CN111915339B - Data processing method, device and equipment - Google Patents
Data processing method, device and equipment Download PDFInfo
- Publication number
- CN111915339B CN111915339B CN201910384167.5A CN201910384167A CN111915339B CN 111915339 B CN111915339 B CN 111915339B CN 201910384167 A CN201910384167 A CN 201910384167A CN 111915339 B CN111915339 B CN 111915339B
- Authority
- CN
- China
- Prior art keywords
- data
- processed
- description information
- language model
- information
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the invention provides a data processing method, a device and equipment, wherein the method comprises the following steps: obtaining data to be processed, wherein the data to be processed comprises at least one of the following: text information, picture information, and video information; and processing the data to be processed by using a language model to obtain at least one data description information corresponding to the data to be processed, wherein the language model is used for analyzing data elements included in the data to be processed and relations among the data elements and establishing a language rule system. The method has the advantages that the data to be processed is obtained, the language model is utilized to process the data to be processed, at least one data description information corresponding to the data to be processed is obtained, the accurate data description information can be obtained on the basis of guaranteeing the data promotion cost, meanwhile, the promotion or promotion effect of the data is guaranteed, the practicability of the method is further improved, and the method is beneficial to popularization and application of markets.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method, an apparatus, and a device for processing data.
Background
Along with the rapid development of science and technology, the technology of digitizing information has gradually advanced to various fields in human life, especially in the fields of electronic commerce, internet finance, logistics, cloud computing and the like, and the application of the technology of digitizing information is more extensive.
Taking the e-commerce field as an example, when data (such as data information, image information and text information) on an e-commerce platform is released, data description information corresponding to the data needs to be filled in, so that effective promotion of the data is realized through the data description information. In the prior art, the data description information is generally edited and designed by a professional publisher, or the data description information is filled in by a user. However, when editing data description information by professionals, promotion or promotion costs are increased; when the user fills in the data description information, the data description information is not accurate enough and is not attractive to the user, so that the promotion or promotion effect of the data is reduced.
Disclosure of Invention
The embodiment of the invention provides a data processing method, a device and equipment, which can acquire more accurate data description information on the basis of ensuring the data promotion cost, thereby improving the promotion or promotion effect of data.
In a first aspect, an embodiment of the present invention provides a method for processing data, including:
obtaining data to be processed, wherein the data to be processed comprises at least one of the following: text information, picture information, and video information;
and processing the data to be processed by using a language model to obtain at least one data description information corresponding to the data to be processed, wherein the language model is used for analyzing data elements included in the data to be processed and relations among the data elements and establishing a language rule system.
In a second aspect, an embodiment of the present invention provides a data processing apparatus, including:
An acquisition module for acquiring data to be processed, the data to be processed comprises at least one of the following: text information, picture information, and video information;
The processing module is used for processing the data to be processed by utilizing a language model to obtain at least one data description information corresponding to the data to be processed, wherein the language model is used for analyzing the data elements included in the data to be processed and the relation among the data elements and establishing a language rule system.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement a method of processing data as described in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium storing a computer program, where the computer program makes a computer execute a method for processing data according to the first aspect.
The method has the advantages that the data to be processed is obtained, the language model is utilized to process the data to be processed, at least one data description information corresponding to the data to be processed is obtained, the accurate data description information can be obtained on the basis of guaranteeing the data promotion cost, meanwhile, the promotion or promotion effect of the data is guaranteed, the practicability of the method is further improved, and the method is beneficial to popularization and application of markets.
In a fifth aspect, an embodiment of the present invention provides a method for processing data, including:
Determining a language model;
inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information, and video information;
The language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
In a sixth aspect, an embodiment of the present invention provides a data processing apparatus, including:
A determining module for determining a language model;
The input module is used for inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information, and video information;
The language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
In a seventh aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement a method of processing data as described in the fifth aspect above.
In an eighth aspect, an embodiment of the present invention provides a computer storage medium storing a computer program, where the computer program causes a computer to implement the data processing method according to the fifth aspect.
Through determining a language model, the to-be-processed object and to-be-processed data corresponding to the to-be-processed object are input into the language model, then the language model is utilized to process the data information, at least one propaganda description information corresponding to the to-be-processed object is obtained, the propaganda description information can be used for promoting and propaganda on the to-be-processed object, the relatively accurate propaganda description information can be obtained on the basis of guaranteeing the data promoting cost, the promoting or promoting effect of the to-be-processed object is guaranteed, the practicability of the method is further improved, and the popularization and application of the market are facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1a is a schematic system structure diagram of a method for processing application data according to an embodiment of the present invention;
FIG. 1 is a flowchart illustrating a method for processing data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an interface of data description information according to an embodiment of the present invention;
FIG. 3 is a second flowchart of a data processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart III of a data processing method according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for processing data according to an embodiment of the present invention;
FIG. 6 is a flowchart of another method for processing data according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating a method for processing data according to an embodiment of the present invention;
FIG. 8 is a second flowchart of a data processing method according to an embodiment of the present invention;
FIG. 9 is a flowchart III of a method for processing data according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a data processing device according to an embodiment of the present invention;
FIG. 11 is a schematic structural diagram of an electronic device corresponding to the data processing apparatus provided in the embodiment shown in FIG. 10;
FIG. 12 is a schematic diagram of another data processing apparatus according to an embodiment of the present invention;
Fig. 13 is a schematic structural diagram of an electronic device corresponding to the data processing apparatus provided in the embodiment shown in fig. 12.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two, but does not exclude the case of at least one.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or system comprising such elements.
In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.
Definition of terms:
The language model is language abstract mathematical modeling according to language objective facts, and is a corresponding relation; the relation between the language model and the language objective facts is similar to the relation between the mathematical abstract straight line and the specific straight line. The language model is mainly of three types: generating a sex model, an analytical model and an identification model; specifically, the generative model starts from a formal language system and generates a certain set of languages, such as n. The analytical model is a language model which starts from a certain set of languages, clarifies the relation among the elements according to the analysis of the properties of each element in the set, and establishes a language rule system on the basis of the analysis, such as a language model which is proposed by a set theory method by Soviet mathematician O.C. kurarina and Romania mathematician S. Ma Erku. On the basis of the generative model and the analytic model, the two models are combined to generate a model with high practical value, namely an identification model. The recognition model can start from a certain set of language elements and a rule system, and determine whether the elements are certain words or qualified sentences in the language through operation of limited steps. Such as a syntax type calculus model proposed by the mathematical logic method of the Bare-Hill.
In order to facilitate understanding of the technical solution of the present application, the prior art will be briefly described by taking the e-commerce field as an example:
In the prior art, related commodity information descriptions can be automatically generated according to a few information (pictures, characters and the like) provided by a user, so that industry is gradually attracted, for example, data can be processed by utilizing a Boltzmann machine (VAE, boltzmann Machine) generation technology to obtain the commodity information descriptions; subsequently, the boltzmann machine generation technique was replaced by an antagonistic generation technique (GENERATIVE ADVERSARIAL Networks, GAN for short). However, when analyzing data using GAN technology, there are the following problems:
1) GAN technology has been used to advantage in image style transfer, such as: pix2Pix GAN and Cycle GAN for Image-to-Image, but GAN technology is not yet mature in processing technology of video data;
2) The GAN technique alone has limited effectiveness in word generation, but in combination with reinforcement learning algorithms, such as: the Seq GAN achieves good effect, so how to train GAN to produce accurate, rich, various and personalized commodity descriptions is a great challenge;
3) The comprehensive multi-mode information (pictures, videos and characters) automatically generates a series of related commodity description information (poster, main picture, title and description), meanwhile, the attribute of the buyer is considered for personalized generation, and the season is considered for related recommendation to be a difficult problem.
In order to solve the above technical problem, referring to fig. 1a, the present embodiment provides a data processing system capable of implementing a data processing method, where the data processing system includes a user terminal 01 and a processing device 02 communicatively connected to the user terminal 01, where the user terminal 01 may be various electronic devices such as a mobile phone, a tablet computer, a personal computer, etc., and the processing device 02 may be implemented as software, or a combination of software and hardware. In addition, the user terminal 01 and the processing means 02 may be a client/server CS architecture established on a local area network; alternatively, the user terminal 01 and the processing device 02 may be a browser/server BS architecture established on a wide area network, and those skilled in the art may select different implementations according to specific application scenarios. Specific:
The user terminal 01 is configured to detect an execution operation input by a user, and generate a to-be-processed request based on the execution operation, where the to-be-processed request may include to-be-processed data, where the to-be-processed data may include at least one of: text information, picture information, video information. After the user terminal 01 acquires the request to be processed input by the user, the request to be processed may be sent to the processing apparatus 02.
The user terminal 01 may be provided with an application program or an application website corresponding to the processing device 02, and the user may send the input request to be processed to the processing device 02 through the application program or the application website; for example, when the user wants to perform the prediction processing of the data, the data input port in the application program may be used to input a request to be processed, and after the user terminal 01 obtains the request to be processed, the request to be processed may be sent to the processing device 02 for processing.
The processing device 02 is in communication connection with the user terminal 01, and is configured to receive a request to be processed sent by the user terminal 01, and after receiving the request to be processed, process data to be processed by using a language model to obtain at least one data description information corresponding to the data to be processed, where the data description information includes at least one of the following: image information, title, data description text, data description video.
In this embodiment, after a request to be processed is obtained, corresponding data to be processed may be obtained through the request to be processed, and then the data to be processed is processed by using a language model to obtain at least one data description information corresponding to the data to be processed, so that the data description information may be automatically generated according to the information included in the data to be processed, thereby effectively realizing that relatively accurate commodity description information is obtained on the basis of guaranteeing commodity promotion cost, further improving the promotion or promotion effect on commodities, satisfying the use requirement of users, further improving the practicality of the method, and being beneficial to the promotion and application of markets.
In order to facilitate understanding of the technical solution in this embodiment, the following describes the data processing process in detail, and referring to fig. 1, this embodiment provides a data processing method, where an execution body of the processing method is a data processing device, and the processing device may be implemented as software, or a combination of software and hardware. Specifically, the method may include:
s101: obtaining data to be processed, wherein the data to be processed comprises at least one of the following: text information, picture information, video information.
The video information may include picture information and text information. However, the specific implementation manner of acquiring the data to be processed is not limited in this embodiment, and those skilled in the art may set the data according to specific use requirements, for example: the data to be processed can be stored in a preset area, and can be obtained by accessing the preset area. Or the data to be processed may be stored in other equipment ends (for example, a user terminal), and the data to be processed stored in the equipment ends is obtained through communication connection with the equipment ends, and specifically, one implementation manner is as follows: a data acquisition request can be sent to the equipment end, so that the equipment end can return data to be processed based on the data request; or another way of realisation is: the device side can actively send the data to be processed to the processing device, so that the processing device can actively acquire the data to be processed.
It can be understood that when the device side is a user terminal, after the user terminal obtains the data to be processed, preferably, the user terminal can actively send the data to be processed to the processing device for processing, so that the quality and efficiency of data processing can be improved.
S102: processing data to be processed by using a language model to obtain at least one data description information corresponding to the data to be processed, wherein the language model is used for analyzing data elements included in the data to be processed and relations among the data elements and establishing a language rule system.
The language model may be an analytical language model or an identifying language model, and the language model is used for processing data to be processed, specifically, the language model is used for analyzing data elements included in the data to be processed and relationships among the data elements, and establishing a rule system of language, wherein in the field of computers, the minimum unit of representing information is one bit of binary number, which is called bit; a bit string formed by combining several bits represents a data element (e.g., a bit string of a word length represents an integer, an 8-bit binary number represents a character, etc.), and is commonly referred to as an element or node. Thus, after obtaining the data elements included in the data to be processed, the properties of the data elements included in the data to be processed can be analyzed using a language model, the relationships between the individual data elements can be determined, and on the basis of the above information, a rule system of the language can be established in a deductive way.
It should be noted that the language model may directly process the data to be processed including the video information accurately and effectively, so as to obtain at least one data description information corresponding to the data to be processed, where the data description information may include at least one of the following: image information, titles, data description text, data description video; the popularization or promotion effect of the data can be effectively improved through the generated data description information.
For example, a set of data to be processed about the suit-dress is acquired, the data to be processed at this time includes text information and picture information for the suit-dress, after the data to be processed is acquired, the data to be processed can be analyzed and processed by using a language model, so that at least one data description information corresponding to the suit-dress can be obtained, on the basis of ensuring the data promotion cost, more accurate data description information can be acquired, and further the promotion or promotion effect of the data can be improved through the generated data description information.
Specifically, as shown in fig. 2, the diagram is a schematic diagram of a display interface of data description information, where the data description information in the display interface may include: where the title is, "good", title description information, text title "style", text title description information, image information (e.g., poster, picture, etc.) corresponding to picture information in the data to be processed, or data description video, etc. It can be appreciated that the style or layout of the display interface of the data description information is not limited to the style or layout of the display interface shown in fig. 2, and those skilled in the art may also perform any setting according to specific design requirements and application requirements, which is not described herein.
Optionally, after obtaining at least one data description information corresponding to the data to be processed, the method in the present embodiment further includes:
S103: at least one data description information is output.
After the data description information is obtained, the data description information may be selectively output according to user's needs, for example: when the user requests to output the data description information, at least one data description information can be output according to the request of the user, so that the user can intuitively and rapidly acquire the content of the data description information; when the user does not request to output the data description information, the operation of outputting the data description information can not be performed, so that the flexibility of the method is effectively improved.
According to the data processing method, the data to be processed is obtained, the language model is utilized to process the data to be processed, at least one data description information corresponding to the data to be processed is obtained, the fact that relatively accurate data description information can be obtained on the basis of guaranteeing data promotion cost is effectively achieved, meanwhile, the promotion or promotion effect of the data is guaranteed, the practicability of the method is further improved, and the popularization and application of the method are facilitated.
FIG. 3 is a second flowchart of a data processing method according to an embodiment of the present invention; on the basis of the foregoing embodiment, with continued reference to fig. 3, before acquiring the data to be processed, the method in this embodiment may further include:
s001: training data and training description information corresponding to the training data are acquired.
Wherein the training data may include at least one of: processed data for the historical object, feedback data fed back for the historical object, and model output data generated for the historical object. Correspondingly, the training description information may include at least one of: descriptive information corresponding to the processed data, descriptive information fed back for the historical object, and descriptive information generated for the historical object. It is understood that a history object may refer to: goods, services, or other similar objects, etc.
In addition, the specific implementation manner of acquiring the training data and the training description information corresponding to the training data is not limited in this embodiment, and those skilled in the art may set the implementation manner according to specific use requirements, for example: the training data and the training description information corresponding to the training data may be stored in a preset area, and the training data and the training description information corresponding to the training data may be acquired by accessing the preset area. Or the training data and the training description information corresponding to the training data can be stored in other equipment ends, and the training data stored in the equipment ends and the training description information corresponding to the training data can be obtained through communication connection with the equipment ends.
Of course, those skilled in the art may also acquire the training data and the training description information corresponding to the training data in other manners, so long as accuracy and reliability of acquiring the training data and the training description information can be ensured, and details are not repeated herein.
S002: and learning and training the training data and the training description information to obtain a language model.
After the training data and the training description information are acquired, the training data and the training description information can be learned and trained, so that a language model can be obtained, and the language model can analyze and identify each element of the training data and the training description information, so that the relation among each element can be obtained.
The language model is obtained through the method, the accuracy and the reliability of the language model are effectively ensured, and the processing quality and the processing efficiency of the method are further improved.
Optionally, based on an implementation manner of the foregoing embodiment, after obtaining at least one data description information corresponding to the data to be processed, the method in this embodiment may further include:
S201: and adjusting the language model by using the training data, the training description information corresponding to the training data, the data to be processed and at least one data description information.
For example, after the training data and the training description information are used to obtain the language model, the language model can be used to analyze and process the data to be processed a, so that the data description information a corresponding to the data to be processed a can be obtained, after the data description information a is obtained, the training data, the training description data, the data to be processed a and the data description information a can be used again to adjust and update the language model, so that the accuracy and reliability of the language model in processing the data can be improved, and the quality and efficiency of the language model in processing other data are further improved.
FIG. 4 is a flowchart III of a data processing method according to an embodiment of the present invention; on the basis of any one of the foregoing embodiments, with continued reference to fig. 4, after obtaining at least one data description information corresponding to the data to be processed, the method in this embodiment may further include:
S301: and acquiring the behavior characteristics of the user.
Wherein the behavioral characteristics of the user may include at least one of: user operation network behavior, user login network behavior, user access network behavior. In addition, the specific acquisition mode of the behavior feature of the user is not limited in this embodiment, and a person skilled in the art may set any setting according to specific design requirements and application requirements, for example: a blog may be obtained, behavioral characteristics of the user may be obtained through analytical identification of the blog, and so on.
S302: and determining target description information in at least one data description information according to the behavior characteristics of the user.
After the behavior feature of the user is obtained, the target description information may be determined in at least one data description information according to the behavior feature of the user, for example: according to the behavior characteristics of the user, preference, interest and the like of the user are analyzed, then the matching degree of at least one data description information can be identified based on the preference or interest of the user, and the data description information with the matching degree being greater than or equal to a preset threshold value can be determined as target description information.
Optionally, the method in this embodiment may further include:
s303: and outputting the target description information.
After the target description information is obtained, the target description information may be selectively output according to the user's demand, for example: when the user requests to output the target description information, at least one target description information can be output according to the request of the user, so that the user can intuitively and rapidly acquire the content of the target description information; when the user does not request to output the target description information, the operation of outputting the target description information can not be performed, so that the flexibility of the method is effectively improved.
FIG. 5 is a flowchart of a method for processing data according to an embodiment of the present invention; on the basis of any one of the foregoing embodiments, with continued reference to fig. 5, the method in this embodiment may further include:
s401: and acquiring feedback information sent by the user aiming at the data description information.
S402: and adjusting the language model according to the feedback information.
The data description information in this embodiment may be at least one data description information obtained directly after processing the data to be processed by using a language model, or the data description information may also refer to target description information obtained after analyzing and processing the at least one data description information. That is, one way that can be achieved is: after obtaining at least one data description information corresponding to the data to be processed, the user may send feedback information for the data description information through the terminal device, where the feedback information may include an accuracy description of the data description information or standard data description information for the data to be processed, and so on; after obtaining feedback information sent by the user for the data description information, the language model may be adjusted according to the feedback information. Another way that can be achieved is: after determining the target description information in at least one data description information according to the behavior characteristics of the user, the user can send feedback information for the target description information through the terminal equipment, wherein the feedback information can comprise accuracy description of the target description information or standard data description information for data to be processed and the like; after obtaining feedback information sent by the user for the target description information, the language model may be adjusted according to the feedback information.
Specifically, when the language model is adjusted according to the feedback information, one implementation manner is as follows: after obtaining the language model based on the training data and the training description information, the language model may be adjusted according to the feedback information; or the language model can be adjusted according to the data to be processed, at least one data description information corresponding to the data to be processed and the feedback information. Yet another way of realising is: after the language model is obtained based on the training data and the training description information, the language model may be adjusted according to the training data, the training description information, and the feedback information. Or yet another way of realising is: after the language model is obtained based on the training data and the training description information, the language model may be adjusted according to the training data, the training description information, the feedback information, the data to be processed, and at least one data description information corresponding to the data to be processed.
The method can be used for adjusting and updating the language model in different modes according to specific application requirements by a person skilled in the art, and only the timely adjustment and updating operation of the language model can be realized, so that the accuracy and the reliability of the processing of the data by the language model can be improved, and the quality and the efficiency of the processing of other data by the language model can be further improved.
FIG. 6 is a flowchart of another method for processing data according to an embodiment of the present invention; referring to fig. 6, the present embodiment provides another data processing method, where the execution body of the processing method is a data processing device, and the processing device may be implemented as software, or a combination of software and hardware. Specifically, the method may include:
S501: a language model is determined.
The language model can comprise a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is a statistical analysis method for determining the interdependent quantitative relationship between two or more variables; in this embodiment, the regression estimation sub-algorithm is configured to analyze the data elements included in the data to be processed and the relationships between the data elements, so as to obtain an element relationship result. In addition, the rule reasoning sub-algorithm is used for establishing a rule system of a language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
S502: inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information, video information.
Wherein the object to be processed may comprise goods and/or services, such as: the object to be processed may be clothing, a product, etc. to be promoted for sale, or the object to be processed may be a restaurant service, an entertainment service, etc. to be sold. And processing the data information by using a language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the language model is used for analyzing the data elements included in the data to be processed and the relation among the data elements and establishing a language rule system.
The implementation process and implementation effect of the steps in this embodiment are similar to those of the steps S101 to S102 in the embodiment, and specific reference may be made to the above description, which is not repeated here.
It is contemplated that the method of this embodiment may include some or all of the methods described above in the embodiments of fig. 2-6, and reference may be made to the descriptions of the embodiments of fig. 2-6 for portions of this embodiment not described in detail. The implementation process and the technical effect of this technical solution are described in the embodiments shown in fig. 2 to 6, and are not described herein.
According to the data processing method provided by the embodiment, the language model is determined, the to-be-processed object and the to-be-processed data corresponding to the to-be-processed object are input into the language model, then the language model is utilized to process the data information, at least one propaganda description information corresponding to the to-be-processed object is obtained, the propaganda description information can be used for promoting and propaganda of the to-be-processed object, the relatively accurate propaganda description information can be obtained on the basis of guaranteeing the data promotion cost, the promotion or promotion effect of the to-be-processed object is guaranteed, the practicability of the method is further improved, and the marketing and application are facilitated.
In a specific application, referring to fig. 7 to fig. 9, the present application embodiment provides a data processing method, where the data processing method includes a training obtaining language model and a process for using the language model, and specifically referring to fig. 7, the step of training obtaining the language model includes:
step1: obtaining training data
Wherein the training data comprises at least one of: training data a-the commodity and description data pair of the product edited by the user, training data b-the commodity and description data pair produced according to online user feedback and training data c-the commodity and description data pair produced by the current model. Specifically, the training data a is a product description and description data pair edited for a historical product, after the training data a is obtained, the training data a can be independently subjected to learning training to obtain a language model, the training data b is feedback information provided by data description information output by a user for the language model, and the feedback information can comprise data information and data description information for a product to be processed.
Step2: model training is carried out based on training data, and a language model is obtained.
Specifically, in the model training process, a multi-dimensional estimation process may be performed on training data by using a preset algorithm (for example, a review estimation model), where the estimation process is used to ensure objective descriptions such as diversity and richness of the training data, and further, the training data may be subjected to a correlation analysis process, so as to obtain a correlation score between the training data, and further, the training data may be further subjected to an evaluation process by using a GAN discriminator, so as to improve accuracy of distinguishing the training data.
It can be understood that after the language model is obtained, the model parameters in the language model can be timely adjusted and updated by using an error back propagation algorithm, so that the accuracy of the use of the language model is further improved.
Referring to fig. 8-9, the steps of processing data using a language model include:
step101: and collecting external data, wherein the external data refers to training data in the drawings, the external data is used for realizing a training process of a language model, and the language model can process data to be processed so as to output commodity description information.
Step102: language model training is performed based on the collected external data.
Input: integrating the completed training data;
and (3) outputting: a language model.
Step103: the data to be processed is processed using the language model, thereby generating data description information (e.g., commodity description information).
Input: data information (e.g., merchandise information), language model;
and (3) outputting: at least one data description information corresponding to the data.
Step104: the data describes personalized distribution.
Input: user information and data description;
And (3) outputting: the user data description information is recommended.
Step105: and recovering data on the user line.
And (3) outputting: and the user can optimally update the language model for displaying the feedback result of the description.
The step103 may specifically include the following steps, as shown in fig. 9:
step1031: acquiring commodity information to be processed, wherein the commodity information can comprise: commodity images, commodity text (text), commodity video, or the like.
Step1032: and inputting the commodity information to be processed into the language model to realize analysis and identification of the commodity information, and outputting a commodity description set corresponding to the commodity information.
Step1033: analyzing and processing the commodity description set by using a preset correlation model, so that the high-precision commodity description set can be obtained; specifically, the correlation model can perform correlation sorting on the commodity description information in the commodity description set and the behavior of the user, so that commodity description information with higher correlation with the behavior of the user can be obtained, and the commodity description information recommended to the user is further improved to be more accurate.
Step1034: and outputting the final high-precision commodity description set by the output commodity description set, so that the user can directly check the commodity description set conveniently.
According to the data processing method provided by the application embodiment, the data to be processed can comprise text information, picture information and video information, and the data to be processed is processed by utilizing a language model to obtain at least one data description information corresponding to the data to be processed, so that the defect that the GAN technology in the prior art is not mature in video processing is overcome; in addition, the commodity description set is analyzed and processed through the correlation model, so that the commodity description set with high precision can be obtained, different commodity description information is effectively recommended for different users, personalized recommendation information for the users is realized, in addition, the method also effectively realizes that relatively accurate commodity description information can be obtained on the basis of guaranteeing commodity promotion cost, ensures the promotion or promotion effect of commodities, further improves the practicability of the method, and is beneficial to market promotion and application.
Fig. 10 is a schematic structural diagram of a data processing device according to an embodiment of the present invention; referring to fig. 10, the present embodiment provides a data processing apparatus, and the processing apparatus may perform the data processing method corresponding to fig. 1. Specifically, the processing device may include:
An obtaining module 11, configured to obtain data to be processed, where the data to be processed includes at least one of: text information, picture information, and video information;
The processing module 12 is configured to process data to be processed by using a language model, and obtain at least one data description information corresponding to the data to be processed, where the language model is configured to analyze data elements included in the data to be processed and relationships between the data elements, and establish a rule system of a language.
Optionally, the data description information includes at least one of: image information, title, data description text.
Alternatively, before acquiring the data to be processed, the acquisition module 11 and the processing module 12 in the present embodiment may be further configured to perform the following steps:
An acquiring module 11, configured to acquire training data and training description information corresponding to the training data;
the processing module 12 is configured to learn and train the training data and the training description information to obtain a language model.
Optionally, after obtaining at least one data description information corresponding to the data to be processed, the method further comprises:
And adjusting the language model by using the training data, the training description information corresponding to the training data, the data to be processed and at least one data description information.
Optionally, after obtaining at least one data description information corresponding to the data to be processed, the processing module 12 in this embodiment may be further configured to perform the following steps: at least one data description information is output.
Optionally, after obtaining at least one data description information corresponding to the data to be processed, the obtaining module 11 and the processing module 12 in the present embodiment may be further configured to perform the following steps:
an obtaining module 11, configured to obtain a behavior feature of a user;
the processing module 12 is configured to determine the target description information from the at least one data description information according to the behavior characteristics of the user.
Optionally, the processing module 12 in this embodiment may be further configured to perform the following steps: and outputting the target description information.
Alternatively, the acquisition module 11 and the processing module 12 in the present embodiment may be further configured to perform the following steps:
An obtaining module 11, configured to obtain feedback information sent by a user for the data description information;
the processing module 12 is configured to adjust the language model according to the feedback information.
The apparatus shown in fig. 10 may perform the method of the embodiment shown in fig. 1-5 and fig. 7-9, and reference is made to the relevant description of the embodiment shown in fig. 1-5 and fig. 7-9 for parts of this embodiment not described in detail. The implementation process and technical effects of this technical solution are described in the embodiments shown in fig. 1 to 5 and fig. 7 to 9, and are not described herein.
In one possible design, the structure of the data processing apparatus shown in fig. 10 may be implemented as an electronic device, which may be a mobile phone, a tablet computer, a server, or other devices. As shown in fig. 11, the electronic device may include: a first processor 21 and a first memory 22. The first memory 22 is used for storing a program for supporting the electronic device to execute the processing method of the data provided in the embodiments shown in fig. 1 to 8, and the first processor 21 is configured to execute the program stored in the first memory 22.
The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the first processor 21, are capable of performing the steps of:
obtaining data to be processed, wherein the data to be processed comprises at least one of the following: text information, picture information, and video information;
and processing the data to be processed by using the language model to obtain at least one data description information corresponding to the data to be processed.
Optionally, the first processor 21 is further configured to perform all or part of the steps in the embodiments shown in fig. 1-5 and fig. 7-9.
The electronic device may further include a first communication interface 23 in a structure for the electronic device to communicate with other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium, which is used for storing computer software instructions for an electronic device, and includes a program for executing the data processing method in the method embodiments shown in fig. 1 to 5 and fig. 7 to 9.
FIG. 12 is a schematic diagram of another data processing apparatus according to an embodiment of the present invention; referring to fig. 12, this embodiment provides another data processing apparatus, and the processing apparatus may perform the data processing method corresponding to fig. 6. Specifically, the processing device may include:
A determining module 31 for determining a language model; the language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
An input module 32, configured to input an object to be processed and data to be processed corresponding to the object to be processed into the language model, and obtain at least one advertisement description information corresponding to the object to be processed, where the data to be processed includes at least one of the following: text information, picture information, video information.
The apparatus of fig. 12 may perform the method of the embodiment of fig. 6-9, and reference is made to the relevant description of the embodiment of fig. 6-9 for parts of this embodiment not described in detail. The implementation process and the technical effect of this technical solution are described in the embodiments shown in fig. 6 to 9, and are not described herein.
In one possible design, the structure of the data processing apparatus shown in fig. 12 may be implemented as an electronic device, which may be a mobile phone, a tablet computer, a server, or other devices. As shown in fig. 13, the electronic device may include: a second processor 41 and a second memory 42. Wherein the second memory 42 is for storing a program for supporting the electronic device to execute the processing method of the data provided in the embodiment shown in fig. 6 described above, the second processor 41 is configured for executing the program stored in the second memory 42.
The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the second processor 41, are capable of performing the steps of:
Determining a language model;
inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information, and video information;
The language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
Optionally, the second processor 41 is further configured to perform all or part of the steps in the embodiments shown in fig. 7-9.
The electronic device may further include a second communication interface 43 in the structure of the electronic device, for communicating with other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions for an electronic device, where the computer storage medium includes a program for executing the method for processing data in the method embodiments shown in fig. 6 to fig. 9.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by adding necessary general purpose hardware platforms, or may be implemented by a combination of hardware and software. Based on such understanding, the foregoing aspects, in essence and portions contributing to the art, may be embodied in the form of a computer program product, which may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (13)
1. A method of processing data, comprising:
obtaining data to be processed, wherein the data to be processed comprises at least one of the following: text information, picture information, and video information;
processing the data to be processed by using a language model to obtain at least one data description information corresponding to the data to be processed, wherein the data description information is used for promoting and propaganda the data to be processed, the language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results, and the relations are related to the properties of the data elements; the rule reasoning sub-algorithm is used for establishing a rule system of a language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model;
and analyzing and processing the at least one data description information by using a preset correlation model to obtain at least one target data description information, wherein the correlation model is used for carrying out correlation sequencing on the at least one data description information and the user behavior so as to obtain at least one target data description information with higher correlation with the user behavior.
2. The method of claim 1, wherein the data description information includes at least one of:
Image information, title, data description text.
3. The method of claim 1, wherein prior to acquiring the data to be processed, the method further comprises:
Acquiring training data and training description information corresponding to the training data;
And learning and training the training data and the training description information to obtain the language model.
4. A method according to claim 3, wherein after obtaining at least one data description information corresponding to the data to be processed, the method further comprises:
And adjusting the language model by using the training data, training description information corresponding to the training data, the data to be processed and at least one data description information.
5. The method according to any one of claims 1-4, wherein after obtaining at least one data description information corresponding to the data to be processed, the method further comprises:
and outputting at least one piece of data description information.
6. The method according to any one of claims 1-4, wherein after obtaining at least one data description information corresponding to the data to be processed, the method further comprises:
Acquiring behavior characteristics of a user;
And determining target description information in at least one piece of data description information according to the behavior characteristics of the user.
7. The method of claim 6, wherein the method further comprises:
And outputting the target description information.
8. The method according to any one of claims 1-4, further comprising:
acquiring feedback information sent by a user aiming at the data description information;
And adjusting the language model according to the feedback information.
9. A data processing apparatus, comprising:
An acquisition module for acquiring data to be processed, the data to be processed comprises at least one of the following: text information, picture information, and video information;
The processing module is used for processing the data to be processed by utilizing a language model to obtain at least one data description information corresponding to the data to be processed, wherein the data description information is used for promoting the data to be processed, the language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results, and the relations are related to the properties of the data elements; the rule reasoning sub-algorithm is used for establishing a rule system of a language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model; and analyzing and processing the at least one data description information by using a preset correlation model to obtain at least one target data description information, wherein the correlation model is used for carrying out correlation sequencing on the at least one data description information and the user behavior so as to obtain at least one target data description information with higher correlation with the user behavior.
10. An electronic device, comprising: a memory, a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of processing data as claimed in any one of claims 1 to 8.
11. A method of processing data, comprising:
Determining a language model;
Inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information and video information, wherein the propaganda description information is used for promoting and propaganda on the object to be processed;
analyzing and processing the at least one propaganda description information by using a preset correlation model to obtain at least one target propaganda description information, wherein the correlation model is used for sequencing the correlation of the at least one propaganda description information and the behavior of the user so as to obtain at least one target propaganda description information with higher correlation with the behavior of the user;
The language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results, and the relations are related to the properties of the data elements; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
12. A data processing apparatus, comprising:
a determining module for determining a language model;
The input module is used for inputting an object to be processed and data to be processed corresponding to the object to be processed into the language model to obtain at least one propaganda description information corresponding to the object to be processed, wherein the data to be processed comprises at least one of the following components: text information, picture information and video information, wherein the propaganda description information is used for promoting and propaganda on the object to be processed; analyzing and processing the at least one propaganda description information by using a preset correlation model to obtain at least one target propaganda description information, wherein the correlation model is used for sequencing the correlation of the at least one propaganda description information and the behavior of the user so as to obtain at least one target propaganda description information with higher correlation with the behavior of the user;
The language model comprises a regression estimation sub-algorithm and a rule reasoning sub-algorithm, wherein the regression estimation sub-algorithm is used for analyzing data elements included in the data to be processed and relations among the data elements to obtain element relation results, and the relations are related to the properties of the data elements; the rule reasoning sub-algorithm is used for establishing a rule system of the language, and the rule system is used for analyzing and processing the element relation result so as to determine output data of the language model.
13. An electronic device, comprising: a memory, a processor; wherein the memory is configured to store one or more computer instructions that, when executed by the processor, implement the method of processing data as recited in claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910384167.5A CN111915339B (en) | 2019-05-09 | 2019-05-09 | Data processing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910384167.5A CN111915339B (en) | 2019-05-09 | 2019-05-09 | Data processing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111915339A CN111915339A (en) | 2020-11-10 |
| CN111915339B true CN111915339B (en) | 2024-11-15 |
Family
ID=73242118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910384167.5A Active CN111915339B (en) | 2019-05-09 | 2019-05-09 | Data processing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111915339B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051748B (en) * | 2021-03-19 | 2024-09-03 | 北京圣涛平试验工程技术研究院有限责任公司 | Method and device for constructing all-factor risk of aircraft reliability data asset |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514209A (en) * | 2012-06-27 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and equipment for generating promotion information of object to be promoted based on object information base |
| CN109117485A (en) * | 2018-09-06 | 2019-01-01 | 北京京东尚科信息技术有限公司 | Bless language document creation method and device, computer readable storage medium |
| CN109597973A (en) * | 2017-09-30 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of recommendation, generation method and the device of official documents and correspondence information |
| CN109685116A (en) * | 2018-11-30 | 2019-04-26 | 腾讯科技（深圳）有限公司 | Description information of image generation method and device and electronic device |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7542971B2 (en) * | 2004-02-02 | 2009-06-02 | Fuji Xerox Co., Ltd. | Systems and methods for collaborative note-taking |
| US10002325B2 (en) * | 2005-03-30 | 2018-06-19 | Primal Fusion Inc. | Knowledge representation systems and methods incorporating inference rules |
| CN101551825A (en) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | Personalized film recommendation system and method based on attribute description |
| CN103514191A (en) * | 2012-06-20 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and device for determining keyword matching mode of target popularization information |
| CN103971268B (en) * | 2014-04-14 | 2017-03-08 | 百度在线网络技术（北京）有限公司 | The processing method and processing device of promotion message |
| US20150331936A1 (en) * | 2014-05-14 | 2015-11-19 | Faris ALQADAH | Method and system for extracting a product and classifying text-based electronic documents |
| CN110443351B (en) * | 2014-11-14 | 2021-05-28 | 谷歌有限责任公司 | Generate a natural language description of the image |
| US10311859B2 (en) * | 2016-01-16 | 2019-06-04 | Genesys Telecommunications Laboratories, Inc. | Material selection for language model customization in speech recognition for speech analytics |
| US10296548B2 (en) * | 2016-11-30 | 2019-05-21 | Facebook, Inc. | Delivering content promoting a web page to users of an online system |
| CN107918782B (en) * | 2016-12-29 | 2020-01-21 | 中国科学院计算技术研究所 | Method and system for generating natural language for describing image content |
| CN108509465B (en) * | 2017-02-28 | 2022-03-15 | 阿里巴巴集团控股有限公司 | Video data recommendation method and device and server |
| CN107592334A (en) * | 2017-07-17 | 2018-01-16 | 阿里巴巴集团控股有限公司 | A kind of information popularization method, apparatus and equipment |
| CN108932335B (en) * | 2018-07-10 | 2022-01-07 | 北京京东尚科信息技术有限公司 | Method and device for generating file |
| CN109284363B (en) * | 2018-12-03 | 2023-03-14 | 北京羽扇智信息科技有限公司 | Question answering method and device, electronic equipment and storage medium |
-
2019
- 2019-05-09 CN CN201910384167.5A patent/CN111915339B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103514209A (en) * | 2012-06-27 | 2014-01-15 | 百度在线网络技术（北京）有限公司 | Method and equipment for generating promotion information of object to be promoted based on object information base |
| CN109597973A (en) * | 2017-09-30 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of recommendation, generation method and the device of official documents and correspondence information |
| CN109117485A (en) * | 2018-09-06 | 2019-01-01 | 北京京东尚科信息技术有限公司 | Bless language document creation method and device, computer readable storage medium |
| CN109685116A (en) * | 2018-11-30 | 2019-04-26 | 腾讯科技（深圳）有限公司 | Description information of image generation method and device and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111915339A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680219B (en) | Content recommendation method, device, equipment and readable storage medium | |
| US12314830B2 (en) | Aspect pre-selection using machine learning | |
| WO2018188576A1 (en) | Resource pushing method and device | |
| CN106649774A (en) | Artificial intelligence-based object pushing method and apparatus | |
| WO2019114423A1 (en) | Method and apparatus for merging model prediction values, and device | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN107545301B (en) | Page display method and device | |
| CN109189921A (en) | Comment on the training method and device of assessment models | |
| CN113704509B (en) | Multimedia recommendation method and device, electronic equipment and storage medium | |
| CN111738807B (en) | Method, computing device, and computer storage medium for recommending target objects | |
| KR20210062522A (en) | Control method, device and program of user participation keyword selection system | |
| CN110532469B (en) | An information recommendation method, device, equipment and storage medium | |
| US10579752B2 (en) | Generating a model based on input | |
| CN111915339B (en) | Data processing method, device and equipment | |
| CN112102304B (en) | Image processing method, device, computer equipment and computer readable storage medium | |
| CN111507471B (en) | A model training method, device, equipment and storage medium | |
| CN113159877B (en) | Data processing method, device, system and computer readable storage medium | |
| US20250182181A1 (en) | Generating product profile recommendations and quality indicators to enhance product profiles | |
| CN115129829A (en) | Question-answer calculation method, server and storage medium | |
| US20140324524A1 (en) | Evolving a capped customer linkage model using genetic models | |
| US20140324523A1 (en) | Missing String Compensation In Capped Customer Linkage Model | |
| CN119336977A (en) | Method, device, storage medium and electronic device for constructing customer portrait | |
| CN115438268A (en) | Method, apparatus, device and storage medium for content recommendation | |
| CN115982393A (en) | A book push method, push book text generation method, device and electronic equipment | |
| CN117216357A (en) | Recommendation method and device and recommendation model training method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |