Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be noted that, the information and the data related to the present application are all information and data authorized by the user or fully authorized by each party, and the collection, the use and the processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
It should be understood that, although the terms first, second, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first parameter may also be referred to as a second parameter, and similarly, a second parameter may also be referred to as a first parameter, without departing from the scope of the application. The term "if" as used herein may be interpreted as "at..once" or "when..once" or "in response to a determination", depending on the context.
In the big data age, advertisement recommendation systems play a vital role in accurately predicting products or services that a user may be interested in by deeply analyzing the user's behavioral patterns, personal preferences, and specific contextual information, and providing personalized advertisement recommendations accordingly. Through highly-refined data analysis, the comprehensive capturing of the user interests is realized, and then the matched products are recommended, so that the user experience is improved, and the effectiveness of advertisements is enhanced.
In the related art, an advertisement recommendation system mainly depends on data such as search history and browsing records of users, and determines a product type of recommended advertisements based on the data. By analyzing these data, advertisement content conforming to the user's search behavior is pushed.
However, such a recommendation mechanism based on a single data source has a certain limitation, and often cannot fully capture the diversified interests and needs of the user. Resulting in too single content of the recommended advertisement to fully mine the user's potential interest in other types of products or services. In addition, since the recommendation system tends to repeatedly push advertisements of the same type, users may face the problem of information overload, which not only increases the difficulty of selecting among a plurality of similar advertisements, but also may cause users to feel tired of advertisement contents, thereby reducing the overall effect and accuracy of advertisement recommendation.
The application provides a content recommendation method, which is used for analyzing the frequently used equipment types of a user, combining the frequently used equipment types on the basis of the browsing records of the user account, recommending advertisement content related to the frequently used equipment for the user account, increasing the data source when determining the recommended content, solving the problem of serious homogenization of the recommended content, and improving the effect and accuracy of content recommendation.
As shown in fig. 1, fig. 1 is a schematic diagram of a content recommendation system according to an exemplary embodiment of the present application, where the content recommendation system relates to a first device 110, a second device 120, a third device 130, and a server side 100, and the first device 110, the third device 130, and the server side 100 are connected through a communication network 140. The first device 110 and the third device 130, which are the same or different, each have a first account number logged in.
The first device 110 and the second device 120 are connected in a short-distance wireless transmission connection mode, the first device 110 can acquire device connection information of the second device 120 when the connection is established, the device connection information is sent to the server side 100, the server side 100 can analyze the device type of the second device 120 based on the device connection information, and the type of a product to be recommended is determined.
The first device 110 and the third device 130 are respectively provided with an application program capable of playing multimedia content, and the application programs in different devices can be the same or different, and the association is established by logging in the first account together. The first device 110 is configured to play the first multimedia content, the third device 130 is configured to play the second multimedia content, the first device 110 sends a first browsing record generated when the first multimedia content is played to the server side 100, the third device 130 sends a second browsing record generated when the second multimedia content is played to the server side 100, the server side 100 determines a preference tag when the first account browses the multimedia content based on the first browsing record and the second browsing record, and determines the first content based on the preference tag and a type of a product to be recommended.
For example, the preference tag indicates that the first account prefers to browse songs sung by singer a, and the device type of the second device 120 is a bluetooth headset, and the product type to be recommended refers to products related to the bluetooth headset, such as a headset protective shell, a headset with the same model as the second device 120, and the like, and the first content is advertisement content and is used for recommending headset protective shell products of the singer a to the first account.
The first device 110 and the third device 130 log in with the first account, and then display the first content on the recommendation page of the first device 110 and the third device 130.
The first device, the second device, and the third device may be various terminal devices such as a mobile phone, a tablet computer, a desktop computer, a portable notebook computer, an intelligent television, a vehicle-mounted terminal, and an intelligent home device, which is not limited in the embodiment of the present application.
It should be noted that the server may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, a content delivery network (Content Delivery Network, CDN), and basic cloud computing services such as big data and an artificial intelligence platform.
Cloud technology (Cloud technology) refers to a hosting technology that unifies serial resources such as hardware, software, networks and the like in a wide area network or a local area network to realize calculation, storage, processing and sharing of data. The cloud technology is based on the general names of network technology, information technology, integration technology, management platform technology, application technology and the like applied by the cloud computing business mode, can form a resource pool, and is flexible and convenient as required. Cloud computing technology will become an important support. Background services of technical networking systems require a large amount of computing, storage resources, such as video websites, picture-like websites, and more portals. Along with the high development and application of the internet industry, each article possibly has an own identification mark in the future, the identification mark needs to be transmitted to a background system for logic processing, data with different levels can be processed separately, and various industry data needs strong system rear shield support and can be realized only through cloud computing.
In some embodiments, the servers described above may also be implemented as nodes in a blockchain system.
The content recommendation method provided by the present application is described with reference to the above noun introduction and application scenario, and the method may be executed by a server or a terminal, or may be executed by both the server and the terminal, and in the embodiment of the present application, the method is executed by the server as an example, as shown in fig. 2, and fig. 2 is a flowchart of the content recommendation method provided by an exemplary embodiment of the present application. The method comprises the following steps.
Step 210, receiving device connection information uploaded by the first device.
The device connection information is information which is acquired by the first device and related to the second device when the second device is connected with the first device, the first device is connected with the second device in a short-distance wireless transmission connection mode, and the first device is logged in with a first account.
Optionally, the device connection information includes at least one of the following information.
(1) A device name indicating a name in the first device of the second device when establishing a connection with the first device. For example, when the first device is first connected to the second device, the first device displays the connection name of the second device as earphone.
(2) The device model is used for indicating the model of the second device. For example, when the first device is first connected to the second device, the first device displays the model number X1 of the second device.
(3) And the equipment parameter is used for indicating the operation parameter in the operation process of the second equipment. For example, the power of the second device, the endurance (the time that the device can last after a single charge), the voltage and current specifications required when the device is running, the energy consumption of the second device in different operating states, the memory size of the second device, and the like.
Optionally, the short-range wireless transmission connection between the first device and the second device includes at least one of the following.
(1) The first device and the second device are connected through a Bluetooth connection mode, wherein the first device is a smart phone, the second device is an earphone, and the first device and the second device are connected through the Bluetooth connection mode.
(2) The first device is used as a wireless station, the second device is used as a wireless access point to access the wireless station, for example, the first device and the second device are smart phones, the first device starts a WiFi (wireless communication network) hotspot to provide networking service for the second device, and the second device accesses the hotspot of the first device to realize networking.
(3) The first device is used as a first wireless access point, the second device is used as a second wireless access point, and the first wireless access point and the second wireless access point access the same wireless station, for example, the first device and the second device realize networking based on a local area network provided by the same router in a historical time period or at the current moment.
(4) The first equipment and the second equipment are connected in a Zigbee connection mode. The purple peak Zigbee is a novel wireless communication technology with short distance, low power consumption and low data transmission rate. The method is suitable for the fields of automatic control and remote control, and is particularly suitable for application scenes with small data flow and short transmission distance.
Step 220, obtaining the first content based on the device connection information.
The first content is to-be-recommended content, and the first content comprises elements associated with the device connection information.
The first content is illustratively to-be-recommended content, such as the first content belonging to advertising content, the first content being for recommending a product or service to the first account based on an element associated with the device connection information. The elements associated with the device connection information comprise at least one of (1) elements contained in the second device, such as parts/components of the second device and software contained in the second device, (2) elements with a function matching relationship with the second device, such as products or services capable of matching with the second device to realize functions of the second device, (3) elements with a space matching relationship with the second device, such as products identical to the application occasion of the second device or products with the frequency of the second device occurring at the same time in space meeting the preset frequency requirement, (4) elements with a context associated with the second device, such as elements occurring with the second device in a specific context in a general way when a specific theme is discussed.
For example, the device connection information includes device type information of the second device and endurance information of the second device, the device connection information indicates that the endurance of the second device is 80% of its factory setting, it may be determined that an element associated with the device connection information includes a battery of the second device, and the first content may be advertisement content for recommending a replaceable battery of the second device.
For example, if the device connection information includes device type information of the second device and power information of the second device, and the device type information indicates that the current power of the second device is 20%, it may be determined that an element associated with the device connection information includes a mobile power source, a charging device, and the like capable of providing a charging service for the second device, and the first content may be advertisement content including (1) recommending a charger, and (2) recommending a charger with a fast charging function that is matched with the second device, and (3) recommending a site capable of providing a charging treasured return service.
Optionally, determining a device type of the second device based on the device connection information, determining an association product associated with the second device based on the device type of the second device, and associating a function of the association product with a function of the second device. The first content is obtained based on the second device and the associated product.
And acquiring a device library, wherein the device library comprises a plurality of candidate devices marked with device type labels and device names, and the device connection information comprises the device names of the second devices.
In response to the device name of the first candidate device matching the device name of the second device of the plurality of candidate devices, a device type of the second device is determined based on the device type tag of the first candidate device.
The device type tag is used for indicating the device type and the device model of the candidate device, and the device name of the second device includes the device type and the device model of the second device.
The equipment library comprises 10 candidate equipment, and each type of candidate equipment is respectively corresponding to 1000 candidate equipment according to different models.
The device name of the second device is Bxse Comfort In-ear as follows.
The 5 th candidate device In the device library is a headset device, the device type tag comprises In-ear, 1000 candidate devices corresponding to In-ear comprise candidate devices corresponding to 50 brands respectively, 35 th brand is Bxse, 35 th brand corresponds to 20 device models In total, and 8 th device model is Comfort.
The device type label for the first candidate device is In-ear device type Bxse brand and Comfort model.
Then the device name of the second device matches the device type tag of the first candidate device, and the determination that the device name of the second device contains information Bxse indicating the brand of the second device, in-ear indicating the device type of the second device as an embedded earphone, comfort indicating the device model of the second device.
That is, the second device is a model Comfort embedded earphone developed by brand Bxse.
Optionally, in response to the device type tag of the first candidate device, determining that the similarity between the device type tag of the second candidate device and the device type tag of the second candidate device in the device library meets a first similarity threshold, determining the second candidate device as an associated product.
For example, the device type label for the first candidate device is for the device type In-ear, brand Bxse, model Comfort. The second candidate device is of device type In-ear Case, brand Bxse, model Comfort.
The similarity calculation method comprises the steps of taking each item in equipment type labels of first candidate equipment as a reference, removing the coincident item which is the same as that in equipment type labels of second candidate equipment, marking the weight of each coincident item as 1, extracting features of each non-coincident item to obtain feature vectors, calculating cosine similarity or vector distance between the vectors, carrying out normalization processing to obtain a numerical value between 0 and 1, taking the numerical value as the weight of the non-coincident item, and calculating the weighted sum of each item in the equipment type labels of the first candidate equipment to obtain the similarity between the two.
For example, brand Bxse, model Comfort are coincident terms, device type In-ear is non-coincident term, in-ear is converted to feature vector a, in-ear Case is converted to feature vector b, the similarity between vector a and vector b is calculated to be 0.7, and the weighted sum of each item In the device type label of the first candidate device is calculated to be (1+1+0.7)/3=2.7/3=0.9. The first similarity threshold is 0.85, then the second candidate device is determined to be an associated product.
The second candidate device is an earphone storage box matched with an embedded earphone with the model of Comfort developed by brand Bxse.
The device type of the second device is the same as the device type of the first candidate device. The similarity between the device tag of the second candidate device and the device tag of the first candidate device meets a preset requirement, which indicates that the second candidate device is associated with the first candidate device, that is, the second candidate device is associated with the second device, and the second candidate device is an associated product with the second device. The type of associated product of the second device can be determined based on the device type of the second candidate device.
Optionally, after determining the type of the second device and the associated product, first content is determined, the first content being used to recommend elements related to the second device and the associated product.
And obtaining a content resource pool, wherein the content resource pool comprises a plurality of candidate contents marked with content types, and the content types are used for indicating elements contained in the candidate contents.
In response to there being a match of the content type of the candidate content with the second device or associated product in the content asset pool, determining the candidate content matching the second device or associated product as the first content.
The content resource pool comprises 1000 candidate contents, wherein the 800 th candidate content is of a headset product type, namely the 800 th product is used for recommending the headset product and matched service to a user, and the 800 th candidate content is determined to be the first content.
Illustratively, the 90 th candidate content is of the type of embedded earphone receiver, and is used for recommending earphone receiver products and matched services to the user, and the 90 th candidate content is also determined to be the first content.
The first content is two advertisement contents, and the earphone product and the earphone storage box product are respectively recommended to the first account.
Step 230, pushing the first content to the third device logged in with the first account.
Wherein the third device is the same as or different from the first device. And after the application programs log in the first account, displaying the first content on a recommendation page of the application program, and recommending products to the first account.
The first equipment and the third equipment are at least one of the following relation among the application programs for logging in the first account number, namely (1) different application programs developed by the same enterprise/individual, data between the two application programs can be communicated and mutually transmitted, the first account number can be logged in the two application programs at the same time, (2) different application programs developed by different enterprises/individuals, the data communication and mutually transmitted between the two application programs can be realized after the two application programs are mutually authorized, and a binding relation or an association relation and the like are established between the account numbers logged in by the two application programs.
The first device and the third device are not the same device, the first device is a smart phone, and the third device is a smart television.
The second device is an embedded earphone, and when Bluetooth connection is established between the first device and the second device, the first device acquires device connection information of the second device.
And after the equipment type and the equipment model of the second equipment are determined based on the equipment connection information, determining that the first content is an earphone product advertisement, and pushing the first content to the first account. And when the first device logs in the first account, displaying the first content through a recommendation page of the application program in the first device. And when the third device logs in the first account, displaying the first content through a recommendation page of the application program in the third device.
In summary, in the content recommendation method provided by the application, when the first device is connected with the second device, the first device can acquire the device connection information of the second device, and use the device connection information as a basis for acquiring the first content, so that the data source during content recommendation is enlarged, the accuracy of an analysis result is improved, and the content meeting the user requirement is recommended for the first device or the third device logged in with the first account. Compared with the mode of determining the recommended content by only relying on the browsing record of the first account, the method can avoid the homogenization of the recommended content, help users expand interests, find the recommended content with potential preference and improve the recommending effect.
Fig. 3 is a flowchart of a content recommendation method according to another exemplary embodiment of the present application, where when determining first content recommended to a first account, device connection information of a second device connected to the first device and preference determination of browsing multimedia content by the first account may be combined, so that content recommendation effect and accuracy can be improved. The method comprises the following steps.
Step 310, receiving device connection information uploaded by the first device.
The device connection information is information which is acquired by the first device and related to the second device when the second device is connected with the first device, the first device is connected with the second device in a short-distance wireless transmission connection mode, and the first device is logged in with a first account.
Illustratively, a bluetooth communication connection is established between the first device and the second device, and the device connection information includes a connection name of the second device.
When the first device and the second device establish Bluetooth communication connection for the first time, the Bluetooth connection name of the second device is obtained from the Bluetooth connection list and stored locally, and the initial name displayed by the second device in the first device can reflect the device type of the second device.
When the first device modifies or remarks the name of the second device, when the first device needs to upload the device connection information of the second device to the server, the name information of the second device contained in the device connection information is an initial name displayed in the first device when the second device is connected with the first device for the first time.
Step 320, obtaining a content browsing record of the first account.
The content browsing record refers to a record of multimedia content browsed by at least one client logged with the first account in a historical time period.
For example, the client for logging in the first account includes a first client and a second client, wherein the first client is an application program capable of playing the first multimedia content installed in the third device, and the second client is an application program capable of playing the second multimedia content installed in the first device, and the first client and the second client establish association through logging in the first account together.
Alternatively, in the present embodiment, the content types of the first multimedia content and the second multimedia content are different.
For example, the first multimedia content includes a browse recording (e.g., television program, movie, animation, etc.) of the video content by the first account over a historical period of time.
For example, the second multimedia content includes a browsing record of the electronic book by the first account number in the historical time period, a playing record of playing songs, and a playing record of playing long audio (such as a broadcasting play, an audio book, a radio program, etc.).
Alternatively, a first viewing record of the first multimedia content is obtained, or a second viewing record of the second multimedia content is obtained. The first multimedia content and the second multimedia content are different in content type.
And receiving playing channel information sent by the first client, wherein the playing channel information is used for indicating a playing channel when the first multimedia content is played, collecting playing images when the first multimedia content is played by the first client, identifying the playing images and determining the playing channel information of the first multimedia content.
And receiving a second browsing record sent by the second client, wherein the second browsing record is acquired when the second client plays the second multimedia content.
Step 330, determining a preference tag of the first account based on the content browsing record.
The preference tag is used for indicating the preference of the first account for browsing the multimedia content.
Optionally, determining a list of columns played by the playing channel in the historical time period based on the first browsing record, wherein the list of columns contains at least one candidate column marked with a column label. And determining a column with the audience rating meeting the preset audience rating requirement in at least one candidate column as a target column, and determining that the preference label of the first account comprises a column label corresponding to the target column.
Illustratively, the first navigation record includes a plurality of sub-records, and the kth sub-record includes kth play time stamp information and column information to which the kth content belongs, where k is a positive integer.
When the first client plays the first multimedia content, information is collected based on preset frequency and sent to the server, and the server analyzes the information after receiving the information sent by the first client each time to obtain a sub record. For example, the first client sends information to the server every 30 seconds, and after sending information to the server for the 1 st time, the server receives and analyzes the first information to obtain the 1 st sub-record.
Illustratively, in the case of acquiring the kth sub-record, the kth playing image and the kth playing channel information sent by the first client are received.
The kth playing image is an image acquired when the first client plays the first multimedia content, and the first client identifies the kth playing image after acquiring the kth playing image and determines kth playing channel information.
That is, the first multimedia content played by the first client is composed of at least one multimedia content, and the user may have operations of changing channels and changing types of the multimedia content while viewing the multimedia content played by the first client.
For example, the first client plays the first multimedia content in a time period from 13:00 to 14:00, plays the multimedia content a (being a documentary program) in a time period from 13:00 to 13:45, and plays the multimedia content B (being a synthetic program) in a time period from 13:45 to 14:00, wherein the playing channel information corresponding to the multimedia content a is a first channel, and the playing channel information corresponding to the multimedia content B is a second channel.
The kth play time stamp information of the first multimedia content is determined based on the kth play image. The play time stamp information is used to indicate a time stamp of intercepting a play image, and the time stamp information can reflect a progress of the first multimedia content when the first multimedia content is played out under the channel.
And determining column information of the kth content based on the kth play channel information and the kth play time stamp information, wherein the column information of the kth content is used for indicating a column of the content of the first multimedia content played by the first client in the kth sub-record.
For example, the kth playing time stamp information is 13:00 on 1 month and 1 day in 2020, and at this time, the playing channel information corresponding to the first multimedia content is the first channel, and the first channel plays a music process program between 12:00 and 14:00 on 1 month and 1 day in 2020, so that the column to which the first multimedia content belongs is "music process", and the kth playing time stamp indicates that the playing progress of the music process program is 1 hour (1/2).
And in response to the fact that the number of the sub-records corresponding to the first browsing record reaches a preset number threshold, counting the plurality of sub-records, and determining a target playing channel meeting the requirement of the preset playing time length in the plurality of sub-records.
The ratio of the playing time length of the first multimedia content played on the first client through the target playing channel to the total playing time length of the first multimedia content played on the first client reaches the preset ratio requirement.
For example, the preset number threshold of sub-records is 100, and the preset ratio requirement refers to that the ratio of the playing duration of the target playing channel to the total playing duration is the highest in all the playing channels.
The first browsing record acquired by the server side comprises 150 sub-records, wherein the playing channel information of the first multimedia content in the 1 st to 50 th sub-records is a first channel, the playing channel information of the first multimedia content in the 51 st to 90 th sub-records is a second channel, and the playing channel information of the first multimedia content in the 91 st to 150 th sub-records is a third channel.
Since the time intervals of each sub-record are the same, the ratio of the playing time length of the first channel to the total playing time length is calculated to be 50/150=1/3, the ratio of the playing time length of the second channel to the total playing time length is calculated to be 40/150=4/15, and the ratio of the playing time length of the third channel to the total playing time length is calculated to be 60/150=2/5.
And determining the third channel as a target playing channel, wherein the ratio of the playing time length of the third channel to the total playing time length is highest.
And acquiring a column list played by the target playing channel in the historical time period, wherein the column list comprises at least one candidate column marked with a column label, and determining a column with the audience rating meeting the preset audience rating requirement in the at least one candidate column as a target column. And determining that the preference label of the first account comprises a column label corresponding to the target column.
For example, the target playing channel is a local television station channel, and candidate columns played by the target playing channel in the last day include a television play column, a music variety column, an cartoon column and a news column.
The column labels of the drama column comprise at least one of a drama name, a director name, a drama theme and a drama total duration.
The column labels of the music variety column comprise at least one of variety name, singer name, composer name, singing song, and total duration of variety.
The column labels of the cartoon column comprise at least one of cartoon names, dubbing actor names, director names, cartoon topics and cartoon total duration.
The column labels of the news column include at least one of a moderator name, a category of reporting events, and a daily news broadcast duration.
The column labels of the candidate columns can be obtained through at least one of (1) manual labeling, (2) keyword extraction and (3) model analysis.
Optionally, the preset viewing requirement is that the average rating of the column in the past month is highest among all candidate columns.
For example, if the target playing channel has only one candidate list, the label of the candidate list is used as the preference label of the first account.
For example, the target playing channel comprises 4 candidate columns, namely candidate column 1, candidate column 2, candidate column 3 and candidate column 4, wherein the average audience rating of each candidate column is 20%, 23%, 15% and 10% respectively.
The average audience rating of the candidate column 2 is 23% at most, the candidate column 2 is determined to be a target column, and the preference label of the first account number is determined to contain a column label corresponding to the candidate column 2.
Optionally, a second production list participating in producing the second multimedia content is determined based on the second browsing record, and the second production list includes the name of the producer of the second multimedia content.
For example, the second multimedia content is an electronic book, and the first production list includes names of authors and names of authors drawing a cover chart of the electronic book.
And determining a second content label of the second multimedia content based on the second browsing record, wherein the second content label is used for indicating the theme of the second multimedia content, and determining that the preference label of the first account comprises at least one of a second making list and the second content label.
For example, the second multimedia content is a novel of the present spy case type, and the second content tag is suspicion, case breaking, reasoning, spy, mystery.
The second content label can be obtained by (1) analyzing the first multimedia content by a worker, manually labeling the first multimedia content, (2) publishing or referring to a statistical keyword in an article, a blog and a comment of the first multimedia content in a social network according to the name of the first multimedia content, taking the keyword as the first content label, wherein the keyword is a word indicating that the occurrence frequency meets the preset frequency requirement, (3) inputting information disclosed by the first multimedia content or a file obtained after downloading the first multimedia content into a pre-training model, analyzing input data by the pre-training model, and outputting to obtain the first content label, wherein the type of the pre-training model is determined according to the type of the first multimedia content, for example, the first multimedia content is a language program, and then using a natural language model as the pre-training model.
Step 340, obtaining the first content based on the preference tag and the device connection information.
The first content is content to be recommended, and the first content includes an element associated with the device connection information.
Optionally, the method for acquiring the first content includes, but is not limited to, (1) acquiring the product content to be recommended based on the device connection information, acquiring the information content to be recommended based on the preference tag, and the like, taking the product content and the information content together as the first content, and (2) acquiring the content simultaneously containing the product to be recommended and the information to be recommended as the first content based on the device connection information and the preference tag.
1. Optionally, a content resource pool is acquired, wherein the content resource pool contains a plurality of candidate contents marked with content labels, and the content type is used for indicating elements contained in the candidate contents.
And determining the candidate content matched with the device type of the second device as the first candidate content in response to the fact that the content tag of the candidate content in the content resource pool is matched with the device type of the second device indicated by the device connection information.
And in response to the content tags of the candidate content in the content resource pool matching the preference tags, determining the candidate content matching the preference tags as a second candidate content.
And recommending the first candidate content and the second candidate content to the first account as the first content.
The device connection information indicates that the second device is a wired earphone, there is a candidate content whose content tag is a wired earphone storage box, the content tag of which matches the device connection information, the candidate content whose content tag is the wired earphone storage box is determined as a first candidate content, and the product for recommendation of the first candidate content is the wired earphone storage box.
The preference label is the name of a composer A, the first account is indicated to prefer to browse the works of the composer A when browsing the multimedia content, the content label is a 'composer A work B', the content label is matched with the preference label, candidate contents with the content label of 'composer A work B' are determined to be second candidate contents, and the information of the second candidate contents for recommendation is the composer A work B.
2. Optionally, a content resource pool is acquired, wherein the content resource pool contains a plurality of candidate contents marked with content labels, and the content type is used for indicating elements contained in the candidate contents.
And determining the candidate content matched with the device type of the second device as the first type of candidate content in response to the fact that the content tag of the candidate content in the content resource pool is matched with the device type of the second device indicated by the device connection information.
And in response to the content tags of the candidate contents in the first type of candidate contents being matched with the preference tags, determining the candidate contents matched with the preference tags as target candidate contents.
And recommending the target candidate content to the first account as the first content.
When matching analysis is performed on the ith candidate content in the content resource pool, determining the ith candidate content as a first type of candidate content in response to the similarity between the device type of the second device indicated by the device connection information and the content label corresponding to the ith candidate content reaching a first preset threshold, wherein i is a positive integer.
When matching analysis is carried out on the j-th candidate content in the first type of candidate contents, the j-th candidate content is determined to be the target candidate content in response to the fact that the similarity between the preference label and the content label corresponding to the j-th candidate content reaches a second preset threshold value, wherein j is a positive integer.
The device connection information indicates that the second device is a wired headset, and there is a content tag that matches the device connection information for the candidate content, the content tag comprising the candidate content for the wired headset receiver, the candidate content for the wireless headset, and the candidate content for the headset. Candidate contents whose content tags match the device connection information are determined as first candidate contents.
The preference tag is the name of the composer a and indicates that the first account prefers to browse the composition of the composer a when browsing the multimedia content. The complete content label of each candidate content in the first candidate content is as follows, a wired earphone storage box-a home C (a product wired earphone storage box for a home C expression), a wireless earphone-a home A (a product wireless earphone for a home A expression), and a headset-a home A (a product headset for a home A expression).
There are candidate contents whose content tags are "wireless headset-composer a", "headset-composer a", whose content tags match the preference tags, and these two candidate contents are determined as target candidate contents for recommending products spoken by composer a, including headsets and wireless headsets.
Step 350, pushing the first content to the third device logged in with the first account.
The third device may be the same as or different from the first device.
And after the application programs log in the first account, displaying the first content on a recommendation page of the application program, and recommending products to the first account.
The first device and the third device are not the same device, the first device is a smart phone, and the third device is a smart television.
When a user logs in the first account to browse the multimedia content by using the third device, the first content is displayed through a recommendation page of the third device.
In summary, in the content recommendation method provided by the application, when the first device is connected with the second device, the first device can acquire the device connection information of the second device, and use the device connection information as a basis for acquiring the first content, so that the data source during content recommendation is enlarged, the accuracy of an analysis result is improved, and the content meeting the user requirement is recommended for the first device or the third device logged in with the first account. Compared with the mode of determining the recommended content by only relying on the browsing record of the first account, the method can avoid the homogenization of the recommended content, help users expand interests, find the recommended content with potential preference and improve the recommending effect.
The first device is taken as a smart phone terminal, the second device is taken as a device supporting Bluetooth functions such as an automobile, a watch and a headset, and the third device is taken as a smart television terminal for illustration. A bluetooth communication connection can be established between the first device and the second device.
Fig. 4 is a schematic diagram of a content recommendation process provided in the present application, as shown in fig. 4, a first application 411 is installed in a smart phone terminal 410 to play a first multimedia content, a second application 421 is installed in a smart tv terminal 420 to play a second multimedia content, where the first multimedia content includes songs, electronic books, long audio, etc., and the second multimedia content includes tv programs, etc.
When the smart phone terminal 410 plays the first multimedia content through the first application 411, the first application 411 collects the song, the electronic book, and the playing/viewing record of the long audio, and sends the record to the server terminal 400.
When the smart tv 420 plays the second multimedia content through the second application 421, the second application 421 collects the playing image of the tv program and the channel information of the playing tv program, and sends the playing image and the channel information to the server 400, and the tv program analysis module 401 of the server 400 analyzes the column to which the content of the second multimedia content belongs.
When the smart phone terminal 410 establishes bluetooth connection with a second device (a device supporting bluetooth functions such as an automobile, a watch, and a headset), the smart phone terminal 410 collects a bluetooth name of the second device through the bluetooth name collection module 413 in the first application 411, sends the bluetooth name to the server terminal 400, and analyzes a device type of the second device through the bluetooth name analysis module 403 of the server terminal 400.
The user analysis module 402 of the server 400 analyzes songs, electronic books, long audio play/viewing records, columns to which the content of the second multimedia content belongs, device types of the second device, selects personalized advertisements from the advertisement library as the first content, and pushes the personalized advertisements to the device/client registered in the first account.
Fig. 5 is a flowchart based on the content recommendation method shown in fig. 4, which is performed by the server side 500, the first device 510, the second device 520, and the third device 530, and includes the following steps.
S511, the first device establishes a short-distance wireless transmission connection with the second device, and acquires device connection information of the second device.
Optionally, the short-range wireless transmission connection between the first device and the second device includes at least one of the following.
(1) The first equipment and the second equipment are connected through a Bluetooth connection mode.
(2) The first device serves as a wireless station, and the second device serves as a wireless access point to access the wireless station.
(3) The first device is used as a first wireless access point, the second device is used as a second wireless access point, and the first wireless access point and the second wireless access point access the same wireless station.
(4) The first equipment and the second equipment are connected in a Zigbee connection mode.
The first device is a smart phone, the second device is an earphone device for establishing bluetooth connection with the first device, and the device connection information of the second device includes a bluetooth name of the second device, where the bluetooth name refers to a name of the second device displayed in the first device when the bluetooth connection is first established between the first device and the second device.
For example, the device connection information of the second device is Bxse Comfort In-ear as follows. Bxse indicates the brand of the second device, in-ear indicates the device type of the second device as an embedded earphone, comfort indicates the device model of the second device.
That is, the device connection information indicates that the second device is a type Comfort embedded earphone developed by brand Bxse.
S512, the first device sends device connection information of the second device to the server.
The first device is internally provided with a first application program, the first account can be logged in through the first application program, and the first application program can analyze the device connection information of the second device to determine the device type of the second device. The first application is capable of playing the second multimedia content.
And S513, the first device sends a second browse record of the second multimedia content to the server side.
The second multimedia content browsed by the first account through the first application program is a plurality of songs singed by singer a, and the second browsed record includes a record of songs of singer a played by the first account in a historical time period.
Note that the order between step S512 and step S513 is arbitrary, and step S512 may be performed first and then step S513 may be performed, step S513 may be performed first and then step S512 may be performed, or step S512 and step S513 may be performed simultaneously.
And S531, the third device sends a first browse record of the first multimedia content to the server side.
The third device is internally provided with a second application program, the first account can be logged in through the second application program, and the second application program can play the first multimedia content.
The first multimedia content browsed by the first account through the second application program is a multi-channel television program played by the first channel, and the second browsed record includes records of a plurality of television programs in the first channel played by the first account in a historical time period.
Note that the order between step S513 and step S531 is arbitrary, and step S513 may be performed first and then step S531 may be performed, step S531 may be performed first and then step S513 may be performed, or step S513 and step S531 may be performed simultaneously.
S501, the server side determines the first content based on the device connection information, the first browsing record, and the second browsing record.
The type of the product or service to be recommended is determined based on the device type of the second device indicated by the device connection information.
For example, if the second device is an embedded earphone, the recommended embedded earphone, an earphone storage box matched with the embedded earphone, an earphone charging data line and the like can be used as the product content to be recommended.
And analyzing preference labels of the first account number when browsing the multimedia content based on the first browsing record and the second browsing record, and determining the expression form of the first content and other elements when recommending the product based on the preference labels.
For example, based on the first browsing record and the second browsing record, when the frequency of playing the song sung by the singer a is highest when the multimedia content is played by the first account is analyzed, and the preference label is determined as the singer a, a product related to the embedded earphone (second device) and referred to by the singer a is taken as a product to be recommended, and the content containing the product to be recommended is taken as the first content.
S502, the server pushes first content to first equipment logged in with a first account.
In this embodiment, the first device is different from the third device, and in some embodiments, if the first device is the same as the third device, the first device pushes the first content to different clients (e.g., the first application and the second application) that log in with the first account.
S503, the server pushes the first content to the third device logged in with the first account.
It should be noted that the order between the step S502 and the step S503 is arbitrary, and the step S502 may be performed first and then the step S503 may be performed, the step S503 may be performed first and then the step S502 may be performed, or the step S502 and the step S503 may be performed simultaneously.
In summary, in the content recommendation method provided by the application, when the first device is connected with the second device, the first device can acquire the device connection information of the second device, and use the device connection information as a basis for acquiring the first content, so that the data source during content recommendation is enlarged, the accuracy of an analysis result is improved, and the content meeting the user requirement is recommended for the first device or the third device logged in with the first account. Compared with the mode of determining the recommended content by only relying on the browsing record of the first account, the method can avoid the homogenization of the recommended content, help users expand interests, find the recommended content with potential preference and improve the recommending effect.
Fig. 6 is a block diagram illustrating a content recommendation apparatus according to an exemplary embodiment of the present application, which includes the following parts as shown in fig. 6.
A receiving module 610, configured to receive device connection information uploaded by a first device, where the device connection information is information related to a second device collected by the first device when the second device is connected to the first device, the first device is connected to the second device by a short-distance wireless transmission connection manner, and a first account is logged on the first device;
an obtaining module 620, configured to obtain first content based on the device connection information, where the first content is to-be-recommended content, and the first content includes an element associated with the device connection information;
And a recommending module 630, configured to push the first content to a third device that logs in to the first account, where the third device is the same as or different from the first device.
In an alternative embodiment, the device connection information includes at least one of the following:
A device name indicating a name of the second device in the first device when a connection is established with the first device;
a device model for indicating a model of the second device;
And the equipment parameter is used for indicating the operation parameter in the operation process of the second equipment.
In an alternative embodiment, the first device and the second device are connected by a Bluetooth connection, or
The first device is used as a wireless station, the second device is used as a wireless access point to access the wireless station, or
The first device is used as a first wireless access point, the second device is used as a second wireless access point, and the first wireless access point and the second wireless access point access the same wireless station, or
The first device and the second device are connected through a Zig6ee connection mode.
In an alternative embodiment, as shown in fig. 7, the apparatus further comprises:
A preference determining module 640, configured to obtain a content browsing record of a first account, where the content browsing record refers to a record of multimedia content browsed by at least one client logged in the first account in a historical period of time;
The obtaining module 620 is further configured to obtain the first content based on the preference tag and the device connection information.
In an alternative embodiment, the preference determining module 640 is further configured to obtain a first browsing record of a first multimedia content, or obtain a second browsing record of a second multimedia content, where the content types of the first multimedia content and the second multimedia content are different.
In an optional embodiment, the preference determining module 640 is further configured to receive playing channel information sent by a first client, where the playing channel information is used to indicate a playing channel when the first multimedia content is played, collect a playing image when the first client plays the first multimedia content, identify the playing image, determine the playing channel information of the first multimedia content, determine, based on the first browsing record, a list of columns played by the playing channel in a historical time period, where the list of columns includes at least one candidate column labeled with a column label, determine, as a target column, a column whose rating meets a preset viewing requirement in the at least one candidate column, and determine that a preference label of the first account includes a column label corresponding to the target column.
In an optional embodiment, the preference determining module 640 is further configured to receive the second browsing record sent by the second client, where the second browsing record is collected when the second client plays the second multimedia content, determine, based on the second browsing record, a second production list participating in producing the second multimedia content, where the second production list includes a name of a producer of the second multimedia content, determine, based on the second browsing record, a second content tag of the second multimedia content, where the second content tag is used to indicate a subject of the second multimedia content, and determine that a preference tag of the first account includes at least one of the second production list and the second content tag.
In an alternative embodiment, the obtaining module 620 is further configured to determine a device type of the second device based on the device connection information, determine, based on the device type of the second device, an association product associated with the second device, where an association exists between a function of the association product and a function of the second device, and obtain the first content based on the second device and the association product.
In an optional embodiment, the obtaining module 620 is further configured to obtain a device library, where the device library includes a plurality of candidate devices labeled with a device type tag and a device name, the device connection information includes a device name of the second device, and determine, in response to a device name of a first candidate device in the plurality of candidate devices matching the device name of the second device, a device type of the second device based on the device type tag of the first candidate device.
In an optional embodiment, the obtaining module 620 is further configured to determine, in response to the device type tag of the first candidate device, that a similarity between the device type tag of the first candidate device and a device type tag of a second candidate device in the device library meets a first similarity threshold, the second candidate device as the association product.
In an alternative embodiment, the obtaining module 620 is further configured to obtain a content resource pool, where the content resource pool includes a plurality of candidate contents marked with a content type, where the content type is used to indicate an element included in the candidate contents, and determine, as the first content, the candidate content that matches the second device or the associated product in response to that the content type of the candidate content exists in the content resource pool and matches the second device or the associated product.
In summary, in the content recommendation device provided by the application, when the first device is connected with the second device, the first device can acquire the device connection information of the second device, and use the device connection information as a basis for acquiring the first content, so that the data source during content recommendation is enlarged, the accuracy of an analysis result is improved, and the content meeting the user requirement is recommended for the first device or the third device logged in with the first account. Compared with the mode of determining the recommended content by only relying on the browsing record of the first account, the method can avoid the homogenization of the recommended content, help users expand interests, find the recommended content with potential preference and improve the recommending effect.
It should be noted that, in the content recommendation apparatus provided in the foregoing embodiment, only the division of the foregoing functional modules is illustrated, and in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to perform all or part of the functions described above. In addition, the content recommendation device and the content recommendation method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the content recommendation device and the content recommendation method are detailed in the method embodiments and are not described herein again.
Fig. 8 shows a block diagram of a computer device 800 provided in an exemplary embodiment of the application. The computer device 800 may be a smart phone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III, MPEG 3), MP4 (Moving Picture Experts Group Audio Layer IV, MPEG 4) player, notebook computer, or desktop computer. The computer device 800 may also be referred to by other names of user devices, portable terminals, laptop terminals, desktop terminals, and the like.
In general, computer device 800 includes a processor 801 and memory 802.
Processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 801 may be implemented in at least one hardware form of DSP (DIGITAL SIGNAL Processing), FPGA (Field-Programmable gate array), PLA (Programmable Logic Array ). The processor 801 may also include a main processor, which is a processor for processing data in a wake-up state, also called a CPU (Central Processing Unit ), and a coprocessor, which is a low-power processor for processing data in a standby state. In some embodiments, the processor 801 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 801 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.
Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 802 is used to store at least one instruction for execution by processor 801 to implement the content recommendation method provided by the method embodiments of the present application.
In some embodiments, the computer device 800 also includes some other components 803, the type and number of which other components 803 may be selected based on the functional needs of the computer device 800. Those skilled in the art will appreciate that the architecture shown in fig. 8 is not limiting and that more or fewer components than shown may be included or that certain components may be combined or that a different arrangement of components may be employed.
Alternatively, the computer readable storage medium may include a Read Only Memory (ROM), a random access Memory (RAM, random Access Memory), a Solid state disk (SSD, solid STATE DRIVES), an optical disk, or the like. The random access memory may include resistive random access memory (ReRAM, RESISTANCE RANDOM ACCESS MEMORY) and dynamic random access memory (DRAM, dynamic Random Access Memory), among others. The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
The embodiment of the application also provides a computer device, which comprises a processor and a memory, wherein at least one instruction, at least one section of program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one section of program, the code set or the instruction set is loaded and executed by the processor to realize the content recommendation method according to any one of the embodiments of the application.
The embodiment of the application also provides a computer readable storage medium, in which at least one instruction, at least one section of program, a code set or an instruction set is stored, where the at least one instruction, the at least one section of program, the code set or the instruction set is loaded and executed by a processor to implement the content recommendation method according to any one of the embodiments of the application.
Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the content recommendation method according to any of the above embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but rather, the application is to be construed as limited to the appended claims.