CN113507626A

CN113507626A - Commodity association method, device and equipment in video interaction

Info

Publication number: CN113507626A
Application number: CN202110418883.8A
Authority: CN
Inventors: 贺三元; 汪亮
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-04-19
Filing date: 2021-04-19
Publication date: 2021-10-15

Abstract

The embodiment of the specification discloses a commodity association method, a commodity association device and commodity association equipment in video interaction. The scheme comprises the following steps: determining interactive information sent by a user aiming at a display video, and extracting key information from the interactive information; determining keywords hit by the key information in a pre-established commodity keyword library through intention identification; performing image recognition on a frame image in the display video, determining an object corresponding to the keyword in the frame image, and extracting image information of the object; and searching corresponding commodities according to the image information, and displaying the purchase guide information of the searched commodities in a viewing interface of the user.

Description

Commodity association method, device and equipment in video interaction

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method, an apparatus, and a device for associating commodities in video interaction.

Background

With the development of science and technology, people gradually start shopping through networks. In order to effectively promote the commodities, the merchants and the platforms can promote the commodities in a video introduction mode in a network.

The user may ask about how to sell the related objects in the live broadcast scene in the process of watching the video, and if the interactive information provided by the user can be fed back in time, the transaction can be prompted with a high probability, so that the requirements of the user are met, and the benefits of merchants and platforms are also improved.

However, the interactive information cannot be fed back in real time, for example, when there is a lot of interactive information, it is difficult to feed back each piece of interactive information. Alternatively, although an object that the user wants to purchase appears in the live broadcast room, the object is not a product that is sold in the video advertisement, and it is difficult to quickly feed back the object.

Based on this, there is also a need for a merchandise association scheme in video interaction that can be more efficient.

Disclosure of Invention

One or more embodiments of the present specification provide a method, an apparatus, a device, and a storage medium for associating commodities in video interaction, so as to solve the following technical problems: there is a need for a merchandise association scheme in a video interaction that can be more efficient.

To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:

one or more embodiments of the present specification provide a method for associating commodities in video interaction, including:

determining interactive information sent by a user aiming at a display video, and extracting key information from the interactive information;

determining keywords hit by the key information in a pre-established commodity keyword library through intention identification;

performing image recognition on a frame image in the display video, determining an object corresponding to the keyword in the frame image, and extracting image information of the object;

and searching corresponding commodities according to the image information, and displaying the purchase guide information of the searched commodities in a viewing interface of the user.

One or more embodiments of the present specification provide a commodity association apparatus in video interaction, including:

the keyword extraction module is used for determining interactive information sent by a user aiming at the display video and extracting key information from the interactive information;

the intention identification module is used for determining keywords hit by the key information in a pre-established commodity keyword library through intention identification;

the image information extraction module is used for carrying out image recognition on a frame image in the display video, determining an object corresponding to the keyword in the frame image and extracting the image information of the object;

and the guiding information display module is used for searching corresponding commodities according to the image information and displaying the purchasing guiding information of the searched commodities in the viewing interface of the user.

One or more embodiments of the present specification provide a commodity association device in video interaction, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

One or more embodiments of the present specification provide a non-transitory computer storage medium storing computer-executable instructions configured to:

At least one technical scheme adopted by one or more embodiments of the specification can achieve the following beneficial effects: by analyzing key information in the interactive information sent by the user and displaying corresponding guide information to the user according to an analysis result, even if the object is not a commodity sold by an anchor, the related requirements of the user on the object in the display video can be quickly met, high-efficiency video interaction is realized, the commodity sale possibility is improved, and the win-win result of the anchor, the user and a merchant is achieved. And the object in the frame image is subjected to image recognition through the keywords, so that the commodity of the displayed guide information is ensured to be the object seen by the user.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic flowchart of a method for associating commodities in video interaction according to one or more embodiments of the present disclosure;

FIG. 2 is a schematic diagram of guidance information presented in a viewing interface provided in one or more embodiments of the present description;

fig. 3 is a detailed flowchart of the method in fig. 1 in an application scenario provided in one or more embodiments of the present disclosure;

fig. 4 is a schematic structural diagram of a product association apparatus in video interaction according to one or more embodiments of the present disclosure;

fig. 5 is a schematic structural diagram of a product association device in video interaction according to one or more embodiments of the present specification.

Detailed Description

The embodiment of the specification provides a commodity association method, a commodity association device, commodity association equipment and a storage medium in video interaction.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.

In one or more embodiments of the present specification, a commodity association scheme in video interaction is devised. Firstly, extracting key information from interactive information sent by a user in a display video, and then determining hit keywords in a commodity keyword library according to the key information. And then, extracting image information of a corresponding object from the frame image according to the keyword, finally determining the guide information of the corresponding commodity according to the image information and displaying the guide information to a user, thereby achieving the effect of commodity association in high-efficiency video interaction.

The following is a detailed description based on such a concept.

Fig. 1 is a flowchart illustrating a method for associating a commodity in video interaction according to one or more embodiments of the present disclosure. The method can be applied to different business fields, such as the field of e-commerce business (live broadcast and goods delivery of e-commerce platforms), the field of internet financial business, the field of instant messaging business, the field of game business, the field of official business and the like. The process can be executed by computing equipment in the corresponding field (for example, a wind control server or an intelligent mobile terminal corresponding to the payment service, and the like), and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve the accuracy.

The process in fig. 1 may include the following steps:

s102: determining interactive information sent by a user aiming at a display video, and extracting key information from the interactive information.

In one or more embodiments of the present description, a presentation video refers to a video made for the purpose of advertising a commodity, for the purpose of presentation to the public or a specific group of people. The user can watch the display video on a client (the client on various terminals including a mobile terminal, a PC terminal and the like) through a network. The display video comprises the forms of live network, non-real-time video (such as video which is recorded) and the like when being played.

During the process of watching the display video, the user interacts with an author of the display video (usually in a non-real-time video) or a host in the display video for selling goods (usually in a live webcast) by sending interactive information (for example, expressing the purchase intention of a certain object or expressing the value of a certain goods as an opinion). The interactive information may have various forms, for example, sending text comments in the display video, sending a barrage, sending a corresponding virtual gift (after sending the corresponding virtual gift, the user has corresponding rights, and may trigger a certain position in the viewing interface in various forms to indicate that the user has a desire to purchase an object at the position), and collecting praise for the display video.

The interactive information indicates the user's desire to initiate an interaction, but not all interactive information gets timely feedback from the anchor or author. For network live broadcast, when the quantity of interactive information is particularly large, the anchor is difficult to feed back the interactive information in time; for non-real-time videos, after the user provides the interactive information, the anchor or the author is difficult to feed back in time, and the feedback can only be performed through channels such as private letters or comments, so that the timeliness is difficult to guarantee.

The user's desire to purchase an object is often time-sensitive, and after a period of time has elapsed, the user may forget or otherwise not want to purchase the object, which is a loss to both the user and the merchant. Based on the above, for the interactive information sent by the user, especially the interactive information which is difficult to obtain feedback in time, the key information in the interactive information is extracted. If the interactive information is the text contents such as comments, barrage and the like, the extracted key information can be corresponding keywords. If the interactive information is an operation such as clicking performed by the user, the extracted key information may be information such as a position and a mode triggered by the user in the viewing interface. If the interactive information is the operation of collection approval and the like, the extracted key information can be information of the anchor, the sold commodities and the like in the display video.

S104: and determining the keywords hit by the key information in a pre-established commodity keyword library through intention identification.

If the key information is information such as a clicked position, the intention of the user is identified according to a mode triggered by the user, for example, if the user clicks, it indicates that the user has a lower purchase intention or other intention for an object at the clicked position, and if the user clicks continuously for multiple times, it indicates that the user has a stronger purchase intention or other intention for the object. At this time, the hit keyword may include the name of the object.

If the key information is behaviors such as praise collection of the user and the user approves other display videos of the main broadcasting which collects the display videos, the behavior can be obtained through intention identification, and the praise collection behavior of the user at this time is probably based on the favor of the main broadcasting. At this time, the hit keyword may be an object related to the anchor, such as a brand worn by the anchor, a brand of cosmetics used, a brand of a representative, and the like.

And if the key information is the extracted key words, identifying and identifying the content which the user actually wants to express through text intention.

Specifically, if the extracted keyword directly includes a content that the user actually wants to express, for example, the comment information sent by the user is that "fruit knives held by the anchor are good" and the extracted key information is "fruit knives", the keyword "fruit knives" can be easily hit in the commodity keyword library.

If the extracted keywords are not directly included, but the user expresses the content that the user actually wants to express in a specific scene or thought by other expression modes (for example, omitting part of words or changing description modes) (in this case, the association between the associated information and the keywords is referred to as an explicit association), when the keywords are hit, it is also difficult to hit the corresponding keywords in the product keyword library. For example, the comment information sent by the user is "good-looking to wear on the anchor", the extracted key information may be "to wear", and the final hit keyword may be "clothing".

There is also a case where a user sends comment information unconsciously or intentionally while hiding the content that the user actually wants to express, due to his or her own habits or some objective reasons, and at this time, it is difficult to hit the corresponding keyword in the keyword library (in this case, the association between the association information and the keyword is referred to as implicit association), and it is necessary to perform more recent intention recognition by a correlation algorithm or a training model when the keyword is hit.

Specifically, in the current display video, a good comment return activity is being performed, and based on this, the user intentionally hides a real idea that the user does not like the product, and sends good comment information about the product.

Alternatively, the user may intentionally use a word that seems dissatisfactory for the purpose of following the wind, entertainment, etc., to indicate his or her own thoughts of satisfaction. For example, the user is satisfied with the clothing being sold by the anchor, and inputs the interactive information "for the clothing sold by the anchor, i can say only one sentence without tolerance and the sale is very good", at this time, if the extracted key information is the words "clothing", "live the sentence", and "too much", the user may be considered to be uninterested in the clothing, and finally, the keyword related to the clothing is not hit. But in practice the user is of satisfactory interest for the piece of clothing and should hit keywords related to the piece of clothing.

Or, in the current display video, if the user sends interaction information for almost every commodity sold by the anchor program, the real idea of the user is likely to be unconsciously hoped to interact with other users or the anchor program instead of having a purchase intention for every commodity, and at this time, the hit keyword may be a coupon of a friend making platform or a chat platform.

For both explicit and implicit associations, corresponding recognition models can be trained in advance to determine the true intention of the user to assist in hitting keywords.

S106: and carrying out image recognition on the frame image in the display video, determining the object corresponding to the keyword in the frame image, and extracting the image information of the object.

For the keywords that are partially hit, for example, "coupon of friend-making platform or chat platform", "brand of main broadcasting agent", etc. that have been mentioned in the above embodiments, it is difficult to identify the corresponding object in the frame image, that is, it is difficult to extract the corresponding image information. At this time, the corresponding object may not be extracted from the frame image, but the corresponding product may be directly searched for by the keyword.

In one or more embodiments of the present specification, when the video is presented as a live video, the anchor typically sells some goods during the live video, and presents the related guidance information (such as a purchase link, a detail page of the goods, etc.) of the goods in the viewing interface of the user without continuously searching for the guidance information of the goods. If the object is determined not to be a commodity sold in the live video, the anchor may have difficulty in feeding back the user, and at this time, the image information of the object may be continuously extracted, so as to continuously search for corresponding guide information. For example, if the product sold by the anchor at this time is fruit and the fruit knife is being used to cut the fruit, and the comment information sent by the user is that the fruit knife held by the anchor looks good, it may be difficult for the anchor to feed back the information related to the object, that is, the fruit knife, to the user.

S108: and searching corresponding commodities according to the image information, and displaying the purchase guide information of the searched commodities in a viewing interface of the user.

If the corresponding image information is extracted, the corresponding commodity is directly searched according to the image information, and the finally searched commodity can be guaranteed to be the commodity which is seen by the user in the display video and is interested by the user. And if the corresponding image information is not extracted, searching the corresponding commodity according to the keyword. Of course, if the same item is not found (for example, the item is an item of non-selling nature that is created manually by the owner, or the item is not put on shelf), an approximate item may be searched for instead.

The guidance information is to guide the user to obtain more information about the content related to the commodity, and if the user has a strong interest in the commodity, the user may further view the related content or perform related operations on the commodity by triggering the guidance information. The guiding information includes various forms, for example, the guiding information is a purchase link, a detail introduction page and the like of the commodity, and the user adds the commodity into a shopping cart or enters a payment interface of the commodity after clicking the purchase link. And when the commodity is described in more detail in other display videos, the guide information can also be a link entry of other display videos. Or when the commodity has been off-shelf or out-of-edition, the guide information may be a prompt for the situation. Fig. 2 is a schematic diagram of displaying guidance information in a viewing interface according to one or more embodiments of the present disclosure, and as shown in the drawing, guidance information is displayed below the user viewing interface, so as to reduce the obstruction of the guidance information to the anchor and the merchandise in the viewing interface.

In one or more embodiments of the present disclosure, some users do not participate in the related interaction, but do not represent that they do not have a demand for goods, and if the users are presented with the corresponding guidance information only through their own interaction information, the demands of the users cannot be met. Based on this, first, each commodity found according to the interaction information sent by different users (usually, most or all users watching the video displayed this time) is determined, then, a commodity (herein, referred to as a first commodity) whose occurrence frequency is higher than a first preset threshold is determined among the commodities, and first guidance information corresponding to the first commodity is determined.

Since the first commodity is a commodity that is more interested among different users, even for a first user who has not issued interactive information related to the first commodity, there is a high possibility that the first commodity will be interested in. Based on the above, the guiding information corresponding to the first commodity is displayed in the viewing interface of the first user. Of course, other users who have sent relevant comment information can still be exposed.

When the first user uses the mobile terminal, it is difficult to display all the first guide information when the number of the first products is large due to the limitation of the size of the screen of the mobile terminal. Therefore, the maximum number of clients on the mobile side that can simultaneously present guidance information is first determined. And then, displaying the part of the first guide information with the highest frequency of appearance in the viewing interface of the first user in all the first guide information. The corresponding maximum number may be different for different operating systems, different client versions.

Fig. 3 is a detailed flowchart of the method in fig. 1 in an application scenario provided in one or more embodiments of the present disclosure. As shown in fig. 3, a trusted goods repository is established in the goods server. And after the user watches the display video through the client and sends the interactive information, the server extracts the key information from the interactive information and determines the hit key words in the commodity server. After the corresponding object is identified in the frame image according to the keyword, extracting image information, searching the corresponding commodity in a commodity server according to the image information, returning a purchase link of the commodity by the commodity server, returning the purchase link to the client by the server, and displaying the purchase link in a viewing interface of a user.

Further, the first commodity with high frequency is determined, corresponding commodity information is inquired in the commodity server, and a purchase link of the returned first commodity is received. After determining the maximum number of simultaneous presentations, presenting purchase links for the maximum number of first items in the clients of all users.

In one or more embodiments of the present disclosure, it has been mentioned above that displaying the first guidance information in the viewing interface of the first user may increase the attention of the first user to the first merchandise appearing with high frequency. However, not all of the first users may be interested in the first merchandise, and if the first guidance information is displayed for all of the first users, a poor viewing experience may be generated for some of the first users.

Based on this, the times of sending the interactive information in the present display video by each first user are determined, and the more the times of sending the interactive information are, the higher the activity of the first user is, and the more the first user is willing to obtain the first guide information. And selecting a user (referred to as a second user herein) with the activity higher than a second preset threshold from the first user, and displaying the first guide information in a viewing interface of the second user.

Further, even for the second user, who is willing to obtain the first guiding information, if the first guiding information is presented in a direct presentation manner, the viewing experience of the second user may still be negatively impressed.

Therefore, after determining at least a part of the first commodity needing to display the guiding information, rendering image information corresponding to the at least a part of the first commodity in a viewing interface of the second user, and displaying the image information in the viewing interface in a highlighting mode. For example, adding a corresponding special effect at the edge of the image information, changing the brightness contrast of the image information, etc. At the moment, the rendered first commodity is easily found in the watching interface of the second user, the problem of poor watching experience of the user due to the fact that the first guide information pops up is solved, and interestingness of the user in watching is increased. If the second user wants to further obtain the first guiding information, the rendered image information may be triggered in the viewing interface (for example, the image information is clicked or pressed for a long time), and at this time, the first guiding information of the first commodity corresponding to the image information may be displayed to the second user.

In one or more embodiments of the present specification, during a process of watching a live video, if a user is interested in a certain object, the user may input related interactive information in a text input manner. In this case, the current frame image is usually subjected to image recognition to determine the corresponding object. However, if an event such as the anchor rotating the camera or moving the relevant object out of the lens occurs during the time when the user edits the interactive information, it is easy to cause that the object does not exist in the current frame image after the user edits the interactive information.

Based on this, if the object corresponding to the keyword is not identified in the current frame image, the duration range required by the user to input the interactive information is estimated according to the attributes of the interactive information input by the user (such as the length of characters in the interactive information, the number of uncommon characters, and the like), and then image identification is performed in the corresponding frame image before the estimated duration range to determine the object corresponding to the keyword. Generally, the longer the character is, the more the rare word is, and the longer the time range is. Of course, the time when the user opens the input panel may be recorded, and the image recognition may be performed in the frame image corresponding to the time, so that the time when the user starts to input the interactive information may be determined more accurately, but more data storage may be added, and the scheme in this embodiment may be adopted based on actual requirements.

Based on the same idea, one or more embodiments of the present specification further provide apparatuses and devices corresponding to the above-described method, as shown in fig. 4 and 5.

Fig. 4 is a schematic structural diagram of a product association apparatus in video interaction according to one or more embodiments of the present specification, where a dashed box in the diagram indicates an optional module, and the apparatus includes:

the keyword extraction module 402 is used for determining interactive information sent by a user aiming at a display video and extracting key information from the interactive information;

an intention identifying module 404, which determines keywords hit by the key information in a pre-established commodity keyword library through intention identification;

an image information extraction module 406, configured to perform image recognition on a frame image in the display video, determine an object corresponding to the keyword in the frame image, and extract image information of the object;

the guidance information display module 408 searches for a corresponding commodity according to the image information, and displays the purchase guidance information of the searched commodity in the viewing interface of the user.

Optionally, a high-frequency merchandise display module 410 is further included, and the high-frequency merchandise display module includes a first merchandise determination sub-module 4102, a first guidance information obtaining sub-module 4104, and a first guidance information display sub-module 4106;

the first commodity determining sub-module 4102 is configured to determine a plurality of first commodities, which are found according to the interaction information sent by different users and have the occurrence frequency higher than a first preset threshold;

the first guidance information obtaining sub-module 4104 is configured to obtain first guidance information corresponding to each of the plurality of first commodities;

the first guiding information displaying sub-module 4106 is configured to display at least part of the first guiding information in a viewing interface of a first user, where the first user includes a user who does not send the interaction information related to the first commodity.

Optionally, the first guidance information presenting sub-module 4106 determines a maximum number of the first guidance information that can be presented simultaneously in the mobile terminal used by the first user;

and selecting part of the first guide information with the highest frequency of occurrence from the first guide information, and displaying the part of the first guide information in the viewing interface of the first user.

Optionally, the presentation video comprises a live video; the apparatus further includes a non-offering item determination module 412;

and the non-sold commodity determining module is used for determining that the corresponding object does not belong to the commodity sold in the live video.

Optionally, the presentation video comprises a live video; the image information extraction module 406 is configured to perform image recognition on a current frame image of the live video;

if the object corresponding to the keyword is not identified, estimating a duration range required by the user for inputting the interactive information according to the attribute of the character in the interactive information;

and performing image recognition in a corresponding frame image before the estimated duration range, and determining an object corresponding to the keyword in the frame image.

Optionally, the first guidance information displaying sub-module 4106 determines, according to the number of times of the interaction information sent by each first user, the activity degrees corresponding to the first users, and determines, from the first users, a second user whose activity degree is higher than a second preset threshold;

rendering image information corresponding to at least part of the first commodities in a viewing interface of the second user;

and if the second user triggers the rendered image information in the viewing interface, displaying the first guide information of the first commodity corresponding to the rendered image information to the second user.

Fig. 5 is a schematic structural diagram of a product association device in video interaction according to one or more embodiments of the present specification, where the device includes:

at least one processor; and the number of the first and second groups,

The processor and the memory may communicate via a bus, and the device may further include an input/output interface for communicating with other devices.

Based on the same idea, one or more embodiments of the present specification further provide a non-volatile computer storage medium corresponding to the above method, and storing computer-executable instructions configured to:

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A commodity association method in video interaction comprises the following steps:

2. The method of claim 1, after the corresponding merchandise is located according to the image information, the method further comprising:

determining a plurality of first commodities which are found out according to the interaction information sent by different users and have the occurrence frequency higher than a first preset threshold value;

acquiring first guide information corresponding to the first commodities respectively;

displaying at least part of the first guiding information in a viewing interface of a first user, wherein the first user comprises a user who does not send the interaction information related to the first commodity.

3. The method of claim 2, wherein displaying at least a portion of the first guidance information in a viewing interface of the first user specifically comprises:

determining the maximum number of the first guide information which can be simultaneously displayed in a mobile terminal used by a first user;

4. The method of claim 1, the presentation video comprising a live video;

after determining the corresponding object of the keyword in the frame image, the method further includes:

and determining that the corresponding object does not belong to the commodity sold in the live video.

5. The method of claim 1, the presentation video comprising a live video;

the image recognition of the frame image in the display video and the determination of the object corresponding to the keyword in the frame image specifically include:

carrying out image recognition on a current frame image of the live video;

6. The method of claim 2, wherein displaying at least a portion of the first guidance information in a viewing interface of the first user specifically comprises:

determining the activity degrees corresponding to the first users respectively according to the times of the interactive information respectively sent by the first users, and determining a second user with the activity degree higher than a second preset threshold value in the first users;

7. A merchandise association apparatus in video interaction, comprising:

8. The apparatus of claim 7, further comprising a high frequency goods presentation module comprising a first goods determination sub-module, a first guide information acquisition sub-module, a first guide information presentation sub-module;

the first commodity determining submodule determines a plurality of first commodities which are found out according to the interaction information sent by different users and have the occurrence frequency higher than a first preset threshold value;

the first guiding information obtaining sub-module is used for obtaining first guiding information corresponding to the first commodities respectively;

the first guiding information displaying sub-module displays at least part of the first guiding information in a viewing interface of a first user, wherein the first user comprises a user who does not send the interaction information related to the first commodity.

9. The apparatus of claim 8, wherein the first guiding message displaying sub-module determines a maximum number of the first guiding messages that can be simultaneously displayed in the mobile terminal used by the first user;

10. The apparatus of claim 7, the presentation video comprising a live video; the apparatus further comprises a non-offering item determination module;

11. The apparatus of claim 7, the presentation video comprising a live video; the image information extraction module is used for carrying out image recognition on the current frame image of the live broadcast video;

12. The apparatus of claim 8, wherein the first guiding information displaying sub-module determines respective activity degrees of first users according to the number of times of interaction information respectively sent by the first users, and determines a second user with the activity degree higher than a second preset threshold among the first users;

13. A merchandise association device in video interaction, comprising:

at least one processor; and the number of the first and second groups,