CN110598077A

CN110598077A - Cloud resource content screening method and device

Info

Publication number: CN110598077A
Application number: CN201910860072.6A
Authority: CN
Inventors: 杜国威
Original assignee: Beijing Anyun Century Technology Co Ltd
Current assignee: Beijing Anyun Century Technology Co Ltd
Priority date: 2019-09-11
Filing date: 2019-09-11
Publication date: 2019-12-20

Abstract

The invention discloses a method and a device for screening cloud resource contents, wherein the method is applied to a client terminal and comprises the following steps: according to the operation of a user on a target application, acquiring a resource label and a classification table of the target application; displaying the resource label and the classification table; receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result; and sending the classification result to a cloud server so that the cloud server adjusts the adoption rate of each slot position on the resource label based on the category corresponding to the resource label in the classification result. The invention improves the accuracy of identifying the user requirement and improves the accuracy of resource adaptation.

Description

Cloud resource content screening method and device

Technical Field

The invention relates to the technical field of cloud services, in particular to a method and a device for screening cloud resource contents.

Background

At present, when the intelligent device is controlled by voice, the device is usually waken up, then the intelligent device is controlled by hand or voice to enter into a certain Application to play the contents of songs, voices, novels, videos and the like, the intelligent device can directly call a cloud platform API (Application Programming Interface), and all large resource providers pull corresponding resources through the API. When the resources are pulled, the user can not adapt to the hobbies of each person easily, and the resources required by the user can not be pushed effectively.

Disclosure of Invention

In view of the above problems, the invention provides a method and a device for screening cloud resource content, which improve the accuracy of identifying user requirements, improve the accuracy of resource adaptation, and ensure that a user can quickly obtain content preferred by the user.

In a first aspect, the present application provides the following technical solutions through an embodiment:

a cloud resource screening method is applied to a client terminal, and comprises the following steps:

according to the operation of a user on a target application, acquiring a resource label and a classification table of the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories; displaying the resource label and the classification table; receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result; sending the classification result to a cloud server so that the cloud server adjusts the adoption rate of each slot position on the resource label based on the category corresponding to the resource label in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

Preferably, the obtaining the resource label and the classification table of the target application according to the operation of the user on the target application includes:

receiving a preset touch operation of a user on the icon of the target application, and obtaining a resource tag and a classification table of the target application based on the preset touch operation; or receiving the voice editing operation of the target application by the user, and obtaining the resource label and the classification table of the target application based on the voice editing operation.

Preferably, the obtaining a resource tag of a target application according to an operation of a user on the target application includes:

according to the operation of a user on the target application, obtaining the attribute of the historical cloud resource played or displayed by the target application; and acquiring a resource tag of the target application according to the attribute of the historical cloud resource.

Preferably, the classification table includes a first category and a second category, wherein the first category is a category that is preferred by the user, and the second category is a category that is not preferred by the user.

Preferably, the receiving a classification operation of the user on the resource tag, and adding the resource tag into a category corresponding to the classification table according to the classification operation to obtain a classification result includes:

and receiving the classification operation of the user on the resource label, and adding the resource label into the first category or the second category according to the classification operation to obtain the classification result.

Preferably, the first category corresponds to a first tab index, and the second category corresponds to a second tab index; before sending the classification result to the cloud server, the method further includes:

receiving a first expansion tag input by a user in the first tag index, and adding the first expansion tag into the first category; and/or receiving a second expanded label input by a user in the second label index, and adding the second expanded label into the second category; and the first expansion label and the second expansion label are both resource labels input by a user.

In a second aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment:

a high in clouds resource content sieving mechanism is applied to client terminal, the device includes:

the resource tag acquisition module is used for acquiring a resource tag and a classification table of a target application according to the operation of a user on the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories; the display module is used for displaying the resource labels and the classification tables; the classification module is used for receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result; the adoption rate adjusting module is used for sending the classification result to a cloud server so that the cloud server can adjust the adoption rate of each slot position on the resource label based on the class corresponding to the resource label in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

Preferably, the resource tag obtaining module is further configured to:

Preferably, the classification module is further configured to:

Preferably, the first category corresponds to a first tab index, and the second category corresponds to a second tab index; the system also comprises a label input module used for sending the classification result to the cloud server,

In a third aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment:

a cloud resource content screening method is applied to a cloud server, and comprises the following steps:

receiving a classification result sent by a client terminal, wherein the classification result records the category of a resource tag of a target application, and the resource tag is used for representing the attribute of cloud resources of the target application; adjusting the adoption rate of the resource label based on the category of the resource label; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

Preferably, after the adjusting the utilization rate of the resource label based on the category of the resource label, the method further includes:

acquiring a resource request which is sent by the client terminal and corresponds to the target application; acquiring the adoption rate of the resource label based on the resource request; obtaining a target resource label from the resource labels based on the adoption rate of the resource labels; and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

Preferably, after the adjusting the utilization rate of the resource label based on the category of the resource label, the method includes:

obtaining an approximate label corresponding to the resource label based on the resource label in the classification result; and adjusting the adoption rate of the approximate label based on the category of the resource label.

Preferably, after the adjusting the adoption rate of the approximate tag based on the category of the resource tag, the method further includes:

acquiring a resource request which is sent by the client terminal and corresponds to the target application; acquiring the adoption rate of the resource label based on the resource request; obtaining a target resource label from the resource label and the approximate label based on the utilization rate of the resource label; and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

In a fourth aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment:

a high in clouds resource content sieving mechanism is applied to cloud server, the device includes:

the classification result receiving module is used for receiving a classification result sent by a client terminal, the classification result records the category of a resource tag of a target application, and the resource tag is used for representing the attribute of cloud resources of the target application; the first adoption rate adjusting module is used for adjusting the adoption rate of the resource label based on the category of the resource label; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

Preferably, the system further comprises a first resource obtaining module, configured to adjust the utilization rate of the resource tag based on the category of the resource tag,

Preferably, the system further comprises a second utilization rate adjusting module, configured to adjust the utilization rate of the resource tag based on the category of the resource tag,

Preferably, the system further comprises a second resource obtaining module, configured to, after adjusting the adoption rate of the approximate tag based on the category of the resource tag,

In a fifth aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment:

a smart sound box comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the smart sound box to perform the steps of the method of any one of the first aspects.

In a sixth aspect, based on the same inventive concept, the present application provides the following technical solutions through an embodiment:

a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of the first aspects.

According to the cloud resource content screening method provided by the invention, the corresponding resource label and the classification table are obtained through the operation of the user on the target application in the client terminal. The resource labels and the classification tables can then be presented to the user for the user to perform classification operations. The resource labels can be added into different categories in the classification table according to the classification operation to obtain a classification result. And finally, the classification result is sent to the cloud server, so that the cloud server can adjust the utilization rate of the resource tags adopted by the slots according to the classification result, the user can adjust the utilization rate of the resource tags corresponding to the cloud server on the client terminal, the probability of the occurrence of a certain resource tag is improved or reduced, the number of bits which are preferentially adopted by the slots among the resource tags is changed, the resources required by the cloud resource bit user recommended to the user are ensured, the accuracy of user demand identification is improved through the method, and the user is ensured to quickly obtain the favorite content.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a flowchart illustrating a method for screening content of cloud resources according to an embodiment of the present invention;

FIG. 2 shows a schematic diagram of a touch application process of step S10 according to an embodiment;

fig. 3 is a flowchart illustrating a cloud resource content screening method according to a second embodiment of the present invention;

fig. 4 is a functional block diagram of a cloud resource content screening apparatus according to a third embodiment of the present invention;

fig. 5 is a functional block diagram of a cloud resource content screening apparatus according to a fourth embodiment of the present invention;

fig. 6 shows a block diagram of a smart speaker according to a fifth embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Turning to cloud computing (cloud computing) is a major change that is currently faced by various industries. The emergence of various cloud platforms (cloud platforms) is one of the most important links of this transition. This platform allows developers to either run written programs in the "cloud" or use services provided in the "cloud". Ecological construction of various service resources is gradually promoted through a cloud platform, and all functions can be directly used without downloading in an AI (Artificial Intelligence) era. For example, in NLU (Natural language understanding) in human-machine communication, the intention represents the purpose that the user wants to achieve, namely, "what the user wants" is expressed in language expression, and the problem of communication between human and human, and between human and machine is solved. The Android Intent component is composed of an Action, data and some attributes, in an NLU, an intention can be expressed by a slot, and the slot refers to a specific concept extracted from a sentence and is used as parameter information of the intention. Based on the above, the cloud resource content screening method provided by the invention locks the user intention by determining the slot position, and further screens the cloud resource content by the cloud server through the slot position, so that the resource content meeting the user intention can be obtained.

Example one

Referring to fig. 1, a flowchart of a method for screening content of cloud resources according to a first embodiment of the present invention is shown. The cloud resource content screening method can be applied to client terminals in communication connection with the cloud server, and the client terminals include but are not limited to intelligent devices such as intelligent sound boxes, intelligent mobile phones, tablet computers, intelligent wristwatches, wearable devices and vehicle-mounted terminals. Specifically, the method comprises the following implementation steps:

step S10: according to the operation of a user on a target application, acquiring a resource label and a classification table of the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories;

step S20: displaying the resource label and the classification table;

step S30: receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result;

step S40: sending the classification result to a cloud server so that the cloud server adjusts the adoption rate of each slot position on the resource label based on the category corresponding to the resource label in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

In step S10, the target application is an application installed on the client terminal, including, but not limited to, applications containing music, vocal books, vocal programs, encyclopedias, radio stations, ancient poems, drama reviews, vocals, dictionaries, and the like. Further, each type of target application may be used to play or show its corresponding content, such as: the target application related to music may be used to search and play music, the target application related to vocal book may be used to search and play novel or news, etc., and the target application related to vocal measures may be used to search and play vocal measures or measures, etc.

The resource tag of the target application can be used for representing attributes of the cloud resource corresponding to the target application, where the attributes include at least one or more of the following: style, creator, creation year, resource name, lyric subject; the attributes of the resources may be different and different in different target applications.

For example, in a target application of the music class, its resources may be songs. Thus, the resource tag of the target application may be a song name, such as: the night half minor nocturnal music, Beijing welcome you, and Daoxiang fragrance; the resource label of the target application can also be the creation age, such as: the 70 s, 80 s, 90 s, etc.; the resource label of the target application can also be a resource style, such as: rock music, pure music, jazz, pop, etc.; the resource tag of the target application may also be an author, such as: zhang three, Li four, Wang two, Zhang five, etc.

For another example, in a target application of a part of ancient poetry, the cloud resource can be poetry. Thus, the resource tag of the target application may be a style, such as: graceful, luxurious, garden, etc.; the resource tag of the target application may also be a lyric body, such as: thinking, hometown missing, friend missing, worrying about the country, etc.

The classification table may include more than two categories, for example, a first category and a second category, wherein the first category is a category that is preferred by the user and the second category is a category that is not preferred by the user. The resource tags may be added to different categories in the classification table. The categories that the user likes or dislikes can be distinguished in the classification table through the step S20. Further, the classification table may further include a third category, where the third category may be a random category, and the random category is used to indicate that the resource tag related to the resource can be added to the random category after the user views the resource and cannot express whether the resource is liked or not, and the random category may periodically and randomly add the resource tag stored therein to the liked category or the disliked category, so as to avoid repeatedly playing the resource corresponding to the resource tag of the random category to the user. For example, every fixed period of time (e.g., 24 hours) the resource label in the random category is changed from the like category to the dislike category (or from the dislike category to the like category).

Further, in step S10, the manner of generating the classification table and the resource label may be as follows:

1. and touch generation, namely receiving touch operation of a user on the icon of the target application, and generating a resource label and a classification table of the target application. The touch operation may be a long press operation, a click operation, a double click operation, a slide operation, or the like. Specifically, referring to fig. 2, a touch screen is provided on the client terminal, various applications including a target application are displayed on the touch screen, and when a user performs a long-time pressing operation on an icon of the target application, a classification table and a plurality of resource labels can be generated.

2. And voice control generation, namely receiving the voice editing operation of the target application by a user, and generating a resource label and a classification table of the target application. The user can directly carry out voice control on the user terminal, and the controlled voice command can be preset in the user terminal. For example, the voice command may be "xx music," create resource tag "," xx novel, create resource tag "," xx music, "create category table", "xx music, perform preference customization" or the like. The voice control command can be adaptively adjusted, and the expression form is not limited.

Further, a principle of generating resource tags is also provided in this embodiment, and the resource tags generated by this principle will more quickly locate the favorite types of the user for the resources in the target application. The method comprises the following steps:

step S11: and obtaining the attribute of the historical cloud resource played or displayed by the target application according to the operation of the target application by the user. Specifically, when the user operates the target application, the historical cloud resources can be directly searched in the historical play records or browsing records, and the attributes of the historical cloud resources are obtained, so that the user can operate the target application quickly.

Step S12: and acquiring a resource tag of the target application according to the attribute of the historical cloud resource.

Specifically, in step S12, the present embodiment provides two generation manners. First, a resource tag corresponding to an attribute of a historical cloud resource may be used as a resource tag of a target application. Taking music target applications as an example, when the historical cloud resources are song "chapter seven of night" (more than one historical cloud resource is browsed in most cases, and for convenience of description, only one example is mentioned here), the attribute corresponding resource tag includes: and at the moment, the week, the yellow, the classical rap and the Mandarin can be used as resource labels of target application. Second, continuing with the first example, a resource tag associated with a resource tag corresponding to an attribute of the historical cloud resource may be searched according to the resource tag corresponding to the attribute of the historical cloud resource, where the associated resource tag indicates that there is an association between the two tags. For example, the resource label is sometime of week, and the resource label associated with sometime of week may include somebody in the week, classical rap, pop music, etc. (the word of a certain work in somebody in the week is somebody in the week, and the style is classical rap, pop music). After the associated resource tag of the resource tag corresponding to the attribute of the historical cloud resource is found, the resource tag corresponding to the attribute of the historical cloud resource and the associated resource tag can be used as the resource tag of the target application.

Step S20: and displaying the resource label and the classification table.

In step S20, the method shown is not limited, and may specifically be: after the resource tag is generated, the resource tag can be displayed on a display screen of the client terminal equipment, and voice broadcasting can also be performed. For example, voice broadcast can be respectively adopted to show on the intelligent sound box that possesses the touch display screen, also can show on the display screen.

Step S30: and receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result.

In step S30, the following classification method is also applied to the generation method of the resource tag in step S10:

1. the user can press the displayed resource label on the touch screen and drag the resource label to a category corresponding to the classification table, for example, a first category (for example, a category representing a like), a second category (for example, a category representing a dislike), or a third category (for example, a category representing a random category) added to the classification table.

2. The user can control the resource label by means of voice command, for example, voice command "somebody a week joins into a favorite category, somebody a king and a cai joins into a dislike category", and the recognition rule of voice command can be pre-built in the user terminal.

After the resource labels are added to different categories in the classification table according to the classification operation of the user, the classification result can be obtained.

The resource labels are classified through the classification table, and finally the classification result is sent to the cloud server, so that the preference of the user on the resource can be further determined, the simple algorithm identification is avoided, and the preference of the user cannot be met.

Furthermore, since the target application has a limited number of resource tag classifications for cloud resources, it is difficult to meet the user's needs at some time. For example, a user may not be able to find a favorite resource tag among the resource tags obtained for a particular target application. For this, in this embodiment, each category in the classification table may be set with a corresponding tag index. Specifically, if the classification table includes a first category and a second category, a first tab index may be set for the first category, and a second tab index may be set for the second category. Before step S40, the method further includes:

step S301: receiving a first expansion tag input by a user in the first tag index, and adding the first expansion tag into the first category; and/or

Step S302: and receiving a second expanded label input in the second label index by the user, and adding the second expanded label into the second category.

It should be noted that, when both steps S301 and S302 are executed, the execution sequence is not limited.

In step S40, after the user completes the classification of the resource tag, the client terminal sends the classification result to the cloud server, and the cloud server increases or decreases the utilization rate of the slot adopted by the resource tag based on the type of the resource tag. Specifically, the adoption probability of the resource tag being adopted by the slot is increased when the resource tag is of the first category (representing like), and the adoption probability of the resource tag being adopted by the slot is decreased when the resource tag is of the second category (representing dislike).

In order to reduce the classification frequency of the resource tags of the user and reduce the operation burden of the user, the cloud server can increase or decrease the utilization rate of the resource tags by the following steps:

step S401: and obtaining an approximate label corresponding to the resource label based on the resource label in the classification result.

Step S402: and adjusting the adoption rate of the approximate label based on the category of the resource label.

In step S401, the approximate tags represent one or more tags with a high association degree with the resource tags, and the number of the tags may be 2, 3, 4, and the like, which may be preset. The approximate tags represent tags associated with the resource tags in the sorted list, e.g., when the resource tag is "somebody a week", the approximate tags associated with somebody a week may include somebody a party, classical rap, pop music, etc. If "somebody in week" exists in the first category (representing a favorite category), the cloud server increases the adoption rate of both "somebody in week" and its approximate tag, and the specific way of increasing may be: the adoption rate of the resource label of the first category (such as 'a certain week') is increased by a preset value, and the adoption rate increase value of the approximate label is reduced relative to the resource label corresponding to the approximate label. When a plurality of approximate tags exist in the resource tags in the favorite categories, the increasing value of the adoption rate can be sequentially decreased from large to small according to the approximate degree of the approximate tags, for example: if the utilization rate increase value of the resource label is 50%, then the utilization rate increase value of the approximate label with the maximum degree of association with the resource label is reduced to 60% of the original value, that is, the utilization rate increase value of the approximate label with the maximum degree of association with the resource label is 50% × 60% — 30%; the rate of increase of the approximate tag ranked second in the degree of association is 18%, and so on, the rate of increase of the subsequent approximate tags is 10.8% and 6.48% … … in turn.

The determination of the approximate label is not limited, and for example, the determination may be performed according to whether a corresponding label appears in the encyclopedia, or according to the frequency of two different resource labels appearing in the same resource at the same time, and the like.

In addition, in order to ensure that the terminal device can still obtain the resource corresponding to the resource label with the reduced utilization rate under certain specified conditions. The method can be realized by the following steps:

step S511: acquiring a designated command sent by a user;

step S512: obtaining a designated label designated by a user according to the designated command; the appointed label is a resource label corresponding to the resource appointed and obtained by the user;

step S513: and sending a canceling instruction carrying the specified label to a cloud server so that the cloud server cancels the operation of reducing the adoption rate of the specified label.

For example, when the user says "i want to listen to a song of wang", and can obtain the designated tag "wang", the client terminal sends a cancel instruction carrying "wang" to the cloud server at this time, so that the cloud server cancels the previous operation of reducing the probability (adoption rate) of being adopted by the slot for the resource tag of "wang".

It should be noted that, in the client terminal, a plurality of status modes may exist. In a certain status mode, some resource tags will not be used by the slot all the time, which may specifically include:

step S521: obtaining a forbidden tag in the current mode state according to the current mode state; wherein the prohibited tag represents a resource tag that will not be filled into the slot by the cloud server;

step S522: and sending the prohibited label to a cloud server so that the cloud server adjusts the adoption rate of the prohibited label to 0. The prohibited tag indicates a resource tag that prohibits playing of the corresponding cloud resource. Specifically, the transmission mode of the forbidden tag may be: and setting a fourth class prohibition class in the classification table, automatically filling related prohibition labels into the prohibition classes after the client terminal enters a certain specified mode, and customizing the prohibition classes. In each status mode, the disable tag can be preset. For example, in the normal mode, the preset prohibition flag is null (not set); in the child mode, the preset prohibition tag may include "wangzo", which will automatically fill in the prohibition category in the classification table when entering the child mode, and the prohibition category will prohibit the editing operation due to the child mode. The adoption rate of the prohibited tag adopted by the slot position is adjusted to be 0 by the cloud server based on the prohibited tag in the prohibited category, so that any resource corresponding to the tag cannot be recommended to the user, and the effect of protecting children is achieved. By the method, resource content can be provided to the user as required, personalized adjustment of the cloud server resource label by the user terminal is realized, and more reasonable resource content is provided by the cloud server.

In summary, the cloud resource content screening method provided in this embodiment obtains the corresponding resource tag and the classification table through the operation of the user on the target application in the client terminal. The resource labels and the classification tables can then be presented to the user for the user to perform classification operations. The resource labels can be added into different categories in the classification table according to the classification operation to obtain a classification result. And finally, the classification result is sent to the cloud server, so that the cloud server can adjust the utilization rate of the resource tags adopted by the slots according to the classification result, the user can adjust the utilization rate of the resource tags corresponding to the cloud server on the client terminal, the probability of the occurrence of a certain resource tag is improved or reduced, the number of bits which are preferentially adopted by the slots among the resource tags is changed, the resources required by the cloud resource bit user recommended to the user are ensured, the accuracy of user demand identification is improved through the method, and the user is ensured to quickly obtain the favorite content.

Example two

Referring to fig. 3, in this embodiment, a method for screening content of cloud resources is provided, where the method is applied to a cloud server, and the cloud server may be in communication connection with a client terminal in the embodiment, and the method includes:

step S61: receiving a classification result sent by a client terminal, wherein the classification result records the category of a resource tag of a target application, and the resource tag is used for representing the attribute of cloud resources of the target application;

step S62: adjusting the adoption rate of the resource label based on the category of the resource label; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

The adoption rate of the resource tags in the cloud server adopted by the slots can be adjusted through the steps of S61 and S62. The method specifically comprises the following steps after the adoption rate of the resource label is adjusted:

step S631 a: acquiring a resource request which is sent by the client terminal and corresponds to the target application;

step S632 a: acquiring the adoption rate of the resource label based on the resource request;

step S633 a: obtaining a target resource label from the resource labels based on the adoption rate of the resource labels;

step S634 a: and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

Further, when or after the adjustment of the utilization rate of the resource tag, the method may further include: obtaining an approximate label corresponding to the resource label based on the resource label in the classification result; and adjusting the adoption rate of the approximate label based on the category of the resource label. Specifically, refer to the descriptions of steps S401 to S402 in the first embodiment, and are not described again.

After the resource tag and the adoption rate of the approximate tag are adjusted, the method specifically comprises the following steps:

step S631 b: acquiring a resource request which is sent by the client terminal and corresponds to the target application;

step S632 b: acquiring the adoption rate of the resource label based on the resource request;

step S633 b: obtaining a target resource label from the resource label and the approximate label based on the utilization rate of the resource label;

step S634 b: and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

The steps S634a and S634b are explained as a specific example. Taking a music application as an example, the slot for the cloud server to acquire the resource may be (as an example): "____" (year) "____" (song title), "____" (singer name), "____" (song category). When the favorite category in the classification table sent by the client terminal includes "somebody a week", the server has already improved the adoption rate of "somebody a week" (can improve the adoption rate of the approximate label "90 years" associated with "somebody a week"). After the rate of adoption was adjusted, the rate of adoption of "90 s", "somebody of week" was already very advanced. Then, when the resource request information sent by the user to the client terminal is "i want to listen to popular music", the cloud server will fill in the slot position of the song era in a greater probability of "90 s", the slot position of the song category in a greater probability of "popular music", the slot position of the singer name in a greater probability of "somebody all round", the slot position of the song name in a greater probability of filling in a resource tag with a higher adoption rate in a certain song all round, and finally resource acquisition is performed in the resource provider according to the filled slot position.

In this embodiment, the cloud server adjusts the utilization rate of the resource tag based on the classification of the resource tag in the classification result by receiving the classification result sent by the client terminal, so that the adjustment of the utilization rate of the resource tag of the cloud server in the client terminal is realized, and the cloud server is ensured to be more suitable for the interests and hobbies of the user when recommending the cloud resource for the user.

EXAMPLE III

Referring to fig. 4, in the present embodiment, a cloud resource content screening apparatus 300 is provided, and is applied to a client terminal, where the apparatus 300 includes:

a resource tag obtaining module 301, configured to obtain a resource tag and a classification table of a target application according to an operation of a user on the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories;

a display module 302, configured to display the resource labels and the classification tables;

the classification module 303 is configured to receive a classification operation performed on the resource tag by a user, and add the resource tag to a category corresponding to the classification table according to the classification operation to obtain a classification result;

an adoption rate adjusting module 304, configured to send the classification result to a cloud server, so that the cloud server adjusts the adoption rate of each slot to the resource tag based on the category corresponding to the resource tag in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

As an optional implementation manner, the resource tag obtaining module 301 is further configured to:

As an optional implementation manner, the classification table includes a first category and a second category, where the first category is a category that is preferred by the user, and the second category is a category that is not preferred by the user.

As an optional implementation manner, the classification module 303 is further configured to:

As an optional implementation, the first category corresponds to a first tab index, and the second category corresponds to a second tab index; the system further comprises a tag input module, which is used for receiving a first extended tag input by a user in the first tag index before the classification result is sent to the cloud server, and adding the first extended tag into the first category; and/or receiving a second expanded label input by a user in the second label index, and adding the second expanded label into the second category; and the first expansion label and the second expansion label are both resource labels input by a user.

It should be noted that, the specific implementation and technical effects of the cloud resource content screening apparatus 300 provided in the embodiment of the present invention are the same as those of the foregoing method embodiment, and for a brief description, reference may be made to corresponding contents in the foregoing method embodiment for a part not mentioned in the apparatus embodiment.

Example four

Referring to fig. 5, in the present embodiment, an apparatus 400 for screening cloud resource content is provided, where the apparatus 400 is applied to a cloud server, and the apparatus 400 includes:

a classification result receiving module 401, configured to receive a classification result sent by a client terminal, where a category of a resource tag of a target application is recorded in the classification result, and the resource tag is used to represent an attribute of a cloud resource of the target application;

a first adoption rate adjusting module 402, configured to adjust the adoption rate of the resource tag based on the category of the resource tag; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

As an optional implementation manner, the system further includes a first resource obtaining module, configured to obtain a resource request corresponding to the target application, sent by the client terminal, after adjusting the utilization rate of the resource tag based on the category of the resource tag; acquiring the adoption rate of the resource label based on the resource request; obtaining a target resource label from the resource labels based on the adoption rate of the resource labels; and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

As an optional implementation manner, the system further includes a second utilization rate adjustment module, configured to adjust the utilization rate of the resource tag based on the category of the resource tag, and then obtain an approximate tag corresponding to the resource tag based on the resource tag in the classification result; and adjusting the adoption rate of the approximate label based on the category of the resource label.

As an optional implementation manner, the system further includes a second resource obtaining module, configured to obtain a resource request corresponding to the target application, sent by the client terminal, after adjusting the adoption rate of the approximate tag based on the category of the resource tag; acquiring the adoption rate of the resource label based on the resource request; obtaining a target resource label from the resource label and the approximate label based on the utilization rate of the resource label; and filling the target resource label into the slot to obtain the cloud resource corresponding to the target application which needs to be recommended to the client terminal.

It should be noted that, the specific implementation and technical effects of the cloud resource content screening apparatus 400 provided in the embodiment of the present invention are the same as those of the foregoing method embodiment, and for brief description, reference may be made to corresponding contents in the foregoing method embodiment for the part of the apparatus embodiment that is not mentioned.

EXAMPLE five

Based on the same inventive concept, a fifth embodiment of the present invention further provides a smart sound box, including a processor and a memory, the memory being coupled to the processor, the memory storing instructions that, when executed by the processor, cause the smart sound box to:

It should be noted that, in the intelligent speaker provided in the embodiment of the present invention, the specific implementation and the generated technical effect of each step are the same as those of the foregoing method embodiment, and for a brief description, for the sake of brevity, reference may be made to corresponding contents in the foregoing method embodiment for what is not mentioned in this embodiment.

In the embodiment of the invention, the intelligent sound box is provided with an operating system and a third-party application program.

Fig. 6 illustrates a block diagram of an exemplary smart sound box 500. As shown in fig. 6, smart sound box 500 includes a memory 502, a storage controller 504, one or more processors 506 (only one shown), a peripheral interface 508, a network module 510, an input-output module 512, a display module 514, and the like. These components communicate with one another via one or more communication buses/signal lines 516.

The memory 502 may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for screening cloud resource content in the embodiment of the present invention, and the processor 506 executes various functional applications and data processing by operating the software programs and modules stored in the memory 502, such as the method for screening cloud resource content provided in the embodiment of the present invention.

The memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. Access to the memory 502 by the processor 506, and possibly other components, may be under the control of the memory controller 504.

Peripheral interface 508 couples various input/output devices to processor 506 and memory 502. In some embodiments, the peripheral interface 508, the processor 506, and the memory controller 504 may be implemented in a single chip. In other examples, they may be implemented separately from the individual chips.

The network module 510 is used for receiving and transmitting network signals. The network signal may include a wireless signal or a wired signal.

The input/output module 512 is used for providing input data for the user to realize the interaction between the user and the smart speaker. The input/output module 512 can be, but is not limited to, a mouse, a keyboard, a touch screen, and the like.

Display module 514 provides an interactive interface (e.g., a user interface) between smart sound box 500 and a user or for displaying image data for reference by the user. In this embodiment, the display module 514 may be a liquid crystal display or a touch display. In the case of a touch display, the display can be a capacitive touch screen or a resistive touch screen, which supports single-point and multi-point touch operations. The support of single-point and multi-point touch operations means that the touch display can sense touch operations simultaneously generated from one or more positions on the touch display, and the sensed touch operations are sent to the processor for calculation and processing.

It is understood that the configuration shown in fig. 6 is merely illustrative, and that smart sound box 500 may include more or fewer components than shown in fig. 6, or have a different configuration than shown in fig. 6. The components shown in fig. 6 may be implemented in hardware, software, or a combination thereof.

EXAMPLE six

A sixth embodiment of the present invention provides a computer storage medium, and if the function module integrated by the cloud resource content screening method apparatus in the third and fourth embodiments of the present invention is implemented in the form of a software function module and sold or used as an independent product, the function module may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the cloud resource content screening method according to the first and second embodiments of the present invention may also be completed by instructing related hardware through a computer program, where the computer program may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the foregoing method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the cloud resource content screening apparatus, the smart speaker, the cloud server, and the client terminal according to the embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

The invention discloses A1. a cloud resource screening method, which is applied to a client terminal and comprises the following steps:

A2. According to the method described in a1, the obtaining a resource tag and a classification table of a target application according to an operation of a user on the target application includes:

A3. The method according to a1, wherein the obtaining a resource tag of a target application according to an operation of a user on the target application includes:

A4. The method according to any of a1-A3, wherein the classification table comprises a first category and a second category, the first category is a user's favorite category, and the second category is a user's disliked category.

A5. According to the method of a4, the receiving a classification operation of a user on the resource tag, and adding the resource tag to a category corresponding to the classification table according to the classification operation to obtain a classification result includes:

A6. According to the method of a4, the first category corresponds to a first tab index and the second category corresponds to a second tab index; before sending the classification result to the cloud server, the method further includes:

The invention also discloses B7. a cloud resource content screening device, which is applied to a client terminal, and the device comprises:

B8. The apparatus of B7, the resource tag obtaining module further configured to:

B9. The apparatus of B7, the resource tag obtaining module further configured to:

B10. The apparatus according to any of claims B7-B9, wherein the classification table comprises a first category and a second category, the first category being a user's favorite category and the second category being a user's disliked category.

B11. The apparatus of B10, the classification module further configured to:

B12. According to the apparatus of B10, the first category corresponds to a first tab index and the second category corresponds to a second tab index; the system further comprises a tag input module, which is used for receiving a first extended tag input by a user in the first tag index before the classification result is sent to the cloud server, and adding the first extended tag into the first category; and/or receiving a second expanded label input by a user in the second label index, and adding the second expanded label into the second category; and the first expansion label and the second expansion label are both resource labels input by a user.

The invention also discloses C13. a cloud resource content screening method, which is applied to a cloud server and comprises the following steps:

C14. According to the method of C13, after the adjusting the utilization rate of the resource tag based on the category of the resource tag, the method further includes:

C15. The method according to C13, wherein the adjusting the utilization rate of the resource label based on the category of the resource label includes:

C16. According to the method of C15, after the adjusting the usage rate of the approximate tags based on the category of the resource tags, the method further includes:

The invention also discloses a D17 cloud resource content screening device, which is applied to a cloud server, and comprises:

D18. The apparatus of D17, further comprising a first resource obtaining module, configured to adjust the utilization rate of the resource tag based on the category of the resource tag,

D19. The apparatus of claim 17, further comprising a second utilization rate adjustment module configured to, after adjusting the utilization rate of the resource tag based on the category of the resource tag,

D20. The apparatus of D19, further comprising a second resource obtaining module configured to, after adjusting the usage rate of the approximate tag based on the category of the resource tag,

Also disclosed is an intelligent sound box, comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the intelligent sound box to perform the steps of any of the methods of a1-a 6.

The invention also discloses f22 a computer readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of a1-a 6.

Claims

1. A cloud resource screening method is applied to a client terminal, and comprises the following steps:

according to the operation of a user on a target application, acquiring a resource label and a classification table of the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories;

displaying the resource label and the classification table;

receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result;

sending the classification result to a cloud server so that the cloud server adjusts the adoption rate of each slot position on the resource label based on the category corresponding to the resource label in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

2. The method of claim 1, wherein the obtaining the resource label and the classification table of the target application according to the operation of the target application by the user comprises:

receiving a preset touch operation of a user on the icon of the target application, and obtaining a resource tag and a classification table of the target application based on the preset touch operation; or

And receiving voice editing operation of a user on the target application, and obtaining a resource label and a classification table of the target application based on the voice editing operation.

3. The method of claim 1, wherein obtaining the resource tag of the target application according to the operation of the target application by the user comprises:

according to the operation of a user on the target application, obtaining the attribute of the historical cloud resource played or displayed by the target application;

and acquiring a resource tag of the target application according to the attribute of the historical cloud resource.

4. The method according to any one of claims 1-3, wherein the classification table comprises a first category and a second category, wherein the first category is a category that is preferred by the user, and the second category is a category that is not preferred by the user.

5. The method according to claim 4, wherein the receiving a classification operation of the user on the resource tag and adding the resource tag to a category corresponding to the classification table according to the classification operation to obtain a classification result comprises:

6. The utility model provides a high in the clouds resource content sieving mechanism which characterized in that is applied to client terminal, the device includes:

the resource tag acquisition module is used for acquiring a resource tag and a classification table of a target application according to the operation of a user on the target application; the resource tag is used for representing the attribute of the cloud resource of the target application, and the classification table comprises more than two categories;

the display module is used for displaying the resource labels and the classification tables;

the classification module is used for receiving the classification operation of the user on the resource label, and adding the resource label into the category corresponding to the classification table according to the classification operation to obtain a classification result;

the adoption rate adjusting module is used for sending the classification result to a cloud server so that the cloud server can adjust the adoption rate of each slot position on the resource label based on the class corresponding to the resource label in the classification result; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

7. A cloud resource content screening method is applied to a cloud server, and comprises the following steps:

receiving a classification result sent by a client terminal, wherein the classification result records the category of a resource tag of a target application, and the resource tag is used for representing the attribute of cloud resources of the target application;

adjusting the adoption rate of the resource label based on the category of the resource label; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

8. The utility model provides a high in clouds resource content sieving mechanism which is applied to cloud server, the device includes:

the classification result receiving module is used for receiving a classification result sent by a client terminal, the classification result records the category of a resource tag of a target application, and the resource tag is used for representing the attribute of cloud resources of the target application;

the first adoption rate adjusting module is used for adjusting the adoption rate of the resource label based on the category of the resource label; the adoption rate represents the probability that the resource tag is filled into a slot when the cloud server recommends the cloud resource corresponding to the target application to the client terminal based on the slot, and the slot is used for screening the content of the cloud resource.

9. A smart sound box comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the smart sound box to perform the steps of the method of any one of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.