Object recommendation method, apparatus, and computer-readable storage medium

Abstract

The application provides an object recommendation method and device and a computer readable storage medium, relates to the technical field of computers, and can recommend objects in multiple fields to a user and improve the comprehensiveness of the recommended objects. The method comprises the following steps: obtaining a relative evaluation value of a target user for a target label and an average score of each object in multiple objects labeled by the target label; the multiple objects belong to multiple different fields, and the relative evaluation value indicates the closeness of the score of the target user for the target label to the average score of the target label; for each object, determining a recommendation value of the object according to the relative evaluation value and the average score of the object; the recommendation value has a positive correlation with the recommendation priority of the object; recommending a first object in the multiple objects to the target user; and the recommendation value of the first object is greater than a first threshold value.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to object recommendation methods, apparatus and computer-readable storage media. Background Technology

[0002] When a user has no explicit intention, object recommendation methods can be used to recommend objects that the user may be interested in. The application scenarios of object recommendation methods include single-domain scenarios and cross-domain scenarios.

[0003] In single-domain scenarios, existing recommendation methods include collaborative filtering-based recommendation methods and content-based recommendation methods.

[0004] In cross-domain scenarios, existing cross-domain recommendation methods typically train a model based on user data from the source domain and data from the target domain to obtain a mapping function, and then recommend corresponding objects from the target domain to the user based on the mapping function.

[0005] In the scenarios described above, existing object recommendation methods can only recommend objects from one domain to users, and cannot recommend objects from multiple domains. Therefore, the comprehensiveness of existing object recommendation methods is relatively low. Summary of the Invention

[0006] This application provides an object recommendation method, apparatus, and computer-readable storage medium, which can recommend objects from multiple fields to users, thereby improving the comprehensiveness of the recommended objects.

[0007] To achieve the above objectives, this application adopts the following technical solution: Firstly, an object recommendation method is provided, comprising: obtaining the relative rating value of a target user for a target tag and the average rating of each object among multiple objects labeled with the target tag; the multiple objects belong to multiple different domains, and the relative rating value indicates the similarity between the target user's rating of the target tag and the average rating of the target tag; for each object, determining the object's recommendation value based on the relative rating value and the object's average rating; the recommendation value is positively correlated with the object's recommendation priority; recommending the first object among the multiple objects to the target user; the recommendation value of the first object is greater than a first threshold.

[0008] Based on this scheme, compared with existing schemes, the scheme of this application obtains the relative evaluation value of the target user for the target tag and the average score of each object among the multiple objects labeled by the target tag. Then, for each object, the recommendation value of the object is determined based on the evaluation and the average score of the object. Finally, the first object among the multiple objects with a recommendation value greater than a first threshold is recommended to the target user. Since the multiple objects labeled by the target tag belong to multiple different domains, it is possible to recommend objects from multiple domains to the target user, thereby improving the comprehensiveness of the recommended objects.

[0009] In conjunction with the first aspect, in some embodiments of the first aspect, obtaining the relative evaluation value of the target user for the target tag includes: obtaining the number of multiple objects, a first number of each object in the multiple objects, a number of second objects in the multiple objects, and the target user's rating for each second object; the first number is the number of users associated with the object, and the target user has a rating behavior for the second object; determining the average rating of the target tag based on the number of multiple objects, the first number of each object in the multiple objects, and the average rating of each object in the multiple objects; determining the target user's rating for the target tag based on the number of second objects in the multiple objects, the target user's rating for each second object, and the first number of each second object; and determining the ratio of the average rating of the target tag to the target user's rating for the target tag as the relative evaluation value of the target tag.

[0010] Based on this scheme, the average rating of the target tag is determined by the number of multiple objects, the first number of each object in the multiple objects, and the average rating of each object in the multiple objects. The rating of the target user for the target tag is determined by the number of second objects in the multiple objects, the rating of the target user for each second object, and the first number of each second object. The ratio of the average rating of the target tag to the rating of the target user for the target tag is determined as the relative evaluation value of the target tag. This scheme can achieve the goal of obtaining the relative evaluation value of the target user for the target tag.

[0011] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: obtaining a preference value of a target user for each of a plurality of tags; the preference value is positively correlated with the target user's degree of liking for the tag; and identifying the tag with a preference value greater than a second threshold among the plurality of tags as the target tag.

[0012] Based on this scheme, by obtaining the target user's preference value for each of the multiple tags, the tags with preference values ​​greater than a second threshold are identified as target tags. Since the preference value is used to indicate the target user's degree of liking for the tag, it is possible to determine the tags that the target user prefers, thereby improving the accuracy of the recommended objects.

[0013] In conjunction with the first aspect, in some embodiments of the first aspect, for each tag, obtaining the tag's preference value includes: obtaining a second quantity corresponding to the target user and a second quantity corresponding to each user among multiple users; the second quantity is the number of objects associated with the user among the multiple objects labeled by the tag, and the value of the second quantity is not 0; the ratio of the second quantity of the target user to the third quantity is used as the target user's browsing value; the third quantity is the ratio of the sum of the second quantities of multiple users to the user quantity of multiple users; and the product of the browsing value and the relative evaluation value is used as the preference value.

[0014] Based on this scheme, by obtaining the second number corresponding to the target user and the second number corresponding to each of the multiple users, then using the ratio of the second number to the third number of the target user as the target user's browsing value, and finally using the product of the browsing value and the relative evaluation value as the preference value, it is possible to obtain the preference value of the tag.

[0015] Secondly, an object recommendation apparatus is provided for implementing the object recommendation method of the first aspect described above. The object recommendation apparatus includes modules, units, or means corresponding to the above method. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.

[0016] In conjunction with the second aspect, in some embodiments of the second aspect, the object recommendation device includes: an acquisition module and a processing module; the acquisition module is used to acquire the relative evaluation value of a target user for a target tag and the average rating of each object among multiple objects labeled with the target tag; the multiple objects belong to multiple different domains, and the relative evaluation value indicates the similarity between the target user's rating of the target tag and the average rating of the target tag; the processing module is used to determine the recommendation value of each object based on the relative evaluation value and the average rating of the object; the recommendation value is positively correlated with the recommendation priority of the object; the processing module is also used to recommend a first object among the multiple objects to the target user; the recommendation value of the first object is greater than a first threshold.

[0017] In conjunction with the second aspect, in some embodiments of the second aspect, the acquisition module is used to acquire the relative evaluation value of the target user for the target tag, including: acquiring the number of multiple objects, a first number of each object in the multiple objects, a number of second objects in the multiple objects, and the target user's rating for each second object; the first number is the number of users associated with the object, and the target user has rating behavior for the second object; determining the average rating of the target tag based on the number of multiple objects, the first number of each object in the multiple objects, and the average rating of each object in the multiple objects; determining the target user's rating for the target tag based on the number of second objects in the multiple objects, the target user's rating for each second object, and the first number of each second object; and determining the ratio of the average rating of the target tag to the target user's rating for the target tag as the relative evaluation value of the target tag.

[0018] In conjunction with the second aspect, in some embodiments of the second aspect, the processing module is further configured to: obtain the target user's preference value for each of the multiple tags; the preference value is positively correlated with the target user's degree of preference for the tag; and identify the tag with a preference value greater than a second threshold among the multiple tags as the target tag.

[0019] In conjunction with the second aspect, in some embodiments of the second aspect, for each tag, the processing module is further configured to obtain the tag's preference value, including: obtaining a second quantity corresponding to the target user and a second quantity corresponding to each user among multiple users; the second quantity is the number of objects associated with the user among the multiple objects labeled by the tag, and the value of the second quantity is not 0; the ratio of the second quantity of the target user to the third quantity is used as the target user's browsing value; the third quantity is the ratio of the sum of the second quantities of multiple users to the user quantity of multiple users; and the product of the browsing value and the relative evaluation value is used as the preference value.

[0020] Thirdly, an object recommendation apparatus is provided, comprising: at least one processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method provided by the first aspect and any possible implementation thereof.

[0021] Fourthly, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of an object recommendation device, the object recommendation device is enabled to perform the method provided in the first aspect and any possible implementation thereof.

[0022] Fifthly, a computer program product containing instructions is provided that, when run on a computer, enables the computer to perform the methods provided in the first aspect and any possible implementation thereof.

[0023] In a sixth aspect, a chip system is provided, comprising: a processor and an interface circuit; the interface circuit being configured to receive a computer program or instructions and transmit them to the processor; the processor being configured to execute the computer program or instructions to cause the chip system to perform the methods provided in the first aspect and any of its possible embodiments.

[0024] The technical effects of any one of the second to sixth aspects can be found in the technical effects of the different embodiments of the first aspect described above, and will not be repeated here. Attached Figure Description

[0025] Figure 1 This application provides an architectural diagram of an object recommendation system. Figure 2 A flowchart illustrating an object recommendation method provided in this application; Figure 3 A flowchart illustrating yet another object recommendation method provided in this application; Figure 4 A flowchart illustrating yet another object recommendation method provided in this application; Figure 5 A flowchart illustrating yet another object recommendation method provided in this application; Figure 6 A flowchart illustrating yet another object recommendation method provided in this application; Figure 7 A schematic diagram of the structure of an object recommendation device provided in this application; Figure 8 A schematic diagram of another object recommendation device provided in this application. Detailed Implementation

[0026] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0027] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0028] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0029] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0030] It is understood that in this application, "when," "if," and "if" all refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require that there must be a judgment action when implemented, nor do they imply any other limitations.

[0031] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0032] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments and implementation methods of the various embodiments in this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the implementation methods of the various embodiments are consistent and can be mutually referenced. The technical features in different embodiments and between the implementation methods of the various embodiments can be combined according to their inherent logical relationships to form new embodiments, implementation methods, implementation methods, or implementation approaches. The following embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0033] When a user has no explicit intention, object recommendation methods can be used to recommend objects that the user may be interested in. The application scenarios of object recommendation methods include single-domain scenarios and cross-domain scenarios.

[0034] In single-domain scenarios, existing recommendation methods include collaborative filtering-based recommendation methods and content-based recommendation methods.

[0035] Among them, the collaborative filtering-based recommendation method generates a user-object rating matrix based on the user's historical rating of the object or the user's implicit rating of the object, when the user's historical data exists in the domain.

[0036] Content-based recommendation methods recommend objects to users based on the content of the objects, without relying on the user's historical data. They are often used for cold starts in recommendation systems and as a supplement to collaborative filtering-based recommendation methods.

[0037] In cross-domain scenarios, existing cross-domain recommendation methods typically train a model based on user data from the source domain and data from the target domain to obtain a mapping function, and then recommend corresponding objects from the target domain to the user based on the mapping function.

[0038] In the scenarios described above, existing object recommendation methods can only recommend objects from one domain to users, and cannot recommend objects from multiple domains. Therefore, the comprehensiveness of existing object recommendation methods is relatively low.

[0039] To address the aforementioned issues, this application provides an object recommendation method: obtaining the relative rating of a target user for a target tag and the average rating of each object among multiple objects labeled with the target tag; the multiple objects belong to multiple different domains, and the relative rating indicates the similarity between the target user's rating of the target tag and the average rating of the target tag; for each object, determining the object's recommendation value based on the relative rating and the object's average rating; the recommendation value is positively correlated with the object's recommendation priority; recommending the first object among multiple objects to the target user; the recommendation value of the first object is greater than a first threshold.

[0040] Based on this scheme, compared with existing schemes, the scheme of this application obtains the relative evaluation value of the target user for the target tag and the average score of each object among the multiple objects labeled by the target tag. Then, for each object, the recommendation value of the object is determined based on the evaluation and the average score of the object. Finally, the first object among the multiple objects with a recommendation value greater than a first threshold is recommended to the target user. Since the multiple objects labeled by the target tag belong to multiple different domains, it is possible to recommend objects from multiple domains to the target user, thereby improving the comprehensiveness of the recommended objects.

[0041] Figure 1 This is a schematic diagram of the architecture of an object recommendation system provided in this application. The technical solutions of the embodiments of this application can be applied to... Figure 1 The object recommendation system shown is as follows: Figure 1As shown, the object recommendation system 10 includes an object recommendation device 11 and an electronic device 12.

[0042] The object recommendation device 11 is directly or indirectly connected to the electronic device 12. This connection can be wired or wireless, and this embodiment of the application does not limit the connection.

[0043] The object recommendation device 11 can be used to receive data from the electronic device 12.

[0044] Electronic device 12 can be used to send data to object recommendation device 11.

[0045] It should be noted that the object recommendation device 11 and the electronic device 12 can be independent devices or integrated into the same device; this application does not make specific limitations in this regard.

[0046] When the object recommendation device 11 and the electronic device 12 are integrated into the same device, the communication method between the object recommendation device 11 and the electronic device 12 is the same as the communication method between internal modules of the device. In this case, the communication process between the two is the same as the communication process between the object recommendation device 11 and the electronic device 12 when they are independent of each other.

[0047] In the following embodiments provided in this application, the object recommendation device 11 and the electronic device 12 are described as being configured independently of each other.

[0048] In practical applications, the object recommendation method provided in this application embodiment can be applied to the object recommendation device 11, or to the devices included in the object recommendation device 11.

[0049] The object recommendation method provided in this application embodiment will be described below with reference to the accompanying drawings, taking the application of the object recommendation method to the object recommendation device 11 as an example.

[0050] Figure 2 A flowchart illustrating an object recommendation method provided in this application is shown below. Figure 2 As shown, the method includes the following steps: S201, The object recommendation device obtains the relative evaluation value of the target user for the target tag and the average score of each object among the multiple objects labeled by the target tag.

[0051] Among them, multiple objects belong to multiple different domains, and the relative rating value indicates how similar the target user's rating of the target tag is to the average rating of the target tag.

[0052] It should be noted that the target tag can be the intellectual property (IP) of the object. IP can be understood as a collective term for all objects (literature, film and television, animation, games, etc.) with the same level of recognizability.

[0053] Multiple objects tagged with a target tag can have an adaptation relationship with each other; for example, one object might be a novel, and another object might be a movie adapted from that novel. Alternatively, multiple objects tagged with a target tag can have a derivative relationship; for example, one object might be a movie, and another object might be the original music of that movie or a derivative comic book of that movie. Or, multiple objects tagged with a target tag can be a series of objects; for example, multiple objects might be a series of movies. Multiple objects tagged with a target tag can also share the same background.

[0054] An object can have multiple tags at the same time.

[0055] The field to which the object belongs may include the fields of commodities, music, literature, or film. Of course, the field to which the object belongs may also include other fields, and this application does not impose any specific restrictions on this.

[0056] When the object belongs to the film field, the object can be film A. When the object belongs to the music field, the object can be music D.

[0057] For example, if the target tag is "xx universe", the multiple objects labeled by the target tag can include movies from the xx universe, the original music from movies from the xx universe, derivative comics from the xx universe, and original novels from the xx universe.

[0058] As one possible implementation method, combined Figure 1 The object recommendation device receives a message from an electronic device, which includes the target user's relative rating of the target tag and the average rating of each object among the multiple objects labeled with the target tag.

[0059] As another possible implementation method, combined with Figure 1 The object recommendation device receives a message from an electronic device, which includes the average rating of each object among multiple objects labeled with the target tag, the number of multiple objects, the first number of each object among multiple objects, the number of second objects among multiple objects, and the target user's rating for each second object. The object recommendation device obtains the average rating of each object among multiple objects labeled with the target tag, the number of multiple objects, the first number of each object among multiple objects, the number of second objects among multiple objects, and the target user's rating for each second object from the message.

[0060] The object recommendation device determines the average score of the target tag based on the number of multiple objects, the first number of each object among the multiple objects, and the average score of each object among the multiple objects.

[0061] The object recommendation device determines the target user's rating of the target tag based on the number of second objects among multiple objects, the target user's rating of each second object, and the first number of each second object.

[0062] The object recommendation device determines the relative evaluation value of the target tag as the ratio of the average rating of the target tag to the rating of the target user on the target tag.

[0063] It should be noted that for a detailed description of this possible implementation method, please refer to the relevant description in the subsequent sections of the specific implementation method of this application, which will not be described here.

[0064] S202, The object recommendation device determines the recommended value of each object based on the relative evaluation value and the average score of the object.

[0065] Among them, the recommendation value is positively correlated with the recommendation priority of the object.

[0066] It should be noted that the higher an object's recommendation score, the more likely that object will be recommended.

[0067] As one possible implementation, the object recommendation device determines, for each object, a relative rating, the object's average rating, and the object's recommendation value, satisfying the following relationship: Rq=q×r Where Rq represents the object's recommendation value, q represents the relative evaluation value, and r represents the object's average rating.

[0068] For example, the object recommendation device multiplies the relative rating value of the first object by the average rating of the first object, and determines the product as the recommendation value of the first object.

[0069] For the second object, the object recommendation device multiplies the relative evaluation value by the average rating of the second object, and determines the product as the recommendation value for the second object.

[0070] For the third object, the object recommendation device multiplies the relative evaluation value by the average rating of the third object, and determines the product as the recommendation value for the third object.

[0071] In this manner, the object recommendation device determines the recommendation value for each object.

[0072] S203, The object recommendation device recommends the first object among multiple objects to the target user.

[0073] Among them, the recommendation value of the first object is greater than the first threshold.

[0074] It should be noted that the first threshold can be 5, or the first threshold can be 6. Of course, the first threshold can also have other values, and this application does not impose specific restrictions on this.

[0075] As one possible implementation, the object recommendation device determines whether the recommendation value of the first object is greater than a first threshold. If it is, the first object is determined to be the first object; otherwise, the first object is determined not to be the first object.

[0076] The object recommendation device determines whether the recommendation value of the second object is greater than the first threshold. If it is, the second object is determined to be the first object; otherwise, the second object is determined not to be the first object.

[0077] The object recommendation device determines whether the recommendation value of the third object is greater than the first threshold. If it is, the third object is determined to be the first object; otherwise, the third object is determined not to be the first object.

[0078] Similarly, the object recommendation device makes the above judgment for each object to determine the first object among multiple objects.

[0079] Then, the object recommendation device recommends the first object among multiple objects to the target user through the object recommendation channel.

[0080] It should be noted that, in this possible implementation, the specific scheme by which the object recommendation device recommends objects to the target user through the object recommendation channel can refer to existing schemes, and will not be described in this application.

[0081] Based on this scheme, compared with existing schemes, the scheme of this application obtains the relative evaluation value of the target user for the target tag and the average score of each object among the multiple objects labeled by the target tag. Then, for each object, the recommendation value of the object is determined based on the evaluation and the average score of the object. Finally, the first object among the multiple objects with a recommendation value greater than a first threshold is recommended to the target user. Since the multiple objects labeled by the target tag belong to multiple different domains, it is possible to recommend objects from multiple domains to the target user, thereby improving the comprehensiveness of the recommended objects.

[0082] The above is a general description of the object recommendation method provided in this application. The following will provide a further explanation of the object recommendation method provided in this application in conjunction with the accompanying drawings.

[0083] In one design, Figure 3 A flowchart illustrating another object recommendation method provided in this application is shown below. Figure 3 As shown in the specific embodiment of this application, the object recommendation device obtains the relative evaluation value of the target user for the target tag, which may specifically include the following steps: S301, The object recommendation device obtains the number of multiple objects, the first number of each object among the multiple objects, the second number of the multiple objects, and the target user's rating for each second object.

[0084] The first quantity refers to the number of users who have a relationship with the object, and the target users have rating behavior towards the second object.

[0085] It should be noted that the association relationship can be a browsing relationship, or it can be a purchase relationship.

[0086] Taking movie A as the object and browsing relationship as an example, the first quantity of the object can be the number of users who have browsed movie A.

[0087] As one possible implementation method, combined Figure 1 The object recommendation device receives a message from an electronic device, which includes the number of multiple objects, a first number of each of the multiple objects, a second number of the multiple objects, and the target user's rating for each second object. The object recommendation device obtains the number of multiple objects, the first number of each of the multiple objects, the second number of the multiple objects, and the target user's rating for each second object from the message.

[0088] S302, The object recommendation device determines the average score of the target label based on the number of multiple objects, the first number of each object among the multiple objects, and the average score of each object among the multiple objects.

[0089] As one possible implementation, the object recommendation device determines that the number of multiple objects, the first number of each object in the multiple objects, the average score of each object in the multiple objects, and the average score of the target label satisfy the following relationship: R=

[0090] Where R represents the average score of the target label, and m represents the number of objects. This represents the average rating of the i-th object. This represents the first quantity of the i-th object.

[0091] S303, the object recommendation device determines the target user's rating of the target tag based on the number of second objects among multiple objects, the target user's rating of each second object, and the first quantity of each second object.

[0092] As one possible implementation, the object recommendation device determines that the number of second objects among multiple objects, the target user's rating for each second object, the first number of each second object, and the target user's rating for the target tag satisfy the following relationship: E=

[0093] Where E represents the target user's rating of the target tag, and t represents the number of second objects among multiple objects. This represents the target user's rating of the i-th second object. This represents the first quantity of the i-th second object.

[0094] S304. The object recommendation device determines the relative evaluation value of the target tag as the ratio of the average rating of the target tag to the rating of the target user on the target tag.

[0095] As one possible implementation, taking the implementations in S302 and S303 above as an example, the object recommendation device determines the relative evaluation value q=R / E of the target label.

[0096] Based on this scheme, the average rating of the target tag is determined by the number of multiple objects, the first number of each object in the multiple objects, and the average rating of each object in the multiple objects. The rating of the target user for the target tag is determined by the number of second objects in the multiple objects, the rating of the target user for each second object, and the first number of each second object. The ratio of the average rating of the target tag to the rating of the target user for the target tag is determined as the relative evaluation value of the target tag. This scheme can achieve the goal of obtaining the relative evaluation value of the target user for the target tag.

[0097] In one design, Figure 4 A flowchart illustrating another object recommendation method provided in this application is shown below. Figure 4 As shown, prior to S201, the object recommendation method provided in this application may also include the following steps: S401, The object recommendation device obtains the target user's preference value for each of the multiple tags.

[0098] Among them, the preference value is positively correlated with the target user's degree of liking for the tag.

[0099] As one possible implementation method, combined Figure 1 The object recommendation device receives a message from an electronic device, which includes the target user's preference value for each of the multiple tags. The object recommendation device obtains the target user's preference value for each of the multiple tags from the message.

[0100] As another possible implementation method, combined with Figure 1 The object recommendation device receives a message from an electronic device, which includes obtaining a second quantity corresponding to the target user and a second quantity corresponding to each of the multiple users. Then, the ratio of the second quantity to the third quantity of the target user is used as the browsing value of the target user. Finally, the product of the browsing value and the relative evaluation value is used as the preference value.

[0101] The second quantity is the number of objects that are associated with the user among the multiple objects labeled with the tag. The value of the second quantity is not 0. The third quantity is the ratio of the sum of the second quantities of multiple users to the total number of users of multiple users.

[0102] It should be noted that for a detailed description of this possible implementation method, please refer to the relevant description in the subsequent sections of the specific implementation method of this application, which will not be described here.

[0103] S402, The object recommendation device identifies the tag with a preference value greater than the second threshold among multiple tags as the target tag.

[0104] It should be noted that the second threshold can be 1, or it can be the average of multiple preference values. Of course, the second threshold can also have other values, and this application does not impose any specific restrictions on this.

[0105] As one possible implementation, the object recommendation device determines whether the preference value of the first tag is greater than a second threshold. If so, the first tag is determined to be the target tag; otherwise, the first tag is determined not to be the target tag.

[0106] The object recommendation device determines whether the preference value of the second tag is greater than a second threshold. If it is, the second tag is determined to be the target tag; otherwise, the second tag is determined not to be the target tag.

[0107] The object recommendation device determines whether the preference value of the third tag is greater than the second threshold. If it is, the third tag is determined to be the target tag; otherwise, the third tag is determined not to be the target tag.

[0108] Similarly, the object recommendation device performs the above judgment for each tag to obtain the target tag.

[0109] Based on this scheme, by obtaining the target user's preference value for each of the multiple tags, the tags with preference values ​​greater than a second threshold are identified as target tags. Since the preference value is used to indicate the target user's degree of liking for the tag, it is possible to determine the tags that the target user prefers, thereby improving the accuracy of the recommended objects.

[0110] In one design, Figure 5 A flowchart illustrating another object recommendation method provided in this application is shown below. Figure 5 As shown, for the above S401, the object recommendation device obtains the preference value of each tag, which may specifically include the following steps: S501, The object recommendation device obtains the second quantity corresponding to the target user and the second quantity corresponding to each user among the multiple users.

[0111] The second quantity is the number of objects that are associated with the user among the multiple objects labeled with the tag, and the value of the second quantity is not 0.

[0112] Taking browsing relationships as an example, the second quantity of the target user or the user can specifically be the number of objects that the target user or the user has browsed among the multiple objects marked with tags.

[0113] As one possible implementation method, combined Figure 1 The object recommendation device receives a message from an electronic device, which includes a second quantity corresponding to the target user and a second quantity corresponding to each of the multiple users. The object recommendation device obtains the second quantity corresponding to the target user and the second quantity corresponding to each of the multiple users from the message.

[0114] S502, The object recommendation device uses the ratio of the second number to the third number of target users as the browsing value of the target users.

[0115] The third quantity is the ratio of the sum of the second quantities of multiple users to the total number of users.

[0116] As one possible implementation, the object recommendation device adds up the second quantity of each user among multiple users to obtain a sum, and uses the ratio of the sum to the number of users among multiple users as the third quantity.

[0117] The object recommendation device uses the ratio of the second number to the third number of target users as the target user's browsing value p.

[0118] S503, The object recommendation device uses the product of the browsing value and the relative evaluation value as the preference value.

[0119] As one possible implementation, the object recommendation device determines L = p × q.

[0120] Where L represents the preference value, p represents the browsing value, and q represents the relative evaluation value.

[0121] Based on this scheme, by obtaining the second number corresponding to the target user and the second number corresponding to each of the multiple users, then using the ratio of the second number to the third number of the target user as the browsing value of the target user, and finally using the product of the browsing value and the relative evaluation value as the preference value, it is possible to obtain the preference value of the tag.

[0122] In one design, Figure 6 A flowchart illustrating another object recommendation method provided in this application is shown below. Figure 6As shown, the object recommendation method provided in this application may specifically include the following steps: S601, The object recommendation device obtains the target user's preference value for each of the multiple tags.

[0123] It should be noted that the specific description of S601 can be found in the relevant description of S401 above, and will not be repeated here.

[0124] S602, The object recommendation device determines the relative evaluation value of the target tag as the ratio of the average rating of the target tag to the rating of the target user on the target tag.

[0125] It should be noted that the specific explanation of S602 can be found in the relevant explanation of S303 above, and will not be repeated here.

[0126] S603, The object recommendation device recommends the first object among multiple objects to the target user.

[0127] It should be noted that the specific description of S603 can be found in the relevant description of S203 above, and will not be repeated here.

[0128] S604. After detecting data generated by the target user, the object recommendation device recommends new objects to the target user based on the first object and in combination with a content-based recommendation method.

[0129] S605, The object recommendation device displays new objects.

[0130] As one possible implementation, the display screen of the object recommendation device shows new objects.

[0131] The foregoing mainly describes the solution provided by the embodiments of this application from the perspective of the object recommendation device executing the object recommendation method. To achieve the above functions, the object recommendation device includes hardware structures and / or software modules corresponding to each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0132] This application embodiment can divide the object recommendation device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation. Furthermore, "module" here can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0133] When using functional module division Figure 7 A schematic diagram of an object recommendation device is shown. Figure 7 As shown, the object recommendation device 70 includes an acquisition module 701 and a processing module 702.

[0134] In some embodiments, the object recommendation device 70 may further include a storage module ( Figure 7 (not shown in the image) is used to store program instructions and data.

[0135] The acquisition module 701 is used to acquire the relative evaluation value of the target user for the target tag and the average rating of each object among multiple objects labeled by the target tag; the multiple objects belong to multiple different domains, and the relative evaluation value indicates the similarity between the target user's rating of the target tag and the average rating of the target tag; the processing module 702 is used to determine the recommendation value of each object based on the relative evaluation value and the average rating of the object; the recommendation value is positively correlated with the recommendation priority of the object; the processing module 702 is also used to recommend the first object among the multiple objects to the target user; the recommendation value of the first object is greater than a first threshold.

[0136] Optionally, the acquisition module 701 is used to acquire the relative evaluation value of the target user for the target tag, including: acquiring the number of multiple objects, the first number of each object in the multiple objects, the number of second objects in the multiple objects, and the target user's rating for each second object; the first number is the number of users associated with the object, and the target user has rating behavior for the second object; determining the average rating of the target tag based on the number of multiple objects, the first number of each object in the multiple objects, and the average rating of each object in the multiple objects; determining the target user's rating for the target tag based on the number of second objects in the multiple objects, the target user's rating for each second object, and the first number of each second object; and determining the ratio of the average rating of the target tag to the target user's rating for the target tag as the relative evaluation value of the target tag.

[0137] Optionally, the processing module 702 is further configured to: obtain the target user's preference value for each of the multiple tags; the preference value is positively correlated with the target user's degree of preference for the tag; and identify the tag with the preference value greater than a second threshold among the multiple tags as the target tag.

[0138] Optionally, for each tag, the processing module 702 is further configured to obtain the tag's preference value, including: obtaining a second quantity corresponding to the target user and a second quantity corresponding to each user among multiple users; the second quantity is the number of objects with a relationship to the user among the multiple objects labeled by the tag, and the value of the second quantity is not 0; the ratio of the second quantity of the target user to the third quantity is used as the target user's browsing value; the third quantity is the ratio of the sum of the second quantities of multiple users to the user quantity of multiple users; and the product of the browsing value and the relative evaluation value is used as the preference value.

[0139] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0140] When the functions of the above modules are implemented in hardware... Figure 8 A schematic diagram of an object recommendation device is shown. Figure 8 As shown, the object recommendation device 80 includes a processor 801, a memory 802, and a bus 803. The processor 801 and the memory 802 can be connected via the bus 803.

[0141] Processor 801 is the control center of object recommendation device 80. It can be a single processor or a collective term for multiple processing elements. For example, processor 801 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0142] As one embodiment, processor 801 may include one or more CPUs, for example Figure 8 CPU 0 and CPU 1 are shown in the diagram.

[0143] The memory 802 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0144] As one possible implementation, the memory 802 can exist independently of the processor 801. The memory 802 can be connected to the processor 801 via a bus 803 and is used to store instructions or program code. When the processor 801 calls and executes the instructions or program code stored in the memory 802, it can implement the object recommendation method provided in the embodiments of this application.

[0145] In another possible implementation, the memory 802 can also be integrated with the processor 801.

[0146] The 803 bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, and control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0147] It should be pointed out that, Figure 8 The structure shown does not constitute a limitation on the recommended device 80 for this object. Except... Figure 8 In addition to the components shown, the recommended device 80 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0148] As an example, combined Figure 7 The functions implemented by the acquisition module 701 and the processing module 702 in the object recommendation device 70 are the same as those of the acquisition module 701 and the processing module 702. Figure 8 The processor 801 in it has the same function.

[0149] Optional, such as Figure 8 As shown, the object recommendation device 80 provided in this application embodiment may further include a communication interface 804.

[0150] Communication interface 804 is used to connect to other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 804 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0151] In one possible implementation, the communication interface 804 in the object recommendation device 80 provided in this application embodiment can also be integrated into the processor 801, and this application embodiment does not specifically limit this.

[0152] As a possible product form, the object recommendation device of this application embodiment can also be implemented using the following: one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0153] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0154] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed, causes a computer to perform the various steps in the method flow shown in the above method embodiments.

[0155] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform the various steps in the method flow shown in the above-described method embodiments.

[0156] This application provides a chip system, including: a processor and an interface circuit; the interface circuit is used to receive computer programs or instructions and transmit them to the processor; the processor is used to execute the computer programs or instructions so that the chip system performs each step in the method flow shown in the above method embodiments.

[0157] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in a purpose-specific ASIC. In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0158] Since the object recommendation device, computer-readable storage medium, and computer program product provided in this embodiment can be applied to the object recommendation method provided in this embodiment, the technical effects they can achieve can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0159] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0160] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. An object recommendation method, characterized in that, The method includes: Obtain the relative rating of the target user for the target tag and the average rating of each object among multiple objects labeled by the target tag; the multiple objects belong to multiple different domains, and the relative rating is the ratio of the average rating of the target tag to the rating of the target user for the target tag; For each object, a recommendation value is determined based on the relative evaluation value and the object's average rating; the recommendation value is positively correlated with the object's recommendation priority. The first object among the plurality of objects is recommended to the target user; the recommendation value of the first object is greater than a first threshold.

2. The method according to claim 1, characterized in that, Obtaining the relative evaluation value of the target user for the target tag includes: The number of the plurality of objects, a first number of each of the plurality of objects, a second number of the plurality of objects, and the rating of each second object by the target user are obtained; the first number is the number of users associated with the object, and the target user has rating behavior for the second object; The average score of the target label is determined based on the number of the plurality of objects, the first number of each object in the plurality of objects, and the average score of each object in the plurality of objects; The target user's rating of the target tag is determined based on the number of second objects among the plurality of objects, the target user's rating of each second object, and the first number of each second object; The ratio of the average rating of the target tag to the rating of the target user for the target tag is determined as the relative evaluation value of the target tag.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the target user's preference value for each of the multiple tags; the preference value is positively correlated with the target user's degree of liking for the tags; The tags with a preference value greater than a second threshold among the multiple tags are identified as the target tags.

4. The method according to claim 3, characterized in that, For each tag, obtain the preference value for that tag, including: Obtain the second quantity corresponding to the target user and the second quantity corresponding to each user among the multiple users; the second quantity is the number of objects that are associated with the user among the multiple objects labeled by the tag, and the value of the second quantity is not 0; The ratio of the second number to the third number of target users is taken as the browsing value of the target user; the third number is the ratio of the sum of the second numbers of the multiple users to the total number of users of the multiple users; The product of the browsing value and the relative evaluation value is used as the preference value.

5. An object recommendation device, characterized in that, The object recommendation device includes: an acquisition module and a processing module; The acquisition module is used to acquire the relative evaluation value of the target user for the target tag and the average score of each object among the multiple objects labeled by the target tag; the multiple objects belong to multiple different domains, and the relative evaluation value is the ratio of the average score of the target tag to the score of the target user for the target tag; The processing module is used to determine a recommendation value for each object based on the relative evaluation value and the object's average rating; the recommendation value is positively correlated with the object's recommendation priority. The processing module is further configured to recommend a first object among the plurality of objects to the target user; the recommendation value of the first object is greater than a first threshold.

6. The object recommendation device according to claim 5, characterized in that, The acquisition module is used to acquire the relative evaluation value of the target user for the target tag, including: The number of the plurality of objects, a first number of each of the plurality of objects, a second number of the plurality of objects, and the rating of each second object by the target user are obtained; the first number is the number of users associated with the object, and the target user has rating behavior for the second object; The average score of the target label is determined based on the number of the plurality of objects, the first number of each object in the plurality of objects, and the average score of each object in the plurality of objects; The target user's rating of the target tag is determined based on the number of second objects among the plurality of objects, the target user's rating of each second object, and the first number of each second object; The ratio of the average rating of the target tag to the rating of the target user on the target tag is determined as the relative evaluation value of the target tag.

7. The object recommendation device according to claim 5 or 6, characterized in that, The processing module is further configured to: Obtain the target user's preference value for each of the multiple tags; the preference value is positively correlated with the target user's degree of liking for the tags; The tags with a preference value greater than a second threshold among the multiple tags are identified as the target tags.

8. The object recommendation device according to claim 7, characterized in that, For each tag, the processing module is further configured to obtain the preference value of the tag, including: Obtain the second quantity corresponding to the target user and the second quantity corresponding to each user among the multiple users; the second quantity is the number of objects that are associated with the user among the multiple objects labeled by the tag, and the value of the second quantity is not 0; The ratio of the second number to the third number of target users is taken as the browsing value of the target user; the third number is the ratio of the sum of the second numbers of the multiple users to the total number of users of the multiple users; The product of the browsing value and the relative evaluation value is used as the preference value.

9. An object recommendation device, characterized in that, The object recommendation device includes: a processor coupled to a memory for storing programs or instructions that, when executed by the processor, cause the device to perform the method as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they cause the computer to perform the method as described in any one of claims 1 to 4.

Images