CN115564476A

CN115564476A - Advertisement playing progress adjusting method and system and cloud platform

Info

Publication number: CN115564476A
Application number: CN202211172034.XA
Authority: CN
Inventors: 樊昆; 李远智
Original assignee: Individual
Current assignee: Kunming Lantuo Technology Co ltd
Priority date: 2022-09-26
Filing date: 2022-09-26
Publication date: 2023-01-03

Abstract

The application relates to the technical field of data processing and advertisement playing, in particular to an advertisement playing progress adjusting method, an advertisement playing progress adjusting system and a cloud platform. According to the method, the system and the cloud platform for adjusting the advertisement playing progress, the target elements are screened through the multiple advertisement playing data, so that the identification result of the target elements is more accurate. Finally, if the target elements are screened, determining target playing data participating in the target elements in at least two playing data in the advertisement playing data to be processed and the identified advertisement playing data set; therefore, the accuracy and the reliability of the target playing data can be improved; therefore, the target playing data can be debugged more reliably, and the accuracy and the integrity of the advertisement data playing are improved.

Description

Advertisement playing progress adjusting method and system and cloud platform

Technical Field

The application relates to the technical field of data processing and advertisement playing, in particular to an advertisement playing progress adjusting method, an advertisement playing progress adjusting system and a cloud platform.

Background

Economic advertising refers to advertising for profit purposes, typically commercial advertising, which is a means of disseminating information of goods or services to consumers or users through advertising media in a paid manner for the purpose of promoting the goods or providing the services. Commercial advertisements are such economic advertisements.

With the continuous development and progress of science and technology, when an advertisement is played, data is abnormal or data is interfered, so that the advertisement cannot be played normally, and the accuracy and integrity of advertisement data playing are difficult to guarantee.

Disclosure of Invention

In order to solve the technical problems in the related art, the application provides an advertisement playing progress adjusting method, an advertisement playing progress adjusting system and a cloud platform.

In a first aspect, a method for adjusting an advertisement playing progress is provided, where the method at least includes: identifying the obtained advertisement playing data to be processed to obtain an identification result of first playing data in the advertisement playing data to be processed; determining first element information of the first playing data according to the identification result and second element information in the advertisement playing data set which is identified; the identified advertisement playing data set is used for storing the advertisement playing data subjected to the identification processing, and the identified advertisement playing data has second element information of second playing data in an advertisement theme; on the premise that the global advertisement item coefficient of the identified advertisement playing data set and the advertisement playing data to be processed meets the judgment value of a designated item, performing target element screening on the advertisement playing data to be processed and the identified advertisement playing data set through the second element information and the first element information; in response to the target element being screened, determining target playing data participating in the target element from the first playing data and the second playing data; and debugging the target playing data.

In an embodiment that is implemented independently, the identifying the obtained advertisement playing data to be processed to obtain an identification result of a first playing data in the advertisement playing data to be processed includes: carrying out abnormal identification processing on the advertisement playing data to be processed to obtain a plurality of identification labels of the abnormal playing data; determining the bias degree of the plurality of abnormal playing data as the first playing data through the identification tags of the plurality of abnormal playing data; screening the first playing data meeting the specified requirement from the plurality of abnormal playing data through the bias degree; and determining the identification result through the identification label of the first playing data and the category information of the first playing data.

In an embodiment of this application, the screening, by the bias degree, the first playing data that meets a specified requirement from the plurality of abnormal playing data includes: deleting the abnormal playing data with the bias degree lower than the first bias degree target value from the plurality of abnormal playing data to obtain a plurality of other abnormal playing data; determining sharing weight among the identification tags of the plurality of rest abnormal playing data; and cleaning a part of abnormal playing data with the sharing weight larger than the specified sharing weight target value in the rest abnormal playing data to obtain the first playing data.

In an embodiment, the determining first element information of the first playing data according to the identification result and the second element information in the advertisement playing data set that has completed identification includes: determining differences between the first playing data and a plurality of second playing data of the identified advertisement playing data set through the identification result and the second element information; searching the second playing data for pending playing data associated with the first playing data through the difference; in response to the search of the data to be played, determining the recording data of the data to be played as the recording data of the first playing data; and splicing the identification result and the recorded data to obtain the first element information.

In an embodiment, the determining, according to the identification result and the second element information, the difference between the first playing data and a plurality of second playing data of the identified advertisement playing data set includes: respectively identifying important contents of the advertisement playing data to be processed and the identified advertisement playing data set according to the identification result and the second element information to obtain an advertisement playing data vector to be processed and an advertisement playing data vector which is identified; determining vector difference between the advertisement playing data vector to be processed and the advertisement playing data vector which is identified already; determining a comparison result between the identification tag of the first playing data and the identification tags of the plurality of second playing data; and obtaining differences between the first playing data and the plurality of second playing data through the vector differences and/or the comparison result.

In an embodiment, after searching for the pending playing data associated with the first playing data in the second playing data through the difference, the method further includes: responding to the undetected playing data, obtaining specified recording data used for identifying the first playing data; wherein the specified recording data is different from the recording data of the plurality of second playback data; and splicing the specified record data and the identification result to obtain the first element information.

In an embodiment, in an independent implementation manner, on the premise that the global advertisement item coefficient of the already identified advertisement playing data set and the to-be-processed advertisement playing data meets a specified item determination value, performing target element screening on the to-be-processed advertisement playing data and the already identified advertisement playing data set through the second element information and the first element information includes: determining the bias degree of the target element in the identified advertisement playing data set and the advertisement playing data to be processed according to the second element information and the first element information; and determining whether the target elements are screened from the identified advertisement playing data set and the advertisement playing data to be processed or not according to the target values of the bias degree and the second bias degree.

In an independently implemented embodiment, in response to the target element being screened, the target playing data participating in the target element is determined in the first playing data and the second playing data; and debugging the target playing data, including: in response to the target element being screened, important identification playing data associated with the target element is determined in the advertisement playing data to be processed to which the first playing data belongs and the advertisement playing data to which the second playing data belongs and which has been identified; determining the important playing data covered by the identification tag in the important identification playing data as the target playing data; wherein the important play data includes the first play data or the second play data.

In an embodiment of this invention, after determining the important playing data covered by the identification tag in the important identified playing data as the target playing data, the method further includes: performing important content identification on important playing data through element information corresponding to the important playing data in the important identification playing data to obtain a playing data vector, and comparing the playing data vector with a specified advertisement playing data set annotated with a target element type to obtain the type of the target element; and optimizing the types of the target elements and the target playing data.

In a separately implemented embodiment, the important identification playing data includes one or more of the following items: the identified advertisement playing data set and the advertisement playing data to be processed comprise the advertisement playing data with the optimal bias degree of the target element; and the identified advertisement playing data set and the advertisement playing data with the distribution condition meeting the specified condition in the advertisement playing data to be processed.

In an embodiment, after determining the first element information of the first playing data according to the identification result and the second element information in the advertisement playing data set with the identification completed, the method further includes: on the premise that the global advertisement item coefficient does not accord with the specified item judgment value, obtaining the latter advertisement playing data which is continuously distributed with the advertisement playing data to be processed; associating the third element information of the latter advertisement playing data with the latter advertisement playing data to obtain associated advertisement playing data; storing the associated advertisement playing data in the advertisement playing data set which is identified, so as to obtain a mined advertisement playing data set which is identified; and on the premise that the advertisement playing data type of the mined identified advertisement playing data set meets the specified project judgment value, performing target element screening on the mined identified advertisement playing data set through the first element information, the second element information and the third element information.

In a second aspect, there is provided an advertisement playing progress adjustment system, including: the progress adjusting cloud platform is in communication connection with the advertisement data acquisition end;

wherein, the progress adjustment cloud platform is used for: identifying the obtained advertisement playing data to be processed to obtain an identification result of first playing data in the advertisement playing data to be processed; determining first element information of the first playing data according to the identification result and second element information in the advertisement playing data set which is identified; the identified advertisement playing data set is used for storing the advertisement playing data subjected to the identification processing, and the identified advertisement playing data has second element information of second playing data in an advertisement theme; on the premise that the global advertisement item coefficient of the identified advertisement playing data set and the advertisement playing data to be processed meets the judgment value of a designated item, performing target element screening on the advertisement playing data to be processed and the identified advertisement playing data set through the second element information and the first element information; in response to the target element being screened, determining target playing data participating in the target element from the first playing data and the second playing data; and debugging the target playing data.

In a third aspect, a progress adjustment cloud platform is provided, including: a memory for storing a computer program; a processor coupled to the memory for executing the computer program stored by the memory to implement the above-described method.

According to the method, the system and the cloud platform for adjusting the advertisement playing progress, after the advertisement playing data to be processed are obtained, firstly, the advertisement playing data to be processed are identified so as to identify the identification result of the first playing data in the advertisement playing data to be processed; secondly, combining the second element information of the second playing data which is stored in the advertisement playing data set and is identified with the identification result to obtain the first element information of the first playing data; therefore, the first element information is set for the first playing data through the identification result obtained by identification and the element information stored in the identified advertisement playing data set, and the association between the first playing data in the advertisement playing data to be processed and the first playing data in the identified advertisement playing data set can be embodied through the first element information, so that the subsequent identification of the target element is facilitated; thirdly, after the advertisement playing data to be processed is identified, whether the global advertisement item coefficient accords with the specified item judgment value is judged, if the stored global advertisement item coefficient accords with the specified item judgment value, the target elements are identified in the advertisement playing data to be processed and the advertisement playing data which is already identified through the second element information and the first element information; therefore, the target elements are screened through various advertisement playing data, and the identification result of the target elements is more accurate. Finally, if the target elements are screened, determining target playing data participating in the target elements in at least two playing data in the advertisement playing data to be processed and the identified advertisement playing data set; therefore, the accuracy and the reliability of the target playing data can be improved; therefore, the target playing data can be debugged more reliably, and the accuracy and the integrity of the advertisement data playing are improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a flowchart of an advertisement playing progress adjusting method according to an embodiment of the present application.

Fig. 2 is a block diagram of an advertisement playing progress adjusting device according to an embodiment of the present application.

Fig. 3 is a schematic diagram of a hardware structure of a progress adjustment cloud platform according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions of the present application, the following detailed descriptions are provided with accompanying drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and in a case of no conflict, the technical features in the embodiments and examples of the present application may be combined with each other.

Referring to fig. 1, a method for adjusting an advertisement playing progress is shown, which may include the technical solutions described in the following steps S101 to S104.

Step S101, the obtained advertisement playing data to be processed is identified, and an identification result of first playing data in the advertisement playing data to be processed is obtained.

In some possible embodiments, the type of the first playing data in the advertisement playing data to be processed may be determined based on a target element, and the playing data required for participating in the target element is the playing data. The first playing data in the advertisement playing data to be processed may be one playing data or several playing data.

Step S102, determining the first element information of the first playing data according to the identification result and the second element information in the advertisement playing data set which has finished identification.

In some possible embodiments, the already identified advertisement playing data set includes already identified advertisement playing data having second element information of second playing data in the advertisement topic, and the already identified advertisement playing data in the already identified advertisement playing data set is a plurality of types of advertisement playing data which are distributed continuously; the second playback data is the same as or different from the first playback data. The advertisement playing data to be processed may be advertisement playing data that is continuous in distribution with the advertisement playing data in the advertisement playing data set that has completed identification, for example, the advertisement playing data to be processed is continuous with the last advertisement playing data that has completed identification. Each identified advertisement playing data includes the second playing data identified in the identified advertisement playing data and element information of the second playing data, that is, second element information.

In some possible embodiments, the second element information in the advertisement playing data set with the identification completed includes element information of the second playing data in each advertisement playing data with the identification completed.

For some possible embodiments, since the second element information includes the identification result corresponding to the second playing data, the identification tag of the first playing data in the advertisement playing data to be processed and the identification tag of the second playing data in the advertisement playing data set that has completed identification can be obtained according to the identification result of the first playing data in the advertisement playing data to be processed and the identification result of the second playing data in the advertisement playing data set that has completed identification; by comparing the similarity between the playing data in the two types of identification tags, whether the first playing data in the advertisement playing data to be processed exists in the advertisement playing data set which is identified can be determined; if the similarity is higher, determining that the first playing data in the advertisement playing data to be processed exists in the identified advertisement playing data set, and determining the identifier of the playing data with higher similarity to the second playing data in the identified advertisement playing data set as the recording data of the first playing data; thereby, the element information of the first play data, i.e., the first element information, is obtained by combining the recording data of the first play data and the recognition result of the first play data with each other.

Step S103, on the premise that the global advertisement item coefficient of the identified advertisement playing data set and the advertisement playing data to be processed accords with a specified item judgment value, target element screening is carried out on the advertisement playing data to be processed and the identified advertisement playing data set through the second element information and the first element information.

In some possible embodiments, after the identification of the advertisement playing data to be processed is completed, and the first element information of the first playing data in the advertisement playing data to be processed is determined, the currently stored identified advertisement playing data in the identified advertisement playing data set and the global advertisement item coefficient of the advertisement playing data to be processed are determined. And if the global advertisement item coefficient accords with the specified item judgment value, performing target element screening on the currently identified advertisement playing data to be processed and the advertisement playing data in the identified advertisement playing data set. If the global advertisement item coefficient does not accord with the appointed item judgment value, adding the advertisement playing data to be processed and the first element information of the corresponding first playing data into the identified advertisement playing data set, continuously obtaining the latter advertisement playing data to be processed for identification processing until the global advertisement item coefficient stored in the identified advertisement playing data set accords with the appointed item judgment value, and screening target elements.

Step S104, responding to the target element screened, and determining target playing data participating in the target element in the first playing data and the second playing data; and debugging the target playing data.

In some possible embodiments, if the target element included in the advertisement playing data to be processed and the advertisement playing data set with completed identification is more than the specified offset target value, it indicates that the target element is selected from the advertisement playing data to be processed and the advertisement playing data set with completed identification.

For some possible embodiments, if the target element is screened, the important identifier playing data where the target element is located is screened from the advertisement playing data to be processed and the advertisement playing data that has completed recognition, that is, the important identifier playing data of the target element occurs.

In this embodiment, first element information is set for the first playing data by identifying the obtained identification result and the element information stored in the identified advertisement playing data set, and the first element information can reflect the association between the first playing data in the advertisement playing data to be processed and the second playing data in the identified advertisement playing data set, so as to facilitate the subsequent identification of the target element; after the advertisement playing data to be processed is identified, judging whether the global advertisement item coefficient accords with a specified item judgment value, if the stored global advertisement item coefficient accords with the specified item judgment value, identifying target elements in the advertisement playing data to be processed and the advertisement playing data which is identified already through second element information and first element information; therefore, the target elements are screened through various advertisement playing data, and the identification result of the target elements is more accurate. If the target elements are screened, determining target playing data participating in the target elements in at least two playing data in the advertisement playing data to be processed and the identified advertisement playing data set; therefore, the accuracy and the reliability of the target playing data can be improved; therefore, the target playing data can be debugged more reliably, and the accuracy and the integrity of the advertisement data playing are improved.

In some possible embodiments, before obtaining the advertisement playing data to be processed, the type of the advertisement playing data in the currently stored advertisement playing data set that has been identified is counted, if the type of the advertisement playing data does not meet the specified item determination value, the advertisement playing data to be processed is obtained, and after the identification processing is performed, the advertisement playing data to be processed is stored in the advertisement playing data set that has been identified, that is, the following contents are included before the above step S101.

(a) And on the premise that the advertisement playing data type in the identified advertisement playing data set does not accord with the specified item judgment value, obtaining initial advertisement data corresponding to the identified advertisement playing data set.

Here, if the type of the advertisement playing data in the advertisement playing data set which has completed the identification does not meet the specified item determination value, which indicates that the type of the currently stored advertisement playing data which has completed the identification is not enough for screening the target elements, the initial advertisement data corresponding to the advertisement playing data set which has completed the identification is obtained first, then the video type is continuously obtained from the video stream, and after the video type is identified, the video type is stored in the advertisement playing data set which has completed the identification. The initial advertisement data can be understood as a video stream where the original advertisement playing data corresponding to the advertisement playing data set which has completed identification is located, the advertisement playing data which has completed identification in the advertisement playing data set which has completed identification corresponds to the video types which are distributed continuously in the initial advertisement data, that is, the advertisement playing data which has completed identification is obtained by identifying the video types.

(b) And in the initial advertisement data, determining the original video species to be processed which is distributed and continuous with the identified advertisement playing data in the identified advertisement playing data set.

(c) And preprocessing the original video species to be processed to obtain the advertisement playing data to be processed.

In some possible embodiments, if the currently stored global advertisement item coefficient does not meet the specified item determination value, the currently identified pending advertisement playing data needs to be identified, and then stored in the already identified advertisement playing data set, and the already identified kind of the advertisement playing data set is updated synchronously, so that the target element screening is performed on the premise that the global advertisement item coefficient meets the specified item determination value, that is, after the step S104, the following contents are included.

(a) And on the premise that the global advertisement item coefficient does not accord with the specified item judgment value, obtaining the latter advertisement playing data which is continuously distributed with the advertisement playing data to be processed.

In some possible embodiments, if the global advertisement item coefficient does not meet the specified item determination value, it indicates that the type of currently stored advertisement playing data subjected to the identification processing cannot be used for target element screening, and it is necessary to continue to obtain the latter advertisement playing data, so as to perform playing data identification on the latter advertisement playing data. The latter advertisement playing data is distributed continuously with the advertisement playing data to be processed and is distributed after the distribution of the advertisement playing data to be processed.

(b) And associating the third element information of the latter advertisement playing data with the latter advertisement playing data to obtain associated advertisement playing data.

In some possible embodiments, the third factor information is assigned to the latter advertisement playing data on the premise that the global advertisement item coefficient does not meet the specified item determination value. If the currently stored global advertisement item coefficient does not meet the specified item judgment value, the third element information is given to the latter advertisement playing data, namely the latter advertisement playing data of the third element information is associated. For some possible embodiments, the recorded data and the recognition result of each playing data in the third element information are respectively assigned to the playing data in the latter advertisement playing data, so that the third element information and the latter advertisement playing data are associated together.

(c) And storing the associated advertisement playing data in the advertisement playing data set which is identified, so as to obtain the mined advertisement playing data set which is identified.

In some possible implementation embodiments, the latter advertisement playing data associated with the third element information is stored in the advertisement playing data set which has completed the identification, and meanwhile, the global advertisement item coefficient after mining is counted; if the mined global advertisement item coefficient still does not accord with the specified item judgment value, continuously obtaining the latter advertisement playing data of the latter advertisement playing data and carrying out identification processing until the type of the currently stored advertisement playing data which is identified completely accords with the specified item judgment value.

(d) And on the premise that the type of the advertisement playing data of the mined identified advertisement playing data set meets the specified project judgment value, performing target element screening on the mined identified advertisement playing data set through the first element information, the second element information and the third element information.

In some possible embodiments, if the category of the advertisement playing data of the mined identified advertisement playing data set meets the specified item determination value, the target element screening is performed on the advertisement playing data stored in the mined identified advertisement playing data set based on the element information of all the advertisement playing data stored in the mined identified advertisement playing data set. The mined advertisement playing data set which is identified already comprises: and then, through the element information (namely the first element information, the second element information and the third element information) of the advertisement playing data, performing target element screening in the mined and identified advertisement playing data set so as to identify whether the advertisement playing data stored in the mined and identified advertisement playing data set includes a target element.

If the current stored global advertisement item coefficient does not accord with the appointed item judgment value, continuously obtaining the latter advertisement playing data which is continuously distributed with the advertisement playing data to be processed, and determining the third element information after identifying the latter advertisement playing data; after the latter advertisement playing data is associated with the third element information of the playing data in the advertisement playing data, the latter advertisement playing data is stored in the advertisement playing data set which is identified; and updating the global advertisement item coefficient in real time until the global advertisement item coefficient accords with the specified item judgment value, and screening the target elements of the stored advertisement playing data, thereby improving the accuracy of screening the target elements.

In some possible embodiments, a plurality of abnormal playing data are identified in the advertisement playing data to be processed, and then the abnormal playing data are screened through the bias degree to obtain the first playing data, so that the identification result of the playing data is obtained by splicing the identification tag and the category information, that is, the above step S101 may be described in the following steps S111 to S114.

And step S111, carrying out abnormal identification processing on the advertisement playing data to be processed to obtain a plurality of identification labels of the abnormal playing data.

Step S112, determining the bias degree of the plurality of abnormal playing data as the first playing data through the identification tags of the plurality of abnormal playing data.

Step S113, screening the first playing data meeting the specified requirement from the plurality of abnormal playing data according to the bias degree.

In some possible implementation embodiments, the specified requirement may be that the degree of bias is greater than a specified degree of bias target value and that the sharing weight between the identification tags is small. In this way, according to the offset of each abnormal playing data, the abnormal playing data with lower offset in the plurality of abnormal playing data is deleted, and then the abnormal playing data with higher identification tag sharing weight is cleaned, so that the abnormal playing data with higher offset and lower sharing weight among the rest abnormal playing data is determined as the first playing data, and the accuracy of identifying the first playing data can be improved.

Step S114, determining the identification result according to the identification tag of the first playing data and the category information of the first playing data.

In the above steps S111 to S114, all abnormal playing data that may be the first playing data are obtained by performing identification processing on the advertisement playing data to be processed; and then, screening first playing data meeting the specified requirement from the plurality of abnormal playing data according to the bias degree of each abnormal playing data, and thus, screening the identified abnormal playing data again to ensure that the obtained first playing data is smoother and more reliable.

In some possible embodiments, for the identified abnormal playing data, the first playing data with higher definition and accuracy is obtained through bias degree screening and washing of the sharing weight, that is, the above step S113 may be as follows.

(a) And deleting the abnormal playing data with the bias degree lower than the first bias degree target value from the plurality of abnormal playing data to obtain a plurality of other abnormal playing data.

In some possible embodiments, the bias degree of each abnormal playing data may be a confidence degree that each abnormal playing data is the first playing data, and the abnormal playing data with the bias degree lower than the target value of the first bias degree is deleted; in this way, the abnormal playing data with lower confidence is deleted, and the rest abnormal playing data are all playing data with higher possibility of being the first playing data.

(b) And determining the sharing weight among the identification tags of the plurality of remaining abnormal playing data.

In some possible embodiments, for a number of remaining abnormal playing data, a sharing weight between the identification tags of every no less than two remaining abnormal playing data is determined. For some possible embodiments, in the advertisement playing data to be processed, for every two remaining abnormal playing data, determining a comparison result between the identification tags of the two remaining abnormal playing data, and characterizing a sharing weight between the two remaining abnormal playing data through the comparison result; thus, a larger comparison result between the identification tags of the two remaining abnormal-play data indicates a larger sharing weight between the two remaining abnormal-play data.

(c) And in the rest abnormal playing data, cleaning one part of abnormal playing data of which the sharing weight is greater than the target value of the designated sharing weight to obtain the first playing data.

In some possible embodiments, the sharing weight being greater than the specified sharing weight target value indicates that the corresponding abnormal playing data has a higher confidence that the same playing data is the abnormal playing data, and therefore, if one part of the overlapped not less than two remaining abnormal playing data is cleaned. And further cleaning a part of abnormal playing data in the rest abnormal playing data with larger sharing weight among the rest abnormal playing data with smaller offset degree, and keeping the abnormal playing data with the largest offset degree.

For some possible embodiments, for some remaining pieces of playing data from which the abnormal playing data with a smaller bias degree has been deleted, the remaining abnormal playing data with a larger sharing weight and a non-maximum bias degree is cleaned, so that the cleaned abnormal playing data is determined as the first playing data.

In this embodiment, the abnormal playing data with a smaller bias degree is deleted from the plurality of abnormal playing data, so as to obtain a plurality of other abnormal playing data with a larger bias degree, and then, by analyzing the sharing weight between different other abnormal playing data, part of the abnormal playing data with a larger sharing weight is cleaned from at least two abnormal playing data with a larger sharing weight, so as to obtain the abnormal playing data with a higher bias degree and a smaller sharing weight.

In some embodiments that may be implemented, after the identification processing is performed on the advertisement playing data to be processed to obtain the identification result of the first playing data, multi-target tracking is further performed, so as to determine the difference between the first playing data and the second playing data in the identified advertisement playing data set, and further, the record data of the first playing data can be set, that is, the implementation step of the step S102 may include the following steps.

Step S201, determining differences between the first playing data and a plurality of second playing data of the identified advertisement playing data set according to the identification result and the second factor information.

Step S202, through the difference, the data to be played related to the first playing data is searched for in the plurality of second playing data.

In some possible embodiments, according to the difference between each second playing data in the identified advertisement playing data set and the first playing data in the advertisement playing data to be processed, the playing data with the highest difference and larger than the difference target value is screened from the second playing data, and is determined as the data to be played pending.

Step S203, in response to the search of the data to be played, determining the recording data of the data to be played as the recording data of the first playing data.

In some embodiments that may be implemented, if there exists in the identified advertisement playing data set playing data that has a difference greater than a difference target value from the first playing data in the advertisement playing data to be processed, the to-be-played data is searched, which further illustrates that the to-be-played data and the first playing data in the advertisement playing data to be processed are most likely to be the same playing data, and therefore, the record data of the to-be-played data in the second element information may be determined as the record data of the first playing data.

And step S204, splicing the identification result and the recorded data to obtain the first element information.

In some possible implementation embodiments, the identification result of the first playing data in the advertisement playing data to be processed and the recording data of the first playing data are determined as the first factor information.

In some possible embodiments, the differences between different playing data are obtained by the vector differences between different advertisement playing data vectors and the comparison result between the identification tags of different playing data, that is, the above step S201 can be described by the following steps S211 to S214.

Step S211, respectively performing important content identification on the advertisement playing data to be processed and the identified advertisement playing data set according to the identification result and the second element information, to obtain an advertisement playing data vector to be processed and an advertisement playing data vector having been identified.

In some possible embodiments, the identification tag of each second playing data in the advertisement playing data to which the second playing data belongs can be obtained through the identification result and the second element information of the second playing data in each advertisement playing data in the advertisement playing data set which has already been identified; and then, by identifying the important content of the area where the identification tag is located, the advertisement playing data vector to be processed and the identified advertisement playing data vector of each identified advertisement playing data can be obtained. For some possible embodiments, the advertisement playing data after the identification is completed, that is, the advertisement playing data of the identification tag marked with the second playing data, may be input into an artificial intelligence thread, and the artificial intelligence thread performs important content identification on the second playing data in the identification tag; in this way, the mentioned ad playing data vector to be processed and the identified ad playing data vector can represent the corresponding second playing data.

Step S212, determining a vector difference between the advertisement playing data vector to be processed and the advertisement playing data vector that has completed the identification.

Step S213, determining a comparison result between the identification tag of the first playing data and the identification tags of the plurality of second playing data.

In some possible embodiments, the identification tag of each second playing data in the second element information can be obtained through the second element information of the second playing data in each identified advertisement playing data set; therefore, the comparison result between the identification tag of the first playing data in the advertisement playing data to be processed and the identification tag of the second playing data in each advertisement playing data which is already identified can be determined, and the difference of the two playing data can be represented through the comparison result.

Step S214, obtaining differences between the first playing data and the plurality of second playing data according to the vector differences and/or the comparison result.

In some possible embodiments, at least one of the vector differences and the comparison result of the identification tag is used to represent differences between the first playing data in the advertisement playing data to be processed and the second playing data in each identified advertisement playing data, so that differences between different playing data can be analyzed more accurately.

In the above steps S211 to S214, by respectively identifying important content of the advertisement playing data to be processed and each advertisement playing data in the identified advertisement playing data set, vector difference is obtained; and, the result of comparison between the identification tags of different playing data; therefore, the difference between different playing data is represented by at least one of the vector difference and the comparison result, so that the difference between the playing data in different advertisement playing data can be analyzed in a multi-aspect and multi-layer manner.

In some possible embodiments, if the second playing data in the identified advertisement playing data set does not have the first playing data, the new designated record data is assigned to the first playing data in the advertisement playing data to be processed, that is, after the step S202, the following contents are also included.

(a) And in response to that the first play data is not searched, obtaining the specified recording data for identifying the first play data.

Here, the specified recording data is different from the recording data of the several second play data. If there is no playing data with a higher difference from the first playing data in the advertisement playing data to be processed in the second playing data of the advertisement playing data set that has already been identified, it indicates that the first playing data in the advertisement playing data to be processed has not been identified, that is, the identified advertisement playing data including the first playing data has not been stored. For the first play data not associated with the first play data, a specified record data different from the record data that has been currently used is newly obtained, i.e., new record data is obtained.

(b) And splicing the specified record data and the identification result to obtain the first element information.

In the above (a) and (b), on the premise that the second playing data in the advertisement playing data set which has completed the identification is not associated with the first playing data, the specified recording data which does not exist in the advertisement playing data set which has completed the identification is obtained, and the specified recording data is assigned to the first playing data; in this way, the first playback data that has not been stored is given new designated recorded data, facilitating enrichment of stored element information by the first element information including the designated recorded data.

In some possible embodiments, the second element information and the first element information are used to analyze the bias degree of the target element occurring in the already identified advertisement playing data set and the advertisement playing data to be processed, and further determine whether the target element exists in the already identified advertisement playing data set and the advertisement playing data to be processed, that is, the above step S103 may be performed through the following steps S131 and S132.

Step S131, determining, through the second element information and the first element information, that the identified advertisement playing data set and the advertisement playing data to be processed include the bias degree of the target element.

Step S132, determining whether the target element is screened from the identified advertisement playing data set and the advertisement playing data to be processed according to the bias and the second bias target value.

In some possible embodiments, after the target element is screened, important identification playing data including the target element is searched from the advertisement playing data set and the advertisement playing data to be processed, which have already completed the identification, so as to identify the target playing data participating in the target element, i.e. the above step S104 is further described.

Step S301, in response to the target element being screened, determining important identifier playing data associated with the target element in the advertisement playing data to be processed to which the first playing data belongs and the identified advertisement playing data to which the second playing data belongs.

In some possible implementation embodiments, after the target element is screened, important tag playing data of which the advertisement topic includes the target element, that is, important tag playing data associated with the target element, is searched from currently stored advertisement playing data to be processed and advertisement playing data for which recognition is completed.

For some possible embodiments, the filtering manner of the important mark playing data may include the following two manners.

Firstly, the advertisement playing data set which is recognized and the advertisement playing data to be processed, including the advertisement playing data with the optimal bias degree of the target element, are determined as important identification playing data.

Here, if the determined bias is a possibility that each advertisement playing data includes a target element, then the advertisement playing data with the best bias is screened from the determined bias, and the advertisement playing data may be the advertisement playing data to be processed or the advertisement playing data already identified.

Secondly, the advertisement playing data set which is recognized and the advertisement playing data of which the distribution condition accords with the specified condition in the advertisement playing data to be processed are determined as important mark playing data.

Here, the recognized advertisement playing data in the recognized advertisement playing data set and the advertisement playing data to be processed are distributed continuously, so that the advertisement playing data whose distribution condition meets the specified condition may be determined as the important identification playing data. The specific situation may be set based on the number of the advertisement playing data sets that have completed recognition, for example, setting the specific situation as a middle situation, a situation where the first three-third distribution of the number of the advertisement playing data sets that have completed recognition is performed, or a situation where the first three-fifth distribution of the number of the advertisement playing data sets that have completed recognition is performed, for example, determining the advertisement playing data that have been distributed in the middle situation among the advertisement playing data sets that have completed recognition and the advertisement playing data to be processed as important identification playing data. For some possible embodiments, if the determined bias is a probability that the advertisement playing data set and the advertisement playing data to be processed, which are already identified, entirely include the target element, the advertisement playing data whose distribution condition meets the specified condition is determined as the important identification playing data. Therefore, the advertisement playing data with the distribution condition meeting the designated condition is determined as the important identification playing data, so that the important identification playing data can be quickly positioned, and the accuracy of the positioned important identification playing data can be improved.

Step S302, determining the important playing data covered by the identification tag in the important identification playing data as the target playing data.

In some possible embodiments, the important play data includes the first play data or the second play data. If the important mark playing data is the advertisement playing data to be processed, the important playing data is the first playing data in the advertisement playing data to be processed; if the important identification playing data is the advertisement playing data which is already identified in the advertisement playing data set which is already identified, the important playing data is the second playing data in the advertisement playing data which is already identified. If the important identification playing data includes at least one identification tag, the important playing data included in the identification tag is the target playing data participating in the target element.

In some possible embodiments, after determining the target playing data from the first playing data and the second playing data, further determining the type of the target element so as to establish and output the element relationship between the type of the target element and the target playing data, that is, after the step S302, the following steps S303 to S305 are included.

Step S303, performing important content identification on the important playing data through the element information corresponding to the important playing data in the important identifier playing data, so as to obtain a playing data vector.

Step S304, comparing the playing data vector with the specified advertisement playing data set annotated with the target element type to obtain the type of the target element.

Step S305 optimizes the type of the target element and the target playback data.

On the basis, please refer to fig. 2 in combination, an advertisement playing progress adjusting apparatus 200 is provided, and is applied to an advertisement playing progress adjusting system, the apparatus includes:

the result identification module 210 is configured to perform identification processing on the obtained advertisement playing data to be processed to obtain an identification result of first playing data in the advertisement playing data to be processed;

an information determining module 220, configured to determine first factor information of the first playing data according to the identification result and second factor information in the advertisement playing data set that has been identified; the identified advertisement playing data set is used for storing the advertisement playing data subjected to the identification processing, and the identified advertisement playing data has second element information of second playing data in an advertisement theme;

an element screening module 230, configured to perform target element screening on the advertisement playing data to be processed and the advertisement playing data set that has completed identification through the second element information and the first element information on the premise that a global advertisement item coefficient of the advertisement playing data set that has completed identification and the advertisement playing data to be processed meets a specified item determination value;

a data debugging module 240, configured to determine, in response to the target element being screened, target playing data participating in the target element from the first playing data and the second playing data; and debugging the target playing data.

On the basis of the above, please refer to fig. 3, which shows an advertisement playing progress adjustment system 300, which includes a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program to implement the above method.

On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.

In summary, after the advertisement playing data to be processed is obtained based on the above scheme, firstly, the advertisement playing data to be processed is identified to identify the identification result of the first playing data in the advertisement playing data to be processed; secondly, combining second element information of second playing data which are centrally stored in the advertisement playing data and are already identified with the identification result to obtain first element information of the first playing data; in this way, the first element information is set for the first playing data through the identification result obtained by identification and the element information stored in the advertisement playing data set which has finished identification, and the association between the first playing data in the advertisement playing data to be processed and the first playing data in the advertisement playing data set which has finished identification can be embodied through the first element information, so that the subsequent identification of the target element is facilitated; thirdly, after the advertisement playing data to be processed are identified, judging whether the global advertisement item coefficient accords with a specified item judgment value, if the stored global advertisement item coefficient accords with the specified item judgment value, identifying the target elements in the advertisement playing data to be processed and the advertisement playing data which is identified already through the second element information and the first element information; therefore, the target elements are screened through various advertisement playing data, and the identification result of the target elements is more accurate. Finally, if the target elements are screened, determining target playing data participating in the target elements in at least two playing data in the advertisement playing data to be processed and the identified advertisement playing data set; therefore, the accuracy and the reliability of the target playing data can be improved; therefore, the target playing data can be debugged more reliably, and the accuracy and the integrity of the advertisement data playing are improved.

It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, a conventional programming language such as C, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, unless explicitly recited in the claims, the order of processing elements and sequences, use of numbers and letters, or use of other designations in this application is not intended to limit the order of the processes and methods in this application. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Where numerals describing the number of components, attributes or the like are used in some embodiments, it is to be understood that such numerals used in the description of the embodiments are modified in some instances by the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for variation in flexibility. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those explicitly described and illustrated herein.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An advertisement playing progress adjusting method is characterized by at least comprising the following steps:

identifying the obtained advertisement playing data to be processed to obtain an identification result of first playing data in the advertisement playing data to be processed;

determining first element information of the first playing data according to the identification result and second element information in the advertisement playing data set which is identified; the identified advertisement playing data set is used for storing the advertisement playing data subjected to the identification processing, and the identified advertisement playing data has second element information of second playing data in an advertisement theme;

on the premise that the global advertisement item coefficient of the identified advertisement playing data set and the advertisement playing data to be processed meets the judgment value of a designated item, performing target element screening on the advertisement playing data to be processed and the identified advertisement playing data set through the second element information and the first element information;

in response to the target element being screened, determining target playing data participating in the target element from the first playing data and the second playing data; and debugging the target playing data.

2. The method according to claim 1, wherein the identifying the obtained advertisement playing data to be processed to obtain an identification result of a first playing data in the advertisement playing data to be processed comprises:

carrying out abnormal identification processing on the advertisement playing data to be processed to obtain a plurality of identification labels of the abnormal playing data;

determining the bias degree of the plurality of abnormal playing data as the first playing data through the identification tags of the plurality of abnormal playing data;

screening the first playing data meeting the specified requirements from the plurality of abnormal playing data through the bias degree;

and determining the identification result through the identification tag of the first playing data and the category information of the first playing data.

3. The method according to claim 2, wherein the screening the first playing data meeting a specified requirement from the plurality of abnormal playing data by the bias degree comprises:

deleting the abnormal playing data of which the bias degree is lower than the first bias degree target value from the plurality of abnormal playing data to obtain a plurality of other abnormal playing data;

determining a sharing weight between the identification tags of the plurality of remaining abnormal playing data;

and cleaning a part of abnormal playing data with the sharing weight larger than the specified sharing weight target value in the rest abnormal playing data to obtain the first playing data.

4. The method according to any one of claims 1 to 3, wherein the determining first factor information of the first playing data according to the identification result and the second factor information in the advertisement playing data set that has completed identification comprises:

determining differences between the first playing data and a plurality of second playing data of the identified advertisement playing data set through the identification result and the second element information;

searching the second playing data for pending playing data associated with the first playing data through the difference;

in response to the search of the data to be played, determining the recording data of the data to be played as the recording data of the first playing data;

and splicing the identification result and the recorded data to obtain the first element information.

5. The method according to claim 1, wherein the determining, from the identification result and the second element information, the difference between the first playing data and a plurality of second playing data of the identified advertisement playing data set comprises:

respectively identifying important contents of the advertisement playing data to be processed and the identified advertisement playing data set according to the identification result and the second element information to obtain an advertisement playing data vector to be processed and an advertisement playing data vector with the identified advertisement playing data vector;

determining vector difference between the advertisement playing data vector to be processed and the advertisement playing data vector which is identified already;

determining a comparison result between the identification tag of the first playing data and the identification tags of the plurality of second playing data;

and obtaining differences between the first playing data and the plurality of second playing data through the vector differences and/or the comparison result.

6. The method according to claim 4, wherein after searching the second playing data for the pending playing data associated with the first playing data through the difference, the method further comprises:

in response to that the data to be played is not searched, obtaining specified recording data for identifying the first playing data; wherein the specified recording data is different from the recording data of the plurality of second playing data;

and splicing the specified record data and the identification result to obtain the first element information.

7. The method as claimed in claim 6, wherein the performing target element screening on the advertisement playing data to be processed and the advertisement playing data set that has completed identification through the second element information and the first element information on the premise that the global advertisement item coefficient of the advertisement playing data set that has completed identification and the advertisement playing data to be processed meets a specified item determination value comprises:

determining the bias degree of the target element in the identified advertisement playing data set and the advertisement playing data to be processed according to the second element information and the first element information;

and determining whether the target elements are screened from the advertisement playing data set which is identified and the advertisement playing data to be processed or not through the bias degree and the second bias degree target value.

8. The method according to claim 1, wherein the determining, in response to the screening of the target element, target play data participating in the target element, from among the first play data and the second play data; and debugging the target playing data, including:

in response to the target element being screened, important identification playing data associated with the target element is determined in the advertisement playing data to be processed to which the first playing data belongs and the advertisement playing data which is identified and belongs to which the second playing data belongs;

determining the important playing data covered by the identification tag in the important identification playing data as the target playing data; wherein the important playing data comprises the first playing data or the second playing data;

after determining the important playing data covered by the identification tag in the important identification playing data as the target playing data, the method further includes:

identifying important contents of the important playing data through the element information corresponding to the important playing data in the important identification playing data to obtain a playing data vector

Comparing the playing data vector with an appointed advertisement playing data set annotated with the type of the target element to obtain the type of the target element;

optimizing the types of the target elements and the target playing data;

wherein the important identification playing data comprises one or more of the following items:

the advertisement playing data set which is identified and the advertisement playing data to be processed comprise the advertisement playing data with the optimal bias degree of the target element;

the identified advertisement playing data set and the advertisement playing data with the distribution condition meeting the specified condition in the advertisement playing data to be processed;

after determining the first element information of the first playing data according to the identification result and the second element information in the advertisement playing data set which has completed identification, the method further comprises:

on the premise that the global advertisement item coefficient does not accord with the specified item judgment value, obtaining the latter advertisement playing data which is continuously distributed with the advertisement playing data to be processed; associating the third element information of the latter advertisement playing data with the latter advertisement playing data to obtain associated advertisement playing data;

storing the associated advertisement playing data in the advertisement playing data set which is identified, so as to obtain a mined advertisement playing data set which is identified;

and on the premise that the advertisement playing data type of the mined identified advertisement playing data set meets the specified project judgment value, performing target element screening on the mined identified advertisement playing data set through the first element information, the second element information and the third element information.

9. An advertisement playing progress adjustment system, comprising: the progress adjustment cloud platform is in communication connection with the advertisement data acquisition end;

wherein, the progress adjustment cloud platform is used for: identifying the obtained advertisement playing data to be processed to obtain an identification result of first playing data in the advertisement playing data to be processed; determining first element information of the first playing data according to the identification result and second element information in the advertisement playing data set which is already identified; the identified advertisement playing data set is used for storing the advertisement playing data subjected to the identification processing, and the identified advertisement playing data has second element information of second playing data in an advertisement theme; on the premise that the global advertisement item coefficient of the identified advertisement playing data set and the advertisement playing data to be processed meets the judgment value of a designated item, performing target element screening on the advertisement playing data to be processed and the identified advertisement playing data set through the second element information and the first element information; in response to the target element being screened, determining target playing data participating in the target element from the first playing data and the second playing data; and debugging the target playing data.

10. A progress-adjusting cloud platform, comprising:

a memory for storing a computer program;

a processor coupled to the memory for executing the computer program stored by the memory to implement the method of any of claims 1-8.