Advertisement intelligent scheduling generation method and device, equipment and storage medium
Through dynamic planning algorithms and advertising resource optimization schedules, the problems of high artificial complexity and insufficient broadcasting in traditional large-screen advertising intelligent schedules are solved, and efficient and automated intelligent schedules of advertising are achieved, which improves delivery effect and operation efficiency.
Patent Information
- Application Number
- CN202411160741.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-06
AI Technical Summary
When facing multi-device and multi-advertising services, the traditional intelligent schedule of large-screen advertising leads to high complexity and low efficiency of manual schedule, which is prone to mis-ordering and missing schedule problems, and cannot effectively solve the problem of advertisements within the specified time period. The problem of insufficient broadcasting leads to inconsistent delivery results.
Use dynamic planning algorithm to intelligently schedule advertising resources, calculate the overlap time between the estimated time of the single broadcast of advertising resources and the time period of the switching screen of large-screen devices, determine the feasibility of delivery plans, and optimize the schedule through the expansion of the ad broadcast time set. During the period, calculate the frequency of filling public service advertising resources to achieve automated schedule.
It improves the operational efficiency of the advertising delivery system, ensures that the advertisements are broadcast as planned, improves the delivery effect, reduces manual errors, and realizes the even distribution of advertising resources and the effective filling of public service advertisements.
Smart Images

Figure CN119090566A_ABST
Abstract
Description
Background Art
[0002] As an important means of disseminating information and promoting products, advertising has diversified behaviors. With the development of digital technology, the channels and forms of advertising have become more extensive, and the advertising business has also increased day by day. The large-screen advertising delivery system plays a very important role in the advertising business. However, in the face of increasing demand for delivery, the traditional scheduling method has gradually become incapable of meeting the needs.
[0003] The traditional large-screen advertising delivery system relies on the delivery plan of the statistical contract. After the broadcast time of each advertising resource is counted, the advertising schedule of the large-screen device is manually arranged. This approach is relatively effective when the number of devices is small, the advertising business is small, and the customization demand is small. As the scale of the system expands, the number of large-screen devices installed increases, resulting in a sharp increase in the complexity and cost of manual scheduling. The scheduling plan is prone to errors and omissions, and the efficiency is extremely low, which seriously affects the operation of the large-screen advertising delivery system.
[0004] Although the traditional large-screen advertising intelligent scheduling method can effectively and strictly control the number of advertisements to be broadcast according to the contract plan and avoid excessive advertising, it fails to solve the problem of insufficient advertising in the specified time period. At the same time, the large-screen devices in different regions have different opening and closing time periods due to human and physical reasons, resulting in inconsistent advertising effects in different regions. Summary of the invention
[0005] In view of the problems existing in the traditional large-screen advertising intelligent scheduling method, the present invention provides an advertising intelligent scheduling generation method, device, equipment and storage medium.
[0006] In a first aspect, the technical solution of the present invention provides a method for generating an intelligent advertising schedule, comprising the following steps: Statistics and analysis of signed electronic advertising contracts, calculation of the estimated duration of a single broadcast of contract-related advertising resources, and associated information on large-screen devices for advertising broadcast; Calculate the overlap time between the large-screen device's on / off time period and the ad playback time period to determine whether the ad delivery plan is feasible; When the advertising plan is feasible, the number of advertisements that can be broadcast is calculated based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. ; Get the ad resource set, get the ad broadcast duration set corresponding to the ad resource set, and expand the ad broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; Calculate the remaining broadcast time according to the scheduled advertisement set, and calculate the frequency of filling the scheduled advertisement set with public service advertisement resources; The public service advertisement resources are filled into the scheduled advertisement set according to the calculated frequency to obtain a filled scheduled advertisement set.
[0007] As a further limitation of the technical solution of the present invention, the steps of counting and analyzing the signed electronic advertising contracts, calculating the estimated single broadcast duration of the contract-related advertising resources, and associating the advertising broadcast large-screen device information include: Statistics and analysis of signed electronic advertising contracts, parsing of contract-related advertising large-screen device resources, acquisition of advertising broadcast times, advertising broadcast date sets and advertising designated broadcast device sets; acquisition of advertising broadcast time period sets based on the broadcast start time nodes of each time period; Calculate the estimated duration of a single broadcast of associated resources.
[0008] As a further limitation of the technical solution of the present invention, the estimated duration of a single broadcast of an advertisement resource is ; in, represents the broadcasting duration of the advertising video resource i; n represents the total number of broadcasts of the advertising video resource; It represents the rotation interval of the advertising image resource i, and m represents the total number of broadcasts of the advertising image resource.
[0009] As a further limitation of the technical solution of the present invention, the steps of calculating the overlapping time between the large-screen device on / off time period and the advertisement broadcast time period and determining whether the advertisement delivery plan is feasible include: Get the scheduled time periods for turning on and off the screen of large-screen devices; Calculate the overlap duration between the planned screen on / off time period of the large-screen device and the advertisement broadcast time period; If the estimated duration of a single broadcast is less than or equal to the overlapping duration, the advertising delivery plan is feasible; If the estimated duration of a single broadcast is greater than the overlapping duration, the advertising delivery plan is determined to be unfeasible and the set of designated devices for broadcasting the advertisement needs to be updated again.
[0010] As a further limitation of the technical solution of the present invention, when the advertising delivery plan is feasible, the number of advertisements that can be broadcast is calculated based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. The steps include: When the advertising delivery plan is feasible, the number of advertisements that can be broadcast is obtained by rounding down the ratio of the overlapping duration to the estimated duration of a single broadcast of the advertising resources and multiplying it by the total number of days on which the advertisements are broadcast.
[0011] As a further limitation of the technical solution of the present invention, an advertisement resource set is obtained, and at the same time, an advertisement broadcast duration set corresponding to the advertisement resource set is obtained, and the advertisement broadcast duration set is expanded. The steps of using the dynamic programming algorithm to schedule the advertising resources and obtain the scheduled advertising set include: Obtain an advertisement resource set, an advertisement broadcast time period set, an advertisement broadcast time period maximum duration set, and an advertisement broadcast duration set; Expand the advertisement broadcast duration collection with the same collection elements times, and get the set of advertisement broadcasting duration for the whole day; Initialize dynamic programming two-dimensional array , the two-dimensional array represents the maximum advertisement duration using the first i advertisements, when the total duration does not exceed j; Construct the state transfer equation to update the two-dimensional array to obtain the optimal solution; Based on the obtained optimal solution, reversely trace the advertisements inserted into the time period to obtain a set of scheduled advertisements for the corresponding time period; As a further limitation of the technical solution of the present invention, the steps of calculating the remaining broadcast time according to the scheduled advertisement set, calculating the number of public service advertisement resources broadcast according to the preset broadcast interval, and then calculating the frequency of inserting the public service advertisement resources into the scheduled advertisement set include: Calculate the remaining playing time of the kth time period based on the scheduled advertisement set; The ratio of the remaining broadcasting time of the kth time period to the preset broadcasting interval is rounded up to obtain the number of public service advertisement resources broadcasted according to the preset broadcasting interval; The frequency of inserting the public service advertisement resources into the scheduled advertisement set is obtained by calculating the ratio of the number of scheduled advertisement sets to the number of public service advertisement resources broadcast at the preset broadcast interval.
[0012] In a second aspect, the technical solution of the present invention further provides an advertisement intelligent scheduling generation device, including a parsing module, a control module, a generation module and a filling module; The parsing module is used to count and analyze the signed electronic advertising contracts, calculate the estimated single broadcast duration of the contract-related advertising resources, and associate the information of the large-screen device on which the advertisements are broadcast; The control module is used to calculate the overlap time between the large-screen device on / off time period and the advertisement broadcast time period to determine whether the advertisement delivery plan is feasible; The generation module is used to calculate the number of advertisements that can be broadcast based on the estimated duration of a single broadcast of the advertisement resources and the total number of days the advertisements are broadcast when the advertisement delivery plan is feasible. ; Get the advertising resource set, get the advertising broadcast duration set corresponding to the advertising resource set, and expand the advertising broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; The filling module is used to calculate the remaining playback time according to the scheduled advertisement set, and calculate the frequency of filling the public service advertisement resources into the scheduled advertisement set; fill the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain the filled scheduled advertisement set.
[0013] As a further limitation of the technical solution of the present invention, the parsing module includes a statistical analysis unit and a first calculation unit; The statistical analysis unit is used to count and analyze the signed electronic advertising contract plan, parse the contract-related advertising large-screen resources; obtain the number of advertisement broadcasts, the advertisement broadcast date set and the advertisement designated broadcast device set; obtain the advertisement broadcast time period set according to the broadcast start time node of the advertisement in each time period; A first calculation unit calculates an estimated duration of a single broadcast of associated resources; Estimated duration of a single broadcast of advertising resources ; in, represents the broadcasting duration of the advertising video resource i; n represents the total number of broadcasts of the advertising video resource; It represents the rotation interval of the advertising image resource i, and m represents the total number of broadcasts of the advertising image resource.
[0014] As a further limitation of the technical solution of the present invention, the control module is used to obtain the planned time period for turning on and off the screen of the large-screen device; calculate the overlapping duration of the planned time period for turning on and off the screen of the large-screen device and the time period for broadcasting advertisements; if the expected duration of a single broadcast is less than or equal to the overlapping duration, it is determined that the advertising delivery plan is feasible; if the expected duration of a single broadcast is greater than the overlapping duration, it is determined that the advertising delivery plan is not feasible, and the set of designated broadcast devices for advertisements needs to be updated again.
[0015] As a further limitation of the technical solution of the present invention, the generation module includes a second calculation unit and an initial schedule generation unit; The second calculation unit is used for, when the advertisement delivery plan is feasible, multiplying the result of rounding down the ratio of the overlapping duration to the estimated duration of a single broadcast of the advertisement resources by the total number of days of the advertisement broadcast date to obtain the number of advertisements that can be broadcasted.
[0016] The initial scheduling generation unit obtains the advertising resource set, the advertising broadcast time period set, the advertising broadcast time period maximum duration set and the advertising broadcast duration set; expands the advertising broadcast duration set with the same set elements times, get the set of advertisement broadcast duration for the whole day; initialize the dynamic programming two-dimensional array , the two-dimensional array represents the maximum advertising duration using the first i advertisements, with the total duration not exceeding j; construct a state transfer equation to update the two-dimensional array to obtain the optimal solution; based on the obtained optimal solution, reversely trace the advertisements inserted into the time period to obtain the scheduled advertisement set for the corresponding time period.
[0017] As a further limitation of the technical solution of the present invention, the filling module includes a third calculation unit and a filling unit; The third calculation unit is used to calculate the remaining broadcast time of the kth time period according to the scheduled advertisement set; round up the ratio of the remaining broadcast time of the kth time period to the preset broadcast interval to obtain the number of public service advertisement resources broadcast according to the preset broadcast interval; calculate the ratio of the number of scheduled advertisement sets to the number of public service advertisement resources broadcast according to the preset broadcast interval to obtain the frequency of public service advertisement resources being inserted into the scheduled advertisement set; The filling unit is used to insert the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain the scheduled advertisement set.
[0018] In a third aspect, the technical solution of the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the advertising intelligent scheduling generation method as described in the first aspect.
[0019] In a fourth aspect, the technical solution of the present invention further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the method for generating intelligent advertising schedules as described in the first aspect.
[0020] It can be seen from the above technical scheme that the present invention has the following advantages: using a dynamic programming algorithm to schedule advertising resources to obtain a scheduled advertising set; and calculating the frequency of inserting public service advertising resources into the scheduled advertising set; inserting public service advertising resources into the scheduled advertising set according to the calculated frequency to obtain a scheduled advertising set to realize automatic scheduling of advertisements, improve the effect of advertising delivery, and the efficiency of the operation of the large-screen advertising delivery system.
[0021] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0023] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.
[0024] Figure 2is a schematic flow chart of a method according to another embodiment of the present invention.
[0025] Figure 3 is a schematic block diagram of an apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0027] like Figure 1 As shown, an embodiment of the present invention provides a method for generating an intelligent advertisement schedule, including the following: Step 1: Count and analyze the signed electronic advertising contracts, calculate the estimated duration of a single broadcast of contract-related advertising resources, and associate the information of large-screen devices on which the advertisements are broadcast; Step 2: Calculate the overlap time between the large-screen device on / off time period and the advertisement broadcast time period to determine whether the advertisement delivery plan is feasible; Step 3: When the advertising plan is feasible, calculate the number of times the advertisement can be broadcast based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisement will be broadcast. ; Step 4: Get the ad resource set, get the ad broadcast duration set corresponding to the ad resource set, and expand the ad broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; Step 5: Calculate the remaining broadcast time according to the scheduled advertisement set, and calculate the frequency of the public service advertisement resources filling into the scheduled advertisement set; Step 6: Fill the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain a filled scheduled advertisement set.
[0028] In some embodiments, the steps of counting and analyzing the signed electronic advertising contracts, calculating the estimated single broadcast duration of the contract-related advertising resources, and associating the advertising broadcasting large-screen device information include: Step 11: Count and analyze the signed electronic advertising contract plans, parse the contract-related advertising large-screen device resources, obtain the number of advertising broadcasts, the advertising broadcast date set and the advertising designated broadcast device set; obtain the advertising broadcast time period set according to the broadcast start time node of the advertisement in each time period; Step 12: Calculate the estimated duration of a single broadcast of the associated resources.
[0029] Estimated duration of a single broadcast of advertising resources ; in, represents the broadcasting duration of the advertising video resource i; n represents the total number of broadcasts of the advertising video resource; It represents the rotation interval of the advertising image resource i, and m represents the total number of broadcasts of the advertising image resource.
[0030] You can also get the set of advertising broadcast time periods :
[0031] in, Indicates k The start time of the advertisement in each time period. Indicates k The time point at which the advertisement broadcasting ends in a time period.
[0032] and the number of times the ad was played s , Advertisement airing date collection And the set of devices specified for advertisement broadcasting ,in Indicates air date, Indicates the zth broadcast device.
[0033] like Figure 2 As shown, in some embodiments, the steps of calculating the overlapping time of the large-screen device screen on / off time period and the advertisement broadcast time period and determining whether the advertisement delivery plan is feasible include: Step 21: Obtain the planned time period for turning on and off the screen of the large-screen device; Step 22: Calculate the overlapping duration between the planned time period for turning on and off the screen of the large-screen device and the time period for playing advertisements; Step 23: If the estimated duration of a single broadcast is less than or equal to the overlapping duration, it is determined that the advertising delivery plan is feasible; Step 24: If the estimated duration of a single broadcast is greater than the overlapping duration, it is determined that the advertising delivery plan is not feasible, and the set of designated advertising broadcast devices needs to be updated again.
[0034] Specifically, get a large screen device The switch screen planning time period ,calculate .in Indicates large screen devices The switch screen planning time period The time period of the advertisement The overlap duration.
[0035] like , it means that the broadcast duration of the advertising resources is less than the overlapping duration, and the advertising delivery plan is feasible.
[0036] like , it means that the broadcast time of the advertising resources is longer than the overlapping time, and the advertising delivery plan is not feasible. It is necessary to reselect the appropriate device for delivery. In some embodiments, when the advertising delivery plan is feasible, the number of advertisements that can be broadcast is calculated based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. The steps include: When the advertising delivery plan is feasible, the number of advertisements that can be broadcast is obtained by rounding down the ratio of the overlapping duration to the estimated duration of a single broadcast of the advertising resources and multiplying it by the total number of days on which the advertisements are broadcast.
[0037] If the advertising plan is feasible, calculate the number of ads that can be broadcast :
[0038] in, It represents the ratio of the overlapping duration to the single broadcast duration of the advertising resources and is rounded down. Indicates the total number of days that the ad will be aired.
[0039] Due to the time period of the advertisement It may not be continuous. Some advertising resources scheduled later may exceed the scheduled time period after being broadcast, deviating from the expected delivery effect. Therefore, a reasonable scheduling algorithm is needed to evenly distribute advertising resources. In some embodiments, an advertising resource set is obtained, and at the same time, an advertising broadcast time set corresponding to the advertising resource set is obtained, and the advertising broadcast time set is expanded. The steps of using the dynamic programming algorithm to schedule the advertising resources and obtain the scheduled advertising set include: Step 41: Obtain an advertisement resource set, an advertisement broadcast time period set, an advertisement broadcast time period maximum duration set, and an advertisement broadcast duration set; In this step, the advertising resource set is known ,in , n is the number of advertising video resources, m The number of advertising image resources; the advertising broadcast time period collection ; Maximum duration of advertisement broadcast time period ; Advertisement broadcast duration collection ; The goal of the algorithm is to make the advertising duration B Assign to these time periods The total duration of advertisements in each time period is as close to its maximum duration as possible, and each advertisement can only be broadcast once; Step 42: Expand the advertisement broadcast duration set with the same set elements times, and get the set of advertisement broadcasting duration for the whole day; Aggregate the duration of advertisements B Expanding with the same set of elements times, get the total duration of advertisements for the whole day ,in The purpose of this step is to make each advertisement This solved the problem of broadcast frequency.
[0040] Step 43: Initialize the dynamic programming two-dimensional array , the two-dimensional array represents the maximum advertisement duration using the first i advertisements, when the total duration does not exceed j; Initialize the dynamic programming two-dimensional array, ,in Before use i ads, with a total duration of no more than j The maximum total duration of advertisements, j Indicates the remaining available time of the current time period. The purpose of this step is to construct the starting and boundary conditions of the algorithm.
[0041] Step 44: construct a state transfer equation to update the two-dimensional array to obtain the optimal solution; In this step, the state transition equation is constructed. For each advertisement i and each possible time j, there are two options: Do not select advertisement i: advertisement i is not assigned to the current time period. Under this condition, the value of the current state is the same as the previous state, that is,
[0042] Select ad i: If the duration of ad i is less than or equal to the current remaining duration j, ad i can be assigned to the current time period. Under this condition, the current state value is: the previous The remaining duration of the ad is The optimal solution under the condition of The duration of .
[0043] In summary, the state transfer equation is expressed as:
[0044] The purpose of this step is to dynamically update and obtain the optimal solution.
[0045] Step 45: Based on the obtained optimal solution, reversely trace the advertisements inserted into the time period to obtain a set of scheduled advertisements for the corresponding time period; In this step, the optimal solution path is constructed and the dynamic programming array is traced back. The tracing rules are described as follows: 1. If , then the advertisement i Not selected, continue tracking forward.
[0046] 2. If , then the advertisement i is selected, record the duration and subtract the remaining duration , continue tracking forward.
[0047] In summary, k A collection of scheduled ads for a time period Expressed as
[0048] The purpose of this step is to track which advertisements are inserted into the time period after obtaining the optimal solution, so as to obtain the scheduled advertisement set for the corresponding time period.
[0049] In some embodiments, the steps of calculating the remaining broadcast duration according to the scheduled advertisement set, calculating the number of public service advertisement resources broadcast at a preset broadcast interval, and then calculating the frequency of inserting the public service advertisement resources into the scheduled advertisement set include: Step 51: Calculate the remaining playing time of the kth time period according to the scheduled advertisement set; Step 52: rounding up the ratio of the remaining broadcasting time of the kth time period to the preset broadcasting interval to obtain the number of public service advertisement resources broadcasted according to the preset broadcasting interval; Step 52: Calculate the ratio of the number of scheduled advertisement sets to the number of public service advertisement resources broadcast at the preset broadcast interval to obtain the frequency of inserting the public service advertisement resources into the scheduled advertisement sets.
[0050] Since the broadcasting time of advertising resources is not regular, there may be unused fragmented time in each time period. Therefore, this method evenly inserts the preset public service advertisement segments into the corresponding time period broadcast advertisement set, which can improve the delivery effect to a certain extent.
[0051] A set of scheduled ads generated by a given algorithm , can get the first k The remaining playing time of the time period , calculate the preset broadcast interval Number of public service advertising resources broadcast ,in The ratio of the broadcast duration to the broadcast interval is rounded up. The frequency of inserting these public service advertising resources into the scheduled advertising set is ,in, Represents an ad collection The number of Indicates each interval Insert a public service advertising resource into each record.
[0052] Finally, we get the filled scheduled advertisement set ,in Indicates The first public service advertising resource that is frequently inserted.
[0053] like Figure 3 As shown, an embodiment of the present invention further provides an advertisement intelligent scheduling generation device, including a parsing module, a control module, a generation module and a filling module; The parsing module is used to count and analyze the signed electronic advertising contracts, calculate the estimated single broadcast duration of the contract-related advertising resources, and associate the information of the large-screen device on which the advertisements are broadcast; The control module is used to calculate the overlap time between the large-screen device on / off time period and the advertisement broadcast time period to determine whether the advertisement delivery plan is feasible; The generation module is used to calculate the number of advertisements that can be broadcast based on the estimated duration of a single broadcast of the advertisement resources and the total number of days the advertisements are broadcast when the advertisement delivery plan is feasible. ; Get the advertising resource set, and at the same time get the advertising broadcast duration set corresponding to the advertising resource set, and expand the advertising broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; The filling module is used to calculate the remaining playback time according to the scheduled advertisement set, and calculate the frequency of filling the public service advertisement resources into the scheduled advertisement set; fill the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain the filled scheduled advertisement set.
[0054] In some embodiments, the parsing module includes a statistical analysis unit and a first calculation unit; The statistical analysis unit is used to count and analyze the signed electronic advertising contract plan, parse the contract-related advertising large-screen resources; obtain the number of advertisement broadcasts, the advertisement broadcast date set and the advertisement designated broadcast device set; obtain the advertisement broadcast time period set according to the broadcast start time node of the advertisement in each time period; A first calculation unit calculates an estimated duration of a single broadcast of associated resources; Estimated duration of a single broadcast of advertising resources ; in, represents the broadcasting duration of the advertising video resource i; n represents the total number of broadcasts of the advertising video resource; It represents the rotation interval of the advertising image resource i, and m represents the total number of broadcasts of the advertising image resource.
[0055] In some embodiments, the control module is used to obtain the planned time period for turning the screen on and off for the large-screen device; calculate the overlapping duration between the planned time period for turning the screen on and off for the large-screen device and the time period for broadcasting advertisements; if the estimated duration of a single broadcast is less than or equal to the overlapping duration, it is determined that the advertising delivery plan is feasible; if the estimated duration of a single broadcast is greater than the overlapping duration, it is determined that the advertising delivery plan is not feasible and the set of designated broadcast devices for the advertisement needs to be updated again.
[0056] In some embodiments, the generation module includes a second calculation unit and an initial schedule generation unit; The second calculation unit is used for, when the advertisement delivery plan is feasible, multiplying the result of rounding down the ratio of the overlapping duration to the estimated duration of a single broadcast of the advertisement resources by the total number of days of the advertisement broadcast date to obtain the number of advertisements that can be broadcasted.
[0057] The initial scheduling generation unit obtains the advertising resource set, the advertising broadcast time period set, the advertising broadcast time period maximum duration set and the advertising broadcast duration set; expands the advertising broadcast duration set with the same set elements times, get the set of advertisement broadcast duration for the whole day; initialize the dynamic programming two-dimensional array , the two-dimensional array represents the maximum advertising duration using the first i advertisements, with the total duration not exceeding j; construct a state transfer equation to update the two-dimensional array to obtain the optimal solution; based on the obtained optimal solution, reversely trace the advertisements inserted into the time period to obtain the scheduled advertisement set for the corresponding time period.
[0058] In some embodiments, the filling module includes a third calculation unit and a filling unit; The third calculation unit is used to calculate the remaining broadcast time of the kth time period according to the scheduled advertisement set; round up the ratio of the remaining broadcast time of the kth time period to the preset broadcast interval to obtain the number of public service advertisement resources broadcast according to the preset broadcast interval; calculate the ratio of the number of scheduled advertisement sets to the number of public service advertisement resources broadcast according to the preset broadcast interval to obtain the frequency of public service advertisement resources being inserted into the scheduled advertisement set; The filling unit is used to insert the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain the scheduled advertisement set.
[0059] An embodiment of the present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus. The communication bus can be used for information transmission between the electronic device and the sensor. The processor can call the logic instructions in the memory to execute the following method: Step 1: Count and analyze the signed electronic advertising contracts, calculate the estimated duration of a single broadcast of the contract-associated advertising resources, and associate the information of the large-screen device for broadcasting the advertisements; Step 2: Calculate the overlapping time between the time period of turning on and off the large-screen device and the time period of broadcasting the advertisements, and determine whether the advertising delivery plan is feasible; Step 3: When the advertising delivery plan is feasible, calculate the number of advertisements that can be broadcast based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. ; Step 4: Get the advertising resource set, get the advertising broadcast duration set corresponding to the advertising resource set, and expand the advertising broadcast duration set After that, the advertising resources are scheduled using a dynamic programming algorithm to obtain a scheduled advertising set; Step 5: Calculate the remaining broadcast time according to the scheduled advertising set, and calculate the frequency of filling the public service advertising resources into the scheduled advertising set; Step 6: Fill the public service advertising resources into the scheduled advertising set according to the calculated frequency to obtain the filled scheduled advertising set.
[0060] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.
[0061] An embodiment of the present invention provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to execute the method provided by the above method embodiment, for example, including: Step 1: Count and analyze the signed electronic advertising contracts, calculate the estimated duration of a single broadcast of contract-related advertising resources, and associate the information of the large-screen device for broadcasting the advertisements; Step 2: Calculate the overlapping time of the large-screen device's on / off screen time period and the advertisement broadcast time period to determine whether the advertising delivery plan is feasible; Step 3: When the advertising delivery plan is feasible, calculate the number of advertisements that can be broadcast based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. ; Step 4: Get the advertising resource set, get the advertising broadcast duration set corresponding to the advertising resource set, and expand the advertising broadcast duration set After that, the advertising resources are scheduled using a dynamic programming algorithm to obtain a scheduled advertising set; Step 5: Calculate the remaining broadcast time according to the scheduled advertising set, and calculate the frequency of filling the public service advertising resources into the scheduled advertising set; Step 6: Fill the public service advertising resources into the scheduled advertising set according to the calculated frequency to obtain the filled scheduled advertising set.
[0062] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0063] An embodiment of an intelligent advertising scheduling generation device provided in an embodiment of the present invention belongs to the same inventive concept as the intelligent advertising scheduling generation method of the above-mentioned embodiments. For details not described in detail in the embodiment of the intelligent advertising scheduling generation device, reference can be made to the embodiment of the above-mentioned intelligent advertising scheduling generation method.
[0064] The advertising intelligent scheduling generation device is a unit and algorithm step of each example described in combination with the embodiments disclosed in this document, which can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.
[0065] Those skilled in the art will appreciate that various aspects of the method for generating intelligent advertising schedules can be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which can be collectively referred to as "circuit", "module" or "system".
[0066] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. A method for generating intelligent advertising schedule, characterized in that: The steps include: Statistics and analysis of signed electronic advertising contracts, calculation of the estimated duration of a single broadcast of contract-related advertising resources, and associated information on large-screen devices for advertising broadcast; Calculate the overlap time between the large-screen device's on / off time period and the ad playback time period to determine whether the ad delivery plan is feasible; When the advertising plan is feasible, the number of advertisements that can be broadcast is calculated based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. ; Get the ad resource set, get the ad broadcast duration set corresponding to the ad resource set, and expand the ad broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; Calculate the remaining broadcast time according to the scheduled advertisement set, and calculate the frequency of filling the scheduled advertisement set with public service advertisement resources; The public service advertisement resources are filled into the scheduled advertisement set according to the calculated frequency to obtain a filled scheduled advertisement set.
2. The method for generating intelligent advertising schedule according to claim 1, characterized in that: The steps of counting and analyzing the signed electronic advertising contracts, calculating the estimated single broadcast duration of the contract-related advertising resources, and associating the information of the large-screen device for broadcasting the advertisements include: Statistics and analysis of signed electronic advertising contracts, parsing of contract-related advertising large-screen device resources, acquisition of advertising broadcast times, advertising broadcast date sets and advertising designated broadcast device sets; acquisition of advertising broadcast time period sets based on the broadcast start time nodes of each time period; Calculate the estimated duration of a single broadcast of associated resources.
3. The method for generating intelligent advertising schedule according to claim 2, characterized in that: Estimated duration of a single broadcast of advertising resources ; in, represents the broadcasting duration of the advertising video resource i; n represents the total number of broadcasts of the advertising video resource; It represents the rotation interval of the advertising image resource i, and m represents the total number of broadcasts of the advertising image resource.
4. The method for generating intelligent advertising schedule according to claim 3, characterized in that: The steps to calculate the overlap time between the large-screen device on / off time period and the advertisement broadcast time period and determine whether the advertisement delivery plan is feasible include: Get the scheduled time periods for turning on and off the screen of large-screen devices; Calculate the overlap duration between the planned screen on / off time period of the large-screen device and the advertisement broadcast time period; If the estimated duration of a single broadcast is less than or equal to the overlapping duration, the advertising delivery plan is feasible; If the estimated duration of a single broadcast is greater than the overlapping duration, the advertising delivery plan is determined to be unfeasible and the set of designated devices for broadcasting the advertisement needs to be updated again.
5. The method for generating intelligent advertising schedule according to claim 4, characterized in that: When the advertising plan is feasible, the number of advertisements that can be broadcast is calculated based on the estimated duration of a single broadcast of the advertising resources and the total number of days the advertisements are broadcast. The steps include: When the advertising delivery plan is feasible, the number of advertisements that can be broadcast is obtained by rounding down the ratio of the overlapping duration to the estimated duration of a single broadcast of the advertising resources and multiplying it by the total number of days on which the advertisements are broadcast.
6. The method for generating intelligent advertising schedule according to claim 5, characterized in that: Get the ad resource set, get the ad broadcast duration set corresponding to the ad resource set, and expand the ad broadcast duration set The steps of using the dynamic programming algorithm to schedule the advertising resources and obtain the scheduled advertising set include: Obtain an advertisement resource set, an advertisement broadcast time period set, an advertisement broadcast time period maximum duration set, and an advertisement broadcast duration set; Expand the advertisement broadcast duration collection with the same collection elements times, and get the set of advertisement broadcasting duration for the whole day; Initialize dynamic programming two-dimensional array , the two-dimensional array represents the maximum advertisement duration using the first i advertisements, when the total duration does not exceed j; Construct the state transfer equation to update the two-dimensional array to obtain the optimal solution; Based on the obtained optimal solution, the advertisements inserted into the time period are traced back to obtain a set of scheduled advertisements for the corresponding time period.
7. The method for generating intelligent advertising schedule according to claim 6, characterized in that: The steps of calculating the remaining broadcasting time according to the scheduled advertisement set, calculating the number of public service advertisement resources broadcast at the preset broadcast interval, and then calculating the frequency of inserting the public service advertisement resources into the scheduled advertisement set include: Calculate the remaining playing time of the kth time period based on the scheduled advertisement set; The ratio of the remaining broadcasting time of the kth time period to the preset broadcasting interval is rounded up to obtain the number of public service advertisement resources broadcasted according to the preset broadcasting interval; The frequency of inserting the public service advertisement resources into the scheduled advertisement set is obtained by calculating the ratio of the number of scheduled advertisement sets to the number of public service advertisement resources broadcast at the preset broadcast interval.
8. An intelligent advertising schedule generation device, characterized in that: It includes parsing module, control module, generation module and filling module; The parsing module is used to count and analyze the signed electronic advertising contracts, calculate the estimated single broadcast duration of the contract-related advertising resources, and associate the information of the large-screen device on which the advertisements are broadcast; The control module is used to calculate the overlap time between the large-screen device on / off time period and the advertisement broadcast time period to determine whether the advertisement delivery plan is feasible; The generation module is used to calculate the number of advertisements that can be broadcast based on the estimated duration of a single broadcast of the advertisement resources and the total number of days the advertisements are broadcast when the advertisement delivery plan is feasible. ; Get the advertising resource set, and at the same time get the advertising broadcast duration set corresponding to the advertising resource set, and expand the advertising broadcast duration set After that, the dynamic programming algorithm is used to schedule the advertising resources to obtain a set of scheduled advertisements; The filling module is used to calculate the remaining playback time according to the scheduled advertisement set, and calculate the frequency of filling the public service advertisement resources into the scheduled advertisement set; fill the public service advertisement resources into the scheduled advertisement set according to the calculated frequency to obtain the filled scheduled advertisement set.
9. An electronic device, characterized in that: The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the advertising intelligent scheduling generation method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the advertising intelligent scheduling generation method as described in any one of claims 1 to 7.
