CN115250365A - Commodity text generation method and device, computer equipment and storage medium - Google Patents
Commodity text generation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115250365A CN115250365A CN202110470407.0A CN202110470407A CN115250365A CN 115250365 A CN115250365 A CN 115250365A CN 202110470407 A CN202110470407 A CN 202110470407A CN 115250365 A CN115250365 A CN 115250365A
- Authority
- CN
- China
- Prior art keywords
- text
- description text
- description
- commodity
- generating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000000694 effects Effects 0.000 claims abstract description 37
- 238000013473 artificial intelligence Methods 0.000 claims description 79
- 238000012549 training Methods 0.000 claims description 35
- 230000015654 memory Effects 0.000 claims description 20
- 230000008901 benefit Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 239000003795 chemical substances by application Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000002787 reinforcement Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000006403 short-term memory Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/26603—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
Abstract
The application provides a method, a device, computer equipment and a storage medium for generating a commodity text, wherein the method comprises the steps of obtaining object characteristics of a target object and initial description information related to the target object; generating an open field description text and a preferential description text related to the target object according to the initial description information; generating a content description text corresponding to the target object according to the object characteristics; and generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text. By the method and the device, the automation of generation of the commodity text for introduction can be effectively realized, the commodity text for introduction can be generated in batches, the consumption of manpower resources is reduced, the generation efficiency and the generation quality of the commodity text for introduction are improved, and the generation effect of the commodity text for introduction is improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for generating a commodity text, a computer device, and a storage medium.
Background
In recent years, with the rapid development of e-commerce platforms and video live broadcast industries, live broadcast e-commerce services combining the characteristics of the e-commerce platforms and the video live broadcast industries gradually become a mainstream online shopping mode. The anchor form of the live broadcast delivery is changed at a high speed, and the live broadcast delivery not only has the online cash and the artists with flow to carry the delivery through the interaction with the audience and the fan effect, but also has the live broadcast delivery form of the shop mainly showing commodities. With the rapid development of artificial intelligence, virtual idols and virtual anchor driven entirely by artificial intelligence have also been added to cargo rows and columns.
Generally, in a commodity introduction link, a real person anchor can sufficiently introduce selling points and preferential information of commodities and promote purchasing willingness of audiences. Due to the limitation of artificial intelligent virtual anchor, the current process of introducing commodities mainly relies on an intelligent voice synthesis technology to convert commodity texts for introduction, which are provided by merchants in advance, into voice for reading.
In this way, the commodity text for introduction in the virtual live broadcast is mainly written manually, which is time-consuming and uneven in quality, and the writing process of the commodity text for introduction cannot be performed in batch, so that excessive labor cost is consumed in the writing process of the commodity text for introduction, and resource waste is caused.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present application is to provide a method, an apparatus, a computer device, and a storage medium for generating a commodity text for introduction, which can effectively automate generation of the commodity text for introduction, generate commodity texts for introduction in batches, reduce human resource consumption, improve generation efficiency and generation quality of the commodity text for introduction, and improve generation effect of the commodity text for introduction.
In order to achieve the above object, a method for generating a commodity text provided in an embodiment of a first aspect of the present application includes: acquiring object characteristics of a target object and initial description information related to the target object; generating an open-field description text and a preferential description text related to the target object according to the initial description information; generating a content description text corresponding to the target object according to the object characteristics; and generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text.
According to the method for generating the commodity text provided by the embodiment of the first aspect of the application, the object feature of the target object and the initial description information related to the target object are obtained, the opening description text and the preferential description text related to the target object are generated according to the initial description information, the content description text corresponding to the target object is generated according to the object feature, and the target commodity text corresponding to the target object is generated according to the opening description text, the content description text and the preferential description text, so that the automation of the generation of the commodity text for introduction can be effectively realized, the generation of the commodity text for introduction in batches is realized, the human resource consumption is reduced, the generation efficiency and the generation quality of the commodity text for introduction are improved, and the generation effect of the commodity text for introduction is improved.
In order to achieve the above object, an apparatus for generating a product text according to an embodiment of the second aspect of the present application includes: the acquisition module is used for acquiring object characteristics of a target object and initial description information related to the target object; the first generation module is used for generating an opening description text and a preferential description text related to the target object according to the initial description information; the second generation module is used for generating a content description text corresponding to the target object according to the object characteristics; and the third generation module is used for generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text.
According to the device for generating the commodity text, which is provided by the embodiment of the second aspect of the application, the object feature of the target object and the initial description information related to the target object are obtained, the opening description text and the preferential description text related to the target object are generated according to the initial description information, the content description text corresponding to the target object is generated according to the object feature, and the target commodity text corresponding to the target object is generated according to the opening description text, the content description text and the preferential description text, so that the automation of the generation of the commodity text for introduction can be effectively realized, the generation of the commodity text for introduction in batches is realized, the consumption of human resources is reduced, the generation efficiency and the generation quality of the commodity text for introduction are improved, and the generation effect of the commodity text for introduction is improved.
An embodiment of a third aspect of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for generating a text of a commodity as set forth in the embodiment of the first aspect of the present application.
An embodiment of a fourth aspect of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for generating a text of an article of commerce as set forth in the embodiment of the first aspect of the present application.
An embodiment of a fifth aspect of the present application provides a computer program product, where when being executed by an instruction processor in the computer program product, the method for generating a text of an article as set forth in the embodiment of the first aspect of the present application is performed.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for generating a commodity text according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for generating a product text according to another embodiment of the present application;
fig. 3 is a schematic flow chart of a method for generating a product text according to another embodiment of the present application;
FIG. 4 is a schematic diagram of an architecture of an artificial intelligence model in an embodiment of the application;
fig. 5 is a schematic structural diagram of a device for generating a product text according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a device for generating a product text according to another embodiment of the present application;
FIG. 7 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application. On the contrary, the embodiments of the application include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Fig. 1 is a schematic flow chart of a method for generating a commodity text according to an embodiment of the present application.
It should be noted that an execution subject of the method for generating a product text in this embodiment is a device for generating a product text, where the device may be implemented in a software and/or hardware manner, and the device may be configured in an electronic device, and the electronic device may include, but is not limited to, a terminal, a server, and the like.
As shown in fig. 1, the method for generating a product text includes:
s101: the object characteristics of the target object and the initial description information related to the target object are obtained.
The description object of the generated commodity text may be referred to as a target object, and the target object may be, for example, a product to be sold, and the target object specifically includes, for example, a "small household appliance," which is not limited thereto.
The object feature may be used to describe an attribute feature of the target object, and assuming that the target object is a product to be sold, the object feature may be, for example, a product type, and the target object is specifically, for example, a "small household appliance", and the object feature may be, for example, a "household appliance class", which is not limited to this.
The initial description information may be used to describe some description features of the target object, for example, some information of the activity associated with the target object, the initial description information is, for example, a name of the target object, a name of the associated activity, a holding time, and the like, or may also be some offer information related to the target object, for example, when the target object is purchased, a is given, and a name, number, and the like of a given are referred to as some offer information related, which is not limited herein.
When the object feature of the target object and the initial description information related to the target object are obtained, the method may specifically be to provide an input interface of the object feature and the initial description information, receive the content input by the user, and automatically analyze the content input by the user to obtain the object feature and the initial description information, or may also be to identify an existing image, identify a product to be sold from the image, and analyze the object feature and the initial description information by invoking a preset algorithm, or may also capture the content of a main broadcast in a live broadcast, determine the target object according to the content, and determine the object feature and the initial description information, which is not limited thereto.
S102: and generating an open field description text and a preferential description text related to the target object according to the initial description information.
In the embodiment of the application, after the initial description information related to the target object is obtained, the opening description text and the preferential description text related to the target object can be generated according to the initial description information.
It can be understood that the embodiment of the present application may be applied to a live application scenario, a commodity text generated for live broadcast generally includes a description text with a cut-out property for receiving subsequent specific description contents, and the description text with the cut-out property may be referred to as a cut-out description text, and description texts related to some preferential contents related to a target object may be referred to as preferential description texts.
In the embodiment of the application, the initial description information can be input into the pre-trained text generation model to obtain the open-field description text output by the text generation model and the preferential description text related to the target object.
In some other embodiments, in order to take account of the generation efficiency and the generation quality of the commodity text for live broadcasting, an opening description text and a preferential description text related to the target object may be generated according to the initial description information in a template matching manner.
Optionally, as shown in fig. 2, fig. 2 is a flowchart illustrating a method for generating a product text according to another embodiment of the present application, and generating an opening description text and a offer description text related to a target object according to initial description information, where the method includes:
s201: and generating an opening description text by combining a first commodity text template according to the initial description information.
The product text template used for assisting in generating the opening description text may be referred to as a first product text template, and correspondingly, the product text template used for assisting in generating the opening description text may be referred to as a second product text template, and the product text template may include, for example, some standard dialogs, may include standard dialogs related to the opening description in the first product text template used for assisting in generating the opening description text, and may include standard dialogs related to the opening description in the second product text template used for assisting in generating the opening description text, which is not limited thereto.
For example, assuming that the initial description information is the name of the target object, the name of the associated event, the holding time, and the like, the first product text template may be called, the standard dialogs related to the opening description in the first product text template may be parsed, and then the opening description text may be generated according to the name of the target object, the name of the associated event, the holding time, and the like, in combination with the standard dialogs related to the opening description.
Optionally, in some embodiments, the initial description information includes: and generating an open-field description text by combining the initial description information and the first commodity text template according to the initial description information, wherein the open-field description text can be obtained by respectively analyzing a time descriptor text corresponding to the time information, an activity descriptor text corresponding to the activity information and a name descriptor text corresponding to the name from the first commodity text template and splicing the time descriptor text, the activity descriptor text and the name descriptor text to obtain the open-field description text.
The time information may be, for example, the holding time of a campaign associated with the target object, the campaign information of the platform to which the target object belongs may be, for example, a campaign name, and the name of the target object may be, for example, "small appliance a", a time descriptor text corresponding to the time information, a campaign descriptor text corresponding to the campaign information, and a name descriptor text corresponding to the name may be respectively parsed from the first product text template, where the time descriptor text may specifically be a phrase field for describing an opening description of the time information, the campaign descriptor text may specifically be a phrase field for describing an opening description of the campaign information, and the name descriptor text may specifically be a phrase field for describing an opening description of the name, and then, the time descriptor text, the campaign descriptor text, and the name descriptor text may be concatenated to obtain the opening description text.
For example, automatic generation of open-field description text: the opening description text may be generated from a predefined template (a first article text template) as follows:
"old ironmen, a month and b days are activity days of a platform c, various preferential activities of the platform c, great strength and good price are shared, and today, I also get a very good use and material d recommended to everyone in a live broadcasting room! ".
Where a is a month (time information), b is a date (time information), c is a specific activity (activity information), and d is a recommended specific commodity (name of a target object).
The open-field description text generated according to the first commodity text template includes: "old ironmen, no. 6 and No. 18 are fierce shopping days in 618 years of platform c, various preferential activities of the platform c, great strength and good price are provided, today, I also get a very good-to-use and economical small household appliance in the live broadcast room and recommend to everyone! ".
S202: and generating a preferential description text related to the target object by combining a second commodity text template according to the initial description information, wherein the first commodity text template is different from the second commodity text template.
For example, assuming that the initial description information is some offer information related to the target object, the second product text template may be called, a standard dialect related to an offer description in the second product text template is analyzed, and then, according to some offer information related to the target object and the like, an offer description text is generated in combination with the standard dialect related to the offer description, which is not limited.
Optionally, in some embodiments, the initial description information includes: and if the discount type indicates that no discount content exists, the template content text in the second commodity text template is directly used as the discount description text.
The offer type may be specifically used to describe a way of the offer, and the offer type is, for example, a type of presenting other goods, a price offer type, and a full discount offer type, which is not limited to this.
Correspondingly, when the second commodity text template is configured in advance, the corresponding second commodity text template may be configured for different offer types, in addition, if the offer type is any one of other gift types, price offer types, and full-minus offer types, it may be indicated that the offer type indicates that the corresponding offer content exists, and if the offer type is not any one of the above, it may be indicated that the offer type indicates that the offer content does not exist, which is not limited.
Therefore, in the embodiment of the application, the generated discount description text can be matched with the specific discount type, the flexibility and the convenience of generating the discount description text are improved, and the automatic generation effect of the discount description text is effectively improved.
For example, automatic generation of offer description text: the specific second commodity text template designed for different preference types is as follows:
if the offer type is: when other commodity types are presented, the second commodity text template is as follows: "buy a, also attach a b, buy a remuneration guest", where a is the current promotional product and b is the complimentary product.
If the offer type is: when other commodity types are presented, the second commodity text template is as follows: "today live rooms can enjoy ultra-low exclusive prices, as long as xx elements! ".
If the offer type is: if the discount type is fully reduced, the second commodity text template is as follows: "get coupon first and buy, full xx element minus yy element, hand only needs zz element, must get coupon first and buy! ".
If the offer type is: if the category is not the above three categories or no preferential information exists, the general second commodity text template is used, such as: "No purchase, loss and no purchase, the price here is the most substantial and guaranteed to be genuine, one claim ten! ".
The above-mentioned "today live broadcast room can enjoy ultra-low exclusive share price, as long as … yuan", "get coupon first and buy, full … yuan minus … yuan", "get only … yuan", "get coupon first and buy" can all be called benefit descriptor texts, and then, at least one benefit descriptor text can be spliced to obtain a benefit description text, which is not limited.
S103: and generating a content description text corresponding to the target object according to the object characteristics.
The object feature may be used to describe an attribute feature of the target object, and assuming that the target object is a product to be sold, the object feature may be, for example, a product type, and the target object is specifically, for example, a "small household appliance", and the object feature may be, for example, a "household appliance class", which is not limited to this.
After the object features are obtained, the content description text corresponding to the target object may be generated by adopting a template matching method according to the object features, or may also be generated by adopting any other possible method, which is not limited to this.
S104: and generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text.
After the open-field description text and the offer description text related to the target object are generated according to the initial description information and the content description text corresponding to the target object is generated according to the object characteristics, the target commodity text corresponding to the target object can be generated according to the open-field description text, the content description text and the offer description text, for example, the open-field description text, the content description text and the offer description text can be spliced, so that the spliced description text is used as the target commodity text corresponding to the target object.
In this embodiment, by obtaining the object feature of the target object and the initial description information related to the target object, generating the opening description text and the benefit description text related to the target object according to the initial description information, generating the content description text corresponding to the target object according to the object feature, and generating the target commodity text corresponding to the target object according to the opening description text, the content description text, and the benefit description text, automation of generation of the commodity text for introduction can be effectively achieved, generation of the commodity text for introduction in batches is achieved, human resource consumption is reduced, generation efficiency and generation quality of the commodity text for introduction are improved, and generation effect of the commodity text for introduction is improved.
Fig. 3 is a flowchart illustrating a method for generating a product text according to another embodiment of the present application.
As shown in fig. 3, the method for generating a product text includes:
s301: and determining the description text of the labeling content corresponding to the object characteristics.
In the embodiment of the application, an artificial intelligence model can be trained in advance, and the artificial intelligence model can be specifically a neural network model or a machine learning model, so that the artificial intelligence model has a function of generating a corresponding content description text according to the object characteristics.
The content description text may be a description text having an overall description property, for example, if the commodity text is used to assist a selling product in a live broadcast process, the description text for generally describing details of the selling product may be referred to as a content description text.
The labeled content description text may be a standard content description text for training an artificial intelligence model, and is not limited to this.
The determination of the description text of the labeled content corresponding to the object features takes into account the target objects with different object features, and usually has personalized description content, so that the trained artificial intelligence model can generate the description text of the content matched with the object features, and the accuracy of the generated description text of the content is improved.
S302: a plurality of sample objects is determined based on the object characteristics.
That is to say, in the embodiment of the present application, a plurality of sample objects whose features are adapted to the above features may be determined, and assuming that the object features are product types, for example, "household appliances", a plurality of sample objects of products of a plurality of household appliances may be selected, so as to assist in training the artificial intelligence model.
S303: a plurality of actual purchase rates corresponding to the plurality of sample objects, respectively, is determined.
When determining the training data for training the artificial intelligence model, a plurality of actual purchase rates corresponding to the plurality of sample objects may also be determined, where the actual purchase rates may be historical actual purchase rates of a plurality of products of corresponding product types, and the actual purchase rates may be obtained according to historical purchase condition statistics, which is not limited thereto.
For example, for different products (sample objects), historical purchase data of users can be collected, and the purchase rate corresponding to the product selling point introduction product text of each product, that is, the ratio of the number of purchasing people to the number of watching people, is recorded. For example, the number of viewers of mobile phone A is 100, the number of purchasers is 10, and the actual purchase rate is 10%, while the number of viewers of mobile phone B is 200, the number of purchasers is 50, and the actual purchase rate is 25%.
S304: and training an initial artificial intelligence model according to the actual purchase rates and the object characteristics until a target content description text and a labeled content description text output by the artificial intelligence model meet set conditions, and taking the artificial intelligence model obtained by training as the target artificial intelligence model.
When the time for determining the convergence of the artificial intelligence model is determined, the loss value between the target content description text and the labeled content description text output by the artificial intelligence model can be specifically determined, and if the loss value meets the set condition, the initial artificial intelligence model is determined to be trained completely, so that the time for completing model training can be accurately determined in an assisting manner, and the training efficiency is improved while the training effect of the artificial intelligence model is ensured.
The loss value between the target content description text and the labeled content description text output by the artificial intelligence model can be determined by determining the similarity between the target content description text and the labeled content description text, determining a plurality of product values obtained by multiplying the similarity and a plurality of actual purchase rates respectively, and taking the average value of the product values as the loss value, so that the actual purchase rate can be used as reward reference content for artificial intelligence model training, the model generation effect of the artificial intelligence model is measured based on the dimension of the purchase rate, the artificial intelligence model obtained by training is matched with the scene of live selling, and the model expression effect is improved.
In the training of the initial artificial intelligence model, a reinforcement learning algorithm may be used to perform the training process, and the description of the reinforcement learning algorithm may be as follows:
based on a reinforcement learning algorithm, the loss function may be used to calculate the similarity between it and the high conversion rate commodity text of the same product type.
For example, if the similarity between the generated product text and the product text of mobile phone a is 0.3 and the similarity between the generated product text and the product text of mobile phone B is 0.2, the loss value may be (0.3 × 10% +0.2 × 25%)/2 =0.04.
The artificial intelligence model in the embodiment of the present application may be trained using a policy gradient (policygredient) -based reinforcement learning algorithm framework in which the digest automatic generation model is a reinforcement learning agent (agent) that uses an encoder-decoder (encoder-decoder) framework, and the environment (environment) in which the agent interacts with the agent is a context semantic vector of words that have been generated at a historical time and a current time; the agent's parameters are used as policy (policy), and then, depending on the policy and the environment, the agent can make an action (action) at the current time, i.e. generate a word at the current time.
In this embodiment, as shown in fig. 4, fig. 4 is a schematic structural diagram of an artificial intelligence model in this embodiment, and includes a plurality of encoders, where a Bi-directional Long Short-Term Memory (BiLSTM) may be used as the encoder, a product detailed introduction text a may be input, and the encoder (Bi-directional Long Short-Term Memory, biLSTM) may be used as the encoder) to encode the Bi-directional Long Short-Term Memory (Bi) to generate a coding layer sequence h, and the formula is: h = BilSTM (a), then a plurality of decoders (which may use a unidirectional Short-Term Memory (LSTM) as a decoder) generate a decoded hidden sequence s using the encoded hidden sequence h and an attention mechanism, and then generate a word at the current time based thereon (the word may be regarded as a partial word in the target content description text to be output). The formula is as follows:
s t ＝LSTM(s t-1 ，y t-1 ，c t )；
wherein, { t 1 ，t 2 ，...，t m Is the decoder hidden layer sequence, { y } 1 ，y 2 ，...，y m Is the target abstract, c t The context vector at the time t is generated by an attention mechanism, and the formula is as follows:
α t ＝softmax(e t )；
c t ＝∑ i α t，i h i 。
wherein u is a 、W a And V a Is a matrix of model parameters, alpha t，i For t time to source end vocabulary x i Attention of (1).
The decoder generates the probability of the abstract word w by using the decoder hidden layer state and the context vector, and the formula is as follows: p (W) = softmax (W) b s t +V b c t )；
Wherein, W b And V b Is a model parameter matrix.
The reward (reward) function (i.e. loss function) of the model is the average value of the similarity of the text of the high-conversion commodity of the same type product multiplied by the purchase rate, and the formula is as follows:
wherein x is i Description text of the label content for other sample objects of the same object type as the current object, p (x) i ) Is x i And corresponding actual purchase rate, N is the total number of the label content description texts of other sample objects of the same object type. The purpose of the reward function is to make the rate of purchases actually achieved for the sales activity based on the text of the item generated by the artificial intelligence model higher. sim (x) i And x) represents the markup content description text x i With object content descriptionCosine similarity of eigenvectors of this x, x i The feature vector with x is defined as the mean of all hidden states of the decoder of the artificial intelligence model.
S305: the object characteristics of the target object and the initial description information related to the target object are obtained.
S306: and generating an open field description text and a preferential description text related to the target object according to the initial description information.
The descriptions of S305-S306 may specifically refer to the above embodiments, and are not repeated herein.
S307: and determining a target artificial intelligence model corresponding to the object characteristics.
In the process of practical application, a plurality of artificial intelligence models can be trained according to different object features, so that the artificial intelligence models correspond to the object features one to one, after the artificial intelligence models are obtained through training and the artificial intelligence models obtained through training can generate content description texts matched with the object features, in the process of actually generating the content description texts, target artificial intelligence models corresponding to the object features can be determined, and the target artificial intelligence models are used for assisting to determine the content description texts.
S308: and inputting the object characteristics into the target artificial intelligence model, and acquiring a content description text which is output by the target artificial intelligence model and corresponds to the target object.
After the target artificial intelligence model corresponding to the object characteristics is determined, the object characteristics can be directly input into the target artificial intelligence model, and the content description text corresponding to the target object and output by the target artificial intelligence model is obtained.
S309: and generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text.
The description of S309 may specifically refer to the above embodiments, and is not repeated herein.
In this embodiment, by obtaining the object feature of the target object and the initial description information related to the target object, generating the opening description text and the benefit description text related to the target object according to the initial description information, generating the content description text corresponding to the target object according to the object feature, and generating the target commodity text corresponding to the target object according to the opening description text, the content description text, and the benefit description text, automation of generation of the commodity text for introduction can be effectively achieved, generation of the commodity text for introduction in batches is achieved, human resource consumption is reduced, generation efficiency and generation quality of the commodity text for introduction are improved, and generation effect of the commodity text for introduction is improved. The method realizes the pre-training of an artificial intelligence model, so that the artificial intelligence model has the function of generating a corresponding content description text according to the object characteristics. By determining the loss value between the target content description text and the labeled content description text output by the artificial intelligence model, if the loss value meets the set condition, the initial artificial intelligence model is determined to be trained completely, so that the training completion time of the model can be accurately determined in an auxiliary manner, the training efficiency is improved while the training effect of the artificial intelligence model is ensured. The similarity between the target content description text and the labeled content description text is determined, a plurality of product values obtained by multiplying the similarity and a plurality of actual purchase rates respectively are determined, and the average value of the product values is used as a loss value, so that the actual purchase rate can be used as reward reference content for artificial intelligence model training, the model generation effect of the artificial intelligence model is measured based on the dimension of the purchase rate, the artificial intelligence model obtained through training is matched with a selling live broadcast scene, and the model expression effect is improved. After the target artificial intelligence model corresponding to the object characteristics is determined, the object characteristics can be directly input into the target artificial intelligence model, and the content description text corresponding to the target object and output by the target artificial intelligence model is obtained.
Fig. 5 is a schematic structural diagram of a device for generating a product text according to an embodiment of the present application.
As shown in fig. 5, the product text generation device 50 includes:
an obtaining module 501, configured to obtain object features of a target object and initial description information related to the target object;
a first generating module 502, configured to generate an open-field description text and a preferential description text related to the target object according to the initial description information;
a second generating module 503, configured to generate a content description text corresponding to the target object according to the object feature;
and a third generating module 504, configured to generate a target commodity text corresponding to the target object according to the opening description text, the content description text, and the offer description text.
In some embodiments of the present application, as shown in fig. 6, the first generating module 502 includes:
the first generation submodule 5021 is used for generating an opening description text by combining a first commodity text template according to the initial description information;
the second generating sub-module 5022 is used for generating a preferential description text related to the target object by combining a second commodity text template according to the initial description information, wherein the first commodity text template is different from the second commodity text template.
In some embodiments of the present application, the initial description information includes: the time information, the activity information of the platform to which the target object belongs, and the name of the target object, the first generation submodule 5021 is specifically configured to:
respectively analyzing a time descriptor text corresponding to the time information, an activity descriptor text corresponding to the activity information and a name descriptor text corresponding to the name from the first commodity text template;
and splicing the time descriptor text, the activity descriptor text and the name descriptor text to obtain an open field description text.
In some embodiments of the present application, the initial description information includes: the preferential type is, then, the second generation submodule 5022 is specifically used for:
determining a second commodity text template matched with the discount type;
if the discount type indicates that the corresponding discount content exists, at least one discount descriptor text corresponding to the discount content is analyzed from the second commodity text template, and a discount description text is generated according to the at least one discount descriptor text;
and if the preference type indicates that no preference content exists, directly taking a template content text in the second commodity text template as a preference description text.
In some embodiments of the present application, the second generating module 503 is specifically configured to:
determining a target artificial intelligence model corresponding to the object characteristics;
and inputting the object characteristics into the target artificial intelligence model, and acquiring a content description text which is output by the target artificial intelligence model and corresponds to the target object.
In some embodiments of the present application, as shown in fig. 6, further comprising:
and the training module 505 is configured to determine the label content description text corresponding to the object features, determine a plurality of sample objects according to the object features, determine a plurality of actual purchase rates corresponding to the plurality of sample objects, respectively, and train the initial artificial intelligence model according to the plurality of actual purchase rates and the object features until the target content description text and the label content description text output by the artificial intelligence model satisfy the set conditions, so as to use the artificial intelligence model obtained through training as the target artificial intelligence model.
In some embodiments of the present application, the training module 505 is specifically configured to:
determining a loss value between a target content description text and a labeling content description text output by an artificial intelligence model;
and if the loss value meets the set condition, determining that the training of the initial artificial intelligence model is finished.
In some embodiments of the present application, the training module 505 is specifically configured to:
determining the similarity between the target content description text and the annotation content description text;
and determining a plurality of product values obtained by multiplying the similarity and the actual purchase rates respectively, and taking the average value of the product values as a loss value.
Corresponding to the method for generating a product text provided in the embodiments of fig. 1 to 4, the present application also provides a device for generating a product text, and since the device for generating a product text provided in the embodiments of the present application corresponds to the method for generating a product text provided in the embodiments of fig. 1 to 4, the embodiment of the method for generating a product text is also applicable to the device for generating a product text provided in the embodiments of the present application, and will not be described in detail in the embodiments of the present application.
In this embodiment, by obtaining the object feature of the target object and the initial description information related to the target object, generating the opening description text and the benefit description text related to the target object according to the initial description information, generating the content description text corresponding to the target object according to the object feature, and generating the target commodity text corresponding to the target object according to the opening description text, the content description text, and the benefit description text, automation of generation of the commodity text for introduction can be effectively achieved, generation of the commodity text for introduction in batches is achieved, human resource consumption is reduced, generation efficiency and generation quality of the commodity text for introduction are improved, and generation effect of the commodity text for introduction is improved.
In order to implement the foregoing embodiments, the present application also provides a computer device, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the method for generating the commodity text is realized as provided by the foregoing embodiments of the present application.
In order to implement the above embodiments, the present application also proposes a non-transitory computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the generation method of the article text as proposed by the foregoing embodiments of the present application.
In order to implement the foregoing embodiments, the present application also proposes a computer program product, which when executed by an instruction processor in the computer program product, executes the method for generating the article text as proposed in the foregoing embodiments of the present application.
FIG. 7 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application. The computer device 12 shown in fig. 7 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in FIG. 7, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Although not shown in FIG. 7, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 over the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing by running a program stored in the system memory 28, for example, implementing the generation method of the article text mentioned in the foregoing embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.
Claims (18)
1. A method for generating a commodity text, the method comprising:
acquiring object characteristics of a target object and initial description information related to the target object;
generating an open field description text and a preferential description text related to the target object according to the initial description information;
generating a content description text corresponding to the target object according to the object characteristics;
and generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the preferential description text.
2. The method of claim 1, wherein generating an opening description text and a benefit description text related to the target object according to the initial description information comprises:
generating the opening description text by combining a first commodity text template according to the initial description information;
and generating the preferential description text related to the target object by combining a second commodity text template according to the initial description information, wherein the first commodity text template is different from the second commodity text template.
3. The method of claim 2, wherein the initial description information comprises: generating the opening description text by combining a first commodity text template according to the initial description information, wherein the time information, the activity information of the platform to which the target object belongs, and the name of the target object comprise:
respectively analyzing a time descriptor text corresponding to the time information, an activity descriptor text corresponding to the activity information and a name descriptor text corresponding to the name from the first commodity text template;
and splicing the time descriptor text, the activity descriptor text and the name descriptor text to obtain the open field description text.
4. The method of claim 2, wherein the initial description information comprises: and if the offer type is the offer type, generating an offer description text related to the target object by combining a second commodity text template according to the initial description information, wherein the offer description text comprises the following steps:
determining a second commodity text template matched with the discount type;
if the offer type indicates that corresponding offer content exists, analyzing at least one offer descriptor text corresponding to the offer content from the second commodity text template, and generating the offer description text according to the at least one offer descriptor text;
and if the offer type indicates that the offer content does not exist, directly taking a template content text in the second commodity text template as the offer description text.
5. The method of claim 1, wherein generating a content description text corresponding to the target object based on the object features comprises:
determining a target artificial intelligence model corresponding to the object characteristics;
and inputting the object characteristics into the target artificial intelligence model, and acquiring a content description text which is output by the target artificial intelligence model and corresponds to the target object.
6. The method of claim 5, prior to said obtaining object features of the target object, further comprising:
determining a description text of the labeling content corresponding to the object feature;
determining a plurality of sample objects according to the object features;
determining a plurality of actual purchase rates corresponding to the plurality of sample objects, respectively;
training an initial artificial intelligence model according to the actual purchase rates and the object characteristics until a target content description text and the labeled content description text output by the artificial intelligence model meet set conditions, and taking the artificial intelligence model obtained through training as the target artificial intelligence model.
7. The method of claim 6, wherein,
determining a loss value between a target content description text output by the artificial intelligence model and the marked content description text;
and if the loss value meets the set condition, determining that the training of the initial artificial intelligence model is finished.
8. The method of claim 6, wherein said determining a loss value between the target content description text and the annotation content description text output by the artificial intelligence model comprises:
determining the similarity between the target content description text and the annotation content description text;
determining a plurality of product values obtained by multiplying the similarity and the actual purchase rates respectively, and taking the average value of the product values as the loss value.
9. An apparatus for generating a text of an article, the apparatus comprising:
the acquisition module is used for acquiring the object characteristics of a target object and initial description information related to the target object;
the first generation module is used for generating an opening description text and a preferential description text related to the target object according to the initial description information;
the second generation module is used for generating a content description text corresponding to the target object according to the object characteristics;
and the third generation module is used for generating a target commodity text corresponding to the target object according to the opening description text, the content description text and the discount description text.
10. The apparatus of claim 9, wherein the first generating module comprises:
the first generation submodule is used for generating the opening description text by combining a first commodity text template according to the initial description information;
and the second generation submodule is used for generating the preferential description text related to the target object by combining a second commodity text template according to the initial description information, wherein the first commodity text template is different from the second commodity text template.
11. The apparatus of claim 10, wherein the initial description information comprises: the first generation submodule is specifically configured to:
respectively analyzing a time descriptor text corresponding to the time information, an activity descriptor text corresponding to the activity information and a name descriptor text corresponding to the name from the first commodity text template;
and splicing the time descriptor text, the activity descriptor text and the name descriptor text to obtain the open field description text.
12. The apparatus of claim 10, wherein the initial description information comprises: the second generation submodule is specifically configured to:
determining a second commodity text template matched with the discount type;
if the offer type indicates that corresponding offer content exists, analyzing at least one offer descriptor text corresponding to the offer content from the second commodity text template, and generating the offer description text according to the at least one offer descriptor text;
and if the offer type indicates that the offer content does not exist, directly taking a template content text in the second commodity text template as the offer description text.
13. The apparatus of claim 9, wherein the second generating module is specifically configured to:
determining a target artificial intelligence model corresponding to the object characteristics;
and inputting the object characteristics into the target artificial intelligence model, and acquiring a content description text which is output by the target artificial intelligence model and corresponds to the target object.
14. The apparatus of claim 13, further comprising:
and the training module is used for determining the labeled content description texts corresponding to the object features, determining a plurality of sample objects according to the object features, determining a plurality of actual purchase rates respectively corresponding to the sample objects, training an initial artificial intelligence model according to the actual purchase rates and the object features, and taking the artificial intelligence model obtained by training as the target artificial intelligence model until the target content description texts and the labeled content description texts output by the artificial intelligence model meet set conditions.
15. The apparatus of claim 14, wherein the training module is specifically configured to:
determining a loss value between a target content description text output by the artificial intelligence model and the marked content description text;
and if the loss value meets the set condition, determining that the training of the initial artificial intelligence model is finished.
16. The apparatus of claim 14, wherein the training module is specifically configured to:
determining the similarity between the target content description text and the annotation content description text;
determining a plurality of product values obtained by multiplying the similarity and the actual purchase rates respectively, and taking the average value of the product values as the loss value.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of claims 1-8 when executing the program.
18. A storage medium having instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110470407.0A CN115250365A (en) | 2021-04-28 | 2021-04-28 | Commodity text generation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110470407.0A CN115250365A (en) | 2021-04-28 | 2021-04-28 | Commodity text generation method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115250365A true CN115250365A (en) | 2022-10-28 |
Family
ID=83696007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110470407.0A Pending CN115250365A (en) | 2021-04-28 | 2021-04-28 | Commodity text generation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115250365A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706055A (en) * | 2019-08-22 | 2020-01-17 | 平安科技（深圳）有限公司 | Commodity information pushing method and device, storage medium and computer equipment |
| CN111209725A (en) * | 2018-11-19 | 2020-05-29 | 阿里巴巴集团控股有限公司 | Text information generation method and device and computing equipment |
| CN111597326A (en) * | 2019-02-21 | 2020-08-28 | 北京京东尚科信息技术有限公司 | Method and device for generating commodity description text |
| WO2020207431A1 (en) * | 2019-04-12 | 2020-10-15 | 智慧芽信息科技(苏州)有限公司 | Document classification method, apparatus and device, and storage medium |
| CN112035624A (en) * | 2020-09-11 | 2020-12-04 | 上海明略人工智能(集团)有限公司 | Text recommendation method and device and storage medium |
-
2021
- 2021-04-28 CN CN202110470407.0A patent/CN115250365A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209725A (en) * | 2018-11-19 | 2020-05-29 | 阿里巴巴集团控股有限公司 | Text information generation method and device and computing equipment |
| CN111597326A (en) * | 2019-02-21 | 2020-08-28 | 北京京东尚科信息技术有限公司 | Method and device for generating commodity description text |
| WO2020207431A1 (en) * | 2019-04-12 | 2020-10-15 | 智慧芽信息科技(苏州)有限公司 | Document classification method, apparatus and device, and storage medium |
| CN110706055A (en) * | 2019-08-22 | 2020-01-17 | 平安科技（深圳）有限公司 | Commodity information pushing method and device, storage medium and computer equipment |
| CN112035624A (en) * | 2020-09-11 | 2020-12-04 | 上海明略人工智能(集团)有限公司 | Text recommendation method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shahbaznezhad et al. | The role of social media content format and platform in users’ engagement behavior | |
| Wu et al. | Community engagement and online word of mouth: An empirical investigation | |
| Yun et al. | Challenges and future directions of computational advertising measurement systems | |
| Rossi | Even the rich can make themselves poor: A critical examination of IV methods in marketing applications | |
| US20130212177A1 (en) | Method and System for Generating a Social Commerce and Marketing Site | |
| Sudirjo et al. | The Application of Extended Expectation-Confirmation Model to Identify Influencing Factors Digital Loyalty for Mobile-Based Travel Platform | |
| CN111784400A (en) | Advertisement bidding method, device, electronic device and computer readable medium | |
| US20170262882A1 (en) | Systems, media, and methods for printing customized paper receipts at the point-of-sale | |
| Peng et al. | Exploring the influence of determinants on behavior intention to use of multiple media kiosks through technology readiness and acceptance model | |
| CN112100558A (en) | Method, device, equipment and storage medium for object recommendation | |
| CN111612588A (en) | Commodity presentation method and device, computing equipment and computer-readable storage medium | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN108229997A (en) | A kind of method and system of internet shopping promotion | |
| CN110796480A (en) | Real-time advertisement putting management method, device and system | |
| CN112348590A (en) | Method and device for determining value of article, electronic equipment and storage medium | |
| Nugraheni et al. | Continuance Intention to Use (CIU) on Technology Acceptance Model (TAM) for m-payment (Case Study: TIX ID) | |
| CN115250365A (en) | Commodity text generation method and device, computer equipment and storage medium | |
| WO2022089427A1 (en) | Video generation method and apparatus, and electronic device and computer-readable medium | |
| Vali et al. | Comparative reviews vs. regular consumer reviews: Effects of presentation format and review valence | |
| Yoo et al. | Understanding online purchase intentions of licensed sports merchandise through integration of technology acceptance model and trust | |
| KR20220118703A (en) | Machine Learning based Online Shopping Review Sentiment Prediction System and Method | |
| Herrera-Collins et al. | The Effect of Shop Design, Digital Signage and Digital Spirit on the Online Shopping Experience of Retail Businesses | |
| CN113421106A (en) | Commodity data processing method and device and electronic equipment | |
| US20230401634A1 (en) | Product card ecommerce purchase within short-form videos | |
| CN117273821B (en) | Issuing method, training method and related device of electronic equity certificates |
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 |