CN113393259B - Advertisement scheduling method, system, device and storage medium - Google Patents
Advertisement scheduling method, system, device and storage medium Download PDFInfo
- Publication number
- CN113393259B CN113393259B CN202110506337.XA CN202110506337A CN113393259B CN 113393259 B CN113393259 B CN 113393259B CN 202110506337 A CN202110506337 A CN 202110506337A CN 113393259 B CN113393259 B CN 113393259B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- candidate
- scheme
- configuration
- target
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
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
- G06Q30/0272—Period of advertisement exposure
-
- 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
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
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 invention provides a method, a system, a device and a storage medium for advertisement scheduling, wherein the method comprises the following steps: acquiring a configuration instruction, and determining a configuration condition according to the configuration instruction; filtering the first candidate advertisement position according to the configuration condition, and sequencing the filtered result to obtain an advertisement position list; generating a candidate scheme by beam searching according to a first target condition in the configuration conditions; the candidate scheme is obtained by combining a plurality of first advertisement positions; determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme; the time consumption of the first section beam search of the method is controllable; the second section of search achieves the purpose of reducing search time, and time consumption can be controlled in a certain interval range; the method provides an advertisement scheduling scheme meeting various limiting conditions under the condition of extremely large data volume, and can be widely applied to the technical field of advertisement scheduling.
Description
Technical Field
The invention relates to the technical field of advertisement scheduling, in particular to a method, a system and a storage medium for advertisement scheduling.
Background
In the prior art advertising process, as a media party, numerous ad spots need to be provided to advertisers to deliver advertisements. Depending on the amount of the advertiser's impression charge and other impression conditions, it may be desirable to select an appropriate ad spot combination scheme from a plurality of ad spots, including the selection of ad spots and the date selection of each ad spot, hereinafter referred to as an ad scheduling scheme. By automatically generating the advertisement scheduling scheme to replace a manual scheme, the manpower can be released, and the scheme generation time can be shortened.
However, the prior art advertisement scheduling schemes still suffer from two problems:
1. the number of advertisement sites is large, the selectable date range of each advertisement site is wide, and the number of schemes which can be combined is very large.
2. Each advertisement delivery has a plurality of limiting conditions, such as a delivery amount interval limit, a date range limit, an advertisement space occupation ratio limit of a certain attribute and the like.
Disclosure of Invention
In view of the foregoing, an object of an embodiment of the present invention is to provide a method for intelligent advertisement scheduling under the condition of large data size and complex constraint conditions, and a system, a device and a computer readable storage medium capable of correspondingly implementing the method.
In a first aspect, the present invention provides a method for advertisement scheduling, the method comprising the steps of:
acquiring a configuration instruction, and determining a configuration condition according to the configuration instruction;
filtering the first candidate advertisement position according to the configuration condition, and sequencing the filtered result to obtain an advertisement position list;
generating a candidate scheme through beam searching according to a first target condition in the configuration conditions; the candidate scheme is obtained by combining a plurality of first advertisement spots;
and determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions, and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme.
In some alternative embodiments, the method of advertisement scheduling further comprises the steps of:
determining advertisement attributes in the target advertisement scheduling scheme according to the configuration instruction, and performing secondary filtering on the first candidate advertisement position according to the advertisement attributes;
the advertisement attributes include advertisement type and advertisement location.
In some alternative embodiments, the step of generating the candidate solution by beam search according to a first target condition of the configuration conditions includes:
constructing a first search tree according to the advertisement space list, wherein leaf nodes of the first search tree are the first candidate advertisement spaces;
traversing the first search tree layer by layer, and selecting the leaf nodes;
and determining a path from the leaf node to the root node, and determining a candidate scheme according to the leaf node contained in the path.
In some alternative embodiments, the step of generating the candidate solution by beam search according to a first target condition of the configuration conditions further comprises:
acquiring the first target condition, and screening the candidate schemes according to the first target condition;
and selecting the candidate scheme with the minimum distance weighted sum from the screening result according to the distance weighted sum of the first target condition of the candidate scheme.
In some alternative embodiments, the step of determining a second ad spot by depth-first search and adding the second ad spot to the candidate solution according to a second target condition in the configuration conditions, generating a target ad scheduling solution, includes:
constructing a second search tree according to the candidate scheme, wherein leaf nodes of the second search tree are selectable days of the advertisement space;
starting from a root node of the second search tree, determining a node path, wherein the node path comprises a plurality of leaf nodes meeting a second target condition;
and generating the target advertisement scheduling scheme according to the node path.
In a second aspect, the present invention further provides a system for advertisement scheduling, including:
the configuration acquisition unit is used for acquiring a configuration instruction and determining a configuration condition according to the configuration instruction;
the primary screening unit is used for filtering the first candidate advertisement positions according to the configuration conditions and sequencing the filtered results to obtain an advertisement position list;
a scheme generating unit configured to generate a candidate scheme by beam search according to a first target condition among the configuration conditions; the candidate scheme is obtained by combining a plurality of first advertisement spots; and determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions, and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme.
In a third aspect, the present invention further provides an advertisement scheduling apparatus, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to perform a method of advertisement scheduling in the first aspect.
In a fourth aspect, the present invention provides a storage medium having stored therein a processor executable program which when executed by a processor is for running the method of the first aspect.
Advantages and benefits of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention:
according to the technical scheme, through a two-section searching mode, the first section searching adopts beam searching, the advertisement position combinations of the obtained candidate schemes are various, and the possibility of the situation that the advertisement position combinations are identical in different schemes is low; the time consumption of the first section of beam search is controllable and is far smaller than that of breadth-first search; and each round of searching of the beam search is carried out to obtain an optimal scheme according to the limiting conditions, the limiting conditions are used for screening suitable candidate schemes, the searching is carried out in a targeted mode, and the probability that the scheme obtained by searching meets the limiting conditions is improved. The second section of search limits the depth-first search of adding the number of advertisement positions, achieves the aim of reducing search time, can control time consumption within a certain interval range, and can provide advertisement scheduling schemes meeting various limiting conditions under the condition of extremely large data quantity.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating steps of an advertisement scheduling method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a first search tree according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a second search tree according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
Firstly, explanation is made on technical nouns related to the technical scheme of the application:
the advertisement space in the technical scheme refers to the position on line or off line for carrying advertisements in the forms of pictures, text chains and the like.
In a first aspect, as shown in fig. 1, the technical solution of the present application provides an embodiment of a method for advertisement scheduling, where the method includes steps S100-S400:
s100, acquiring a configuration instruction, and determining a configuration condition according to the configuration instruction;
the configuration instruction refers to configuration operation of the user on advertisement scheduling through user interaction interfaces of various terminal devices; after receiving the configuration instruction, the background in the embodiment analyzes the configuration instruction and extracts the configuration condition from the configuration instruction, for example, the configuration condition obtained by analyzing a certain configuration instruction of a user is: the amount of the put-in is 100 ten thousand, and the put-in amount is 1000 in an up-and-down floating way; the date ranges from 2021, 3, 1 to 2021, 3, 31, and no holiday is put in.
S200, filtering the first candidate advertisement space according to the configuration conditions, and sequencing the filtered result to obtain an advertisement space list;
the first candidate advertisement positions refer to all advertisement positions which can be used for advertisement delivery under the condition that the condition is not limited; the ad spot list is a number of selectable ad spots remaining after conditional screening according to configuration conditions. Specifically, according to the configuration conditions obtained by analyzing in step S100, all advertisement positions that can be put in are primarily screened, wherein the screening process can be to screen according to attribute entries of the configuration conditions, and advertisement positions in which the same attribute entries or records corresponding to the attribute entries are obviously not provided in the advertisement positions are deleted are removed; for example, the configuration condition is that the put amount is 100 ten thousand yuan, and the put amount floats up and down by 1000 yuan; the date ranges from 2021, 3, 1, to 2021, 3, 31; if the advertisement space with the missing deliverable date attribute value exists in the advertisement space, the advertisement space is removed in the preliminary screening process.
S300, generating a candidate scheme through beam searching according to a first target condition in the configuration conditions;
the candidate scheme is obtained by combining a plurality of first advertisement positions; the first target condition may be one of the configuration conditions, such as: the amount of the advertisement space; in the embodiment, the beam search, the similarity breadth first search is also traversed by layers, but all nodes of the layers are not reserved, part of the nodes and the sub-nodes thereof are removed according to rules, and the removed nodes and the sub-nodes thereof are not accessed any more. Specifically, the first target condition is selected as the amount of the advertisement slot, step S300 is a first search stage of this embodiment, and according to the configuration condition set by the user, the embodiment sets a target amount close to the amount of the advertisement slot, where the target amount is the amount of the advertisement slot in the configuration condition, and the range of the amount is a floating interval of the amount of the advertisement slot unit price x the sum of the days selected in the advertisement scheduling scheme; n candidate schemes are obtained by adopting a beam searching mode, and the N candidate schemes are formed by combining different advertisement positions. It should be noted that the beam search is not an improvement of the technical solution of the present application, and thus is not described herein.
S400, determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions, and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme;
wherein the second target condition is another constraint condition in the configuration condition that is different from the first target condition, for example, all contents of the configuration condition may be regarded as the second target condition in the embodiment; in the embodiment, the depth-first search starts from the root node, then accesses an unaccessed child node of the node, accesses an unaccessed child node of the child node, and obtains a path from the root node to the leaf node until the leaf node. Then, the next non-accessed neighbor node is found by rollback from the leaf node, and the path from the other root node to the leaf node is obtained again. Specifically, selecting a second target condition as an example of days on which advertisements are put, entering a first search stage according to candidate schemes provided by the first search stage, and adding advertisement positions, for example, not more than 5, to the candidate schemes in a depth-first search mode; and selecting proper days of dates so that the scheme meets all configuration conditions to obtain the target advertisement scheduling scheme.
In some alternative embodiments, the method of advertisement scheduling further includes step S500:
s500, determining advertisement attributes in a target advertisement scheduling scheme according to the configuration instruction, and performing secondary filtering on the first candidate advertisement position according to the advertisement attributes;
wherein the advertisement attribute comprises advertisement type and advertisement position; the secondary filtering is to screen out advertisement positions which cannot meet the requirements of the corresponding attributes according to the attributes of the advertisements; in the embodiment of the application, besides the configuration conditions set by the user, various attributes, such as text chains, pictures, and columns, can be included; the location is for example on a first screen, a second screen, etc. of the page. The embodiment of the application comprises complete configuration conditions of attributes, taking advertisement putting A as an example, wherein the configuration conditions are that the putting amount is 100 ten thousand yuan and 1000 yuan is floated up and down. The date ranges from 2021, 3, 1, to 2021, 3, 31, and no holiday is put in; the advertisement attribute is that the picture type accounts for 50% and the text chain accounts for 50%; the first screen is 60%.
In some alternative embodiments, the step S300 of generating the candidate solution by beam search according to the first target condition in the configuration conditions may include steps S310-S330:
s310, constructing a first search tree according to the advertisement position list;
s320, traversing the first search tree layer by layer, and selecting leaf nodes;
s330, determining a path from the leaf node to the root node, and determining a candidate scheme according to the leaf node contained in the path;
wherein the leaf node of the first search tree is a first candidate advertisement space; the first search tree is constructed according to the ordered advertisement position list to obtain a search tree. Specifically, a target amount of money is first set:
target＝final-min(maxGap,midPrice*maxDays*5)
final is the total impression of the constraint, midPrice is the median of the ad spot price, maxDays is the maximum number of days selectable for the ad spot, maxGap is the maximum value of the difference between the set impression and the target amount, and 5 is the maximum number of added ad spots in the second search constraint. Then, constructing a search tree according to the ordered advertisement position list as shown in fig. 2; ad slots that are ranked behind an ad slot are all child nodes of the ad slot. And finally, performing beam searching, traversing the search tree according to layers, taking N nodes at each layer, removing the rest nodes and child nodes of the layer, and traversing the next layer until all the nodes are accessed. All ad slots on the path from each leaf node to the root node remaining in the tree constitute a candidate, and the date days of the ad slots select the largest selectable number of days.
In some alternative embodiments, the step S300 of generating the candidate solution by beam search according to the first target condition in the configuration conditions further includes a step S340:
s340, acquiring a first target condition, and screening candidate schemes according to the first target condition; selecting a candidate solution with the smallest distance weighted sum from the screening result according to the distance weighted sum of the first target conditions of the candidate solution;
specifically, in the technical scheme, in the process of searching a bundle, N nodes are taken at each layer of a search tree, all advertisement positions on a path from each node to a root node of the layer form a candidate scheme, and the date days of the advertisement positions select the largest selectable days. Two values are calculated for each candidate: the number of the limit conditions is satisfied, and the gap weighted sum of the limit conditions is not satisfied. And preferentially taking candidate schemes with more satisfied conditions, and preferentially taking candidate schemes with small difference weights if the satisfied conditions are the same. And judging whether the total sum of each candidate scheme is larger than the target sum, and outputting the candidate scheme of which the total sum is smaller than the target sum.
In some possible embodiments, the step S400 of determining a second advertisement slot by depth-first search and adding to the candidate solution according to a second target condition in the configuration conditions, and generating a target advertisement scheduling solution may include steps S410-S430:
s410, constructing a second search tree according to the candidate scheme, wherein leaf nodes of the second search tree are selected days of the advertisement space;
s420, starting from a root node of a second search tree, determining a node path, wherein the node path comprises a plurality of leaf nodes meeting a second target condition;
s430, generating a target advertisement scheduling scheme according to the node path;
wherein each layer of nodes of the second search tree is the optional days of the advertisement space in the candidate scheme; specifically, according to step S300, an advertisement space in the candidate solution is obtained, and an advertisement space search tree is constructed, as shown in fig. 3, each layer of the tree corresponds to an advertisement space, and each layer of nodes is a selectable number of days of the advertisement space; then, performing depth-first search, starting access from the root node, then accessing an unaccessed child node of the node, and then accessing an unaccessed child node of the child node until the number of advertisement slots with date days greater than 1 on leaf nodes or paths reaches 5, wherein advertisement slots on the paths and date days thereof form an advertisement scheduling scheme. Then the next neighbor node which is not accessed is found by rollback, and another advertisement scheduling scheme is obtained again. Judging whether each advertisement scheduling scheme meets the second target condition, and outputting the advertisement scheduling scheme meeting the second target condition as a final advertisement scheduling scheme.
In a second aspect, the present application provides a system for implementing an advertisement scheduling for a method of the first aspect, comprising:
the configuration acquisition unit is used for acquiring a configuration instruction and determining a configuration condition according to the configuration instruction;
the primary screening unit is used for filtering the first candidate advertisement positions according to the configuration conditions and sequencing the filtered results to obtain an advertisement position list;
a scheme generating unit for generating a candidate scheme by beam search according to a first target condition among the configuration conditions; the candidate scheme is obtained by combining a plurality of first advertisement positions; and determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme.
In a third aspect, the present application further provides an apparatus for advertisement scheduling, including at least one processor; at least one memory for storing at least one program; the at least one program, when executed by the at least one processor, causes the at least one processor to perform a method of advertisement scheduling as in the first aspect.
The embodiment of the invention also provides a storage medium storing a program, and the program is executed by a processor to implement the method as in the first aspect.
From the above specific implementation process, it can be summarized that, compared with the prior art, the technical solution provided by the present invention has the following advantages or advantages:
1. the first search of the technical scheme adopts beam search, the advertisement space combinations of the obtained candidate schemes are various, and the possibility of the situation that the advertisement space combinations are identical in different schemes is low. The time consumption of a beam search is controllable and much smaller than breadth-first searches. Each round of searching of the bundle searching is used for taking the optimal candidate advertisement position according to the limiting condition, which is equivalent to screening a proper candidate scheme by using the limiting condition, searching is performed in a targeted manner, and the probability that the scheme obtained by searching meets the limiting condition is improved.
2. According to the second-stage search of the technical scheme, the depth-first search of adding the number of the advertisement positions is limited, the number of the advertisement positions is limited to be equivalent to pruning the tree, and the purpose of reducing search time is achieved. By setting the maximum search times to stop searching in advance, the time consumption can be controlled within a certain interval range.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present invention, and these equivalent modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (5)
1. A method of advertisement scheduling, comprising the steps of:
acquiring a configuration instruction, and determining a configuration condition according to the configuration instruction;
filtering the first candidate advertisement position according to the configuration condition, and sequencing the filtered result to obtain an advertisement position list;
generating a candidate scheme through beam search according to a first target condition in the configuration conditions, wherein the candidate scheme is obtained by combining a plurality of first advertisement spots;
determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme;
wherein the step of generating a candidate solution by beam search according to a first target condition among the configuration conditions includes: constructing a first search tree according to the advertisement space list, wherein leaf nodes of the first search tree are the first candidate advertisement spaces; traversing the first search tree layer by layer, and selecting the leaf nodes; determining a path from the leaf node to a root node, and determining a candidate scheme according to the leaf node contained in the path;
the step of generating a candidate solution by beam search according to a first target condition of the configuration conditions further comprises: acquiring the first target condition, and screening the candidate schemes according to the first target condition; selecting the candidate scheme with the minimum distance weighted sum from the screening result according to the distance weighted sum of the first target conditions of the candidate scheme;
wherein the step of determining a second advertisement position by depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position to the candidate solution to generate a target advertisement scheduling solution comprises the following steps: constructing a second search tree according to the candidate scheme, wherein leaf nodes of the second search tree are selectable days of the advertisement space; starting from a root node of the second search tree, determining a node path, wherein the node path comprises a plurality of leaf nodes meeting a second target condition; and generating the target advertisement scheduling scheme according to the node path.
2. The method of advertising scheduling according to claim 1, wherein the method of advertising scheduling further comprises the steps of:
determining advertisement attributes in the target advertisement scheduling scheme according to the configuration instruction, and performing secondary filtering on the first candidate advertisement position according to the advertisement attributes;
the advertisement attributes include advertisement type and advertisement location.
3. A system for advertisement scheduling, comprising:
the configuration acquisition unit is used for acquiring a configuration instruction and determining a configuration condition according to the configuration instruction;
the primary screening unit is used for filtering the first candidate advertisement positions according to the configuration conditions and sequencing the filtered results to obtain an advertisement position list;
a scheme generating unit configured to generate a candidate scheme by beam search according to a first target condition among the configuration conditions; the candidate scheme is obtained by combining a plurality of first advertisement positions;
determining a second advertisement position through depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position into the candidate scheme to generate a target advertisement scheduling scheme;
wherein the step of generating a candidate solution by beam search according to a first target condition among the configuration conditions includes: constructing a first search tree according to the advertisement space list, wherein leaf nodes of the first search tree are the first candidate advertisement spaces; traversing the first search tree layer by layer, and selecting the leaf nodes; determining a path from the leaf node to a root node, and determining a candidate scheme according to the leaf node contained in the path;
the step of generating a candidate solution by beam search according to a first target condition of the configuration conditions further comprises: acquiring the first target condition, and screening the candidate schemes according to the first target condition; selecting the candidate scheme with the minimum distance weighted sum from the screening result according to the distance weighted sum of the first target conditions of the candidate scheme;
wherein the step of determining a second advertisement position by depth-first search according to a second target condition in the configuration conditions and adding the second advertisement position to the candidate solution to generate a target advertisement scheduling solution comprises the following steps: constructing a second search tree according to the candidate scheme, wherein leaf nodes of the second search tree are selectable days of the advertisement space; starting from a root node of the second search tree, determining a node path, wherein the node path comprises a plurality of leaf nodes meeting a second target condition; and generating the target advertisement scheduling scheme according to the node path.
4. An apparatus for advertisement scheduling, comprising:
at least one processor;
at least one memory for storing at least one program;
the method of advertisement scheduling of any of claims 1-2 when said at least one program is executed by said at least one processor.
5. A storage medium having stored therein a processor executable program which when executed by a processor is for running a method of advertisement scheduling according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506337.XA CN113393259B (en) | 2021-05-10 | 2021-05-10 | Advertisement scheduling method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110506337.XA CN113393259B (en) | 2021-05-10 | 2021-05-10 | Advertisement scheduling method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113393259A CN113393259A (en) | 2021-09-14 |
| CN113393259B true CN113393259B (en) | 2024-03-29 |
Family
ID=77616789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110506337.XA Active CN113393259B (en) | 2021-05-10 | 2021-05-10 | Advertisement scheduling method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393259B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514561A (en) * | 2013-10-21 | 2014-01-15 | 东莞市东信网络技术有限公司 | Advertisement scheduling management method and system |
| CN110135903A (en) * | 2019-05-10 | 2019-08-16 | 重庆八戒电子商务有限公司 | Advertisement position ranks method, system, medium and electronic equipment |
| CN112767039A (en) * | 2021-01-26 | 2021-05-07 | 深圳市易售科技有限公司 | Method, device, equipment and medium for generating advertising machine delivery order |
-
2021
- 2021-05-10 CN CN202110506337.XA patent/CN113393259B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514561A (en) * | 2013-10-21 | 2014-01-15 | 东莞市东信网络技术有限公司 | Advertisement scheduling management method and system |
| CN110135903A (en) * | 2019-05-10 | 2019-08-16 | 重庆八戒电子商务有限公司 | Advertisement position ranks method, system, medium and electronic equipment |
| CN112767039A (en) * | 2021-01-26 | 2021-05-07 | 深圳市易售科技有限公司 | Method, device, equipment and medium for generating advertising machine delivery order |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113393259A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hulse et al. | Envisioning alternatives: using citizen guidance to map future land and water use | |
| US8880515B2 (en) | Determining concepts associated with a query | |
| US7962443B2 (en) | Method and system for replacing data in a structured design template | |
| Nijkamp et al. | Success factors for sustainable urban brownfield development: A comparative case study approach to polluted sites | |
| Baker et al. | Alternative futures for the Willamette River basin, Oregon | |
| Polhill et al. | Using qualitative evidence to enhance an agent-based modelling system for studying land use change | |
| US6154736A (en) | Belief networks with decision graphs | |
| CN105868332A (en) | hot topic recommendation method and device | |
| JP2012501489A (en) | Search method and system using extended keyword pool | |
| Regnier et al. | Replacement under ongoing technological progress | |
| CN103530414B (en) | Web Page Key Words open up word method and apparatus | |
| CN101022377A (en) | Interactive service establishing method based on service relation body | |
| CN108876470A (en) | Tagging user extended method, computer equipment and storage medium | |
| Dasari et al. | Multi-start heuristics for the profitable tour problem | |
| Birsak et al. | Automatic generation of tourist brochures | |
| Oliveira et al. | Social media use by citizen science projects: Characterization and recommendations | |
| CN113393259B (en) | Advertisement scheduling method, system, device and storage medium | |
| US20080300981A1 (en) | Campaign optimization | |
| Yamawaki | The location of American and Japanese multinationals in Europe | |
| Billig et al. | Residents' preferences for private amenities and trade-offs associated with various spatial densities and patterns | |
| CN114201663B (en) | Group customer mining method and device based on label propagation and electronic equipment | |
| JP2003337832A (en) | Database | |
| CN116451787B (en) | Content risk identification method, device, system and equipment | |
| Smith et al. | Ngāi Tahu print media before and after settlement | |
| CN115526616B (en) | MaaS payment settlement system based on artificial intelligence |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |