CN111654714A - Information processing method, device, electronic equipment and storage medium - Google Patents

Information processing method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111654714A
CN111654714A CN202010450387.6A CN202010450387A CN111654714A CN 111654714 A CN111654714 A CN 111654714A CN 202010450387 A CN202010450387 A CN 202010450387A CN 111654714 A CN111654714 A CN 111654714A
Authority
CN
China
Prior art keywords
transaction
trading
factor
search
transaction object
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.)
Granted
Application number
CN202010450387.6A
Other languages
Chinese (zh)
Other versions
CN111654714B (en
Inventor
陈春勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202010450387.6A priority Critical patent/CN111654714B/en
Publication of CN111654714A publication Critical patent/CN111654714A/en
Application granted granted Critical
Publication of CN111654714B publication Critical patent/CN111654714B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/254—Management at additional data server, e.g. shopping server, rights management server
    • H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/47815—Electronic shopping

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Databases & Information Systems (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application discloses an information processing method, an information processing device, electronic equipment and a storage medium; the method and the device for searching the transaction objects can obtain the search content, then obtain the information of the transaction objects from the transaction platforms respectively based on the search content, the information of the transaction objects comprises the transaction objects matched with the search content in each transaction platform and the multi-dimensional characteristic information corresponding to the transaction objects, then calculate the relevancy factors of the transaction objects, calculate the importance factors of the transaction objects according to the multi-dimensional characteristic information corresponding to the transaction objects, then fuse the relevancy factors and the importance factors of the transaction objects to obtain the ranking parameters of the transaction objects for uniform ranking, then rank the transaction objects according to the ranking parameters of the transaction objects in the transaction object platforms to obtain a ranked transaction object set, and output the ranked transaction object set. The scheme can effectively improve the efficiency of selecting the transaction object.

Description

Information processing method, device, electronic equipment and storage medium
Technical Field
The present application relates to the field of communications technologies, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.
Background
With the rapid development of the internet, live e-commerce is carried forward. Live E-commerce refers to the online promotion of customers and sellers of the entity family through a live platform or live software of the network to the customers of the broad products, so that the customers can purchase the commodities while knowing the performances of the products. The live E-commerce system is a system for helping platform merchants to realize online live selling in a live broadcast mode after each E-commerce opens a live broadcast function.
Live broadcast of E-commerce absorbs and continues the advantages of the Internet, so that more and more anchor broadcasters start live broadcast of goods on live broadcast platforms. The skill of the anchor selection product is related to the conversion rate of the commodity, but most of the current anchor selection products are selected based on manual intuition and historical experience, and the sales data of different platforms do not have comprehensive measurement dimensionality. The anchor needs to spend a lot of time on the selection of commodity before live broadcast, and is time-consuming and labor-consuming.
Disclosure of Invention
The embodiment of the application provides an information processing method, an information processing device, electronic equipment and a storage medium, and the efficiency of transaction object selection can be effectively improved.
An embodiment of the present application provides an information processing method, including:
acquiring search content;
acquiring trading object information from a plurality of trading platforms respectively based on the search content, wherein the trading object information comprises a trading object matched with the search content in each trading platform and multi-dimensional feature information corresponding to the trading object;
calculating a relevancy factor of the trading object, and calculating an importance factor of the trading object according to multi-dimensional feature information corresponding to the trading object, wherein the relevancy factor represents the relevancy between the search content and the trading object, and the importance factor represents the importance of the trading object;
fusing the relevancy factor and the importance factor of the transaction objects to obtain a ranking parameter for uniformly ranking each transaction object;
sequencing the transaction objects according to sequencing parameters of the transaction objects in a plurality of transaction object platforms to obtain a sequenced transaction object set;
and outputting the ordered transaction object set.
Correspondingly, an embodiment of the present application further provides an information processing apparatus, including:
a first acquisition unit configured to acquire search content;
the second acquisition unit is used for respectively acquiring transaction object information from a plurality of transaction platforms based on the search content, wherein the transaction object information comprises transaction objects matched with the search content in each transaction platform and multi-dimensional feature information corresponding to the transaction objects;
the calculating unit is used for calculating a relevancy factor of the trading object and calculating an importance factor of the trading object according to multi-dimensional characteristic information corresponding to the trading object, wherein the relevancy factor represents the relevancy between the search content and the trading object, and the importance factor represents the importance of the trading object;
the fusion unit is used for fusing the relevancy factor and the importance factor of the transaction objects to obtain a sequencing parameter for uniformly sequencing each transaction object;
the sorting unit is used for sorting the transaction objects according to sorting parameters of the transaction objects in the transaction object platforms to obtain a sorted transaction object set;
and the output unit is used for outputting the ordered trading object set.
Optionally, in some embodiments, the computing unit may include a first computing subunit and a second computing subunit, as follows:
the first calculating subunit is used for dividing the search content into at least one search keyword and setting the weight of the search keyword; calculating the correlation between the search content and the transaction object according to the search keyword and the weight of the search keyword to obtain a correlation factor of the transaction object;
the second calculation subunit is configured to obtain an importance preset rule in the trading platform corresponding to each trading object; and calculating the importance factor of the transaction object according to the importance preset rule and the multi-dimensional characteristic information corresponding to each transaction object.
Optionally, in some embodiments, the first calculating subunit may be specifically configured to calculate a relevance between each search keyword and the search content, so as to obtain a first score of the search keyword; calculating the relevancy factor of each search keyword and the transaction object to obtain a second score of the search keyword; and calculating the correlation between the search content and the transaction object according to the weight of the search keyword, the first score of the search keyword and the second score of the search keyword to obtain a correlation factor of the transaction object.
Optionally, in some embodiments, the second calculating subunit may be specifically configured to determine, according to the preset importance rule, a weight of each dimension feature object information of the transaction object; and calculating the importance factor of the trading object according to the weight of each dimension characteristic object information of the trading object and the multi-dimension characteristic information.
Optionally, in some embodiments, the fusion unit may include a fusion subunit and a processing subunit, as follows:
the fusion subunit is configured to fuse the relevancy factor and the importance factor of the transaction object to obtain a comprehensive factor of the transaction object;
and the processing subunit is used for carrying out standardization processing on the comprehensive factors of the transaction objects by utilizing the sequencing learning model to obtain sequencing parameters of each transaction object for unified sequencing.
Optionally, in some embodiments, the processing subunit is specifically configured to perform feature extraction on the comprehensive factor of the transaction object by using a ranking learning model to obtain comprehensive feature information of the transaction object; and calculating the ranking score of the transaction objects according to the comprehensive characteristic information to obtain ranking parameters of each transaction object for uniform ranking.
Optionally, in some embodiments, the information processing apparatus may further include a training unit, as follows:
the training unit is used for acquiring a plurality of groups of sample data; and training a preset sequencing learning model by using the sample data to obtain a sequencing learning model.
Optionally, in some embodiments, the sorting unit may include a combination subunit and a sorting subunit, as follows:
the combination subunit is used for combining the ranking parameters of the trading objects in the trading object platforms to obtain a combined ranking parameter sequence;
and the sorting subunit is used for sorting the combined sorting parameter sequence by using a heap sorting algorithm to obtain a sorted transaction object set.
Optionally, in some embodiments, the sorting subunit may be specifically configured to obtain a maximum value of the sorting parameters in the combined sorting parameter sequence; exchanging the maximum value of the sorting parameter with the tail sorting parameter in the combined sorting parameter sequence to obtain an exchanged tail sorting parameter; obtaining the maximum value of the non-exchanged sorting parameters in the combined sorting parameter sequence; and exchanging the maximum value of the unaltered sorting parameter with the tail sorting parameter in the unaltered sorting parameters in the combined sorting parameter sequence until all the sorting parameters in the combined sorting parameter sequence are exchanged, so as to obtain a sorted transaction object set.
Optionally, in some embodiments, the second obtaining unit may be specifically configured to obtain interface information of a plurality of trading platforms; and acquiring trading object information matched with the search content from the plurality of trading platforms based on the interface information.
Optionally, in some embodiments, the first obtaining unit may be specifically configured to display a search page of a live client, where the search page includes a search input control; determining input search content based on an input operation for the search input control;
the output unit may be specifically configured to display the sorted transaction object set in the search page.
In addition, a computer-readable storage medium is provided, where the computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to perform steps in any one of the information processing methods provided in the embodiments of the present application.
In addition, an electronic device is further provided in an embodiment of the present application, and includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps in any one of the information processing methods provided in the embodiment of the present application.
The embodiment may obtain search content, then obtain trading object information from a plurality of trading platforms respectively based on the search content, where the trading object information includes a trading object matched with the search content in each trading platform and multidimensional feature information corresponding to the trading object, then calculate a relevancy factor of the trading object, and calculate an importance factor of the trading object according to the multidimensional feature information corresponding to the trading object, where the relevancy factor represents a relevancy between the search content and the trading object, the importance factor represents an importance of the trading object, then fuse the relevancy factor and the importance factor of the trading object to obtain a ranking parameter for uniform ranking of each trading object, and then rank the trading objects according to the ranking parameters of the trading objects in the plurality of trading object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set. The scheme can effectively improve the efficiency of selecting the transaction object.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1a is a schematic view of a scene of information processing provided by an embodiment of the present application;
FIG. 1b is a first flowchart of an information processing method provided by an embodiment of the present application;
FIG. 2a is a second flowchart of an information processing method provided by an embodiment of the present application;
fig. 2b is a schematic view of a table-in-showcase page provided in the embodiment of the present application;
FIG. 2c is a schematic diagram of a search page provided by an embodiment of the present application;
FIG. 2d is a schematic illustration of a popularity value presentation page provided by an embodiment of the present application;
FIG. 2e is a schematic diagram of a merchandise data page provided in the embodiment of the present application;
FIG. 2f is a schematic view of a management page provided by an embodiment of the present application;
FIG. 2g is a schematic diagram of an information processing flow provided by an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The principles of the present application are illustrated as being implemented in a suitable computing environment. In the description that follows, specific embodiments of the present application will be described with reference to steps and symbols executed by one or more computers, unless otherwise indicated. Accordingly, these steps and operations will be referred to, several times, as being performed by a computer, the computer performing operations involving a processing unit of the computer in electronic signals representing data in a structured form. This operation transforms the data or maintains it at locations in the computer's memory system, which may be reconfigured or otherwise altered in a manner well known to those skilled in the art. The data maintains a data structure that is a physical location of the memory that has particular characteristics defined by the data format. However, while the principles of the application have been described in language specific to above, it is not intended to be limited to the specific form set forth herein, and it will be recognized by those of ordinary skill in the art that various of the steps and operations described below may be implemented in hardware.
The term "unit" as used herein may be considered a software object executing on the computing system. The various components, units, engines, and services described herein may be viewed as implementation objects on the computing system. The apparatus and method described herein may be implemented in software, or may be implemented in hardware, and are within the scope of the present application.
The terms "first", "second", and "third", etc. in this application are used to distinguish between different objects and not to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but rather, some embodiments may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The embodiment of the application provides an information processing method, an information processing device, electronic equipment and a storage medium. The information processing apparatus may be integrated into an electronic device, and the electronic device may be a server or a terminal.
For example, as shown in fig. 1a, first, the terminal integrated with the information processing apparatus may obtain search content input by a user when the user performs a live selection, then obtain transaction object information from a plurality of transaction platforms respectively based on the search content, where the transaction object information includes a transaction object matched with the search content in each transaction platform and multidimensional feature information corresponding to the transaction object, then calculate a relevance factor of the transaction object, and calculate an importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object, where the relevance factor represents a relevance between the search content and the transaction object, the importance factor represents an importance of the transaction object, and then fuse the relevance factor and the importance factor of the transaction object to obtain a ranking parameter for uniform ranking of each transaction object, and then, sequencing the transaction objects according to the sequencing parameters of the transaction objects in the plurality of transaction object platforms to obtain a sequenced transaction object set, and outputting the sequenced transaction object set.
According to the scheme, when the anchor needs to conduct live broadcast selection, the search content can be obtained, the trading object information in the trading platforms corresponding to the search content is further obtained, the trading object information is processed in a unified mode and then is sequenced, a sequenced trading object set is obtained, the sequenced trading object set integrates the multi-dimensional characteristic information of the trading objects, the sequencing of the trading objects with the highest conversion rate is provided for the anchor, the boundary between the platforms is broken, the anchor is helped to improve the efficiency and quality of selection, the cost of anchor selection is reduced, and the conversion rate of the carried goods is improved.
The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.
The embodiment will be described from the perspective of an information processing apparatus, which may be specifically integrated in an electronic device, where the electronic device may be a server or a terminal; the terminal may include a mobile phone, a tablet Computer, a notebook Computer, a Personal Computer (PC), and other devices.
An information processing method comprising: acquiring search content, acquiring trading object information from a plurality of trading platforms respectively based on the search content, wherein the trading object information comprises a trading object matched with the search content in each trading platform and multidimensional characteristic information corresponding to the trading object, calculating a relevancy factor of the trading object, and calculating an importance factor of the trading object according to the multidimensional characteristic information corresponding to the trading object, wherein the relevancy factor represents the relevancy between the search content and the trading object, the importance factor represents the importance of the trading object, then fusing the relevancy factor and the importance factor of the trading object to obtain a ranking parameter for uniformly ranking each trading object, and then ranking the trading objects according to the ranking parameters of the trading objects in the trading object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set.
As shown in fig. 1b, the specific flow of the information processing method may be as follows:
101. search content is acquired.
For example, a search page of a live client may be displayed, the search page including a search input control, the input search content being determined based on an input operation for the search input control. The representation form of the control can be in the form of an icon, an input box, a button and the like.
For example, a live show window middle station page of a live client can be displayed specifically, before the anchor starts live goods delivery of the e-commerce, an account can be logged in first, one of multiple login modes can be selected for logging in, and then a search page of the live client is displayed to select the needed goods delivery. And when the input operation of the user for the search input control is detected, determining the input search content.
The middle station corresponds to the foreground and the background, and refers to a set of shared middleware in some systems, which is commonly found in website architectures, financial systems, and the like. The middle platform is a platform which is mainly born as a foreground, and the only purpose of the middle platform is to better serve the foreground for large-scale innovation and further better serve users, so that the enterprise really realizes the continuous butt joint of the self ability and the user requirements.
102. Transaction object information is acquired from the plurality of transaction platforms based on the search content, respectively.
The trading object information comprises trading objects matched with the search content in each trading platform and multi-dimensional feature information corresponding to the trading objects. For example, the transaction object information matching the search content may be acquired from a plurality of different transaction platforms, such as platform X, platform Y, platform Z, etc., respectively, according to the search content input by the user.
The trading platform is a platform for providing services for trading parties of a trading object. For example, the transaction platform may be a third-party e-commerce platform, which is independent of the provider and the demander of the product or service, and provides services for both the buyer and the seller through the network service platform according to specific transaction and service specifications, and the service content may include, but is not limited to, "supply and demand information publishing and searching, transaction establishment, payment, logistics". The transaction object refers to an article, such as a commodity, equipment, a prop, and the like, traded by both parties on the trading platform.
For example, when the anchor needs to perform live selection, for example, the transaction object may be a commodity, and interface information of a plurality of transaction platforms may be acquired to perform configuration access according to the interface information, so as to acquire transaction object information in the transaction platforms. For example, interface information of a plurality of trading platforms may be specifically acquired, and trading object information matching the search content may be acquired from the plurality of trading platforms based on the interface information. At this time, the trading platform may be a platform that provides services for both the buyer and the seller of the goods.
103. And calculating the relevancy factor of the trading object, and calculating the importance factor of the trading object according to the multi-dimensional characteristic information corresponding to the trading object.
Wherein, the relevancy factor characterizes the relevancy between the search content and the transaction object, and the importance factor characterizes the importance of the transaction object.
There are many ways to calculate the relevancy factor of the transaction object, for example, the relevancy ranking Model, such as Boolean Model (Boolean Model), Vector Space Model (Vector Space Model), Latent Semantic Analysis (Latent Semantic Analysis), BM25 (an algorithm for evaluating the relevancy between search terms and documents), information retrieval Language Model (LMIR) and so on, may be used for calculation.
For example, the search content may be divided into at least one search keyword, the weight of the search keyword is set, and the correlation between the search content and the transaction object is calculated according to the search keyword and the weight of the search keyword, so as to obtain the correlation factor of the transaction object.
For example, in some embodiments, the correlation between the search content and the transaction object is calculated according to the search keyword and the weight of the search keyword to obtain the correlation factor of the transaction object, and specifically, the correlation between each search keyword and the search content may be calculated to obtain a first score of the search keyword, the correlation factor between each search keyword and the transaction object is calculated to obtain a second score of the search keyword, and the correlation between the search content and the transaction object is calculated according to the weight of the search keyword, the first score of the search keyword, and the second score of the search keyword to obtain the correlation factor of the transaction object.
For example, when the transaction object is a commodity, the relevancy factor refers to the degree of occurrence of the commodity keyword in the document, and when the degree is higher, the relevancy of the document is considered to be higher. The relevancy factor is the matching between the title keywords of the product and the product, and the degree of matching, the matching of important words, the distance between the matched words and the like may affect the relevancy. For example, when the search content is "duck washing machine", the keyword of a commodity is that the relevance of the washing machine to the selling of accessories of the washing machine is higher, and the relevance of the connection of the ducks is higher than that of the separation of the small duck from the duck.
For example, the importance ranking model, such as web page ranking (PageRank), hypertext-Induced Topic Search (HITS), HillTop (a patent for ranking Search engine results), trust index (TrustRank), and the like, may be used to calculate the importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object.
For example, an importance degree preset rule in the trading platform corresponding to each trading object may be specifically obtained, and the importance degree factor of the trading object is calculated according to the importance degree preset rule and the multidimensional feature information corresponding to each trading object.
The setting mode of the importance degree preset rule may be various, for example, the setting mode may be set according to the requirement of the actual application, or the setting mode may be preset and stored in the electronic device. In addition, the importance degree preset rule may be built in the electronic device, or may be stored in a memory and transmitted to the electronic device, and the like. The preset rules of importance degree corresponding to each trading platform may be the same or different, for example, the preset rules of importance degree of platform X and the preset rules of importance degree of platform Y may be the same or different, and may be set according to specific situations. Because the multidimensional characteristic information of each trading platform may be the same or different, the multidimensional characteristic information used for calculating the importance factor of each trading platform may be the same or different and may be set according to specific conditions.
For example, in some embodiments, the importance factor of each transaction object is calculated according to the preset importance rule and the multidimensional feature information corresponding to each transaction object, specifically, the weight of each dimension feature object information of each transaction object may be determined according to the preset importance rule, and the importance factor of each transaction object is calculated according to the weight of each dimension feature object information of each transaction object and the multidimensional feature information.
For example, when the transaction object is a commodity, the importance factor may include the number of keyword conversions of the commodity, and for example, the more keyword conversions of the commodity, the more valuable the commodity. That is, the higher the conversion rate of the keywords of a commodity on all the e-commerce platforms is, the higher the importance degree of the commodity is. The importance factor is the element directly influencing the commodity conversion rate, such as the commodity sales volume, the commodity selling price and the like. The importance factor of the commodity can be one or a combination of more characteristic factors of commodity sales, sale price, cost, evaluation, click rate, order placing conversion rate, exposure rate, deal amount and the like.
Wherein, the conversion rate refers to the ratio of the number of persons who arrive at the trading platform and generate the purchasing behavior and the number of persons who arrive at the trading platform. The calculation method comprises the following steps: conversion rate ═ (number of customers who make purchases/number of visitors to all stores) × 100%. The factors that influence the conversion may be: baby description, sales goals, evaluation of a baby, and the like.
For example, the comprehensive commodity ranking may be related to 10 factors, and the weight of each dimension feature object information may be volume: 15%, good evaluation: 10% and storage amount: 8%, go up and down the frame: 12%, conversion: 14%, shop window recommendation: 10% and buyback rate: 10%, DSR: an 8% Seller service Rating system (Detail Seller Rating), etc., the weight ratio of each dimension feature object information in the importance factor affecting the ranking may be flexibly set according to the actual situation, which is not limited herein.
104. And fusing the relevancy factor and the importance factor of the transaction object to obtain a ranking parameter for uniformly ranking each transaction object.
For example, a variety of different characteristic factors may be combined to give a final keyword to transaction object ranking score. If only one to two of the characteristic factors are used, some most basic ordering of the commodities can be performed. If more characteristic factors participate in the ranking, a better ranking algorithm can be obtained. The combinatorial approach may have simple manual configuration to a complex Learning model like Learning to Rank et al.
For example, the relevancy factor and the importance factor of the transaction object may be fused to obtain a comprehensive factor of the transaction object, and the comprehensive factor of the transaction object is normalized by using a ranking learning model to obtain ranking parameters for uniformly ranking each transaction object.
For example, in some embodiments, the ranking parameter of the transaction object is obtained according to the ranking learning model, specifically, the ranking learning model may be used to perform feature extraction on the comprehensive factor of the transaction object to obtain comprehensive feature information of the transaction object, and the ranking score of the transaction object is calculated according to the comprehensive feature information to obtain the ranking parameter of each transaction object for uniform ranking.
In order to improve the efficiency of ranking, before the comprehensive characteristic information of the transaction object is normalized by using the ranking learning model, the method may further include:
acquiring a plurality of groups of sample data; and training a preset sequencing learning model by using the sample data to obtain a sequencing learning model.
For example, the query content may be specifically determined, a plurality of sample transaction object data are obtained based on the query content, the sample transaction object data include sample transaction objects matched with the query content, feature extraction is performed on the sample transaction objects by using a preset ranking learning model to obtain comprehensive feature information of the sample transaction objects, ranking scores of the sample transaction objects are calculated according to the comprehensive feature information to obtain sample predicted values, and the preset ranking learning model is converged according to the sample predicted values and the sample real values to obtain a ranking learning model.
For example, the training data may be obtained by manual labeling, searching logs, and the like. For example, a portion of a Query (Query) may be randomly selected from a search log, leaving a professionally trained data evaluator to give a relevance determination for the "Query-URL pair". The common is a 5-grade score, poor, general, good, excellent, perfect. This is used as training data. The manual marking is the subjective judgment of the marker and can be influenced by factors such as background knowledge of the marker. Wherein, the URL is uniform resource Locator, uniform resource Locator.
For example, the training may be performed using a single document method (poitwise) in a ranking to Rank (LTR) Learning model. For example, the Pointwise method only considers the absolute relevance of a single document under a given query, and does not consider the relevance of other documents and the given query. I.e. a true document sequence for a given query q, only a single document di and the relevance ci of the query need to be considered, i.e. the input data may be in the form:
Figure BDA0002507303970000121
105. and sequencing the transaction objects according to the sequencing parameters of the transaction objects in the transaction object platforms to obtain a sequenced transaction object set.
For example, the ranking parameters of the trading objects in the multiple trading object platforms may be combined to obtain a combined ranking parameter sequence, and the combined ranking parameter sequence may be ranked by using a heap ranking algorithm to obtain a ranked set of trading objects.
For example, if the same transaction object exists on only one transaction platform, the ranking parameters of the transaction object can be directly used as the ranking parameters after processing, and then the ranking parameters after processing of the transaction objects in the multiple transaction object platforms are combined to obtain a sequence of the ranking parameters after combination. For example, the parameter weight of each trading platform may be set, and then the ranking parameter and the parameter weight corresponding to the ranking parameter are weighted to obtain a processed ranking parameter, and the like.
For example, in some embodiments, the combined sorting parameter sequence is sorted by using a heap sorting algorithm, and specifically, a maximum value of the sorting parameters in the combined sorting parameter sequence may be obtained; exchanging the maximum value of the sorting parameter with the tail sorting parameter in the combined sorting parameter sequence to obtain an exchanged tail sorting parameter; obtaining the maximum value of the non-exchanged sorting parameters in the combined sorting parameter sequence; and exchanging the maximum value of the unaltered sorting parameter with the tail sorting parameter in the unaltered sorting parameters in the combined sorting parameter sequence until all the sorting parameters in the combined sorting parameter sequence are exchanged, and obtaining a sorted transaction object set.
For example, the sequence of the combined sorting parameters is constructed into a large top heap, and at this time, the maximum value of the whole sequence is the root node of the top of the heap. It is swapped with the last element, which is now the maximum. The remaining n-1 elements are then reconstructed into a stack, which results in the next smallest value of n elements. The above-mentioned steps are repeatedly implemented so as to obtain an ordered sequence.
For example, the initial array a [0 … n-1] may be constructed into a maximum heap, which is the initial unordered area, and then the element a [0] with the maximum value is exchanged with the last element a [ n-1] of the unordered area, so as to obtain the new unordered area a [0.. n-2] and ordered area a [ n-1 ]. Since the swapped new root a [0] may violate heap properties, the current unordered region a [0.. n-2] should be adjusted to the maximum heap. Then the element a 0 with the largest value in a 0.. n-2 is exchanged with the last record a n-2 in the interval again, thus obtaining a new disordered area a 0.. n-3 and an ordered area a n-2.. n-1. This operation is repeated until the unordered region has only one element.
The sorting mode only needs to carry out sorting for n-1 times, the unordered area is always in front of the ordered area in the heap sorting, and the ordered area is gradually enlarged from back to front at the tail of the original vector until the whole vector.
For example, when the trading object is a commodity, the system can perform heap sorting and integration according to commodity sorting parameters generated by the sorting learning model, recommend the first few commodities with the highest popularity value of the commodity class according to a heap sorting algorithm, and display the first few commodities with popularity values of the corresponding class when the anchor selects the class of the corresponding class. Thereby generating a ranking of the heat value of the platform's goods.
The popularity value can be obtained by integrating the sales data and the popularity of the commodity on all E-commerce platforms by the platform. The popularity value can be composed of data such as commodity sales volume, sales price, cost, evaluation, click rate, order-placing conversion rate, exposure rate, deal amount and the like. Clicking the popularity value Top label of the commodity, and checking the comprehensive sales data details of the commodity on each platform, and the like.
106. And outputting the ordered transaction object set.
For example, the set of ranked transaction objects may be displayed in the search page. And the popularity value sequence of the corresponding commodities is displayed in the sequenced trading object set. The anchor can click the corresponding trading object personal value label, a commodity data page is displayed, the comprehensive historical sales data details of the commodity on each platform can be checked, and the anchor can be helped to know the sales data of the commodity in more detail.
As can be seen from the above, the embodiment may obtain search content, then obtain transaction object information from a plurality of transaction platforms respectively based on the search content, where the transaction object information includes a transaction object matched with the search content in each transaction platform and multidimensional feature information corresponding to the transaction object, then calculate a relevancy factor of the transaction object, and calculate an importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object, where the relevancy factor represents a relevancy between the search content and the transaction object, the importance factor represents an importance of the transaction object, then fuse the relevancy factor and the importance factor of the transaction object to obtain a ranking parameter for uniform ranking of each transaction object, and then rank the transaction objects according to the ranking parameters of the transaction objects in the plurality of transaction object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set. According to the scheme, when the anchor needs to conduct live broadcast selection, the search content can be obtained, the trading object information in the trading platforms corresponding to the search content is further obtained, the trading object information is processed in a unified mode and then is sequenced, a sequenced trading object set is obtained, the sequenced trading object set integrates the multi-dimensional characteristic information of the trading objects, the sequencing of the trading objects with the highest conversion rate is provided for the anchor, the boundary between the platforms is broken, the anchor is helped to improve the efficiency and quality of selection, the cost of anchor selection is reduced, and the conversion rate of the carried goods is improved.
The method described in the previous embodiment is further detailed by way of example.
In this embodiment, the information processing apparatus is specifically integrated in an electronic device, and the transaction object may be a commodity.
Firstly, in order to improve the efficiency of ranking, a ranking learning model may be trained first, specifically as follows:
acquiring a plurality of groups of sample data; and training a preset sequencing learning model by using the sample data to obtain a sequencing learning model.
For example, query content may be determined specifically, a plurality of sample commodity data are obtained based on the query content, the sample commodity data include sample commodities matched with the query content, feature extraction is performed on the sample commodities by using a preset ranking learning model to obtain comprehensive feature information of the sample commodities, ranking scores of the sample commodities are calculated according to the comprehensive feature information to obtain sample predicted values, and the preset ranking learning model is converged according to the sample predicted values and the sample true values to obtain a ranking learning model.
For example, the training data may be obtained by manual labeling, searching logs, and the like. For example, a portion of Query may be randomly selected from the search logs for a professionally trained data evaluator to give a relevance determination for the "Query-URL pair". The common is a 5-grade score, poor, general, good, excellent, perfect. This is used as training data. The manual marking is the subjective judgment of the marker and can be influenced by factors such as background knowledge of the marker.
For example, the training may be performed using a single document method (poitwise) in a ranking to Rank (LTR) Learning model. For example, the Pointwise method only considers the absolute relevance of a single document under a given query, and does not consider the relevance of other documents and the given query. I.e. a true document sequence for a given query q, only a single document di and the relevance ci of the query need to be considered, i.e. the input data is in the form:
Figure BDA0002507303970000151
and thirdly, the commodities of a plurality of trading platforms can be ranked through the trained ranking learning model, and specific reference can be made to fig. 2a and 2 g.
As shown in fig. 2a, a specific flow of an information processing method may be as follows:
201. the electronic device displays a search page of a live client.
Wherein the search page includes a search input control. The representation form of the control can be specifically an input box.
For example, the electronic device may specifically display a show window middle page of the live broadcast client, as shown in fig. 2b, before the anchor starts live broadcast of the e-commerce live broadcast with goods, the anchor may log in an account in a "XXX login" manner, and then display a search page of the live broadcast client, as shown in fig. 2c, the anchor may input goods with goods to be selected in an input box of the search page, that is, a goods name box.
202. The electronic device determines input search content based on an input operation for the search input control.
For example, when the electronic device detects an input operation of a user on the search input control, the electronic device determines search content input by the user and acquires the search content, for example, if the user inputs "men T-shirts", the acquired search content is "men T-shirts".
203. The electronic device acquires commodity information from the plurality of trading platforms respectively based on the search content.
The commodity information comprises commodities matched with the search content in each transaction platform and multi-dimensional characteristic information corresponding to the commodities. The multi-dimensional characteristic information of the commodity can comprise commodity sales volume, sales price, cost, evaluation, click rate, order placing conversion rate, exposure rate, deal amount and the like.
For example, the system of the electronic device generates the feature factor of the commodity according to the heat of the commodity, and the feature factor generates the algorithm model according to the relevance and the importance. The live show window middle station can access the commodities of different E-commerce platforms, such as a platform X, a platform Y, a platform Z and the like. Different E-commerce platforms have a set of commodity sequencing algorithms belonging to the E-commerce platforms. When data is accessed, if the sales data fields on each platform are simply displayed, the comprehensive conditions of the popularity value and the conversion rate of the commodity are difficult to visually see. Therefore, the system generates the characteristic factors of the commodities according to the attributes of the commodities. When the anchor broadcasts the selected commodities, the system can calculate each commodity matched according to the algorithm model in real time and sequence the commodities according to the size of the score. The algorithm model basically calculates a score for the commodity according to the importance and the relevance of the commodity, and then carries out the ranking. Here, the relevance and importance are two important factors in the commodity ranking model.
For example, when the anchor needs to perform live selection, for example, interface information of a plurality of trading platforms may be acquired, so as to perform configuration access according to the interface information, thereby acquiring commodity information in the trading platforms. For example, the electronic device may specifically obtain interface information of a plurality of transaction platforms, and obtain, based on the interface information, commodity information matched with the search content from the plurality of transaction platforms, such as platform X, platform Y, and the like. At this time, the trading platform may be a platform that provides services for both the buyer and the seller of the goods.
204. The electronic device calculates a relevancy factor for the item.
Wherein the relevancy factor characterizes relevancy between the search content and the commodity. For example, the electronic device may specifically divide the search content into at least one search keyword, set a weight of the search keyword, then calculate a degree of correlation between each search keyword and the search content to obtain a first score of the search keyword, calculate a degree of correlation factor between each search keyword and the product to obtain a second score of the search keyword, and calculate a degree of correlation between the search content and the product according to the weight of the search keyword, the first score of the search keyword, and the second score of the search keyword to obtain a degree of correlation factor of the product.
For example, the relevancy factor may refer to the degree of occurrence of the product keyword in the document, and when the degree is higher, the relevancy of the document is considered to be higher. The relevancy factor is the matching between the title keywords of the product and the product, and the degree of matching, the matching of important words, the distance between the matched words and the like may affect the relevancy. For example, when the search content is "duck washing machine", the keyword of a commodity is that the relevance of the washing machine to the selling of accessories of the washing machine is higher, and the relevance of the connection of the ducks is higher than that of the separation of the small duck from the duck.
205. And the electronic equipment calculates the importance factor of the commodity according to the multi-dimensional characteristic information corresponding to the commodity.
Wherein the importance factor characterizes the importance of the good. For example, the electronic device may specifically obtain an importance degree preset rule in a transaction platform corresponding to each commodity, then determine a weight of each dimension feature object information of the commodity according to the importance degree preset rule, and calculate an importance degree factor of the commodity according to the weight of each dimension feature object information of the commodity and the multi-dimension feature information.
The setting mode of the importance degree preset rule may be various, for example, the setting mode may be set according to the requirement of the actual application, or the setting mode may be preset and stored in the electronic device. In addition, the importance degree preset rule may be built in the electronic device, or may be stored in a memory and transmitted to the electronic device, and the like.
For example, the importance factor may include the number of conversions of a commodity keyword, e.g., the more conversions of a commodity keyword, the more valuable the commodity. In particular, the higher the conversion rate of the keywords of a commodity on all the e-commerce platforms, the higher the importance of the commodity. The importance factor is an element directly influencing the commodity conversion rate, such as the commodity sales volume, the commodity sales price and the like, and can be the importance factor of the commodity, such as the commodity sales volume, the commodity sales price, the cost, the evaluation, the click rate, the order-placing conversion rate, the exposure rate, the amount of orders for deal, the amount of deals and other characteristic factors.
For example, the weight of each dimension feature object information in the platform X may be: volume of finished delivery: 15%, good evaluation: 10% and storage amount: 8%, go up and down the frame: 12%, conversion: 14%, shop window recommendation: 10% and buyback rate: 10%, DSR: 8% Seller service Rating system (Detail Seller Rating), etc., the weight of each dimension feature object information in platform Y may be: volume of finished delivery: 20%, good evaluation: 15% and storage amount: 10%, conversion: 12%, shop window recommendation: 10% and buyback rate: 10%, DSR: an 8% vendor service Rating system (Detail Seller Rating), and so on.
206. And the electronic equipment fuses the relevancy factor and the importance factor of the commodity to obtain a sorting parameter for uniformly sorting each commodity.
For example, the electronic device may specifically fuse the relevancy factor and the importance factor of the commodity to obtain an integrated factor of the commodity, perform feature extraction on the integrated factor of the commodity by using a ranking learning model to obtain integrated feature information of the commodity, calculate a ranking score of the commodity according to the integrated feature information, and obtain a ranking parameter for uniform ranking of each commodity.
For example, the background of the electronic device requests a third-party platform (i.e., a trading platform) server to return corresponding commodity data, and the data of multiple platforms are reintegrated through a heap sorting algorithm to generate a popularity sorting of the commodities. For example, the background requests the third-party platform server to transmit corresponding commodity data back, and heap sorting and integration are performed according to the commodity relevance scores generated by the algorithm model, so that the popularity value sorting of the commodities of the platform is generated.
207. The electronic equipment sorts the commodities according to the sorting parameters of the commodities in the plurality of commodity platforms to obtain a sorted commodity set.
For example, the electronic device may specifically combine the sorting parameters of the commodities in the plurality of commodity platforms to obtain a combined sorting parameter sequence, and sort the combined sorting parameter sequence by using a heap sorting algorithm to obtain a sorted commodity set.
For example, if the same commodity has a plurality of different trading platforms, the sorting parameters of the different trading platforms of the commodity may be processed to obtain processed sorting parameters, and if the same commodity only exists on one trading platform, the sorting parameters of the commodity may be directly used as the processed sorting parameters, and then the processed sorting parameters of the commodities in the plurality of commodity platforms are combined to obtain a combined sorting parameter sequence. For example, the processing mode may be to set a parameter weight of each trading platform, and then weight the ranking parameter and the parameter weight corresponding to the ranking parameter to obtain a processed ranking parameter, and so on.
For example, in some embodiments, the electronic device may specifically obtain a maximum value of the sorting parameters in the combined sorting parameter sequence, exchange the maximum value of the sorting parameters with an end sorting parameter in the combined sorting parameter sequence to obtain an exchanged end sorting parameter, obtain a maximum value of an unaltered sorting parameter in the combined sorting parameter sequence, and exchange the maximum value of the unaltered sorting parameter with the end sorting parameter in the unaltered sorting parameter in the combined sorting parameter sequence until all the sorting parameters in the combined sorting parameter sequence are exchanged, so as to obtain a sorted commodity set.
For example, the electronic device may perform heap sorting and integration according to the commodity sorting parameters generated by the sorting learning model, and the system recommends Top3 commodities with the highest popularity values of the commodity categories according to a heap sorting algorithm, as shown in fig. 2c, when the anchor selects the category of the corresponding category, the Top3 commodities with popularity values of the corresponding category are also displayed. Thereby generating a ranking of the heat value of the platform's goods. The user may click on the popularity value tab and display a popularity value description page, as shown in fig. 2d, the data sources: the popularity value can be obtained by integrating the sales data and the popularity of the commodity on all E-commerce platforms by the platform. The data composition is as follows: the popularity value can be composed of data such as commodity sales volume, sales price, cost, evaluation, click rate, order-placing conversion rate, exposure rate, deal amount and the like. Popularity value Top label: clicking the popularity value Top label of the commodity, and checking the comprehensive sales data details of the commodity on each platform, and the like.
208. The electronic device displays the ordered set of items in the search page.
For example, the sorted set of items may be displayed in the search page. And the popularity value of the corresponding commodities is displayed in the sorted commodity set. The anchor can click the corresponding commodity popularity value Top label and can display a commodity data page, as shown in fig. 2e, the comprehensive historical sales data detail of the commodity on each platform can be checked, and the anchor can know the sales data of the commodity in more detail. When the anchor has finished adding the goods, the added goods can be displayed in the management page of the show window middle station, as shown in fig. 2f, the anchor can need the goods with goods in the show window management page.
For example, the ranking data of the commodities may be stored in a server, and when the anchor selects a commodity, the electronic device may request the server for the data and present the popularity ranking corresponding to the commodity data. The anchor can select the corresponding commodity ranking value according to the requirement.
As can be seen from the above, the embodiment may obtain search content, then obtain transaction object information from a plurality of transaction platforms respectively based on the search content, where the transaction object information includes a transaction object matched with the search content in each transaction platform and multidimensional feature information corresponding to the transaction object, then calculate a relevancy factor of the transaction object, and calculate an importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object, where the relevancy factor represents a relevancy between the search content and the transaction object, the importance factor represents an importance of the transaction object, then fuse the relevancy factor and the importance factor of the transaction object to obtain a ranking parameter for uniform ranking of each transaction object, and then rank the transaction objects according to the ranking parameters of the transaction objects in the plurality of transaction object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set. According to the scheme, when the anchor needs to conduct live broadcast selection, search content can be obtained, transaction object information in a plurality of transaction platforms corresponding to the search content is further obtained, the transaction object information is processed in a unified mode and then sequenced to obtain a sequenced transaction object set, the sequenced transaction object set integrates multi-dimensional characteristic information of transaction objects, sequencing of the transaction objects with the highest conversion rate is provided for the anchor, the boundary between the platforms is broken, commodities with the highest whole network popularity value are screened out, the anchor is helped to improve selection efficiency and quality, the cost of anchor selection is further reduced, and the conversion rate of goods is improved.
In order to better implement the method, correspondingly, the embodiment of the present application further provides an information processing apparatus, which may be specifically integrated in an electronic device, where the electronic device may be a server, or may be a terminal or other device.
For example, as shown in fig. 3, the information processing apparatus may include a first acquisition unit 301, a second acquisition unit 302, a calculation unit 303, a fusion unit 304, a sorting unit 305, and an output unit 306 as follows:
a first acquisition unit 301 for acquiring search content;
a second obtaining unit 302, configured to obtain trading object information from multiple trading platforms respectively based on the search content, where the trading object information includes a trading object matched with the search content in each trading platform and multidimensional feature information corresponding to the trading object;
a calculating unit 303, configured to calculate a relevancy factor of the transaction object, and calculate an importance factor of the transaction object according to multidimensional feature information corresponding to the transaction object, where the relevancy factor represents a relevancy between the search content and the transaction object, and the importance factor represents an importance of the transaction object;
the fusion unit 304 is configured to fuse the relevancy factor and the importance factor of the transaction object to obtain a ranking parameter for uniformly ranking each transaction object;
the sorting unit 305 is configured to sort the transaction objects according to the sorting parameters of the transaction objects in the multiple transaction object platforms, so as to obtain a sorted transaction object set;
and the output unit 306 is used for outputting the ordered transaction object set.
Optionally, in some embodiments, the calculating unit 303 may include a first calculating subunit and a second calculating subunit, as follows:
the first calculating subunit is used for dividing the search content into at least one search keyword and setting the weight of the search keyword; calculating the correlation between the search content and the transaction object according to the search keyword and the weight of the search keyword to obtain a correlation factor of the transaction object;
the second calculation subunit is used for acquiring an importance degree preset rule in the trading platform corresponding to each trading object; and calculating the importance factor of each transaction object according to the preset importance rule and the multi-dimensional characteristic information corresponding to each transaction object.
Optionally, in some embodiments, the first calculating subunit may be specifically configured to calculate a relevance between each search keyword and the search content, so as to obtain a first score of the search keyword; calculating the relevancy factor of each search keyword and the transaction object to obtain a second score of the search keyword; and calculating the correlation between the search content and the transaction object according to the weight of the search keyword, the first score of the search keyword and the second score of the search keyword to obtain a correlation factor of the transaction object.
Optionally, in some embodiments, the second calculating subunit may be specifically configured to determine, according to the preset rule of importance, a weight of feature object information of each dimension of the transaction object; and calculating the importance factor of the trading object according to the weight of each dimension characteristic object information of the trading object and the multi-dimension characteristic information.
Optionally, in some embodiments, the fusion unit 304 may include a fusion subunit and a processing subunit, as follows:
the fusion subunit is used for fusing the relevance factor and the importance factor of the trading object to obtain a comprehensive factor of the trading object;
and the processing subunit is used for carrying out standardization processing on the comprehensive factors of the transaction objects by utilizing the sequencing learning model to obtain sequencing parameters for uniformly sequencing each transaction object.
Optionally, in some embodiments, the processing subunit may be specifically configured to perform feature extraction on the comprehensive factor of the transaction object by using a ranking learning model to obtain comprehensive feature information of the transaction object; and calculating the ranking score of the transaction object according to the comprehensive characteristic information to obtain ranking parameters of each transaction object for uniform ranking.
Optionally, in some embodiments, the information processing apparatus may further include a training unit 307, as follows:
the training unit is used for acquiring a plurality of groups of sample data; and training a preset sequencing learning model by using the sample data to obtain a sequencing learning model.
Optionally, in some embodiments, the sorting unit 305 may include a combination subunit and a sorting subunit, as follows:
the combination subunit is used for combining the ranking parameters of the trading objects in the trading object platforms to obtain a combined ranking parameter sequence;
and the sorting subunit is used for sorting the combined sorting parameter sequence by using a heap sorting algorithm to obtain a sorted transaction object set.
Optionally, in some embodiments, the sorting subunit may be specifically configured to obtain a maximum value of the sorting parameters in the combined sorting parameter sequence; exchanging the maximum value of the sorting parameter with the tail sorting parameter in the combined sorting parameter sequence to obtain an exchanged tail sorting parameter; obtaining the maximum value of the non-exchanged sorting parameters in the combined sorting parameter sequence; and exchanging the maximum value of the unaltered sorting parameter with the tail sorting parameter in the unaltered sorting parameters in the combined sorting parameter sequence until all the sorting parameters in the combined sorting parameter sequence are exchanged, and obtaining a sorted transaction object set.
Optionally, in some embodiments, the second obtaining unit 302 may be specifically configured to obtain interface information of a plurality of trading platforms; and acquiring transaction object information matched with the search content from the plurality of transaction platforms based on the interface information.
Optionally, in some embodiments, the first obtaining unit 301 may be specifically configured to display a search page of a live client, where the search page includes a search input control; determining input search content based on an input operation for the search input control;
the output unit 306 may be specifically configured to display the sorted set of transaction objects in the search page.
In a specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and the specific implementation of the above units may refer to the foregoing method embodiments, which are not described herein again.
As can be seen from the above, in this embodiment, the first obtaining unit 301 obtains the search content, then the second obtaining unit 302 obtains the transaction object information from the multiple transaction platforms respectively based on the search content, where the transaction object information includes the transaction object matched with the search content in each transaction platform and the multidimensional feature information corresponding to the transaction object, then the calculating unit 303 calculates the correlation factor of the transaction object, and calculates the importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object, where the correlation factor represents the correlation between the search content and the transaction object, and the importance factor represents the importance of the transaction object, and then the fusing unit 304 fuses the correlation factor and the importance factor of the transaction object to obtain the ranking parameter for uniform ranking of each transaction object, then, the ranking unit 305 ranks the trading objects according to ranking parameters of the trading objects in the plurality of trading object platforms to obtain a ranked trading object set, and the output unit 306 is configured to output the ranked trading object set. According to the scheme, when the anchor needs to conduct live broadcast selection, the search content can be obtained, the trading object information in the trading platforms corresponding to the search content is further obtained, the trading object information is processed in a unified mode and then is sequenced, a sequenced trading object set is obtained, the sequenced trading object set integrates the multi-dimensional characteristic information of the trading objects, the sequencing of the trading objects with the highest conversion rate is provided for the anchor, the boundary between the platforms is broken, the anchor is helped to improve the efficiency and quality of selection, the cost of anchor selection is reduced, and the conversion rate of the carried goods is improved.
In addition, an electronic device according to an embodiment of the present application is further provided, as shown in fig. 4, which shows a schematic structural diagram of the electronic device according to an embodiment of the present application, and specifically:
the electronic device may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the electronic device configuration shown in fig. 4 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 401 is a control center of the electronic device, connects various parts of the whole electronic device by various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.
The electronic device further comprises a power supply 403 for supplying power to the various components, and preferably, the power supply 403 is logically connected to the processor 401 through a power management system, so that functions of managing charging, discharging, and power consumption are realized through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The electronic device may further include an input unit 404, and the input unit 404 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the electronic device may further include a display unit and the like, which are not described in detail herein. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application program stored in the memory 402, thereby implementing various functions as follows:
acquiring search content, acquiring trading object information from a plurality of trading platforms respectively based on the search content, wherein the trading object information comprises a trading object matched with the search content in each trading platform and multi-dimensional characteristic information corresponding to the trading object, calculating a correlation factor of the trading object, and calculating an importance factor of the trading object according to the multi-dimensional characteristic information corresponding to the trading object, wherein the correlation factor represents the correlation between the search content and the trading object, the importance factor represents the importance of the trading object, then fusing the correlation factor and the importance factor of the trading object to obtain a ranking parameter for uniformly ranking each trading object, and then ranking the trading objects according to the ranking parameters of the trading objects in the trading object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
As can be seen from the above, in this embodiment, search content may be obtained, then, transaction object information is obtained from a plurality of transaction platforms respectively based on the search content, where the transaction object information includes a transaction object matched with the search content in each transaction platform and multidimensional feature information corresponding to the transaction object, then a relevancy factor of the transaction object is calculated, and an importance factor of the transaction object is calculated according to the multidimensional feature information corresponding to the transaction object, where the relevancy factor represents a relevancy between the search content and the transaction object, the importance factor represents an importance of the transaction object, then the relevancy factor and the importance factor of the transaction object are fused to obtain a ranking parameter for uniform ranking of each transaction object, and then the transaction objects are ranked according to the ranking parameters of the transaction objects in the plurality of transaction object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set. According to the scheme, when the anchor needs to conduct live broadcast selection, the search content can be obtained, the trading object information in the trading platforms corresponding to the search content is further obtained, the trading object information is processed in a unified mode and then is sequenced, a sequenced trading object set is obtained, the sequenced trading object set integrates the multi-dimensional characteristic information of the trading objects, the sequencing of the trading objects with the highest conversion rate is provided for the anchor, the boundary between the platforms is broken, the anchor is helped to improve the efficiency and quality of selection, the cost of anchor selection is reduced, and the conversion rate of the carried goods is improved.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application further provide a storage medium, in which a plurality of instructions are stored, where the instructions can be loaded by a processor to execute the steps in any one of the information processing methods provided in the embodiments of the present application. For example, the instructions may perform the steps of:
acquiring search content, acquiring trading object information from a plurality of trading platforms respectively based on the search content, wherein the trading object information comprises a trading object matched with the search content in each trading platform and multi-dimensional characteristic information corresponding to the trading object, calculating a correlation factor of the trading object, and calculating an importance factor of the trading object according to the multi-dimensional characteristic information corresponding to the trading object, wherein the correlation factor represents the correlation between the search content and the trading object, the importance factor represents the importance of the trading object, then fusing the correlation factor and the importance factor of the trading object to obtain a ranking parameter for uniformly ranking each trading object, and then ranking the trading objects according to the ranking parameters of the trading objects in the trading object platforms, and obtaining a sorted transaction object set, and outputting the sorted transaction object set.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the storage medium can execute the steps in any information processing method provided in the embodiments of the present application, beneficial effects that can be achieved by any information processing method provided in the embodiments of the present application can be achieved, and detailed descriptions are omitted here for the foregoing embodiments.
The foregoing detailed description is directed to an information processing method, an information processing apparatus, an electronic device, and a storage medium provided in the embodiments of the present application, and specific examples are applied in the present application to explain the principles and implementations of the present application, and the descriptions of the foregoing embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (15)

1. An information processing method characterized by comprising:
acquiring search content;
acquiring trading object information from a plurality of trading platforms respectively based on the search content, wherein the trading object information comprises a trading object matched with the search content in each trading platform and multi-dimensional feature information corresponding to the trading object;
calculating a relevancy factor of the trading object, and calculating an importance factor of the trading object according to multi-dimensional feature information corresponding to the trading object, wherein the relevancy factor represents the relevancy between the search content and the trading object, and the importance factor represents the importance of the trading object;
fusing the relevancy factor and the importance factor of the transaction objects to obtain a ranking parameter for uniformly ranking each transaction object;
sequencing the transaction objects according to sequencing parameters of the transaction objects in a plurality of transaction object platforms to obtain a sequenced transaction object set;
and outputting the ordered transaction object set.
2. The method of claim 1, wherein said calculating a relevancy factor for said trading object comprises:
dividing the search content into at least one search keyword, and setting the weight of the search keyword;
and calculating the correlation between the search content and the transaction object according to the search keyword and the weight of the search keyword to obtain a correlation factor of the transaction object.
3. The method according to claim 2, wherein the calculating the correlation between the search content and the transaction object according to the search keyword and the weight of the search keyword to obtain the correlation factor of the transaction object comprises:
calculating the relevance of each search keyword and the search content to obtain a first score of the search keyword;
calculating the relevancy factor of each search keyword and the transaction object to obtain a second score of the search keyword;
and calculating the correlation between the search content and the transaction object according to the weight of the search keyword, the first score of the search keyword and the second score of the search keyword to obtain a correlation factor of the transaction object.
4. The method according to claim 1, wherein the calculating the importance factor of the transaction object according to the multidimensional feature information corresponding to the transaction object comprises:
acquiring an importance degree preset rule in a trading platform corresponding to each trading object;
and calculating the importance factor of the transaction object according to the importance preset rule and the multi-dimensional characteristic information corresponding to each transaction object.
5. The method according to claim 4, wherein the calculating the importance factor of the transaction object according to the preset importance rule and the multidimensional feature information corresponding to each transaction object comprises:
determining the weight of each dimension characteristic object information of the transaction object according to the importance degree preset rule;
and calculating the importance factor of the trading object according to the weight of each dimension characteristic object information of the trading object and the multi-dimension characteristic information.
6. The method according to claim 1, wherein the fusing the relevancy factor and the importance factor of the transaction objects to obtain a ranking parameter for uniformly ranking each transaction object comprises:
fusing the relevancy factor and the importance factor of the transaction object to obtain a comprehensive factor of the transaction object;
and carrying out standardization processing on the comprehensive factors of the transaction objects by using a sequencing learning model to obtain sequencing parameters for uniformly sequencing each transaction object.
7. The method of claim 6, wherein the normalizing the composite factors of the transaction objects by using the ranking learning model to obtain ranking parameters for each transaction object for uniform ranking comprises:
performing feature extraction on the comprehensive factors of the transaction objects by using a sequencing learning model to obtain comprehensive feature information of the transaction objects;
and calculating the ranking score of the transaction objects according to the comprehensive characteristic information to obtain ranking parameters of each transaction object for uniform ranking.
8. The method of claim 6, further comprising, prior to the normalizing the composite feature information of the transaction object using the ranked learning model:
acquiring a plurality of groups of sample data;
and training a preset sequencing learning model by using the sample data to obtain a sequencing learning model.
9. The method of claim 1, wherein the ranking the transaction objects according to ranking parameters of the transaction objects in the multiple transaction object platforms to obtain a set of ranked transaction objects comprises:
combining the sequencing parameters of the transaction objects in the transaction object platforms to obtain a sequence of the combined sequencing parameters;
and sequencing the combined sequencing parameter sequence by using a heap sequencing algorithm to obtain a sequenced transaction object set.
10. The method of claim 9, wherein the sorting the combined sorted parameter sequence using a heap sorting algorithm to obtain a set of sorted transaction objects comprises:
obtaining the maximum value of the sorting parameters in the combined sorting parameter sequence;
exchanging the maximum value of the sorting parameter with the tail sorting parameter in the combined sorting parameter sequence to obtain an exchanged tail sorting parameter;
obtaining the maximum value of the non-exchanged sorting parameters in the combined sorting parameter sequence;
and exchanging the maximum value of the unaltered sorting parameter with the tail sorting parameter in the unaltered sorting parameters in the combined sorting parameter sequence until all the sorting parameters in the combined sorting parameter sequence are exchanged, so as to obtain a sorted transaction object set.
11. The method of claim 1, wherein the obtaining trading object information from a plurality of trading platforms based on the search content respectively comprises:
acquiring interface information of a plurality of transaction platforms;
and acquiring trading object information matched with the search content from the plurality of trading platforms based on the interface information.
12. The method of claim 1, wherein the obtaining search content comprises:
displaying a search page of a live client, wherein the search page comprises a search input control;
determining input search content based on an input operation for the search input control;
the outputting the ordered set of transaction objects comprises: displaying the sorted set of transaction objects in the search page.
13. An information processing apparatus characterized by comprising:
a first acquisition unit configured to acquire search content;
the second acquisition unit is used for respectively acquiring transaction object information from a plurality of transaction platforms based on the search content, wherein the transaction object information comprises transaction objects matched with the search content in each transaction platform and multi-dimensional feature information corresponding to the transaction objects;
the calculating unit is used for calculating a relevancy factor of the trading object and calculating an importance factor of the trading object according to multi-dimensional characteristic information corresponding to the trading object, wherein the relevancy factor represents the relevancy between the search content and the trading object, and the importance factor represents the importance of the trading object;
the fusion unit is used for fusing the relevancy factor and the importance factor of the transaction objects to obtain a sequencing parameter for uniformly sequencing each transaction object;
the sorting unit is used for sorting the transaction objects according to sorting parameters of the transaction objects in the transaction object platforms to obtain a sorted transaction object set;
and the output unit is used for outputting the ordered trading object set.
14. A computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps of the information processing method according to any one of claims 1 to 12.
15. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method according to any of claims 1 to 12 are implemented when the program is executed by the processor.
CN202010450387.6A 2020-05-25 2020-05-25 Information processing method, apparatus, electronic device and storage medium Active CN111654714B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010450387.6A CN111654714B (en) 2020-05-25 2020-05-25 Information processing method, apparatus, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010450387.6A CN111654714B (en) 2020-05-25 2020-05-25 Information processing method, apparatus, electronic device and storage medium

Publications (2)

Publication Number Publication Date
CN111654714A true CN111654714A (en) 2020-09-11
CN111654714B CN111654714B (en) 2024-03-12

Family

ID=72348599

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010450387.6A Active CN111654714B (en) 2020-05-25 2020-05-25 Information processing method, apparatus, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN111654714B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112785390A (en) * 2021-02-02 2021-05-11 微民保险代理有限公司 Recommendation processing method and device, terminal device and storage medium
CN113763131A (en) * 2021-09-08 2021-12-07 北京快来文化传播集团有限公司 Live broadcast commodity selection method, electronic device and computer-readable storage medium
CN118096326A (en) * 2024-04-26 2024-05-28 杭州面朝信息科技有限公司 Potential commodity mining method, system, equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016034028A1 (en) * 2014-09-04 2016-03-10 广州神马移动信息科技有限公司 Method, apparatus and device for obtaining product information
CN106777405A (en) * 2017-04-05 2017-05-31 安徽机器猫电子商务股份有限公司 Promote the e-business method of low frequency class transaction based on SaaS services
CN107016006A (en) * 2016-01-28 2017-08-04 苏宁云商集团股份有限公司 A kind of page display method and system
WO2018090786A1 (en) * 2016-11-18 2018-05-24 深圳市世强元件网络有限公司 Method for accurately searching within website
CN108572992A (en) * 2017-03-14 2018-09-25 苏宁云商集团股份有限公司 A kind of method and device of commodity sequence
CN110807687A (en) * 2019-10-29 2020-02-18 阿里巴巴（中国）有限公司 Object data processing method, device, computing equipment and medium
CN111192115A (en) * 2019-12-30 2020-05-22 江苏随易信息科技有限公司 Community group purchase commodity selection method and device, readable storage medium and terminal

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016034028A1 (en) * 2014-09-04 2016-03-10 广州神马移动信息科技有限公司 Method, apparatus and device for obtaining product information
CN107016006A (en) * 2016-01-28 2017-08-04 苏宁云商集团股份有限公司 A kind of page display method and system
WO2018090786A1 (en) * 2016-11-18 2018-05-24 深圳市世强元件网络有限公司 Method for accurately searching within website
CN108572992A (en) * 2017-03-14 2018-09-25 苏宁云商集团股份有限公司 A kind of method and device of commodity sequence
CN106777405A (en) * 2017-04-05 2017-05-31 安徽机器猫电子商务股份有限公司 Promote the e-business method of low frequency class transaction based on SaaS services
CN110807687A (en) * 2019-10-29 2020-02-18 阿里巴巴（中国）有限公司 Object data processing method, device, computing equipment and medium
CN111192115A (en) * 2019-12-30 2020-05-22 江苏随易信息科技有限公司 Community group purchase commodity selection method and device, readable storage medium and terminal

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
石玉强，闫大顺: "《数据结构与算法》", 中国农业大学出版社, pages: 8 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112785390A (en) * 2021-02-02 2021-05-11 微民保险代理有限公司 Recommendation processing method and device, terminal device and storage medium
CN112785390B (en) * 2021-02-02 2024-02-09 微民保险代理有限公司 Recommendation processing method, device, terminal equipment and storage medium
CN113763131A (en) * 2021-09-08 2021-12-07 北京快来文化传播集团有限公司 Live broadcast commodity selection method, electronic device and computer-readable storage medium
CN113763131B (en) * 2021-09-08 2024-03-29 北京快来文化传播集团有限公司 Live commodity selection method, electronic device and computer readable storage medium
CN118096326A (en) * 2024-04-26 2024-05-28 杭州面朝信息科技有限公司 Potential commodity mining method, system, equipment and storage medium

Also Published As

Publication number Publication date
CN111654714B (en) 2024-03-12

Similar Documents

Publication Publication Date Title
US10846775B1 (en) Identifying item recommendations through recognized navigational patterns
US9727616B2 (en) Systems and methods for predicting sales of item listings
JP5451673B2 (en) Search ranking generation apparatus and method
US8301514B1 (en) System, method, and computer readable medium for providing recommendations based on purchase phrases
CN111654714B (en) Information processing method, apparatus, electronic device and storage medium
CN108205768A (en) Database building method and data recommendation method and device, equipment and storage medium
CN109840796B (en) Decision factor analysis device and decision factor analysis method
CN103890762A (en) Information processing device, information processing method, information processing program, and recording medium
US9330071B1 (en) Tag merging
CN111506849A (en) Page generation method and device
CN111582973A (en) Commodity recommendation data generation method, device and system
CN116308684B (en) Online shopping platform store information pushing method and system
KR20220086932A (en) Method and apparatus for analyzing customer's needs
CN110599291A (en) Intelligent e-commerce operation system and method for efficiently and accurately fusing multiple markets of merchant and buyer
EP2755181B1 (en) Information processing device, information processing method, information processing program, and recording medium
KR20190140701A (en) Hierarchical Category Cluster Based Shopping Basket Associated Recommendation Method
CN114820123A (en) Group purchase commodity recommendation method, device, equipment and storage medium
CN112488781A (en) Search recommendation method and device, electronic equipment and readable storage medium
CN110866191A (en) Recommendation recall method, apparatus and storage medium
CN110930223A (en) Recommendation recall method, device and storage medium based on field-aware factorization machine
CN111680213A (en) Information recommendation method, data processing method and device
CN112435059A (en) Method and device for evaluating value of article in real time, electronic equipment and storage medium
Sadeddin et al. Online shopping bots for electronic commerce: the comparison of functionality and performance
CN115760315A (en) Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and commodity recommendation medium
CN111639989B (en) Commodity recommendation method and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant