CN111556330B - Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform - Google Patents

Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform Download PDF

Info

Publication number
CN111556330B
CN111556330B CN202010363668.8A CN202010363668A CN111556330B CN 111556330 B CN111556330 B CN 111556330B CN 202010363668 A CN202010363668 A CN 202010363668A CN 111556330 B CN111556330 B CN 111556330B
Authority
CN
China
Prior art keywords
live broadcast
flow direction
heat flow
target
push
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010363668.8A
Other languages
Chinese (zh)
Other versions
CN111556330A (en
Inventor
许周
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.)
Zhao Yongkui
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202011147721.7A priority Critical patent/CN112333457A/en
Priority to CN202010363668.8A priority patent/CN111556330B/en
Priority to CN202011149624.1A priority patent/CN112291578A/en
Publication of CN111556330A publication Critical patent/CN111556330A/en
Application granted granted Critical
Publication of CN111556330B publication Critical patent/CN111556330B/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]
    • G06Q30/0631—Item recommendations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/254—Management at additional data server, e.g. shopping server, rights management server
    • H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • 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
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/47815—Electronic shopping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/812—Monomedia components thereof involving advertisement data

Abstract

The embodiment of the disclosure provides an electronic commerce information pushing method based on artificial intelligence and an artificial intelligence cloud platform, a live broadcast commodity recommendation area where a live broadcast commodity target is located in a live broadcast video sharing data stream is identified through a preset artificial intelligence model, a corresponding heat flow direction node diagram is determined according to heat relation information between the attention heat and the total attention heat of the live broadcast video sharing data stream, then, a heat flow direction relation between the heat flow direction node diagram and a heat flow direction node diagram of a hot spot electronic commerce topic is obtained, a pushing deviation parameter is obtained by combining the heat flow direction relation, and electronic commerce information pushed to an electronic commerce live broadcast terminal is generated based on the pushing deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located and a link click object. Therefore, related e-commerce information can be pushed for the user in a targeted manner, so that the user can be added to live videos of interested different e-commerce live broadcast commodities in an all-around manner.

Description

Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform
Technical Field
The disclosure relates to the technical field of artificial intelligence and electronic commerce, in particular to an electronic commerce information pushing method based on artificial intelligence and an artificial intelligence cloud platform.
Background
Electronic commerce generally refers to a novel business operation mode in which, in wide commercial and trade activities worldwide, in an internet environment open to the internet, buyers and sellers conduct various commercial and trade activities without conspiracy based on a browser/server application mode, and consumer online shopping, online transactions and online electronic payments among merchants, and various commercial activities, transaction activities, financial activities, and related comprehensive service activities are realized.
With the rapid development of the internet technology, various live broadcast platforms are continuously developed, and the user can know commodity experience at any time more easily through the commodity live broadcast of electronic commerce. In the process of live broadcasting of commodities, for users watching live broadcasting, how to push relevant e-commerce information for the users in a targeted manner so that the users can be added to live videos of different interested e-commerce live broadcasting commodities in an all-around manner is a technical problem to be solved in the field.
Disclosure of Invention
In order to overcome at least the above disadvantages in the prior art, an object of the present disclosure is to provide an e-commerce information push method and an artificial intelligence cloud platform based on artificial intelligence, which can push relevant e-commerce information for a user in a targeted manner, so that the user can join in live videos of different interested e-commerce live broadcast commodities in an all-around manner.
In a first aspect, the present disclosure provides an electronic commerce information pushing method based on artificial intelligence, which is applied to an artificial intelligence cloud platform, wherein the artificial intelligence cloud platform is in communication connection with a plurality of electronic commerce live broadcast terminals, and the method includes:
acquiring a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal, wherein the live video sharing data stream comprises a link click object of the live commodity target;
identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model, and determining heat flow direction node diagrams of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between attention heat corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and total attention heat of the live broadcast video sharing data stream;
acquiring a heat flow direction relationship between the heat flow direction node diagram and a heat flow direction node diagram of a hot e-commerce topic, wherein the heat flow direction node diagram of the hot e-commerce topic is a heat flow direction node diagram of the live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a video sharing data stream in which other live broadcast commodity information associated with the live broadcast commodity target and indicated by all the link click objects are located;
and obtaining a push deviation parameter according to the heat flow direction relation, and generating electronic commerce information pushed to the electronic commerce live broadcast terminal based on the push deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located and the link click object.
In a possible implementation manner of the first aspect, the step of obtaining a push bias parameter according to the heat flow direction relationship includes:
acquiring heat flow direction interactive information of the heat flow direction relation, wherein the heat flow direction interactive information comprises a plurality of interactive process information respectively corresponding to a plurality of heat flow direction circulating processes;
when confirming that a plurality of mutual process information that any one heat flow direction circulation process corresponds all satisfy and predetermine propelling movement erroneous tendency condition, according to the mutual process information of heat flow direction circulation process with match the propelling movement deviation scope of predetermineeing propelling movement deviation unit, confirm with predetermine the initial propelling movement deviation node of the first propelling movement deviation unit of predetermineeing that propelling movement deviation condition matches, wherein, predetermine propelling movement deviation condition and include: the preset pushing deviation unit is larger than the set pushing deviation range;
determining a plurality of preset push deflection units matched with the preset push deflection conditions to correspond to the initial push deflection nodes of the heat flow circulation process according to the interactive process information of the heat flow circulation process, the push deflection range of the preset push deflection units, the initial push deflection nodes of the first preset push deflection unit and the push heat of the preset push deflection units;
if the position of a heat flow direction circulation process of a push deflection assembly corresponding to the heat flow direction circulation process in the heat flow direction circulation process is matched with the initial push deflection node of the interest point position change section, and if the push deflection assembly is the first push deflection assembly of the interest point position change section, acquiring a heat flow direction circulation process matched with a previous preset push deflection unit adjacent to the interest point position change section as a screening heat flow direction circulation process, and identifying one heat flow direction circulation process of the screening heat flow direction circulation process in the push deflection assembly as a target heat flow direction circulation process matched with the interest point position change section;
if the push deviation component is not the first push deviation component of the interest point position change interval, acquiring a target heat flow direction circulation process matched with the interest point position change interval, identifying the target heat flow direction circulation process in the push deviation component, and identifying at least one active push deviation object of the target heat flow direction circulation process, wherein the heat flow direction circulation process corresponds to a plurality of preset push deviation units;
in the preset push deviation unit, calculating the push deviation association degree of at least one active push deviation object in the target heat flow direction circulation process between any two adjacent push deviation assemblies in the preset push deviation unit and the feature vector of at least one active push deviation object in the target heat flow direction circulation process in the preset push deviation unit according to the push behavior mapping information of the at least one active push deviation object in the plurality of push deviation assemblies in the target heat flow direction circulation process;
and counting the pushing deviation virtual key vectors of the preset pushing deviation units, and mapping and associating the pushing deviation virtual key vectors of each matched preset pushing deviation unit to obtain pushing deviation parameters.
In a possible implementation manner of the first aspect, the live video sharing data stream further includes a link source object of the live commodity target;
the identifying of the live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model comprises the following steps:
extracting the total attention heat corresponding to the live video sharing data stream through the preset artificial intelligence model;
identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located according to the total attention heat, and identifying a user push object corresponding to the live broadcast commodity target according to the live broadcast commodity recommendation area where the live broadcast commodity target is located;
the step of generating the e-commerce information pushed to the e-commerce live broadcast terminal based on the push deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located, and the link click object includes:
acquiring first e-commerce information, second e-commerce information and third e-commerce information which are respectively associated with the link source object, the user push object and the link click object;
screening the first electronic commerce information, the second electronic commerce information and the third electronic commerce information respectively based on the push deviation parameter to obtain screened electronic commerce information;
and the screened e-commerce information is subjected to e-commerce according to the live broadcast commodity recommendation area where the live broadcast commodity target is located.
In a possible implementation manner of the first aspect, the identifying, according to a live broadcast item recommendation area where the live broadcast item target is located, a user push object corresponding to the live broadcast item target includes:
respectively acquiring initial association degrees of the live broadcast commodity targets aiming at each target push object according to the live broadcast commodity recommendation area in which the live broadcast commodity target is located;
and determining the target push object with the highest numerical value initial association degree as the user push object corresponding to the live broadcast commodity target.
In a possible implementation manner of the first aspect, the step of respectively obtaining the initial association degrees of the live broadcast commodity targets for each target push object according to the live broadcast commodity recommendation areas where the live broadcast commodity targets are located includes:
acquiring local recommendation behavior feature degrees corresponding to a live broadcast commodity recommendation area where the live broadcast commodity target is located from the total attention heat degree;
and acquiring initial association degrees of the live broadcast commodity targets aiming at each target push object respectively according to the local recommended behavior feature degrees.
In a possible implementation manner of the first aspect, the target push object includes an active push object and a passive push object, and the attention degree includes an active attention degree and a passive attention degree;
the step of obtaining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to the heat relation information between the attention heat corresponding to the live broadcast commodity recommendation area in which the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data flow includes:
determining the initial association degree corresponding to the object pushed by the user as the object association degree corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located;
determining the user pushing object as a live broadcast commodity recommending area of the active pushing object as an active object video sharing data stream;
determining the user push object as a live broadcast commodity recommendation area of the passive push object as a passive object video sharing data stream;
determining the active attention heat according to the object association degree corresponding to the active object video sharing data stream, and determining the passive attention heat according to the object association degree corresponding to the passive object video sharing data stream;
and determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the active attention heat and the passive attention heat and the total attention heat.
In a possible implementation manner of the first aspect, the heat flow direction node map includes an active heat flow direction node map and a passive heat flow direction node map;
the step of determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to the heat relation information between the active attention heat and the passive attention heat and the total attention heat respectively comprises the following steps:
determining the active heat flow to a node map according to heat relation information between the active attention heat and the total attention heat;
and determining that the passive heat flows to the node map according to heat relation information between the passive attention heat and the total attention heat.
In a possible implementation manner of the first aspect, the flowing of the heat degree of the hot spot e-commerce topic to the node map includes flowing the heat degree of the forward hot spot e-commerce topic to the node map and flowing the heat degree of the reverse hot spot e-commerce topic to the node map;
the step of obtaining a heat flow direction relationship between the heat flow direction node map and the heat flow direction node map of the hot spot e-commerce topic comprises the following steps:
determining the active heat flow direction relation according to the active heat flow direction node diagram and the heat flow direction node diagram of the forward hot spot e-commerce topic;
determining a passive heat flow direction relation according to the passive heat flow direction node diagram and the heat flow direction node diagram of the reverse hot spot e-commerce topic;
and determining the active heat flow direction relation and the passive heat flow direction relation as the heat flow direction relation.
In a possible implementation manner of the first aspect, the step of obtaining a live video sharing data stream including a live commodity target from the e-commerce live broadcast terminal includes:
after acquiring basic live broadcast commodity information corresponding to a live broadcast commodity target needing commodity object live broadcast video sharing from an e-commerce live broadcast request, determining network security label information matched with the basic live broadcast commodity information, and generating corresponding video transmission protection information according to the network security label information and network security big data information corresponding to the network security label information;
the video transmission protection information is related to a transmission control assembly of a video transmission channel of a live broadcast commodity video stream of the basic information of the live broadcast commodity through an electronic commerce live broadcast plug-in, and after the transmission control assembly is configured according to the video transmission protection information, commodity object live broadcast video sharing is executed;
carrying out corresponding video transmission protection operation on the electronic commerce live broadcast terminal through the transmission control component in a commodity object live broadcast video sharing process, wherein in the video transmission protection operation process, updating and configuring the transmission control component through the video transmission channel continuously according to the obtained video transmission protection information;
and acquiring a live broadcast video sharing data stream containing a live broadcast commodity target from the electronic commerce live broadcast terminal in the commodity object live broadcast video sharing process.
In a second aspect, an embodiment of the present disclosure further provides an electronic commerce information pushing device based on artificial intelligence, which is applied to an artificial intelligence cloud platform, the artificial intelligence cloud platform is in communication connection with a plurality of electronic commerce live broadcast terminals, the device includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal, and the live video sharing data stream contains a link click object of the live commodity target;
the identification determination module is used for identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model, and determining a heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the attention heat corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data stream;
a second obtaining module, configured to obtain a heat flow direction relationship between the heat flow direction node map and a heat flow direction node map of a hot e-commerce topic, where the heat flow direction node map of the hot e-commerce topic is a heat flow direction node map of the live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a video sharing data stream where other live broadcast commodity information associated with the live broadcast commodity target indicated by all the link click objects is located;
and the generation module is used for obtaining a pushing deviation parameter according to the heat flow direction relation and generating electronic commerce information pushed to the electronic commerce live broadcast terminal based on the pushing deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located and the link click object.
In a third aspect, an embodiment of the present disclosure further provides an electronic commerce information pushing system based on artificial intelligence, where the electronic commerce information pushing system based on artificial intelligence includes an artificial intelligence cloud platform and a plurality of electronic commerce live broadcast terminals in communication connection with the artificial intelligence cloud platform;
the artificial intelligence cloud platform is used for acquiring a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal, wherein the live video sharing data stream comprises a link click object of the live commodity target;
the artificial intelligence cloud platform is used for identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model, and determining a heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the attention heat corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data stream;
the artificial intelligence cloud platform is used for acquiring a heat flow direction relationship between the heat flow direction node diagram and a heat flow direction node diagram of a hot spot e-commerce topic, the heat flow direction node diagram of the hot spot e-commerce topic is a heat flow direction node diagram of the live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a local video sharing data stream of other live broadcast commodity information related to the live broadcast commodity target indicated by all the link click objects;
the artificial intelligence cloud platform is used for obtaining a pushing deviation parameter according to the heat flow direction relation, and generating electronic commerce information pushed to the electronic commerce live broadcast terminal based on the pushing deviation parameter, a live broadcast commodity recommendation area where the live broadcast commodity target is located and the link click object.
In a fourth aspect, an embodiment of the present disclosure further provides an artificial intelligence cloud platform, where the artificial intelligence cloud platform includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one e-commerce live broadcast terminal, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium, so as to execute the method for pushing the e-commerce information based on artificial intelligence in any one of the first aspect or the possible designs of the first aspect.
In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, where instructions are stored, and when executed, cause a computer to perform the method for pushing artificial intelligence-based e-commerce information in the first aspect or any one of the possible designs of the first aspect.
Based on any one of the above aspects, the live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream is identified through the preset artificial intelligence model, the corresponding heat flow direction node diagram is determined according to heat relation information between the attention heat and the total attention heat of the live broadcast video sharing data stream, and then the heat flow direction relation between the heat flow direction node diagram and the heat flow direction node diagram of the hot spot e-commerce topic is obtained, so that a push deviation parameter is obtained by combining the heat flow direction relation, and electronic commerce information pushed to an electronic live broadcast commerce terminal is generated based on the push deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located and a link click object. Therefore, related e-commerce information can be pushed for the user in a targeted manner, so that the user can be added to live videos of interested different e-commerce live broadcast commodities in an all-around manner.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present disclosure and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings may be obtained from the drawings without inventive effort.
Fig. 1 is a schematic view of an application scenario of an artificial intelligence-based e-commerce information pushing system according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of an artificial intelligence-based e-commerce information pushing method according to an embodiment of the present disclosure;
FIG. 3 is a functional block diagram of an artificial intelligence-based electronic commerce information pushing apparatus according to an embodiment of the disclosure;
fig. 4 is a block diagram illustrating a structure of an artificial intelligence cloud platform for implementing the artificial intelligence-based e-commerce information pushing method according to the embodiment of the present disclosure.
Detailed Description
The present disclosure is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the device embodiments or the system embodiments.
Fig. 1 is an interaction diagram of an artificial intelligence-based e-commerce information pushing system 10 provided by an embodiment of the present disclosure. The artificial intelligence based e-commerce information pushing system 10 can comprise an artificial intelligence cloud platform 100 and an e-commerce live broadcast terminal 200 which is in communication connection with the artificial intelligence cloud platform 100. The artificial intelligence based e-commerce information pushing system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the artificial intelligence based e-commerce information pushing system 10 may also include only one of the components shown in fig. 1 or may also include other components.
In this embodiment, the e-commerce live terminal 200 may include a mobile device, a tablet computer, a laptop computer, or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home devices may include control devices of smart electrical devices, smart monitoring devices, smart televisions, smart cameras, and the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant, a gaming device, and the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like.
In this embodiment, the artificial intelligence cloud platform 100 and the live e-commerce terminal 200 in the artificial intelligence based e-commerce information push system 10 may cooperatively execute the artificial intelligence based e-commerce information push method described in the following method embodiment, and the following detailed description of the method embodiment may be referred to for the specific steps executed by the artificial intelligence cloud platform 100 and the live e-commerce terminal 200.
To solve the technical problem in the passive technology, fig. 2 is a schematic flow chart of an artificial intelligence based e-commerce information pushing method provided in this embodiment of the disclosure, which can be executed by the artificial intelligence cloud platform 100 shown in fig. 1, and the following describes in detail the artificial intelligence based e-commerce information pushing method.
Step S110, a live video sharing data stream including a live commodity target is obtained from the e-commerce live broadcast terminal 200.
Step S120, identifying a live broadcast commodity recommendation area where a live broadcast commodity target is located in a live broadcast video sharing data stream through a preset artificial intelligence model, and determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the attention heat corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data stream.
Step S130, acquiring a heat flow direction relation between the heat flow direction node diagram and the heat flow direction node diagram of the hot spot e-commerce topic.
Step S140, obtaining a push bias parameter according to the heat flow direction relationship, and generating e-commerce information to be pushed to the e-commerce live broadcast terminal 200 based on the push bias parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located, and the link click object.
In this embodiment, the live video sharing data stream may include a link click object of a live commodity target. The live merchandise target may refer to any merchandise that needs to be subjected to electronic commerce, such as but not limited to pregnant women supplies, fast food, cosmetics, electronic products, and the like. The link click object may refer to an interest access link in the live video sharing data stream, which is associated with the link click object of the live commodity target.
In this embodiment, the heat flow direction node map of the hot e-commerce topic may be a heat flow direction node map of a live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a video sharing data stream where other live broadcast commodity information associated with the live broadcast commodity target indicated by all link click objects is located.
Based on the above steps, in the embodiment, a live broadcast commodity recommendation area where a live broadcast commodity target is located in a live broadcast video sharing data stream is identified through a preset artificial intelligence model, a corresponding hot flow direction node map is determined according to hot relationship information between the attention hot degree of the live broadcast video sharing data stream and the total attention hot degree of the live broadcast video sharing data stream, and then a hot flow direction relationship between the hot flow direction node map and a hot flow direction node map of a hot spot e-commerce topic is obtained, so that a push deviation parameter is obtained by combining the hot flow direction relationship, and e-commerce information pushed to the e-commerce live broadcast terminal 200 is generated based on the push deviation parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located, and a link click object. Therefore, related e-commerce information can be pushed for the user in a targeted manner, so that the user can be added to live videos of interested different e-commerce live broadcast commodities in an all-around manner.
The preset artificial intelligence model can be obtained through training of a large number of training samples, for example, can be obtained through training of a large number of live video sharing data streams and corresponding label data, the label data can refer to a live commodity recommendation area where a live commodity target is located, and the specific label degree can be attention. It should also be noted that the specific training process of the preset artificial intelligence model is not the key point of the present disclosure, and the specific training process may be obtained by referring to a general training mode in the prior art, which is not described herein again.
In a possible implementation manner, for step S110, in the process of obtaining a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal 200, the following sub-steps may be specifically implemented, and an example is described as follows.
And a substep S111 of determining the network security label information matched with the basic information of the live broadcast commodity after obtaining the basic information of the live broadcast commodity corresponding to the live broadcast commodity target needing commodity object live broadcast video sharing from the e-commerce live broadcast request.
And a substep S112, generating corresponding video transmission protection information according to the network security label information and the network security big data information corresponding to the network security label information.
And a substep S113, associating the video transmission protection information to a transmission control assembly of a video transmission channel of a live broadcast commodity video stream of the basic information of the live broadcast commodity through the e-commerce live broadcast plug-in, configuring the transmission control assembly according to the video transmission protection information, and then executing commodity object live broadcast video sharing.
In the substep S114, a corresponding video transmission protection operation is performed on the e-commerce live broadcast terminal 200 through the transmission control component in the live broadcast video sharing process of the commodity object.
And in the process of carrying out video transmission protection operation, continuously updating and configuring the transmission control assembly according to the obtained video transmission protection information through the video transmission channel.
In the substep S115, a live video sharing data stream containing a live commodity target is obtained from the e-commerce live video terminal 200 in the commodity object live video sharing process.
In a possible implementation manner, step S111 may be specifically implemented by sub-steps, which are described in detail below.
And the substep S1111 is used for obtaining the basic information of the live broadcast commodities corresponding to the live broadcast commodity target needing commodity object live broadcast video sharing from the electronic commerce live broadcast request.
For example, the basic information of the live commodities can include a reference network security label, commodity sharing times, commodity association range and peripheral commodity range. In other possible embodiments, the basic information of the live broadcast commodities may further include commodity attribute information of the target of the live broadcast commodities, such as commodity types, commodity adapted groups, commodity marketing time, commodity hot information, and the like. The reference cyber security label may be a preset cyber security label determined according to a history situation, the commodity sharing frequency may be a frequency of sharing the live broadcast commodity target by various channels (e.g., a chat tool, an e-commerce tool, etc.) historically, the commodity association range may be a commodity channel service associated with the live broadcast commodity target, and the peripheral commodity range may be a commodity channel service associated with peripheral commodities of the live broadcast commodity target.
In the substep S1112, the number of times of sharing commodities/commodity association range value and the number of times of sharing commodities/peripheral commodity range value of the basic information of the live commodities are determined.
And a substep S1113, constructing a network security label matrix according to the commodity sharing times/commodity association range value and the commodity sharing times/peripheral commodity range value of the basic information of the live broadcast commodity, and determining each first network security label corresponding to the basic information of the live broadcast commodity in the network security label matrix according to the commodity sharing times/commodity association range value and the commodity sharing times/peripheral commodity range value of the basic information of the live broadcast commodity.
And a substep S1114, extracting a vector according to the tag feature of each reference network security tag, and determining the tag association range of each reference network security tag in the network security tag matrix.
And a substep S1115, determining an initial network security situation value of each reference network security label according to the label association range corresponding to each reference network security label and the corresponding relation between the preset label association range and the initial network security situation value.
In sub-step S1116, for each first network security label included in each reference network security label, a target network security posture value of the first network security label is determined according to the initial network security posture value of the reference network security label to which the first network security label belongs.
And a substep S1117 of determining a target commodity association range value, a target commodity sharing number value and a target peripheral commodity range value corresponding to each first network security label according to the preset commodity sharing number, the preset commodity association range value and the target network security situation value corresponding to each first network security label.
In the substep S1118, network security label information matched with the basic information of the live broadcast commodity is determined according to the target commodity sharing frequency value, the target commodity association range value and the target peripheral commodity range value corresponding to each first network security label, the commodity sharing frequency in the basic information of the live broadcast commodity, the attack matching data between the commodity association range and the peripheral commodity range, and the relationship between the attack matching data and the preset attack matching data.
In a possible implementation manner, step S112 may be specifically implemented by sub-steps, which are described in detail below.
And a substep S1121, determining, according to the network security big data information corresponding to the network security tag information, a target network security tag in which the frequency degree of network security protection in the network security tag information is greater than the set frequency degree, and a first protection unit and a second protection unit which use the target network security tag as protection basic objects, where a protection object of the first protection unit and a protection object of the second protection unit are not overlapped and have a logical association with each other.
And a substep S1122 of determining a vulnerability situation evaluation target meeting a first preset condition in the first protection unit, and determining first attack source path information corresponding to the first protection unit according to a data feature vector of attack matching data between the network attack behavior information of the vulnerability situation evaluation target meeting the first preset condition and preset attack verification behavior information.
For example, the vulnerability situational assessment target meeting the first preset condition may be a vulnerability situational assessment target in which the network attack behavior information matches the preset attack verification behavior information.
And a substep S1123 of determining a vulnerability situation evaluation target meeting a second preset condition in the second protection unit, and determining second attack source path information corresponding to the second protection unit according to a data feature vector of attack matching data between the network attack behavior information of the vulnerability situation evaluation target meeting the second preset condition and preset attack verification behavior information.
For example, the vulnerability situational assessment target meeting the second preset condition may be a vulnerability situational assessment target in which the network attack behavior information matches the preset attack verification behavior information.
And a substep S1124, obtaining a virtual attack situation linkage value of the vulnerability situation assessment target at each first protection object according to the first attack source path information corresponding to the first protection unit, and obtaining a virtual attack situation linkage value of the vulnerability situation assessment target at each second protection object according to the second attack source path information in the second protection unit.
And S1125, respectively carrying out protection simulation tests on the vulnerability situation assessment target on each protection object according to the virtual attack situation linkage value of each first protection object and each second protection object, and obtaining first protection simulation test information of each first protection object and second protection simulation test information of each second protection object.
And a substep S1126 of obtaining corresponding protection simulation test information according to the first protection simulation test information of each first protection object and the second protection simulation test information of each second protection object.
And a substep S1127 of generating corresponding video transmission protection information according to the protection simulation test information.
In a possible implementation manner, step S113 may be specifically implemented by sub-steps, which are described in detail below.
And a substep S1131, associating each video transmission protection unit in the video transmission protection information to a corresponding transmission control node in a transmission control component of a video transmission channel of the live broadcast commodity video stream of the live broadcast commodity basic information through the e-commerce live broadcast plug-in.
And a substep S1132, configuring the video transmission protection configuration information of each video transmission protection unit on the transmission control template of the corresponding transmission control node in the transmission control assembly, and then executing live video sharing of the commodity object.
In a possible implementation manner, for step S140, in the process of obtaining the push bias parameter according to the heat flow direction relationship, the detailed description below may specifically be implemented by using substeps as examples.
And a substep S141 of obtaining heat flow direction mutual information of the heat flow direction relationship, the heat flow direction mutual information including a plurality of mutual process information respectively corresponding to the plurality of heat flow direction circulation processes.
Substep S142, when confirming that a plurality of interactive process information that any one heat flow direction circulation process corresponds all satisfy preset propelling movement deviation condition, according to the interactive process information that the heat flow direction circulation process, and the propelling movement deviation scope of matching preset propelling movement deviation unit, confirm with the initial propelling movement deviation node of presetting the propelling movement deviation unit of presetting the first propelling movement deviation unit that preset propelling movement deviation condition matches, wherein, preset propelling movement deviation condition includes: the preset pushing deviation unit is larger than the set pushing deviation range.
And a substep S143, determining a plurality of preset push deviation units matched with the preset push deviation conditions to correspond to the initial push deviation nodes of the heat flow circulation process according to the interaction process information of the heat flow circulation process, the push deviation range of the preset push deviation unit, the initial push deviation nodes of the first preset push deviation unit and the push heat of the preset push deviation unit.
And a substep S144, if the position of the heat flow direction cycle process of the push deflection assembly corresponding to the heat flow direction cycle process in the heat flow direction cycle process is matched with the initial push deflection node of the interest point position change interval, and if the push deflection assembly is the first push deflection assembly of the interest point position change interval, acquiring the heat flow direction cycle process matched with the previous preset push deflection unit adjacent to the interest point position change interval as a screening heat flow direction cycle process, and identifying one heat flow direction cycle process of the screening heat flow direction cycle process in the push deflection assembly as a target heat flow direction cycle process matched with the interest point position change interval.
And a substep S145, if the push deviation component is not the first push deviation component of the interest point position change interval, acquiring a target heat flow direction circulation process matched with the interest point position change interval, identifying the target heat flow direction circulation process in the push deviation component, and identifying at least one active push deviation object of the target heat flow direction circulation process, wherein the heat flow direction circulation process corresponds to a plurality of preset push deviation units.
And a substep S146, in the preset pushing deviation unit, calculating the pushing deviation association degree of at least one active pushing deviation object in the target heat flow direction circulation process between any two adjacent pushing deviation assemblies in the preset pushing deviation unit and the feature vector of at least one active pushing deviation object in the target heat flow direction circulation process in the preset pushing deviation unit according to the pushing behavior mapping information of the at least one active pushing deviation object in the target heat flow direction circulation process in the plurality of pushing deviation assemblies.
And in the substep S147, counting the push deviation virtual key vectors of the preset push deviation units, and performing mapping association on the push deviation virtual key vectors of each matched preset push deviation unit to obtain push deviation parameters.
In a possible implementation manner, the live video sharing data stream may further include a link source object of the live commodity target, where the link source object may refer to a corresponding user accessing a providing source of the link.
For step S120, in the process of identifying the live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through the preset artificial intelligence model, the process may be specifically implemented through a sub-step exemplarily, and the detailed description is as follows.
And a substep S121, extracting the total attention heat corresponding to the live video sharing data stream through a preset artificial intelligence model.
And S122, identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located according to the total attention heat degree, and identifying a user push object corresponding to the live broadcast commodity target according to the live broadcast commodity recommendation area where the live broadcast commodity target is located.
On this basis, for step S140, in the process of generating the e-commerce information to be pushed to the e-commerce live broadcast terminal 200 based on the push bias parameter, the live broadcast item recommendation area where the live broadcast item target is located, and the link click object, specific exemplary implementation may be performed through substeps, which are described in detail below.
In the substep S148, first e-commerce information, second e-commerce information, and third e-commerce information respectively associated with the link source object, the user push object, and the link click object are obtained.
And a substep S149 of respectively screening the first electronic commerce information, the second electronic commerce information and the third electronic commerce information based on the push deviation parameter to obtain screened electronic commerce information.
And a substep S1495, selecting the screened electronic commerce information according to the live broadcast commodity recommendation area where the live broadcast commodity target is located.
Exemplarily, in the substep S122, initial association degrees of live broadcast commodity targets for each target push object may be respectively obtained according to live broadcast commodity recommendation areas where the live broadcast commodity targets are located, and then the target push object with the initial association degree having the highest numerical value is determined as the user push object corresponding to the live broadcast commodity target.
For example, local recommendation behavior feature degrees corresponding to a live broadcast commodity recommendation area where a live broadcast commodity target is located may be obtained from the total attention heat degree, and then initial association degrees of the live broadcast commodity target for each target push object are obtained according to the local recommendation behavior feature degrees.
In one possible implementation, the target push object may specifically include an active push object and a passive push object, and the attention degree may specifically include an active attention degree and a passive attention degree. The active push object may represent a user object actively subscribing to push, and the passive push object may represent a user object not actively subscribing to push. The active attention degree may refer to attention degree of the user object pushed for active subscription, and the passive attention degree may be attention degree of the pointer to the user object pushed for non-active subscription.
In step S120, in the process of obtaining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to the heat relationship information between the attention heat corresponding to the live broadcast commodity recommendation area in which the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data flow, the specific implementation may be exemplarily realized through sub-steps, which are described in detail below.
And S123, determining the initial association degree corresponding to the object pushed by the user as the object association degree corresponding to the live broadcast commodity recommendation area in which the live broadcast commodity target is located.
And a substep S124, determining the live broadcast commodity recommendation area with the user push object as the active object video sharing data stream.
And a substep S125, determining the live broadcast commodity recommendation area with the passive push object as the user push object as the passive object video sharing data stream.
And a substep S126, determining an active attention heat according to the object association degree corresponding to the active object video sharing data stream, and determining a passive attention heat according to the object association degree corresponding to the passive object video sharing data stream.
And a substep S127 of determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the active attention heat and the passive attention heat and the total attention heat.
In a possible implementation manner, the heat flow to node map may specifically include an active heat flow to node map and a passive heat flow to node map.
In the process of determining that the heat of the live broadcast commodity target in the live broadcast commodity recommendation area flows to the node map according to the heat relation information between the active attention heat and the passive attention heat and the total attention heat, the active heat flow to the node map can be determined according to the heat relation information between the active attention heat and the total attention heat. Meanwhile, the passive heat flow direction node map can be determined according to heat relation information between the passive attention heat and the total attention heat.
In one possible implementation manner, the hot flow direction node map of the hot spot e-commerce topic may include a forward hot spot e-commerce topic hot flow direction node map and a reverse hot spot e-commerce topic hot flow direction node map.
In the process of obtaining the heat flow direction relationship between the heat flow direction node map and the heat flow direction node map of the hot spot e-commerce topic, the active heat flow direction relationship may be determined according to the heat flow direction node map of the active heat flow direction node map and the forward hot spot e-commerce topic. Meanwhile, the passive heat flow direction relationship can be determined according to the heat flow direction node diagram of the passive heat flow direction node diagram and the heat flow direction node diagram of the reverse hot spot e-commerce topic. Thus, the active heat flow direction relationship and the passive heat flow direction relationship can be determined as the heat flow direction relationship.
Fig. 3 is a schematic diagram of functional modules of an artificial intelligence based e-commerce information pushing apparatus 300 according to an embodiment of the present disclosure, in this embodiment, the artificial intelligence based e-commerce information pushing apparatus 300 may be divided into the functional modules according to the method embodiment executed by the artificial intelligence cloud platform 100, that is, the following functional modules corresponding to the artificial intelligence based e-commerce information pushing apparatus 300 may be used to execute the method embodiments executed by the artificial intelligence cloud platform 100. The artificial intelligence based e-commerce information pushing apparatus 300 may include a first obtaining module 310, an identification determining module 320, a second obtaining module 330, and a generating module 340, wherein the functions of the functional modules of the artificial intelligence based e-commerce information pushing apparatus 300 are described in detail below.
The first obtaining module 310 is configured to obtain a live video sharing data stream including a live commodity target from the e-commerce live broadcast terminal 200, where the live video sharing data stream includes a link click object of the live commodity target. The first obtaining module 310 may be configured to perform the step S110, and for a detailed implementation of the first obtaining module 310, reference may be made to the detailed description of the step S110.
The identification determining module 320 is configured to identify a live broadcast commodity recommendation area where a live broadcast commodity target is located in a live broadcast video sharing data stream through a preset artificial intelligence model, and determine a heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between a heat of interest corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and a total heat of interest of the live broadcast video sharing data stream. The identification determination module 320 may be configured to perform the step S120, and as for a detailed implementation of the identification determination module 320, reference may be made to the detailed description of the step S120.
The second obtaining module 330 is configured to obtain a heat flow direction relationship between the heat flow direction node map and the heat flow direction node map of the hot e-commerce topic, where the heat flow direction node map of the hot e-commerce topic is a heat flow direction node map of a live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a local video sharing data stream of other live broadcast commodity information associated with the live broadcast commodity target indicated by all link click objects. The second obtaining module 330 may be configured to perform the step S130, and the detailed implementation of the second obtaining module 330 may refer to the detailed description of the step S130.
The generating module 340 is configured to obtain a push bias parameter according to the heat flow direction relationship, and generate the e-commerce information to be pushed to the e-commerce live broadcast terminal 200 based on the push bias parameter, the live broadcast commodity recommendation area where the live broadcast commodity target is located, and the link click object. The generating module 340 may be configured to execute the step S140, and the detailed implementation of the generating module 340 may refer to the detailed description of the step S140.
It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the first obtaining module 310 may be a separate processing element, or may be integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the functions of the first obtaining module 310. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).
Fig. 4 shows a hardware structure diagram of an artificial intelligence cloud platform 100 for implementing the control device, which is provided by the embodiment of the present disclosure, and as shown in fig. 4, the artificial intelligence cloud platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.
In a specific implementation process, at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120 (for example, the first obtaining module 310, the identification determining module 320, the second obtaining module 330, and the generating module 340 included in the artificial intelligence based e-commerce information pushing apparatus 300 shown in fig. 3), so that the processor 110 may execute the artificial intelligence based e-commerce information pushing method according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control a transceiving action of the transceiver 140, so as to transceive data with the foregoing e-commerce live broadcast terminal 200.
For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the artificial intelligence cloud platform 100, which implement principles and technical effects are similar, and this embodiment is not described herein again.
In the embodiment shown in fig. 4, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus 130 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus 130 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
In addition, the embodiment of the disclosure also provides a readable storage medium, in which computer execution instructions are stored, and when a processor executes the computer execution instructions, the method for pushing the electronic commerce information based on the artificial intelligence is implemented.
The readable storage medium described above may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.

Claims (6)

1. The electronic commerce information pushing method based on artificial intelligence is characterized by being applied to an artificial intelligence cloud platform, wherein the artificial intelligence cloud platform is in communication connection with a plurality of electronic commerce live broadcast terminals, and the method comprises the following steps:
acquiring a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal, wherein the live video sharing data stream comprises a link click object of the live commodity target;
identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model, and determining heat flow direction node diagrams of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between attention heat corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located and total attention heat of the live broadcast video sharing data stream;
acquiring a heat flow direction relationship between the heat flow direction node diagram and a heat flow direction node diagram of a hot e-commerce topic, wherein the heat flow direction node diagram of the hot e-commerce topic is a heat flow direction node diagram of the live broadcast commodity target in a target online live broadcast video sharing data stream, and the target online live broadcast video sharing data stream is a video sharing data stream in which other live broadcast commodity information associated with the live broadcast commodity target and indicated by all the link click objects are located;
obtaining a push deviation parameter according to the heat flow direction relation, and generating electronic commerce information pushed to the electronic commerce live broadcast terminal based on the push deviation parameter, a live broadcast commodity recommendation area where the live broadcast commodity target is located and the link click object;
the live video sharing data stream further comprises a link source object of the live commodity target;
the identifying of the live broadcast commodity recommendation area where the live broadcast commodity target is located in the live broadcast video sharing data stream through a preset artificial intelligence model comprises the following steps:
extracting the total attention heat corresponding to the live video sharing data stream through the preset artificial intelligence model;
identifying a live broadcast commodity recommendation area where the live broadcast commodity target is located according to the total attention heat, and identifying a user push object corresponding to the live broadcast commodity target according to the live broadcast commodity recommendation area where the live broadcast commodity target is located;
the step of identifying a user push object corresponding to the live broadcast commodity target according to the live broadcast commodity recommendation area in which the live broadcast commodity target is located comprises the following steps:
respectively acquiring initial association degrees of the live broadcast commodity targets aiming at each target push object according to the live broadcast commodity recommendation area in which the live broadcast commodity target is located;
determining a target push object with the highest numerical value of initial association degree as the user push object corresponding to the live broadcast commodity target;
the target push objects comprise active push objects and passive push objects, and the attention heat comprises active attention heat and passive attention heat;
the step of obtaining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to the heat relation information between the attention heat corresponding to the live broadcast commodity recommendation area in which the live broadcast commodity target is located and the total attention heat of the live broadcast video sharing data flow includes:
determining the initial association degree corresponding to the object pushed by the user as the object association degree corresponding to the live broadcast commodity recommendation area where the live broadcast commodity target is located;
determining the user pushing object as a live broadcast commodity recommending area of the active pushing object as an active object video sharing data stream;
determining the user push object as a live broadcast commodity recommendation area of the passive push object as a passive object video sharing data stream;
determining the active attention heat according to the object association degree corresponding to the active object video sharing data stream, and determining the passive attention heat according to the object association degree corresponding to the passive object video sharing data stream;
determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to heat relation information between the active attention heat and the passive attention heat and the total attention heat;
the heat flow direction node diagram comprises an active heat flow direction node diagram and a passive heat flow direction node diagram;
the step of determining the heat flow direction node diagram of the live broadcast commodity target in the live broadcast commodity recommendation area according to the heat relation information between the active attention heat and the passive attention heat and the total attention heat respectively comprises the following steps:
determining the active heat flow to a node map according to heat relation information between the active attention heat and the total attention heat;
determining that the passive heat flows to a node map according to heat relation information between the passive attention heat and the total attention heat;
the hot degree flow direction node diagram of the hot spot e-commerce topic comprises a forward hot spot e-commerce topic hot degree flow direction node diagram and a reverse hot spot e-commerce topic hot degree flow direction node diagram;
the step of obtaining a heat flow direction relationship between the heat flow direction node map and the heat flow direction node map of the hot spot e-commerce topic comprises the following steps:
determining the active heat flow direction relation according to the active heat flow direction node diagram and the heat flow direction node diagram of the forward hot spot e-commerce topic;
determining a passive heat flow direction relation according to the passive heat flow direction node diagram and the heat flow direction node diagram of the reverse hot spot e-commerce topic;
and determining the active heat flow direction relation and the passive heat flow direction relation as the heat flow direction relation.
2. The method as claimed in claim 1, wherein the step of obtaining a push bias parameter according to the heat flow direction relationship comprises:
acquiring heat flow direction interactive information of the heat flow direction relation, wherein the heat flow direction interactive information comprises a plurality of interactive process information respectively corresponding to a plurality of heat flow direction circulating processes;
when confirming that a plurality of mutual process information that any one heat flow direction circulation process corresponds all satisfy and predetermine propelling movement erroneous tendency condition, according to the mutual process information of heat flow direction circulation process with match the propelling movement deviation scope of predetermineeing propelling movement deviation unit, confirm with predetermine the initial propelling movement deviation node of the first propelling movement deviation unit of predetermineeing that propelling movement deviation condition matches, wherein, predetermine propelling movement deviation condition and include: the preset pushing deviation unit is larger than the set pushing deviation range;
determining a plurality of preset push deflection units matched with the preset push deflection conditions to correspond to the initial push deflection nodes of the heat flow circulation process according to the interactive process information of the heat flow circulation process, the push deflection range of the preset push deflection units, the initial push deflection nodes of the first preset push deflection unit and the push heat of the preset push deflection units;
if the position of a heat flow direction circulation process of a push deflection assembly corresponding to the heat flow direction circulation process in the heat flow direction circulation process is matched with the initial push deflection node of the interest point position change section, and if the push deflection assembly is the first push deflection assembly of the interest point position change section, acquiring a heat flow direction circulation process matched with a previous preset push deflection unit adjacent to the interest point position change section as a screening heat flow direction circulation process, and identifying one heat flow direction circulation process of the screening heat flow direction circulation process in the push deflection assembly as a target heat flow direction circulation process matched with the interest point position change section;
if the push deviation component is not the first push deviation component of the interest point position change interval, acquiring a target heat flow direction circulation process matched with the interest point position change interval, identifying the target heat flow direction circulation process in the push deviation component, and identifying at least one active push deviation object of the target heat flow direction circulation process, wherein the heat flow direction circulation process corresponds to a plurality of preset push deviation units;
in the preset push deviation unit, calculating the push deviation association degree of at least one active push deviation object in the target heat flow direction circulation process between any two adjacent push deviation assemblies in the preset push deviation unit and the feature vector of at least one active push deviation object in the target heat flow direction circulation process in the preset push deviation unit according to the push behavior mapping information of the at least one active push deviation object in the plurality of push deviation assemblies in the target heat flow direction circulation process;
and counting the pushing deviation virtual key vectors of the preset pushing deviation units, and mapping and associating the pushing deviation virtual key vectors of each matched preset pushing deviation unit to obtain pushing deviation parameters.
3. The method for pushing e-commerce information based on artificial intelligence as claimed in claim 1, wherein the step of generating e-commerce information to be pushed to the e-commerce live broadcast terminal based on the push bias parameter, a live broadcast merchandise recommendation area where the live broadcast merchandise target is located, and the link click object includes:
acquiring first e-commerce information, second e-commerce information and third e-commerce information which are respectively associated with the link source object, the user push object and the link click object;
screening the first electronic commerce information, the second electronic commerce information and the third electronic commerce information respectively based on the push deviation parameter to obtain screened electronic commerce information;
and the screened e-commerce information is subjected to e-commerce according to the live broadcast commodity recommendation area where the live broadcast commodity target is located.
4. The method for pushing e-commerce information based on artificial intelligence as claimed in claim 1, wherein the step of respectively obtaining the initial association degree of the live commodity target for each target pushing object according to the live commodity recommendation area where the live commodity target is located includes:
acquiring local recommendation behavior feature degrees corresponding to a live broadcast commodity recommendation area where the live broadcast commodity target is located from the total attention heat degree;
and acquiring initial association degrees of the live broadcast commodity targets aiming at each target push object respectively according to the local recommended behavior feature degrees.
5. The artificial intelligence based e-commerce information pushing method as claimed in any one of claims 1 to 4, wherein the step of obtaining a live video sharing data stream containing a live commodity target from the e-commerce live broadcast terminal includes:
after acquiring basic live broadcast commodity information corresponding to a live broadcast commodity target needing commodity object live broadcast video sharing from an e-commerce live broadcast request, determining network security label information matched with the basic live broadcast commodity information, and generating corresponding video transmission protection information according to the network security label information and network security big data information corresponding to the network security label information;
the video transmission protection information is related to a transmission control assembly of a video transmission channel of a live broadcast commodity video stream of the basic information of the live broadcast commodity through an electronic commerce live broadcast plug-in, and after the transmission control assembly is configured according to the video transmission protection information, commodity object live broadcast video sharing is executed;
carrying out corresponding video transmission protection operation on the electronic commerce live broadcast terminal through the transmission control component in a commodity object live broadcast video sharing process, wherein in the video transmission protection operation process, updating and configuring the transmission control component through the video transmission channel continuously according to the obtained video transmission protection information;
and acquiring a live broadcast video sharing data stream containing a live broadcast commodity target from the electronic commerce live broadcast terminal in the commodity object live broadcast video sharing process.
6. An artificial intelligence cloud platform, comprising a processor, a machine-readable storage medium and a network interface, wherein the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one e-commerce live broadcast terminal, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium to execute the artificial intelligence based e-commerce information pushing method of any one of claims 1 to 5.
CN202010363668.8A 2020-04-30 2020-04-30 Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform Active CN111556330B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202011147721.7A CN112333457A (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method and information pushing system based on artificial intelligence
CN202010363668.8A CN111556330B (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform
CN202011149624.1A CN112291578A (en) 2020-04-30 2020-04-30 Artificial intelligence-based e-commerce information pushing method and system and cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010363668.8A CN111556330B (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform

Related Child Applications (2)

Application Number Title Priority Date Filing Date
CN202011147721.7A Division CN112333457A (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method and information pushing system based on artificial intelligence
CN202011149624.1A Division CN112291578A (en) 2020-04-30 2020-04-30 Artificial intelligence-based e-commerce information pushing method and system and cloud platform

Publications (2)

Publication Number Publication Date
CN111556330A CN111556330A (en) 2020-08-18
CN111556330B true CN111556330B (en) 2021-01-05

Family

ID=72002641

Family Applications (3)

Application Number Title Priority Date Filing Date
CN202011147721.7A Withdrawn CN112333457A (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method and information pushing system based on artificial intelligence
CN202010363668.8A Active CN111556330B (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform
CN202011149624.1A Withdrawn CN112291578A (en) 2020-04-30 2020-04-30 Artificial intelligence-based e-commerce information pushing method and system and cloud platform

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN202011147721.7A Withdrawn CN112333457A (en) 2020-04-30 2020-04-30 Electronic commerce information pushing method and information pushing system based on artificial intelligence

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN202011149624.1A Withdrawn CN112291578A (en) 2020-04-30 2020-04-30 Artificial intelligence-based e-commerce information pushing method and system and cloud platform

Country Status (1)

Country Link
CN (3) CN112333457A (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113327154B (en) * 2021-06-18 2022-05-13 苏州极易科技股份有限公司 E-commerce user message pushing method and system based on big data
CN113645474A (en) * 2021-07-26 2021-11-12 阿里巴巴（中国）有限公司 Interactive information processing method, interactive information display method and electronic equipment
CN116527967B (en) * 2023-06-29 2023-08-29 北京优贝在线网络科技有限公司 Live broadcast system with information recommendation function

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102955805A (en) * 2011-08-24 2013-03-06 阿里巴巴集团控股有限公司 Method and system for processing recommendation data of website information
CN103501464A (en) * 2013-09-24 2014-01-08 深圳市同洲电子股份有限公司 Method, terminal, server and system for pushing advertisement
CN104732413A (en) * 2013-12-20 2015-06-24 中国科学院声学研究所 Intelligent individuation video advertisement pushing method and system
CN105721905A (en) * 2016-02-02 2016-06-29 林蔚 Advertisement pushing method based on video tag
CN106651496A (en) * 2016-09-21 2017-05-10 唐艳春 Video social network shopping platform
CN107657004A (en) * 2017-09-21 2018-02-02 广州华多网络科技有限公司 Video recommendation method, system and equipment
CN109446419A (en) * 2018-10-17 2019-03-08 武汉斗鱼网络科技有限公司 A kind of method and device for recommending video

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102955805A (en) * 2011-08-24 2013-03-06 阿里巴巴集团控股有限公司 Method and system for processing recommendation data of website information
CN103501464A (en) * 2013-09-24 2014-01-08 深圳市同洲电子股份有限公司 Method, terminal, server and system for pushing advertisement
CN104732413A (en) * 2013-12-20 2015-06-24 中国科学院声学研究所 Intelligent individuation video advertisement pushing method and system
CN105721905A (en) * 2016-02-02 2016-06-29 林蔚 Advertisement pushing method based on video tag
CN106651496A (en) * 2016-09-21 2017-05-10 唐艳春 Video social network shopping platform
CN107657004A (en) * 2017-09-21 2018-02-02 广州华多网络科技有限公司 Video recommendation method, system and equipment
CN109446419A (en) * 2018-10-17 2019-03-08 武汉斗鱼网络科技有限公司 A kind of method and device for recommending video

Also Published As

Publication number Publication date
CN112291578A (en) 2021-01-29
CN111556330A (en) 2020-08-18
CN112333457A (en) 2021-02-05

Similar Documents

Publication Publication Date Title
CN111556330B (en) Electronic commerce information pushing method based on artificial intelligence and artificial intelligence cloud platform
CN111626817B (en) User portrait analysis method based on electronic commerce big data and artificial intelligence platform
KR101972285B1 (en) Image evaluation
CN110648185A (en) Target crowd circling method and device and computer equipment
CN111626816B (en) Image interaction information processing method based on e-commerce live broadcast and cloud computing platform
US20140365305A1 (en) Providing geospatial-temporal next-best-action decisions
CN111586477B (en) E-commerce live broadcast processing method based on big data and network security live broadcast platform
CN111611581B (en) Internet of things-based network big data information anti-disclosure method and cloud communication server
CN111444422A (en) Logistics information recommendation method and device, logistics distribution system and server
CN111476595A (en) Product pushing method and device, computer equipment and storage medium
CN113225580B (en) Live broadcast data processing method and device, electronic equipment and medium
CN112116434B (en) Commodity searching method and system based on big data and electronic mall and cloud service platform
CN111723000A (en) Test method, test device, electronic equipment and storage medium
CN111429148A (en) Evaluation interface entering method and device
CN117422553A (en) Transaction processing method, device, equipment, medium and product of blockchain network
CN112966066A (en) Information generation method and system based on block chain and financial subscription and service center
CN112308648A (en) Information processing method and device
CN113869982A (en) Product recommendation system
CN113420220B (en) Service recommendation method and device, server and terminal
CN116229216A (en) Virtual clothes changing method, device, computer equipment and storage medium
CN116010682A (en) Data query method and device, equipment, medium and product thereof
CN117541106A (en) Object processing method, rule configuration method and computing device
Elgomati et al. A Simple Secured One-Click Approval Method for A Single or Multi Systems
CN117575803A (en) Object recommendation method and device, electronic equipment and storage medium
CN117633017A (en) Data processing method, system, equipment and 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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: Room 607, building 7, Yunnan returnee Pioneer Park, information industry base, economic development zone, Kunming City, Yunnan Province

Applicant after: Xu Zhou

Address before: Room 206, building 3, hi tech Pioneer Park, No. 288, Changjiang West Road, hi tech Zone, Hai'an City, Nantong City, Jiangsu Province

Applicant before: Xu Zhou

TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20201215

Address after: Group 2, Guanyintang community, Ganhe office, Xiantao City, Hubei Province 433000

Applicant after: Zhao Yongkui

Address before: Room 607, building 7, Yunnan returnee Pioneer Park, information industry base, economic development zone, Kunming City, Yunnan Province

Applicant before: Xu Zhou

GR01 Patent grant
GR01 Patent grant