CN114887333A

CN114887333A - Recommendation method and device for virtual pet pairing

Info

Publication number: CN114887333A
Application number: CN202210444117.3A
Authority: CN
Inventors: 贾彤
Original assignee: New Ruipeng Pet Healthcare Group Co Ltd
Current assignee: New Ruipeng Pet Healthcare Group Co Ltd
Priority date: 2022-04-26
Filing date: 2022-04-26
Publication date: 2022-08-12

Abstract

The embodiment of the application discloses a recommendation method and a recommendation device for virtual pet pairing, wherein the method comprises the following steps: acquiring demand information of a first user for offspring of the virtual pet of the first user and data information of the virtual pet of the first user; determining data information of a virtual pet of a second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user; determining a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user; recommending at least one target virtual pet to be matched of the virtual pet of the first user to the first user based on the target matching degree. The method and the device for the virtual pet breeding can recommend the virtual pet to be bred to the user in a targeted manner, and the breeding success rate of the virtual pet is effectively improved.

Description

Recommendation method and device for virtual pet pairing

Technical Field

The application relates to the internet technology, is applied to the field of big data and pet matching and the like, and particularly relates to a recommendation method and device for virtual pet matching.

Background

With the development of economy and the continuous improvement of living standard in recent years, people seek different ways of spiritual comfort and trusting while pursuing rich physical life, and the feeding of pets gradually becomes one of ways of spiritual comfort and trusting for people in large cities in recent years, and the demand for pet companions is increasing, but many people have inconvenience for feeding physical pets or feel that the feeding of physical pets is troublesome, but the spiritual trusting is needed, so that emerging virtual pets are born accordingly.

The virtual pet can be born, grown, bred and killed as a pet in real life, and at present, problems in the aspect of virtual pet mating or pairing are mainly freely selected and initiated by a user in the prior art, and the selection mode is relatively high in randomness, so that the experience degree of the user for feeding the virtual pet and the success rate of breeding offspring of the virtual pet are relatively low.

Disclosure of Invention

The embodiment of the application provides a recommendation method and device for virtual pet pairing, which can recommend a virtual pet to be paired to a user in a targeted manner according to the requirement of the user on the offspring of the virtual pet and the characteristics of the virtual pet, and effectively improve the success rate of virtual pet pairing.

In a first aspect, an embodiment of the present application provides a recommendation method for virtual pet pairing, including:

acquiring demand information of a first user for offspring of a virtual pet of the first user and data information of the virtual pet of the first user, wherein the data information comprises one or more items of type information, gene information, hair color information, body length information, body state information, spleen qi information and responsibility feeling of the virtual pet;

determining data information of a virtual pet of a second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, wherein the virtual pet of the second user is at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user;

determining a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user;

recommending at least one target virtual pet to be bred of the first user's virtual pets to the first user based on the target matching degree.

In the method, the method initially screens at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user through the requirement information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, then further screens the candidate to-be-matched virtual pet, comprehensively determines the target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user, and can comprehensively consider whether the users and the virtual pets of the users are proper or not, and more pertinently recommends the target to-be-matched virtual pet to the first user. However, in the prior art, the selection is mainly freely selected and initiated by the user, the selection mode is relatively high in randomness, and the virtual pet to be bred with at least one target of the virtual pet of the first user is not determined in a targeted manner, so that the success rate of breeding is relatively low, and the first user cannot know the most suitable virtual pet to be paired with the virtual pet. Therefore, the method and the device can recommend the preliminarily screened virtual pet to be bred to the first user in a targeted manner according to the demand of the first user on the offspring of the virtual pet and the characteristic information of the virtual pet, and the breeding success rate of the virtual pet is effectively improved.

In one possible embodiment, the determining a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user, and the data information of the second user includes:

determining a first matching degree according to the data information of the virtual pet of the first user and the data information of the virtual pet of the second user;

determining a second matching degree according to the data information of the first user and the data information of the second user;

and determining the target matching degree according to the first matching degree and the second matching degree.

In the method, whether the character, the life habit and the like between the virtual pet of the first user and the virtual pet of the second user are appropriate is determined through the matching degree between the virtual pet of the first user and the virtual pet of the second user (for example, the spleen qi of a female cat is mild, but the spleen qi of a male cat is violent, the matching degree between the virtual pet is 20%, for example, the spleen qi of a female cat is mild, the male cat is householder and responsible for the female cat, the matching degree between the virtual pet is 90%), whether the character between the owners of the virtual pets is appropriate and good in phase is determined through the matching degree between the first user and the second user (for example, the matching degree between two spleen qi is violent, the matching degree between the users with the life habit is 20%, and the matching degree between the users with the good life habit and the mild character is 90%), the target matching degree is determined through the first matching degree and the second matching degree, the method and the device can screen the data information of the matched virtual pet and the master data information of the virtual pet in a targeted manner, avoid unnecessary conflict caused by offspring when the two parties contact each other subsequently, and improve the matching success rate of the virtual pets.

In another possible embodiment, the demand information of the first user for the offspring of the virtual pet of the first user includes one or more of whether the type of the virtual pet of the first user is the same, physical condition health information, body type standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information.

In the above method, the demand information of the offspring of the virtual pet of the first user may include many aspects, for example, the demand types of the users for the virtual pet and the offspring of the virtual pet thereof may be the same or different (for example, the type of the virtual pet of the first user is a golden hair dog, and the demand type of the first user for the offspring of the virtual pet thereof may also be a golden hair dog or other varieties), the physical condition is healthy (no congenital disease, no defect), the body type standard (meets the body length of a normal dog), the gene is good (belongs to a pure puppy required by the first user), the eye pupil color (for example, may be black pupil or brown pupil), the hair color (for example, gold, yellow), through performing feature analysis on the demand information of the offspring of the virtual pet of the first user, clustering and primarily screening the candidate virtual pets to be bred matching with the virtual pet of the first user and meeting the demand information, and obtaining data information of the virtual pet of the second user, and providing a precondition for subsequently determining at least one target virtual pet to be bred.

In yet another possible embodiment, the method further comprises:

creating a user communication platform between the first user and the second user, wherein the user communication platform comprises a chat room or a virtual community;

and recommending the user communication platform to the first user and the second user.

In the method, a matching communication platform about respective virtual pets is provided for the first user and the second user which are successfully matched based on the target matching degree, for example, the first user and the second user with the highest target matching degree may be assigned to chat rooms with the same theme (e.g., golden hair dog pairing) or corresponding social links may be pushed (e.g., pushing respective two-dimensional codes), or the first five users with the highest target matching degree may be assigned to chat rooms with the same theme (e.g., golden hair dog pairing) or corresponding social links may be pushed (e.g., pushing group chat two-dimensional codes), or a virtual community may be provided (as a community in a virtual world counterpart), so as to provide a party place for users with virtual pets related to the same favorite, experience, or professional similar services, and facilitate their interaction and experience sharing. The scheme can provide an exchange platform for users with the highest target matching degree, and can also provide an exchange platform for people with relatively high target matching degree, convenience can be provided for the users through the scheme, and the experience of the users is improved.

In yet another possible embodiment, the method further comprises:

training demand information of offspring of the virtual pet of the first user, data information of the virtual pet of the first user and data information of the successfully recommended virtual pet to be bred, which is determined by the first user, to obtain a recommendation model, wherein the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user are characteristic information, the data information of the successfully recommended virtual pet to be bred, which is determined by the first user, is tag information, and the data information of the target virtual pet to be bred is determined by the first user from the recommended at least one target virtual pet to be bred;

acquiring demand information of offspring of virtual pets of a new user and data information of the virtual pets of the new user;

and inputting the requirement information of the offspring of the virtual pet of the new user and the data information of the virtual pet of the new user into the recommendation model to obtain at least one target to-be-bred virtual pet of the new user.

In the method, a training model is obtained by obtaining a batch of data of the whole process and training, and the obtained training model provides accurate mapping from input to required output. When a new user appears, the service distribution of the new user can be completed only by acquiring the demand information of the offspring of the virtual pet of the user and the data information of the virtual pet of the user, then performing characteristic analysis on the demand information of the offspring of the virtual pet of the user and the data information of the virtual pet of the user to obtain a characteristic vector, inputting the characteristic vector into a training model, and not needing to execute the whole process again, so that at least one target to-be-bred virtual pet of the new user can be obtained. The efficiency of recommending at least one target virtual pet to be bred to a new user's virtual pet is improved by utilizing a training model.

In a second aspect, the present application provides a recommendation device for virtual pet pairing, where the recommendation device includes an obtaining unit, a generating unit, a determining unit, and a recommending unit, and the recommendation device is configured to implement the method described in the first aspect or any one of the possible embodiments of the first aspect.

It should be noted that the processor included in the recommendation apparatus described in the second aspect may be a processor dedicated to execute the methods (referred to as a special-purpose processor for convenience), or may be a processor that executes the methods by calling a computer program, such as a general-purpose processor. Optionally, at least one processor may also include both special purpose and general purpose processors.

Alternatively, the computer program may be stored in a memory. For example, the Memory may be a non-transitory (non-transitory) Memory, such as a Read Only Memory (ROM), which may be integrated with the processor on the same device or separately disposed on different devices, and the embodiment of the present application is not limited to the type of the Memory and the arrangement manner of the Memory and the processor.

In a possible embodiment, said at least one memory is located outside said recommending means.

In yet another possible embodiment, the at least one memory is located within the recommendation device.

In yet another possible embodiment, a part of the memory of the at least one memory is located inside the recommending apparatus, and another part of the memory is located outside the recommending apparatus.

In this application, it is also possible that the processor and the memory are integrated in one device, i.e. that the processor and the memory are integrated together.

In a third aspect, an embodiment of the present application provides a recommendation device for virtual pet pairing, including a processor and a memory; the memory has stored therein a computer program; when the processor executes the computer program, the computing device performs the method described in any of the preceding first or second aspects.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein instructions that, when executed on at least one processor, implement the method described in any of the first to fourth aspects.

In a fifth aspect, the present application provides a computer program product comprising computer instructions that, when run on at least one processor, implement the method described in any of the preceding first to fourth aspects. The computer program product may be a software installation package, which may be downloaded and executed on a computing device in case it is desired to use the method as described above.

The advantages of the technical methods provided in the second to fifth aspects of the present application may refer to the advantages of the technical solution of the first aspect, and are not described herein again.

Drawings

The drawings that are required to be used in the description of the embodiments will now be briefly described.

FIG. 1 is a schematic diagram of a virtual pet pairing recommendation system according to an embodiment of the present application;

FIG. 2 is a flowchart illustrating a method for recommending a virtual pet pairing according to an embodiment of the present application;

FIG. 3 is a schematic diagram of data information associated with a virtual pet of a first user according to an embodiment of the present application;

FIG. 4 is a schematic diagram of at least one candidate virtual pet to be matched for matching with a virtual pet of a first user according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a recommendation device 50 for virtual pet pairing according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a recommendation device 60 for virtual pet pairing according to an embodiment of the present application.

Detailed Description

The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a virtual pet pairing recommendation system according to an embodiment of the present application, where the system includes a server 101 and a user device 102.

The server 101 may be a server or a server cluster composed of a plurality of servers, and may specifically be a computer or an upper computer. The server 101 includes a virtual pet pairing platform 103 that provides application services for the user device 102.

The user equipment 102 is a device having processing capabilities and data transceiving capabilities. The user device 102 may be a Computer, a laptop, a tablet, a palmtop, a desktop, a diagnostic device, a cell phone, an Ultra-mobile Personal Computer (UMPC), a netbook, a Personal Digital Assistant (PDA), or the like. In the embodiment of the present Application, the user equipment 102 is an Application (APP) 104.

The user group corresponding to the user of the user device 102 may be a general user, a system administrator, and a developer, wherein the general user may include, but is not limited to, a crowd with a virtual pet or a crowd interested in the virtual pet, or a crowd with a virtual pet that has arrived when the virtual pet needs to be paired, and the crowd may perform pairing selection or design and development on the application 104 for the virtual pet. The user logs in through the user device 102, uploads the data information of the user, the image of the virtual pet of the user and the virtual pet data information or issues information to be paired or paired (for example, if the user is a male cat, the information issued by the user is pairing information, and if the user is a female cat, the information to be paired is issued by the user) to the server 101 through the user device 102, and the user can also receive the intelligent pushing of the virtual pet pairing information fed back by the virtual pet pairing platform 103 through the user device 102.

The virtual pet matching platform 103 mainly has the functions of analyzing images of virtual pets uploaded by users or keywords input by the users, feeding back to the users and displaying matching objects and relevant matching degrees of the virtual pets. In addition, a system manager can manage and maintain the data information of the user and the data information of the virtual pet based on the virtual pet matching platform 103, and the virtual pet matching platform 103 also supports intelligent display and sequencing of videos and supports comment and approval, video online interaction and audio online interaction.

The method of the embodiments of the present application is described in detail below.

Referring to fig. 2, fig. 2 is a flowchart illustrating a method for recommending virtual pet pairing according to an embodiment of the present application. Alternatively, the method may be applied to the system described in fig. 1.

The recommendation method for virtual pet pairing as shown in fig. 2 at least comprises steps S201 to S204.

Step S201: the server acquires demand information of the first user for offspring of the virtual pet of the first user and data information of the virtual pet of the first user.

Wherein the demand information of the offspring of the virtual pet of the first user includes one or more of whether the type of the virtual pet of the first user is the same, physical condition information, body type standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information. For example, as shown in fig. 3, fig. 3 is a schematic diagram of data information associated with a virtual pet of a first user according to an embodiment of the present application, where a demand of a user a for offspring of a virtual pet butterfly dog 1 is: the offspring type of the butterfly dog is expected to be the pure butterfly dog, the eye pupil is black, the character is mild, the butterfly dog has no congenital disease, the physical state is healthy, and the beautiful body state and the beautiful characteristic of fur of the butterfly dog can be inherited. As another example, user a may desire offspring from his virtual pet dog 2 (i.e., butterfly dog 2) to be of a type other than pure butterfly dog, with high genetic quality, healthy body, robust body, and smart.

In addition, the data information of the virtual pet of the first user includes one or more of type information, genetic information, coat color information, body length information, body state information, spleen qi information, and whether or not it is responsible for the virtual pet. For example, as shown in fig. 3, the virtual pet of the user a has a butterfly dog 1, which is clever, outlying, bold, lovely close, strong in body and free of body odor. For another example, the butterfly dog 2 is the virtual pet of the user A, and the hair color of the butterfly dog is black and white intersection, lively character and standard body length.

Specifically, the source of the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user itself are various, for example, the first user uploads the data information on a platform, the platform may be an Application program (APP), a cloud platform or a web page, etc., the server receives the data information, and may label and display the data information on the platform in a manner of a tree diagram or a schematic diagram, as shown in fig. 3, for example, the user a has 2 virtual pet dogs (the server labels the data information of the butterfly dog 1 and the data information of the butterfly dog 2 on the platform respectively) and 1 virtual pet cat (the server labels the data information of the english blue cat on the platform) and the server also needs to label the demand information of the user a on the offspring of the butterfly dog 1, the demand information of the user a on the offspring of the butterfly dog 2 and the demand information of the user a on the offspring of the english blue cat, and the server integrates the labeling condition of the data information on the platform and outputs the demand information of the offspring of the virtual pet of the first user and the schematic diagram of the data information of the virtual pet of the first user.

Step S202: the server determines the data information of the virtual pet of the second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user.

Optionally, the server may determine the data information of the virtual pet of the second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user through a preset algorithm.

Specifically, the virtual pet of the second user is at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user, the data information of the virtual pet of the second user can be the data information of the virtual pet of one or more second users, one second user can have a plurality of virtual pets, the application does not limit the second user to be only one user, and does not limit the second user to only have one virtual pet, and similarly, the application does not limit the first user to be only one user, and does not limit the first user to only have one virtual pet to be matched. For example, as shown in fig. 4, fig. 4 is a schematic diagram of at least one candidate virtual pet to be bred for virtual pet matching of a first user according to an embodiment of the present application, where the first user may have three virtual pets, namely, a butterfly dog 1, a butterfly dog 2 and an english-blue cat, the second user may be a user B, a user C or a user D, the user B may have a butterfly dog 3 and a bomei 1, the user C may have a bomei 2 and a poon dog 1, and the user D may have a gilla cat.

The data information for determining the virtual pet of the second user is specifically as follows: firstly, a candidate virtual pet type to be bred matched with the virtual pet of the first user needs to be preliminarily screened, and then, a result of the preliminarily screened virtual pet to be bred can be obtained according to the condition whether the candidate virtual pet type to be bred matched with the virtual pet of the first user meets the requirement information (such as whether the gene is high in quality, whether the body state is healthy, whether the physique is healthy and clever) of the first user on the offspring of the virtual pet of the first user.

Wherein, the preliminary screening of the type of the candidate virtual pet to be bred matched with the virtual pet of the first user comprises the preliminary screening of the type of at least one candidate virtual pet to be bred matched with the virtual pet of the first user according to the requirement information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, for example, if the type of the virtual pet dog 1 of the user A is a butterfly dog, the requirement of the offspring of the butterfly dog by the user A is that the offspring of the butterfly dog is expected to be a pure butterfly dog, the eye pupil is black, the character is mild, no congenital disease exists, the physical state is healthy, and the beautiful body state and the beautiful character of the quilt of the butterfly dog can be inherited, the close relatives of the butterfly dog need to be screened firstly, otherwise, the offspring can lose the beautiful body state and the beautiful character of the quilt of the butterfly dog, and the close-relative mating method has two extremes, either the offspring can inherit to the maximum of the benefit on the parent, or else the disadvantage. The butterfly dog with good quality, health and good taste is selected for propagation, and the quality of the propagated offspring is also guaranteed. At present, a plurality of butterfly dog hybrids, such as Bomei hybrids and Guibin dog hybrids, are available, but the butterfly dog hybrids are matched with a butterfly dog to ensure that the beautiful body form and the beautiful hair characteristic of the butterfly dog can be inherited if the butterfly dog hybrids are wanted to breed a pure butterfly dog. Therefore, the candidate to-be-bred virtual pet dog type matched with the butterfly dog of the user A after preliminary screening is the butterfly dog, data information of at least one candidate to-be-bred butterfly dog matched with the butterfly dog 1 of the user A is obtained according to other requirements of the user A on the offspring of the butterfly dog 1, and the data information of the at least one candidate to-be-bred butterfly dog matched with the butterfly dog 1 of the user A is the data information of the virtual pet of the second user.

For another example, if the type of the requirement of the user a for the offspring of the virtual pet dog 2 (i.e., the butterfly dog 2) is not a pure butterfly dog, and the offspring gene of the butterfly dog 2 is required to be high quality, healthy in body state, strong in body constitution and smart, and the data information of the butterfly dog 2 itself is hair color, black and white intersection, lively in character and body length standard, the preliminarily screened candidate to-be-bred virtual pet dog type matched with the butterfly dog of the user a may be a virtual pet type such as a bona or poodle, but the condition of high gene quality, healthy in body state, strong in body constitution and smart needs to be satisfied, so that the data information of at least one candidate to-be-bred virtual pet dog matched with the butterfly dog 2 of the user a can be obtained. The scheme can recommend the preliminarily screened virtual pet to be bred to the first user in a targeted manner according to the demand of the first user on the offspring of the virtual pet and the characteristic information of the virtual pet, and effectively improves the breeding success rate of the virtual pet.

Step S203: the server determines the target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user.

Specifically, the server determines a first matching degree according to the data information of the virtual pet of the first user and the data information of the virtual pet of the second user, determines a second matching degree according to the data information of the first user and the data information of the second user, and finally integrates the first matching degree and the second matching degree to determine a target matching degree.

The manner in which the target match is determined can be elaborated from both non-modeled and modeled manners.

Firstly, determining the target matching degree in an unmodeled mode:

the unmodeled method may be that after the server initially screens out the virtual pets to be bred, the server determines a first matching degree according to data information of the virtual pet of the first user and data information of the virtual pet of the second user, where the first matching degree is a matching degree between the virtual pet of the first user and the virtual pet of the second user, for example, the data information of the virtual pet of the first user is spleen qi information, the data information of the virtual pet of the second user is spleen qi information, and the first matching degree may be determined according to whether the characters, life habits, and the like between the virtual pet of the first user and the virtual pet of the second user are appropriate (for example, if the virtual pet of the first user is a female cat, the spleen qi is mild, but the virtual pet of the second user is a male cat, the spleen qi is violent, the matching degree between the virtual pets is 20% through algorithm calculation, if the virtual pet of the first user is a female cat with mild character, the virtual pet of the second user is a male cat, giving attention to the family and being responsible for the female cat, calculating by an algorithm to obtain the matching degree between the virtual pets to be 90%), determining the matching degree between the first user and the second user according to the data information of the first user and the data information of the second user, wherein the data information of the first user is character information, spleen qi information and life habit information, the data information of the second user is character information, spleen qi information and life habit information, and determining a second matching degree through whether the character between the owners of the virtual pets is proper and whether the character between the owners of the virtual pets is good (for example, the first user and the second user are both irritable in spleen qi, poor in life habit, and the matching degree between the first user and the second user is 20%, while the matching degree between the first user and the second user is good and the character between the first user and the second user is mild is 90%), and finally, integrating the first matching degree and the second matching degree to determine the target matching degree. Through the method, the data information of the matched virtual pet and the data information of the owner of the virtual pet can be screened in a targeted manner, unnecessary conflict caused by offspring when the two parties contact each other subsequently is avoided, and the matching success rate of the virtual pets is improved.

The target matching degrees determined by the first matching degree and the second matching degree include, but are not limited to, the following two results, which may be an optimal target matching degree or by sorting the obtained matching degrees, and the top three is the target matching degree.

As a result, if the data information of the virtual pets of the user a and the user a, and the data information of the virtual pets of the user B and the user B are clustered, and then a best matching degree is obtained by integrating the first matching degree between the virtual pet of the user a and the virtual pet of the user B and the second matching degree between the user a and the user B, it indicates that the virtual pet of the user a and the virtual pet of the user B are successfully matched, and the target matching degree may be the best matching degree obtained by integrating the first matching degree and the second matching degree (for example, 50%, 67%, 84%, 88%, 92% and the like matching degrees are obtained after integrating the first matching degree and the second matching degree, where 92% is the best matching degree), so that the virtual pet of the second user corresponding to the target matching degree of 92% may be selected.

As a result, the target matching degree may be the best matching degree with the ratio of the first matching degree to the second matching degree being the top three after the first matching degree and the second matching degree are combined (e.g. 50%, 67%, 84%, 88%, 92% and the like after the first matching degree and the second matching degree are combined, wherein 92%, 88%, 84% are the matching degrees of the top three), so that the virtual pets of the second user with the target matching degrees of 92%, 88%, 84% can be selected.

Secondly, determining the target matching degree in a modeling mode:

specifically, the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user are input into the recommendation model as feature information through training of the recommendation model, and the target matching degree is obtained according to a specific algorithm. Specifically, a first matching degree between each to-be-matched virtual pet and a second matching degree between each user associated with the to-be-matched virtual pet can be extracted, a first feature vector and a second feature vector are respectively generated, the first feature vector and the second feature vector are input into the model in a comprehensive mode, the mean value of the maximum similarity is calculated, a target feature vector is obtained, then the target feature vector is decoded, a target matching degree is generated, and the final matching degree of the candidate to-be-matched virtual pet and the virtual pet of the first user is obtained.

Step S204: the server recommends at least one target virtual pet to be bred of the virtual pet of the first user to the first user based on the target matching degree.

Specifically, a user logs in a virtual pet matching APP through user equipment, uploads data information of the user, image information of a virtual pet of the user and data information of the virtual pet or releases information to be matched or matched (for example, if the user is a male cat, the user releases the information to be matched, and if the user is a female cat, the user releases the information to be matched) to a server through the virtual pet matching APP, the user receives final information of the virtual pet to be matched, which is matched with the first user, through the user equipment receiving server based on a target matching degree, and the server performs intelligent recommendation on feedback information to the user through the user equipment (for example, data information of a virtual pet based on a second user corresponding to the target matching degree is output to the first user through the user equipment).

Optionally, the manner in which the server recommends at least one target to-be-matched virtual pet of the first user to the first user based on the target matching degree may be to create a user communication platform between the first user and the second user, and recommend the user communication platform to the first user and the second user, where the user communication platform includes a chat room or a virtual community. If user a has a butterfly dog 1 and a butterfly dog 2, user B has a bomei, a poodle and a silver-colored split british shorthair cat, communication platforms such as chat rooms, push social links, or open virtual communities can be respectively established for the pairing of different virtual pets of the user a and the user B, for example, a chat room A can be correspondingly established for the group 1 to be recommended, if the butterfly dog 1 and the butterfly dog 2 of the user A in the group 1 to be recommended can be paired with the Bomei and the poodle dog of the user B, the server may create a chat room M first, the topic of which may be # puppy's postpartum care #, # butterfly dog's family #, # little dog's happy life # and so on, and then directly recommending a chat room M for the user A and the user B based on the target matching degree, pushing a group chat two-dimensional code to the user A and the user B or directly sending a group chat link through a system, and inviting the user A and the user B to enter the chat room M for communication. For another example, a chat room N may be correspondingly established for the group 2 to be recommended, if both the british kitten 1 and the civet cat 1 of the user C in the group 2 to be recommended can be paired with the british kitten 2 and the civet cat 2 of the user D, the server may first establish the chat room N, the topics of the chat room N may be # post-partum care of # cat #, # beautiful treasure house #, # happy life of # cat, and the like, then directly recommend the chat room N for the user C and the user D based on the target matching degree, and push a group chat two-dimensional code to the user C and the user D or directly send a group chat link through the system, and invite the user C and the user D to enter the chat room N for communication. In addition to creating a chat room for the group to be recommended, social links may also be pushed to the group to be recommended. For the pushing social link, a WeChat two-dimensional code can be pushed to the group to be recommended, so that the social contact of the user is facilitated; the open virtual community can be a virtual world corresponding to a real community established on the internet, and the groups to be recommended can communicate with each other based on the respective matched virtual pets or other topics.

Optionally, the above steps of the embodiment of the present application have already recommended at least one target virtual pet to be matched of the virtual pets corresponding to the multiple users, but there is no mention about how to recommend at least one target virtual pet to be matched to the virtual pet of the new user more conveniently. In order to make the subsequent process of recommending to the new user by the system administrator more convenient, the training algorithm receives the input existing user data (such as the demand information of the offspring of the virtual pet of the first user, the data information of the virtual pet of the first user and the data information of the successfully recommended virtual pet to be bred determined by the first user), then the operation training is carried out, the operation result forms a recommendation model, the recommendation model is specifically used for recommending at least one target virtual pet to be bred to the virtual pet of the new user, the data of a plurality of users is trained according to the steps by utilizing a model building method to obtain a recommendation model, wherein the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user are characteristic information, the data information of the successfully recommended virtual pet to be bred determined by the first user is label information, the data information of the target virtual pet to be bred is determined by the first user from the recommended at least one target virtual pet to be bred, the demand information of the offspring of the virtual pet of the new user and the data information of the virtual pet of the new user are obtained, then the demand information of the offspring of the virtual pet of the new user and the data information of the virtual pet of the new user are input into the recommendation model, and then the at least one target virtual pet to be bred of the virtual pet of the new user can be obtained, and the related step flows are not described repeatedly here.

In the embodiment of the application, at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user is preliminarily screened through the requirement information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, then the candidate to-be-matched virtual pet is further screened, the target matching degree is comprehensively determined according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user, whether the target matching degree is suitable between the users and the virtual pets of the users can be comprehensively considered, and the target to-be-matched virtual pet can be recommended to the first user in a more targeted mode. However, in the prior art, the selection is mainly freely selected and initiated by the user, the selection mode is relatively high in randomness, and the virtual pet to be bred with at least one target of the virtual pet of the first user is not determined in a targeted manner, so that the success rate of breeding is relatively low, and the first user cannot know the most suitable virtual pet to be paired with the virtual pet. Therefore, the method and the device can recommend the preliminarily screened virtual pet to be bred to the first user in a targeted manner according to the demand of the first user on the offspring of the virtual pet and the characteristic information of the virtual pet, and the breeding success rate of the virtual pet is effectively improved.

The method of the embodiments of the present application is explained in detail above, and the apparatus of the embodiments of the present application is provided below.

It is to be understood that a plurality of apparatuses, such as an analysis apparatus, provided in the embodiments of the present application include a hardware structure, a software module, or a combination of a hardware structure and a software structure, which performs respective functions, in order to implement the functions in the above-described method embodiments.

Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. A person skilled in the art may implement the foregoing method embodiments in different usage scenarios by using different device implementations, and the different implementation manners of the device should not be considered as exceeding the scope of the embodiments of the present application.

The embodiment of the application can divide the functional modules of the device. For example, each functional module may be divided for each function, or two or more functions may be integrated into one functional module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.

For example, in the case where the respective functional blocks of the apparatus are divided in an integrated manner, the present application exemplifies several possible processing apparatuses.

Referring to fig. 5, fig. 5 is a schematic structural diagram of a recommendation device 50 for virtual pet pairing according to an embodiment of the present application, where the recommendation device 50 may be a server or a device in the server, such as a chip, a software module, an integrated circuit, and the like. The recommendation device 50 is used to implement the aforementioned recommendation method for virtual pet pairing, for example, the recommendation method for virtual pet pairing illustrated in fig. 2.

In a possible implementation, the recommendation apparatus 50 may include an obtaining unit 501, a determining unit 502, and a recommending unit 503.

The obtaining unit 501 is configured to obtain demand information of a first user for offspring of a virtual pet of the first user and data information of the virtual pet of the first user, where the data information includes one or more of type information, genetic information, hair color information, body length information, body state information, spleen qi information, and whether or not there is responsibility for the virtual pet;

the determining unit 502 is configured to determine data information of a virtual pet of a second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, where the virtual pet of the second user is at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user;

the determining unit 502 is further configured to determine a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user, and the data information of the second user;

the recommending unit 503 is configured to recommend at least one target virtual pet to be bred of the virtual pet of the first user to the first user based on the target matching degree.

In the embodiment of the application, at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user is preliminarily screened through the requirement information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, then the candidate to-be-matched virtual pet is further screened, and the target matching degree is comprehensively determined according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user, wherein the target matching degree can comprehensively consider whether the users and the virtual pets of the users are proper or not, and the target to-be-matched virtual pet can be more pertinently recommended to the first user. However, in the prior art, the selection is mainly freely selected and initiated by the user, the selection mode is relatively high in randomness, and the virtual pet to be bred with at least one target of the virtual pet of the first user is not determined in a targeted manner, so that the success rate of breeding is relatively low, and the first user cannot know the most suitable virtual pet to be paired with the virtual pet. Therefore, the method and the device can recommend the preliminarily screened virtual pet to be bred to the first user in a targeted manner according to the demand of the first user on the offspring of the virtual pet and the characteristic information of the virtual pet, and the breeding success rate of the virtual pet is effectively improved.

In another possible embodiment, the determining unit 502 is further configured to determine a first matching degree according to the information of the virtual pet of the first user and the information of the virtual pet of the second user;

the determining unit 502 is further configured to determine a second matching degree according to the data information of the first user and the data information of the second user;

the determining unit 502 is further configured to determine the target matching degree according to the first matching degree and the second matching degree.

In the embodiment of the application, whether the character, the life habit and the like between the virtual pet of the first user and the virtual pet of the second user are appropriate is determined through the matching degree between the virtual pet of the first user and the virtual pet of the second user (for example, the spleen qi of a female cat is mild, but the spleen qi of a male cat is violent, the matching degree between the virtual pets is 20%, for example, the spleen qi of a female cat is mild, the male cat is householder and responsible for the female cat, and the matching degree between the virtual pets is 90%), whether the character between the owners of the virtual pets is appropriate and good in phase is determined through the matching degree between the first user and the second user (for example, the matching degree between two spleen qi is violent, the matching degree between users with good life habits is 20%, and the matching degree between users with good life habits and mild character is 90%), the target matching degree is determined through the first matching degree and the second matching degree, the method and the device can screen the data information of the matched virtual pet and the master data information of the virtual pet in a targeted manner, avoid unnecessary conflict caused by offspring when the two parties contact each other subsequently, and improve the matching success rate of the virtual pets.

In still another possible embodiment, the demand information of the first user for the offspring of the virtual pet of the first user includes one or more of the same type as the virtual pet of the first user, physical condition health information, body shape standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information.

In the embodiment of the present application, the requirement information of the offspring of the virtual pet of the first user may include many aspects, for example, the requirement types of the users for the virtual pet and the offspring of the virtual pet thereof may be the same or different (for example, the type of the virtual pet of the first user is a golden hair dog, and the requirement type of the first user for the offspring of the virtual pet thereof may also be a golden hair dog or other varieties), the physical condition is healthy (no congenital disease, no defect), the body type standard (meets the body length of a normal dog), the gene is good (belongs to a pure puppy required by the first user), the eye pupil color (for example, may be black pupil or brown pupil), the hair color (for example, gold, yellow), through performing feature analysis on the requirement information of the offspring of the virtual pet of the first user, clustering and primarily screening the candidate virtual pets to be bred matching with the virtual pet of the first user and meeting the requirement information, and obtaining data information of the virtual pet of the second user, and providing a precondition for subsequently determining at least one target virtual pet to be bred.

In another possible embodiment, the method further includes:

the creating unit is configured to create a user communication platform between the first user and the second user, where the user communication platform includes a chat room or a virtual community;

the recommending unit 503 is further configured to recommend the user communication platform to the first user and the second user.

In the embodiment of the application, a pairing communication platform about respective virtual pets is provided for the first user and the second user which are successfully matched based on the target matching degree, for example, the first user and the second user with the highest target matching degree may be assigned to chat rooms with the same theme (e.g., golden hair dog pairing) or corresponding social links may be pushed (e.g., pushing respective two-dimensional codes), or the first five users with the highest target matching degree may be assigned to chat rooms with the same theme (e.g., golden hair dog pairing) or corresponding social links may be pushed (e.g., pushing group chat two-dimensional codes), or a virtual community may be provided (as a community in a virtual world counterpart), so as to provide a party place for users with virtual pets related to the same favorite, experience, or professional similar services, and facilitate their interaction and experience sharing. The scheme can provide an exchange platform for users with the highest target matching degree, and can also provide an exchange platform for people with relatively high target matching degree, convenience can be provided for the users through the scheme, and the experience of the users is improved.

In yet another possible embodiment, the method further includes:

the training unit is used for training the demand information of the offspring of the virtual pet of the first user, the data information of the virtual pet of the first user and the data information of the successfully recommended to-be-matched virtual pet determined by the first user to obtain a recommendation model, wherein the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user are characteristic information, the data information of the successfully recommended to-be-matched virtual pet determined by the first user is label information, and the data information of the target to-be-matched virtual pet is determined by the first user from the recommended at least one target to-be-matched virtual pet;

the obtaining unit 501 is further configured to obtain demand information of offspring of virtual pets of a new user and data information of virtual pets of the new user;

the input unit is used for inputting the requirement information of the offspring of the virtual pet of the new user and the data information of the virtual pet of the new user into the recommendation model to obtain at least one target virtual pet to be bred of the virtual pet of the new user.

In the embodiment of the application, a training model is obtained by obtaining a batch of data of the whole process and training, and the obtained training model provides accurate mapping from input to required output. When a new user appears, the service distribution of the new user can be completed only by acquiring the demand information of the offspring of the virtual pet of the user and the data information of the virtual pet of the user, then performing characteristic analysis on the demand information of the offspring of the virtual pet of the user and the data information of the virtual pet of the user to obtain a characteristic vector, inputting the characteristic vector into a training model, and not needing to execute the whole process again, so that at least one target to-be-bred virtual pet of the new user can be obtained. The efficiency of recommending at least one target virtual pet to be bred to a new user's virtual pet is improved by utilizing a training model.

Referring to fig. 6, fig. 6 is a schematic structural diagram of a recommendation device 60 for virtual pet pairing according to an embodiment of the present application, where the recommendation device 60 may be a server or a device in the server, such as a chip, a software module, an integrated circuit, and the like. The recommendation device 60 may include at least one processor 601. Optionally, at least one memory 603 may also be included. Further optionally, the recommendation device 60 may also include a communication interface 602. Still further optionally, a bus 604 may be included, wherein the processor 601, the communication interface 602, and the memory 603 are coupled via the bus 604.

The processor 601 is a module for performing arithmetic operation and/or logical operation, and may specifically be one or a combination of multiple Processing modules, such as a Central Processing Unit (CPU), a picture Processing Unit (GPU), a Microprocessor (MPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Complex Programmable Logic Device (CPLD), a coprocessor (assisting the Central Processing Unit to complete corresponding Processing and Application), and a Micro Control Unit (MCU).

The communication interface 602 may be used to provide information input or output to the at least one processor. And/or, the communication interface 602 may be used to receive and/or transmit data externally, and may be a wired link interface such as an ethernet cable, and may also be a wireless link (Wi-Fi, bluetooth, general wireless transmission, vehicle-mounted short-range communication technology, other short-range wireless communication technology, and the like) interface. Optionally, the communication interface 602 may further include a transmitter (e.g., a radio frequency transmitter, an antenna, etc.) or a receiver, etc. coupled to the interface.

The memory 603 is used to provide a storage space in which data, such as an operating system and computer programs, may be stored. The Memory 603 may be one or a combination of Random Access Memory (RAM), Read-only Memory (ROM), Erasable Programmable Read-only Memory (EPROM), or portable Read-only Memory (CD-ROM), among others.

The at least one processor 601 of the recommendation device 60 is configured to perform the method described above, for example, the method described in the embodiment illustrated in fig. 2.

Alternatively, the processor 601 may be a processor dedicated to performing the methods (referred to as a special purpose processor for convenience), or may be a processor for executing the methods by calling a computer program, such as a general purpose processor. Optionally, at least one processor may also include both special purpose and general purpose processors. Optionally, in case the computing device comprises at least one processor 601, the above mentioned computer program may be stored in the memory 603.

Optionally, at least one processor 601 in the recommendation device 60 is configured to execute the calling computer instructions to perform the following operations:

recommending at least one target virtual pet to be bred of the first user's virtual pets to the first user based on the target matching degree. In the embodiment of the application, at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user is preliminarily screened through the requirement information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, then the candidate to-be-matched virtual pet is further screened, the target matching degree is comprehensively determined according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user and the data information of the second user, whether the target matching degree is suitable between the users and the virtual pets of the users can be comprehensively considered, and the target to-be-matched virtual pet can be recommended to the first user in a more targeted mode. However, in the prior art, the selection is mainly freely selected and initiated by the user, the selection mode is relatively high in randomness, and the virtual pet to be bred with at least one target of the virtual pet of the first user is not determined in a targeted manner, so that the success rate of breeding is relatively low, and the first user cannot know the most suitable virtual pet to be paired with the virtual pet. Therefore, the method and the device can recommend the preliminarily screened virtual pet to be bred to the first user in a targeted manner according to the demand of the first user on the offspring of the virtual pet and the characteristic information of the virtual pet, and the breeding success rate of the virtual pet is effectively improved.

Optionally, the processor 601 is further configured to:

determining a first matching degree according to the information of the virtual pet of the first user and the information of the virtual pet of the second user;

Optionally, the demand information of the first user for the offspring of the virtual pet of the first user includes one or more of the same type as the virtual pet of the first user, physical health condition information, body type standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information.

Optionally, the processor 601 is further configured to:

The present application also provides a computer-readable storage medium having instructions stored thereon, which when executed on at least one processor, implement the aforementioned recommendation method for virtual pet pairing, such as the method described in fig. 2.

The present application also provides a computer program product comprising computer instructions that, when executed by a computing device, implement the aforementioned recommendation method for virtual pet pairing, such as the method described in fig. 2.

In the embodiments of the present application, words such as "for example" or "like" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "for example" or "such as" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "for example" or "such as" are intended to present relevant concepts in a concrete fashion.

In the present application, the embodiments refer to "at least one" and "a plurality" and two or more. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a. b, c, (a and b), (a and c), (b and c), or (a and b and c), wherein a, b and c can be single or multiple. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a alone, A and B together, and B alone, wherein A, B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

And unless stated to the contrary, the ordinal numbers such as "first", "second", etc. are used in the embodiments of the present application to distinguish a plurality of objects and are not used to limit the sequence, timing, priority, or importance of the plurality of objects. For example, a first device and a second device are for convenience of description only and do not represent differences in structure, importance, etc. of the first device and the second device, and in some embodiments, the first device and the second device may be the same device.

As used in the above embodiments, the term "when … …" may be interpreted to mean "if … …" or "after … …" or "in response to determination … …" or "in response to detection … …", depending on the context. The above description is only exemplary of the present application and is not intended to limit the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the present application.

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 instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A recommendation method for pairing a virtual pet, comprising:

2. The method of claim 1, wherein determining a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user, and the data information of the second user comprises:

3. The method according to claim 1 or 2, wherein the demand information of the first user for the offspring of the virtual pet of the first user includes one or more of whether or not the type of the virtual pet of the first user is the same, physical condition health information, body type standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information.

4. The method according to any one of claims 1-3, further comprising:

5. The method according to any one of claims 1-3, further comprising:

6. A recommendation device for virtual pet pairing is characterized by comprising an acquisition unit, a determination unit and a recommendation unit, wherein:

the acquiring unit is used for acquiring demand information of a first user for offspring of the virtual pet of the first user and data information of the virtual pet of the first user, wherein the data information comprises one or more items of type information, gene information, hair color information, body length information, body state information, spleen qi information and responsibility feeling of the virtual pet;

the determining unit is used for determining data information of a virtual pet of a second user according to the demand information of the offspring of the virtual pet of the first user and the data information of the virtual pet of the first user, wherein the virtual pet of the second user is at least one candidate to-be-matched virtual pet matched with the virtual pet of the first user;

the determining unit is further configured to determine a target matching degree according to the data information of the virtual pet of the first user, the data information of the virtual pet of the second user, the data information of the first user, and the data information of the second user;

the recommending unit is used for recommending at least one target virtual pet to be matched of the virtual pet of the first user to the first user based on the target matching degree.

7. The apparatus of claim 6,

the determining unit is further used for determining a first matching degree according to the data information of the virtual pet of the first user and the data information of the virtual pet of the second user;

the determining unit is further configured to determine a second matching degree according to the data information of the first user and the data information of the second user;

the determining unit is further configured to determine the target matching degree according to the first matching degree and the second matching degree.

8. The apparatus according to claim 6 or 7, wherein the demand information of the first user for the offspring of the virtual pet of the first user includes one or more of whether or not the type of the virtual pet of the first user is the same, physical condition health information, body type standard information, gene quality information, eye pupil color information, hair color information, life habit information, and character information.

9. A recommendation device for virtual pet pairing, the device comprising a processor and a memory, the memory for storing computer instructions, the processor for invoking the computer instructions to implement the method of any one of claims 1-5.

10. A computer-readable storage medium having stored therein instructions which, when executed on at least one processor, implement the method of any one of claims 1-5.