CN115212561B

CN115212561B - Service processing method based on voice game data of player and related product

Info

Publication number: CN115212561B
Application number: CN202211137456.3A
Authority: CN
Inventors: 王一
Original assignee: Shenzhen Renma Interactive Technology Co Ltd
Current assignee: Shenzhen Renma Interactive Technology Co Ltd
Priority date: 2022-09-19
Filing date: 2022-09-19
Publication date: 2022-12-09
Anticipated expiration: 2042-09-19
Also published as: CN115212561A

Abstract

The application provides a service processing method based on voice game data of a player and a related product, wherein the method is applied to a server of a service recommendation system, and comprises the following steps: calling a human-computer interaction engine in a server to perform voice interaction with a player through terminal equipment, and acquiring voice data input by the player in the love simulation game; determining a target user representation of a player in a love scene according to the voice data; determining a service which is matched with the requirements of the player in the associated service scene according to the target user portrait; and sending a service recommendation message to the terminal equipment, wherein the service recommendation message is used for indicating the service. Therefore, the server can accurately depict the user portrait through the voice data input by the player, service pushing is carried out based on the user portrait, the pushed service is more adaptive to the user demand and more accurate, and the conversion rate of the merchant for popularizing the product/service is improved while the user experience is improved.

Description

Service processing method based on voice game data of player and related product

Technical Field

The application belongs to the technical field of general data processing of the Internet industry, and particularly relates to a service processing method of voice game data based on players and a related product.

Background

At present, when a business sends a service recommendation message to a user through a terminal device, the business can not accurately recommend the service according to the requirements of the user, so that the accuracy of service push is low, the user can easily have negative impressions on the inaccurate service recommendation message, and the user experience and the efficiency of service popularization are influenced.

Disclosure of Invention

The application provides a service processing method based on voice game data of a player and a related product, so that accuracy of service recommendation is improved, and user experience is improved.

In a first aspect, an embodiment of the present application provides a service processing method based on voice game data of a player, where the method is applied to a server of a service recommendation system, where the service recommendation system includes the server and a terminal device logging in a game account of the player, the server includes a human-computer interaction engine supporting human-computer voice interaction in a voice virtual world, the voice virtual world includes a love simulation game of a voice interaction type, and a game associated with the game account includes the love simulation game, and the method includes:

calling the human-computer interaction engine to perform voice interaction with the player through the terminal equipment, and acquiring voice data input by the player in the love simulation game;

determining a target user portrait of the player in a love scene according to voice data input by the player in the love simulation game;

determining a service which is matched with the requirements of the player in an associated service scene according to the target user portrait of the player in the love scene, wherein the associated service scene is a social account number recommendation service scene or an expression package recommendation service scene associated with the love scene;

and sending a service recommendation message to the terminal equipment, wherein the service recommendation message is used for indicating the service.

In a second aspect, an embodiment of the present application provides a service processing apparatus based on voice game data of a player, where the apparatus is applied to a server of a service recommendation system, the service recommendation system includes the server and a terminal device that logs in a game account of the player, the server includes a human-computer interaction engine that supports human-computer voice interaction in a voice virtual world, the voice virtual world includes a love simulation game of a voice interaction type, and a game associated with the game account includes the love simulation game, the apparatus includes: the acquisition unit is used for calling the human-computer interaction engine to perform voice interaction with the player through the terminal equipment, and acquiring voice data input by the player in the love simulation game; a first determination unit for determining a target user figure of the player in a love scene according to voice data input by the player in the love simulation game; a second determining unit, configured to determine, according to a target user portrait of the player in a love scene, a service that meets a requirement of the player in an associated service scene, where the associated service scene is a social account recommendation service scene or an expression package recommendation service scene associated with the love scene; and the sending unit is used for sending a service recommendation message to the terminal equipment, wherein the service recommendation message is used for indicating the service.

In a third aspect, embodiments of the present application provide a server, including a processor, a memory, and one or more programs stored in the memory and configured to be executed by the processor, the program including instructions for performing the steps in the first aspect of embodiments of the present application.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium on which a computer program/instruction is stored, where the computer program/instruction, when executed by a processor, implements the steps in the first aspect of the embodiments of the present application.

In a fifth aspect, embodiments of the present application provide a computer program product, where the computer program product comprises a non-transitory computer-readable storage medium storing a computer program, where the computer program is operable to cause a computer to perform some or all of the steps as described in the first aspect of embodiments of the present application.

It can be seen that, in the embodiment of the present application, a server first obtains voice data input by a player in a voice virtual world, where the voice virtual world includes a love simulation game, then determines a target user portrait of the player in a love scene according to the voice data, finally determines a service adapted to a player requirement in an associated service scene according to the target user portrait, and finally sends a service recommendation message to a terminal device, so as to implement pushing the service adapted to the player requirement to the player. Therefore, the server can accurately depict the user portrait through the voice data input by the user in the voice interaction type love simulation game, service pushing is carried out based on the user portrait, the pushed service is more adaptive to the user demand and more accurate, and the conversion rate of popularization products/services of merchants is improved while the user experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a block diagram illustrating a service recommendation system according to an embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating a method for processing services based on voice game data of a player according to an embodiment of the present application;

FIG. 3 is a schematic flow chart illustrating a process for determining a partial user representation of a player according to an embodiment of the present application;

FIG. 3a is a simplified exemplary diagram of a triplet provided by an embodiment of the present application;

FIG. 4 is a schematic illustration of a process for determining a player global user representation according to an embodiment of the present application;

FIG. 5 is an example diagram of a social account recommendation message provided by an embodiment of the present application;

fig. 6 is an expression package of a virtual character with an emotional state of anger provided by an embodiment of the application;

FIG. 7 is a diagram illustrating an example emoticon recommendation message according to an embodiment of the present application;

FIG. 8a is a block diagram of functional units of a device for processing services based on voice game data of a player according to an embodiment of the present application;

FIG. 8b is a block diagram of functional units of another device for processing a voice game data service based on a player according to an embodiment of the present application;

fig. 9 is a block diagram of a server according to an embodiment of the present disclosure.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the foregoing drawings are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

At present, when a service recommendation message is sent to a user through a terminal device, related product/service messages are mostly pushed through search records of the user, browsing records of goods and the like, but when the user does not search and browse goods, the user demand cannot be accurately positioned, so that the accuracy of service pushing is not high, the user is prone to generate negative impressions on the inaccurate service recommendation messages, and the user experience and the efficiency of service popularization are influenced.

In order to solve the above problems, embodiments of the present application provide a service processing method based on voice game data of a player and a related product, where the method is applied to a server of a service recommendation system. The server accurately portrays the user portrait through voice data input by the user in the voice interaction type love simulation game, service pushing is carried out based on the user portrait, the pushed service is enabled to be more adaptive to user requirements and more accurate, user experience is improved, and meanwhile the conversion rate of products/services popularized by merchants is improved.

Referring to fig. 1, fig. 1 is a block diagram illustrating a service recommendation system according to an embodiment of the present disclosure. As shown in fig. 1, the service recommendation system 10 includes a server 11 and a terminal device 12, the server 11 is in communication connection with the terminal device 12, the server 11 includes a human-machine interaction engine supporting human-machine voice interaction in a voice virtual world, the server 11 performs voice interaction with a player through the terminal device 12 by calling the human-machine interaction engine, further obtains voice data input by the player, and after determining a service that is adapted to a requirement of the player in a relevant service scene according to a target user figure, is used for sending a service recommendation message to the terminal device 12, a game account of the player is logged in the terminal device 12, and a game related to the game account includes a voice interaction type love simulation game. The server 11 may be a server, a server cluster composed of a plurality of servers, or a cloud computing service center, and the terminal device 12 may be a mobile phone terminal, a tablet computer, a notebook computer, or the like.

The following describes a service processing method based on voice game data of a player according to an embodiment of the present application.

Referring to fig. 2, fig. 2 is a flowchart illustrating a service processing method based on voice game data of a player according to an embodiment of the present application, where the method is applied to a server 11 in a service recommendation system 10 shown in fig. 1, the service recommendation system 10 includes the server 11 and a terminal device 12 logging in a game account of the player, the server includes a human-computer interaction engine supporting human-computer voice interaction in a voice virtual world, the voice virtual world includes a love simulation game of a voice interaction type, and a game associated with the game account includes the love simulation game, as shown in fig. 2, the method includes:

step 201, calling the human-computer interaction engine to perform voice interaction with the player through the terminal device, and acquiring voice data input by the player in the love simulation game.

Step 202, determining a target user portrait of the player in the love scene according to the voice data input by the player in the love simulation game.

Step 203, determining the service which is matched with the requirements of the player in the associated service scene according to the target user portrait of the player in the love scene.

The associated service scene refers to a social account recommendation service scene or an expression package recommendation service scene associated with the love scene.

Step 204, sending a service recommendation message to the terminal device, where the service recommendation message is used to indicate the service.

It can be seen that, in the embodiment of the present application, a server first obtains voice data input by a player in a voice virtual world, where the voice virtual world includes a love simulation game, then determines a target user portrait of the player in a love scene according to the voice data, finally determines a service adapted to a player requirement in an associated service scene according to the target user portrait, and finally sends a service recommendation message to a terminal device, so as to implement pushing the service adapted to the player requirement to the player. Therefore, the server can accurately depict the user portrait through the voice data input by the user in the voice interaction type love simulation game, service pushing is carried out based on the user portrait, the pushed service is more adaptive to the user demand and more accurate, and the conversion rate of promoting products/services by merchants is improved while the user experience is improved.

In one possible example, the voice data input by the player in the love simulation game includes a plurality of sets of user sentences input by the player in a plurality of game scenario nodes of the love simulation game, a single set of user sentences includes at least one user sentence input by the player in a corresponding game scenario node, and the determining the target user representation of the player in the love scene according to the voice data input by the player in the love simulation game includes: performing core semantic extraction operation on each user statement in each user statement set in the plurality of user statement sets to obtain a plurality of core semantic sets corresponding to the plurality of user statement sets; obtaining at least one partial user representation of the player in a love scene for the plurality of game scenario nodes by: judging whether the currently processed game scenario nodes are game scenario nodes in a preset associated scenario node set or not, wherein the associated scenario node set comprises pre-marked game scenario nodes which are strongly associated with the selection tendencies of the players in the loving scenes; if yes, determining a local user portrait of the player in the love scene according to the core semantic set of the currently processed game scenario node; if not, jumping to the next game scenario node to be processed until the plurality of game scenario nodes are processed; and performing the following operations for the plurality of game scenario nodes to obtain a global user representation of the player in a love scene: analyzing voice data input by the player in the love simulation game to obtain voice characteristics of the player in a speaking process; determining a global user representation of the player in a love scene according to the voice characteristics; determining a target user representation of the player in a love scene based on the local user representation and the global user representation.

In the embodiment of the application, the target user representation comprises a local user representation and a global user representation, the local user representation can be the image characteristics of the player in a specific aspect, such as the characteristics of the player in specific scenes of puppet selection standard, gift sending preference, gift receiving preference and the like, and can be comprehensively evaluated by combining the game scenario nodes which are in progress when the player inputs user sentences; the global user representation may be a representation feature for macroscopically evaluating characteristics of a player, such as a character feature of the player, a love view of the player, or the like, and may be specifically integrated with a voice feature of voice data input by the player.

For ease of understanding, the process of determining a player partial user representation and the process of determining a player global user representation in the embodiments of the present application will be described separately below.

Referring to fig. 3, a process for determining a partial user representation of a player in an embodiment of the present application is described below, where fig. 3 is a schematic diagram of a process for determining a partial user representation of a player provided in an embodiment of the present application, and as shown in fig. 3, the process includes:

step 301, performing a core semantic extraction operation on each user statement in each user statement set in the plurality of user statement sets to obtain a plurality of core semantic sets corresponding to the plurality of user statement sets.

Wherein the core semantic extraction operation comprises the steps of: and performing semantic recognition on the currently processed user statement to obtain a semantic recognition result of the user statement, wherein the semantic recognition result comprises at least one knowledge triple, and extracting a main triple capable of representing the event type from the semantic recognition result as the core semantic of the currently processed user statement.

The knowledge triples are matched with template triples in a knowledge base, each knowledge triplet consists of a semantic/syntactic relation and two knowledge nodes, each knowledge node comprises a first knowledge node and a second knowledge node, each knowledge node is a single entity, each template triplet consists of a semantic/syntactic relation and two template nodes, each template node comprises a first template node and a second template node, each template node is a set consisting of entities with a common reference relation, each entity refers to a word or a phrase, and matching of the knowledge triples with the template triples in the knowledge base refers to: the semantic/syntactic relations of the knowledge triples and the template triples are the same, a first knowledge node of the knowledge triples belongs to the first template node, and a second knowledge node of the knowledge triples belongs to the second template node.

Illustratively, a triplet may be characterized in the form of { P (a, B) }, where a refers to an entity at one end of the triplet, B refers to an entity at the other end of the triplet, and P refers to a semantic/syntactic relationship between entities at both ends of the triplet, and the semantic/syntactic relationship is directional, and the triplet { P (a, B) }maybe understood as a semantic/syntactic relationship P between a and B. For example, as shown in fig. 3a, semantic recognition is performed on a sentence "mingming walks to eat room", and triples thereof are { noumenon (mingming, walking) }, { dependency (walking, go) }, { direct object (go, eat room) }. In the following description, a triplet { noumenon (xiaoming, walking) } is taken as an example for simple explanation, where "xiaoming" is an entity a, "walking" is an entity B, and "noumenon" is a semantic/syntactic relation P, and the direction is from "walking" to "xiaoming", and the meaning represented by: the noun subject of walking is xiaoming.

The semantic/syntactic relations are the same, that is, the relation types and the directions of the relation types of the connection relations between entities at two ends of the triples are the same, for example, the triples (1) { noumenon (Xiaoming, walking) }, and the triples (2) { noumenon (Xiaohong, swimming) }, where the semantic/syntactic relations P of the triples (1) and the triples (2) are both "noumenon" and the directions are both that the entity B points to the entity a, and then it is determined that the semantic/syntactic relations of the triples (1) and the triples (2) are the same.

To assist understanding, the matching mechanism for identifying triples and template triples is described below by way of a specific example. There is a generic self-learning system for semantic recognition in the server, which has a knowledge base that has undergone a lot of self-learning and historical training, and there is at least one template triple in the knowledge base, where a and B of { P (a, B) } are both in the form of sets, and the entities in each set have a common reference relationship, for example, a may be a set consisting of (xiaming + pinkish + floret + he + she), where the entities have a common reference relationship, and similarly, B may be a set consisting of (walk + walk), and then P is a "nominal subject" and the direction is pointed to a by B. At this time, if one of the knowledge triples extracted from the user history sentence input by the user is { noumenon (xiaoming, walking) }, it is determined that the knowledge triples match the template triples, and the semantic recognition result includes the knowledge triples { noumenon (xiaoming, walking) }. It is understood that the currently processed user statement may include a plurality of entities, a plurality of semantic/syntactic relations and a plurality of knowledge triples, and the above simple examples are only used to assist understanding of the solution disclosed in the embodiments of the present application, and do not constitute any limitation to the present application.

To assist understanding, the concept of a main triple is explained below by way of a specific example. For example, the currently processed user statement is: "i like to watch a movie", then the triple corresponding to the user sentence has { noumenon subject (i, like) }, { motile guest relationship (like, watch a movie) }, so that it can be analyzed that, of the two knowledge triples, the triple capable of representing the event type is { motile guest relationship (like, watch a movie) }, and then the triple is determined to be the main triple, and further the core semantics of the user sentence, namely "like to watch a movie" is determined according to the main triple, thereby determining that the target user image of the player includes the image feature of "like to watch a movie".

Step 302, determining whether the currently processed game scenario node is a game scenario node in a preset associated scenario node set.

If yes, go to step 303;

if not, go to step 304.

The association scenario node set comprises game scenario nodes which are marked in advance and strongly associated with the selection tendentiousness of the player in the love scene, and the game scenario nodes with the selection tendentiousness comprise game scenario nodes when the player selects a love object, game scenario nodes when the player selects a gift for the simulated love object, game scenario nodes when the simulated love object inquires about the gift type of the player, and the like.

Step 303, determining a local user portrait of the player in the love scene according to the core semantic set of the currently processed game scenario node.

And step 304, jumping to the next game scenario node to be processed until the plurality of game scenario nodes are processed.

Referring now to fig. 4, a process for determining a player global user representation in an embodiment of the present application is described, where fig. 4 is a schematic diagram of a process for determining a player global user representation in an embodiment of the present application, and as shown in fig. 4, the process includes:

step 401, analyzing the voice data input by the player in the love simulation game to obtain the voice characteristics of the player in the speaking process.

The voice characteristics of the player in the speaking process comprise the speaking volume and the speaking speed of the player.

Step 402, determining a global user representation of the player in the love scene according to the voice characteristics.

The voice characteristics are macro characteristics formed by behavior habits of the player in the love scene, and are not necessarily related to a specific game scenario node, so that the global user representation of the player can be determined through the voice characteristics, and particularly, the character characteristics of the player can be determined through the speaking volume and speaking speed of the player.

In this example, the server determines the local user representation and the global user representation of the player, and combines the obtained local user representation and the global user representation to obtain the target user representation, so as to improve the accuracy of the target user representation.

In one possible example, the determining the local user representation of the player in the love scene according to the core semantic set of the currently processed game scenario node includes: if the currently processed game scenario node is judged to be the game scenario node when the player selects the loving object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is an image selection standard, wherein the type of the image selection standard at least comprises one of the following types: constellation, height, weight, age, school calendar; determining a local user image of the player in the aspect of the puppet selection standard as a first label set according to the core semantic set of the currently processed game scenario node, wherein the first label set comprises at least one first label with a value range, and the first label is used for indicating the type of the puppet selection standard; if the currently processed game scenario node is judged to be the game scenario node when the player selects a gift for the simulated love object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift sending preference, wherein the type of the gift sending preference at least comprises one of the following types: practical gift-offering preference and atmosphere gift-offering preference; determining a local user image of the player in the aspect of the gift sending preference as a second label set according to the core semantic set of the currently processed game scenario node, wherein the second label set comprises at least one second label with a value range, and the second label is used for indicating the type of the gift sending preference; if the currently processed game scenario node is judged to be the game scenario node when the simulated love object inquires the gift type liked by the player, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift collection preference, wherein the type of the gift collection preference at least comprises one of the following types: practical gift collection preference and atmosphere gift collection preference; and determining a local user image of the player in the aspect of the gift-receiving preference as a third label set according to the core semantic set of the currently processed game scenario node, wherein the third label set comprises at least one third label with a value range, and the third label is used for indicating the type of the gift-receiving preference.

For convenience of understanding, the game scenario node when the player selects the love object is taken as a first game scenario node, the game scenario node when the player selects the gift as the simulated love object is taken as a second game scenario node, and the game scenario node when the simulated love object inquires the gift type liked by the player is taken as a third game scenario node. In each game scenario node, the intention represented by the input voice data of the player is associated with the corresponding game scenario, namely, the local user portrait of the player reflected under the game scenario node is determined according to the core semantic set of the currently processed game scenario node.

Illustratively, the first game scenario node may be the following scenario. Machine output statement (system bypass): please say the conditions that the love object in your ideal needs to satisfy, which can be described in terms of constellation, height, weight, age, academic calendar, etc. "at this time, the player inputs voice data: "I hope his constellation is the Aries or Gemini, height is above 1.75m but not over 1.85m, weight is not over 140 jin, age is between 20 and 25 years, and the study is unlimited. At this time, the server obtains a plurality of main triples corresponding to the user statement through semantic recognition, and further obtains a core semantic set of the user statement: the "constellation is a white sheep seat or a twin seat", "height is greater than 1.75m and less than or equal to 1.85 m", "weight is less than or equal to 140 jin", "age is greater than or equal to 20 years and less than or equal to 25 years", and "the academic calendar is not limited". Based on the above, it can be determined that the local user of the player in the puppet selection standard is drawn as a first label set, and an example form of the first label set can be as follows: { constellation (Aries or Gemini) }, { height (1.75m, 1.85m ] }, { weight (0, 140 jin ] }, { age [20 years, 25 years ] }, { academic (unlimited) }, where constellation, height, weight, age, academic are the types of the dual selection criteria, i.e., the first label, "Aries or Gemini" is the value field of the "constellation" label, indicating that the partial user representation of the player in the dual selection criteria includes constellations, and the requirement for constellations is Aries or Gemini.

The second game scenario node may specifically be the following scenario, for example. Scenario occurrence site: gift shop of game mall, scenario task: choosing a birthday present for simulating a love object, machine outputting a sentence (gift shop boss): "welcome, you can tell me what you need. "the player inputs voice data: "I want a white shirt, a jeans, all need L sign indicating number". Similarly to the previous embodiment, after the knowledge nodes in the user statement are recombined into correct knowledge triples, the screened primary triples may be { adjectives (shirt, white) }, { adjectives (shirt, L code) }, { adjectives (jeans, L code) }, if these triples match with the template triples in the knowledge base, it is determined that the statements corresponding to these triples are understandable, and it is determined that the core semantic set of the user statement is "white shirt in L code" or "jeans in L code". Based on this, it may be determined that the local user representation of the player at the present gifting preference is a second set of tags, in this example, the second tag is "apparel," and the corresponding value field is "white shirt, jeans," indicating that the local user representation of the player at the gifting preference includes: the gift type that likes to be given is clothing, and the specific gift preferences for this gift type of clothing are white shirts and jeans.

Optionally, the gift type corresponding to the "clothes" can be found as a practical gift by checking a preset mapping relation set, so that the gift selected by the player under the current game scenario node is determined as a practical gift. In the simulated love game, the player has a gift sending preference value, the gift sending preference value comprises a practical gift preference value and an atmosphere gift preference value, and when the system detects that the gift sent by the player is a practical gift, the practical gift preference value of the player can be increased by 1-point progress. When detecting that the gift sent by the player is the atmosphere gift, the atmosphere gift preference value of the player can be increased by 1-point progress, meanwhile, the background can record the specific commodity given by the player, when the practical gift preference value of the player is larger than the atmosphere gift preference value, the gift sending preference of the player at the moment can be recorded as the practical gift, and on the contrary, the atmosphere gift can be recorded. Practical gift can be the commodity that has practical value such as dress, food, atmosphere type gift can be the commodity that has the atmosphere sense such as flower, fragrance candle, dry flower goods of furniture for display rather than for use. Thus, in this example, the particular aspect of the partial user representation of the player in terms of gifting preferences may further include: practical gifts-clothes-white shirts/jeans.

The third game scenario node may specifically be the following scenario, for example. Machine output statement (simulating love object): "lovely, what gift you like, flower, or clothing. "the player inputs voice data: "I would like to receive flowers, but in many flower varieties I prefer pink tulip". Like the previous embodiment, after the knowledge nodes in the user sentence are recombined into the correct knowledge triples, the core semantic sets of the sentence are located as "like flowers" and "like pink tulip" according to the main triples in the user sentence. Based on this, it may be determined that the local user representation of the player in the gifting preference is the third set of tags, in this example, the third tag is "fresh flowers", and the corresponding value field is "pink tulip", indicating that the local user representation of the player in the gifting preference includes: the type of gift received is liked to be a flower, and the specific gift preference for this type of gift is pink tulip.

Alternatively, the gift type corresponding to the "flower" can be found as the atmosphere gift by checking a preset mapping relation set, so as to determine that the gift desired by the player under the current game scenario node is the atmosphere gift. As in the previous embodiment, the specific aspect of the partial user representation of the player in terms of the gifting preference may further include: atmosphere gift-fresh flower-pink tulip.

In addition to the exemplary form of the partial representation feature provided in the embodiments of the present application, there is a partial user representation for characterizing other aspects of the player, which may be specifically determined by other game scenario nodes in combination with the voice data input by the player at the corresponding game scenario node, for example, a partial user representation for characterizing the preferences of a player's appointment may also be determined by the game scenario in which the player appoints with a simulated love object. It will be appreciated that the more partial user representations of the player that are captured by the system, the more accurate the resulting target user representation will be.

In this example, the server accurately locates the local user figures of the player in different dimensions according to the specific game scenario corresponding to the currently processed game scenario node and the user statements input by the player, so that the accuracy of the target user figures is improved.

In one possible example, the voice features include a volume feature and a speech rate feature of the player, the volume feature is used for indicating an average volume of all voice data input by the player, the speech rate feature is used for indicating an average speech rate of all voice data input by the player, the global user representation includes a personality characteristic of the player, and the determining the global user representation of the player in a love scene according to the voice features includes: if the average volume is larger than a first preset decibel value, determining the character characteristic that the player is of the Kairan type; if the average volume is less than a second preset decibel value, determining the character of the player as \33148orhuba type, wherein the second preset decibel value is less than or equal to the first preset decibel value; if the average speech rate is greater than a first preset speech rate, determining that the player is a personality characteristic of impatience type; if the average speed of speech is less than a second preset speed of speech, determining that the player is a deep and steady character, wherein the second preset speed of speech is less than or equal to the first preset speed of speech; combining the plurality of character characteristics of the player results in a global user representation indicative of the player's character.

The first preset decibel value, the second preset decibel value, the first preset speech rate, and the second preset speech rate may be empirical values obtained by analyzing historical data. According to data statistics in the game and relevant psychological theories, the character characteristics of the player in the love scene can be related to the voice characteristics of the player when the player inputs voice. For example, in a normal situation, the volume of a speaking player is in a normal or large state, and the language expression is smooth, so that the character of the player can be positioned to be a Kairan type or an outward type; if the volume of the player is smaller, and the situations of unsmooth language expression, voice ending and the like exist, the character characteristics of the player can be positioned as \33148, an huba type or an inward type; if the input speed of the player is faster, the character characteristic of the player can be positioned to be impatient; if the input speech rate of the player is normal or slow, the character of the player can be positioned to be a steady character. In this example, the server may determine the common volume and the common speech rate of the player in the love scene by analyzing the average volume and the average speech rate of all the voice data input by the player, determine whether the speaking volume of the player in the love scene is large or small according to the magnitude relationship between the average volume and the first preset decibel value and the second preset decibel value, determine whether the personality of the player is a first personality or a ' 33148, a ' second personality ', and determine whether the speaking speech rate of the player in the love scene is fast or slow according to the magnitude relationship between the average speech rate and the first preset speech rate and the second preset speech rate, thereby determining whether the personality of the player is a impatient personality or a deep personality.

In other possible examples, the server collects all X pieces of voice data input by the player, where the volume of Y pieces of voice data is greater than a first preset decibel value, and if Y is greater than the first preset value, it may be determined that the common volume of the player is greater than the first preset decibel value, where the first preset value may be determined according to an empirical value, for example, 0.8X, that is, when Y is greater than 0.8X, that is, when the volume of 0.8X pieces of voice data in the X pieces of voice data is greater than the first preset decibel value, it may be determined that the common volume of the player is greater than the first preset decibel value, and then it is determined that the personality characteristic of the player is a karaoke type or an outward type. Similarly, the server collects X pieces of voice data input by the player, wherein the voice speed of Z pieces of voice data is greater than a first preset voice speed, at this time, if Z is greater than a second preset value, it can be determined that the common voice speed of the player is greater than the first preset voice speed, the second preset value is also determined according to an empirical value, for example, 0.9X, that is, when Z is greater than 0.9X, that is, when the voice speed of 0.9X pieces of voice data in Z pieces of voice data is greater than the first preset voice speed, it can be determined that the common voice speed of the player is greater than the first preset voice speed, and then it is determined that the player is a temperament character.

It will be appreciated that the above process of determining a global user representation of a player's personality traits based on speech characteristics is merely illustrative in exemplary form, and that more representation localization may be subsequently performed based on other speech characteristics. In addition, a player may have multiple personality traits, i.e., the global user representation used to characterize a player's personality traits may also be multiple, e.g., a player may have both Kernel and Settlement personality traits.

Therefore, in this example, the server obtains the common volume and the common speech rate of the player in the love scene by analyzing the voice data input by the player, and accurately locates the global user portrait of the player in the aspect of character and character features, thereby improving the accuracy of the target user portrait.

In one possible example, the determining a service that fits the player's needs in an associated service scenario based on the target user representation of the player in a love scenario includes: acquiring a selective puppet standard weight coefficient, wherein the selective puppet standard weight coefficient is a weight coefficient of a selective puppet standard matching degree variable in a comprehensive matching degree calculation formula, the comprehensive matching degree calculation formula is used for calculating the comprehensive matching degree between the player and the candidate player, the candidate player is any one player in a player set to be matched, the numerical value of the selective puppet standard matching degree variable is used for representing the fit degree between basic information of the candidate player and the selective puppet standard of the player, and the basic information comprises at least one of the following: the system comprises a constellation, height, weight, age and a study history, wherein variables of a calculation formula comprise a puppet selection standard matching degree variable, a character feature matching degree variable and a love habit matching degree variable, numerical values of the character feature matching degree variable are used for representing the degree of fit between character features of the candidate player and portrait preference of the player for character feature dimensions, numerical values of the love habit matching degree variable are used for representing the matching degree of the candidate player and the player in love habits, and the love habits at least comprise a gift sending preference and a gift receiving preference; obtaining a character characteristic weight coefficient, wherein the character characteristic weight coefficient is the weight coefficient of the character characteristic matching degree variable; acquiring a love habit weight coefficient, wherein the love habit weight coefficient is a weight coefficient of the love habit matching degree variable; determining the comprehensive matching degree between the player and the candidate player according to the puppet selection standard weight coefficient, the puppet selection standard matching degree variable, the character characteristic weight coefficient, the character characteristic matching degree variable, the love habit weight coefficient and the love habit matching degree variable; if the comprehensive matching degree is larger than a preset value, determining the social account number of the candidate player as a social account number to be recommended; and repeating the steps until all the players in the player set to be matched are matched, so as to obtain a social account set to be recommended, wherein the arrangement sequence of the social accounts in the social account set to be recommended is arranged from top to bottom according to the magnitude of the comprehensive matching degree. And generating the service recommendation message according to the social account set to be recommended.

The dual-preference standard weight coefficient, the personality characteristic weight coefficient and the love habit weight coefficient can be set by a player in a self-defined mode according to experience values obtained by analyzing historical data through the server, and are used for representing the importance degree of each matching degree during matching, for example, the player sets the weight coefficients in the self-defined mode, wherein the dual-preference standard weight coefficient is 0.5, the personality characteristic weight coefficient is 0.3, and the love habit weight coefficient is 0.2, so that the ranking of the importance degree of each matching degree considered by the player is that the dual-preference standard matching degree is larger than the personality characteristic matching degree and larger than the love habit matching degree. An example modality of the integrated matching degree calculation formula may be: y = AX1+ BX2+ CX3, wherein Y represents the overall degree of matching; x1 represents a couple-selective standard matching degree variable, and A represents a couple-selective standard weight coefficient; x2 represents a character characteristic matching degree variable, and B represents a character characteristic weight coefficient; x3 represents a love habit matching degree variable, and C represents a love habit weight coefficient.

Illustratively, note that the maximum value of the specific numerical values of the variables is 100, a =0.5, b =0.3, c =0.2, and then Y =0.5x1+0.3x2+0.2x3. The specific numerical value of the alternative standard matching degree variable X1 can be determined in the following way: judging whether the basic information of the candidate player meets various types in the player puppet selection standard or not, if so, adding points, wherein the value of the added points corresponds to the preset value of the type, and finally accumulating all the values of the added points to obtain the specific value of X1. For example, the puppet selection standard types of the players include constellation, height, weight, age, and school calendar, and five items are added by 20 points when one item is satisfied. The specific bonus amplitude can be set by a player in a self-defined manner, and if the player thinks that the height is an important index in the own puppet selection standard, the score corresponding to the height index can be set to be 50, but the sum of the scores corresponding to the indexes needs to be ensured to be 100, namely the maximum value of X1 is 100.

For example, the local user portrayal of Player A in the duality selection criterion is: the basic information of the candidate player B comprises a constellation, a height of 1.78m, a weight of 150 catties, an age of 22 years and a study of the subject, wherein the candidate player B can be known to accord with the couple selection standard of the player A in terms of constellation, height, weight, age and study, and the adding rule set by the player A in terms of the couple selection standard is constellation, height, weight, age and study, and the couple selection standard matching degree variable X1=80 when the sum of the five indexes of constellation, height, weight, age and study is increased by 20 points every time one index is met.

The specific numerical value of the character feature matching degree variable X2 may be determined in the following example: obtaining portrait preference for personality trait dimension input by a player in advance, wherein the portrait trait is Karan or 33148, the weight ratio set for the huckle type is 0.4, and the weight ratio set for the impatience type or sincere type is 0.6; wherein, players score 100 scores for Kairang type, 33148red huo type, 70 scores for impatient type, 40 scores for impatient type and 80 scores for deep and steady type. If the character of candidate player B is characterized as Kelang and Daizhi, then X2=100 × 0.4+80 × 0.6=88.

The specific numerical value of the love habit matching degree variable X3 can be determined as follows: if the gift receiving preference of the candidate player matches the gift sending preference of the player, marking the candidate player as meeting the first love habit; if the present preference of the candidate player matches the present preference of the player, the candidate player is marked as meeting the second love habit. The matching of the candidate player's gifting preference with the player's gifting preference means that the gift type corresponding to the candidate player's gifting preference is the same as the gift type corresponding to the player's gifting preference, and similarly, the matching of the candidate player's gifting preference with the player's gifting preference means that the gift type corresponding to the candidate player's gifting preference is the same as the gift type corresponding to the player's gifting preference. For example, player a's gifting preference is an atmosphere-type gift, particularly prefers to receive flower-type merchandise, and has a more specific gifting preference for flower-type merchandise: "love roses of different colors"; the gift sending preference of the candidate player B is an atmosphere gift, and the background of the system records that most of the atmosphere gift sent in the gift sending record of the candidate player B is fresh flowers, so that the candidate player B can be determined to meet the second love habit. Because the importance of the first love habit and the second love habit is not necessarily the same for the player, the player can self-define two situations with different bonus points, but the final score is 100 when the love habits are required to be satisfied, that is, the maximum value of X3 is 100. For example, if the candidate player satisfies the first love habit, the bonus point value is set to 40, if the candidate player satisfies the second love habit, the bonus point value is set to 60, and if the candidate player satisfies all the love habits, the bonus point value is set to 100. In this example, let the candidate player satisfy all love habits, X3=100.

The numerical values of a, B, C, X1, X2, and X3 are all substituted into the comprehensive matching degree calculation formula Y = AX1+ BX2+ CX3, and Y =0.5 × 80+0.3 × 88+0.2 × 100=86.4 is obtained, that is, the comprehensive matching degree between the player a and the candidate player B is 86.4. And at the moment, judging the size relationship between the comprehensive matching degree and a preset value, and if the comprehensive matching degree is greater than the preset value, determining the social account number of the candidate player B as the social account number to be recommended. The preset value may be an empirical value obtained by analyzing historical data by the server. Exemplarily, if the preset value is 70, determining that the social account of the candidate player B is the account to be recommended, repeating the steps in the above embodiment to match all players in the player set to be matched, and finally screening out the social account set to be recommended, wherein the comprehensive matching degrees of the candidate players corresponding to the social accounts in the social account set to be recommended are all greater than 70 and are arranged from top to bottom according to the size of the comprehensive matching degrees, so that the player can more intuitively see the candidate player with the highest matching degree with the player.

It should be noted that, the player and the candidate player in the set of players to be matched both perform interactive confirmation with the server, allowing the server to collect and analyze personal data and push services. If the player does not allow the server to collect the personal data, the player will not be selected as the recommended player, and the player's social account will not be recommended.

Exemplarily, as shown in fig. 5, the service recommendation message is presented on a display screen 51 of the terminal device 50 of the player a, wherein a set of social accounts 52 to be recommended is presented in a form of a list, and the candidate player whose comprehensive matching degree is greater than a preset value, the social account thereof, and the numerical value of the comprehensive matching degree are all displayed; below the set of social account numbers 52 to be recommended there is a prompt message 53: the system screens out candidate players conforming to the images of the players for the players, and if the players want to add friends, the corresponding players are clicked to send friend application bars for prompting the player A to send friend application modes; a clickable control 54 is further arranged below the prompt message 53, when the player a clicks the control, the preset value of the comprehensive matching degree can be adjusted in a customized manner, and the server will re-determine the set of social accounts meeting the conditions according to the adjusted preset value of the comprehensive matching degree, generate a service recommendation message and send the service recommendation message to the terminal device 50.

Optionally, if the player a sends a friend application to the player B according to the service recommendation message, and the player B unifies the friend application, the server automatically sends the target user portrait of the player a to the player B, especially for the specific gift preference of the player for the merchandise of flower type: "enjoy different colored roses" is highlighted so that player B can quickly learn player A's particular preferences for fresh flower merchandise.

It should be understood that the specific values of the above parameters are only exemplary and do not limit the present application. And the meanings represented by a, B, C, X1, X2, and X3 may be interchanged, and it can be understood by those skilled in the art that there may be some matching degree variables other than the several matching degree variables disclosed in the embodiments of the present application, and the present invention is not limited to these.

Therefore, in the example, when the server determines the social account recommending service according to the target user portrait, the server calculates the comprehensive matching degree between the players, recommends other players with the comprehensive matching degree higher than the preset value to the players, intelligently screens out other players who do not meet the requirements of the players, enhances the accuracy of service recommendation, and improves user experience.

In one possible example, the target user representation includes basic information of the player, the basic information includes height, weight, face shape, hair style, clothing collocation habits, common phrases and common moods of the player, and the determining the service in the associated service scene which is adapted to the requirements of the player according to the target user representation of the player in the love scene includes: generating a virtual character matched with the player image and a plurality of expression packets for representing emotional states corresponding to the virtual character according to the height, the weight, the face shape, the hair style and the clothing matching habit of the player; generating a plurality of text messages which are adapted to the player and used for representing emotional states according to the common phrases and the common tone of the player and the character characteristics of the player; correspondingly adding the text information used for representing the emotional state into a plurality of expression packets used for representing the emotional state corresponding to the virtual character according to the content of the text information to obtain an expression packet set of the virtual character; and generating the service recommendation message according to the virtual character expression package set.

The server presets a plurality of emotion states such as vitality, cozy, joy, hurt and the like for the virtual character image, and after the virtual character image is generated, the server adds the emotion states into the virtual character image to generate a plurality of expression packets for representing the emotion states corresponding to the virtual character image; then, text information of the emotional state expressed by the player is generated according to the commonly used phrases, commonly used tone and character features of the player, for example, the commonly used phrases of the player include "dizziness", the commonly used tone is humorous type, and the character features are of a kindly type, the text content of the text information of the emotional state expressed by the player is "dizziness", the text information is added to an expression package corresponding to the virtual character and representing the emotional state of "anger", and the virtual character expression package expressing the emotion of "anger" can be obtained, for example, as shown in fig. 6, fig. 6 is the virtual character expression package with the emotional state of anger provided by the embodiment of the application. Combining the virtual character expression packages expressing various emotions together to obtain a virtual character expression package set, and generating a service recommendation message, thereby realizing recommendation of the virtual character expression package set to the player.

Therefore, in the example, when the server determines the expression package recommendation service according to the target user portrait, the server generates the virtual character image and the corresponding expression package expressing the emotion state according to the appearance characteristics of the player, and then inputs text information frequently used by the player to express the emotion, so that the virtual character expression package expressing the emotion state is finally obtained, the interest and the accuracy of service recommendation are enhanced, and the user experience is improved.

In one possible example, the target user representation includes a constellation of the player, and the determining a service that fits the player's needs in an associated service scenario from the target user representation of the player in a love scenario includes: selecting an expression packet with a cartoon image corresponding to the player constellation from an expression packet commodity set according to the player constellation to obtain a target constellation expression packet set; analyzing the similarity between each expression package commodity in the target constellation expression package set and the character characteristics of the player; screening the expression package commodities with the similarity larger than the preset similarity to obtain an expression package set to be recommended, wherein the arrangement sequence of the expression package commodities in the expression package set to be recommended is arranged from top to bottom according to the similarity; and generating the service recommendation message according to the expression package set to be recommended.

Illustratively, if the constellation of the player is a goat seat, the server may first screen out a cartoon image expression package corresponding to the goat seat from the expression package commodity set to obtain a goat seat expression package set. And analyzing the similarity between each expression package in the Aries expression package set and the character of the player according to the character characteristics of the player, comparing the similarity with the preset similarity, and screening out expression package commodities with the similarity larger than the preset similarity to obtain an expression package set to be recommended. Illustratively, as shown in fig. 7, fig. 7 is a schematic diagram of an expression package recommendation message provided in an embodiment of the present application, where the expression package recommendation message includes an expression package set to be recommended, the expression package set to be recommended includes an expression package (1) and an expression package (2), the expression package (1) is an expression package with a smile in a lamb, and the expression package (2) is an expression package with a smile in a lamb, and through analysis, a similarity between the expression package (1) and a character of a player is 85%, and a similarity between the expression package (2) and a character of a player is 80%, where specific numerical values of the similarities are all displayed in a terminal device, and there is an "add" control near the expression package, and a player may add a corresponding expression package by clicking a screen area corresponding to the control.

Therefore, in the example, when the server determines the expression package recommendation service according to the target user portrait, the server firstly performs screening according to the constellation of the player to obtain the constellation expression package set associated with the constellation of the player, and then analyzes the expression packages in the constellation expression package set based on the similarity with the personality characteristics of the player to finally obtain the expression package set matched with the personality characteristics of the player, so that the interest and the accuracy of service recommendation are enhanced, and the user experience is improved.

In other possible examples, when a player has a need to pick a gift for a love object in a real scene, the server may send a gift recommendation message to the player's terminal device according to the player's target user representation, in particular, according to the player's gifting preferences. If the player inputs the gift-receiving preference of the real love object in advance, the server sends a gift recommendation message according to the gift-receiving preference preferentially, and the requirements of the user can be met better.

In other possible examples, the server may determine whether the player is tired of the current game by comparing the tone characteristics of the player when playing the current game with the tone characteristics of the player when playing the previous game; and if so, sending a game recommendation message to the terminal equipment, wherein the game recommendation message is used for indicating other games of the same type as the love simulation game. For example, the game currently played by the player is a campus love simulation game, and if the player loses interest in the campus love, other types of love simulation games, such as a place love class, can be recommended to the player. Therefore, the emotion of the user on the love game product can be analyzed, the related products can be intelligently recommended for the user, and the product recommendation accuracy is improved.

In accordance with the above-described embodiment, please refer to fig. 8a, fig. 8a is a block diagram of functional units of a service processing apparatus for voice game data based on a player according to an embodiment of the present application, which is applied in the server 11 shown in fig. 1, where the service processing apparatus 80 for voice game data based on a player includes: an obtaining unit 801, configured to invoke the human-machine interaction engine to perform voice interaction with the player through the terminal device, and obtain voice data input by the player in the love simulation game; a first determining unit 802, configured to determine a target user representation of the player in a love scene according to voice data input by the player in the love simulation game; a second determining unit 803, configured to determine, according to a target user portrait of the player in a love scene, a service that meets the requirement of the player in an associated service scene, where the associated service scene is a social account recommendation service scene or an expression package recommendation service scene associated with the love scene; a sending unit 804, configured to send a service recommendation message to the terminal device, where the service recommendation message is used to indicate the service.

In one possible example, the voice data input by the player in the love simulation game includes a plurality of sets of user sentences input by the player in a plurality of game scenario nodes of the love simulation game, a single set of user sentences includes at least one user sentence input by the player in a corresponding game scenario node, and in the aspect of determining the target user portrait of the player in the love scene according to the voice data input by the player in the love simulation game, the first determining unit 802 is specifically configured to: performing core semantic extraction operation on each user statement in each user statement set in the plurality of user statement sets to obtain a plurality of core semantic sets corresponding to the plurality of user statement sets; obtaining at least one partial user representation of the player in a love scene for the plurality of game scenario nodes by: judging whether the currently processed game scenario nodes are game scenario nodes in a preset associated scenario node set or not, wherein the associated scenario node set comprises pre-marked game scenario nodes which are strongly associated with the selection tendencies of the players in the loving scenes; if yes, determining a local user portrait of the player in a love scene according to the core semantic set of the currently processed game scenario node; if not, jumping to the next game scenario node to be processed until the plurality of game scenario nodes are processed; and executing the following operations aiming at the plurality of game scenario nodes to obtain a global user representation of the player in the loving scene: analyzing voice data input by the player in the love simulation game to obtain voice characteristics of the player in a speaking process; determining a global user representation of the player in a love scene according to the voice characteristics; determining a target user representation of the player in a love scene based on the local user representation and the global user representation.

In one possible example, in the aspect of determining the local user representation of the player in the love scene according to the core semantic set of the currently processed game scenario node, the first determining unit 802 is specifically configured to: if the currently processed game scenario node is judged to be the game scenario node when the player selects the loving object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is an image selection standard, wherein the type of the image selection standard at least comprises one of the following types: constellation, height, weight, age, academic calendar; determining a local user image of the player in the aspect of the puppet selection standard as a first label set according to the core semantic set of the currently processed game scenario node, wherein the first label set comprises at least one first label with a value range, and the first label is used for indicating the type of the puppet selection standard; if the currently processed game scenario node is judged to be the game scenario node when the player selects a gift for the simulated love object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift sending preference, wherein the type of the gift sending preference at least comprises one of the following types: flowers, clothing, food; determining a local user image of the player in the aspect of the gift sending preference as a second label set according to the core semantic set of the currently processed game scenario node, wherein the second label set comprises at least one second label with a value range, and the second label is used for indicating the type of the gift sending preference; if the currently processed game scenario node is judged to be the game scenario node when the simulated love object inquires the gift type liked by the player, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift collection preference, wherein the type of the gift collection preference at least comprises one of the following types: flowers, clothing, foods; and determining a local user image of the player in the aspect of the gift collection preference as a third label set according to the core semantic set of the currently processed game scenario node, wherein the third label set comprises at least one third label with a value range, and the third label is used for indicating the type of the gift collection preference.

In one possible example, the voice features include a volume feature and a speech rate feature of the player, the volume feature is used for indicating an average volume of all voice data input by the player, the speech rate feature is used for indicating an average speech rate of all voice data input by the player, the global user representation includes a personality characteristic of the player, and in the aspect of determining the global user representation of the player in a love scene according to the voice features, the first determining unit 802 is specifically configured to: if the average volume is larger than a first preset decibel value, determining the character characteristic that the player is of the Kairan type; if the average volume is smaller than a second preset decibel value, determining the character of the huck type of the players is '33148', wherein the second preset decibel value is smaller than or equal to the first preset decibel value; if the average speech rate is greater than a first preset speech rate, determining that the player is a personality characteristic of impatience type; if the average speed of speech is less than a second preset speed of speech, determining the character of the player in a steady type, wherein the second preset speed of speech is less than or equal to the first preset speed of speech; combining the plurality of personality characteristics of the player results in a global user representation indicative of the player's personality.

In a possible example, in the aspect of determining a service that is adapted to the requirements of the player in an associated service scenario according to the target user representation of the player in a love scenario, the second determining unit 803 is specifically configured to: acquiring a puppet selection standard weight coefficient, wherein the puppet selection standard weight coefficient is a weight coefficient of a puppet selection standard matching degree variable in a comprehensive matching degree calculation formula, the comprehensive matching degree calculation formula is used for calculating the comprehensive matching degree between the player and the candidate player, the candidate player is any one player in a player set to be matched, the numerical value of the puppet selection standard matching degree variable is used for representing the degree of fit between basic information of the candidate player and the puppet selection standard of the player, and the basic information comprises at least one of the following: the system comprises a constellation, height, weight, age and a study history, wherein variables of a calculation formula comprise a puppet selection standard matching degree variable, a character feature matching degree variable and a love habit matching degree variable, numerical values of the character feature matching degree variable are used for representing the degree of fit between character features of the candidate player and portrait preference of the player for character feature dimensions, numerical values of the love habit matching degree variable are used for representing the matching degree of the candidate player and the player in love habits, and the love habits at least comprise a gift sending preference and a gift receiving preference; acquiring a character characteristic weight coefficient, wherein the character characteristic weight coefficient is a weight coefficient of the character characteristic matching degree variable; acquiring a love habit weight coefficient, wherein the love habit weight coefficient is a weight coefficient of the love habit matching degree variable; determining the comprehensive matching degree between the player and the candidate player according to the puppet selection standard weight coefficient, the puppet selection standard matching degree variable, the character characteristic weight coefficient, the character characteristic matching degree variable, the love habit weight coefficient and the love habit matching degree variable; if the comprehensive matching degree is larger than a preset value, determining the social account number of the candidate player as a social account number to be recommended; and repeating the steps until all the players in the player set to be matched are matched, so as to obtain a social account set to be recommended, wherein the arrangement sequence of the social accounts in the social account set to be recommended is arranged from top to bottom according to the comprehensive matching degree. And generating the service recommendation message according to the social account set to be recommended.

In one possible example, the target user representation includes basic information of the player, the basic information includes height, weight, face shape, hair style, clothing match habit, common phrase and common tone of the player, and in the aspect of determining the service that is adapted to the player's requirement in the associated service scenario according to the target user representation of the player in the love scenario, the second determining unit 803 is specifically configured to: generating a virtual character matched with the player image and a plurality of expression packages for representing emotional states corresponding to the virtual character according to the height, the weight, the face shape, the hair style and the clothing matching habit of the player; generating a plurality of text messages which are adapted to the player and used for representing emotional states according to the common phrases and the common tone of the player and the character characteristics of the player; correspondingly adding the text information used for representing the emotional state into a plurality of expression packets used for representing the emotional state corresponding to the virtual character according to the content of the text information to obtain a virtual character expression packet set; and generating the service recommendation message according to the virtual character expression package set.

In one possible example, the target user representation includes a constellation of the player, and in the aspect of determining the service that is adapted to the requirements of the player in the associated service scenario according to the target user representation of the player in the love scenario, the second determining unit 803 is specifically configured to: selecting an expression packet with a cartoon image corresponding to the player constellation from an expression packet commodity set according to the player constellation to obtain a target constellation expression packet set; analyzing the similarity between each expression package commodity in the target constellation expression package set and the character feature of the player; screening the expression package commodities with the similarity larger than the preset similarity to obtain an expression package set to be recommended, wherein the arrangement sequence of the expression package commodities in the expression package set to be recommended is arranged from top to bottom according to the similarity; and generating the service recommendation message according to the expression package set to be recommended.

It can be understood that, since the method embodiment and the apparatus embodiment are different presentation forms of the same technical concept, the content of the method embodiment portion in the present application should be synchronously adapted to the apparatus embodiment portion, and is not described herein again.

In the case of using an integrated unit, as shown in fig. 8b, fig. 8b is a block diagram of functional units of another service processing device based on voice game data of a player according to an embodiment of the present application. In fig. 8b, the service processing device 81 based on the voice game data of the player includes: a processing module 812 and a communication module 811. The processing module 812 is used to control and manage actions of the service processing device based on the voice game data of the player, for example, to perform the steps of the acquisition unit 801, the first determination unit 802, the second determination unit 803, and the transmission unit 804, and/or to perform other processes of the techniques described herein. The communication module 811 is used to support interaction between the service processing apparatus and other devices based on the voice game data of the player. As shown in fig. 8b, the service processing device based on the voice game data of the player may further include a storage module 813, and the storage module 813 is used for storing program codes and data of the service processing device based on the voice game data of the player.

The Processing module 812 may be a Processor or a controller, and may be, for example, a Central Processing Unit (CPU), a general-purpose Processor, a Digital Signal Processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs, and microprocessors, among others. The communication module 811 can be a transceiver, an RF circuit or a communication interface, etc. The storage module 813 may be a memory.

All relevant contents of each scene related to the method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again. The service processing device 81 based on the voice game data of the player may execute the service processing method based on the voice game data of the player shown in fig. 2.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. The procedures or functions according to the embodiments of the present application are wholly or partially generated when the computer instructions or the computer program are loaded or executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, data center, etc., that contains one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.

Fig. 9 is a block diagram of a server according to an embodiment of the present disclosure. As shown in fig. 9, the server 900 may include one or more of the following components: a processor 901, a memory 902 coupled to the processor 901, wherein the memory 902 may store one or more computer programs that may be configured to implement the methods described in the embodiments above when executed by the one or more processors 901. The server 900 may be the server 11 in the above embodiment.

Processor 901 may include one or more processing cores. The processor 901 connects various parts within the overall server 900 using various interfaces and lines, performs various functions of the server 900 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 902, and calling data stored in the memory 902. Alternatively, the processor 901 may be implemented in at least one hardware form of Digital Signal Processing (DSP), field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 901 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 901, but may be implemented by a communication chip.

The Memory 902 may include a Random Access Memory (RAM) or a Read-Only Memory (ROM). The memory 902 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like. The storage data area may also store data created by the server 900 in use, and the like.

It is understood that the server 900 may include more or less structural elements than those shown in the above structural block diagrams, and is not limited thereto.

Embodiments of the present application also provide a computer storage medium, in which a computer program/instructions are stored, and when executed by a processor, implement part or all of the steps of any one of the methods as described in the above method embodiments.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any one of the methods as set out in the above method embodiments.

It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus and system may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative; for example, the division of the unit is only a logic function division, and there may be another division manner in actual implementation; for example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: u disk, removable hard disk, magnetic disk, optical disk, volatile memory or non-volatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, many forms of Random Access Memory (RAM) are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct bus RAM (DR RAM) among various media capable of storing program code.

Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications can be easily made by those skilled in the art without departing from the spirit and scope of the present invention, and it is within the scope of the present invention to include different functions, combination of implementation steps, software and hardware implementations.

Claims

1. A service processing method based on voice game data of a player is applied to a server of a service recommendation system, the service recommendation system comprises the server and terminal equipment for logging in a game account of the player, the server comprises a man-machine interaction engine supporting man-machine voice interaction in a voice virtual world, the voice virtual world comprises a love simulation game of a voice interaction type, and a game associated with the game account comprises the love simulation game, and the method comprises the following steps:

calling the human-computer interaction engine to perform voice interaction with the player through the terminal equipment, and acquiring voice data input by the player in the love simulation game, wherein the voice data comprise a plurality of user statement sets input by the player in a plurality of game scenario nodes of the love simulation game, and a single user statement set comprises at least one user statement input by the player in a corresponding game scenario node;

performing core semantic extraction operation on each user statement in each user statement set in the plurality of user statement sets to obtain a plurality of core semantic sets corresponding to the plurality of user statement sets;

obtaining at least one partial user representation of the player in a love scene for the plurality of game scenario nodes by:

judging whether the currently processed game scenario node is a game scenario node in a preset associated scenario node set, wherein the associated scenario node set comprises pre-marked game scenario nodes which are strongly associated with the selection tendencies of the players in the love scenes;

if yes, determining a local user portrait of the player in the love scene according to the core semantic set of the currently processed game scenario node;

if not, jumping to the next game scenario node to be processed until the processing of the plurality of game scenario nodes is completed;

and performing the following operations for the plurality of game scenario nodes to obtain a global user representation of the player in a love scene:

analyzing voice data input by the player in the love simulation game to obtain voice characteristics of the player in a speaking process;

determining a global user representation of the player in a love scene according to the voice characteristics;

determining a target user representation of the player in a love scene from the local user representation and the global user representation;

2. The method of claim 1, wherein determining the local user representation of the player in a love scene from the core semantic set of the currently processed game scenario node comprises:

if the currently processed game scenario node is judged to be the game scenario node when the player selects the love object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is an idol selection standard, wherein the type of the idol selection standard at least comprises one of the following types: constellation, height, weight, age, school calendar; determining a local user image of the player in the aspect of the puppet selection standard as a first label set according to the core semantic set of the currently processed game scenario node, wherein the first label set comprises at least one first label with a value range, and the first label is used for indicating the type of the puppet selection standard;

if the currently processed game scenario node is judged to be the game scenario node when the player selects a gift for the simulated love object, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift sending preference, wherein the type of the gift sending preference at least comprises one of the following types: flowers, clothing, food; determining a local user image of the player in the aspect of the gift sending preference as a second label set according to the core semantic set of the currently processed game scenario node, wherein the second label set comprises at least one second label with a value range, and the second label is used for indicating the type of the gift sending preference;

if the currently processed game scenario node is judged to be the game scenario node when the simulated love object inquires the gift type liked by the player, determining that the type of the local user portrait corresponding to the currently processed game scenario node is a gift collection preference, wherein the type of the gift collection preference at least comprises one of the following types: flowers, clothing, food; and determining a local user image of the player in the aspect of the gift-receiving preference as a third label set according to the core semantic set of the currently processed game scenario node, wherein the third label set comprises at least one third label with a value range, and the third label is used for indicating the type of the gift-receiving preference.

3. The method of claim 1, wherein the voice features comprise a volume feature and a speech rate feature of the player, the volume feature is used for indicating an average volume of all voice data input by the player, the speech rate feature is used for indicating an average speech rate of all voice data input by the player, the global user representation comprises personality characteristics of the player, and the determining of the global user representation of the player in a love scene according to the voice features comprises:

if the average volume is larger than a first preset decibel value, determining the character characteristic that the player is of the Kairan type;

if the average volume is less than a second preset decibel value, determining the character of the player as \33148orhuba type, wherein the second preset decibel value is less than or equal to the first preset decibel value;

if the average speech rate is larger than a first preset speech rate, determining the personality characteristics of the impatient type of the player;

if the average speed of speech is less than a second preset speed of speech, determining that the player is a deep and steady character, wherein the second preset speed of speech is less than or equal to the first preset speed of speech;

combining the plurality of personality characteristics of the player results in a global user representation indicative of the player's personality.

4. The method of claim 2 or 3, wherein the determining the service that is adapted to the player's needs in the associated service scenario according to the target user representation of the player in the love scenario comprises:

acquiring a puppet selection standard weight coefficient, wherein the puppet selection standard weight coefficient is a weight coefficient of a puppet selection standard matching degree variable in a comprehensive matching degree calculation formula, the comprehensive matching degree calculation formula is used for calculating the comprehensive matching degree between the player and the candidate player, the candidate player is any one player in a player set to be matched, the numerical value of the puppet selection standard matching degree variable is used for representing the degree of fit between basic information of the candidate player and the puppet selection standard of the player, and the basic information comprises at least one of the following: the system comprises a constellation, height, weight, age and a study history, wherein variables of a calculation formula comprise a puppet selection standard matching degree variable, a character feature matching degree variable and a love habit matching degree variable, numerical values of the character feature matching degree variable are used for representing the degree of fit between character features of the candidate player and portrait preference of the player for character feature dimensions, numerical values of the love habit matching degree variable are used for representing the matching degree of the candidate player and the player in love habits, and the love habits at least comprise a gift sending preference and a gift receiving preference;

obtaining a character characteristic weight coefficient, wherein the character characteristic weight coefficient is the weight coefficient of the character characteristic matching degree variable;

acquiring a love habit weight coefficient, wherein the love habit weight coefficient is a weight coefficient of the love habit matching degree variable;

determining a comprehensive matching degree between the player and the candidate player according to the puppet selection standard weight coefficient, the puppet selection standard matching degree variable, the character feature weight coefficient, the character feature matching degree variable, the love habit weight coefficient and the love habit matching degree variable;

if the comprehensive matching degree is larger than a preset value, determining the social account number of the candidate player as a social account number to be recommended;

repeating the steps until all the players in the player set to be matched are matched, so as to obtain a social account set to be recommended, wherein the arrangement sequence of the social accounts in the social account set to be recommended is arranged from top to bottom according to the magnitude of the comprehensive matching degree;

and generating the service recommendation message according to the social account set to be recommended.

5. The method of claim 2 or 3, wherein the target user representation includes basic information of the player, the basic information includes height, weight, face shape, hair style, dress collocation habit, common phrases and common tone of the player, and the determining the service in the associated service scene according to the target user representation of the player in the love scene includes:

generating a virtual character matched with the player image and a plurality of expression packets for representing emotional states corresponding to the virtual character according to the height, the weight, the face shape, the hair style and the clothing matching habit of the player;

generating a plurality of text messages which are adapted to the player and used for representing emotional states according to the common phrases and the common tone of the player and the character characteristics of the player;

correspondingly adding the text information used for representing the emotional state into a plurality of expression packets used for representing the emotional state corresponding to the virtual character according to the content of the text information to obtain an expression packet set of the virtual character;

and generating the service recommendation message according to the virtual character expression package set.

6. The method of claim 2 or 3, wherein the target user representation comprises a constellation of the player, and wherein determining the service that is adapted to the player's needs in the associated service scenario according to the target user representation of the player in the love scenario comprises:

selecting an expression packet with a cartoon image corresponding to the player constellation from an expression packet commodity set according to the player constellation to obtain a target constellation expression packet set;

analyzing the similarity between each expression package commodity in the target constellation expression package set and the character characteristics of the player;

screening the expression package commodities with the similarity larger than the preset similarity to obtain an expression package set to be recommended, wherein the arrangement sequence of the expression package commodities in the expression package set to be recommended is arranged from top to bottom according to the similarity;

and generating the service recommendation message according to the expression package set to be recommended.

7. A service processing apparatus based on voice game data of a player, applied to a server of a service recommendation system, the service recommendation system including the server and a terminal device logging in a game account of the player, the server including a human-machine interaction engine supporting human-machine voice interaction in a voice virtual world, the voice virtual world including a love simulation game of a voice interaction type, the game account-associated game including the love simulation game, the apparatus comprising:

an obtaining unit, configured to invoke the human-machine interaction engine to perform voice interaction with the player through the terminal device, and obtain voice data input by the player in the love simulation game, where the voice data includes a plurality of user statement sets input by the player in a plurality of game scenario nodes of the love simulation game, and a single user statement set includes at least one user statement input by the player in a corresponding game scenario node;

a first determining unit, configured to perform a core semantic extraction operation on each user statement in each user statement set of the multiple user statement sets, to obtain multiple core semantic sets corresponding to the multiple user statement sets;

and performing the following operations for the plurality of game scenario nodes to obtain at least one local user portrait of the player in the loving scene:

judging whether the currently processed game scenario nodes are game scenario nodes in a preset associated scenario node set or not, wherein the associated scenario node set comprises pre-marked game scenario nodes which are strongly associated with the selection tendencies of the players in the loving scenes;

and determining a target user representation of the player in a love scene from the local user representation and the global user representation;

the second determining unit is used for determining a service which is matched with the requirements of the player in an associated service scene according to the target user portrait of the player in the love scene, wherein the associated service scene is a social account recommending service scene or an expression package recommending service scene associated with the love scene;

and the sending unit is used for sending a service recommendation message to the terminal equipment, wherein the service recommendation message is used for indicating the service.

8. A server comprising a processor, memory, and one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method of any of claims 1-6.

9. A computer-readable storage medium, on which a computer program/instructions are stored, which, when being executed by a processor, carry out the steps of the method of any one of claims 1 to 6.