CN112446208A

CN112446208A - Method, device and equipment for generating advertisement title and storage medium

Info

Publication number: CN112446208A
Application number: CN202011450380.0A
Authority: CN
Inventors: 陈陌信
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2020-12-09
Filing date: 2020-12-09
Publication date: 2021-03-05

Abstract

The invention discloses a method, a device, equipment and a storage medium for generating an advertisement title. The method comprises the following steps: identifying a product body word in an original title of the advertisement; performing syntactic analysis on the original title to obtain a syntactic tree of the original title; cutting the syntax tree according to the product main body words to extract the main content of the original title; generating a target title for the advertisement based on the backbone content. According to the method, the syntax tree of the original title is cut through the extracted main words of the product, so that the main content mainly comprising the main words of the product in the original title can be extracted, the target title obtained based on the extracted main content is shorter, meanwhile, the key information in the original title is also reserved, the content integrity of the original title is ensured, the automatic generation of the advertisement title is realized, and the generation efficiency of the advertisement title is improved.

Description

Method, device and equipment for generating advertisement title and storage medium

Technical Field

The embodiment of the invention relates to the technical field of internet application, in particular to a method, a device, equipment and a storage medium for generating an advertisement title.

Background

In order to increase the exposure of the product, an advertiser will typically formulate a corresponding advertisement scheme for the product to be exposed, and place the formulated advertisement scheme on some advertisement spots, so as to publicize the product through the placed advertisement spots.

However, in practical applications, different ad slots are conditional on the ad spots delivered, and the original ad spots specified by the advertiser may not satisfy the above conditions, resulting in that the original ad spots cannot match the delivered ad slots. In this case, the advertiser may write the advertisement title customized for different ad slots, but this approach may result in inefficient production of the advertisement title.

Disclosure of Invention

The embodiment of the invention provides a method, a device, equipment and a storage medium for generating an advertisement title, aiming at the technical problem that the production efficiency of the advertisement title is low in the mode.

In a first aspect, an embodiment of the present invention provides a method for generating an advertisement title, including:

identifying a product body word in an original title of the advertisement;

performing syntactic analysis on the original title to obtain a syntactic tree of the original title;

cutting the syntax tree according to the product main body words to extract the main content of the original title;

generating a target title for the advertisement based on the backbone content.

In a second aspect, an embodiment of the present invention provides an apparatus for generating an advertisement title, including:

the identification module is used for identifying the product main words in the original titles of the advertisements;

the analysis module is used for carrying out syntactic analysis on the original title to obtain a syntactic tree of the original title;

the cutting module is used for cutting the syntax tree according to the product main body words so as to extract the main content of the original title;

a first generation module for generating a target title of the advertisement based on the main content.

In a third aspect, an embodiment of the present invention provides an advertisement title generating device, including a memory and a processor, where the memory stores a computer program, and the processor implements, when executing the computer program, the steps of the advertisement title generating method provided in the first aspect of the embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for generating an advertisement title provided in the first aspect of the embodiment of the present invention.

According to the method, the device, the equipment and the storage medium for generating the advertisement title, provided by the embodiment of the invention, the electronic equipment identifies the product main words in the original title of the advertisement, performs syntactic analysis on the original title to obtain the syntactic tree of the original title, cuts the syntactic tree according to the product main words to extract the main content of the original title, and generates the target title of the advertisement based on the main content. The syntax tree of the original title is cut through the extracted main words of the product, so that the main content mainly comprising the main words of the product in the original title can be extracted, the target title obtained based on the extracted main content is shorter, the key information in the original title is also retained, the content integrity of the original title is ensured, the automatic generation of the advertisement title is realized, and the generation efficiency of the advertisement title is improved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 is a schematic flow chart of a method for generating an advertisement title according to an embodiment of the present invention;

FIG. 2 is a flow chart illustrating the clipping of a syntax tree of an original title of an advertisement according to an embodiment of the present invention;

FIG. 3 is a schematic flow chart illustrating a method for generating an advertisement title according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an apparatus for generating an advertisement title according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an advertisement title generating device according to an embodiment of the present invention.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules, or units, and are not used for limiting the order or interdependence of the functions performed by the devices, modules, or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

In the related art, different ad slots are conditionally restricted to the ad spots delivered, and the original ad title specified by the advertiser may not satisfy the above conditions, resulting in that the original ad title cannot match the ad spots delivered. For example, the condition may be a word count limit for an advertisement title, i.e., an original title of an advertisement made by an advertiser cannot fit the word count limit of different ad slots. In this case, ad titles of different lengths may be custom written for ad slots of different word count limitations. However, this method greatly reduces the efficiency of producing the advertisement title. Or, if the same original advertisement title is continuously used, the content of the title which does not meet the restriction condition can be directly cut off, so that the integrity of the content of the advertisement title is damaged, and the advertisement putting effect is influenced.

Therefore, embodiments of the present invention provide a method, an apparatus, a device and a storage medium for generating an advertisement title, which are intended to solve the above technical problems in the related art, and can automatically generate an advertisement title with complete content and short content based on the same original title.

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments of the present invention may be arbitrarily combined with each other without conflict.

It should be noted that the execution subject of the following method embodiments may be an advertisement title generation apparatus, and the apparatus may be implemented as part or all of an advertisement title generation device (hereinafter referred to as an electronic device) by software, hardware, or a combination of software and hardware. Optionally, the electronic device includes, but is not limited to, a smart phone, a tablet computer, a personal computer, a vehicle-mounted terminal, and other devices capable of delivering advertisements. The method embodiments described below are described by taking as an example that the execution subject is an electronic device.

Fig. 1 is a schematic flow chart of a method for generating an advertisement title according to an embodiment of the present invention. The embodiment relates to a specific process of how the electronic equipment automatically generates a complete content and short advertisement title based on an original title of the same advertisement. As shown in fig. 1, the method may include:

s101, identifying product main words in the original titles of the advertisements.

Specifically, the original banner is an advertisement banner that describes the product to be advertised as a subject. Thus, the product to be advertised may be understood as the product body word in the original title. For example, assume that the original title of the advertisement obtained by the electronic device is "boy girl 2020 new woollen suit double-faced woolen coat women commuting woolen coat", wherein "coat" is the product body word in the original title of the advertisement. Optionally, the process of the electronic device identifying the product body word in the original title of the advertisement may be: the electronic equipment can perform word segmentation on the original title of the advertisement, perform entity category labeling on each obtained word segmentation, extract a word segmentation with an entity category as a product from the labeled entity categories, and use the word segmentation as a main word of the product in the original title.

Optionally, the process of the electronic device identifying the product body word in the original title of the advertisement may further be: product subject words in the original title of the advertisement are identified through a pre-trained named entity recognition model.

The pre-trained named entity recognition model can be a sequence labeling model and is used for directly recognizing the product main words from the input text. In practical applications, the named entity recognition Model may be a Hidden Markov Model (HMM), a Maximum Entropy Hidden Markov Model (MEMM), a Conditional Random Field Model (CRF), and so on. Unlike the general classification problem, the sequence labeling model outputs a sequence of tags. Generally, tags are related to each other, and structure information between tags is formed. By using the structural information, the sequence labeling model can achieve higher performance than the traditional classification method in the aspect of sequence labeling.

Of course, before recognizing the product subject word in the original title through the named entity recognition model, the electronic device needs to train the named entity recognition model based on a large amount of sample data. In practical applications, the named entity recognition model can be jointly trained by using a Bert algorithm (Bidirectional Encoder responses from Transformers) and a Conditional Random Field (Crf) algorithm.

Optionally, before the step S101, the method further includes: the original title of the advertisement is obtained.

The original title of the advertisement can be stored in the electronic device in advance, and when the original title of the advertisement needs to be processed, the original title of the advertisement is directly read from a memory of the electronic device. Of course, the electronic device may also obtain the original title of the advertisement from the external device. For example, the original title of the advertisement made by the advertiser is stored in the cloud. When the original title of the advertisement needs to be processed, the electronic equipment directly acquires the original title of the advertisement from the cloud. The present embodiment does not limit the manner of acquiring the original title of the advertisement.

And S102, carrying out syntactic analysis on the original title to obtain a syntactic tree of the original title.

After obtaining the original title of the advertisement, the electronic equipment analyzes the dependency relationship between words in the original title of the advertisement through a syntax analyzer. Specifically, firstly, segmenting an original title of the advertisement to obtain a plurality of segments, then identifying entity words from the plurality of segments, performing part-of-speech tagging on the plurality of segments, and then performing dependency analysis on the entity words and the plurality of segments according to the tagged part-of-speech, thereby obtaining a syntax tree representing the dependency relationship between each grammar component in the original title.

S103, cutting the syntax tree according to the product main body words to extract the main content of the original title.

The original title of the advertisement is the advertisement title which is described by taking the product main words as the core, so that the electronic equipment can take the identified product main words as the center, prune the syntax tree according to the dependency relationship between the product main words and each participle in the original title, compress redundant information in the original title, retain key information in the original title and extract the main content in the original title of the advertisement.

And S104, generating a target title of the advertisement based on the main content.

Specifically, the target title may be understood as an advertisement title satisfying the delivery condition limit. After obtaining the main content in the original title of the advertisement, the electronic device may perform integration processing on the main content to obtain a target title meeting the delivery condition.

Optionally, the process of S104 may be: traversing the main content by taking the product main word as an initial node to obtain at least one candidate title of the advertisement; and screening the titles meeting a first preset condition from the at least one candidate title as target titles of the advertisements.

The first preset condition is an advertisement putting condition corresponding to the advertisement position to be put. It can be understood that after the syntax tree of the original title of the advertisement is cut centering on the product subject words, the extracted main content mainly includes the product subject words and some words related to the product subject words. And the product main words and the related words exist in the form of nodes in the syntax tree. At this time, the electronic device may traverse the clipped syntax tree, continue traversing the main content with the product main word as a center, and randomly combine the product main word and the related words in the main content to obtain at least one candidate title of the advertisement. And then, the electronic equipment selects a title meeting the advertisement putting condition from the at least one candidate title as a target title of the advertisement and outputs the target title based on the advertisement putting condition corresponding to the advertisement position to be put. Optionally, the advertisement placement condition corresponding to the advertisement placement to be placed may be a word count limiting condition.

For example, taking the first preset condition as the word number limitation condition corresponding to the advertisement space to be delivered, and continuing to take the example in S101 above as an example, it is assumed that the main content obtained by cutting the syntax tree of the original title of the advertisement includes wool, double-faced woolen cloth, commuter, coat, suit, woolen cloth, suit, and the like. And traversing the main content by taking the product main word 'coat' as an initial node to obtain at least one candidate title such as a 'wool commuting coat', 'double-sided woolen coat', 'wool suit coat' and 'wool commuting suit coat'. In this way, based on the target word number required by the advertisement space to be placed, the candidate title satisfying the target word number requirement is selected from the candidate titles and is output as the target title of the advertisement.

According to the method for generating the advertisement title, provided by the embodiment of the invention, the electronic equipment identifies the product main words in the original title of the advertisement, performs syntactic analysis on the original title to obtain the syntactic tree of the original title, cuts the syntactic tree according to the product main words to extract the main content of the original title, and generates the target title of the advertisement based on the main content. The syntax tree of the original title is cut through the extracted main words of the product, so that the main content mainly comprising the main words of the product in the original title can be extracted, the target title obtained based on the extracted main content is shorter, the key information in the original title is also retained, the content integrity of the original title is ensured, the automatic generation of the advertisement title is realized, and the generation efficiency of the advertisement title is improved.

In one embodiment, an implementation of clipping a syntax tree of an original title of an advertisement is also provided. On the basis of the foregoing embodiment, optionally, as shown in fig. 2, the process of S103 may be:

s201, with the product main word as an initial node, reserving a first node in the syntax tree, which has a dependency relationship with the initial node, and cutting a second node, which has no dependency relationship with the initial node.

After syntactic analysis is carried out on an original title of the advertisement, the syntax tree obtained by the electronic equipment comprises the dependency relationship among all syntax components in the original title. Since the original title of the advertisement is the advertisement title described with the product body word as the core, in order to extract the main content in the original title of the advertisement, the electronic device may clip the syntax tree based on the dependency relationship between the syntax components and the product body word. Specifically, the electronic device uses the product main word in the original title as a starting node, traverses the dependency relationship among all grammar components in the syntax tree, reserves a first node in the syntax tree, which has a target dependency relationship with the starting node, cuts a second node, which has no target dependency relationship with the starting node, and a sub-tree of the second node, so that only the node having the target dependency relationship with the starting node is reserved in the cut syntax tree. Wherein the target dependency relationship may be set based on actual requirements. Optionally, the target dependency relationship may be at least one of a noun modifier, a compound noun modifier, an adjective modifier, an adverb modifier, a noun phrase adverb modifier, and a lattice modifier.

Continuing with the example in S101, after the product main word in the original title of the advertisement is "jacket", and the syntax tree is obtained by performing syntax analysis on the original title of the advertisement, the electronic device traverses the syntax tree according to the dependency relationship preset for the starting node with "jacket" as the starting node, retains only the words having the set dependency relationship with "jacket", such as "wool", "tweed", "commute", "suit-dress", and the like, cuts out the words having no set dependency relationship with "jacket", thereby retaining only the important information in the original title of the advertisement, and cutting out the redundant information in the original title.

S202, determining the starting node, the first node and the target dependency relationship between the starting node and the first node as the main content of the original title.

In this embodiment, the electronic device uses the product main word as a starting node, reserves a first node in the syntax tree of the original title, which has a target dependency relationship with the starting node, and cuts a second node, which does not have a target dependency relationship with the starting node, and a sub-tree of the second node, so that only words having a target dependency relationship with the product main word are reserved in the syntax tree, that is, while the original title is compressed, the key information in the original title is also reserved, and thus the finally generated advertisement title is short and accurate.

In practical application, in order to further improve the advertisement delivery effect, on the basis of generating a short and accurate advertisement title, the electronic device can also automatically generate the characteristic description information of the advertisement based on the original title of the advertisement. For this reason, on the basis of the foregoing embodiment, optionally, after the foregoing S103, the method may further include: and generating characteristic description information of the advertisement for the product based on the main content.

The characteristic description information of the product refers to information capable of reflecting the characteristics of the product. For example, taking the product main body word as a shirt, the feature description information of the shirt may be comfortable and breathable, and the like, and at this time, the feature description information may also be used as the selling point information of the advertisement for the product. After obtaining the main content of the original title of the advertisement, the electronic device can further extract more important information from the main content, and form the feature description information of the product based on the more important information. As an optional implementation manner, the electronic device may respectively determine the importance of each node having a target dependency relationship with the product main word, rank the importance of each node, select a plurality of nodes with the highest rank from the ranking results, and form the feature description information of the product based on the plurality of nodes with the highest rank.

As another alternative, as shown in fig. 3, the process of generating the advertisement feature description information for the product based on the main content may be:

s301, obtaining a plurality of initial words taking the product main word as a modification object based on the main content.

After the syntax tree of the original title is cut to obtain the main content of the original title, the electronic equipment traverses the main content, extracts the words of the main words of the modified product in the main content, and obtains a plurality of initial words. As an alternative, since the noun modifier and the compound noun modifier in the above listed dependency relationships have a closer relationship with the product main word than other modifiers, the electronic device may traverse the pruned syntax tree, and select a node having a dependency relationship of the noun modifier and/or the compound noun modifier from the remaining nodes, thereby forming a plurality of initial words of the modified product.

And S302, respectively calculating the closeness among the initial words.

In the information theory, if the correlation and the closeness between two words are larger, the probability that the two words form a phrase is larger. Based on the principle, the electronic device can calculate the closeness among the initial words so as to judge whether the initial words can be further combined with phrases.

Specifically, the electronic device may calculate the closeness between the initial words by the following process: the electronic device may determine a first probability that the first initial word and the second initial word participating in the calculation occur simultaneously, a second probability that the first initial word occurs, and a third probability that the second initial word occurs, and calculate a closeness between the first initial word and the second initial word based on the first probability, the second probability, and the third probability. Optionally, the electronic device may calculate a product of the second probability and the third probability to obtain a product result, and perform a logarithm operation on a ratio of the first probability and the product result, so as to obtain the closeness between the first initial word and the second initial word.

It is understood that when the closeness between the first initial word and the second initial word is 0, it means that the first initial word and the second initial word are completely independent. When the closeness between the first initial word and the second initial word is larger, the possibility that the first initial word and the second initial word form a phrase is higher.

S303, determining the characteristic description information of the advertisement for the product according to the closeness among the initial words.

Specifically, after the closeness between the initial words is obtained, the electronic device may further combine a plurality of initial words with the closeness higher than a preset threshold into a target phrase based on the closeness between the initial words, and use the target phrase as characteristic description information of the advertisement for the product. For example, taking a product main word as a shirt as an example, assuming that a plurality of initial words obtained after traversing the main content are pure white, man, comfortable, breathable and the like, at this time, the electronic device calculates the closeness between the initial words respectively, and obtains the highest closeness between the comfortable words and the breathable words, so that the electronic device can combine the comfortable words and the breathable words to obtain a target word group of "comfortable breathable" and use the target word group of "comfortable breathable" as feature description information of an advertisement for a product.

When the closeness among the initial words is lower than a preset threshold, the electronic device may further extract a target word taking the product subject word as a modification object from the advertisement topic library based on the product subject word, calculate the closeness between the target word and the initial words respectively, combine words with the closeness higher than the preset threshold to form a target word group, and determine the target word group as feature description information of the advertisement for the product.

It should be noted that, in the above process of calculating the closeness between the target word and the initial word, reference may be made to a process of calculating the closeness between the initial words, which is not described herein again in this embodiment.

Compared with the way that the keywords and the hot words are only used as the isolated words, the characteristic description information carries more comprehensive product information and can reflect the characteristics of the product.

In the embodiment, the syntax tree of the original title is cut through the extracted product main words, so that the main content mainly comprising the product main words in the original title can be extracted, and the automatic generation of the characteristic description information of the advertisement based on the main content of the original title is realized. In addition, in the process of generating the characteristic description information, the closeness among the initial words can be determined, and the characteristic description information of the advertisement is determined based on the closeness among the initial words, so that the accuracy of the obtained characteristic description information is high.

Fig. 4 is a schematic structural diagram of an apparatus for generating an advertisement title according to an embodiment of the present invention. As shown in fig. 4, the apparatus may include: a recognition module 401, an analysis module 402, a cropping module 403 and a first generation module 404.

Specifically, the identification module 401 is configured to identify a product body word in an original title of the advertisement;

the analysis module 402 is configured to perform syntax analysis on the original title to obtain a syntax tree of the original title;

the clipping module 403 is configured to clip the syntax tree according to the product main word to extract the main content of the original title;

the first generation module 404 is configured to generate a target title of the advertisement based on the main content.

According to the device for generating the advertisement title, provided by the embodiment of the invention, the electronic equipment identifies the product main words in the original title of the advertisement, performs syntactic analysis on the original title to obtain the syntactic tree of the original title, cuts the syntactic tree according to the product main words to extract the main content of the original title, and generates the target title of the advertisement based on the main content. The syntax tree of the original title is cut through the extracted main words of the product, so that the main content mainly comprising the main words of the product in the original title can be extracted, the target title obtained based on the extracted main content is shorter, the key information in the original title is also retained, the content integrity of the original title is ensured, the automatic generation of the advertisement title is realized, and the generation efficiency of the advertisement title is improved.

On the basis of the above embodiment, optionally, the apparatus further includes: a second generation module;

specifically, the second generation module is configured to generate feature description information of the advertisement for the product based on the main content.

On the basis of the foregoing embodiment, optionally, the second generating module is specifically configured to obtain, based on the main content, a plurality of initial words using the product main word as a modification object; respectively calculating the compactness among the initial words; and determining the characteristic description information of the advertisement for the product according to the closeness among the initial words.

Based on the above embodiments, optionally, the recognition module 401 is specifically configured to recognize the product body words in the original titles of the advertisements through a pre-trained named entity recognition model.

On the basis of the foregoing embodiment, optionally, the clipping module 403 is specifically configured to use the product body word as a starting node, reserve a first node in the syntax tree, where a target dependency relationship exists with the starting node, and clip a second node, where a target dependency relationship does not exist with the starting node; and determining the starting node, the first node and the target dependency relationship between the starting node and the first node as the main content of the original title.

Optionally, the target dependency relationship is at least one of: noun modifiers, compound noun modifiers, adjective modifiers, adverb modifiers, noun phrases adverb modifiers, and all lattice modifiers.

On the basis of the foregoing embodiment, optionally, the first generating module 404 is specifically configured to traverse the main content by taking the product main word as a starting node to obtain at least one candidate title of the advertisement; and screening a title meeting a first preset condition from the at least one candidate title as a target title of the advertisement, wherein the first preset condition is an advertisement putting condition corresponding to an advertisement position to be put.

Referring now to FIG. 5, a block diagram of an electronic device 500 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. 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 506 into a Random Access Memory (RAM) 503. In the RAM503, 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 RAM503 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 506 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 506, 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 at least two internet protocol addresses; sending a node evaluation request comprising the at least two internet protocol addresses to node evaluation equipment, wherein the node evaluation equipment selects the internet protocol addresses from the at least two internet protocol addresses and returns the internet protocol addresses; receiving an internet protocol address returned by the node evaluation equipment; wherein the obtained internet protocol address indicates an edge node in the content distribution network.

Alternatively, the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving a node evaluation request comprising at least two internet protocol addresses; selecting an internet protocol address from the at least two internet protocol addresses; returning the selected internet protocol address; wherein the received internet protocol address indicates an edge node in the content distribution network.

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 units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving 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.

In one embodiment, there is also provided an advertisement title generating device, including a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

identifying a product body word in an original title of the advertisement;

generating a target title for the advertisement based on the backbone content.

In one embodiment, there is also provided a computer readable storage medium having a computer program stored thereon, the computer program when executed by a processor implementing the steps of:

identifying a product body word in an original title of the advertisement;

generating a target title for the advertisement based on the backbone content.

The device, the apparatus and the storage medium for generating an advertisement title provided in the above embodiments may execute the method for generating an advertisement title provided in any embodiment of the present invention, and have corresponding functional modules and advantageous effects for executing the method. For technical details that are not described in detail in the above embodiments, reference may be made to a method for generating an advertisement title provided in any embodiment of the present invention.

According to one or more embodiments of the present disclosure, there is provided a method of generating an advertisement title, including:

identifying a product body word in an original title of the advertisement;

generating a target title for the advertisement based on the backbone content.

According to one or more embodiments of the present disclosure, there is provided the above method for generating an advertisement title, further including: and generating characteristic description information of the advertisement for the product based on the main content.

According to one or more embodiments of the present disclosure, there is provided the above method for generating an advertisement title, further including: obtaining a plurality of initial words taking the product main word as a modification object based on the main content; respectively calculating the compactness among the initial words; and determining the characteristic description information of the advertisement for the product according to the closeness among the initial words.

According to one or more embodiments of the present disclosure, there is provided the above method for generating an advertisement title, further including: product subject words in the original title of the advertisement are identified through a pre-trained named entity recognition model.

According to one or more embodiments of the present disclosure, there is provided the above method for generating an advertisement title, further including: taking the product main word as an initial node, reserving a first node in the syntax tree, which has a target dependency relationship with the initial node, and cutting a second node, which has no target dependency relationship with the initial node; and determining the starting node, the first node and the target dependency relationship between the starting node and the first node as the main content of the original title.

According to one or more embodiments of the present disclosure, there is provided the above method for generating an advertisement title, further including: traversing the main content by taking the product main word as an initial node to obtain at least one candidate title of the advertisement; and screening a title meeting a first preset condition from the at least one candidate title as a target title of the advertisement, wherein the first preset condition is an advertisement putting condition corresponding to an advertisement position to be put.

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.

Claims

1. A method for generating an advertisement title, comprising:

identifying a product body word in an original title of the advertisement;

generating a target title for the advertisement based on the backbone content.

2. The method of claim 1, further comprising:

and generating characteristic description information of the advertisement for the product based on the main content.

3. The method of claim 2, wherein generating the advertisement for product feature description information based on the backbone content comprises:

obtaining a plurality of initial words taking the product main word as a modification object based on the main content;

respectively calculating the compactness among the initial words;

and determining the characteristic description information of the advertisement for the product according to the closeness among the initial words.

4. The method of any of claims 1 to 3, wherein the identifying of the product body words in the original title of the advertisement comprises:

product subject words in the original title of the advertisement are identified through a pre-trained named entity recognition model.

5. The method of any of claims 1-3, wherein said clipping the syntax tree from the product body words to extract the stem content of the original header comprises:

taking the product main word as an initial node, reserving a first node in the syntax tree, which has a target dependency relationship with the initial node, and cutting a second node, which has no target dependency relationship with the initial node;

and determining the starting node, the first node and the target dependency relationship between the starting node and the first node as the main content of the original title.

6. The method of claim 5, wherein the target dependency is at least one of: noun modifiers, compound noun modifiers, adjective modifiers, adverb modifiers, noun phrases adverb modifiers, and all lattice modifiers.

7. The method of any of claims 1-3, wherein generating the target title of the advertisement based on the main content comprises:

traversing the main content by taking the product main word as an initial node to obtain at least one candidate title of the advertisement;

and screening a title meeting a first preset condition from the at least one candidate title as a target title of the advertisement, wherein the first preset condition is an advertisement putting condition corresponding to an advertisement position to be put.

8. An advertisement title generation device, comprising:

9. An apparatus for generating an advertisement title, comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.