CN112446212B - Article generation method and device, electronic equipment and storage medium - Google Patents
Article generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112446212B CN112446212B CN201910810032.0A CN201910810032A CN112446212B CN 112446212 B CN112446212 B CN 112446212B CN 201910810032 A CN201910810032 A CN 201910810032A CN 112446212 B CN112446212 B CN 112446212B
- Authority
- CN
- China
- Prior art keywords
- information
- price
- user
- dimension
- price reduction
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides an article generation method, an article generation device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: determining identification information of the price reduction commodity; acquiring user evaluation information of at least one user of the price reduction commodity corresponding to the identification information, and acquiring price reduction information of the price reduction commodity corresponding to the identification information; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an article generating method, an article generating device, electronic equipment and a storage medium.
Background
With the development of artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) technology, machine authoring technology is gradually applied. The machine is used for replacing manpower, the article with the structural characteristic is authored, the writing efficiency can be greatly improved, the labor cost is saved, and a large number of articles are produced at the first time.
In the field of vertical media of automobiles, the price reduction articles have strong timeliness, but the current price reduction articles mainly rely on manual writing, and the writing efficiency is lower; in addition, the existing price reduction article only contains price reduction information, the information quantity is small, the intention is that a vehicle purchasing user can only acquire the single information of price through the article, and other information is additionally acquired through other channels to make a decision, so that the existing price reduction article cannot well generate a guiding effect and cannot meet the demands of users.
Disclosure of Invention
The application provides an article generating method, an article generating device, electronic equipment and a computer readable storage medium, which can solve the problems that the writing efficiency of manually writing a price reduction type article is low and the information content of the price reduction article is small.
The specific technical scheme provided by the embodiment of the application is as follows:
In a first aspect, an embodiment of the present application provides an article generating method, including:
determining identification information of the price reduction commodity;
acquiring user evaluation information of at least one user of the price reduction commodity corresponding to the identification information, and acquiring price reduction information of the price reduction commodity corresponding to the identification information;
Determining title information of the article according to the price reduction information;
generating user evaluation text content of the article based on the user evaluation information;
generating reduced price text content of the article based on the reduced price information;
and obtaining the article based on the title information, the user evaluation text content and the price reduction text content.
In one possible implementation, generating user rating text content of an article based on user rating information includes:
Classifying the user evaluation information of each user according to each dimension corresponding to the price reduction commodity to obtain the evaluation information of each dimension corresponding to each user;
generating user rating text content of each dimension of the article based on the rating information of each dimension, the user rating text content of each dimension including rating information of respective users corresponding to the dimension;
When the commodity is an automobile, the dimensions include at least one of:
Appearance, interior, power performance, fuel consumption, comfort, handling, interior space size, and reasons for selection.
In one possible implementation, after obtaining the rating information corresponding to each dimension of each user, the method further includes:
Filtering each piece of evaluation information of each dimension according to at least one of a scoring result of each piece of evaluation information of each dimension, information timeliness of user evaluation information corresponding to each piece of evaluation information and information quality of user evaluation information corresponding to each piece of evaluation information, so as to obtain filtered evaluation information of each dimension;
wherein the scoring result is determined by:
Determining a scoring result corresponding to each piece of evaluation information of each dimension by using an emotion classification model;
the information quality of the user evaluation information corresponding to each evaluation information is determined by:
acquiring length information and characteristic identifiers of user evaluation information corresponding to each piece of evaluation information;
determining the information quality of the user evaluation information based on the length information and the feature identification;
Generating user rating text content for each dimension of the article based on the rating information for each dimension, comprising:
user rating text content for each dimension of the article is generated based on the filtered rating information for each dimension.
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
Generating user rating text content for each dimension of the article based on the rating information for each dimension, comprising:
Acquiring associated picture information of at least one dimension corresponding to vehicle type information;
and generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension and the associated picture information corresponding to the dimension.
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
Generating reduced price text content of the article based on the reduced price information, comprising:
determining at least one target city and at least one piece of car money information corresponding to the car type information in each target city;
Acquiring at least two pieces of historical price information corresponding to any one piece of vehicle information of each target city in a preset time range;
and generating a historical price trend chart of each target city according to the time sequence by using any vehicle money information, at least two historical price information and time information corresponding to each historical price information of each target city, wherein the reduced price text content comprises the historical price trend chart corresponding to each target city. In one possible implementation, the price reduction information includes at least one of coupon information, price reduction activity information, historical price information;
generating reduced price text content of the article based on the reduced price information, further comprising:
generating a preferential information table corresponding to the vehicle type information based on the preferential information;
Generating price reduction activity description information corresponding to the vehicle type information based on the price reduction activity information;
generating price trend interpretation information corresponding to any vehicle money information based on the historical price information;
the price reduction text content comprises at least one of a coupon information table, price reduction activity description information and price trend interpretation information.
In one possible implementation manner, after obtaining the user evaluation information of at least one user of the reduced price commodity corresponding to the identification information, the method further includes:
Determining user evaluation information of at least one user corresponding to each piece of car money information;
and calculating the average fuel consumption corresponding to each piece of car money information according to the fuel consumption in at least one piece of user evaluation information corresponding to each piece of car money information.
In one possible implementation, the method further includes: acquiring historical click data of a user;
determining title information of the article according to the price reduction information, including:
title information is determined based on at least one of historical click data and average fuel consumption, and the price reduction information.
In a second aspect, there is provided an article generating apparatus comprising:
The first determining module is used for determining the identification information of the price reduction commodity;
the acquisition module is used for acquiring user evaluation information of at least one user of the price reduction commodity corresponding to the identification information and acquiring price reduction information of the price reduction commodity corresponding to the identification information;
The second determining module is used for determining the title information of the article according to the price reduction information;
the first generation module is used for generating user evaluation text content of the article based on the user evaluation information;
the second generation module is used for generating the price reduction text content of the article based on the price reduction information;
and the third generation module is used for obtaining the article based on the title information, the user evaluation text content and the price reduction text content.
In a third aspect, an electronic device is provided, the electronic device comprising:
one or more processors;
A memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: the article generating method according to the first aspect or any of the possible implementation manners of the first aspect is performed.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the article generating method of the first aspect or any of the possible implementations of the first aspect of the application.
The technical scheme provided by the application has the beneficial effects that:
the application provides an article generating method, an article generating device, electronic equipment and a storage medium, wherein identification information of a price reduction commodity is firstly determined; then, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a flowchart of an article generating method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a processing procedure of automobile price reduction information sent by different dealers according to an embodiment of the present application;
FIG. 3 is a flowchart of filtering and processing automobile price reduction information according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an article generating template according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a user evaluation text content template provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a reduced-price text content template provided by an embodiment of the present application;
Fig. 7 is a schematic structural diagram of an article generating device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device for generating an article according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The implementation main body of the technical scheme of the application is a server, including but not limited to a single network server, a server group formed by a plurality of network servers or a Cloud formed by a large number of computers or network servers related to Cloud Computing (Cloud Computing), wherein the Cloud Computing is one of distributed Computing, and is a super virtual computer formed by a group of loosely coupled computer sets. Wherein the network includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
The embodiment of the application provides an article generating method, as shown in fig. 1, comprising the following steps:
Step S101, determining identification information of the price reduction commodity;
Wherein the reduced price commodity may include a commodity having a price higher at a start time point than at an end time point within a preset time range. The identification information of the reduced price commodity refers to information capable of distinguishing one type of commodity from other types of commodity, and specifically may include brand information, model information and the like of the reduced price commodity, and the purpose of determining the identification information of the reduced price commodity is to determine that an article corresponding to the identification information is to be generated.
When the reduced price commodity is an automobile, the identification information of the reduced price commodity may be model information of the automobile, for example, audi A6.
Step S102, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained;
Specifically, user evaluation information corresponding to the reduced price commodity is obtained, wherein the user evaluation information comprises the evaluation of the reduced price commodity corresponding to different identification information by a user, in practical application, some user evaluation information can be filtered according to preset conditions, and a user evaluation information database is constructed by the filtered user evaluation information. And inquiring user evaluation information of at least one user of the corresponding reduced price commodity from a user evaluation information database according to the identification information, wherein the user evaluation information comprises the user evaluation on each dimension of product quality, performance and the like, and can reflect the experience and feeling of the user using the commodity.
And constructing a price reduction information database according to price reduction information of commodities of different brands and different models provided by the dealer of the commodity. The specific implementation mode is that the price reduction information of different commodities transmitted in real time by a dealer is accessed from a Kafka cluster, whether the price reduction information is effective or not is judged, the effective price reduction information is stored in a price reduction information database, meanwhile, outdated price reduction information in the price reduction information database is cleaned, and the modified price reduction information is updated.
Wherein the card cluster is a distributed, partitionable, replicable messaging system. The message is generalized in units of topic. The program that will publish messages to Kafka topic is called producer, and the program that will subscribe to topics and consume messages is called consumer. Kafka operates in a cluster, which may consist of one or more servers, each service called a broker.products, sending messages to the Kafka cluster via the network, which provides the messages to the consumers.
In an example, when the reduced price commodity is an automobile, the identification information of the reduced price commodity is automobile type information, the same automobile type information corresponds to a plurality of automobile style information with different configurations, for example, the automobile type information is Audi A6, and the automobile style information may include Audi A6L 2019 40TFSI elegant style, audi A6L 2019 45TFSI fashion dynamic style, and the like. Each piece of car money information corresponds to one piece of price reduction information. After the price reduction information of various brands of automobiles is obtained from the Kafka cluster, the information is consumed from the Kafka cluster, the information of the automobile is split, different operations such as adding, updating and deleting are carried out according to the state codes in the information, and finally the processed price reduction information is stored in a price reduction information table in a price reduction information database. Key field definitions of the price reduction information table are shown in the following table:
| dealer information key field | Meaning of field | Dealer information key field | Meaning of field |
| NewsID | Message id | BusinessTax | Commercial tax |
| SerialID | Vehicle model id | TrafficTax | Traffic tax |
| CarID | Vehicle type id | PurchaseTax | Purchase tax |
| Discount | Discount information | StartDateTime | Activity start time |
| FavoriblePrice | Discount amount of | EndDateTime | Time of end of activity |
| CarReferPrice | Guidance price | IsActive | State code |
| VendorID | Distributor id | IsState | State code |
| OilCar | Oil card information | Location | Dealer location information |
Wherein each item in the dealer information key field column represents an English meaning of a key field of the price reduction information table, and the field meaning column represents a Chinese meaning of the key field of the price reduction information table.
The processing of the car price reduction information sent by the different dealers is shown in fig. 2. The dealer stores the automobile price reduction information into the kafka cluster, the consumer reads the automobile price reduction information from the kafka cluster, preprocesses the price reduction information, separates out price reduction information corresponding to different automobile money, and stores the price reduction information into a price reduction information database after filtering processing.
A flowchart of the filtering process for the automobile price reduction information is shown in fig. 3. First, dealer information, which is the price reduction information of the price reduction commodity that the dealer has transmitted through the kafka cluster, is received. The price reduction information is stored according to the requirements of each field in the price reduction information table. Operations of adding, updating, deleting data are determined according to the values of the status code field IsActive and IsState in the price reduction information table. Whether the value IsActive is equal to 1 is judged to determine whether corresponding price reduction commodity data is enabled or not, if yes, whether the price reduction commodity data is in a price reduction information database is further judged, if yes, the data in the database is updated by the data, and if not, the price reduction commodity data is stored in the price reduction information database; if IsActive is not equal to 1, further judging whether IsActive is equal to 2, if IsActive is equal to 2, judging whether IsState is equal to 3, if 3, judging that the piece of data is data which is not approved, and performing reject processing on the data; if IsActive is not equal to 2, it is determined IsActive if the value is equal to 0, if 0, the data is deleted because the dealer activity time has ended or the offer has been cancelled in the reduced price information. If IsActive is a value that is not equal to 0, 1,2, then the status code is considered to be abnormal.
And inquiring the price reduction information of the price reduction commodity corresponding to the identification information in a price reduction information database, wherein the price reduction information comprises price reduction area information of the price reduction commodity, price information of different times, preferential price information, preferential activity information and other information related to price reduction.
Step S103, determining the title information of the article according to the price reduction information;
at least one keyword corresponding to the price reduction commodity, such as a brand, a model, preferential information and the like of the price reduction commodity, is extracted from the price reduction information, and the keywords are combined to obtain an article title of an article corresponding to the price reduction commodity.
Step S104, generating user evaluation text content of the article based on the user evaluation information;
and generating user evaluation text content of an article corresponding to the reduced price commodity according to at least one piece of user evaluation information of the reduced price commodity corresponding to the identification information and the preset user evaluation template.
Step S105, generating reduced price text content of the article based on the reduced price information;
and generating the price reduction text content of the article corresponding to the price reduction commodity according to the price reduction information corresponding to the identification information and the price reduction information of the price reduction commodity.
And step S106, obtaining the article based on the title information, the user evaluation text content and the reduced price text content.
And generating articles corresponding to the price reduction commodities according to the title information, the user evaluation text content and the price reduction text content according to a preset article generation template, wherein the article generation template can be designed by adopting html5, as shown in fig. 4.
The article generating method provided by the embodiment of the application comprises the steps of firstly determining the identification information of the price reduction commodity; then, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
In one possible implementation, generating user rating text content of an article based on user rating information includes the steps of:
Classifying the user evaluation information of each user according to each dimension corresponding to the price reduction commodity to obtain the evaluation information of each dimension corresponding to each user;
generating user rating text content of each dimension of the article based on the rating information of each dimension, the user rating text content of each dimension including rating information of respective users corresponding to the dimension;
When the commodity is an automobile, the dimensions include at least one of:
Appearance, interior, power performance, fuel consumption, comfort, handling, interior space size, and reasons for selection.
In an example, when the reduced price commodity is an automobile, user evaluation information of each user is classified according to at least one of appearance, interior trim, power performance, oil consumption, comfort, operability, internal space size and selection reason, and user evaluation text content corresponding to at least one of appearance, interior trim, power performance, oil consumption, comfort, operability, internal space size and selection reason of the reduced price automobile is generated based on the evaluation information of each dimension, wherein the user evaluation text content contains evaluation information of each user for each dimension.
The evaluation information of the user is divided into different dimensions to be displayed in the article, so that the display content of the article is clearer, and the readability of the article is enhanced.
For example, the evaluation information of the user a includes evaluation information of two dimensions of the appearance and the interior of the reduced-price automobile, and after classifying the evaluation information of the user a according to the dimensions, two pieces of evaluation information of the user a are obtained: one piece is evaluation information of the appearance by the user a; one piece is the evaluation information of the user a for the interior. The evaluation information of the user B includes evaluation information on the appearance. The user evaluates the text content, and the evaluation information for the appearance includes: evaluation information of the appearance by the user A and evaluation information of the appearance by the user B; the evaluation information for the interior trim includes: evaluation information of the user a on the interior.
In one possible implementation, after obtaining the rating information corresponding to each dimension of each user, the method further includes the steps of:
Filtering each piece of evaluation information of each dimension according to at least one of a scoring result of each piece of evaluation information of each dimension, information timeliness of user evaluation information corresponding to each piece of evaluation information and information quality of user evaluation information corresponding to each piece of evaluation information, so as to obtain filtered evaluation information of each dimension;
wherein the scoring result is determined by:
Determining a scoring result corresponding to each piece of evaluation information of each dimension by using an emotion classification model;
the information quality of the user evaluation information corresponding to each evaluation information is determined by:
acquiring length information and characteristic identifiers of user evaluation information corresponding to each piece of evaluation information;
determining the information quality of the user evaluation information based on the length information and the feature identification;
Generating user rating text content for each dimension of the article based on the rating information for each dimension, comprising:
user rating text content for each dimension of the article is generated based on the filtered rating information for each dimension.
The evaluation information is classified by using a classification model based on Bert, so as to obtain the probability that the user evaluation information belongs to each class, the probability value is used as the evaluation result of each evaluation information, the score of the evaluation information is a number between 0 and 1, a score close to 1 indicates that the comment is positive, and a score close to 0 indicates that the comment is negative.
When the evaluation information is filtered according to the scoring result, the filtering condition may be determined according to the score, for example, comments having a score of less than 0.5 may be filtered out.
The information timeliness of the user evaluation information corresponding to each evaluation information can be determined according to the release time of the user evaluation information and the timeliness of the car money information.
When the user evaluation is filtered according to the timeliness of the information, the set filtering condition may be that the release time is not in a preset time range or the corresponding car information of the comment does not accord with the preset condition (the car is out of date, the car is stopped selling), and the user evaluation information is filtered.
The information quality of the user evaluation information corresponding to each evaluation information can be determined according to the length of the user evaluation information and the feature identifier, wherein the feature identifier can be an identifier which is marked for a part of the user evaluation information in advance and indicates the quality of the evaluation information, for example, after the user evaluation information is obtained, a part of the user evaluation information with higher quality is marked with an essence label and the like.
The purpose of filtering the user evaluation information according to the three aspects is to enable the obtained user evaluation information to be more objective, have higher timeliness and higher quality, so that the user evaluation information displayed in the article has a higher reference value.
Specifically, classifying user evaluation information by using a Bert-based classification model;
A) Data preparation: the user evaluation information data has two labels of 'most satisfactory' and 'least satisfactory', the user evaluation information under the two labels can clearly show the attitude tendency of a user, the data is used as a training set, the user evaluation information which cannot form complete description is filtered, more than 48000 negative samples and more than 49000 positive samples are finally obtained, the positive-negative sample ratio is close to 1:1, and the data is divided into a training set, a verification set and a test set according to the proportion of 7:1:2;
B) Model training: performing word segmentation on each piece of user evaluation information, characterizing the user evaluation information as a vector by using a pre-trained word vector, training by using a Bert model, selecting super parameters according to the performance of the Bert model on a verification set, and finally evaluating the effect of the classification model on a test set;
c) Model deployment: and deploying a classification model of the user evaluation information on the GPU server by using a flash frame, and determining a grading result of each user evaluation information by using the classification model.
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
generating user rating text content for each dimension of the article based on the rating information for each dimension, comprising the steps of:
Acquiring associated picture information of at least one dimension corresponding to vehicle type information;
and generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension and the associated picture information corresponding to the dimension.
In one example, when the commodity is an automobile, the user evaluation text template is as shown in fig. 5. Inquiring associated picture information of at least one dimension corresponding to the vehicle type information in a vehicle type picture database, enabling the dimension information to correspond to the associated picture information and user evaluation information of a user 1 and a user 2 of the dimension of the vehicle type to generate user evaluation text content of each dimension of the vehicle type, and if some dimensions do not have associated pictures, not displaying the associated pictures.
The associated pictures with at least one dimension are added in the articles of the price reduction commodity, so that a user reading the articles can more intuitively know the price reduction vehicle type, and the user experience is improved.
For example, if the vehicle type information is kala and the dimension is the appearance and the dynamic performance, the user evaluation text content includes: the picture of the appearance of the kalman roller, the evaluation information of the appearance of the kalman roller by the user and the evaluation information of the dynamic performance of the kalman roller by the user (the picture which is not correspondingly related to the dynamic performance dimension is not displayed).
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
generating reduced price text content of the article based on the reduced price information, comprising the steps of:
determining at least one target city and at least one piece of car money information corresponding to the car type information in each target city;
Acquiring at least two pieces of historical price information corresponding to any one piece of vehicle information of each target city in a preset time range;
And generating a historical price trend chart of each target city according to the time sequence by using any vehicle money information, at least two historical price information and time information corresponding to each historical price information of each target city, wherein the reduced price text content comprises the historical price trend chart corresponding to each target city. In an example, when the commodity is an automobile, at least one target city, namely at least one city corresponding to a reduced-price automobile type and which automobile money of the automobile type is reduced in the city, is determined according to reduced-price area information in the reduced-price information, price information of any automobile money of the reduced-price automobile type in a period of time in the past of the target city is obtained, and a historical price trend chart of the automobile money in the target city is generated according to time sequence.
For example, the model of the price-reducing automobile is a land tiger winning, the corresponding price-reducing automobile money is a flourishing edition, the price-reducing city is Beijing and Shanghai, and the sales prices of the land tiger winning flourishing edition in Beijing and Shanghai for each month are respectively obtained, and a Beijing sales price trend chart and a Shanghai sales price trend chart are respectively generated according to the time sequence.
The historical price trend chart of the price reduction commodity is generated, so that a user reading an article can know the historical price of the price reduction car more clearly and intuitively, and the purchasing time is conveniently determined according to the price trend chart.
In one possible implementation, the price reduction information includes at least one of coupon information, price reduction activity information, historical price information;
generating reduced price text content of the article based on the reduced price information, further comprising:
generating a preferential information table corresponding to the vehicle type information based on the preferential information;
Generating price reduction activity description information corresponding to the vehicle type information based on the price reduction activity information;
generating price trend interpretation information corresponding to any vehicle money information based on the historical price information;
the price reduction text content comprises at least one of a coupon information table, price reduction activity description information and price trend interpretation information.
In an example, when the reduced price commodity is an automobile, as shown in fig. 6, according to the preference information in the reduced price information, the method includes: the price reduction car money, manufacturer guiding price, preferential amplitude, preferential price and the like, and a preferential information table corresponding to each price reduction car type is generated. And generating price reduction activity description information corresponding to the vehicle type information according to the price reduction activity information in the price reduction information, for example, which cities have sales promotion activities of the vehicle type, activity price reduction degree and the like. And generating price trend interpretation information corresponding to any vehicle type information, such as the highest price, the lowest price, the average price, the price change trend and the like in a certain time range according to the historical price information in the price reduction information. And generating reduced price text content according to a preset template by using the preferential information table, the reduced price activity description information, the historical price trend graph and the price trend interpretation information.
The coupon information table, the price reduction activity description information, the historical price trend graph and the price trend interpretation information of the price reduction automobile are displayed in the article, so that the content of the article is more abundant, and a user can more comprehensively know the related coupon information of the price reduction automobile, thereby playing a better guiding role for the purchasing user.
In one possible implementation manner, after obtaining the user evaluation information of at least one user of the reduced price commodity corresponding to the identification information, the method further includes:
Determining user evaluation information of at least one user corresponding to each piece of car money information;
and calculating the average fuel consumption corresponding to each piece of car money information according to the fuel consumption in at least one piece of user evaluation information corresponding to each piece of car money information.
In an example, when the reduced price commodity is an automobile, after obtaining the user evaluation information of the reduced price commodity, classifying the user evaluation information according to the automobile money, determining at least one piece of user evaluation information corresponding to each automobile money, extracting oil consumption information in the user evaluation information, and calculating the average oil consumption of the automobile.
The fuel consumption is an important reference index for purchasing the vehicle, and the purpose of calculating the fuel consumption is to add the fuel consumption information of the price reduction vehicle into the article corresponding to the price reduction vehicle, so that a user reading the article can know the fuel consumption information of the price reduction vehicle, and the article of the price reduction vehicle plays a better guiding role on the purchasing decision of the user.
In one possible implementation, the method further includes: acquiring historical click data of a user;
determining title information of the article according to the price reduction information, including:
title information is determined based on at least one of historical click data and average fuel consumption, and the price reduction information.
In an example, historical click data of a user is obtained, click rates of historical click articles of the user are determined according to the historical click data of the user, titles of a plurality of articles with the click rates meeting a preset threshold are analyzed, common features are extracted, at least one keyword is determined according to the common features, at least one keyword is determined according to price reduction information, for example, at least one of a keyword obtained according to the historical click data, average oil consumption and keywords obtained according to the price reduction information are combined, and the titles of the articles are determined.
Based on the same principle as the method shown in fig. 1, there is also provided in an embodiment of the present disclosure an article generating apparatus 70, as shown in fig. 7, the article generating apparatus 70 including: a first determining module 701, an acquiring module 702, a second determining module 703, a first generating module 704, a second generating module 705, and a third generating module 706;
A first determining module 701, configured to determine identification information of a reduced price commodity;
an obtaining module 702, configured to obtain user evaluation information of at least one user of the reduced price commodity corresponding to the identification information, and obtain reduced price information of the reduced price commodity corresponding to the identification information;
a second determining module 703, configured to determine title information of the article according to the price reduction information;
a first generation module 704, configured to generate user evaluation text content of an article based on user evaluation information;
a second generation module 705, configured to generate reduced price text content of an article based on reduced price information;
A third generation module 706 is configured to obtain an article based on the title information, the user rating text content, and the reduced price text content.
In one possible implementation, the first generating module 704 is specifically configured to:
Classifying the user evaluation information of each user according to each dimension corresponding to the price reduction commodity to obtain the evaluation information of each dimension corresponding to each user;
generating user rating text content of each dimension of the article based on the rating information of each dimension, the user rating text content of each dimension including rating information of respective users corresponding to the dimension;
When the commodity is an automobile, the dimensions include at least one of:
Appearance, interior, power performance, fuel consumption, comfort, handling, interior space size, and reasons for selection.
In one possible implementation, the article generating apparatus 70 further includes a filtering module configured to:
determining a scoring result corresponding to each piece of evaluation information of each dimension by using a scoring model;
filtering the evaluation information according to the grading result to obtain filtered evaluation information of each dimension;
the first generating module 704 is specifically configured to: user rating text content for each dimension of the article is generated based on the filtered rating information for each dimension.
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
The first generating module 704 is specifically configured to:
Acquiring associated picture information of at least one dimension corresponding to vehicle type information;
and generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension and the associated picture information corresponding to the dimension.
In one possible implementation manner, when the commodity is an automobile, the identification information is specifically automobile type information;
the second generating module 705 is specifically configured to:
determining at least one target city and at least one piece of car money information corresponding to the car type information in each target city;
Acquiring at least two pieces of historical price information corresponding to any one piece of vehicle information of each target city in a preset time range;
and generating a historical price trend chart of each target city according to the time sequence by using any vehicle money information, at least two historical price information and time information corresponding to each historical price information of each target city, wherein the reduced price text content comprises the historical price trend chart corresponding to each target city.
In one possible implementation, the price reduction information includes at least one of coupon information, price reduction activity information, historical price information;
the second generating module 705 is specifically configured to:
generating a preferential information table corresponding to the vehicle type information based on the preferential information;
Generating price reduction activity description information corresponding to the vehicle type information based on the price reduction activity information;
generating price trend interpretation information corresponding to any vehicle money information based on the historical price information;
the price reduction text content comprises at least one of a coupon information table, price reduction activity description information and price trend interpretation information.
In one possible implementation, the article generating apparatus 70 further includes a third determining module configured to:
Determining user evaluation information of at least one user corresponding to each piece of car money information;
and calculating the average fuel consumption corresponding to each piece of car money information according to the fuel consumption in at least one piece of user evaluation information corresponding to each piece of car money information.
In one possible implementation, the second determining module 703 is further configured to;
Acquiring historical click data of a user;
title information is determined based on at least one of historical click data and average fuel consumption, and the price reduction information.
The article generating device of the embodiment of the present disclosure may perform the method of the article generating device provided by the embodiment of the present disclosure, and the implementation principle is similar, and the actions performed by each module in the article generating device of the embodiment of the present disclosure correspond to the steps in the method of the article generating device of each embodiment of the present disclosure, and for detailed functional descriptions of each module of the article generating device, reference may be specifically made to descriptions in the corresponding method of the article generating device shown in the foregoing, which are not repeated herein.
The article generating device provided by the embodiment of the application firstly determines the identification information of the price reduction commodity; then, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
The above embodiment describes the coordinate determining apparatus from the viewpoint of the virtual module, and the following describes an electronic device from the viewpoint of the physical module, specifically as follows:
An embodiment of the present application provides an electronic device, as shown in fig. 8, an electronic device 8000 shown in fig. 8 includes: a processor 8001, and a memory 8003. Processor 8001 is coupled to memory 8003, such as via bus 8002. Optionally, electronic device 8000 may also include a transceiver 8004. It should be noted that, in practical applications, the transceiver 8004 is not limited to one, and the structure of the electronic device 8000 is not limited to the embodiment of the present application.
The processor 8001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor 8001 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of DSP and microprocessor, etc.
Bus 8002 may include a path to transfer information between the components. Bus 8002 may be a PCI bus or an EISA bus, etc. Bus 8002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.
Memory 8003 may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 8003 is used to store application code for executing the inventive arrangements and is controlled for execution by the processor 8001. Processor 8001 is used to execute application code stored in memory 8003 to implement what is shown in any of the method embodiments described above.
The embodiment of the application provides an electronic device, which comprises: a memory and a processor; at least one program stored in the memory for execution by the processor, as compared to the prior art: the electronic equipment provided by the embodiment of the application firstly determines the identification information of the price reduction commodity; then, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
Embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which when run on a computer, causes the computer to perform the corresponding method embodiments described above. Compared with the prior art, the article generation method provided by the embodiment of the application comprises the steps of firstly determining the identification information of the price reduction commodity; then, user evaluation information of at least one user of the price reduction commodity corresponding to the identification information is obtained, and price reduction information of the price reduction commodity corresponding to the identification information is obtained; determining title information of the article according to the price reduction information; generating user evaluation text content of the article based on the user evaluation information; generating reduced price text content of the article based on the reduced price information; and obtaining the article based on the title information, the user evaluation text content and the price reduction text content. According to the method, the article corresponding to the price reduction commodity is generated through the machine, so that the article generation efficiency is improved; in addition, the generated article contains the user evaluation information of the price reduction commodity, so that the related information of the price reduction commodity obtained by the user is more comprehensive, and the guiding function on the user decision can be better realized.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A method of generating an article, the method comprising:
determining identification information of the price reduction commodity;
Acquiring user evaluation information of at least one user of the price reduction commodity corresponding to the identification information, and acquiring price reduction information of the price reduction commodity corresponding to the identification information;
Determining the title information of the article according to the price reduction information;
Classifying the user evaluation information of each user according to each dimension corresponding to the price reduction commodity to obtain the evaluation information of each dimension corresponding to each user;
generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension, wherein the user evaluation text content of each dimension comprises evaluation information of each user corresponding to the dimension;
when the commodity is an automobile, the dimension includes at least one of:
appearance, interior, power performance, fuel consumption, comfort, handling, interior space size, and reasons for selection;
Generating reduced text content of the article based on the reduced information;
And obtaining the article based on the title information, the user evaluation text content and the price reduction text content.
2. The method according to claim 1, wherein after obtaining the rating information for each dimension of each user, the method further comprises:
Filtering each piece of evaluation information of each dimension according to at least one of a scoring result of each piece of evaluation information of each dimension, information timeliness of user evaluation information corresponding to each piece of evaluation information and information quality of user evaluation information corresponding to each piece of evaluation information, so as to obtain filtered evaluation information of each dimension;
Wherein the scoring result is determined by:
Determining a scoring result corresponding to each piece of scoring information of each dimension by using an emotion classification model;
The information quality of the user evaluation information corresponding to each of the evaluation information is determined by:
Acquiring length information and characteristic identifiers of user evaluation information corresponding to each piece of evaluation information;
determining information quality of the user evaluation information based on the length information and the feature identification;
the generating the user evaluation text content of each dimension of the article based on the evaluation information of each dimension comprises the following steps:
And generating user evaluation text content of each dimension of the article based on the filtered evaluation information of each dimension.
3. The method according to claim 1, wherein when the commodity is an automobile, the identification information is specifically automobile type information;
the generating the user evaluation text content of each dimension of the article based on the evaluation information of each dimension comprises the following steps:
acquiring associated picture information of at least one dimension corresponding to the vehicle type information;
and generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension and the associated picture information corresponding to the dimension.
4. The method according to claim 1, wherein when the commodity is an automobile, the identification information is specifically automobile type information;
the generating the reduced price text content of the article based on the reduced price information comprises the following steps:
Determining at least one target city and at least one corresponding vehicle type information of the vehicle type information in each target city;
acquiring at least two pieces of historical price information corresponding to any vehicle type information of each target city in a preset time range;
and generating the historical price trend graph of each target city according to time sequence by using the vehicle type information, at least two pieces of historical price information and the time information corresponding to each piece of historical price information of each target city, wherein the reduced price text content comprises the historical price trend graph corresponding to each target city.
5. The method of claim 4, wherein the price reduction information comprises at least one of coupon information, price reduction activity information, historical price information;
the generating the reduced price text content of the article based on the reduced price information further comprises:
Generating a preferential information table corresponding to the vehicle type information based on the preferential information;
generating price reduction activity description information corresponding to the vehicle type information based on the price reduction activity information;
generating price trend interpretation information corresponding to any vehicle type information based on the historical price information;
The price reduction text content comprises at least one of the coupon information table, price reduction activity description information and price trend interpretation information.
6. The method according to claim 3, wherein after acquiring the user evaluation information of at least one user of the reduced price commodity corresponding to the identification information, the method further comprises:
Determining user evaluation information of at least one user corresponding to each vehicle type information;
And calculating the average fuel consumption corresponding to each vehicle type information according to the fuel consumption in at least one piece of user evaluation information corresponding to each vehicle type information.
7. The method of claim 6, wherein the method further comprises: acquiring historical click data of a user;
Determining title information of the article according to the price reduction information, wherein the title information comprises the following steps:
the title information is determined based on the price reduction information and at least one of the historical click data and the average fuel consumption.
8. An article generating apparatus, the apparatus comprising:
The first determining module is used for determining the identification information of the price reduction commodity;
the acquisition module is used for acquiring user evaluation information of at least one user of the price reduction commodity corresponding to the identification information and acquiring price reduction information of the price reduction commodity corresponding to the identification information;
The second determining module is used for determining the title information of the article according to the price reduction information;
The first generation module is used for classifying the user evaluation information of each user according to the dimensions corresponding to the price reduction commodity to obtain the evaluation information of each dimension corresponding to each user; generating user evaluation text content of each dimension of the article based on the evaluation information of each dimension, wherein the user evaluation text content of each dimension comprises evaluation information of each user corresponding to the dimension; when the commodity is an automobile, the dimension includes at least one of: appearance, interior, power performance, fuel consumption, comfort, handling, interior space size, and reasons for selection;
The second generation module is used for generating the reduced text content of the article based on the reduced information;
And the third generation module is used for obtaining the article based on the title information, the user evaluation text content and the price reduction text content.
9. An electronic device, comprising:
one or more processors;
A memory;
One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: the article generating method according to any one of claims 1 to 7 is performed.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the article generating method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910810032.0A CN112446212B (en) | 2019-08-29 | 2019-08-29 | Article generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910810032.0A CN112446212B (en) | 2019-08-29 | 2019-08-29 | Article generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446212A CN112446212A (en) | 2021-03-05 |
| CN112446212B true CN112446212B (en) | 2024-05-28 |
Family
ID=74741723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910810032.0A Active CN112446212B (en) | 2019-08-29 | 2019-08-29 | Article generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446212B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6976031B1 (en) * | 1999-12-06 | 2005-12-13 | Sportspilot, Inc. | System and method for automatically generating a narrative report of an event, such as a sporting event |
| KR20090035801A (en) * | 2007-10-08 | 2009-04-13 | 최낙상 | Digital newspaper article production and its provision method |
| CN103020170A (en) * | 2012-11-27 | 2013-04-03 | 江苏乐买到网络科技有限公司 | WEB inforamtion extraction method |
| CN107145482A (en) * | 2017-03-28 | 2017-09-08 | 百度在线网络技术（北京）有限公司 | Article generation method and device, equipment and computer-readable recording medium based on artificial intelligence |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| WO2018209254A1 (en) * | 2017-05-11 | 2018-11-15 | Hubspot, Inc. | Methods and systems for automated generation of personalized messages |
| CN108932220A (en) * | 2018-06-29 | 2018-12-04 | 北京百度网讯科技有限公司 | article generation method and device |
| CN109582945A (en) * | 2018-12-17 | 2019-04-05 | 北京百度网讯科技有限公司 | Article generation method, device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9881059B2 (en) * | 2014-08-08 | 2018-01-30 | Yahoo Holdings, Inc. | Systems and methods for suggesting headlines |
-
2019
- 2019-08-29 CN CN201910810032.0A patent/CN112446212B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6976031B1 (en) * | 1999-12-06 | 2005-12-13 | Sportspilot, Inc. | System and method for automatically generating a narrative report of an event, such as a sporting event |
| KR20090035801A (en) * | 2007-10-08 | 2009-04-13 | 최낙상 | Digital newspaper article production and its provision method |
| CN103020170A (en) * | 2012-11-27 | 2013-04-03 | 江苏乐买到网络科技有限公司 | WEB inforamtion extraction method |
| CN107145482A (en) * | 2017-03-28 | 2017-09-08 | 百度在线网络技术（北京）有限公司 | Article generation method and device, equipment and computer-readable recording medium based on artificial intelligence |
| WO2018209254A1 (en) * | 2017-05-11 | 2018-11-15 | Hubspot, Inc. | Methods and systems for automated generation of personalized messages |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
| CN108563620A (en) * | 2018-04-13 | 2018-09-21 | 上海财梵泰传媒科技有限公司 | The automatic writing method of text and system |
| CN108932220A (en) * | 2018-06-29 | 2018-12-04 | 北京百度网讯科技有限公司 | article generation method and device |
| CN109582945A (en) * | 2018-12-17 | 2019-04-05 | 北京百度网讯科技有限公司 | Article generation method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446212A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sudirjo et al. | The Application of Extended Expectation-Confirmation Model to Identify Influencing Factors Digital Loyalty for Mobile-Based Travel Platform | |
| CN111967970B (en) | Bank product recommendation method and device based on spark platform | |
| CN106570718B (en) | Information delivery method and delivery system | |
| US20180374141A1 (en) | Information pushing method and system | |
| CN112559903B (en) | Community member searching method, system, device and medium | |
| CN111352962A (en) | Client portrait construction method and device | |
| EP2812856A1 (en) | Tools and methods for determining relationship values | |
| CN108805598A (en) | Similarity information determines method, server and computer readable storage medium | |
| CN108305181B (en) | Social influence determination, information delivery method and device, equipment and storage medium | |
| CN113204714B (en) | A task recommendation method, device, storage medium and terminal based on user portrait | |
| CN107016006B (en) | Page display method and system | |
| CN106202393A (en) | Media information method for pushing and device | |
| CN111597355A (en) | Information processing method and device | |
| CN111192111A (en) | Product sales data analysis method and terminal equipment | |
| CN110782232A (en) | Business process visual configuration method and device, electronic equipment and storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| CN115689651A (en) | Marketing information intelligent layout method and system | |
| CN114971664B (en) | Advertisement putting method and related equipment | |
| CN112446212B (en) | Article generation method and device, electronic equipment and storage medium | |
| CN118606673A (en) | A method, device, equipment and vehicle for extracting vehicle scene perception data | |
| CN118133797A (en) | Concept verification method, device, equipment and medium based on pre-training language model | |
| CN117196723A (en) | Advertisement space matching method, system, medium and equipment | |
| CN110929123A (en) | E-commerce product competition analysis method and system | |
| CN116747523A (en) | Bank game generation method, apparatus, computer device and storage medium | |
| CN116523069A (en) | Coupon pushing method and device based on federal modeling |
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 |