implementation principles and beneficial effects thereof are similar and will not be described herein again.
Referring to fig. 5, the object processing apparatus 20 may include a processor 21 and a memory 22. The processor 21, the memory 22, and the various parts are illustratively interconnected by a bus 23.
The memory 22 stores computer-executable instructions;
the processor 21 executes computer-executable instructions stored by the memory 22 to cause the processor 21 to perform the object processing method as shown in the above-described method embodiments.
All or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The aforementioned program may be stored in a readable memory. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state disk, magnetic tape (magnetic tape), floppy disk (flexible disk), optical disk (optical disk), and any combination thereof.
The embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the object processing method according to the above-mentioned method embodiment.
The present application may further provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the object processing method shown in the foregoing method embodiments may be implemented.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to encompass such modifications and variations.
In the present application, the terms "include" and variations thereof may refer to non-limiting inclusions; the term "or" and variations thereof may mean "and/or". The terms "first," "second," and the like in this application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. In the present application, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Claims (10)

1. An object processing method, comprising:
determining a total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning;
acquiring object distribution duration and object attenuation in a preset database, wherein the object distribution duration comprises a plurality of unit durations, and the object attenuation is an attenuation proportion of the number of objects distributed to the first party in two adjacent unit durations;
determining a plurality of object allocation information according to the total target object amount, the object allocation duration and the object attenuation amount, wherein the object allocation information comprises the object number, the object state and the object effective time period;
sending the plurality of object assignment information to the first participant's device.
2. The method of claim 1, wherein determining a total amount of target objects to be allocated to the first participant comprises:
sending object confirmation requests to devices of a plurality of second parties, wherein the object confirmation requests comprise the identification of the first party and a first object total amount, and the second parties are parties of the federal learning;
receiving a plurality of object acknowledgement responses sent by the devices of the plurality of second participants;
and determining the total amount of the target object according to the plurality of object confirmation responses.
3. The method of claim 2, wherein determining the total number of target objects based on the plurality of object confirmation responses comprises:
determining a first object confirmation response among the plurality of object confirmation responses, the first object confirmation response indicating an object agreeing to allocate the first object total for the first participant;
and if the number of the first object confirmation responses is greater than or equal to a preset threshold value, determining the total amount of the first objects as the total amount of the target objects.
4. The method of any one of claims 1-3, wherein determining a plurality of object assignment information based on the total target object amount, the object assignment duration, and the object attenuation amount comprises:
determining the information quantity N of the object allocation information according to the object allocation duration and the unit duration, wherein N is an integer greater than 1;
and determining N pieces of object distribution information according to the total target object amount, the N and the object attenuation amount.
5. The method of claim 4, wherein determining N object assignment information based on the total number of target objects, the N, and the object attenuation amount comprises:
determining the number of objects included in the first object allocation information according to the total target object amount, the N and the object attenuation amount;
determining the number of objects in N-1 object allocation information according to the object attenuation amount and the number of objects included in the first object allocation information, wherein N-1 is other object allocation information except the first object allocation information in the N object allocation information;
determining that the object state in the first object allocation information is an available state and determining that the object state in the N-1 object allocation information is an unavailable state;
and determining the effective time period corresponding to each object distribution information according to the object distribution duration and the unit duration.
6. The method of claim 5, wherein determining the effective time period corresponding to each object allocation message according to the object allocation duration and the unit duration comprises:
determining an effective time period corresponding to the ith object distribution information as a time period after the ith time, wherein the ith time is the time after i-1 unit time from the current time;
wherein i is an integer greater than or equal to 1 and less than or equal to N.
7. The method according to any one of claims 1-6, further comprising:
and sending the objects with the number of the target objects and the object distribution information to third-party equipment so that the third-party equipment stores the objects with the number of the target objects, and distributing the objects to the first participant according to the object distribution information.
8. An object processing apparatus, comprising: a first determining module, an obtaining module, a second determining module and a sending module, wherein,
the first determining module is used for determining the total amount of target objects to be distributed to a first participant, wherein the first participant is a participant of federal learning;
the obtaining module is configured to obtain an object allocation duration and an object attenuation amount in a preset database, where the object allocation duration includes multiple unit durations, and the object attenuation amount is an attenuation ratio of the number of objects allocated to the first participant in two adjacent unit durations;
the second determining module is configured to determine a plurality of object allocation information according to the total target object amount, the object allocation duration, and the object attenuation amount, where the object allocation information includes an object number, an object state, and an object effective period;
the sending module is configured to send the plurality of object allocation information to the device of the first party.
9. An object processing apparatus, characterized by comprising: a processor and a memory;
the memory stores computer-executable instructions;
the processor executing the computer-executable instructions stored by the memory causes the processor to perform the object processing method of any one of claims 1 to 7.
10. A computer-readable storage medium having stored therein computer-executable instructions for implementing the object processing method of any one of claims 1 to 7 when executed by a processor.
CN202111467076.1A 2021-12-02 2021-12-02 Object processing method, device and equipment Pending CN114118446A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111467076.1A CN114118446A (en) 2021-12-02 2021-12-02 Object processing method, device and equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111467076.1A CN114118446A (en) 2021-12-02 2021-12-02 Object processing method, device and equipment

Publications (1)

Publication Number Publication Date
CN114118446A true CN114118446A (en) 2022-03-01

Family

ID=80366146

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111467076.1A Pending CN114118446A (en) 2021-12-02 2021-12-02 Object processing method, device and equipment

Country Status (1)

Country Link
CN (1) CN114118446A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106096924A (en) * 2016-06-21 2016-11-09 阿里巴巴集团控股有限公司 object distribution method and device
CN111950739A (en) * 2020-08-13 2020-11-17 深圳前海微众银行股份有限公司 Data processing method, device, equipment and medium based on block chain
WO2021115480A1 (en) * 2020-06-30 2021-06-17 平安科技（深圳）有限公司 Federated learning method, device, equipment, and storage medium
CN113344610A (en) * 2021-05-18 2021-09-03 网易（杭州）网络有限公司 Block chain-based virtual object allocation method, device and readable storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106096924A (en) * 2016-06-21 2016-11-09 阿里巴巴集团控股有限公司 object distribution method and device
WO2021115480A1 (en) * 2020-06-30 2021-06-17 平安科技（深圳）有限公司 Federated learning method, device, equipment, and storage medium
CN111950739A (en) * 2020-08-13 2020-11-17 深圳前海微众银行股份有限公司 Data processing method, device, equipment and medium based on block chain
CN113344610A (en) * 2021-05-18 2021-09-03 网易（杭州）网络有限公司 Block chain-based virtual object allocation method, device and readable storage medium

Similar Documents

Publication Publication Date Title
CN110837410B (en) Task scheduling method and device, electronic equipment and computer readable storage medium
Condorelli What money canʼt buy: Efficient mechanism design with costly signals
Halevy et al. “In‐group love” and “out‐group hate” in repeated interaction between groups
Dai et al. A predictive headway-based bus-holding strategy with dynamic control point selection: A cooperative game theory approach
CN110020888A (en) The sharing method and device of goal task
CN108416615B (en) Resource allocation method based on tree
CN106649638B (en) Big data acquisition method
CN111080126A (en) Task allocation method and device
CN109544015A (en) A kind of method for allocating tasks and relevant device based on data processing
CN108279980A (en) Resource allocation methods and system and resource allocation terminal
CN108241970B (en) Mining method and device based on block chain and computer readable storage medium
US10901801B2 (en) Distributed monitoring of network computers for dynamically updating assignments of tasks
CN114118446A (en) Object processing method, device and equipment
CN112200444B (en) Service distribution method, device, equipment and storage medium
CN113743979A (en) Virtual resource allocation method and device, computer equipment and storage medium
Cabrales et al. Can there be a market for cheap-talk information? An experimental investigation
Pereyra et al. Optimal assignment mechanisms with imperfect verification
Landeo et al. Shotgun mechanisms for common-value partnerships: The unassigned-offeror problem
CN111369270B (en) Method, device and system for distributing rewarding resources
CN116629556A (en) Recommendation task distribution method and device, storage medium and electronic equipment
CN108337263B (en) Sybil attack prevention incentive method based on mobile crowd sensing system
CN115169797A (en) Working dog calling method and related device
CN113763026A (en) Method and device for testing information delivery strategy
CN114710411A (en) Bandwidth allocation method, device, gateway and storage medium
CN109284634B (en) Block chain node and product information acquisition method and device

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