CN113988949A - Promotion information processing method, device, equipment, medium and program product - Google Patents
Promotion information processing method, device, equipment, medium and program product Download PDFInfo
- Publication number
- CN113988949A CN113988949A CN202111348147.6A CN202111348147A CN113988949A CN 113988949 A CN113988949 A CN 113988949A CN 202111348147 A CN202111348147 A CN 202111348147A CN 113988949 A CN113988949 A CN 113988949A
- Authority
- CN
- China
- Prior art keywords
- feature
- feature vector
- sample
- information
- library
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 17
- 238000003672 processing method Methods 0.000 title abstract description 6
- 239000013598 vector Substances 0.000 claims abstract description 273
- 238000000034 method Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims description 88
- 230000001737 promoting effect Effects 0.000 claims description 33
- 239000000463 material Substances 0.000 claims description 26
- 238000012986 modification Methods 0.000 claims description 24
- 230000004048 modification Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012423 maintenance Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000012015 optical character recognition Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 208000001613 Gambling Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/41—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/45—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0276—Advertisement creation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The present disclosure provides a promotion information processing method, apparatus, device, medium, and program product. The method comprises the following steps: acquiring a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information; acquiring a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped; and constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination. The method can save computing resources and improve the efficiency of constructing the model.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, a computer-readable storage medium, and a computer program product for promoting information processing.
Background
Merchants typically publish promotional information (e.g., advertisements) carrying target objects (e.g., promoted digital products, tourist attractions, literary works, etc.), increase the user's attention to the target objects, and guide the user to consume the target objects. With the development of the artificial intelligence technology, the popularization information can be identified from multiple angles (such as the angle of visual effect and the angle of auditory effect) by constructing popularization information identification models of multiple different types, and then modification suggestions of multiple angles are obtained. Therefore, the popularization information is modified based on the modification suggestions at a plurality of angles, the popularization information with friendly visual effect and auditory effect can be obtained, and a good popularization effect is achieved.
At present, in the process of constructing a popularization information identification model, an identifier of sample popularization information, such as a Uniform Resource Locator (URL), needs to be obtained from a database, the sample popularization information is obtained through the identifier, vectorization processing is performed on the sample popularization information to obtain a feature vector (such as a text vector and an image vector), and then model training is performed based on the feature vector to obtain the popularization information identification model.
However, when a plurality of different types of popularization information recognition models need to be constructed, the above-mentioned process of vectorizing the sample popularization information needs to be repeated to obtain the feature vector for model training. Therefore, the above method for repeating the vectorization processing of the sample popularization information not only causes the waste of computing resources, but also reduces the efficiency of model construction.
Disclosure of Invention
The purpose of the present disclosure is: provided are a method, a device and equipment for processing promotion information, a computer readable storage medium and a computer program product, which can save computing resources and improve the efficiency of constructing a model.
In a first aspect, the present disclosure provides a method for processing promotion information, including:
acquiring a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information;
acquiring a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped;
and constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination.
In a second aspect, the present disclosure provides a popularization information processing apparatus including:
the system comprises a vector unit, a characteristic library and a processing unit, wherein the vector unit is used for acquiring the characteristic library which comprises a characteristic vector obtained by vectorizing at least one sample popularization information;
an obtaining unit, configured to obtain a first feature vector combination and a second feature vector combination from the feature library, where the first feature vector combination and the second feature vector combination overlap;
and the construction unit is used for constructing a first popularization information identification model by using the first characteristic vector combination and constructing a second popularization information identification model by using the second characteristic vector combination.
In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method of any one of the first aspects of the present disclosure.
In a fourth aspect, the present disclosure provides an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to implement the steps of the method of any one of the first aspect of the present disclosure.
In a fifth aspect, the present disclosure provides a computer program product comprising instructions which, when run on a device, cause the device to perform the method according to any of the implementations of the first aspect.
According to the technical scheme, the method has the following advantages:
the method includes the steps that a plurality of feature vector combinations, such as a first feature vector combination and a second feature vector combination, are obtained on the basis of feature vectors obtained by vectorizing sample popularization information in a feature library, and the first feature vector combination and the second feature vector combination are overlapped. In the process of constructing the first popularization information identification model by using the first feature vector combination and constructing the second popularization information identification model by using the second feature vector combination, for the feature vectors overlapped in the first feature vector combination and the second feature vector combination, the overlapped feature vectors are obtained by performing one-time vectorization processing on the sample popularization information, and the sample popularization information does not need to be subjected to vectorization processing again. Therefore, the method not only saves computing resources, but also improves the efficiency of constructing the model.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
In order to more clearly illustrate the technical method of the embodiments of the present disclosure, the drawings used in the embodiments will be briefly described below.
Fig. 1 is a flowchart of a method for promoting information processing according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a feature classification provided by an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a sample popularization information vectorization process according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of an apparatus for promoting information processing according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
The terms "first", "second" in the embodiments of the present disclosure are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.
Some technical terms involved in the embodiments of the present disclosure will be described first.
The promotion information is information for promoting or advertising a target object. The promotional information may be an advertisement, for example. By publishing the advertisement, the attention of the user to the target object in the advertisement can be improved. In some examples, users may be called upon to save water resources through advertisements; the user can also be guided to consume the digital products and the like in the advertisement through the advertisement. In order to enable the promotion information to achieve a good promotion effect, based on an artificial intelligence technology, promotion information identification models of various different types are constructed, and then the promotion information is identified from multiple angles to obtain modification suggestions from multiple angles.
When the sample promotion information is a video advertisement, the sample promotion information is directly stored, and a large storage space is needed. In order to reduce the storage space occupied by the sample promotion information, a URL that only stores the sample promotion information in the database is usually adopted, and when the sample promotion information needs to be used (for example, a promotion information identification model is constructed based on the sample promotion information), the sample promotion information is obtained according to the URL. When a plurality of different types of popularization information identification models are constructed, the same sample popularization information needs to be repeatedly subjected to vectorization processing for many times.
Taking the first popularization information identification model and the second popularization information identification model as an example, in the process of constructing the first popularization information identification model, sample popularization information needs to be obtained first, then vectorization processing is carried out on the sample popularization information to obtain a feature vector of the sample popularization information, and then the first popularization information identification model is constructed based on the feature vector. In the process of constructing the first popularization information identification model, the feature vector obtained after vectorization processing is performed on the sample popularization information is not stored, so that vectorization processing needs to be performed on the sample popularization information again in the subsequent process of constructing the second popularization information identification model. The same sample popularization information is repeatedly subjected to vectorization processing, so that not only is the computing resource waste caused, but also the model building efficiency is reduced.
In view of this, the present disclosure provides a method for processing promotion information. Specifically, the method comprises the steps of obtaining a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information, obtaining a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped, then constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination.
In the method, in the process of constructing the first popularization information identification model by using the first feature vector combination and constructing the second popularization information identification model by using the second feature vector combination, for the overlapped feature vectors in the first feature vector combination and the second feature vector combination, the overlapped feature vectors are obtained by carrying out one-time vectorization processing on sample popularization information, and the overlapped feature vectors are used for constructing various popularization information identification models. Therefore, in the process of constructing various models, the method does not need to carry out vectorization processing on the sample popularization information again by directly obtaining the characteristic vectors from the characteristic library, so that not only is the computing resource saved, but also the efficiency of constructing the models is improved.
Further, in the process of storing the feature vector into the feature library, the method can also calculate the similarity between the feature vector stored in the feature library and the feature vector to be stored, and when the similarity is lower than a preset threshold, the feature vector to be stored is stored into the feature library. Therefore, the method can also reduce the feature vectors with higher similarity in the feature library, and further save the storage space required for storing the feature vectors.
In some possible implementations, the promotion information processing method described above may be performed by a processing device. Wherein the processing device may be a device having a data processing function. The processing device may be a terminal or a server. The terminal includes, but is not limited to, a smart phone, a tablet computer, a notebook computer, a Personal Digital Assistant (PDA), or a smart wearable device. The server may be a cloud server, such as a central server in a central cloud computing cluster, or an edge server in an edge cloud computing cluster. Of course, the server may also be a server in a local data center. The local data center refers to a data center directly controlled by a user.
In order to make the technical solution of the present disclosure clearer and easier to understand, the following introduces the popularization information processing method provided by the embodiment of the present disclosure from the perspective of a processing device.
As shown in fig. 1, the figure is a flowchart of a method for promoting information processing provided by an embodiment of the present disclosure, and the method may be executed by a processing device. Specifically, the method comprises the following steps:
s101: the processing device obtains a library of features.
The feature library comprises a feature vector obtained by vectorizing at least one sample popularization information, and the feature vector of the at least one sample popularization information is stored in the feature library.
In some embodiments, the processing device may pre-build the library of features. The processing device can perform vectorization processing on the sample promotion information from multiple dimensions, and then obtain feature vectors corresponding to the multiple dimensions respectively. Wherein the plurality of dimensions may include any combination of audio, video, pictures and text. For example, the processing device may perform vectorization processing on the sample popularization information from the picture dimension and the character dimension to obtain a feature vector corresponding to the picture dimension and a feature vector corresponding to the character dimension, and then store the feature vector corresponding to the picture dimension and the feature vector corresponding to the character dimension into the feature library to further implement construction of the feature library. The embodiment of the disclosure provides a method for vectorizing sample popularization information, and the following detailed description is provided.
It should be noted that, the above description is only given by taking a way of vectorizing one sample popularization information as an example, in an actual process, the processing device performs vectorization processing on each sample popularization information in at least one sample popularization information by using the above way of vectorizing one sample popularization information, so as to obtain a feature vector of each sample popularization information, and further enrich feature vectors in the feature library.
In other embodiments, the processing device may also directly obtain a pre-constructed feature library, where the feature library includes a feature vector obtained by vectorizing at least one sample popularization information. The method of pre-constructing the feature library may be introduced in the above-mentioned manner, and will not be described herein again.
In some possible implementations, the sample promotional information may be a sample advertisement. Based on this, the processing device may classify features represented by the feature vectors stored in the feature library based on the sample advertisements. For example, the feature vector stored in the feature library may include at least one of a distributor feature of the sample promotion information, a material content feature of the sample promotion information, a material remark feature of the sample promotion information, a modification suggestion feature of the sample promotion information, and a version maintenance feature of the sample promotion information.
As shown in fig. 2, a schematic of feature classification is shown. Taking sample promotion information as a sample advertisement as an example, the sample advertisement can be divided into a sponsor characteristic of the advertisement, a plan or creative characteristic of the advertisement, a material remark characteristic of the advertisement, a modification suggestion characteristic of the advertisement, a version maintenance characteristic of the advertisement and the like. Wherein the planning or creative characteristics of the advertisement and the material characteristics of the advertisement may be collectively referred to as the material content characteristics of the advertisement.
Further, the processing device can subdivide the characteristics of the advertisement emitters into emitter categories, emitter head portraits and emitter sources; it should be noted that all of these pieces of information need to obtain the authorization of the user in advance, and after obtaining the authorized use of the corresponding data by the user, the processing device can obtain the data such as the characteristics of the publisher.
The material content characteristics of the advertisement are subdivided into a document, a picture, a video, landing pages, the affiliated industry, the creative number, the document number, the picture number and the video number; subdividing the material remark characteristics of the advertisement into qualification authorization information, validity period, trademark and logo; the version maintenance feature for an advertisement is subdivided into a number of modifications and a number of submissions.
It should be noted that the schematic diagram of feature classification shown in fig. 2 is only one possible classification manner, and a person skilled in the art may select other manners to perform classification according to actual needs, which is not limited in the embodiment of the disclosure.
In some embodiments, the processing device may further update the sample popularization information, and then store the feature vector obtained by vectorizing the updated sample popularization information in the feature library. For example, the processing device may update the sample advertisement, and then store the feature vector obtained by vectorizing the updated sample advertisement in the feature library.
In some possible implementations, the processing device may obtain an update request for the sample advertisement, where the update request carries updated information of the sample advertisement, and then update the sample advertisement according to the updated information carried in the update request. The updated information of the sample advertisement may be the above-mentioned advertiser head portrait, advertiser category, file, picture, etc. In some examples, when a publisher avatar needs to be updated, a new publisher avatar may be carried in the update request, and the processing device may update the original advertisement based on the new publisher avatar.
Then, the processing device stores the feature vector obtained by vectorizing the updated head portrait of the publisher into the feature library, and adds a version identifier (for example, a version number) to the feature vector of the updated head portrait of the publisher. In some examples, the processing device may store the feature vector of the avatar of the publisher before the update and the feature vector of the avatar of the publisher after the update simultaneously by assigning version identifications to the feature vector of the avatar of the publisher before the update and the feature vector of the avatar of the publisher after the update. For example, the version of the feature vector of the avatar of the publisher before update is denoted by "V1.1", and the version of the feature vector of the avatar of the publisher after update is denoted by "V1.2".
It should be noted that the version identifiers are merely examples, and the embodiments of the present disclosure do not specifically limit the form of the version identifiers.
In other embodiments, the processing device may further update categories, head portraits, sources, and the like of the publishers in the characteristics of the publishers, update detailed texts, pictures, videos, landing pages, industries, creative numbers, text numbers, picture numbers, video numbers, and the like of the material content characteristics, update qualification authorization information, validity periods, trademarks, logos, and the like in the characteristics of the material remarks of the advertisements, and update the number of modifications and submission times, and the like in the version maintenance characteristics of the advertisements.
In some possible implementations, the processing device may classify characteristics of the sample ads into long-term characteristics and short-term characteristics based on how frequently the sample ads are updated. Wherein the long-term characteristic is a characteristic in which the frequent degree of update is lower than a preset degree, and the short-term characteristic is a characteristic in which the frequent degree of update is higher than or equal to the preset degree. The frequency of the updates may be characterized by the number of updates within a preset time, for example, the frequency may be 3 updates within a week. For example, the preset degree may be a one-time update within one month, the long-term characteristic is a characteristic that the number of updates within one month is lower than one time, and the short-term characteristic is a characteristic that the number of updates within one month is higher than or equal to one time.
In an actual scene, the frequency of updating the characteristics of the advertisement placers and the modification suggestion characteristics of the advertisement by the processing device is low, for example, both are lower than the preset degree; the material characteristic of the advertisement, the planning or creative characteristic of the advertisement, the material remark characteristic of the advertisement and the version maintenance characteristic of the advertisement are updated more frequently by the processing device, for example, both are higher than or equal to the preset degree. Based on this, the long-term features may include a sponsor feature of the advertisement and a modification suggestion feature of the advertisement, and the short-term features may include a material feature of the advertisement, a planning or creative feature of the advertisement, a material remark feature of the advertisement, and a version maintenance feature of the advertisement.
S102: the processing device obtains a first feature vector combination and a second feature vector combination from the feature library, and the first feature vector combination and the second feature vector combination are overlapped.
The first feature vector combination comprises a plurality of feature vectors, such as feature vector 1, feature vector 2 and feature vector 3; the second combination of feature vectors includes a plurality of feature vectors, such as feature vector 2, feature vector 3, and feature vector 4. In some examples, the overlapping of the first feature vector combination and the second feature vector combination means that the feature vector 2 and the feature vector 3 are included in both the first feature vector combination and the second feature vector combination.
It should be noted that the number of overlapped eigenvectors is not particularly limited in the embodiments of the present disclosure, and the above example is only described with the example that the number of overlapped eigenvectors is 2. Of course, in an actual scenario, the number of the overlapped feature vectors may also be 1, and may also be more, for example, 4 or 5.
For the overlapped feature vectors (e.g., feature vector 2 and feature vector 3) described above, the processing device does not need to perform vectorization processing on the sample popularization information again, but directly acquires the overlapped feature vectors from the feature library. Therefore, the method reduces the times of vectorization processing of the sample popularization information by the processing equipment and saves the computing resources.
In some possible implementations, the processing device may obtain, based on a feature identifier (e.g., a feature number, a feature sequence number, etc.) of the feature vector, a feature vector corresponding to the feature identifier from a feature library. Continuing the above example, the processing device may obtain the feature vector 1, the feature vector 2, and the feature vector 3 from the feature library respectively based on the feature identifier of the feature vector 1, the feature identifier of the feature vector 2, and the feature identifier of the feature vector 3, and further obtain the first feature vector combination. Similarly, the processing device may obtain the feature vector 2, the feature vector 3, and the feature vector 4 from the feature library respectively based on the feature identifier of the feature vector 2, the feature identifier of the feature vector 3, and the feature identifier of the feature vector 4, so as to obtain the second feature vector combination.
In other possible implementations, one feature identifier may correspond to a plurality of different versions of feature vectors in the feature library. Based on the above, the processing device may further determine, based on the feature identifier of the feature vector and the version identifier of the feature vector, the feature vectors of a plurality of different versions corresponding to the feature identifier, and then obtain, based on the version identifier, the feature vector corresponding to the version identifier. See table 1 below:
table 1:
wherein, the feature identifier "001" corresponds to "feature vector 1-1", "feature vector 1-2" and "feature vector 1-3", and the version identifiers thereof are "V1.1", "V1.2" and "V1.3", respectively. The feature identifier "002" corresponds to "feature vector 2-1" and "feature vector 2-2", the version identifiers of which are "V1.1" and "V1.2", respectively. In some examples, when the feature identification is "001" and the version identification is "V1.2", the processing device may acquire "feature vector 1-2" from the feature library based on the correspondence relationship described in table 1 above.
S103: the processing device constructs a first promotion information identification model by using the first feature vector combination, and constructs a second promotion information identification model by using the second feature vector combination.
And then the processing equipment utilizes the first feature vector combination obtained from the feature library to construct a first popularization information identification model, and utilizes the second feature vector combination to construct a second popularization information identification model. The first popularization information identification model and the second popularization information identification model are used for identifying the popularization information to be identified from different angles, and then identification results for different angles are obtained.
In some embodiments, after constructing the first promotional information identification model and the second promotional information identification model, the processing device may also identify promotional information using the first promotional information identification model and the second promotional information identification model. Specifically, the processing device may obtain popularization information to be recognized, input the popularization information to be recognized to the first popularization information recognition model to obtain a first recognition result, and input the popularization information to be recognized to the second popularization information recognition model to obtain a second recognition result. The first recognition result and the second recognition result comprise modification suggestions different from the promotion information to be recognized. For example, the first recognition result includes a first modification suggestion for the promotion information to be recognized, and the second recognition result includes a second modification suggestion for the promotion information to be recognized, where the first modification suggestion is different from the second modification suggestion.
In some examples, the promotional information to be identified may be unpublished promotional information. Therefore, the undistributed popularization information can be modified from multiple angles based on the first identification result and the second identification result, and the popularization effect of the undistributed popularization information after being published is improved.
In other examples, the promotional information to be identified may also be published promotional information. In this way, whether the issued promotion information meets the requirement can be judged from multiple angles based on the first recognition result and the second recognition result. When the first recognition result or the second recognition result indicates that the issued promotion information does not meet the requirement, taking the example that the first recognition result does not meet the requirement, the modification suggestion included in the first recognition result may be "the promotion information includes words such as 'XX', which may be related to gambling, suggests putting treatment", and then, according to the modification suggestion, the put treatment may be performed on the issued promotion information, thereby reducing the number of poor promotion information.
Based on the above description, the embodiments of the present disclosure provide a method for processing promotion information. The method comprises the steps of firstly obtaining a feature library based on a feature vector obtained by vectorizing sample popularization information, and then obtaining a plurality of feature vector combinations, such as a first feature vector combination and a second feature vector combination, from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped. In the process of constructing the first popularization information identification model by using the first feature vector combination and constructing the second popularization information identification model by using the second feature vector combination, for the overlapped feature vectors in the first feature vector combination and the second feature vector combination, the overlapped feature vectors are obtained by performing one-time vectorization processing on the sample popularization information, and the overlapped feature vectors are used for constructing various popularization information identification models. Therefore, in the process of constructing various models, the method does not need to carry out vectorization processing on the sample popularization information again by directly obtaining the characteristic vectors from the characteristic library, so that not only is the computing resource saved, but also the efficiency of constructing the models is improved.
The embodiment of the present disclosure provides a way to perform vectorization processing on sample popularization information, which is described in detail below.
As shown in fig. 3, a schematic diagram of vectorizing sample promotion information is shown. Taking the sample promotion information as an advertisement as an example, the sample promotion information may include a picture material, a video material, a landing page material, and the like. Wherein the picture material further comprises a picture and an Optical Character Recognition (OCR) text of the picture; the video material further comprises video frame pictures, video frame OCR texts and video Automatic Speech Recognition (ASR) texts; the landing page material further comprises a picture, a video frame, a picture OCR text, a video frame OCR text, a landing page text and a video ASR text. The sample promotion information may further include discrete features and a document, wherein the discrete features may be industries and the like to which the sample promotion information belongs, and the document may be a title, a material title and the like of the sample promotion information.
The processing device may employ different vectorization approaches for different forms of data. In some embodiments, for discrete features, the processing device may perform vectorization in a One-Hot encoding manner to obtain discrete feature vectors. For short texts such as a case and a video ASR text, the processing device may perform vectorization in a transform manner to obtain a text feature vector, where the short text may be a text with less characters than a preset number of characters. For the text with the same length as the landing page text, the processing equipment can carry out vectorization in a pre-training language model XLNET mode to obtain the text characteristic vector. The image OCR text and the video frame OCR text can be vectorized in a convolution and pooling mode to obtain text feature vectors. For pictures and video frame pictures, the processing equipment can carry out vectorization in a residual error network ResNet mode to obtain picture characteristic vectors.
Next, the processing device may store the discrete Feature vectors, the text Feature vectors, and the picture Feature vectors described above in a Feature library (Feature rendering). In some possible implementation manners, the processing device may further calculate similarities between a target feature vector in the feature vectors of the multiple dimensions and historical feature vectors in the feature library, for example, taking the target feature vector as a text feature vector, the processing device may calculate similarities between the text feature vector and the historical feature vectors in the feature library, and when the similarities are lower than a preset threshold, the processing device may store the text feature vector in the feature library; when the similarity is higher than or equal to the preset threshold, the processing equipment does not need to store the text feature vector into the feature library, so that the density of removing the duplicate of the feature vector stored in the feature library is realized, and the storage space required by storing the feature vector is saved.
Based on the above description, in the method for processing popularization information provided in the embodiment of the present disclosure, in the process of storing the feature vector obtained after the vectorization processing in the feature library, when the similarity between the feature vector to be stored and the historical feature vector in the feature library is high, the feature vector to be stored is no longer stored in the feature library, so that the storage resource required for storing the feature vector is reduced. Therefore, when the model is required to be built subsequently, the feature vector is only required to be directly obtained from the feature library, and the vectorization processing is not required to be carried out on the sample clearance information again, so that the computing resource is saved, and the model building efficiency is improved. And after the feature vector obtained by vectorizing the sample popularization information is stored in the feature library, when the feature vector in the feature library is needed to be used in other scenes, the feature vector can be directly obtained from the feature library and used, and the application range of the feature library is expanded.
Fig. 4 is a schematic diagram illustrating a promotion information processing apparatus according to an exemplary disclosed embodiment, the promotion information processing apparatus, as shown in fig. 4, including:
a vector unit 401, configured to obtain a feature library, where the feature library includes a feature vector obtained by performing vectorization processing on at least one sample popularization information;
an obtaining unit 402, configured to obtain a first feature vector combination and a second feature vector combination from the feature library, where the first feature vector combination and the second feature vector combination overlap;
a constructing unit 403, configured to construct a first popularization information identification model by using the first feature vector combination, and construct a second popularization information identification model by using the second feature vector combination.
Optionally, the vector unit 401 is specifically configured to perform vectorization processing on each sample popularization information in the at least one sample popularization information from multiple dimensions to obtain feature vectors respectively corresponding to the multiple dimensions; and constructing a feature library according to the feature vectors respectively corresponding to the dimensions.
Optionally, the multiple dimensions include any combination of audio, video, pictures and text.
Optionally, the feature vector includes at least one of a distributor feature of the sample popularization information, a material content feature of the sample popularization information, a material remark feature of the sample popularization information, a modification suggestion feature of the sample popularization information, and a version maintenance feature of the sample popularization information.
Optionally, the vector unit 401 is specifically configured to store the target feature vector into the feature library when the similarity between the target feature vector in the feature vectors corresponding to the multiple dimensions and the historical feature vector in the feature library is lower than a preset threshold.
Optionally, the apparatus further comprises: an update unit; the updating unit is used for updating the at least one sample promotion message; and vectorizing each sample popularization information in the updated at least one sample popularization information to obtain a feature vector, and storing the feature vector into the feature library.
Optionally, the apparatus further comprises: an identification unit; the identification unit is used for acquiring promotion information to be identified; and respectively inputting the popularization information to be recognized into the first popularization information recognition model and the second popularization information recognition model to obtain a first recognition result and a second recognition result, wherein the first recognition result and the second recognition result comprise different modification suggestions for the popularization information to be recognized.
The functions of the above modules have been elaborated in the method steps in the previous embodiment, and are not described herein again.
Referring now to fig. 5, a schematic diagram of an electronic device 500 suitable for implementing an embodiment of the present disclosure is shown, which may be used to implement the corresponding functions of the generalized information processing apparatus shown in fig. 5. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 501.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information; acquiring a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped; and constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of the module does not in some cases form a limitation of the module itself, for example, the first obtaining module may also be described as a "module for obtaining at least two internet protocol addresses".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example 1 provides a popularization information processing method according to one or more embodiments of the present disclosure, including:
acquiring a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information;
acquiring a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped;
and constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination.
Example 2 provides the method of example 1, the obtaining a feature library, comprising:
vectorizing each sample promotion information in the at least one sample promotion information from a plurality of dimensions to obtain feature vectors respectively corresponding to the plurality of dimensions;
and constructing a feature library according to the feature vectors respectively corresponding to the dimensions.
Example 3 provides the method of example 2, the plurality of dimensions comprising any combination of audio, video, pictures, and text, in accordance with one or more embodiments of the present disclosure.
Example 4 provides the method of example 2, the feature vector including at least one of a presenter feature of the sample promotional information, a material content feature of the sample promotional information, a material remark feature of the sample promotional information, a modification suggestion feature of the sample promotional information, and a version maintenance feature of the sample promotional information.
Example 5 provides the method of example 2, the constructing a feature library from feature vectors corresponding to the plurality of dimensions, respectively, including:
and when the similarity between a target feature vector in the feature vectors respectively corresponding to the multiple dimensions and a historical feature vector in a feature library is lower than a preset threshold, storing the target feature vector into the feature library.
Example 6 provides the method of example 1, further comprising, in accordance with one or more embodiments of the present disclosure:
updating the at least one sample promotion information;
and vectorizing each sample popularization information in the updated at least one sample popularization information to obtain a feature vector, and storing the feature vector into the feature library.
Example 7 provides the methods of examples 1-6, further comprising, in accordance with one or more embodiments of the present disclosure:
acquiring popularization information to be identified;
and respectively inputting the popularization information to be recognized into the first popularization information recognition model and the second popularization information recognition model to obtain a first recognition result and a second recognition result, wherein the first recognition result and the second recognition result comprise different modification suggestions for the popularization information to be recognized.
Example 8 provides, according to one or more embodiments of the present disclosure, a popularization information processing apparatus including:
the system comprises a vector unit, a characteristic library and a processing unit, wherein the vector unit is used for acquiring the characteristic library which comprises a characteristic vector obtained by vectorizing at least one sample popularization information;
an obtaining unit, configured to obtain a first feature vector combination and a second feature vector combination from the feature library, where the first feature vector combination and the second feature vector combination overlap;
and the construction unit is used for constructing a first popularization information identification model by using the first characteristic vector combination and constructing a second popularization information identification model by using the second characteristic vector combination.
According to one or more embodiments of the present disclosure, example 9 provides the apparatus of example 8, where the vector unit is specifically configured to perform vectorization processing on each sample popularization information in the at least one sample popularization information from multiple dimensions, to obtain feature vectors respectively corresponding to the multiple dimensions; and constructing a feature library according to the feature vectors respectively corresponding to the dimensions.
Example 10 provides the apparatus of example 9, the plurality of dimensions comprising any combination of audio, video, pictures, and text, in accordance with one or more embodiments of the present disclosure.
Example 11 provides the apparatus of example 9, the feature vector including at least one of a sponsor feature of the sample promotional information, a material content feature of the sample promotional information, a material remark feature of the sample promotional information, a modification suggestion feature of the sample promotional information, and a version maintenance feature of the sample promotional information, in accordance with one or more embodiments of the present disclosure.
Example 12 provides the apparatus of example 9, and the vector unit is specifically configured to store a target feature vector in the feature library when a similarity between the target feature vector and a historical feature vector in the feature library is lower than a preset threshold, where the target feature vector corresponds to each of the plurality of dimensions.
Example 13 provides the apparatus of example 8, in accordance with one or more embodiments of the present disclosure, further comprising: an update unit; the updating unit is used for updating the at least one sample promotion message; and vectorizing each sample popularization information in the updated at least one sample popularization information to obtain a feature vector, and storing the feature vector into the feature library.
Example 14 provides the apparatus of examples 8-13, the apparatus further comprising, in accordance with one or more embodiments of the present disclosure: an identification unit; the identification unit is used for acquiring promotion information to be identified; and respectively inputting the popularization information to be recognized into the first popularization information recognition model and the second popularization information recognition model to obtain a first recognition result and a second recognition result, wherein the first recognition result and the second recognition result comprise different modification suggestions for the popularization information to be recognized.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (11)
1. A method of promotional information processing, comprising:
acquiring a feature library, wherein the feature library comprises a feature vector obtained by vectorizing at least one sample popularization information;
acquiring a first feature vector combination and a second feature vector combination from the feature library, wherein the first feature vector combination and the second feature vector combination are overlapped;
and constructing a first popularization information identification model by using the first feature vector combination, and constructing a second popularization information identification model by using the second feature vector combination.
2. The method of claim 1, wherein the obtaining a feature library comprises:
vectorizing each sample promotion information in the at least one sample promotion information from a plurality of dimensions to obtain feature vectors respectively corresponding to the plurality of dimensions;
and constructing a feature library according to the feature vectors respectively corresponding to the dimensions.
3. The method of claim 2, wherein the plurality of dimensions comprise any combination of audio, video, pictures, and text.
4. The method of claim 2, wherein a feature vector comprises at least one of a sponsor feature of the sample promotional information, a material content feature of the sample promotional information, a material remark feature of the sample promotional information, a modification recommendation feature of the sample promotional information, and a version maintenance feature of the sample promotional information.
5. The method of claim 2, wherein constructing the feature library from the feature vectors corresponding to the plurality of dimensions, respectively, comprises:
and when the similarity between a target feature vector in the feature vectors respectively corresponding to the multiple dimensions and a historical feature vector in a feature library is lower than a preset threshold, storing the target feature vector into the feature library.
6. The method of claim 1, further comprising:
updating the at least one sample promotion information;
and vectorizing each sample popularization information in the updated at least one sample popularization information to obtain a feature vector, and storing the feature vector into the feature library.
7. The method according to any one of claims 1 to 6, further comprising:
acquiring popularization information to be identified;
and respectively inputting the popularization information to be recognized into the first popularization information recognition model and the second popularization information recognition model to obtain a first recognition result and a second recognition result, wherein the first recognition result and the second recognition result comprise different modification suggestions for the popularization information to be recognized.
8. A promotion information processing apparatus, comprising:
the system comprises a vector unit, a characteristic library and a processing unit, wherein the vector unit is used for acquiring the characteristic library which comprises a characteristic vector obtained by vectorizing at least one sample popularization information;
an obtaining unit, configured to obtain a first feature vector combination and a second feature vector combination from the feature library, where the first feature vector combination and the second feature vector combination overlap;
and the construction unit is used for constructing a first popularization information identification model by using the first characteristic vector combination and constructing a second popularization information identification model by using the second characteristic vector combination.
9. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 7.
11. A computer program product, characterized in that it causes a computer to carry out the method according to any one of claims 1 to 7 when said computer program product is run on the computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111348147.6A CN113988949A (en) | 2021-11-15 | 2021-11-15 | Promotion information processing method, device, equipment, medium and program product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111348147.6A CN113988949A (en) | 2021-11-15 | 2021-11-15 | Promotion information processing method, device, equipment, medium and program product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113988949A true CN113988949A (en) | 2022-01-28 |
Family
ID=79748545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111348147.6A Pending CN113988949A (en) | 2021-11-15 | 2021-11-15 | Promotion information processing method, device, equipment, medium and program product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113988949A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105005593A (en) * | 2015-06-30 | 2015-10-28 | 北京奇艺世纪科技有限公司 | Scenario identification method and apparatus for multi-user shared device |
US20160063244A1 (en) * | 2013-04-08 | 2016-03-03 | Beijing Qihoo Technology Company Limited | Method and system for recognizing advertisement plug-ins |
CN109598527A (en) * | 2017-09-30 | 2019-04-09 | 北京国双科技有限公司 | Analysis of advertising results method and device |
CN110503160A (en) * | 2019-08-28 | 2019-11-26 | 北京达佳互联信息技术有限公司 | Image-recognizing method, device, electronic equipment and storage medium |
US20200097820A1 (en) * | 2017-05-16 | 2020-03-26 | Samsung Electronics Co., Ltd. | Method and apparatus for classifying class, to which sentence belongs, using deep neural network |
CN111259148A (en) * | 2020-01-19 | 2020-06-09 | 北京松果电子有限公司 | Information processing method, device and storage medium |
WO2021017679A1 (en) * | 2019-07-26 | 2021-02-04 | 苏宁易购集团股份有限公司 | Address information parsing method and apparatus, system and data acquisition method |
WO2021159640A1 (en) * | 2020-02-13 | 2021-08-19 | 平安科技(深圳)有限公司 | Drug recommendation method based on artificial intelligence, and related device |
WO2021169209A1 (en) * | 2020-02-27 | 2021-09-02 | 平安科技(深圳)有限公司 | Method, apparatus and device for recognizing abnormal behavior on the basis of voice and image features |
-
2021
- 2021-11-15 CN CN202111348147.6A patent/CN113988949A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160063244A1 (en) * | 2013-04-08 | 2016-03-03 | Beijing Qihoo Technology Company Limited | Method and system for recognizing advertisement plug-ins |
CN105005593A (en) * | 2015-06-30 | 2015-10-28 | 北京奇艺世纪科技有限公司 | Scenario identification method and apparatus for multi-user shared device |
US20200097820A1 (en) * | 2017-05-16 | 2020-03-26 | Samsung Electronics Co., Ltd. | Method and apparatus for classifying class, to which sentence belongs, using deep neural network |
CN109598527A (en) * | 2017-09-30 | 2019-04-09 | 北京国双科技有限公司 | Analysis of advertising results method and device |
WO2021017679A1 (en) * | 2019-07-26 | 2021-02-04 | 苏宁易购集团股份有限公司 | Address information parsing method and apparatus, system and data acquisition method |
CN110503160A (en) * | 2019-08-28 | 2019-11-26 | 北京达佳互联信息技术有限公司 | Image-recognizing method, device, electronic equipment and storage medium |
CN111259148A (en) * | 2020-01-19 | 2020-06-09 | 北京松果电子有限公司 | Information processing method, device and storage medium |
WO2021159640A1 (en) * | 2020-02-13 | 2021-08-19 | 平安科技(深圳)有限公司 | Drug recommendation method based on artificial intelligence, and related device |
WO2021169209A1 (en) * | 2020-02-27 | 2021-09-02 | 平安科技(深圳)有限公司 | Method, apparatus and device for recognizing abnormal behavior on the basis of voice and image features |
Non-Patent Citations (1)
Title |
---|
刘旭: "基于深度学习的互联网广告点击率预估方法研究", 中国优秀硕士学位论文全文数据库经济与管理科学辑, no. 12, 15 December 2018 (2018-12-15), pages 157 - 103 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110633423B (en) | Target account identification method, device, equipment and storage medium | |
CN112905840A (en) | Video processing method, device, storage medium and equipment | |
CN111897950A (en) | Method and apparatus for generating information | |
CN115908640A (en) | Method and device for generating image, readable medium and electronic equipment | |
CN115294501A (en) | Video identification method, video identification model training method, medium and electronic device | |
CN109919220B (en) | Method and apparatus for generating feature vectors of video | |
CN113051933B (en) | Model training method, text semantic similarity determination method, device and equipment | |
CN114067327A (en) | Text recognition method and device, readable medium and electronic equipment | |
CN111756953A (en) | Video processing method, device, equipment and computer readable medium | |
CN113628097A (en) | Image special effect configuration method, image recognition method, image special effect configuration device and electronic equipment | |
CN116912734A (en) | Video abstract data set construction method, device, medium and electronic equipment | |
CN114625876A (en) | Method for generating author characteristic model, method and device for processing author information | |
CN114445813A (en) | Character recognition method, device, equipment and medium | |
CN113988949A (en) | Promotion information processing method, device, equipment, medium and program product | |
CN112395844B (en) | Pinyin generation method and device and electronic equipment | |
CN115760607A (en) | Image restoration method, device, readable medium and electronic equipment | |
CN112651231B (en) | Spoken language information processing method and device and electronic equipment | |
CN111027332B (en) | Method and device for generating translation model | |
CN114429629A (en) | Image processing method and device, readable storage medium and electronic equipment | |
CN111897951A (en) | Method and apparatus for generating information | |
CN115209215A (en) | Video processing method, device and equipment | |
CN111797263A (en) | Image label generation method, device, equipment and computer readable medium | |
CN116974684B (en) | Map page layout method, map page layout device, electronic equipment and computer readable medium | |
CN112364860B (en) | Training method and device of character recognition model and electronic equipment | |
CN114697760B (en) | Processing method, processing device, electronic equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |